From 60a8f428320918458a9a21052777eada68eebfd8 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 16 Nov 2012 19:39:17 -0800 Subject: x86, mm: Move after_bootmem to mm_internel.h it is only used in arch/x86/mm/init*.c Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1353123563-3103-41-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index bcaab4e6fe91..64d5271a3d36 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1355,7 +1355,6 @@ extern void __init mmap_init(void); extern void show_mem(unsigned int flags); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); -extern int after_bootmem; extern __printf(3, 4) void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...); -- cgit v1.2.3 From bbacc0c111c3c5d1f3192b8cc1642b9c3954f80d Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 10 Dec 2012 10:33:09 -0700 Subject: KVM: Rename KVM_MEMORY_SLOTS -> KVM_USER_MEM_SLOTS It's easy to confuse KVM_MEMORY_SLOTS and KVM_MEM_SLOTS_NUM. One is the user accessible slots and the other is user + private. Make this more obvious. Reviewed-by: Gleb Natapov Signed-off-by: Alex Williamson Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2c497ab0d03d..abad7f30771e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -314,7 +314,7 @@ struct kvm_irq_routing_table {}; #endif #ifndef KVM_MEM_SLOTS_NUM -#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS) +#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) #endif /* -- cgit v1.2.3 From 0743247fbf0c4a27185b2aa1fdda91d0745dfed1 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 10 Dec 2012 10:33:15 -0700 Subject: KVM: Make KVM_PRIVATE_MEM_SLOTS optional Seems like everyone copied x86 and defined 4 private memory slots that never actually get used. Even x86 only uses 3 of the 4. These aren't exposed so there's no need to add padding. Reviewed-by: Gleb Natapov Signed-off-by: Alex Williamson Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index abad7f30771e..5a3581ceb036 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -313,6 +313,10 @@ struct kvm_irq_routing_table {}; #endif +#ifndef KVM_PRIVATE_MEM_SLOTS +#define KVM_PRIVATE_MEM_SLOTS 0 +#endif + #ifndef KVM_MEM_SLOTS_NUM #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) #endif -- cgit v1.2.3 From f82a8cfe9354f5cdea55ebeceba3fd19051d3ee8 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 10 Dec 2012 10:33:21 -0700 Subject: KVM: struct kvm_memory_slot.user_alloc -> bool There's no need for this to be an int, it holds a boolean. Move to the end of the struct for alignment. Reviewed-by: Gleb Natapov Signed-off-by: Alex Williamson Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5a3581ceb036..d897f035749f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -270,8 +270,8 @@ struct kvm_memory_slot { unsigned long *dirty_bitmap; struct kvm_arch_memory_slot arch; unsigned long userspace_addr; - int user_alloc; int id; + bool user_alloc; }; static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) @@ -451,10 +451,10 @@ id_to_memslot(struct kvm_memslots *slots, int id) int kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - int user_alloc); + bool user_alloc); int __kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - int user_alloc); + bool user_alloc); void kvm_arch_free_memslot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont); int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); @@ -462,11 +462,11 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_memory_slot old, struct kvm_userspace_memory_region *mem, - int user_alloc); + bool user_alloc); void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, struct kvm_memory_slot old, - int user_alloc); + bool user_alloc); bool kvm_largepages_enabled(void); void kvm_disable_largepages(void); /* flush all memory translations */ @@ -553,7 +553,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - int user_alloc); + bool user_alloc); int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level); long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); -- cgit v1.2.3 From 6104f472a5ea287fbdcf4644e74867dfd905a018 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 10 Dec 2012 10:33:26 -0700 Subject: KVM: struct kvm_memory_slot.flags -> u32 struct kvm_userspace_memory_region.flags is a u32 with a comment that bits 0 ~ 15 are visible to userspace and the other bits are reserved for kvm internal use. KVM_MEMSLOT_INVALID is the only internal use flag and it has a comment that bits 16 ~ 31 are internally used and the other bits are visible to userspace. Therefore, let's define this as a u32 so we don't waste bytes on LP64 systems. Move to the end of the struct for alignment. Reviewed-by: Gleb Natapov Signed-off-by: Alex Williamson Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d897f035749f..fec607537fa3 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -266,10 +266,10 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) struct kvm_memory_slot { gfn_t base_gfn; unsigned long npages; - unsigned long flags; unsigned long *dirty_bitmap; struct kvm_arch_memory_slot arch; unsigned long userspace_addr; + u32 flags; int id; bool user_alloc; }; -- cgit v1.2.3 From 1e702d9af5d633cf0eca76f6340b3c50fbb5a4e5 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 10 Dec 2012 10:33:32 -0700 Subject: KVM: struct kvm_memory_slot.id -> short We're currently offering a whopping 32 memory slots to user space, an int is a bit excessive for storing this. We would like to increase our memslots, but SHRT_MAX should be more than enough. Reviewed-by: Gleb Natapov Signed-off-by: Alex Williamson Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index fec607537fa3..32fdc45ca35e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -270,7 +270,7 @@ struct kvm_memory_slot { struct kvm_arch_memory_slot arch; unsigned long userspace_addr; u32 flags; - int id; + short id; bool user_alloc; }; @@ -330,7 +330,7 @@ struct kvm_memslots { u64 generation; struct kvm_memory_slot memslots[KVM_MEM_SLOTS_NUM]; /* The mapping table from slot id to the index in memslots[]. */ - int id_to_index[KVM_MEM_SLOTS_NUM]; + short id_to_index[KVM_MEM_SLOTS_NUM]; }; struct kvm { -- cgit v1.2.3 From 80f5ab097b87c86581cb9736a8e55c5a3047d4bb Mon Sep 17 00:00:00 2001 From: Shaun Ruffell Date: Sun, 19 Aug 2012 01:11:24 -0300 Subject: edac: edac_mc no longer deals with kobjects directly There are no more embedded kobjects in struct mem_ctl_info. Remove a header and a comment that does not reflect the code anymore. Signed-off-by: Shaun Ruffell Signed-off-by: Mauro Carvalho Chehab --- include/linux/edac.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 1b8c02b36f76..4784213c819d 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -14,7 +14,6 @@ #include #include -#include #include #include #include -- cgit v1.2.3 From 116c14c0191f3378e6567af296529ac287e85aa2 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 21 Dec 2012 08:20:16 -0700 Subject: kvm: Fix memory slot generation updates Previous patch "kvm: Minor memory slot optimization" (b7f69c555ca43) overlooked the generation field of the memory slots. Re-using the original memory slots left us with with two slightly different memory slots with the same generation. To fix this, make update_memslots() take a new parameter to specify the last generation. This also makes generation management more explicit to avoid such problems in the future. Reported-by: Takuya Yoshikawa Signed-off-by: Alex Williamson Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 32fdc45ca35e..cbe0d683e2e5 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -428,7 +428,8 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); -void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new); +void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new, + u64 last_generation); static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) { -- cgit v1.2.3 From 9a32299394d8cce79ca7d0098dc32c4f14032dcd Mon Sep 17 00:00:00 2001 From: Philippe De Muyter Date: Fri, 12 Oct 2012 17:52:45 +0200 Subject: powerpc, dma: move bestcomm driver from arch/powerpc/sysdev to drivers/dma The bestcomm dma hardware, and some of its users like the FEC ethernet component, is used in different FreeScale parts, including non-powerpc parts like the ColdFire MCF547x & MCF548x families. Don't keep the driver hidden in arch/powerpc where it is inaccessible for other arches. .c files are moved to drivers/dma/bestcomm, while .h files are moved to include/linux/fsl/bestcomm. Makefiles, Kconfigs and #include directives are updated for the new file locations. Tested by recompiling for MPC5200 with all bestcomm users enabled. Signed-off-by: Philippe De Muyter Signed-off-by: Anatolij Gustschin --- include/linux/fsl/bestcomm/ata.h | 30 +++ include/linux/fsl/bestcomm/bestcomm.h | 213 ++++++++++++++++++ include/linux/fsl/bestcomm/bestcomm_priv.h | 350 +++++++++++++++++++++++++++++ include/linux/fsl/bestcomm/fec.h | 61 +++++ include/linux/fsl/bestcomm/gen_bd.h | 53 +++++ include/linux/fsl/bestcomm/sram.h | 54 +++++ 6 files changed, 761 insertions(+) create mode 100644 include/linux/fsl/bestcomm/ata.h create mode 100644 include/linux/fsl/bestcomm/bestcomm.h create mode 100644 include/linux/fsl/bestcomm/bestcomm_priv.h create mode 100644 include/linux/fsl/bestcomm/fec.h create mode 100644 include/linux/fsl/bestcomm/gen_bd.h create mode 100644 include/linux/fsl/bestcomm/sram.h (limited to 'include/linux') diff --git a/include/linux/fsl/bestcomm/ata.h b/include/linux/fsl/bestcomm/ata.h new file mode 100644 index 000000000000..0b2371811334 --- /dev/null +++ b/include/linux/fsl/bestcomm/ata.h @@ -0,0 +1,30 @@ +/* + * Header for Bestcomm ATA task driver + * + * + * Copyright (C) 2006 Freescale - John Rigby + * Copyright (C) 2006 Sylvain Munaut + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#ifndef __BESTCOMM_ATA_H__ +#define __BESTCOMM_ATA_H__ + + +struct bcom_ata_bd { + u32 status; + u32 src_pa; + u32 dst_pa; +}; + +extern struct bcom_task * bcom_ata_init(int queue_len, int maxbufsize); +extern void bcom_ata_rx_prepare(struct bcom_task *tsk); +extern void bcom_ata_tx_prepare(struct bcom_task *tsk); +extern void bcom_ata_reset_bd(struct bcom_task *tsk); +extern void bcom_ata_release(struct bcom_task *tsk); + +#endif /* __BESTCOMM_ATA_H__ */ + diff --git a/include/linux/fsl/bestcomm/bestcomm.h b/include/linux/fsl/bestcomm/bestcomm.h new file mode 100644 index 000000000000..a0e2e6b19b57 --- /dev/null +++ b/include/linux/fsl/bestcomm/bestcomm.h @@ -0,0 +1,213 @@ +/* + * Public header for the MPC52xx processor BestComm driver + * + * + * Copyright (C) 2006 Sylvain Munaut + * Copyright (C) 2005 Varma Electronics Oy, + * ( by Andrey Volkov ) + * Copyright (C) 2003-2004 MontaVista, Software, Inc. + * ( by Dale Farnsworth ) + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#ifndef __BESTCOMM_H__ +#define __BESTCOMM_H__ + +/** + * struct bcom_bd - Structure describing a generic BestComm buffer descriptor + * @status: The current status of this buffer. Exact meaning depends on the + * task type + * @data: An array of u32 extra data. Size of array is task dependent. + * + * Note: Don't dereference a bcom_bd pointer as an array. The size of the + * bcom_bd is variable. Use bcom_get_bd() instead. + */ +struct bcom_bd { + u32 status; + u32 data[0]; /* variable payload size */ +}; + +/* ======================================================================== */ +/* Generic task management */ +/* ======================================================================== */ + +/** + * struct bcom_task - Structure describing a loaded BestComm task + * + * This structure is never built by the driver it self. It's built and + * filled the intermediate layer of the BestComm API, the task dependent + * support code. + * + * Most likely you don't need to poke around inside this structure. The + * fields are exposed in the header just for the sake of inline functions + */ +struct bcom_task { + unsigned int tasknum; + unsigned int flags; + int irq; + + struct bcom_bd *bd; + phys_addr_t bd_pa; + void **cookie; + unsigned short index; + unsigned short outdex; + unsigned int num_bd; + unsigned int bd_size; + + void* priv; +}; + +#define BCOM_FLAGS_NONE 0x00000000ul +#define BCOM_FLAGS_ENABLE_TASK (1ul << 0) + +/** + * bcom_enable - Enable a BestComm task + * @tsk: The BestComm task structure + * + * This function makes sure the given task is enabled and can be run + * by the BestComm engine as needed + */ +extern void bcom_enable(struct bcom_task *tsk); + +/** + * bcom_disable - Disable a BestComm task + * @tsk: The BestComm task structure + * + * This function disable a given task, making sure it's not executed + * by the BestComm engine. + */ +extern void bcom_disable(struct bcom_task *tsk); + + +/** + * bcom_get_task_irq - Returns the irq number of a BestComm task + * @tsk: The BestComm task structure + */ +static inline int +bcom_get_task_irq(struct bcom_task *tsk) { + return tsk->irq; +} + +/* ======================================================================== */ +/* BD based tasks helpers */ +/* ======================================================================== */ + +#define BCOM_BD_READY 0x40000000ul + +/** _bcom_next_index - Get next input index. + * @tsk: pointer to task structure + * + * Support function; Device drivers should not call this + */ +static inline int +_bcom_next_index(struct bcom_task *tsk) +{ + return ((tsk->index + 1) == tsk->num_bd) ? 0 : tsk->index + 1; +} + +/** _bcom_next_outdex - Get next output index. + * @tsk: pointer to task structure + * + * Support function; Device drivers should not call this + */ +static inline int +_bcom_next_outdex(struct bcom_task *tsk) +{ + return ((tsk->outdex + 1) == tsk->num_bd) ? 0 : tsk->outdex + 1; +} + +/** + * bcom_queue_empty - Checks if a BestComm task BD queue is empty + * @tsk: The BestComm task structure + */ +static inline int +bcom_queue_empty(struct bcom_task *tsk) +{ + return tsk->index == tsk->outdex; +} + +/** + * bcom_queue_full - Checks if a BestComm task BD queue is full + * @tsk: The BestComm task structure + */ +static inline int +bcom_queue_full(struct bcom_task *tsk) +{ + return tsk->outdex == _bcom_next_index(tsk); +} + +/** + * bcom_get_bd - Get a BD from the queue + * @tsk: The BestComm task structure + * index: Index of the BD to fetch + */ +static inline struct bcom_bd +*bcom_get_bd(struct bcom_task *tsk, unsigned int index) +{ + /* A cast to (void*) so the address can be incremented by the + * real size instead of by sizeof(struct bcom_bd) */ + return ((void *)tsk->bd) + (index * tsk->bd_size); +} + +/** + * bcom_buffer_done - Checks if a BestComm + * @tsk: The BestComm task structure + */ +static inline int +bcom_buffer_done(struct bcom_task *tsk) +{ + struct bcom_bd *bd; + if (bcom_queue_empty(tsk)) + return 0; + + bd = bcom_get_bd(tsk, tsk->outdex); + return !(bd->status & BCOM_BD_READY); +} + +/** + * bcom_prepare_next_buffer - clear status of next available buffer. + * @tsk: The BestComm task structure + * + * Returns pointer to next buffer descriptor + */ +static inline struct bcom_bd * +bcom_prepare_next_buffer(struct bcom_task *tsk) +{ + struct bcom_bd *bd; + + bd = bcom_get_bd(tsk, tsk->index); + bd->status = 0; /* cleanup last status */ + return bd; +} + +static inline void +bcom_submit_next_buffer(struct bcom_task *tsk, void *cookie) +{ + struct bcom_bd *bd = bcom_get_bd(tsk, tsk->index); + + tsk->cookie[tsk->index] = cookie; + mb(); /* ensure the bd is really up-to-date */ + bd->status |= BCOM_BD_READY; + tsk->index = _bcom_next_index(tsk); + if (tsk->flags & BCOM_FLAGS_ENABLE_TASK) + bcom_enable(tsk); +} + +static inline void * +bcom_retrieve_buffer(struct bcom_task *tsk, u32 *p_status, struct bcom_bd **p_bd) +{ + void *cookie = tsk->cookie[tsk->outdex]; + struct bcom_bd *bd = bcom_get_bd(tsk, tsk->outdex); + + if (p_status) + *p_status = bd->status; + if (p_bd) + *p_bd = bd; + tsk->outdex = _bcom_next_outdex(tsk); + return cookie; +} + +#endif /* __BESTCOMM_H__ */ diff --git a/include/linux/fsl/bestcomm/bestcomm_priv.h b/include/linux/fsl/bestcomm/bestcomm_priv.h new file mode 100644 index 000000000000..3b52f3ffbdf8 --- /dev/null +++ b/include/linux/fsl/bestcomm/bestcomm_priv.h @@ -0,0 +1,350 @@ +/* + * Private header for the MPC52xx processor BestComm driver + * + * By private, we mean that driver should not use it directly. It's meant + * to be used by the BestComm engine driver itself and by the intermediate + * layer between the core and the drivers. + * + * Copyright (C) 2006 Sylvain Munaut + * Copyright (C) 2005 Varma Electronics Oy, + * ( by Andrey Volkov ) + * Copyright (C) 2003-2004 MontaVista, Software, Inc. + * ( by Dale Farnsworth ) + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#ifndef __BESTCOMM_PRIV_H__ +#define __BESTCOMM_PRIV_H__ + +#include +#include +#include +#include + +#include "sram.h" + + +/* ======================================================================== */ +/* Engine related stuff */ +/* ======================================================================== */ + +/* Zones sizes and needed alignments */ +#define BCOM_MAX_TASKS 16 +#define BCOM_MAX_VAR 24 +#define BCOM_MAX_INC 8 +#define BCOM_MAX_FDT 64 +#define BCOM_MAX_CTX 20 +#define BCOM_CTX_SIZE (BCOM_MAX_CTX * sizeof(u32)) +#define BCOM_CTX_ALIGN 0x100 +#define BCOM_VAR_SIZE (BCOM_MAX_VAR * sizeof(u32)) +#define BCOM_INC_SIZE (BCOM_MAX_INC * sizeof(u32)) +#define BCOM_VAR_ALIGN 0x80 +#define BCOM_FDT_SIZE (BCOM_MAX_FDT * sizeof(u32)) +#define BCOM_FDT_ALIGN 0x100 + +/** + * struct bcom_tdt - Task Descriptor Table Entry + * + */ +struct bcom_tdt { + u32 start; + u32 stop; + u32 var; + u32 fdt; + u32 exec_status; /* used internally by BestComm engine */ + u32 mvtp; /* used internally by BestComm engine */ + u32 context; + u32 litbase; +}; + +/** + * struct bcom_engine + * + * This holds all info needed globaly to handle the engine + */ +struct bcom_engine { + struct device_node *ofnode; + struct mpc52xx_sdma __iomem *regs; + phys_addr_t regs_base; + + struct bcom_tdt *tdt; + u32 *ctx; + u32 *var; + u32 *fdt; + + spinlock_t lock; +}; + +extern struct bcom_engine *bcom_eng; + + +/* ======================================================================== */ +/* Tasks related stuff */ +/* ======================================================================== */ + +/* Tasks image header */ +#define BCOM_TASK_MAGIC 0x4243544B /* 'BCTK' */ + +struct bcom_task_header { + u32 magic; + u8 desc_size; /* the size fields */ + u8 var_size; /* are given in number */ + u8 inc_size; /* of 32-bits words */ + u8 first_var; + u8 reserved[8]; +}; + +/* Descriptors structure & co */ +#define BCOM_DESC_NOP 0x000001f8 +#define BCOM_LCD_MASK 0x80000000 +#define BCOM_DRD_EXTENDED 0x40000000 +#define BCOM_DRD_INITIATOR_SHIFT 21 + +/* Tasks pragma */ +#define BCOM_PRAGMA_BIT_RSV 7 /* reserved pragma bit */ +#define BCOM_PRAGMA_BIT_PRECISE_INC 6 /* increment 0=when possible, */ + /* 1=iter end */ +#define BCOM_PRAGMA_BIT_RST_ERROR_NO 5 /* don't reset errors on */ + /* task enable */ +#define BCOM_PRAGMA_BIT_PACK 4 /* pack data enable */ +#define BCOM_PRAGMA_BIT_INTEGER 3 /* data alignment */ + /* 0=frac(msb), 1=int(lsb) */ +#define BCOM_PRAGMA_BIT_SPECREAD 2 /* XLB speculative read */ +#define BCOM_PRAGMA_BIT_CW 1 /* write line buffer enable */ +#define BCOM_PRAGMA_BIT_RL 0 /* read line buffer enable */ + + /* Looks like XLB speculative read generates XLB errors when a buffer + * is at the end of the physical memory. i.e. when accessing the + * lasts words, the engine tries to prefetch the next but there is no + * next ... + */ +#define BCOM_STD_PRAGMA ((0 << BCOM_PRAGMA_BIT_RSV) | \ + (0 << BCOM_PRAGMA_BIT_PRECISE_INC) | \ + (0 << BCOM_PRAGMA_BIT_RST_ERROR_NO) | \ + (0 << BCOM_PRAGMA_BIT_PACK) | \ + (0 << BCOM_PRAGMA_BIT_INTEGER) | \ + (0 << BCOM_PRAGMA_BIT_SPECREAD) | \ + (1 << BCOM_PRAGMA_BIT_CW) | \ + (1 << BCOM_PRAGMA_BIT_RL)) + +#define BCOM_PCI_PRAGMA ((0 << BCOM_PRAGMA_BIT_RSV) | \ + (0 << BCOM_PRAGMA_BIT_PRECISE_INC) | \ + (0 << BCOM_PRAGMA_BIT_RST_ERROR_NO) | \ + (0 << BCOM_PRAGMA_BIT_PACK) | \ + (1 << BCOM_PRAGMA_BIT_INTEGER) | \ + (0 << BCOM_PRAGMA_BIT_SPECREAD) | \ + (1 << BCOM_PRAGMA_BIT_CW) | \ + (1 << BCOM_PRAGMA_BIT_RL)) + +#define BCOM_ATA_PRAGMA BCOM_STD_PRAGMA +#define BCOM_CRC16_DP_0_PRAGMA BCOM_STD_PRAGMA +#define BCOM_CRC16_DP_1_PRAGMA BCOM_STD_PRAGMA +#define BCOM_FEC_RX_BD_PRAGMA BCOM_STD_PRAGMA +#define BCOM_FEC_TX_BD_PRAGMA BCOM_STD_PRAGMA +#define BCOM_GEN_DP_0_PRAGMA BCOM_STD_PRAGMA +#define BCOM_GEN_DP_1_PRAGMA BCOM_STD_PRAGMA +#define BCOM_GEN_DP_2_PRAGMA BCOM_STD_PRAGMA +#define BCOM_GEN_DP_3_PRAGMA BCOM_STD_PRAGMA +#define BCOM_GEN_DP_BD_0_PRAGMA BCOM_STD_PRAGMA +#define BCOM_GEN_DP_BD_1_PRAGMA BCOM_STD_PRAGMA +#define BCOM_GEN_RX_BD_PRAGMA BCOM_STD_PRAGMA +#define BCOM_GEN_TX_BD_PRAGMA BCOM_STD_PRAGMA +#define BCOM_GEN_LPC_PRAGMA BCOM_STD_PRAGMA +#define BCOM_PCI_RX_PRAGMA BCOM_PCI_PRAGMA +#define BCOM_PCI_TX_PRAGMA BCOM_PCI_PRAGMA + +/* Initiators number */ +#define BCOM_INITIATOR_ALWAYS 0 +#define BCOM_INITIATOR_SCTMR_0 1 +#define BCOM_INITIATOR_SCTMR_1 2 +#define BCOM_INITIATOR_FEC_RX 3 +#define BCOM_INITIATOR_FEC_TX 4 +#define BCOM_INITIATOR_ATA_RX 5 +#define BCOM_INITIATOR_ATA_TX 6 +#define BCOM_INITIATOR_SCPCI_RX 7 +#define BCOM_INITIATOR_SCPCI_TX 8 +#define BCOM_INITIATOR_PSC3_RX 9 +#define BCOM_INITIATOR_PSC3_TX 10 +#define BCOM_INITIATOR_PSC2_RX 11 +#define BCOM_INITIATOR_PSC2_TX 12 +#define BCOM_INITIATOR_PSC1_RX 13 +#define BCOM_INITIATOR_PSC1_TX 14 +#define BCOM_INITIATOR_SCTMR_2 15 +#define BCOM_INITIATOR_SCLPC 16 +#define BCOM_INITIATOR_PSC5_RX 17 +#define BCOM_INITIATOR_PSC5_TX 18 +#define BCOM_INITIATOR_PSC4_RX 19 +#define BCOM_INITIATOR_PSC4_TX 20 +#define BCOM_INITIATOR_I2C2_RX 21 +#define BCOM_INITIATOR_I2C2_TX 22 +#define BCOM_INITIATOR_I2C1_RX 23 +#define BCOM_INITIATOR_I2C1_TX 24 +#define BCOM_INITIATOR_PSC6_RX 25 +#define BCOM_INITIATOR_PSC6_TX 26 +#define BCOM_INITIATOR_IRDA_RX 25 +#define BCOM_INITIATOR_IRDA_TX 26 +#define BCOM_INITIATOR_SCTMR_3 27 +#define BCOM_INITIATOR_SCTMR_4 28 +#define BCOM_INITIATOR_SCTMR_5 29 +#define BCOM_INITIATOR_SCTMR_6 30 +#define BCOM_INITIATOR_SCTMR_7 31 + +/* Initiators priorities */ +#define BCOM_IPR_ALWAYS 7 +#define BCOM_IPR_SCTMR_0 2 +#define BCOM_IPR_SCTMR_1 2 +#define BCOM_IPR_FEC_RX 6 +#define BCOM_IPR_FEC_TX 5 +#define BCOM_IPR_ATA_RX 7 +#define BCOM_IPR_ATA_TX 7 +#define BCOM_IPR_SCPCI_RX 2 +#define BCOM_IPR_SCPCI_TX 2 +#define BCOM_IPR_PSC3_RX 2 +#define BCOM_IPR_PSC3_TX 2 +#define BCOM_IPR_PSC2_RX 2 +#define BCOM_IPR_PSC2_TX 2 +#define BCOM_IPR_PSC1_RX 2 +#define BCOM_IPR_PSC1_TX 2 +#define BCOM_IPR_SCTMR_2 2 +#define BCOM_IPR_SCLPC 2 +#define BCOM_IPR_PSC5_RX 2 +#define BCOM_IPR_PSC5_TX 2 +#define BCOM_IPR_PSC4_RX 2 +#define BCOM_IPR_PSC4_TX 2 +#define BCOM_IPR_I2C2_RX 2 +#define BCOM_IPR_I2C2_TX 2 +#define BCOM_IPR_I2C1_RX 2 +#define BCOM_IPR_I2C1_TX 2 +#define BCOM_IPR_PSC6_RX 2 +#define BCOM_IPR_PSC6_TX 2 +#define BCOM_IPR_IRDA_RX 2 +#define BCOM_IPR_IRDA_TX 2 +#define BCOM_IPR_SCTMR_3 2 +#define BCOM_IPR_SCTMR_4 2 +#define BCOM_IPR_SCTMR_5 2 +#define BCOM_IPR_SCTMR_6 2 +#define BCOM_IPR_SCTMR_7 2 + + +/* ======================================================================== */ +/* API */ +/* ======================================================================== */ + +extern struct bcom_task *bcom_task_alloc(int bd_count, int bd_size, int priv_size); +extern void bcom_task_free(struct bcom_task *tsk); +extern int bcom_load_image(int task, u32 *task_image); +extern void bcom_set_initiator(int task, int initiator); + + +#define TASK_ENABLE 0x8000 + +/** + * bcom_disable_prefetch - Hook to disable bus prefetching + * + * ATA DMA and the original MPC5200 need this due to silicon bugs. At the + * moment disabling prefetch is a one-way street. There is no mechanism + * in place to turn prefetch back on after it has been disabled. There is + * no reason it couldn't be done, it would just be more complex to implement. + */ +static inline void bcom_disable_prefetch(void) +{ + u16 regval; + + regval = in_be16(&bcom_eng->regs->PtdCntrl); + out_be16(&bcom_eng->regs->PtdCntrl, regval | 1); +}; + +static inline void +bcom_enable_task(int task) +{ + u16 reg; + reg = in_be16(&bcom_eng->regs->tcr[task]); + out_be16(&bcom_eng->regs->tcr[task], reg | TASK_ENABLE); +} + +static inline void +bcom_disable_task(int task) +{ + u16 reg = in_be16(&bcom_eng->regs->tcr[task]); + out_be16(&bcom_eng->regs->tcr[task], reg & ~TASK_ENABLE); +} + + +static inline u32 * +bcom_task_desc(int task) +{ + return bcom_sram_pa2va(bcom_eng->tdt[task].start); +} + +static inline int +bcom_task_num_descs(int task) +{ + return (bcom_eng->tdt[task].stop - bcom_eng->tdt[task].start)/sizeof(u32) + 1; +} + +static inline u32 * +bcom_task_var(int task) +{ + return bcom_sram_pa2va(bcom_eng->tdt[task].var); +} + +static inline u32 * +bcom_task_inc(int task) +{ + return &bcom_task_var(task)[BCOM_MAX_VAR]; +} + + +static inline int +bcom_drd_is_extended(u32 desc) +{ + return (desc) & BCOM_DRD_EXTENDED; +} + +static inline int +bcom_desc_is_drd(u32 desc) +{ + return !(desc & BCOM_LCD_MASK) && desc != BCOM_DESC_NOP; +} + +static inline int +bcom_desc_initiator(u32 desc) +{ + return (desc >> BCOM_DRD_INITIATOR_SHIFT) & 0x1f; +} + +static inline void +bcom_set_desc_initiator(u32 *desc, int initiator) +{ + *desc = (*desc & ~(0x1f << BCOM_DRD_INITIATOR_SHIFT)) | + ((initiator & 0x1f) << BCOM_DRD_INITIATOR_SHIFT); +} + + +static inline void +bcom_set_task_pragma(int task, int pragma) +{ + u32 *fdt = &bcom_eng->tdt[task].fdt; + *fdt = (*fdt & ~0xff) | pragma; +} + +static inline void +bcom_set_task_auto_start(int task, int next_task) +{ + u16 __iomem *tcr = &bcom_eng->regs->tcr[task]; + out_be16(tcr, (in_be16(tcr) & ~0xff) | 0x00c0 | next_task); +} + +static inline void +bcom_set_tcr_initiator(int task, int initiator) +{ + u16 __iomem *tcr = &bcom_eng->regs->tcr[task]; + out_be16(tcr, (in_be16(tcr) & ~0x1f00) | ((initiator & 0x1f) << 8)); +} + + +#endif /* __BESTCOMM_PRIV_H__ */ + diff --git a/include/linux/fsl/bestcomm/fec.h b/include/linux/fsl/bestcomm/fec.h new file mode 100644 index 000000000000..ee565d94d503 --- /dev/null +++ b/include/linux/fsl/bestcomm/fec.h @@ -0,0 +1,61 @@ +/* + * Header for Bestcomm FEC tasks driver + * + * + * Copyright (C) 2006-2007 Sylvain Munaut + * Copyright (C) 2003-2004 MontaVista, Software, Inc. + * ( by Dale Farnsworth ) + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#ifndef __BESTCOMM_FEC_H__ +#define __BESTCOMM_FEC_H__ + + +struct bcom_fec_bd { + u32 status; + u32 skb_pa; +}; + +#define BCOM_FEC_TX_BD_TFD 0x08000000ul /* transmit frame done */ +#define BCOM_FEC_TX_BD_TC 0x04000000ul /* transmit CRC */ +#define BCOM_FEC_TX_BD_ABC 0x02000000ul /* append bad CRC */ + +#define BCOM_FEC_RX_BD_L 0x08000000ul /* buffer is last in frame */ +#define BCOM_FEC_RX_BD_BC 0x00800000ul /* DA is broadcast */ +#define BCOM_FEC_RX_BD_MC 0x00400000ul /* DA is multicast and not broadcast */ +#define BCOM_FEC_RX_BD_LG 0x00200000ul /* Rx frame length violation */ +#define BCOM_FEC_RX_BD_NO 0x00100000ul /* Rx non-octet aligned frame */ +#define BCOM_FEC_RX_BD_CR 0x00040000ul /* Rx CRC error */ +#define BCOM_FEC_RX_BD_OV 0x00020000ul /* overrun */ +#define BCOM_FEC_RX_BD_TR 0x00010000ul /* Rx frame truncated */ +#define BCOM_FEC_RX_BD_LEN_MASK 0x000007fful /* mask for length of received frame */ +#define BCOM_FEC_RX_BD_ERRORS (BCOM_FEC_RX_BD_LG | BCOM_FEC_RX_BD_NO | \ + BCOM_FEC_RX_BD_CR | BCOM_FEC_RX_BD_OV | BCOM_FEC_RX_BD_TR) + + +extern struct bcom_task * +bcom_fec_rx_init(int queue_len, phys_addr_t fifo, int maxbufsize); + +extern int +bcom_fec_rx_reset(struct bcom_task *tsk); + +extern void +bcom_fec_rx_release(struct bcom_task *tsk); + + +extern struct bcom_task * +bcom_fec_tx_init(int queue_len, phys_addr_t fifo); + +extern int +bcom_fec_tx_reset(struct bcom_task *tsk); + +extern void +bcom_fec_tx_release(struct bcom_task *tsk); + + +#endif /* __BESTCOMM_FEC_H__ */ + diff --git a/include/linux/fsl/bestcomm/gen_bd.h b/include/linux/fsl/bestcomm/gen_bd.h new file mode 100644 index 000000000000..de47260e69da --- /dev/null +++ b/include/linux/fsl/bestcomm/gen_bd.h @@ -0,0 +1,53 @@ +/* + * Header for Bestcomm General Buffer Descriptor tasks driver + * + * + * Copyright (C) 2007 Sylvain Munaut + * Copyright (C) 2006 AppSpec Computer Technologies Corp. + * Jeff Gibbons + * + * 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 __BESTCOMM_GEN_BD_H__ +#define __BESTCOMM_GEN_BD_H__ + +struct bcom_gen_bd { + u32 status; + u32 buf_pa; +}; + + +extern struct bcom_task * +bcom_gen_bd_rx_init(int queue_len, phys_addr_t fifo, + int initiator, int ipr, int maxbufsize); + +extern int +bcom_gen_bd_rx_reset(struct bcom_task *tsk); + +extern void +bcom_gen_bd_rx_release(struct bcom_task *tsk); + + +extern struct bcom_task * +bcom_gen_bd_tx_init(int queue_len, phys_addr_t fifo, + int initiator, int ipr); + +extern int +bcom_gen_bd_tx_reset(struct bcom_task *tsk); + +extern void +bcom_gen_bd_tx_release(struct bcom_task *tsk); + + +/* PSC support utility wrappers */ +struct bcom_task * bcom_psc_gen_bd_rx_init(unsigned psc_num, int queue_len, + phys_addr_t fifo, int maxbufsize); +struct bcom_task * bcom_psc_gen_bd_tx_init(unsigned psc_num, int queue_len, + phys_addr_t fifo); +#endif /* __BESTCOMM_GEN_BD_H__ */ + diff --git a/include/linux/fsl/bestcomm/sram.h b/include/linux/fsl/bestcomm/sram.h new file mode 100644 index 000000000000..b6d668963cce --- /dev/null +++ b/include/linux/fsl/bestcomm/sram.h @@ -0,0 +1,54 @@ +/* + * Handling of a sram zone for bestcomm + * + * + * Copyright (C) 2007 Sylvain Munaut + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#ifndef __BESTCOMM_SRAM_H__ +#define __BESTCOMM_SRAM_H__ + +#include +#include +#include + + +/* Structure used internally */ + /* The internals are here for the inline functions + * sake, certainly not for the user to mess with ! + */ +struct bcom_sram { + phys_addr_t base_phys; + void *base_virt; + unsigned int size; + rh_info_t *rh; + spinlock_t lock; +}; + +extern struct bcom_sram *bcom_sram; + + +/* Public API */ +extern int bcom_sram_init(struct device_node *sram_node, char *owner); +extern void bcom_sram_cleanup(void); + +extern void* bcom_sram_alloc(int size, int align, phys_addr_t *phys); +extern void bcom_sram_free(void *ptr); + +static inline phys_addr_t bcom_sram_va2pa(void *va) { + return bcom_sram->base_phys + + (unsigned long)(va - bcom_sram->base_virt); +} + +static inline void *bcom_sram_pa2va(phys_addr_t pa) { + return bcom_sram->base_virt + + (unsigned long)(pa - bcom_sram->base_phys); +} + + +#endif /* __BESTCOMM_SRAM_H__ */ + -- cgit v1.2.3 From d069015e268bcac6c8bd8997b3235f5f977d3ab6 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Mon, 19 Nov 2012 15:33:51 +0800 Subject: Introduce THERMAL_TREND_RAISE_FULL and THERMAL_TREND_DROP_FULL These two new thermal_trend types are used to tell the governor that the temeprature is raising/dropping quickly. Thermal cooling governors should handle this situation and make proper decisions, e.g. set cooling state to upper/lower limit directly instead of one step each time. Signed-off-by: Zhang Rui --- include/linux/thermal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index fe82022478e7..883bcda7e1e4 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -74,6 +74,8 @@ enum thermal_trend { THERMAL_TREND_STABLE, /* temperature is stable */ THERMAL_TREND_RAISING, /* temperature is raising */ THERMAL_TREND_DROPPING, /* temperature is dropping */ + THERMAL_TREND_RAISE_FULL, /* apply highest cooling action */ + THERMAL_TREND_DROP_FULL, /* apply lowest cooling action */ }; /* Events supported by Thermal Netlink */ -- cgit v1.2.3 From 9a6cecc846169159bfce511f4c0034bb96eea1ca Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Fri, 14 Sep 2012 17:41:57 -0500 Subject: dmaengine: add helper function to request a slave DMA channel Currently slave DMA channels are requested by calling dma_request_channel() and requires DMA clients to pass various filter parameters to obtain the appropriate channel. With device-tree being used by architectures such as arm and the addition of device-tree helper functions to extract the relevant DMA client information from device-tree, add a new function to request a slave DMA channel using device-tree. This function is currently a simple wrapper that calls the device-tree of_dma_request_slave_channel() function. Cc: Nicolas Ferre Cc: Benoit Cousson Cc: Stephen Warren Cc: Grant Likely Cc: Russell King Cc: Rob Herring Cc: Arnd Bergmann Cc: Vinod Koul Cc: Dan Williams Acked-by: Arnd Bergmann Signed-off-by: Jon Hunter Reviewed-by: Stephen Warren Acked-by: Rob Herring Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index d3201e438d16..8cd0e2556d04 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -974,6 +974,7 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); void dma_issue_pending_all(void); struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); +struct dma_chan *dma_request_slave_channel(struct device *dev, char *name); void dma_release_channel(struct dma_chan *chan); #else static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) @@ -988,6 +989,11 @@ static inline struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, { return NULL; } +static inline struct dma_chan *dma_request_slave_channel(struct device *dev, + char *name) +{ + return NULL +} static inline void dma_release_channel(struct dma_chan *chan) { } -- cgit v1.2.3 From aa3da644c76d1c2083d085e453c18f7c51f19bc4 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Fri, 14 Sep 2012 17:41:56 -0500 Subject: of: Add generic device tree DMA helpers This is based upon the work by Benoit Cousson [1] and Nicolas Ferre [2] to add some basic helpers to retrieve a DMA controller device_node and the DMA request/channel information. Aim of DMA helpers - The purpose of device-tree is to describe the capabilites of the hardware. Thinking about DMA controllers purely from the context of the hardware to begin with, we can describe a device in terms of a DMA controller as follows ... 1. Number of DMA controllers 2. Number of channels (maybe physical or logical) 3. Mapping of DMA requests signals to DMA controller 4. Number of DMA interrupts 5. Mapping of DMA interrupts to channels - With the above in mind the aim of the DT DMA helper functions is to extract the above information from the DT and provide to the appropriate driver. However, due to the vast number of DMA controllers and not all are using a common driver (such as DMA Engine) it has been seen that this is not a trivial task. In previous discussions on this topic the following concerns have been raised ... 1. How does the binding support devices with multiple DMA controllers? 2. How to support both legacy DMA controllers not using DMA Engine as well as those that support DMA Engine. 3. When using with DMA Engine how do we support the various implementations where the opaque filter function parameter differs between implementations? 4. How do we handle DMA channels that are identified with a string versus a integer? - Hence the design of the DMA helpers has to accomodate the above or align on an agreement what can be or should be supported. Design of DMA helpers 1. Registering DMA controllers In the case of DMA controllers that are using DMA Engine, requesting a channel is performed by calling the following function. struct dma_chan *dma_request_channel(dma_cap_mask_t mask, dma_filter_fn filter_fn, void *filter_param); The mask variable is used to match a type of the device controller in a list of controllers. The filter_fn and filter_param are used to identify the required dma channel and return a handle to the dma channel of type dma_chan. From the examples I have seen, the mask and filter_fn are constant for a given DMA controller and therefore, we can specify these as controller specific data when registering the DMA controller with the device-tree DMA helpers. The filter_param variable is of an unknown type and is typically specific to the DMA engine implementation for a given DMA controller. To allow some flexibility in the type and formating of this filter_param we employ an xlate to translate the device-tree binding information into the appropriate format. The xlate function used for a DMA controller can also be specified when registering the DMA controller with the device-tree DMA helpers. Based upon the above, a function for registering the DMA controller with the DMA helpers now looks like the below. The data variable is used to pass a pointer to DMA controller specific data used by the xlate function. int of_dma_controller_register(struct device_node *np, struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *), void *data) For example, in the case where DMA engine is used, we define the following structure (that stores the DMA engine capability mask and filter function) and pass this to the data variable in the above function. struct of_dma_filter_info { dma_cap_mask_t dma_cap; dma_filter_fn filter_fn; }; 2. Representing and requesting channel information Please see the dma binding documentation included in this patch for a description of how DMA controllers and client information should be represented with device-tree. For more information on how this binding came about please see [3]. In addition to this, feedback received from the Linux kernel summit showed a consensus (among those who attended) to use a name to identify DMA client information [4]. A DMA channel can be requested by calling the following function, where name is a required parameter used for identifying a DMA channel. This function has been designed to return a structure of type dma_chan to work with the DMA engine driver. Note that if DMA engine is used then drivers should be using the DMA engine API dma_request_slave_channel() (implemented in part 2 of this series, "dmaengine: add helper function to request a slave DMA channel") which will in turn call the below function if device-tree is present. The aim being to have a common DMA engine interface regardless of whether device tree is being used. struct dma_chan *of_dma_request_slave_channel(struct device_node *np, char *name) 3. Supporting legacy devices not using DMA Engine These devices present a problem, as there may not be a uniform way to easily support them with regard to device tree. Ideally, these should be migrated to DMA engine. However, if this is not possible, then they should still be able to use this binding, the only constaint imposed by this implementation is that when requesting a DMA channel via of_dma_request_slave_channel(), it will return a type of dma_chan. This implementation has been tested on OMAP4430 using the kernel v3.6-rc5. I have validated that MMC is working on the PANDA board with this implementation. My development branch for testing on OMAP can be found here [5]. v6: - minor corrections in DMA binding documentation v5: - minor update to binding documentation - added loop to exhaustively search for a slave channel in the case where there could be alternative channels available v4: - revert the removal of xlate function from v3 - update the proposed binding format and APIs based upon discussions [3] v3: - avoid passing an xlate function and instead pass DMA engine parameters - define number of dma channels and requests in dma-controller node v2: - remove of_dma_to_resource API - make property #dma-cells required (no fallback anymore) - another check in of_dma_xlate_onenumbercell() function [1] http://article.gmane.org/gmane.linux.drivers.devicetree/12022 [2] http://article.gmane.org/gmane.linux.ports.arm.omap/73622 [3] http://marc.info/?l=linux-omap&m=133582085008539&w=2 [4] http://pad.linaro.org/arm-mini-summit-2012 [5] https://github.com/jonhunter/linux/tree/dev-dt-dma Cc: Nicolas Ferre Cc: Benoit Cousson Cc: Stephen Warren Cc: Grant Likely Cc: Russell King Cc: Rob Herring Cc: Arnd Bergmann Cc: Vinod Koul Cc: Dan Williams Reviewed-by: Arnd Bergmann Reviewed-by: Nicolas Ferre Signed-off-by: Jon Hunter Reviewed-by: Stephen Warren Acked-by: Rob Herring Signed-off-by: Vinod Koul --- include/linux/of_dma.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 include/linux/of_dma.h (limited to 'include/linux') diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h new file mode 100644 index 000000000000..337823dc6b90 --- /dev/null +++ b/include/linux/of_dma.h @@ -0,0 +1,45 @@ +/* + * OF helpers for DMA request / controller + * + * Based on of_gpio.h + * + * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.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 __LINUX_OF_DMA_H +#define __LINUX_OF_DMA_H + +#include +#include + +struct device_node; + +struct of_dma { + struct list_head of_dma_controllers; + struct device_node *of_node; + int of_dma_nbcells; + struct dma_chan *(*of_dma_xlate) + (struct of_phandle_args *, struct of_dma *); + void *of_dma_data; +}; + +struct of_dma_filter_info { + dma_cap_mask_t dma_cap; + dma_filter_fn filter_fn; +}; + +extern int of_dma_controller_register(struct device_node *np, + struct dma_chan *(*of_dma_xlate) + (struct of_phandle_args *, struct of_dma *), + void *data); +extern void of_dma_controller_free(struct device_node *np); +extern struct dma_chan *of_dma_request_slave_channel(struct device_node *np, + char *name); +extern struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma); + +#endif /* __LINUX_OF_DMA_H */ -- cgit v1.2.3 From 4c26bc601d20fa67eefcb27477feda130c10790e Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Tue, 25 Sep 2012 09:57:36 +0530 Subject: of: dma- fix build break for !CONFIG_OF Signed-off-by: Vinod Koul --- include/linux/of_dma.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h index 337823dc6b90..67158ddd1f3e 100644 --- a/include/linux/of_dma.h +++ b/include/linux/of_dma.h @@ -32,6 +32,7 @@ struct of_dma_filter_info { dma_filter_fn filter_fn; }; +#ifdef CONFIG_OF extern int of_dma_controller_register(struct device_node *np, struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *), @@ -41,5 +42,31 @@ extern struct dma_chan *of_dma_request_slave_channel(struct device_node *np, char *name); extern struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma); +#else +static int of_dma_controller_register(struct device_node *np, + struct dma_chan *(*of_dma_xlate) + (struct of_phandle_args *, struct of_dma *), + void *data) +{ + return -ENODEV; +} + +static void of_dma_controller_free(struct device_node *np) +{ +} + +static struct dma_chan *of_dma_request_slave_channel(struct device_node *np, + char *name) +{ + return NULL; +} + +static struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + return NULL; +} + +#endif #endif /* __LINUX_OF_DMA_H */ -- cgit v1.2.3 From d18d5f59797009d86a0ee46feb2a56d53707455a Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Tue, 25 Sep 2012 16:18:55 +0530 Subject: dmaengine: fix build failure due to missing semi-colon Reported-by: Fengguang Wu Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 8cd0e2556d04..c88f302d91c9 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -992,7 +992,7 @@ static inline struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, static inline struct dma_chan *dma_request_slave_channel(struct device *dev, char *name) { - return NULL + return NULL; } static inline void dma_release_channel(struct dma_chan *chan) { -- cgit v1.2.3 From 177d2bf5c7d3ab41bfb4ce2597dde668225958dd Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 16 Oct 2012 09:49:16 +0530 Subject: dmaengine: dw_dmac: Update documentation style comments for dw_dma_platform_data Documentation style comments were missing for few fields in struct dw_dma_platform_data. Add these. Signed-off-by: Viresh Kumar Reviewed-by: Andy Shevchenko Signed-off-by: Vinod Koul --- include/linux/dw_dmac.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h index e1c8c9e919ac..62a6190dee22 100644 --- a/include/linux/dw_dmac.h +++ b/include/linux/dw_dmac.h @@ -19,6 +19,8 @@ * @nr_channels: Number of channels supported by hardware (max 8) * @is_private: The device channels should be marked as private and not for * by the general purpose DMA channel allocator. + * @chan_allocation_order: Allocate channels starting from 0 or 7 + * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0. * @block_size: Maximum block size supported by the controller * @nr_masters: Number of AHB masters supported by the controller * @data_width: Maximum data width supported by hardware per AHB master -- cgit v1.2.3 From 3c449ed0075994b3f3371f8254560428ba787efc Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sat, 3 Nov 2012 21:39:31 -0700 Subject: PCI/ACPI: Reserve firmware-allocated resources for hot-added root buses Firmware may have assigned PCI BARs for hot-added devices, so reserve those resources before trying to allocate more. [bhelgaas: move empty weak definition here] Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 15472d691ee6..907b455ab603 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -674,6 +674,7 @@ extern struct list_head pci_root_buses; /* list of all known PCI buses */ /* Some device drivers need know if pci is initiated */ extern int no_pci_devices(void); +void pcibios_resource_survey_bus(struct pci_bus *bus); void pcibios_fixup_bus(struct pci_bus *); int __must_check pcibios_enable_device(struct pci_dev *, int mask); /* Architecture specific versions may override this (weak) */ -- cgit v1.2.3 From a9ddb575d6d6c58c39e8c44a22b84445fedb0521 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 16 Oct 2012 09:49:17 +0530 Subject: dmaengine: dw_dmac: Enhance device tree support dw_dmac driver already supports device tree but it used to have its platform data passed the non-DT way. This patch does following changes: - pass platform data via DT, non-DT way still takes precedence if both are used. - create generic filter routine - Earlier slave information was made available by slave specific filter routines in chan->private field. Now, this information would be passed from within dmac DT node. Slave drivers would now be required to pass bus_id (a string) as parameter to this generic filter(), which would be compared against the slave data passed from DT, by the generic filter routine. - Update binding document Signed-off-by: Viresh Kumar Reviewed-by: Andy Shevchenko [Fixed __devinit usage] Signed-off-by: Vinod Koul --- include/linux/dw_dmac.h | 43 ++++++++++++++++++++++++++----------------- 1 file changed, 26 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h index 62a6190dee22..41766de66e33 100644 --- a/include/linux/dw_dmac.h +++ b/include/linux/dw_dmac.h @@ -14,6 +14,26 @@ #include +/** + * struct dw_dma_slave - Controller-specific information about a slave + * + * @dma_dev: required DMA master device. Depricated. + * @bus_id: name of this device channel, not just a device name since + * devices may have more than one channel e.g. "foo_tx" + * @cfg_hi: Platform-specific initializer for the CFG_HI register + * @cfg_lo: Platform-specific initializer for the CFG_LO register + * @src_master: src master for transfers on allocated channel. + * @dst_master: dest master for transfers on allocated channel. + */ +struct dw_dma_slave { + struct device *dma_dev; + const char *bus_id; + u32 cfg_hi; + u32 cfg_lo; + u8 src_master; + u8 dst_master; +}; + /** * struct dw_dma_platform_data - Controller configuration parameters * @nr_channels: Number of channels supported by hardware (max 8) @@ -25,6 +45,8 @@ * @nr_masters: Number of AHB masters supported by the controller * @data_width: Maximum data width supported by hardware per AHB master * (0 - 8bits, 1 - 16bits, ..., 5 - 256bits) + * @sd: slave specific data. Used for configuring channels + * @sd_count: count of slave data structures passed. */ struct dw_dma_platform_data { unsigned int nr_channels; @@ -38,6 +60,9 @@ struct dw_dma_platform_data { unsigned short block_size; unsigned char nr_masters; unsigned char data_width[4]; + + struct dw_dma_slave *sd; + unsigned int sd_count; }; /* bursts size */ @@ -52,23 +77,6 @@ enum dw_dma_msize { DW_DMA_MSIZE_256, }; -/** - * struct dw_dma_slave - Controller-specific information about a slave - * - * @dma_dev: required DMA master device - * @cfg_hi: Platform-specific initializer for the CFG_HI register - * @cfg_lo: Platform-specific initializer for the CFG_LO register - * @src_master: src master for transfers on allocated channel. - * @dst_master: dest master for transfers on allocated channel. - */ -struct dw_dma_slave { - struct device *dma_dev; - u32 cfg_hi; - u32 cfg_lo; - u8 src_master; - u8 dst_master; -}; - /* Platform-configurable bits in CFG_HI */ #define DWC_CFGH_FCMODE (1 << 0) #define DWC_CFGH_FIFO_MODE (1 << 1) @@ -106,5 +114,6 @@ void dw_dma_cyclic_stop(struct dma_chan *chan); dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan); dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan); +bool dw_dma_generic_filter(struct dma_chan *chan, void *param); #endif /* DW_DMAC_H */ -- cgit v1.2.3 From e5a087fdc1ebe5bba40bcecb53c28a0af70e3b47 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Fri, 26 Oct 2012 23:35:15 +0900 Subject: dmaengine: use for_each_set_bit Use for_each_set_bit() to implement for_each_dma_cap_mask() and remove unused first_dma_cap() and next_dma_cap(). Signed-off-by: Akinobu Mita Cc: Vinod Koul Cc: Dan Williams Acked-by: Linus Walleij Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index c88f302d91c9..4c8643794e0d 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -849,20 +849,6 @@ static inline bool async_tx_test_ack(struct dma_async_tx_descriptor *tx) return (tx->flags & DMA_CTRL_ACK) == DMA_CTRL_ACK; } -#define first_dma_cap(mask) __first_dma_cap(&(mask)) -static inline int __first_dma_cap(const dma_cap_mask_t *srcp) -{ - return min_t(int, DMA_TX_TYPE_END, - find_first_bit(srcp->bits, DMA_TX_TYPE_END)); -} - -#define next_dma_cap(n, mask) __next_dma_cap((n), &(mask)) -static inline int __next_dma_cap(int n, const dma_cap_mask_t *srcp) -{ - return min_t(int, DMA_TX_TYPE_END, - find_next_bit(srcp->bits, DMA_TX_TYPE_END, n+1)); -} - #define dma_cap_set(tx, mask) __dma_cap_set((tx), &(mask)) static inline void __dma_cap_set(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp) @@ -891,9 +877,7 @@ __dma_has_cap(enum dma_transaction_type tx_type, dma_cap_mask_t *srcp) } #define for_each_dma_cap_mask(cap, mask) \ - for ((cap) = first_dma_cap(mask); \ - (cap) < DMA_TX_TYPE_END; \ - (cap) = next_dma_cap((cap), (mask))) + for_each_set_bit(cap, mask.bits, DMA_TX_TYPE_END) /** * dma_async_issue_pending - flush pending transactions to HW -- cgit v1.2.3 From 9743a3b62dee8c9d8af1319f8d1c1ff39130267d Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Thu, 11 Oct 2012 14:43:01 -0500 Subject: of: dma: fix protection of DMA controller data stored by DMA helpers In the current implementation of the OF DMA helpers, read-copy-update (RCU) linked lists are being used for storing and accessing the DMA controller data. This part of implementation is based upon V2 of the DMA helpers by Nicolas [1]. During a recent review of RCU, it became apparent that the code is missing the required rcu_read_lock()/unlock() calls as well as synchronisation calls before freeing any memory protected by RCU. Having looked into adding the appropriate RCU calls to protect the DMA data it became apparent that with the current DMA helper implementation, using RCU is not as attractive as it may have been before. The main reasons being that ... 1. We need to protect the DMA data around calls to the xlate function. 2. The of_dma_simple_xlate() function calls the DMA engine function dma_request_channel() which employs a mutex and so could sleep. 3. The RCU read-side critical sections must not sleep and so we cannot hold an RCU read lock around the xlate function. Therefore, instead of using RCU, an alternative for this use-case is to employ a simple spinlock inconjunction with a usage count variable to keep track of how many current users of the DMA data structure there are. With this implementation, the DMA data cannot be freed until all current users of the DMA data are finished. This patch is based upon the DMA helpers fix for potential deadlock [2]. [1] http://article.gmane.org/gmane.linux.ports.arm.omap/73622 [2] http://marc.info/?l=linux-arm-kernel&m=134859982520984&w=2 Signed-off-by: Jon Hunter Signed-off-by: Vinod Koul --- include/linux/of_dma.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h index 67158ddd1f3e..84b64f857e23 100644 --- a/include/linux/of_dma.h +++ b/include/linux/of_dma.h @@ -25,6 +25,7 @@ struct of_dma { struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *); void *of_dma_data; + int use_count; }; struct of_dma_filter_info { @@ -37,7 +38,7 @@ extern int of_dma_controller_register(struct device_node *np, struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *), void *data); -extern void of_dma_controller_free(struct device_node *np); +extern int of_dma_controller_free(struct device_node *np); extern struct dma_chan *of_dma_request_slave_channel(struct device_node *np, char *name); extern struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, @@ -51,7 +52,7 @@ static int of_dma_controller_register(struct device_node *np, return -ENODEV; } -static void of_dma_controller_free(struct device_node *np) +static int of_dma_controller_free(struct device_node *np) { } -- cgit v1.2.3 From 91f8aecc501e456c97a6f49f7ea3797e874d5d89 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 29 Nov 2012 12:17:22 +0530 Subject: dmaengine: fix !of_dma compilation warning Reported-by: Stephen Rothwell Reported-by: Fengguang Wu Signed-off-by: Vinod Koul --- include/linux/of_dma.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h index 84b64f857e23..d15073e080dd 100644 --- a/include/linux/of_dma.h +++ b/include/linux/of_dma.h @@ -44,7 +44,7 @@ extern struct dma_chan *of_dma_request_slave_channel(struct device_node *np, extern struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma); #else -static int of_dma_controller_register(struct device_node *np, +static inline int of_dma_controller_register(struct device_node *np, struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *), void *data) @@ -52,17 +52,18 @@ static int of_dma_controller_register(struct device_node *np, return -ENODEV; } -static int of_dma_controller_free(struct device_node *np) +static inline int of_dma_controller_free(struct device_node *np) { + return -ENODEV; } -static struct dma_chan *of_dma_request_slave_channel(struct device_node *np, +static inline struct dma_chan *of_dma_request_slave_channel(struct device_node *np, char *name) { return NULL; } -static struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, +static inline struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma) { return NULL; -- cgit v1.2.3 From a14acb4ac2a1486f6633c55eb7f7ded07f3ec9fc Mon Sep 17 00:00:00 2001 From: Barry Song Date: Tue, 6 Nov 2012 21:32:39 +0800 Subject: DMAEngine: add dmaengine_prep_interleaved_dma wrapper for interleaved api commit b14dab792dee(DMAEngine: Define interleaved transfer request api) adds interleaved request api, this patch adds the dmaengine_prep_interleaved_dma just like we have dmaengine_prep_ for other modes to avoid drivers call: xxx_chan->device->device_prep_interleaved_dma(). Signed-off-by: Barry Song Cc: Jassi Brar Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 4c8643794e0d..3aa76dbed166 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -660,6 +660,13 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_cyclic( period_len, dir, flags, NULL); } +static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma( + struct dma_chan *chan, struct dma_interleaved_template *xt, + unsigned long flags) +{ + return chan->device->device_prep_interleaved_dma(chan, xt, flags); +} + static inline int dmaengine_terminate_all(struct dma_chan *chan) { return dmaengine_device_control(chan, DMA_TERMINATE_ALL, 0); -- cgit v1.2.3 From 944ea4dd38b8575e30a5699633c81945bff1864d Mon Sep 17 00:00:00 2001 From: Jon Mason Date: Sun, 11 Nov 2012 23:03:20 +0000 Subject: dmatest: Fix NULL pointer dereference on ioat device_control is an optional and not implemented in all DMA drivers. Any calls to these will result in a NULL pointer dereference. dmatest makes two of these calls when completing the kernel thread and removing the module. These are corrected by calling the dmaengine_device_control wrapper and checking for a non-existant device_control function pointer there. Signed-off-by: Jon Mason CC: Vinod Koul CC: Dan Williams Reviewed-by: Viresh Kumar Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 3aa76dbed166..be6e95395b11 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -608,7 +608,10 @@ static inline int dmaengine_device_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned long arg) { - return chan->device->device_control(chan, cmd, arg); + if (chan->device->device_control) + return chan->device->device_control(chan, cmd, arg); + else + return -ENOSYS; } static inline int dmaengine_slave_config(struct dma_chan *chan, -- cgit v1.2.3 From b9ee86830f34737a08deead93872a79a37419a13 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 8 Nov 2012 09:59:54 +0000 Subject: dmaengine: remove dma_async_memcpy_pending() macro Just use dma_async_issue_pending() directly. Cc: Vinod Koul Cc: Tomasz Figa Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Kyungmin Park Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index be6e95395b11..cd15958d4d1d 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -901,8 +901,6 @@ static inline void dma_async_issue_pending(struct dma_chan *chan) chan->device->device_issue_pending(chan); } -#define dma_async_memcpy_issue_pending(chan) dma_async_issue_pending(chan) - /** * dma_async_is_tx_complete - poll for transaction completion * @chan: DMA channel -- cgit v1.2.3 From e239345f642e6a255d0ba1e3d92c2f9ec5a44fbe Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 8 Nov 2012 10:01:01 +0000 Subject: dmaengine: remove dma_async_memcpy_complete() macro Just use dma_async_is_tx_complete() directly. Cc: Vinod Koul Cc: Tomasz Figa Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Kyungmin Park Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index cd15958d4d1d..4ca9cf73ad3f 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -926,16 +926,13 @@ static inline enum dma_status dma_async_is_tx_complete(struct dma_chan *chan, return status; } -#define dma_async_memcpy_complete(chan, cookie, last, used)\ - dma_async_is_tx_complete(chan, cookie, last, used) - /** * dma_async_is_complete - test a cookie against chan state * @cookie: transaction identifier to test status of * @last_complete: last know completed transaction * @last_used: last cookie value handed out * - * dma_async_is_complete() is used in dma_async_memcpy_complete() + * dma_async_is_complete() is used in dma_async_is_tx_complete() * the test logic is separated for lightweight testing of multiple cookies */ static inline enum dma_status dma_async_is_complete(dma_cookie_t cookie, -- cgit v1.2.3 From 548bc8e1b38e48653a90f48f636f8d253504f8a2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 9 Jan 2013 08:05:13 -0800 Subject: block: RCU free request_queue RCU free request_queue so that blkcg_gq->q can be dereferenced under RCU lock. This will be used to implement hierarchical stats. Signed-off-by: Tejun Heo Acked-by: Vivek Goyal --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f94bc83011ed..406343c43cda 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -19,6 +19,7 @@ #include #include #include +#include #include @@ -437,6 +438,7 @@ struct request_queue { /* Throttle data */ struct throtl_data *td; #endif + struct rcu_head rcu_head; }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ -- cgit v1.2.3 From 1c810636556c8d53a37406b34a64d9b9b0161aa6 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 4 Jan 2013 18:12:48 +0100 Subject: KVM: PPC: BookE: Implement EPR exit The External Proxy Facility in FSL BookE chips allows the interrupt controller to automatically acknowledge an interrupt as soon as a core gets its pending external interrupt delivered. Today, user space implements the interrupt controller, so we need to check on it during such a cycle. This patch implements logic for user space to enable EPR exiting, disable EPR exiting and EPR exiting itself, so that user space can acknowledge an interrupt when an external interrupt has successfully been delivered into the guest vcpu. Signed-off-by: Alexander Graf --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index cbe0d683e2e5..4dd7d7531e69 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -122,6 +122,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_WATCHDOG 18 #define KVM_REQ_MASTERCLOCK_UPDATE 19 #define KVM_REQ_MCLOCK_INPROGRESS 20 +#define KVM_REQ_EPR_EXIT 21 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 -- cgit v1.2.3 From 242d98f077ac0ab80920219769eb095503b93f61 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Mon, 17 Dec 2012 10:01:27 -0500 Subject: block,elevator: use new hashtable implementation Switch elevator to use the new hashtable implementation. This reduces the amount of generic unrelated code in the elevator. This also removes the dymanic allocation of the hash table. The size of the table is constant so there's no point in paying the price of an extra dereference when accessing it. This patch depends on d9b482c ("hashtable: introduce a small and naive hashtable") which was merged in v3.6. Signed-off-by: Sasha Levin Signed-off-by: Jens Axboe --- include/linux/elevator.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index c03af7687bb4..7c5a7c9789ee 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -2,6 +2,7 @@ #define _LINUX_ELEVATOR_H #include +#include #ifdef CONFIG_BLOCK @@ -96,6 +97,8 @@ struct elevator_type struct list_head list; }; +#define ELV_HASH_BITS 6 + /* * each queue has an elevator_queue associated with it */ @@ -105,8 +108,8 @@ struct elevator_queue void *elevator_data; struct kobject kobj; struct mutex sysfs_lock; - struct hlist_head *hash; unsigned int registered:1; + DECLARE_HASHTABLE(hash, ELV_HASH_BITS); }; /* -- cgit v1.2.3 From 422765c2638924da10ff363b5eed77924911bdc7 Mon Sep 17 00:00:00 2001 From: Jianpeng Ma Date: Fri, 11 Jan 2013 14:46:09 +0100 Subject: block: Remove should_sort judgement when flush blk_plug In commit 975927b942c932,it add blk_rq_pos to sort rq when flushing. Although this commit was used for the situation which blk_plug handled multi devices on the same time like md device. I think there must be some situations like this but only single device. So remove the should_sort judgement. Because the parameter should_sort is only for this purpose,it can delete should_sort from blk_plug. CC: Shaohua Li Signed-off-by: Jianpeng Ma Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f94bc83011ed..dbe74279f3d6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -974,7 +974,6 @@ struct blk_plug { unsigned long magic; /* detect uninitialized use-cases */ struct list_head list; /* requests */ struct list_head cb_list; /* md requires an unplug callback */ - unsigned int should_sort; /* list to be sorted before flushing? */ }; #define BLK_MAX_REQUEST_COUNT 16 -- cgit v1.2.3 From 10ee27a06cc8eb57f83342a8eabcb75deb872d52 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Thu, 10 Jan 2013 13:47:57 +0800 Subject: vfs: re-implement writeback_inodes_sb(_nr)_if_idle() and rename them writeback_inodes_sb(_nr)_if_idle() is re-implemented by replacing down_read() with down_read_trylock() because - If ->s_umount is write locked, then the sb is not idle. That is writeback_inodes_sb(_nr)_if_idle() needn't wait for the lock. - writeback_inodes_sb(_nr)_if_idle() grabs s_umount lock when it want to start writeback, it may bring us deadlock problem when doing umount. In order to fix the problem, ext4 and btrfs implemented their own writeback functions instead of writeback_inodes_sb(_nr)_if_idle(), but it introduced the redundant code, it is better to implement a new writeback_inodes_sb(_nr)_if_idle(). The name of these two functions is cumbersome, so rename them to try_to_writeback_inodes_sb(_nr). This idea came from Christoph Hellwig. Some code is from the patch of Kamal Mostafa. Reviewed-by: Jan Kara Signed-off-by: Miao Xie Signed-off-by: Fengguang Wu --- include/linux/writeback.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index b82a83aba311..9a9367c0c076 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -87,9 +87,9 @@ int inode_wait(void *); void writeback_inodes_sb(struct super_block *, enum wb_reason reason); void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); -int writeback_inodes_sb_if_idle(struct super_block *, enum wb_reason reason); -int writeback_inodes_sb_nr_if_idle(struct super_block *, unsigned long nr, - enum wb_reason reason); +int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason); +int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr, + enum wb_reason reason); void sync_inodes_sb(struct super_block *); long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason); -- cgit v1.2.3 From 61cc13a51bcff737ce02d2047834171c0365b00d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 10 Jan 2013 10:52:56 +0200 Subject: dmaengine: introduce is_slave_direction function This function helps to distinguish the slave type of transfer by checking the direction parameter. Signed-off-by: Andy Shevchenko Reviewed-by: Viresh Kumar Reviewed-by: Mika Westerberg Reviewed-by: Linus Walleij Cc: Nicolas Ferre Cc: Guennadi Liakhovetski Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 4ca9cf73ad3f..bfcdecb5d87a 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -621,6 +621,11 @@ static inline int dmaengine_slave_config(struct dma_chan *chan, (unsigned long)config); } +static inline bool is_slave_direction(enum dma_transfer_direction direction) +{ + return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM); +} + static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single( struct dma_chan *chan, dma_addr_t buf, size_t len, enum dma_transfer_direction dir, unsigned long flags) -- cgit v1.2.3 From 3a95b9fbba893ebfa9b83de105707539e0228e0c Mon Sep 17 00:00:00 2001 From: Alessandro Rubini Date: Sat, 24 Nov 2012 00:22:56 +0000 Subject: pl080.h: moved from arm/include/asm/hardware to include/linux/amba/ The header is used by drivers/dma/amba-pl08x.c, which can be compiled under x86, where PL080 exists under a PCI-to-AMBA bridge. This patche moves it where it can be accessed by other architectures, and fixes all users. Signed-off-by: Alessandro Rubini Acked-by: Giancarlo Asnaghi Acked-by: Linus Walleij Signed-off-by: Vinod Koul --- include/linux/amba/pl080.h | 146 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 146 insertions(+) create mode 100644 include/linux/amba/pl080.h (limited to 'include/linux') diff --git a/include/linux/amba/pl080.h b/include/linux/amba/pl080.h new file mode 100644 index 000000000000..3e7b62fbefbd --- /dev/null +++ b/include/linux/amba/pl080.h @@ -0,0 +1,146 @@ +/* include/linux/amba/pl080.h + * + * Copyright 2008 Openmoko, Inc. + * Copyright 2008 Simtec Electronics + * http://armlinux.simtec.co.uk/ + * Ben Dooks + * + * ARM PrimeCell PL080 DMA controller + * + * 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. +*/ + +/* Note, there are some Samsung updates to this controller block which + * make it not entierly compatible with the PL080 specification from + * ARM. When in doubt, check the Samsung documentation first. + * + * The Samsung defines are PL080S, and add an extra control register, + * the ability to move more than 2^11 counts of data and some extra + * OneNAND features. +*/ + +#ifndef ASM_PL080_H +#define ASM_PL080_H + +#define PL080_INT_STATUS (0x00) +#define PL080_TC_STATUS (0x04) +#define PL080_TC_CLEAR (0x08) +#define PL080_ERR_STATUS (0x0C) +#define PL080_ERR_CLEAR (0x10) +#define PL080_RAW_TC_STATUS (0x14) +#define PL080_RAW_ERR_STATUS (0x18) +#define PL080_EN_CHAN (0x1c) +#define PL080_SOFT_BREQ (0x20) +#define PL080_SOFT_SREQ (0x24) +#define PL080_SOFT_LBREQ (0x28) +#define PL080_SOFT_LSREQ (0x2C) + +#define PL080_CONFIG (0x30) +#define PL080_CONFIG_M2_BE (1 << 2) +#define PL080_CONFIG_M1_BE (1 << 1) +#define PL080_CONFIG_ENABLE (1 << 0) + +#define PL080_SYNC (0x34) + +/* Per channel configuration registers */ + +#define PL080_Cx_STRIDE (0x20) +#define PL080_Cx_BASE(x) ((0x100 + (x * 0x20))) +#define PL080_Cx_SRC_ADDR(x) ((0x100 + (x * 0x20))) +#define PL080_Cx_DST_ADDR(x) ((0x104 + (x * 0x20))) +#define PL080_Cx_LLI(x) ((0x108 + (x * 0x20))) +#define PL080_Cx_CONTROL(x) ((0x10C + (x * 0x20))) +#define PL080_Cx_CONFIG(x) ((0x110 + (x * 0x20))) +#define PL080S_Cx_CONTROL2(x) ((0x110 + (x * 0x20))) +#define PL080S_Cx_CONFIG(x) ((0x114 + (x * 0x20))) + +#define PL080_CH_SRC_ADDR (0x00) +#define PL080_CH_DST_ADDR (0x04) +#define PL080_CH_LLI (0x08) +#define PL080_CH_CONTROL (0x0C) +#define PL080_CH_CONFIG (0x10) +#define PL080S_CH_CONTROL2 (0x10) +#define PL080S_CH_CONFIG (0x14) + +#define PL080_LLI_ADDR_MASK (0x3fffffff << 2) +#define PL080_LLI_ADDR_SHIFT (2) +#define PL080_LLI_LM_AHB2 (1 << 0) + +#define PL080_CONTROL_TC_IRQ_EN (1 << 31) +#define PL080_CONTROL_PROT_MASK (0x7 << 28) +#define PL080_CONTROL_PROT_SHIFT (28) +#define PL080_CONTROL_PROT_CACHE (1 << 30) +#define PL080_CONTROL_PROT_BUFF (1 << 29) +#define PL080_CONTROL_PROT_SYS (1 << 28) +#define PL080_CONTROL_DST_INCR (1 << 27) +#define PL080_CONTROL_SRC_INCR (1 << 26) +#define PL080_CONTROL_DST_AHB2 (1 << 25) +#define PL080_CONTROL_SRC_AHB2 (1 << 24) +#define PL080_CONTROL_DWIDTH_MASK (0x7 << 21) +#define PL080_CONTROL_DWIDTH_SHIFT (21) +#define PL080_CONTROL_SWIDTH_MASK (0x7 << 18) +#define PL080_CONTROL_SWIDTH_SHIFT (18) +#define PL080_CONTROL_DB_SIZE_MASK (0x7 << 15) +#define PL080_CONTROL_DB_SIZE_SHIFT (15) +#define PL080_CONTROL_SB_SIZE_MASK (0x7 << 12) +#define PL080_CONTROL_SB_SIZE_SHIFT (12) +#define PL080_CONTROL_TRANSFER_SIZE_MASK (0xfff << 0) +#define PL080_CONTROL_TRANSFER_SIZE_SHIFT (0) + +#define PL080_BSIZE_1 (0x0) +#define PL080_BSIZE_4 (0x1) +#define PL080_BSIZE_8 (0x2) +#define PL080_BSIZE_16 (0x3) +#define PL080_BSIZE_32 (0x4) +#define PL080_BSIZE_64 (0x5) +#define PL080_BSIZE_128 (0x6) +#define PL080_BSIZE_256 (0x7) + +#define PL080_WIDTH_8BIT (0x0) +#define PL080_WIDTH_16BIT (0x1) +#define PL080_WIDTH_32BIT (0x2) + +#define PL080N_CONFIG_ITPROT (1 << 20) +#define PL080N_CONFIG_SECPROT (1 << 19) +#define PL080_CONFIG_HALT (1 << 18) +#define PL080_CONFIG_ACTIVE (1 << 17) /* RO */ +#define PL080_CONFIG_LOCK (1 << 16) +#define PL080_CONFIG_TC_IRQ_MASK (1 << 15) +#define PL080_CONFIG_ERR_IRQ_MASK (1 << 14) +#define PL080_CONFIG_FLOW_CONTROL_MASK (0x7 << 11) +#define PL080_CONFIG_FLOW_CONTROL_SHIFT (11) +#define PL080_CONFIG_DST_SEL_MASK (0xf << 6) +#define PL080_CONFIG_DST_SEL_SHIFT (6) +#define PL080_CONFIG_SRC_SEL_MASK (0xf << 1) +#define PL080_CONFIG_SRC_SEL_SHIFT (1) +#define PL080_CONFIG_ENABLE (1 << 0) + +#define PL080_FLOW_MEM2MEM (0x0) +#define PL080_FLOW_MEM2PER (0x1) +#define PL080_FLOW_PER2MEM (0x2) +#define PL080_FLOW_SRC2DST (0x3) +#define PL080_FLOW_SRC2DST_DST (0x4) +#define PL080_FLOW_MEM2PER_PER (0x5) +#define PL080_FLOW_PER2MEM_PER (0x6) +#define PL080_FLOW_SRC2DST_SRC (0x7) + +/* DMA linked list chain structure */ + +struct pl080_lli { + u32 src_addr; + u32 dst_addr; + u32 next_lli; + u32 control0; +}; + +struct pl080s_lli { + u32 src_addr; + u32 dst_addr; + u32 next_lli; + u32 control0; + u32 control1; +}; + +#endif /* ASM_PL080_H */ -- cgit v1.2.3 From 6c0cc950ae670403a362bdcbf3cde0df33744928 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 9 Jan 2013 22:33:37 +0100 Subject: ACPI / PCI: Set root bridge ACPI handle in advance The ACPI handles of PCI root bridges need to be known to acpi_bind_one(), so that it can create the appropriate "firmware_node" and "physical_node" files for them, but currently the way it gets to know those handles is not exactly straightforward (to put it lightly). This is how it works, roughly: 1. acpi_bus_scan() finds the handle of a PCI root bridge, creates a struct acpi_device object for it and passes that object to acpi_pci_root_add(). 2. acpi_pci_root_add() creates a struct acpi_pci_root object, populates its "device" field with its argument's address (device->handle is the ACPI handle found in step 1). 3. The struct acpi_pci_root object created in step 2 is passed to pci_acpi_scan_root() and used to get resources that are passed to pci_create_root_bus(). 4. pci_create_root_bus() creates a struct pci_host_bridge object and passes its "dev" member to device_register(). 5. platform_notify(), which for systems with ACPI is set to acpi_platform_notify(), is called. So far, so good. Now it starts to be "interesting". 6. acpi_find_bridge_device() is used to find the ACPI handle of the given device (which is the PCI root bridge) and executes acpi_pci_find_root_bridge(), among other things, for the given device object. 7. acpi_pci_find_root_bridge() uses the name (sic!) of the given device object to extract the segment and bus numbers of the PCI root bridge and passes them to acpi_get_pci_rootbridge_handle(). 8. acpi_get_pci_rootbridge_handle() browses the list of ACPI PCI root bridges and finds the one that matches the given segment and bus numbers. Its handle is then used to initialize the ACPI handle of the PCI root bridge's device object by acpi_bind_one(). However, this is *exactly* the ACPI handle we started with in step 1. Needless to say, this is quite embarassing, but it may be avoided thanks to commit f3fd0c8 (ACPI: Allow ACPI handles of devices to be initialized in advance), which makes it possible to initialize the ACPI handle of a device before passing it to device_register(). Accordingly, add a new __weak routine, pcibios_root_bridge_prepare(), defaulting to an empty implementation that can be replaced by the interested architecutres (x86 and ia64 at the moment) with functions that will set the root bridge's ACPI handle before its dev member is passed to device_register(). Make both x86 and ia64 provide such implementations of pcibios_root_bridge_prepare() and remove acpi_pci_find_root_bridge() and acpi_get_pci_rootbridge_handle() that aren't necessary any more. Included is a fix for breakage on systems with non-ACPI PCI host bridges from Bjorn Helgaas. Signed-off-by: Rafael J. Wysocki Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 907b455ab603..6860f4dec997 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -378,6 +378,8 @@ void pci_set_host_bridge_release(struct pci_host_bridge *bridge, void (*release_fn)(struct pci_host_bridge *), void *release_data); +int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge); + /* * The first PCI_BRIDGE_RESOURCE_NUM PCI bus resources (those that correspond * to P2P or CardBus bridge windows) go in a table. Additional ones (for -- cgit v1.2.3 From 47db92f4a63499b1605b4c66f9347ba5479e7b19 Mon Sep 17 00:00:00 2001 From: Gerald Baeza Date: Fri, 21 Sep 2012 21:21:37 +0200 Subject: dmaengine: ste_dma40: physical channels number correction DMAC_ICFG[0:2]=SCHNB only allows to count 'multiple of 4' physical channels so it was ok with platforms having 8 channels but cannot be used for next versions (with 10 or 14 channels). This patch allows to provide the number of physical channels for a DMA device via platform_data, or still rely on SCHNB if platform_data announces 0 channel. Signed-off-by: Gerald Baeza Reviewed-by: Per Forlin Acked-by: Linus Walleij Acked-by: Vinod Koul Signed-off-by: Fabio Baltieri --- include/linux/platform_data/dma-ste-dma40.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-ste-dma40.h b/include/linux/platform_data/dma-ste-dma40.h index 9ff93b065686..833cb959f3df 100644 --- a/include/linux/platform_data/dma-ste-dma40.h +++ b/include/linux/platform_data/dma-ste-dma40.h @@ -147,6 +147,9 @@ struct stedma40_chan_cfg { * @memcpy_conf_log: default configuration of logical channel memcpy * @disabled_channels: A vector, ending with -1, that marks physical channels * that are for different reasons not available for the driver. + * @num_of_phy_chans: The number of physical channels implemented in HW. + * 0 means reading the number of channels from DMA HW but this is only valid + * for 'multiple of 4' channels, like 8. */ struct stedma40_platform_data { u32 dev_len; @@ -158,6 +161,7 @@ struct stedma40_platform_data { struct stedma40_chan_cfg *memcpy_conf_log; int disabled_channels[STEDMA40_MAX_PHYS]; bool use_esram_lcla; + int num_of_phy_chans; }; #ifdef CONFIG_STE_DMA40 -- cgit v1.2.3 From 762eb33fdebed34d98943d85ee1425663d7cceaa Mon Sep 17 00:00:00 2001 From: Fabio Baltieri Date: Thu, 13 Dec 2012 11:38:39 +0100 Subject: dmaengine: ste_dma40: add missing kernel-doc entry Acked-by: Linus Walleij Acked-by: Vinod Koul Signed-off-by: Fabio Baltieri --- include/linux/platform_data/dma-ste-dma40.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-ste-dma40.h b/include/linux/platform_data/dma-ste-dma40.h index 833cb959f3df..b99024ba94ec 100644 --- a/include/linux/platform_data/dma-ste-dma40.h +++ b/include/linux/platform_data/dma-ste-dma40.h @@ -147,6 +147,7 @@ struct stedma40_chan_cfg { * @memcpy_conf_log: default configuration of logical channel memcpy * @disabled_channels: A vector, ending with -1, that marks physical channels * that are for different reasons not available for the driver. + * @use_esram_lcla: flag for mapping the lcla into esram region * @num_of_phy_chans: The number of physical channels implemented in HW. * 0 means reading the number of channels from DMA HW but this is only valid * for 'multiple of 4' channels, like 8. -- cgit v1.2.3 From 7407048bec896268b50e3c43c1d012a4764dc210 Mon Sep 17 00:00:00 2001 From: Fabio Baltieri Date: Tue, 18 Dec 2012 12:25:14 +0100 Subject: dmaengine: ste_dma40: add software lli support This patch add support to manage LLI by SW for select phy channels. There is a HW issue in certain controllers due to which on certain occassions HW LLI cannot be used on some physical channels. To avoid the HW issue on a specific phy channel, the phy channel number can be added to the list of soft_lli_channels and there after all the transfers on that channel will use software LLI, for peripheral to memory transfers. SoftLLI introduces relink overhead, that could impact performace for certain use cases. This is based on a previous patch of Narayanan Gopalakrishnan. Cc: Shreshtha Kumar Sahu Acked-by: Linus Walleij Acked-by: Vinod Koul Signed-off-by: Fabio Baltieri --- include/linux/platform_data/dma-ste-dma40.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-ste-dma40.h b/include/linux/platform_data/dma-ste-dma40.h index b99024ba94ec..4b781014b0a0 100644 --- a/include/linux/platform_data/dma-ste-dma40.h +++ b/include/linux/platform_data/dma-ste-dma40.h @@ -147,6 +147,12 @@ struct stedma40_chan_cfg { * @memcpy_conf_log: default configuration of logical channel memcpy * @disabled_channels: A vector, ending with -1, that marks physical channels * that are for different reasons not available for the driver. + * @soft_lli_chans: A vector, that marks physical channels will use LLI by SW + * which avoids HW bug that exists in some versions of the controller. + * SoftLLI introduces relink overhead that could impact performace for + * certain use cases. + * @num_of_soft_lli_chans: The number of channels that needs to be configured + * to use SoftLLI. * @use_esram_lcla: flag for mapping the lcla into esram region * @num_of_phy_chans: The number of physical channels implemented in HW. * 0 means reading the number of channels from DMA HW but this is only valid @@ -161,6 +167,8 @@ struct stedma40_platform_data { struct stedma40_chan_cfg *memcpy_conf_phy; struct stedma40_chan_cfg *memcpy_conf_log; int disabled_channels[STEDMA40_MAX_PHYS]; + int *soft_lli_chans; + int num_of_soft_lli_chans; bool use_esram_lcla; int num_of_phy_chans; }; -- cgit v1.2.3 From 3a366e614d0837d9fc23f78cdb1a1186ebc3387f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 11 Jan 2013 13:06:33 -0800 Subject: block: add missing block_bio_complete() tracepoint bio completion didn't kick block_bio_complete TP. Only dm was explicitly triggering the TP on IO completion. This makes block_bio_complete TP useless for tracers which want to know about bios, and all other bio based drivers skip generating blktrace completion events. This patch makes all bio completions via bio_endio() generate block_bio_complete TP. * Explicit trace_block_bio_complete() invocation removed from dm and the trace point is unexported. * @rq dropped from trace_block_bio_complete(). bios may fly around w/o queue associated. Verifying and accessing the assocaited queue belongs to TP probes. * blktrace now gets both request and bio completions. Make it ignore bio completions if request completion path is happening. This makes all bio based drivers generate blktrace completion events properly and makes the block_bio_complete TP actually useful. v2: With this change, block_bio_complete TP could be invoked on sg commands which have bio's with %NULL bi_bdev. Update TP assignment code to check whether bio->bi_bdev is %NULL before dereferencing. Signed-off-by: Tejun Heo Original-patch-by: Namhyung Kim Cc: Tejun Heo Cc: Steven Rostedt Cc: Alasdair Kergon Cc: dm-devel@redhat.com Cc: Neil Brown Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 7c2e030e72f1..0ea61e07a91c 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -12,6 +12,7 @@ struct blk_trace { int trace_state; + bool rq_based; struct rchan *rchan; unsigned long __percpu *sequence; unsigned char __percpu *msg_data; -- cgit v1.2.3 From f0059afd3e6e7aa1a0ffc23468b74c43d47660b8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 11 Jan 2013 13:06:35 -0800 Subject: buffer: make touch_buffer() an exported function We want to add a trace point to touch_buffer() but macros and inline functions defined in header files can't have tracing points. Move touch_buffer() to fs/buffer.c and make it a proper function. The new exported function is also declared inline. As most uses of touch_buffer() are inside buffer.c with nilfs2 as the only other user, the effect of this change should be negligible. Signed-off-by: Tejun Heo Cc: Steven Rostedt Signed-off-by: Jens Axboe --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 458f497738a4..5afc4f94d110 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -126,7 +126,6 @@ BUFFER_FNS(Write_EIO, write_io_error) BUFFER_FNS(Unwritten, unwritten) #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) -#define touch_buffer(bh) mark_page_accessed(bh->b_page) /* If we *know* page->private refers to buffer_heads */ #define page_buffers(page) \ @@ -142,6 +141,7 @@ BUFFER_FNS(Unwritten, unwritten) void mark_buffer_dirty(struct buffer_head *bh); void init_buffer(struct buffer_head *, bh_end_io_t *, void *); +void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); int try_to_free_buffers(struct page *); -- cgit v1.2.3 From 1757d902b029a29dfcef63609964385cf8865b5a Mon Sep 17 00:00:00 2001 From: David Milburn Date: Mon, 14 Jan 2013 09:59:30 -0600 Subject: libata: export host controller number thru /sys As low-level drivers register their host controller(s), keep track of the number of controllers and export thru /sys in a format so that udev can better match up port numbers with a specific controller. # pwd /sys/devices/pci0000:00 # find . -name 'ata*' -print (2nd controller with port multiplier attached) ./0000:00:1e.0/0000:05:01.0/ata2.7 ./0000:00:1e.0/0000:05:01.0/ata2.7/link7/dev7.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.0/dev7.0.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.0/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.1/dev7.1.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.1/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.2/dev7.2.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.2/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.3/dev7.3.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.3/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.4/dev7.4.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.4/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.5/dev7.5.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.5/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.6/dev7.6.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.6/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.7/dev7.7.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.7/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.8/dev7.8.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.8/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.9/dev7.9.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.9/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/ata_port ./0000:00:1e.0/0000:05:01.0/ata2.7/ata_port/ata2.7 ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.10/dev7.10.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.10/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.11/dev7.11.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.11/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.12/dev7.12.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.12/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.13/dev7.13.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.13/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.14/dev7.14.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.7/link7.14/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.8 ./0000:00:1e.0/0000:05:01.0/ata2.8/link8/dev8.0/ata_device ./0000:00:1e.0/0000:05:01.0/ata2.8/link8/ata_link ./0000:00:1e.0/0000:05:01.0/ata2.8/ata_port ./0000:00:1e.0/0000:05:01.0/ata2.8/ata_port/ata2.8 (1st controller) ./0000:00:1f.2/ata1.1 ./0000:00:1f.2/ata1.1/link1/dev1.0/ata_device ./0000:00:1f.2/ata1.1/link1/ata_link ./0000:00:1f.2/ata1.1/ata_port ./0000:00:1f.2/ata1.1/ata_port/ata1.1 ./0000:00:1f.2/ata1.2 ./0000:00:1f.2/ata1.2/link2/dev2.0/ata_device ./0000:00:1f.2/ata1.2/link2/ata_link ./0000:00:1f.2/ata1.2/ata_port ./0000:00:1f.2/ata1.2/ata_port/ata1.2 ./0000:00:1f.2/ata1.3 ./0000:00:1f.2/ata1.3/link3/dev3.0/ata_device ./0000:00:1f.2/ata1.3/link3/ata_link ./0000:00:1f.2/ata1.3/ata_port ./0000:00:1f.2/ata1.3/ata_port/ata1.3 ./0000:00:1f.2/ata1.4 ./0000:00:1f.2/ata1.4/link4/dev4.0/ata_device ./0000:00:1f.2/ata1.4/link4/ata_link ./0000:00:1f.2/ata1.4/ata_port ./0000:00:1f.2/ata1.4/ata_port/ata1.4 ./0000:00:1f.2/ata1.5 ./0000:00:1f.2/ata1.5/link5/dev5.0/ata_device ./0000:00:1f.2/ata1.5/link5/ata_link ./0000:00:1f.2/ata1.5/ata_port ./0000:00:1f.2/ata1.5/ata_port/ata1.5 ./0000:00:1f.2/ata1.6 ./0000:00:1f.2/ata1.6/link6/dev6.0/ata_device ./0000:00:1f.2/ata1.6/link6/ata_link ./0000:00:1f.2/ata1.6/ata_port ./0000:00:1f.2/ata1.6/ata_port/ata1.6 Signed-off-by: David Milburn Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 649e5f86b5f0..7ae207eb29a0 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -546,6 +546,7 @@ struct ata_host { void *private_data; struct ata_port_operations *ops; unsigned long flags; + unsigned int host_id; /* user visible host ID */ struct mutex eh_mutex; struct task_struct *eh_owner; -- cgit v1.2.3 From 8ab3e6a08a98f7ff18c6814065eb30ba2e000233 Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Wed, 2 Jan 2013 15:29:39 +0000 Subject: thermal: Use thermal zone device id in netlink messages This patch changes the function thermal_generate_netlink_event to receive a thermal zone device instead of a originator id. This way, the messages will always be bound to a thermal zone. Signed-off-by: Eduardo Valentin Reviewed-by: Durgadoss R Signed-off-by: Zhang Rui --- include/linux/thermal.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 883bcda7e1e4..9b78f8c6f773 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -246,9 +246,11 @@ int thermal_register_governor(struct thermal_governor *); void thermal_unregister_governor(struct thermal_governor *); #ifdef CONFIG_NET -extern int thermal_generate_netlink_event(u32 orig, enum events event); +extern int thermal_generate_netlink_event(struct thermal_zone_device *tz, + enum events event); #else -static inline int thermal_generate_netlink_event(u32 orig, enum events event) +static int thermal_generate_netlink_event(struct thermal_zone_device *tz, + enum events event) { return 0; } -- cgit v1.2.3 From 6e8575faa8fa680d59404a4d58d12190667be815 Mon Sep 17 00:00:00 2001 From: Sam Lang Date: Fri, 28 Dec 2012 09:56:46 -0800 Subject: ceph: Check for created flag in response from mds The mds now sends back a created inode if the create request performed the create. If the file already existed, no inode is returned in the reply. This allows ceph to set the created flag in atomic_open so that permissions are properly checked in the case that the file wasn't created by the create call to the mds. To ensure compability with previous kernels, a feature for sending back the inode in the create reply was added, so that the mds will only send back the inode if the client indicates it supports the feature. Signed-off-by: Sam Lang Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index dad579b0c0e6..6b7c6acbb3bf 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -14,13 +14,16 @@ #define CEPH_FEATURE_DIRLAYOUTHASH (1<<7) /* bits 8-17 defined by user-space; not supported yet here */ #define CEPH_FEATURE_CRUSH_TUNABLES (1<<18) +/* bits 19-25 defined by user-space; not supported yet here */ +#define CEPH_FEATURE_REPLY_CREATE_INODE (1<<27) /* * Features supported. */ #define CEPH_FEATURES_SUPPORTED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ - CEPH_FEATURE_CRUSH_TUNABLES) + CEPH_FEATURE_CRUSH_TUNABLES | \ + CEPH_FEATURE_REPLY_CREATE_INODE) #define CEPH_FEATURES_REQUIRED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR) -- cgit v1.2.3 From 1604f488ac2dcce33c8218e75a000e8c5fb57e61 Mon Sep 17 00:00:00 2001 From: Jim Schutt Date: Fri, 30 Nov 2012 09:15:25 -0700 Subject: libceph: for chooseleaf rules, retry CRUSH map descent from root if leaf is failed Add libceph support for a new CRUSH tunable recently added to Ceph servers. Consider the CRUSH rule step chooseleaf firstn 0 type This rule means that replicas will be chosen in a manner such that each chosen leaf's branch will contain a unique instance of . When an object is re-replicated after a leaf failure, if the CRUSH map uses a chooseleaf rule the remapped replica ends up under the bucket that held the failed leaf. This causes uneven data distribution across the storage cluster, to the point that when all the leaves but one fail under a particular bucket, that remaining leaf holds all the data from its failed peers. This behavior also limits the number of peers that can participate in the re-replication of the data held by the failed leaf, which increases the time required to re-replicate after a failure. For a chooseleaf CRUSH rule, the tree descent has two steps: call them the inner and outer descents. If the tree descent down to is the outer descent, and the descent from down to a leaf is the inner descent, the issue is that a down leaf is detected on the inner descent, so only the inner descent is retried. In order to disperse re-replicated data as widely as possible across a storage cluster after a failure, we want to retry the outer descent. So, fix up crush_choose() to allow the inner descent to return immediately on choosing a failed leaf. Wire this up as a new CRUSH tunable. Note that after this change, for a chooseleaf rule, if the primary OSD in a placement group has failed, choosing a replacement may result in one of the other OSDs in the PG colliding with the new primary. This requires that OSD's data for that PG to need moving as well. This seems unavoidable but should be relatively rare. This corresponds to ceph.git commit 88f218181a9e6d2292e2697fc93797d0f6d6e5dc. Signed-off-by: Jim Schutt Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 7 +++++-- include/linux/crush/crush.h | 2 ++ 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 6b7c6acbb3bf..2160aab482f6 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -14,7 +14,9 @@ #define CEPH_FEATURE_DIRLAYOUTHASH (1<<7) /* bits 8-17 defined by user-space; not supported yet here */ #define CEPH_FEATURE_CRUSH_TUNABLES (1<<18) -/* bits 19-25 defined by user-space; not supported yet here */ +/* bits 19-24 defined by user-space; not supported yet here */ +#define CEPH_FEATURE_CRUSH_TUNABLES2 (1<<25) +/* bit 26 defined by user-space; not supported yet here */ #define CEPH_FEATURE_REPLY_CREATE_INODE (1<<27) /* @@ -22,7 +24,8 @@ */ #define CEPH_FEATURES_SUPPORTED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ - CEPH_FEATURE_CRUSH_TUNABLES | \ + CEPH_FEATURE_CRUSH_TUNABLES | \ + CEPH_FEATURE_CRUSH_TUNABLES2 | \ CEPH_FEATURE_REPLY_CREATE_INODE) #define CEPH_FEATURES_REQUIRED_DEFAULT \ diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 25baa287cff7..6a1101f24cfb 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -162,6 +162,8 @@ struct crush_map { __u32 choose_local_fallback_tries; /* choose attempts before giving up */ __u32 choose_total_tries; + /* attempt chooseleaf inner descent once; on failure retry outer descent */ + __u32 chooseleaf_descend_once; }; -- cgit v1.2.3 From dd5f049dbdf973d9bceebef1fd73647a5ede6732 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 1 Nov 2012 08:39:27 -0500 Subject: ceph: define ceph_encode_8_safe() It's kind of a silly macro, but ceph_encode_8_safe() is the only one missing from an otherwise pretty complete set. It's not used, but neither are a couple of the others in this set. While in there, insert some whitespace to tidy up the alignment of the line-terminating backslashes in some of the macro definitions. Signed-off-by: Alex Elder Reviewed-by: Dan Mick --- include/linux/ceph/decode.h | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 4bbf2db45f46..cd679f2d348b 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -52,10 +52,10 @@ static inline int ceph_has_room(void **p, void *end, size_t n) return end >= *p && n <= end - *p; } -#define ceph_decode_need(p, end, n, bad) \ - do { \ - if (!likely(ceph_has_room(p, end, n))) \ - goto bad; \ +#define ceph_decode_need(p, end, n, bad) \ + do { \ + if (!likely(ceph_has_room(p, end, n))) \ + goto bad; \ } while (0) #define ceph_decode_64_safe(p, end, v, bad) \ @@ -99,8 +99,8 @@ static inline int ceph_has_room(void **p, void *end, size_t n) * * There are two possible failures: * - converting the string would require accessing memory at or - * beyond the "end" pointer provided (-E - * - memory could not be allocated for the result + * beyond the "end" pointer provided (-ERANGE) + * - memory could not be allocated for the result (-ENOMEM) */ static inline char *ceph_extract_encoded_string(void **p, void *end, size_t *lenp, gfp_t gfp) @@ -217,10 +217,10 @@ static inline void ceph_encode_string(void **p, void *end, *p += len; } -#define ceph_encode_need(p, end, n, bad) \ - do { \ - if (!likely(ceph_has_room(p, end, n))) \ - goto bad; \ +#define ceph_encode_need(p, end, n, bad) \ + do { \ + if (!likely(ceph_has_room(p, end, n))) \ + goto bad; \ } while (0) #define ceph_encode_64_safe(p, end, v, bad) \ @@ -231,12 +231,17 @@ static inline void ceph_encode_string(void **p, void *end, #define ceph_encode_32_safe(p, end, v, bad) \ do { \ ceph_encode_need(p, end, sizeof(u32), bad); \ - ceph_encode_32(p, v); \ + ceph_encode_32(p, v); \ } while (0) #define ceph_encode_16_safe(p, end, v, bad) \ do { \ ceph_encode_need(p, end, sizeof(u16), bad); \ - ceph_encode_16(p, v); \ + ceph_encode_16(p, v); \ + } while (0) +#define ceph_encode_8_safe(p, end, v, bad) \ + do { \ + ceph_encode_need(p, end, sizeof(u8), bad); \ + ceph_encode_8(p, v); \ } while (0) #define ceph_encode_copy_safe(p, end, pv, n, bad) \ -- cgit v1.2.3 From af77f26caa35a95af09d1dac5c513b3901de7e37 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 9 Nov 2012 08:43:15 -0600 Subject: rbd: drop oid parameters from ceph_osdc_build_request() The last two parameters to ceph_osd_build_request() describe the object id, but the values passed always come from the osd request structure whose address is also provided. Get rid of those last two parameters. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index d9b880e977e6..f2e5d2cdca06 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -227,9 +227,7 @@ extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, u64 *plen, struct ceph_osd_req_op *src_ops, struct ceph_snap_context *snapc, - struct timespec *mtime, - const char *oid, - int oid_len); + struct timespec *mtime); extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, struct ceph_file_layout *layout, -- cgit v1.2.3 From c885837f7d4f8c4f5cb2a744cc6929bc078e9dc0 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 13 Nov 2012 21:11:15 -0600 Subject: libceph: always allow trail in osd request An osd request structure contains an optional trail portion, which if present will contain data to be passed in the payload portion of the message containing the request. The trail field is a ceph_pagelist pointer, and if null it indicates there is no trail. A ceph_pagelist structure contains a length field, and it can legitimately hold value 0. Make use of this to change the interpretation of the "trail" of an osd request so that every osd request has trailing data, it just might have length 0. This means we change the r_trail field in a ceph_osd_request structure from a pointer to a structure that is always initialized. Note that in ceph_osdc_start_request(), the trail pointer (or now address of that structure) is assigned to a ceph message's trail field. Here's why that's still OK (looking at net/ceph/messenger.c): - What would have resulted in a null pointer previously will now refer to a 0-length page list. That message trail pointer is used in two functions, write_partial_msg_pages() and out_msg_pos_next(). - In write_partial_msg_pages(), a null page list pointer is handled the same as a message with 0-length trail, and both result in a "in_trail" variable set to false. The trail pointer is only used if in_trail is true. - The only other place the message trail pointer is used is out_msg_pos_next(). That function is only called by write_partial_msg_pages() and only touches the trail pointer if the in_trail value it is passed is true. Therefore a null ceph_msg->trail pointer is equivalent to a non-null pointer referring to a 0-length page list structure. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index f2e5d2cdca06..61562c792855 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -10,6 +10,7 @@ #include #include #include +#include /* * Maximum object name size @@ -22,7 +23,6 @@ struct ceph_snap_context; struct ceph_osd_request; struct ceph_osd_client; struct ceph_authorizer; -struct ceph_pagelist; /* * completion callback for async writepages @@ -95,7 +95,7 @@ struct ceph_osd_request { struct bio *r_bio; /* instead of pages */ #endif - struct ceph_pagelist *r_trail; /* trailing part of the data */ + struct ceph_pagelist r_trail; /* trailing part of the data */ }; struct ceph_osd_event { -- cgit v1.2.3 From 0120be3c60d46d6d55f4bf7a3d654cc705eb0c54 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 14 Nov 2012 09:38:19 -0600 Subject: libceph: pass length to ceph_osdc_build_request() The len argument to ceph_osdc_build_request() is set up to be passed by address, but that function never updates its value so there's no need to do this. Tighten up the interface by passing the length directly. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 61562c792855..4bfb4582439a 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -224,7 +224,7 @@ extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client * struct bio *bio); extern void ceph_osdc_build_request(struct ceph_osd_request *req, - u64 off, u64 *plen, + u64 off, u64 len, struct ceph_osd_req_op *src_ops, struct ceph_snap_context *snapc, struct timespec *mtime); -- cgit v1.2.3 From e8afad656cbcd06d02a7bacd4b318fa0e2907de0 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 14 Nov 2012 09:38:19 -0600 Subject: libceph: pass length to ceph_calc_file_object_mapping() ceph_calc_file_object_mapping() takes (among other things) a "file" offset and length, and based on the layout, determines the object number ("bno") backing the affected portion of the file's data and the offset into that object where the desired range begins. It also computes the size that should be used for the request--either the amount requested or something less if that would exceed the end of the object. This patch changes the input length parameter in this function so it is used only for input. That is, the argument will be passed by value rather than by address, so the value provided won't get updated by the function. The value would only get updated if the length would surpass the current object, and in that case the value it got updated to would be exactly that returned in *oxlen. Only one of the two callers is affected by this change. Update ceph_calc_raw_layout() so it records any updated value. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osdmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 5ea57ba69320..1f653e2ff5cc 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -110,7 +110,7 @@ extern void ceph_osdmap_destroy(struct ceph_osdmap *map); /* calculate mapping of a file extent to an object */ extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, - u64 off, u64 *plen, + u64 off, u64 len, u64 *bno, u64 *oxoff, u64 *oxlen); /* calculate mapping of object to a placement group */ -- cgit v1.2.3 From 4d6b250bf18d44571d69a0f4afec4b6a1969729f Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 13 Nov 2012 21:11:15 -0600 Subject: libceph: drop snapid in ceph_calc_raw_layout() A snapshot id must be provided to ceph_calc_raw_layout() even though it is not needed at all for calculating the layout. Where the snapshot id *is* needed is when building the request message for an osd operation. Drop the snapid parameter from ceph_calc_raw_layout() and pass that value instead in ceph_osdc_build_request(). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 4bfb4582439a..0e82a0a967ef 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -209,7 +209,6 @@ extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, extern int ceph_calc_raw_layout(struct ceph_osd_client *osdc, struct ceph_file_layout *layout, - u64 snapid, u64 off, u64 *plen, u64 *bno, struct ceph_osd_request *req, struct ceph_osd_req_op *op); @@ -227,6 +226,7 @@ extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, u64 len, struct ceph_osd_req_op *src_ops, struct ceph_snap_context *snapc, + u64 snap_id, struct timespec *mtime); extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, -- cgit v1.2.3 From e75b45cf36565fd8ba206a9d80f670a86e61ba2f Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 13 Nov 2012 21:11:14 -0600 Subject: libceph: drop osdc from ceph_calc_raw_layout() The osdc parameter to ceph_calc_raw_layout() is not used, so get rid of it. Consequently, the corresponding parameter in calc_layout() becomes unused, so get rid of that as well. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 0e82a0a967ef..fe3a6e8db1f9 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -207,8 +207,7 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); -extern int ceph_calc_raw_layout(struct ceph_osd_client *osdc, - struct ceph_file_layout *layout, +extern int ceph_calc_raw_layout(struct ceph_file_layout *layout, u64 off, u64 *plen, u64 *bno, struct ceph_osd_request *req, struct ceph_osd_req_op *op); -- cgit v1.2.3 From d178a9e74006e80f568d87e29f2a68f14fc7cbb1 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 13 Nov 2012 21:11:15 -0600 Subject: libceph: don't set flags in ceph_osdc_alloc_request() The only thing ceph_osdc_alloc_request() really does with the flags value it is passed is assign it to the newly-created osd request structure. Do that in the caller instead. Both callers subsequently call ceph_osdc_build_request(), so have that function (instead of ceph_osdc_alloc_request()) issue a warning if a request comes through with neither the read nor write flags set. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index fe3a6e8db1f9..6ddda5bbd1a6 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -213,7 +213,6 @@ extern int ceph_calc_raw_layout(struct ceph_file_layout *layout, struct ceph_osd_req_op *op); extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, - int flags, struct ceph_snap_context *snapc, struct ceph_osd_req_op *ops, bool use_mempool, -- cgit v1.2.3 From 54a5400721da7fa5a16cea151aade5bdfee74111 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 13 Nov 2012 21:11:15 -0600 Subject: libceph: don't set pages or bio in ceph_osdc_alloc_request() Only one of the two callers of ceph_osdc_alloc_request() provides page or bio data for its payload. And essentially all that function was doing with those arguments was assigning them to fields in the osd request structure. Simplify ceph_osdc_alloc_request() by having the caller take care of making those assignments Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 6ddda5bbd1a6..75f56d372d44 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -216,9 +216,7 @@ extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client * struct ceph_snap_context *snapc, struct ceph_osd_req_op *ops, bool use_mempool, - gfp_t gfp_flags, - struct page **pages, - struct bio *bio); + gfp_t gfp_flags); extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, u64 len, -- cgit v1.2.3 From ae7ca4a35b1f5df86e2c32b2cfc01a8d528c7b8c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 13 Nov 2012 21:11:15 -0600 Subject: libceph: pass num_op with ops Both ceph_osdc_alloc_request() and ceph_osdc_build_request() are provided an array of ceph osd request operations. Rather than just passing the number of operations in the array, the caller is required append an additional zeroed operation structure to signal the end of the array. All callers know the number of operations at the time these functions are called, so drop the silly zero entry and supply that number directly. As a result, get_num_ops() is no longer needed. This also means that ceph_osdc_alloc_request() never uses its ops argument, so that can be dropped. Also rbd_create_rw_ops() no longer needs to add one to reserve room for the additional op. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 75f56d372d44..2b04d054e09d 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -214,12 +214,13 @@ extern int ceph_calc_raw_layout(struct ceph_file_layout *layout, extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, - struct ceph_osd_req_op *ops, + unsigned int num_op, bool use_mempool, gfp_t gfp_flags); extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, u64 len, + unsigned int num_op, struct ceph_osd_req_op *src_ops, struct ceph_snap_context *snapc, u64 snap_id, -- cgit v1.2.3 From 2b5fc648af5eec2f4fe984cb6b926214e02c5cf4 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 14 Nov 2012 09:38:20 -0600 Subject: rbd: kill ceph_osd_req_op->flags The flags field of struct ceph_osd_req_op is never used, so just get rid of it. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 2b04d054e09d..69287ccfe68a 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -157,7 +157,6 @@ struct ceph_osd_client { struct ceph_osd_req_op { u16 op; /* CEPH_OSD_OP_* */ - u32 flags; /* CEPH_OSD_FLAG_* */ union { struct { u64 offset, length; -- cgit v1.2.3 From 373d4d099761cb1f637bed488ab3871945882273 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 21 Jan 2013 17:17:39 +1030 Subject: taint: add explicit flag to show whether lock dep is still OK. Fix up all callers as they were before, with make one change: an unsigned module taints the kernel, but doesn't turn off lockdep. Signed-off-by: Rusty Russell --- include/linux/kernel.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index c566927efcbd..80d36874689b 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -398,7 +398,11 @@ extern int panic_on_unrecovered_nmi; extern int panic_on_io_nmi; extern int sysctl_panic_on_stackoverflow; extern const char *print_tainted(void); -extern void add_taint(unsigned flag); +enum lockdep_ok { + LOCKDEP_STILL_OK, + LOCKDEP_NOW_UNRELIABLE +}; +extern void add_taint(unsigned flag, enum lockdep_ok); extern int test_taint(unsigned flag); extern unsigned long get_taint(void); extern int root_mountflags; -- cgit v1.2.3 From 93843b3764170819aeb07fc867a0499b33a875ca Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Mon, 21 Jan 2013 17:17:39 +1030 Subject: module: constify within_module_* These helper functions just check a set intersection with a range, and don't actually modify struct module. Signed-off-by: Sasha Levin Signed-off-by: Rusty Russell --- include/linux/module.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 1375ee3f03aa..ead1b5719a12 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -396,13 +396,13 @@ bool is_module_address(unsigned long addr); bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); -static inline int within_module_core(unsigned long addr, struct module *mod) +static inline int within_module_core(unsigned long addr, const struct module *mod) { return (unsigned long)mod->module_core <= addr && addr < (unsigned long)mod->module_core + mod->core_size; } -static inline int within_module_init(unsigned long addr, struct module *mod) +static inline int within_module_init(unsigned long addr, const struct module *mod) { return (unsigned long)mod->module_init <= addr && addr < (unsigned long)mod->module_init + mod->init_size; -- cgit v1.2.3 From afe759511808cd5bb508b598007cf0c7b0ca8e08 Mon Sep 17 00:00:00 2001 From: Aaron Lu Date: Tue, 15 Jan 2013 17:20:58 +0800 Subject: libata: identify and init ZPODD devices The ODD can be enabled for ZPODD if the following three conditions are satisfied: 1 The ODD supports device attention; 2 The platform can runtime power off the ODD through ACPI; 3 The ODD is either slot type or drawer type. For such ODDs, zpodd_init is called and a new structure is allocated for it to store ZPODD related stuffs. And the zpodd_dev_enabled function is used to test if ZPODD is currently enabled for this ODD. A new config CONFIG_SATA_ZPODD is added to selectively build ZPODD code. Signed-off-by: Aaron Lu Acked-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 7ae207eb29a0..65ff67e34b77 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -620,6 +620,9 @@ struct ata_device { #ifdef CONFIG_ATA_ACPI union acpi_object *gtf_cache; unsigned int gtf_filter; +#endif +#ifdef CONFIG_SATA_ZPODD + void *zpodd; #endif struct device tdev; /* n_sector is CLEAR_BEGIN, read comment above CLEAR_BEGIN */ -- cgit v1.2.3 From 6a89a314ab107a12af08c71420c19a37a30fc2d3 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Fri, 18 Jan 2013 15:57:46 +0800 Subject: gpio: devm_gpio_* support should not depend on GPIOLIB Some architectures (e.g. blackfin) provide gpio API without requiring GPIOLIB support (ARCH_WANT_OPTIONAL_GPIOLIB). devm_gpio_* functions should also work for these architectures, since they do not really depend on GPIOLIB. Add a new option GPIO_DEVRES (enabled by default) to control the build of devres.c. It also removes the empty version of devm_gpio_* functions for !GENERIC_GPIO build from linux/gpio.h, and moves the function declarations from asm-generic/gpio.h into linux/gpio.h. Signed-off-by: Shawn Guo Signed-off-by: Linus Walleij --- include/linux/gpio.h | 28 ++++++++-------------------- 1 file changed, 8 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index bfe665621536..f6c7ae3e223b 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -94,24 +94,12 @@ static inline int gpio_request(unsigned gpio, const char *label) return -ENOSYS; } -static inline int devm_gpio_request(struct device *dev, unsigned gpio, - const char *label) -{ - return -ENOSYS; -} - static inline int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) { return -ENOSYS; } -static inline int devm_gpio_request_one(struct device *dev, unsigned gpio, - unsigned long flags, const char *label) -{ - return -ENOSYS; -} - static inline int gpio_request_array(const struct gpio *array, size_t num) { return -ENOSYS; @@ -125,14 +113,6 @@ static inline void gpio_free(unsigned gpio) WARN_ON(1); } -static inline void devm_gpio_free(struct device *dev, unsigned gpio) -{ - might_sleep(); - - /* GPIO can never have been requested */ - WARN_ON(1); -} - static inline void gpio_free_array(const struct gpio *array, size_t num) { might_sleep(); @@ -248,4 +228,12 @@ gpiochip_remove_pin_ranges(struct gpio_chip *chip) #endif /* ! CONFIG_GENERIC_GPIO */ +struct device; + +/* bindings for managed devices that want to request gpios */ +int devm_gpio_request(struct device *dev, unsigned gpio, const char *label); +int devm_gpio_request_one(struct device *dev, unsigned gpio, + unsigned long flags, const char *label); +void devm_gpio_free(struct device *dev, unsigned int gpio); + #endif /* __LINUX_GPIO_H */ -- cgit v1.2.3 From 35525b79786b2ba58ef13822198ce22c497bc7a2 Mon Sep 17 00:00:00 2001 From: Andriy Skulysh Date: Mon, 7 Jan 2013 00:12:15 +0200 Subject: sunrpc: Fix lockd sleeping until timeout There is a race in enqueueing thread to a pool and waking up a thread. lockd doesn't wake up on reception of lock granted callback if svc_wake_up() is called before lockd's thread is added to a pool. Signed-off-by: Andriy Skulysh Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 676ddf53b3ee..1f0216b9a6c9 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -50,6 +50,7 @@ struct svc_pool { unsigned int sp_nrthreads; /* # of threads in pool */ struct list_head sp_all_threads; /* all server threads */ struct svc_pool_stats sp_stats; /* statistics on pool operation */ + int sp_task_pending;/* has pending task */ } ____cacheline_aligned_in_smp; /* -- cgit v1.2.3 From 2db54c72395298a58f29c75ae880be9e478fdbbd Mon Sep 17 00:00:00 2001 From: Steffen Trumtrar Date: Wed, 14 Nov 2012 10:55:04 +0100 Subject: fbmon: add videomode helpers Add a function to convert from the generic videomode to a fb_videomode. Signed-off-by: Steffen Trumtrar Reviewed-by: Thierry Reding Acked-by: Thierry Reding Tested-by: Thierry Reding Tested-by: Philipp Zabel Reviewed-by: Laurent Pinchart Acked-by: Laurent Pinchart Tested-by: Afzal Mohammed Tested-by: Rob Clark Tested-by: Leela Krishna Amudala --- include/linux/fb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index c7a95714b1fe..100a1765b787 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -19,6 +19,7 @@ struct vm_area_struct; struct fb_info; struct device; struct file; +struct videomode; /* Definitions below are used in the parsed monitor specs */ #define FB_DPMS_ACTIVE_OFF 1 @@ -714,6 +715,9 @@ extern void fb_destroy_modedb(struct fb_videomode *modedb); extern int fb_find_mode_cvt(struct fb_videomode *mode, int margins, int rb); extern unsigned char *fb_ddc_read(struct i2c_adapter *adapter); +extern int fb_videomode_from_videomode(const struct videomode *vm, + struct fb_videomode *fbmode); + /* drivers/video/modedb.c */ #define VESA_MODEDB_SIZE 34 extern void fb_var_to_videomode(struct fb_videomode *mode, -- cgit v1.2.3 From 790890444f591145d3a00623af461c9006e17d51 Mon Sep 17 00:00:00 2001 From: Steffen Trumtrar Date: Wed, 14 Nov 2012 11:12:38 +0100 Subject: fbmon: add of_videomode helpers Add helper to get fb_videomode from devicetree. Signed-off-by: Steffen Trumtrar Reviewed-by: Thierry Reding Acked-by: Thierry Reding Tested-by: Thierry Reding Tested-by: Philipp Zabel Reviewed-by: Laurent Pinchart Acked-by: Laurent Pinchart Tested-by: Afzal Mohammed Tested-by: Rob Clark Tested-by: Leela Krishna Amudala --- include/linux/fb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 100a1765b787..58b98606ac26 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -20,6 +20,7 @@ struct fb_info; struct device; struct file; struct videomode; +struct device_node; /* Definitions below are used in the parsed monitor specs */ #define FB_DPMS_ACTIVE_OFF 1 @@ -715,6 +716,9 @@ extern void fb_destroy_modedb(struct fb_videomode *modedb); extern int fb_find_mode_cvt(struct fb_videomode *mode, int margins, int rb); extern unsigned char *fb_ddc_read(struct i2c_adapter *adapter); +extern int of_get_fb_videomode(struct device_node *np, + struct fb_videomode *fb, + int index); extern int fb_videomode_from_videomode(const struct videomode *vm, struct fb_videomode *fbmode); -- cgit v1.2.3 From 6543becf26fff612cdadeed7250ccc8d49f67f27 Mon Sep 17 00:00:00 2001 From: Andreas Schwab Date: Sun, 20 Jan 2013 17:58:47 +0100 Subject: mod/file2alias: make modalias generation safe for cross compiling Use the target compiler to compute the offsets for the fields of the device_id structures, so that it won't be broken by different alignments between the host and target ABIs. This also fixes missing endian corrections for some modaliases. Signed-off-by: Andreas Schwab Signed-off-by: Michal Marek --- include/linux/mod_devicetable.h | 58 +++++++---------------------------------- 1 file changed, 9 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index fed3def62818..779cf7c4a3d1 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -33,8 +33,7 @@ struct ieee1394_device_id { __u32 model_id; __u32 specifier_id; __u32 version; - kernel_ulong_t driver_data - __attribute__((aligned(sizeof(kernel_ulong_t)))); + kernel_ulong_t driver_data; }; @@ -148,8 +147,7 @@ struct hid_device_id { __u16 group; __u32 vendor; __u32 product; - kernel_ulong_t driver_data - __attribute__((aligned(sizeof(kernel_ulong_t)))); + kernel_ulong_t driver_data; }; /* s390 CCW devices */ @@ -173,8 +171,6 @@ struct ccw_device_id { struct ap_device_id { __u16 match_flags; /* which fields to match against */ __u8 dev_type; /* device type */ - __u8 pad1; - __u32 pad2; kernel_ulong_t driver_info; }; @@ -184,13 +180,10 @@ struct ap_device_id { struct css_device_id { __u8 match_flags; __u8 type; /* subchannel type */ - __u16 pad2; - __u32 pad3; kernel_ulong_t driver_data; }; -#define ACPI_ID_LEN 16 /* only 9 bytes needed here, 16 bytes are used */ - /* to workaround crosscompile issues */ +#define ACPI_ID_LEN 9 struct acpi_device_id { __u8 id[ACPI_ID_LEN]; @@ -231,11 +224,7 @@ struct of_device_id char name[32]; char type[32]; char compatible[128]; -#ifdef __KERNEL__ const void *data; -#else - kernel_ulong_t data; -#endif }; /* VIO */ @@ -260,24 +249,14 @@ struct pcmcia_device_id { /* for pseudo multi-function devices */ __u8 device_no; - __u32 prod_id_hash[4] - __attribute__((aligned(sizeof(__u32)))); + __u32 prod_id_hash[4]; /* not matched against in kernelspace*/ -#ifdef __KERNEL__ const char * prod_id[4]; -#else - kernel_ulong_t prod_id[4] - __attribute__((aligned(sizeof(kernel_ulong_t)))); -#endif /* not matched against */ kernel_ulong_t driver_info; -#ifdef __KERNEL__ char * cisfile; -#else - kernel_ulong_t cisfile; -#endif }; #define PCMCIA_DEV_ID_MATCH_MANF_ID 0x0001 @@ -373,8 +352,7 @@ struct sdio_device_id { __u8 class; /* Standard interface or SDIO_ANY_ID */ __u16 vendor; /* Vendor or SDIO_ANY_ID */ __u16 device; /* Device ID or SDIO_ANY_ID */ - kernel_ulong_t driver_data /* Data private to the driver */ - __attribute__((aligned(sizeof(kernel_ulong_t)))); + kernel_ulong_t driver_data; /* Data private to the driver */ }; /* SSB core, see drivers/ssb/ */ @@ -420,8 +398,7 @@ struct virtio_device_id { */ struct hv_vmbus_device_id { __u8 guid[16]; - kernel_ulong_t driver_data /* Data private to the driver */ - __attribute__((aligned(sizeof(kernel_ulong_t)))); + kernel_ulong_t driver_data; /* Data private to the driver */ }; /* rpmsg */ @@ -440,8 +417,7 @@ struct rpmsg_device_id { struct i2c_device_id { char name[I2C_NAME_SIZE]; - kernel_ulong_t driver_data /* Data private to the driver */ - __attribute__((aligned(sizeof(kernel_ulong_t)))); + kernel_ulong_t driver_data; /* Data private to the driver */ }; /* spi */ @@ -451,8 +427,7 @@ struct i2c_device_id { struct spi_device_id { char name[SPI_NAME_SIZE]; - kernel_ulong_t driver_data /* Data private to the driver */ - __attribute__((aligned(sizeof(kernel_ulong_t)))); + kernel_ulong_t driver_data; /* Data private to the driver */ }; /* dmi */ @@ -484,15 +459,6 @@ struct dmi_strmatch { char substr[79]; }; -#ifndef __KERNEL__ -struct dmi_system_id { - kernel_ulong_t callback; - kernel_ulong_t ident; - struct dmi_strmatch matches[4]; - kernel_ulong_t driver_data - __attribute__((aligned(sizeof(kernel_ulong_t)))); -}; -#else struct dmi_system_id { int (*callback)(const struct dmi_system_id *); const char *ident; @@ -506,7 +472,6 @@ struct dmi_system_id { * error: storage size of '__mod_dmi_device_table' isn't known */ #define dmi_device_id dmi_system_id -#endif #define DMI_MATCH(a, b) { a, b } @@ -515,8 +480,7 @@ struct dmi_system_id { struct platform_device_id { char name[PLATFORM_NAME_SIZE]; - kernel_ulong_t driver_data - __attribute__((aligned(sizeof(kernel_ulong_t)))); + kernel_ulong_t driver_data; }; #define MDIO_MODULE_PREFIX "mdio:" @@ -572,11 +536,7 @@ struct isapnp_device_id { struct amba_id { unsigned int id; unsigned int mask; -#ifndef __KERNEL__ - kernel_ulong_t data; -#else void *data; -#endif }; /* -- cgit v1.2.3 From c3ad83d9efdfe6a86efd44945a781f00c879b7b4 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 24 Jan 2013 23:24:56 -0500 Subject: quota: autoload the quota_v2 module for QFMT_VFS_V1 quota format Otherwise, ext4 file systems with the quota featured enable will get a very confusing "No such process" error message if the quota code is built as a module and the quota_v2 module has not been loaded. Signed-off-by: "Theodore Ts'o" Reviewed-by: Carlos Maiolino Acked-by: Jan Kara Cc: stable@vger.kernel.org --- include/linux/quota.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 58fdef125252..d13371134c59 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -405,6 +405,7 @@ struct quota_module_name { #define INIT_QUOTA_MODULE_NAMES {\ {QFMT_VFS_OLD, "quota_v1"},\ {QFMT_VFS_V0, "quota_v2"},\ + {QFMT_VFS_V1, "quota_v2"},\ {0, NULL}} #endif /* _QUOTA_ */ -- cgit v1.2.3 From e175435ed281d06ffd56d4edc8a2dd56f8672f07 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Fri, 25 Jan 2013 15:30:23 -0500 Subject: Revert "libata: export host controller number thru /sys" This reverts commit 1757d902b029a29dfcef63609964385cf8865b5a. Discussion continues upstream. --- include/linux/libata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 65ff67e34b77..91c9d109e5f1 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -546,7 +546,6 @@ struct ata_host { void *private_data; struct ata_port_operations *ops; unsigned long flags; - unsigned int host_id; /* user visible host ID */ struct mutex eh_mutex; struct task_struct *eh_owner; -- cgit v1.2.3 From 58d9a38f6facb28e935ec2747f6d9e9bf4684118 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 21 Jan 2013 13:20:51 -0800 Subject: PCI: Skip attaching driver in device_add() We want to add PCI devices to the device tree as early as possible but delay attaching drivers. device_add() adds a device to the device hierarchy and (via device_attach()) attaches a matching driver and calls its .probe() method. We want to separate adding the device to the hierarchy from attaching the driver. This patch does that by adding "match_driver" in struct pci_dev. When false, we return failure from pci_bus_match(), which makes device_attach() believe there's no matching driver. Later, we set "match_driver = true" and call device_attach() again, which now attaches the driver and calls its .probe() method. [bhelgaas: changelog, explicitly init dev->match_driver, fold device_attach() call into pci_bus_add_device()] Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 907b455ab603..8ee7e4e46539 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -286,6 +286,7 @@ struct pci_dev { unsigned int irq; struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */ + bool match_driver; /* Skip attaching driver */ /* These fields are used by common fixups */ unsigned int transparent:1; /* Transparent PCI bridge */ unsigned int multifunction:1;/* Part of multi-function device */ -- cgit v1.2.3 From c61a2810a2161986353705b44d9503e6bb079f4f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 28 Dec 2012 18:58:39 -0800 Subject: userns: Avoid recursion in put_user_ns When freeing a deeply nested user namespace free_user_ns calls put_user_ns on it's parent which may in turn call free_user_ns again. When -fno-optimize-sibling-calls is passed to gcc one stack frame per user namespace is left on the stack, potentially overflowing the kernel stack. CONFIG_FRAME_POINTER forces -fno-optimize-sibling-calls so we can't count on gcc to optimize this code. Remove struct kref and use a plain atomic_t. Making the code more flexible and easier to comprehend. Make the loop in free_user_ns explict to guarantee that the stack does not overflow with CONFIG_FRAME_POINTER enabled. I have tested this fix with a simple program that uses unshare to create a deeply nested user namespace structure and then calls exit. With 1000 nesteuser namespaces before this change running my test program causes the kernel to die a horrible death. With 10,000,000 nested user namespaces after this change my test program runs to completion and causes no harm. Acked-by: Serge Hallyn Pointed-out-by: Vasily Kulikov Signed-off-by: "Eric W. Biederman" --- include/linux/user_namespace.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index b9bd2e6c73cc..4ce009324933 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -21,7 +21,7 @@ struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; struct uid_gid_map projid_map; - struct kref kref; + atomic_t count; struct user_namespace *parent; kuid_t owner; kgid_t group; @@ -35,18 +35,18 @@ extern struct user_namespace init_user_ns; static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { if (ns) - kref_get(&ns->kref); + atomic_inc(&ns->count); return ns; } extern int create_user_ns(struct cred *new); extern int unshare_userns(unsigned long unshare_flags, struct cred **new_cred); -extern void free_user_ns(struct kref *kref); +extern void free_user_ns(struct user_namespace *ns); static inline void put_user_ns(struct user_namespace *ns) { - if (ns) - kref_put(&ns->kref, free_user_ns); + if (ns && atomic_dec_and_test(&ns->count)) + free_user_ns(ns); } struct seq_operations; -- cgit v1.2.3 From c7c9c56ca26f7b9458711b2d78b60b60e0d38ba7 Mon Sep 17 00:00:00 2001 From: Yang Zhang Date: Fri, 25 Jan 2013 10:18:51 +0800 Subject: x86, apicv: add virtual interrupt delivery support Virtual interrupt delivery avoids KVM to inject vAPIC interrupts manually, which is fully taken care of by the hardware. This needs some special awareness into existing interrupr injection path: - for pending interrupt, instead of direct injection, we may need update architecture specific indicators before resuming to guest. - A pending interrupt, which is masked by ISR, should be also considered in above update action, since hardware will decide when to inject it at right time. Current has_interrupt and get_interrupt only returns a valid vector from injection p.o.v. Reviewed-by: Marcelo Tosatti Signed-off-by: Kevin Tian Signed-off-by: Yang Zhang Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4dd7d7531e69..0350e0d5e031 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -123,6 +123,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_MASTERCLOCK_UPDATE 19 #define KVM_REQ_MCLOCK_INPROGRESS 20 #define KVM_REQ_EPR_EXIT 21 +#define KVM_REQ_EOIBITMAP 22 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -538,6 +539,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); void kvm_make_mclock_inprogress_request(struct kvm *kvm); +void kvm_make_update_eoibitmap_request(struct kvm *kvm); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -691,6 +693,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level); int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level); int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm, int irq_source_id, int level); +bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); -- cgit v1.2.3 From 0d1c28a449c6c23a126e3a08ee30914609aac227 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 28 Jan 2013 16:23:10 +0200 Subject: gpiolib-acpi: Add ACPI5 event model support to gpio. Add ability to handle ACPI events signalled by GPIO interrupts. ACPI5 platforms can use GPIO signaled ACPI events. These GPIO interrupts are handled by ACPI event methods which need to be called from the GPIO controller's interrupt handler. acpi_gpio_request_interrupt() finds out which gpio pins have acpi event methods and assigns interrupt handlers that calls the acpi event methods for those pins. Partially based on work by Rui Zhang Signed-off-by: Mathias Nyman Signed-off-by: Linus Walleij --- include/linux/acpi_gpio.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi_gpio.h b/include/linux/acpi_gpio.h index 91615a389b65..b76ebd08ff8e 100644 --- a/include/linux/acpi_gpio.h +++ b/include/linux/acpi_gpio.h @@ -2,10 +2,12 @@ #define _LINUX_ACPI_GPIO_H_ #include +#include #ifdef CONFIG_GPIO_ACPI int acpi_get_gpio(char *path, int pin); +void acpi_gpiochip_request_interrupts(struct gpio_chip *chip); #else /* CONFIG_GPIO_ACPI */ @@ -14,6 +16,8 @@ static inline int acpi_get_gpio(char *path, int pin) return -ENODEV; } +static inline void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) { } + #endif /* CONFIG_GPIO_ACPI */ #endif /* _LINUX_ACPI_GPIO_H_ */ -- cgit v1.2.3 From 595ad9af8584908ea5fb698b836169d05b99f186 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:09 -0800 Subject: memblock: Add memblock_mem_size() Use it to get mem size under the limit_pfn. to replace local version in x86 reserved_initrd. -v2: remove not needed cast that is pointed out by HPA. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-29-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- include/linux/memblock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index d452ee191066..f388203db7e8 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -155,6 +155,7 @@ phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr); phys_addr_t memblock_phys_mem_size(void); +phys_addr_t memblock_mem_size(unsigned long limit_pfn); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); -- cgit v1.2.3 From 0212f9159694be61c6bc52e925fa76643e0c1abf Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:11 -0800 Subject: x86: Add Crash kernel low reservation During kdump kernel's booting stage, it need to find low ram for swiotlb buffer when system does not support intel iommu/dmar remapping. kexed-tools is appending memmap=exactmap and range from /proc/iomem with "Crash kernel", and that range is above 4G for 64bit after boot protocol 2.12. We need to add another range in /proc/iomem like "Crash kernel low", so kexec-tools could find that info and append to kdump kernel command line. Try to reserve some under 4G if the normal "Crash kernel" is above 4G. User could specify the size with crashkernel_low=XX[KMG]. -v2: fix warning that is found by Fengguang's test robot. -v3: move out get_mem_size change to another patch, to solve compiling warning that is found by Borislav Petkov -v4: user must specify crashkernel_low if system does not support intel or amd iommu. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-31-git-send-email-yinghai@kernel.org Cc: Eric Biederman Cc: Rob Landley Signed-off-by: H. Peter Anvin --- include/linux/kexec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d0b8458a703a..d2e6927bbaae 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -191,6 +191,7 @@ extern struct kimage *kexec_crash_image; /* Location of a reserved region to hold the crash kernel. */ extern struct resource crashk_res; +extern struct resource crashk_low_res; typedef u32 note_buf_t[KEXEC_NOTE_BYTES/4]; extern note_buf_t __percpu *crash_notes; extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; @@ -199,6 +200,8 @@ extern size_t vmcoreinfo_max_size; int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); +int parse_crashkernel_low(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base); int crash_shrink_memory(unsigned long new_size); size_t crash_get_memory_size(void); void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); -- cgit v1.2.3 From 38fa4175e60d98fb1c9815fb14f8057576dade73 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:15 -0800 Subject: mm: Add alloc_bootmem_low_pages_nopanic() We don't need to panic in some case, like for swiotlb preallocating. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-35-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- include/linux/bootmem.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 3f778c27f825..3cd16ba82f15 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -99,6 +99,9 @@ void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat, extern void *__alloc_bootmem_low(unsigned long size, unsigned long align, unsigned long goal); +void *__alloc_bootmem_low_nopanic(unsigned long size, + unsigned long align, + unsigned long goal); extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, unsigned long align, @@ -132,6 +135,8 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #define alloc_bootmem_low(x) \ __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) +#define alloc_bootmem_low_pages_nopanic(x) \ + __alloc_bootmem_low_nopanic(x, PAGE_SIZE, 0) #define alloc_bootmem_low_pages(x) \ __alloc_bootmem_low(x, PAGE_SIZE, 0) #define alloc_bootmem_low_pages_node(pgdat, x) \ -- cgit v1.2.3 From ac2cbab21f318e19bc176a7f38a120cec835220f Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:16 -0800 Subject: x86: Don't panic if can not alloc buffer for swiotlb Normal boot path on system with iommu support: swiotlb buffer will be allocated early at first and then try to initialize iommu, if iommu for intel or AMD could setup properly, swiotlb buffer will be freed. The early allocating is with bootmem, and could panic when we try to use kdump with buffer above 4G only, or with memmap to limit mem under 4G. for example: memmap=4095M$1M to remove memory under 4G. According to Eric, add _nopanic version and no_iotlb_memory to fail map single later if swiotlb is still needed. -v2: don't pass nopanic, and use -ENOMEM return value according to Eric. panic early instead of using swiotlb_full to panic...according to Eric/Konrad. -v3: make swiotlb_init to be notpanic, but will affect: arm64, ia64, powerpc, tile, unicore32, x86. -v4: cleanup swiotlb_init by removing swiotlb_init_with_default_size. Suggested-by: Eric W. Biederman Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-36-git-send-email-yinghai@kernel.org Reviewed-and-tested-by: Konrad Rzeszutek Wilk Cc: Joerg Roedel Cc: Ralf Baechle Cc: Jeremy Fitzhardinge Cc: Kyungmin Park Cc: Marek Szyprowski Cc: Arnd Bergmann Cc: Andrzej Pietrasiewicz Cc: linux-mips@linux-mips.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: Shuah Khan Signed-off-by: H. Peter Anvin --- include/linux/swiotlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 071d62c214a6..2de42f9401d2 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -23,7 +23,7 @@ extern int swiotlb_force; #define IO_TLB_SHIFT 11 extern void swiotlb_init(int verbose); -extern void swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); +int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); extern unsigned long swiotlb_nr_tbl(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); -- cgit v1.2.3 From 6e69ab1361c44e3ee1398158b56d114b1aef8179 Mon Sep 17 00:00:00 2001 From: Florian Vaussard Date: Mon, 28 Jan 2013 15:00:57 +0100 Subject: pwm: Add pwm_can_sleep() as exported API to users Calls to some external PWM chips can sleep. To help users, add pwm_can_sleep() API. Cc: Thierry Reding Cc: Peter Ujfalusi Signed-off-by: Florian Vaussard Reviewed-by: Peter Ujfalusi Signed-off-by: Thierry Reding --- include/linux/pwm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 6d661f32e0e4..3fef47733ea3 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -146,6 +146,8 @@ struct pwm_ops { * @base: number of first PWM controlled by this chip * @npwm: number of PWMs controlled by this chip * @pwms: array of PWM devices allocated by the framework + * @can_sleep: must be true if the .config(), .enable() or .disable() + * operations may sleep */ struct pwm_chip { struct device *dev; @@ -159,6 +161,7 @@ struct pwm_chip { struct pwm_device * (*of_xlate)(struct pwm_chip *pc, const struct of_phandle_args *args); unsigned int of_pwm_n_cells; + bool can_sleep; }; #if IS_ENABLED(CONFIG_PWM) @@ -179,6 +182,8 @@ void pwm_put(struct pwm_device *pwm); struct pwm_device *devm_pwm_get(struct device *dev, const char *consumer); void devm_pwm_put(struct device *dev, struct pwm_device *pwm); + +bool pwm_can_sleep(struct pwm_device *pwm); #else static inline int pwm_set_chip_data(struct pwm_device *pwm, void *data) { @@ -226,6 +231,11 @@ static inline struct pwm_device *devm_pwm_get(struct device *dev, static inline void devm_pwm_put(struct device *dev, struct pwm_device *pwm) { } + +static inline bool pwm_can_sleep(struct pwm_device *pwm) +{ + return false; +} #endif struct pwm_lookup { -- cgit v1.2.3 From 7c9c003c68de51fb8712a01e904444ef40c742f5 Mon Sep 17 00:00:00 2001 From: Myron Stowe Date: Fri, 25 Jan 2013 17:55:39 -0700 Subject: PCI: Introduce accessor to retrieve PCIe Capabilities Register Provide an accessor to retrieve the PCI Express device's Capabilities Register. Signed-off-by: Myron Stowe Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 15472d691ee6..78581e1d3f64 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1692,6 +1692,15 @@ static inline bool pci_is_pcie(struct pci_dev *dev) return !!pci_pcie_cap(dev); } +/** + * pcie_caps_reg - get the PCIe Capabilities Register + * @dev: PCI device + */ +static inline u16 pcie_caps_reg(const struct pci_dev *dev) +{ + return dev->pcie_flags_reg; +} + /** * pci_pcie_type - get the PCIe device/port type * @dev: PCI device -- cgit v1.2.3 From 1c531d82ee1a220ae7132ba0eb31edaf186b56d1 Mon Sep 17 00:00:00 2001 From: Myron Stowe Date: Fri, 25 Jan 2013 17:55:45 -0700 Subject: PCI: Use PCI Express Capability accessor Use PCI Express Capability access functions to simplify device Capabilities Register usages. Signed-off-by: Myron Stowe Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 78581e1d3f64..63b36281afce 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1707,7 +1707,7 @@ static inline u16 pcie_caps_reg(const struct pci_dev *dev) */ static inline int pci_pcie_type(const struct pci_dev *dev) { - return (dev->pcie_flags_reg & PCI_EXP_FLAGS_TYPE) >> 4; + return (pcie_caps_reg(dev) & PCI_EXP_FLAGS_TYPE) >> 4; } void pci_request_acs(void); -- cgit v1.2.3 From 9ea6cdac9ba5fbc65adde4dc6a3cbee1206508df Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 21 Dec 2012 01:43:55 -0800 Subject: leds: leds-pwm: Convert to use devm_get_pwm Update the driver to use the new API for requesting pwm so we can take advantage of the pwm_lookup table to find the correct pwm to be used for the LED functionality. Signed-off-by: Peter Ujfalusi Signed-off-by: Bryan Wu --- include/linux/leds_pwm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/leds_pwm.h b/include/linux/leds_pwm.h index 33a071167489..a65e9646e4b1 100644 --- a/include/linux/leds_pwm.h +++ b/include/linux/leds_pwm.h @@ -7,7 +7,7 @@ struct led_pwm { const char *name; const char *default_trigger; - unsigned pwm_id; + unsigned pwm_id __deprecated; u8 active_low; unsigned max_brightness; unsigned pwm_period_ns; -- cgit v1.2.3 From d4c0c4705bef1134339b038872ece3705a2783e0 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 21 Dec 2012 01:43:57 -0800 Subject: pwm: Correct parameter name in header for *pwm_get() functions To synchronize the header file definition and the actual code. In the code the consumer parameter is named as con_id, change the header file and replace consumer -> con_id in the parameter list. Signed-off-by: Peter Ujfalusi Ackedy-by: Thierry Reding Signed-off-by: Bryan Wu --- include/linux/pwm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 6d661f32e0e4..cc908a5396f8 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -174,10 +174,10 @@ struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, struct pwm_device *of_pwm_xlate_with_flags(struct pwm_chip *pc, const struct of_phandle_args *args); -struct pwm_device *pwm_get(struct device *dev, const char *consumer); +struct pwm_device *pwm_get(struct device *dev, const char *con_id); void pwm_put(struct pwm_device *pwm); -struct pwm_device *devm_pwm_get(struct device *dev, const char *consumer); +struct pwm_device *devm_pwm_get(struct device *dev, const char *con_id); void devm_pwm_put(struct device *dev, struct pwm_device *pwm); #else static inline int pwm_set_chip_data(struct pwm_device *pwm, void *data) -- cgit v1.2.3 From 8eb9612799605a7988d1c97cdc5980a5b8f04c56 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 21 Dec 2012 01:43:58 -0800 Subject: pwm: core: Rename of_pwm_request() to of_pwm_get() and export it Allow client driver to use of_pwm_get() to get the PWM they need. This is needed for drivers which handle more than one PWM separately, like leds-pwm driver, which have: pwmleds { compatible = "pwm-leds"; kpad { label = "omap4::keypad"; pwms = <&twl_pwm 0 7812500>; max-brightness = <127>; }; charging { label = "omap4:green:chrg"; pwms = <&twl_pwmled 0 7812500>; max-brightness = <255>; }; }; in the dts files. Signed-off-by: Peter Ujfalusi Acked-by: Thierry Reding Signed-off-by: Bryan Wu --- include/linux/pwm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index cc908a5396f8..76a1959f2b23 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -175,6 +175,7 @@ struct pwm_device *of_pwm_xlate_with_flags(struct pwm_chip *pc, const struct of_phandle_args *args); struct pwm_device *pwm_get(struct device *dev, const char *con_id); +struct pwm_device *of_pwm_get(struct device_node *np, const char *con_id); void pwm_put(struct pwm_device *pwm); struct pwm_device *devm_pwm_get(struct device *dev, const char *con_id); @@ -213,6 +214,12 @@ static inline struct pwm_device *pwm_get(struct device *dev, return ERR_PTR(-ENODEV); } +static inline struct pwm_device *of_pwm_get(struct device_node *np, + const char *con_id) +{ + return ERR_PTR(-ENODEV); +} + static inline void pwm_put(struct pwm_device *pwm) { } -- cgit v1.2.3 From 261a5edd3ac77ecb4b33310a1dd1ed8d656f0569 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 21 Dec 2012 01:43:59 -0800 Subject: pwm: Add devm_of_pwm_get() as exported API for users When booted with DT users can use devm version of of_pwm_get() to benefit from automatic resource release. Signed-off-by: Peter Ujfalusi Acked-by: Thierry Reding Signed-off-by: Bryan Wu --- include/linux/pwm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 76a1959f2b23..70655a205b74 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -179,6 +179,8 @@ struct pwm_device *of_pwm_get(struct device_node *np, const char *con_id); void pwm_put(struct pwm_device *pwm); struct pwm_device *devm_pwm_get(struct device *dev, const char *con_id); +struct pwm_device *devm_of_pwm_get(struct device *dev, struct device_node *np, + const char *con_id); void devm_pwm_put(struct device *dev, struct pwm_device *pwm); #else static inline int pwm_set_chip_data(struct pwm_device *pwm, void *data) @@ -230,6 +232,13 @@ static inline struct pwm_device *devm_pwm_get(struct device *dev, return ERR_PTR(-ENODEV); } +static inline struct pwm_device *devm_of_pwm_get(struct device *dev, + struct device_node *np, + const char *con_id) +{ + return ERR_PTR(-ENODEV); +} + static inline void devm_pwm_put(struct device *dev, struct pwm_device *pwm) { } -- cgit v1.2.3 From eaca6eae3e0c41d41fcb9d1d70e00934988dff2e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 25 Nov 2012 23:12:10 -0500 Subject: sanitize rt_sigaction() situation a bit Switch from __ARCH_WANT_SYS_RT_SIGACTION to opposite (!CONFIG_ODD_RT_SIGACTION); the only two architectures that need it are alpha and sparc. The reason for use of CONFIG_... instead of __ARCH_... is that it's needed only kernel-side and doing it that way avoids a mess with include order on many architectures. Signed-off-by: Al Viro --- include/linux/syscalls.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 45e2db270255..75defcd1c276 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -377,6 +377,12 @@ asmlinkage long sys_init_module(void __user *umod, unsigned long len, asmlinkage long sys_delete_module(const char __user *name_user, unsigned int flags); +#ifndef CONFIG_ODD_RT_SIGACTION +asmlinkage long sys_rt_sigaction(int, + const struct sigaction __user *, + struct sigaction __user *, + size_t); +#endif asmlinkage long sys_rt_sigprocmask(int how, sigset_t __user *set, sigset_t __user *oset, size_t sigsetsize); asmlinkage long sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize); -- cgit v1.2.3 From 322a56cb1fcbe228eee5cdb8a9c6df9f797d998c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 25 Dec 2012 13:32:58 -0500 Subject: generic compat_sys_rt_sigprocmask() conditional on GENERIC_COMPAT_RT_SIGPROCMASK; by the end of that series it will become the same thing as COMPAT and conditional will die out. Signed-off-by: Al Viro --- include/linux/compat.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index dec7e2d18875..9d3c2a98d537 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -401,7 +401,8 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); extern int compat_printk(const char *fmt, ...); -extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat); +extern void sigset_from_compat(sigset_t *set, const compat_sigset_t *compat); +extern void sigset_to_compat(compat_sigset_t *compat, const sigset_t *set); asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes, @@ -592,6 +593,11 @@ asmlinkage long compat_sys_rt_sigtimedwait(compat_sigset_t __user *uthese, struct compat_timespec __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat_size_t sigsetsize); +#ifdef CONFIG_GENERIC_COMPAT_RT_SIGPROCMASK +asmlinkage long compat_sys_rt_sigprocmask(int how, compat_sigset_t __user *set, + compat_sigset_t __user *oset, + compat_size_t sigsetsize); +#endif asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info); asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); -- cgit v1.2.3 From fe9c1db2cfc363cd30ecfe6480481b280abf8c0a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 25 Dec 2012 14:31:38 -0500 Subject: generic compat_sys_rt_sigpending() conditional on GENERIC_COMPAT_RT_SIGPENDING; by the end of that series it will become the same thing as COMPAT and conditional will die out. Signed-off-by: Al Viro --- include/linux/compat.h | 4 ++++ include/linux/signal.h | 1 - 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 9d3c2a98d537..75548a43a1c5 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -598,6 +598,10 @@ asmlinkage long compat_sys_rt_sigprocmask(int how, compat_sigset_t __user *set, compat_sigset_t __user *oset, compat_size_t sigsetsize); #endif +#ifdef CONFIG_GENERIC_COMPAT_RT_SIGPENDING +asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, + compat_size_t sigsetsize); +#endif asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info); asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); diff --git a/include/linux/signal.h b/include/linux/signal.h index 0a89ffc48466..786bd99fde65 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -243,7 +243,6 @@ extern int group_send_sig_info(int sig, struct siginfo *info, struct task_struct extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *); extern long do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info); -extern long do_sigpending(void __user *, unsigned long); extern int do_sigtimedwait(const sigset_t *, siginfo_t *, const struct timespec *); extern int sigprocmask(int, sigset_t *, sigset_t *); -- cgit v1.2.3 From 75907d4d7bc5d79b82d1453d9689efc588de1b43 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 25 Dec 2012 15:19:12 -0500 Subject: generic compat_sys_rt_sigqueueinfo() conditional on GENERIC_COMPAT_RT_SIGQUEUEINFO; by the end of that series it will become the same thing as COMPAT and conditional will die out. Signed-off-by: Al Viro --- include/linux/compat.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 75548a43a1c5..bbee15ef3ae9 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -602,6 +602,10 @@ asmlinkage long compat_sys_rt_sigprocmask(int how, compat_sigset_t __user *set, asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, compat_size_t sigsetsize); #endif +#ifdef CONFIG_GENERIC_COMPAT_RT_SIGQUEUEINFO +asmlinkage long compat_sys_rt_sigqueueinfo(compat_pid_t pid, int sig, + struct compat_siginfo __user *uinfo); +#endif asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info); asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); -- cgit v1.2.3 From 0a0e8cdf734ce723bfc4ca6032ffbc03ce17c642 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 25 Dec 2012 16:04:12 -0500 Subject: old sigsuspend variants in kernel/signal.c conditional on OLD_SIGSUSPEND/OLD_SIGSUSPEND3, depending on which variety of that fossil is needed. Signed-off-by: Al Viro --- include/linux/syscalls.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 75defcd1c276..d2dd2f63d220 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -377,6 +377,14 @@ asmlinkage long sys_init_module(void __user *umod, unsigned long len, asmlinkage long sys_delete_module(const char __user *name_user, unsigned int flags); +#ifdef CONFIG_OLD_SIGSUSPEND +asmlinkage long sys_sigsuspend(old_sigset_t mask); +#endif + +#ifdef CONFIG_OLD_SIGSUSPEND3 +asmlinkage long sys_sigsuspend(int unused1, int unused2, old_sigset_t mask); +#endif + #ifndef CONFIG_ODD_RT_SIGACTION asmlinkage long sys_rt_sigaction(int, const struct sigaction __user *, -- cgit v1.2.3 From 9aae8fc05d2d130797be436eb7cae29c32710193 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 24 Dec 2012 23:12:04 -0500 Subject: switch rt_tgsigqueueinfo to COMPAT_SYSCALL_DEFINE C ABI violations on sparc, ppc and mips Signed-off-by: Al Viro --- include/linux/signal.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 786bd99fde65..ed1e71f1aac7 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -241,8 +241,6 @@ extern int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, bool group); extern int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p); extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *); -extern long do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, - siginfo_t *info); extern int do_sigtimedwait(const sigset_t *, siginfo_t *, const struct timespec *); extern int sigprocmask(int, sigset_t *, sigset_t *); -- cgit v1.2.3 From 92a3ce4a1e0047215aa0a0b30cc333bd32b866a8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 25 Nov 2012 21:20:05 -0500 Subject: consolidate declarations of k_sigaction Only alpha and sparc are unusual - they have ka_restorer in it. And nobody needs that exposed to userland. Signed-off-by: Al Viro --- include/linux/signal.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index ed1e71f1aac7..01451a156ff7 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -249,6 +249,13 @@ extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; extern int sigsuspend(sigset_t *); +struct k_sigaction { + struct sigaction sa; +#ifdef __ARCH_HAS_KA_RESTORER + __sigrestore_t ka_restorer; +#endif +}; + extern int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct pt_regs *regs, void *cookie); extern void signal_delivered(int sig, siginfo_t *info, struct k_sigaction *ka, struct pt_regs *regs, int stepping); extern void exit_signals(struct task_struct *tsk); -- cgit v1.2.3 From 574c4866e33d648520a8bd5bf6f573ea6e554e88 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 25 Nov 2012 22:24:19 -0500 Subject: consolidate kernel-side struct sigaction declarations Signed-off-by: Al Viro --- include/linux/signal.h | 14 ++++++++++++++ include/linux/syscalls.h | 2 +- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 01451a156ff7..0b6878e882da 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -249,6 +249,20 @@ extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; extern int sigsuspend(sigset_t *); +struct sigaction { +#ifndef __ARCH_HAS_ODD_SIGACTION + __sighandler_t sa_handler; + unsigned long sa_flags; +#else + unsigned long sa_flags; + __sighandler_t sa_handler; +#endif +#ifdef __ARCH_HAS_SA_RESTORER + __sigrestore_t sa_restorer; +#endif + sigset_t sa_mask; /* mask last for extensibility */ +}; + struct k_sigaction { struct sigaction sa; #ifdef __ARCH_HAS_KA_RESTORER diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index d2dd2f63d220..1c4938bf901e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -68,11 +68,11 @@ struct sigaltstack; #include #include #include +#include #include #include #include #include -#include #include #include #include -- cgit v1.2.3 From 08d32fe504a7670cab3190c624448695adcf70e4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 25 Dec 2012 18:38:15 -0500 Subject: generic sys_compat_rt_sigaction() Again, protected by a temporary config symbol (GENERIC_COMPAT_RT_SIGACTION); will be gone by the end of series. Signed-off-by: Al Viro --- include/linux/compat.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index bbee15ef3ae9..0d53ab4f79c5 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -142,6 +142,22 @@ typedef struct { compat_sigset_word sig[_COMPAT_NSIG_WORDS]; } compat_sigset_t; +#ifdef CONFIG_GENERIC_COMPAT_RT_SIGACTION +struct compat_sigaction { +#ifndef __ARCH_HAS_ODD_SIGACTION + compat_uptr_t sa_handler; + compat_ulong_t sa_flags; +#else + compat_ulong_t sa_flags; + compat_uptr_t sa_handler; +#endif +#ifdef __ARCH_HAS_SA_RESTORER + compat_uptr_t sa_restorer; +#endif + compat_sigset_t sa_mask __packed; +}; +#endif + /* * These functions operate strictly on struct compat_time* */ @@ -602,6 +618,14 @@ asmlinkage long compat_sys_rt_sigprocmask(int how, compat_sigset_t __user *set, asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, compat_size_t sigsetsize); #endif +#ifndef CONFIG_ODD_RT_SIGACTION +#ifdef CONFIG_GENERIC_COMPAT_RT_SIGACTION +asmlinkage long compat_sys_rt_sigaction(int, + const struct compat_sigaction __user *, + struct compat_sigaction __user *, + compat_size_t); +#endif +#endif #ifdef CONFIG_GENERIC_COMPAT_RT_SIGQUEUEINFO asmlinkage long compat_sys_rt_sigqueueinfo(compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); -- cgit v1.2.3 From 495dfbf767553980dbd40a19a96a8ca5fa1be616 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 25 Dec 2012 19:09:45 -0500 Subject: generic sys_sigaction() and compat_sys_sigaction() conditional on OLD_SIGACTION/COMPAT_OLD_SIGACTION Signed-off-by: Al Viro --- include/linux/compat.h | 14 ++++++++++++++ include/linux/signal.h | 9 +++++++++ include/linux/syscalls.h | 5 +++++ 3 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 0d53ab4f79c5..e20b8b404ae9 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -299,6 +299,15 @@ struct compat_robust_list_head { compat_uptr_t list_op_pending; }; +#ifdef CONFIG_COMPAT_OLD_SIGACTION +struct compat_old_sigaction { + compat_uptr_t sa_handler; + compat_old_sigset_t sa_mask; + compat_ulong_t sa_flags; + compat_uptr_t sa_restorer; +}; +#endif + struct compat_statfs; struct compat_statfs64; struct compat_old_linux_dirent; @@ -383,6 +392,11 @@ int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); +#ifdef CONFIG_COMPAT_OLD_SIGACTION +asmlinkage long compat_sys_sigaction(int sig, + const struct compat_old_sigaction __user *act, + struct compat_old_sigaction __user *oact); +#endif static inline int compat_timeval_compare(struct compat_timeval *lhs, struct compat_timeval *rhs) diff --git a/include/linux/signal.h b/include/linux/signal.h index 0b6878e882da..e28e8d455d6e 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -269,6 +269,15 @@ struct k_sigaction { __sigrestore_t ka_restorer; #endif }; + +#ifdef CONFIG_OLD_SIGACTION +struct old_sigaction { + __sighandler_t sa_handler; + old_sigset_t sa_mask; + unsigned long sa_flags; + __sigrestore_t sa_restorer; +}; +#endif extern int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct pt_regs *regs, void *cookie); extern void signal_delivered(int sig, siginfo_t *info, struct k_sigaction *ka, struct pt_regs *regs, int stepping); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1c4938bf901e..02b045012785 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -385,6 +385,11 @@ asmlinkage long sys_sigsuspend(old_sigset_t mask); asmlinkage long sys_sigsuspend(int unused1, int unused2, old_sigset_t mask); #endif +#ifdef CONFIG_OLD_SIGACTION +asmlinkage long sys_sigaction(int, const struct old_sigaction __user *, + struct old_sigaction __user *); +#endif + #ifndef CONFIG_ODD_RT_SIGACTION asmlinkage long sys_rt_sigaction(int, const struct sigaction __user *, -- cgit v1.2.3 From f482e1b4a4abf926507a4c1c6317acd3e7aa61b7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 25 Dec 2012 20:24:38 -0500 Subject: switch compat_sys_open* to COMPAT_SYSCALL_DEFINE --- include/linux/compat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index e20b8b404ae9..8de903587fb9 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -534,7 +534,7 @@ asmlinkage long compat_sys_vmsplice(int fd, const struct compat_iovec __user *, unsigned int nr_segs, unsigned int flags); asmlinkage long compat_sys_open(const char __user *filename, int flags, umode_t mode); -asmlinkage long compat_sys_openat(unsigned int dfd, const char __user *filename, +asmlinkage long compat_sys_openat(int dfd, const char __user *filename, int flags, umode_t mode); asmlinkage long compat_sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, -- cgit v1.2.3 From ca86b5dce213f52c7538932740f83cafb2c34547 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 7 Nov 2012 15:09:38 -0500 Subject: new helper: get_signal() On success get_signal_to_deliver() fills k_sigaction and siginfo. _All_ users pass it addresses of the local variables sitting in the same function. Then they proceed to pass those addresses pretty much in tandem to a bunch of helper functions; again, all callers of those helpers are passing them such a pair, and one that had been through get_signal_to_deliver() at that. The obvious cleanup: introduce a new type that would contain a pair (struct ksignal) and begin switching to using it. Turns out that it's convenient to store the signal number in the same object. New helper, taking that sucker is a wrapper for get_signal_to_deliver(); takes struct ksignal * and returns bool. On success fills ksignal with the information for signal handler to be invoked. For now it's a macro (to avoid header ordering headache), but eventually it'll be a function in kernel/signal.c, with get_signal_to_deliver() folded into it. Signed-off-by: Al Viro --- include/linux/signal.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index e28e8d455d6e..7c2744198dba 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -279,10 +279,28 @@ struct old_sigaction { }; #endif +struct ksignal { + struct k_sigaction ka; + siginfo_t info; + int sig; +}; + extern int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct pt_regs *regs, void *cookie); extern void signal_delivered(int sig, siginfo_t *info, struct k_sigaction *ka, struct pt_regs *regs, int stepping); extern void exit_signals(struct task_struct *tsk); +/* + * Eventually that'll replace get_signal_to_deliver(); macro for now, + * to avoid nastiness with include order. + */ +#define get_signal(ksig) \ +({ \ + struct ksignal *p = (ksig); \ + p->sig = get_signal_to_deliver(&p->info, &p->ka, \ + signal_pt_regs(), NULL);\ + p->sig > 0; \ +}) + extern struct kmem_cache *sighand_cachep; int unhandled_signal(struct task_struct *tsk, int sig); -- cgit v1.2.3 From 2ce5da17570771330f44ac993b77749debf7954b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 7 Nov 2012 15:11:25 -0500 Subject: new helper: signal_setup_done() usual "call force_sigsegv or signal_delivered" logics. Takes ksignal instead of separate siginfo/k_sigaction. Signed-off-by: Al Viro --- include/linux/signal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 7c2744198dba..a2dcb94ea49d 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -286,6 +286,7 @@ struct ksignal { }; extern int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct pt_regs *regs, void *cookie); +extern void signal_setup_done(int failed, struct ksignal *ksig, int stepping); extern void signal_delivered(int sig, siginfo_t *info, struct k_sigaction *ka, struct pt_regs *regs, int stepping); extern void exit_signals(struct task_struct *tsk); -- cgit v1.2.3 From 5a1b98d3096f1d780045f9be812335ad77aed93d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 6 Nov 2012 13:28:21 -0500 Subject: new helper: sigsp() Normal logics for altstack handling in sigframe allocation Signed-off-by: Al Viro --- include/linux/sched.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6fc8f45de4e9..8f983293b403 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2305,6 +2305,17 @@ static inline int sas_ss_flags(unsigned long sp) : on_sig_stack(sp) ? SS_ONSTACK : 0); } +static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) +{ + if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp)) +#ifdef CONFIG_STACK_GROWSUP + return current->sas_ss_sp; +#else + return current->sas_ss_sp + current->sas_ss_size; +#endif + return sp; +} + /* * Routines for handling mm_structs */ -- cgit v1.2.3 From 0aa0203fb43f04714004b2c4ad33b858e240555d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 25 Nov 2012 02:30:08 -0500 Subject: take sys_rt_sigsuspend() prototype to linux/syscalls.h Signed-off-by: Al Viro --- include/linux/syscalls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 02b045012785..66d298f69f98 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -385,6 +385,8 @@ asmlinkage long sys_sigsuspend(old_sigset_t mask); asmlinkage long sys_sigsuspend(int unused1, int unused2, old_sigset_t mask); #endif +asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize); + #ifdef CONFIG_OLD_SIGACTION asmlinkage long sys_sigaction(int, const struct old_sigaction __user *, struct old_sigaction __user *); -- cgit v1.2.3 From bf22433575ef30a4807f0620498017df0f27df67 Mon Sep 17 00:00:00 2001 From: Philip Avinash Date: Fri, 4 Jan 2013 13:26:50 +0530 Subject: mtd: devices: elm: Add support for ELM error correction The ELM hardware module can be used to speedup BCH 4/8/16 ECC scheme error correction. For now only 4 & 8 bit support is added Signed-off-by: Philip Avinash Signed-off-by: Artem Bityutskiy --- include/linux/platform_data/elm.h | 53 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) create mode 100644 include/linux/platform_data/elm.h (limited to 'include/linux') diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h new file mode 100644 index 000000000000..11ab6aaf2431 --- /dev/null +++ b/include/linux/platform_data/elm.h @@ -0,0 +1,53 @@ +/* + * BCH Error Location Module + * + * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef __ELM_H +#define __ELM_H + +enum bch_ecc { + BCH4_ECC = 0, + BCH8_ECC, +}; + +/* ELM support 8 error syndrome process */ +#define ERROR_VECTOR_MAX 8 + +#define BCH8_ECC_OOB_BYTES 13 +#define BCH4_ECC_OOB_BYTES 7 +/* RBL requires 14 byte even though BCH8 uses only 13 byte */ +#define BCH8_SIZE (BCH8_ECC_OOB_BYTES + 1) +#define BCH4_SIZE (BCH4_ECC_OOB_BYTES) + +/** + * struct elm_errorvec - error vector for elm + * @error_reported: set true for vectors error is reported + * @error_uncorrectable: number of uncorrectable errors + * @error_count: number of correctable errors in the sector + * @error_loc: buffer for error location + * + */ +struct elm_errorvec { + bool error_reported; + bool error_uncorrectable; + int error_count; + int error_loc[ERROR_VECTOR_MAX]; +}; + +void elm_decode_bch_error_page(struct device *dev, u8 *ecc_calc, + struct elm_errorvec *err_vec); +void elm_config(struct device *dev, enum bch_ecc bch_type); +#endif /* __ELM_H */ -- cgit v1.2.3 From 62116e5171e00f85a8d53f76e45b84423c89ff34 Mon Sep 17 00:00:00 2001 From: Philip Avinash Date: Fri, 4 Jan 2013 13:26:51 +0530 Subject: mtd: nand: omap2: Support for hardware BCH error correction. ELM module can be used for hardware error correction of BCH 4 & 8 bit. ELM module functionality is verified by checking the availability of handle for ELM module in device tree. Hence supporting 1. ELM module available, BCH error correction done by ELM module. Also support read & write page in one shot by adding custom read_page and write_page methods. This helps in optimizing code for NAND flashes with page size less than 4 KB. 2. If ELM module not available fall back to software BCH error correction support. New structure member is added to omap_nand_info 1. "is_elm_used" to know the status of whether the ELM module is used for error correction or not. 2. "elm_dev" device pointer to elm device on detection of ELM module. Also being here update the device tree documentation of gpmc-nand for adding optional property elm_id. Note: ECC layout uses 1 extra bytes for 512 byte of data to handle erased pages. Extra byte programmed to zero for programmed pages. Also BCH8 requires 14 byte ecc to maintain compatibility with RBL ECC layout. This results a common ecc layout across RBL, U-boot & Linux with BCH8. Signed-off-by: Philip Avinash Signed-off-by: Artem Bityutskiy --- include/linux/platform_data/elm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h index 11ab6aaf2431..1bd5244d1dcd 100644 --- a/include/linux/platform_data/elm.h +++ b/include/linux/platform_data/elm.h @@ -30,7 +30,8 @@ enum bch_ecc { #define BCH4_ECC_OOB_BYTES 7 /* RBL requires 14 byte even though BCH8 uses only 13 byte */ #define BCH8_SIZE (BCH8_ECC_OOB_BYTES + 1) -#define BCH4_SIZE (BCH4_ECC_OOB_BYTES) +/* Uses 1 extra byte to handle erased pages */ +#define BCH4_SIZE (BCH4_ECC_OOB_BYTES + 1) /** * struct elm_errorvec - error vector for elm -- cgit v1.2.3 From a2f74a7dacc1c17a0b146eb3112217874c5db436 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 6 Jan 2013 21:28:50 +0100 Subject: mtd: bcm47xxsflash: add own struct for abstrating bus type MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki --- include/linux/bcma/bcma_driver_chipcommon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 9a0e3fa3ca95..a5bfda6b0a76 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -528,6 +528,7 @@ struct bcma_sflash { u32 size; struct mtd_info *mtd; + void *priv; }; #endif -- cgit v1.2.3 From 1648eaaa1575ea686acb82fb8cb3d8839764ef2c Mon Sep 17 00:00:00 2001 From: Stefan Roese Date: Fri, 18 Jan 2013 13:10:05 +0100 Subject: mtd: cfi_cmdset_0002: Support Persistent Protection Bits (PPB) locking Currently cfi_cmdset_0002.c does not support PPB locking of sectors. This patch adds support for this locking/unlocking mechanism. It is needed on some platforms, since newer U-Boot versions do support this PPB locking and protect for example their environment sector(s) this way. This PPB locking/unlocking will be enabled for all devices supported by cfi_cmdset_0002 reporting 8 in the CFI word 0x49 (Sector Protect/Unprotect scheme). Please note that PPB locking does support sector-by-sector locking. But the whole chip can only be unlocked together. So unlocking one sector will automatically unlock all sectors of this device. Because of this chip limitation, the PPB unlocking function saves the current locking status of all sectors before unlocking the whole device. After unlocking the saved locking status is re-configured. This way only the addressed sectors will be unlocked. To selectively enable this advanced sector protection mechanism, the device-tree property "use-advanced-sector-protection" has been created. To enable support for this locking this property needs to be present in the flash DT node. E.g.: nor_flash@0,0 { compatible = "amd,s29gl256n", "cfi-flash"; bank-width = <2>; use-advanced-sector-protection; ... Tested with Spansion S29GL512S10THI and Micron JS28F512M29EWx flash devices. Signed-off-by: Stefan Roese Tested-by: Holger Brunck Signed-off-by: Artem Bityutskiy --- include/linux/mtd/map.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index f6eb4332ac92..8b9bfd7dcaa3 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -245,6 +245,7 @@ struct map_info { unsigned long pfow_base; unsigned long map_priv_1; unsigned long map_priv_2; + struct device_node *device_node; void *fldrv_priv; struct mtd_chip_driver *fldrv; }; -- cgit v1.2.3 From 379749c46320c82df95c7909ec888da8ed1fb22c Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 14 Jan 2013 13:26:15 +0000 Subject: mfd: ab8500-sysctrl: Provide a platform specific pm_power_off() call-back The kernel allows us to specify a function call-back which will be invoked when a system power-off request has been received. Here we provide one which is to be used when shutting down AB8500 based platforms. Signed-off-by: Lee Jones --- include/linux/mfd/abx500/ab8500.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index 1cb5698b4d76..6119b2fbad97 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -274,6 +274,7 @@ struct ab8500_codec_platform_data; /** * struct ab8500_platform_data - AB8500 platform data * @irq_base: start of AB8500 IRQs, AB8500_NR_IRQS will be used + * @pm_power_off: Should machine pm power off hook be registered or not * @init: board-specific initialization after detection of ab8500 * @num_regulator_reg_init: number of regulator init registers * @regulator_reg_init: regulator init registers @@ -282,6 +283,7 @@ struct ab8500_codec_platform_data; */ struct ab8500_platform_data { int irq_base; + bool pm_power_off; void (*init) (struct ab8500 *); int num_regulator_reg_init; struct ab8500_regulator_reg_init *regulator_reg_init; -- cgit v1.2.3 From 1abf063ffd18e6934bb81a776b3d71278eeff4ab Mon Sep 17 00:00:00 2001 From: Kennet Wallden Date: Tue, 27 Sep 2011 09:23:56 +0200 Subject: mfd: ab8500-sysctrl: Provide configuration for SysClkReqRfClkBuf registers Add the possibility to pass configuration settings for SysCl1kReqRfClkBuf to SysClk8ReqRfClkBuf via platform data. Signed-off-by: Lee Jones Signed-off-by: Kennet Wallden Reviewed-by: Karl-Johan PERNTZ Reviewed-by: Bengt JONSSON --- include/linux/mfd/abx500/ab8500-sysctrl.h | 5 +++++ include/linux/mfd/abx500/ab8500.h | 2 ++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500-sysctrl.h b/include/linux/mfd/abx500/ab8500-sysctrl.h index 10eb50973c39..ebf12e793db9 100644 --- a/include/linux/mfd/abx500/ab8500-sysctrl.h +++ b/include/linux/mfd/abx500/ab8500-sysctrl.h @@ -37,6 +37,11 @@ static inline int ab8500_sysctrl_clear(u16 reg, u8 bits) return ab8500_sysctrl_write(reg, bits, 0); } +/* Configuration data for SysClkReq1RfClkBuf - SysClkReq8RfClkBuf */ +struct ab8500_sysctrl_platform_data { + u8 initial_req_buf_config[8]; +}; + /* Registers */ #define AB8500_TURNONSTATUS 0x100 #define AB8500_RESETSTATUS 0x101 diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index 6119b2fbad97..5251bca56326 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -270,6 +270,7 @@ struct regulator_reg_init; struct regulator_init_data; struct ab8500_gpio_platform_data; struct ab8500_codec_platform_data; +struct ab8500_sysctrl_platform_data; /** * struct ab8500_platform_data - AB8500 platform data @@ -291,6 +292,7 @@ struct ab8500_platform_data { struct regulator_init_data *regulator; struct ab8500_gpio_platform_data *gpio; struct ab8500_codec_platform_data *codec; + struct ab8500_sysctrl_platform_data *sysctrl; }; extern int ab8500_init(struct ab8500 *ab8500, -- cgit v1.2.3 From e0f4fec030ce412666cc127702adbf0a6cfa0855 Mon Sep 17 00:00:00 2001 From: Mian Yousaf Kaukab Date: Fri, 27 Jan 2012 11:22:16 +0100 Subject: mfd: abx500-core: Provide an API to dump all ABx500 registers Some drivers can detect subsystem failures e.g. shared memory driver can detect modem sub system failures. It would be helpful in analyzing these failures if AB register dump is available at that point. This patch adds the API for the drivers to dump AB registers in the kernel log. Signed-off-by: Lee Jones Signed-off-by: Mian Yousaf Kaukab Reviewed-by: Linus WALLEIJ Reviewed-by: Jonas ABERG --- include/linux/mfd/abx500.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h index 2138bd33021a..bd480b248c62 100644 --- a/include/linux/mfd/abx500.h +++ b/include/linux/mfd/abx500.h @@ -308,6 +308,7 @@ int abx500_mask_and_set_register_interruptible(struct device *dev, u8 bank, int abx500_get_chip_id(struct device *dev); int abx500_event_registers_startup_state_get(struct device *dev, u8 *event); int abx500_startup_irq_enabled(struct device *dev, unsigned int irq); +void abx500_dump_all_banks(void); struct abx500_ops { int (*get_chip_id) (struct device *); @@ -318,6 +319,7 @@ struct abx500_ops { int (*mask_and_set_register) (struct device *, u8, u8, u8, u8); int (*event_registers_startup_state_get) (struct device *, u8 *); int (*startup_irq_enabled) (struct device *, unsigned int); + void (*dump_all_banks) (struct device *); }; int abx500_register_ops(struct device *core_dev, struct abx500_ops *ops); -- cgit v1.2.3 From 1d843a6c8c2067615fea0ff8cb62d4a5c4a6f8ae Mon Sep 17 00:00:00 2001 From: Mian Yousaf Kaukab Date: Fri, 27 Jan 2012 11:35:41 +0100 Subject: mfd: ab8500-core: Allow the possibility to dump all AB8500 registers Implement an API so that a user may dump all AB8500 registers via debugfs file access. Signed-off-by: Lee Jones Signed-off-by: Mian Yousaf Kaukab Reviewed-by: Linus WALLEIJ Reviewed-by: Jonas ABERG --- include/linux/mfd/abx500/ab8500.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index 5251bca56326..dbec7b00ea83 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -345,4 +345,10 @@ static inline int is_ab8500_2p0(struct ab8500 *ab) return (is_ab8500(ab) && (ab->chip_id == AB8500_CUT2P0)); } +#ifdef CONFIG_AB8500_DEBUG +void ab8500_dump_all_banks(struct device *dev); +#else +static inline void ab8500_dump_all_banks(struct device *dev) {} +#endif + #endif /* MFD_AB8500_H */ -- cgit v1.2.3 From 8f0eb43be5f461a28341fe724686f265b0719dd3 Mon Sep 17 00:00:00 2001 From: Bengt Jonsson Date: Tue, 14 Feb 2012 13:01:00 +0100 Subject: mfd: ab8500-debugfs: Add interrupt debug This patch adds an entry in debugfs to check number of interrupts from the AB. Signed-off-by: Lee Jones Signed-off-by: Bengt Jonsson Reviewed-by: Rabin VINCENT --- include/linux/mfd/abx500/ab8500.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index dbec7b00ea83..fa7173dd71f2 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -347,8 +347,10 @@ static inline int is_ab8500_2p0(struct ab8500 *ab) #ifdef CONFIG_AB8500_DEBUG void ab8500_dump_all_banks(struct device *dev); +void ab8500_debug_register_interrupt(int line); #else static inline void ab8500_dump_all_banks(struct device *dev) {} +static inline void ab8500_debug_register_interrupt(int line) {} #endif #endif /* MFD_AB8500_H */ -- cgit v1.2.3 From 7b9e8522a65886d8ae168547a67c3617b6ba83f1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 28 Jan 2013 14:41:07 -0500 Subject: nfsd: fix IPv6 address handling in the DRC Currently, it only stores the first 16 bytes of any address. struct sockaddr_in6 is 28 bytes however, so we're currently ignoring the last 12 bytes of the address. Expand the c_addr field to a sockaddr_in6, and cast it to a sockaddr_in as necessary. Also fix the comparitor to use the existing RPC helpers for this. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/clnt.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 34206b84d8da..47354a25a927 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -263,7 +263,9 @@ static inline bool __rpc_copy_addr6(struct sockaddr *dst, * @sap1: first sockaddr * @sap2: second sockaddr * - * Just compares the family and address portion. Ignores port, scope, etc. + * Just compares the family and address portion. Ignores port, but + * compares the scope if it's a link-local address. + * * Returns true if the addrs are equal, false if they aren't. */ static inline bool rpc_cmp_addr(const struct sockaddr *sap1, -- cgit v1.2.3 From 155a345a52e6cda18946efe2529d99d5040fad6d Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 4 Feb 2013 08:10:08 -0500 Subject: sunrpc: copy scope ID in __rpc_copy_addr6 When copying an address, we should also copy the scopeid in the event that this is a link-local address and the scope matters. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 47354a25a927..6a7c2619a355 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -242,6 +242,7 @@ static inline bool __rpc_copy_addr6(struct sockaddr *dst, dsin6->sin6_family = ssin6->sin6_family; dsin6->sin6_addr = ssin6->sin6_addr; + dsin6->sin6_scope_id = ssin6->sin6_scope_id; return true; } #else /* !(IS_ENABLED(CONFIG_IPV6) */ -- cgit v1.2.3 From 5976687a2b3d1969f02aba16b80ad3ed79be6ad3 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 4 Feb 2013 12:50:00 -0500 Subject: sunrpc: move address copy/cmp/convert routines and prototypes from clnt.h to addr.h These routines are used by server and client code, so having them in a separate header would be best. Signed-off-by: Jeff Layton Acked-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/addr.h | 170 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/sunrpc/clnt.h | 155 ---------------------------------------- 2 files changed, 170 insertions(+), 155 deletions(-) create mode 100644 include/linux/sunrpc/addr.h (limited to 'include/linux') diff --git a/include/linux/sunrpc/addr.h b/include/linux/sunrpc/addr.h new file mode 100644 index 000000000000..07d8e53bedfc --- /dev/null +++ b/include/linux/sunrpc/addr.h @@ -0,0 +1,170 @@ +/* + * linux/include/linux/sunrpc/addr.h + * + * Various routines for copying and comparing sockaddrs and for + * converting them to and from presentation format. + */ +#ifndef _LINUX_SUNRPC_ADDR_H +#define _LINUX_SUNRPC_ADDR_H + +#include +#include +#include +#include + +size_t rpc_ntop(const struct sockaddr *, char *, const size_t); +size_t rpc_pton(struct net *, const char *, const size_t, + struct sockaddr *, const size_t); +char * rpc_sockaddr2uaddr(const struct sockaddr *, gfp_t); +size_t rpc_uaddr2sockaddr(struct net *, const char *, const size_t, + struct sockaddr *, const size_t); + +static inline unsigned short rpc_get_port(const struct sockaddr *sap) +{ + switch (sap->sa_family) { + case AF_INET: + return ntohs(((struct sockaddr_in *)sap)->sin_port); + case AF_INET6: + return ntohs(((struct sockaddr_in6 *)sap)->sin6_port); + } + return 0; +} + +static inline void rpc_set_port(struct sockaddr *sap, + const unsigned short port) +{ + switch (sap->sa_family) { + case AF_INET: + ((struct sockaddr_in *)sap)->sin_port = htons(port); + break; + case AF_INET6: + ((struct sockaddr_in6 *)sap)->sin6_port = htons(port); + break; + } +} + +#define IPV6_SCOPE_DELIMITER '%' +#define IPV6_SCOPE_ID_LEN sizeof("%nnnnnnnnnn") + +static inline bool __rpc_cmp_addr4(const struct sockaddr *sap1, + const struct sockaddr *sap2) +{ + const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sap1; + const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sap2; + + return sin1->sin_addr.s_addr == sin2->sin_addr.s_addr; +} + +static inline bool __rpc_copy_addr4(struct sockaddr *dst, + const struct sockaddr *src) +{ + const struct sockaddr_in *ssin = (struct sockaddr_in *) src; + struct sockaddr_in *dsin = (struct sockaddr_in *) dst; + + dsin->sin_family = ssin->sin_family; + dsin->sin_addr.s_addr = ssin->sin_addr.s_addr; + return true; +} + +#if IS_ENABLED(CONFIG_IPV6) +static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1, + const struct sockaddr *sap2) +{ + const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sap1; + const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sap2; + + if (!ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr)) + return false; + else if (ipv6_addr_type(&sin1->sin6_addr) & IPV6_ADDR_LINKLOCAL) + return sin1->sin6_scope_id == sin2->sin6_scope_id; + + return true; +} + +static inline bool __rpc_copy_addr6(struct sockaddr *dst, + const struct sockaddr *src) +{ + const struct sockaddr_in6 *ssin6 = (const struct sockaddr_in6 *) src; + struct sockaddr_in6 *dsin6 = (struct sockaddr_in6 *) dst; + + dsin6->sin6_family = ssin6->sin6_family; + dsin6->sin6_addr = ssin6->sin6_addr; + dsin6->sin6_scope_id = ssin6->sin6_scope_id; + return true; +} +#else /* !(IS_ENABLED(CONFIG_IPV6) */ +static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1, + const struct sockaddr *sap2) +{ + return false; +} + +static inline bool __rpc_copy_addr6(struct sockaddr *dst, + const struct sockaddr *src) +{ + return false; +} +#endif /* !(IS_ENABLED(CONFIG_IPV6) */ + +/** + * rpc_cmp_addr - compare the address portion of two sockaddrs. + * @sap1: first sockaddr + * @sap2: second sockaddr + * + * Just compares the family and address portion. Ignores port, but + * compares the scope if it's a link-local address. + * + * Returns true if the addrs are equal, false if they aren't. + */ +static inline bool rpc_cmp_addr(const struct sockaddr *sap1, + const struct sockaddr *sap2) +{ + if (sap1->sa_family == sap2->sa_family) { + switch (sap1->sa_family) { + case AF_INET: + return __rpc_cmp_addr4(sap1, sap2); + case AF_INET6: + return __rpc_cmp_addr6(sap1, sap2); + } + } + return false; +} + +/** + * rpc_copy_addr - copy the address portion of one sockaddr to another + * @dst: destination sockaddr + * @src: source sockaddr + * + * Just copies the address portion and family. Ignores port, scope, etc. + * Caller is responsible for making certain that dst is large enough to hold + * the address in src. Returns true if address family is supported. Returns + * false otherwise. + */ +static inline bool rpc_copy_addr(struct sockaddr *dst, + const struct sockaddr *src) +{ + switch (src->sa_family) { + case AF_INET: + return __rpc_copy_addr4(dst, src); + case AF_INET6: + return __rpc_copy_addr6(dst, src); + } + return false; +} + +/** + * rpc_get_scope_id - return scopeid for a given sockaddr + * @sa: sockaddr to get scopeid from + * + * Returns the value of the sin6_scope_id for AF_INET6 addrs, or 0 if + * not an AF_INET6 address. + */ +static inline u32 rpc_get_scope_id(const struct sockaddr *sa) +{ + if (sa->sa_family != AF_INET6) + return 0; + + return ((struct sockaddr_in6 *) sa)->sin6_scope_id; +} + +#endif /* _LINUX_SUNRPC_ADDR_H */ diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 6a7c2619a355..4a4abde000cb 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -165,160 +165,5 @@ size_t rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t); const char *rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t); int rpc_localaddr(struct rpc_clnt *, struct sockaddr *, size_t); -size_t rpc_ntop(const struct sockaddr *, char *, const size_t); -size_t rpc_pton(struct net *, const char *, const size_t, - struct sockaddr *, const size_t); -char * rpc_sockaddr2uaddr(const struct sockaddr *, gfp_t); -size_t rpc_uaddr2sockaddr(struct net *, const char *, const size_t, - struct sockaddr *, const size_t); - -static inline unsigned short rpc_get_port(const struct sockaddr *sap) -{ - switch (sap->sa_family) { - case AF_INET: - return ntohs(((struct sockaddr_in *)sap)->sin_port); - case AF_INET6: - return ntohs(((struct sockaddr_in6 *)sap)->sin6_port); - } - return 0; -} - -static inline void rpc_set_port(struct sockaddr *sap, - const unsigned short port) -{ - switch (sap->sa_family) { - case AF_INET: - ((struct sockaddr_in *)sap)->sin_port = htons(port); - break; - case AF_INET6: - ((struct sockaddr_in6 *)sap)->sin6_port = htons(port); - break; - } -} - -#define IPV6_SCOPE_DELIMITER '%' -#define IPV6_SCOPE_ID_LEN sizeof("%nnnnnnnnnn") - -static inline bool __rpc_cmp_addr4(const struct sockaddr *sap1, - const struct sockaddr *sap2) -{ - const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sap1; - const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sap2; - - return sin1->sin_addr.s_addr == sin2->sin_addr.s_addr; -} - -static inline bool __rpc_copy_addr4(struct sockaddr *dst, - const struct sockaddr *src) -{ - const struct sockaddr_in *ssin = (struct sockaddr_in *) src; - struct sockaddr_in *dsin = (struct sockaddr_in *) dst; - - dsin->sin_family = ssin->sin_family; - dsin->sin_addr.s_addr = ssin->sin_addr.s_addr; - return true; -} - -#if IS_ENABLED(CONFIG_IPV6) -static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1, - const struct sockaddr *sap2) -{ - const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sap1; - const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sap2; - - if (!ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr)) - return false; - else if (ipv6_addr_type(&sin1->sin6_addr) & IPV6_ADDR_LINKLOCAL) - return sin1->sin6_scope_id == sin2->sin6_scope_id; - - return true; -} - -static inline bool __rpc_copy_addr6(struct sockaddr *dst, - const struct sockaddr *src) -{ - const struct sockaddr_in6 *ssin6 = (const struct sockaddr_in6 *) src; - struct sockaddr_in6 *dsin6 = (struct sockaddr_in6 *) dst; - - dsin6->sin6_family = ssin6->sin6_family; - dsin6->sin6_addr = ssin6->sin6_addr; - dsin6->sin6_scope_id = ssin6->sin6_scope_id; - return true; -} -#else /* !(IS_ENABLED(CONFIG_IPV6) */ -static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1, - const struct sockaddr *sap2) -{ - return false; -} - -static inline bool __rpc_copy_addr6(struct sockaddr *dst, - const struct sockaddr *src) -{ - return false; -} -#endif /* !(IS_ENABLED(CONFIG_IPV6) */ - -/** - * rpc_cmp_addr - compare the address portion of two sockaddrs. - * @sap1: first sockaddr - * @sap2: second sockaddr - * - * Just compares the family and address portion. Ignores port, but - * compares the scope if it's a link-local address. - * - * Returns true if the addrs are equal, false if they aren't. - */ -static inline bool rpc_cmp_addr(const struct sockaddr *sap1, - const struct sockaddr *sap2) -{ - if (sap1->sa_family == sap2->sa_family) { - switch (sap1->sa_family) { - case AF_INET: - return __rpc_cmp_addr4(sap1, sap2); - case AF_INET6: - return __rpc_cmp_addr6(sap1, sap2); - } - } - return false; -} - -/** - * rpc_copy_addr - copy the address portion of one sockaddr to another - * @dst: destination sockaddr - * @src: source sockaddr - * - * Just copies the address portion and family. Ignores port, scope, etc. - * Caller is responsible for making certain that dst is large enough to hold - * the address in src. Returns true if address family is supported. Returns - * false otherwise. - */ -static inline bool rpc_copy_addr(struct sockaddr *dst, - const struct sockaddr *src) -{ - switch (src->sa_family) { - case AF_INET: - return __rpc_copy_addr4(dst, src); - case AF_INET6: - return __rpc_copy_addr6(dst, src); - } - return false; -} - -/** - * rpc_get_scope_id - return scopeid for a given sockaddr - * @sa: sockaddr to get scopeid from - * - * Returns the value of the sin6_scope_id for AF_INET6 addrs, or 0 if - * not an AF_INET6 address. - */ -static inline u32 rpc_get_scope_id(const struct sockaddr *sa) -{ - if (sa->sa_family != AF_INET6) - return 0; - - return ((struct sockaddr_in6 *) sa)->sin6_scope_id; -} - #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ -- cgit v1.2.3 From de0b65ca55dc62b6b477f6e02088df2281da7b51 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 4 Feb 2013 12:51:17 -0500 Subject: sunrpc: fix comment in struct xdr_buf definition ...these pages aren't necessarily contiguous. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 63988990bd36..224d06047e45 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -56,7 +56,7 @@ struct xdr_buf { struct kvec head[1], /* RPC header + non-page data */ tail[1]; /* Appended after page data */ - struct page ** pages; /* Array of contiguous pages */ + struct page ** pages; /* Array of pages */ unsigned int page_base, /* Start of page data */ page_len, /* Length of page data */ flags; /* Flags for data disposition */ -- cgit v1.2.3 From e6e238c38bd4d42d5e2cddb2165e1a46e0fb1200 Mon Sep 17 00:00:00 2001 From: Amit Daniel Kachhap Date: Mon, 4 Feb 2013 00:30:15 +0000 Subject: thermal: sysfs: Add a new sysfs node emul_temp for thermal emulation This patch adds support to set the emulated temperature method in thermal zone (sensor). After setting this feature thermal zone may report this temperature and not the actual temperature. The emulation implementation may be based on sensor capability through platform specific handler or pure software emulation if no platform handler defined. This is useful in debugging different temperature threshold and its associated cooling action. Critical threshold's cannot be emulated. Writing 0 on this node should disable emulation. Signed-off-by: Amit Daniel Kachhap Acked-by: Kukjin Kim Signed-off-by: Zhang Rui --- include/linux/thermal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 9b78f8c6f773..f0bd7f90a90d 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -123,6 +123,7 @@ struct thermal_zone_device_ops { int (*set_trip_hyst) (struct thermal_zone_device *, int, unsigned long); int (*get_crit_temp) (struct thermal_zone_device *, unsigned long *); + int (*set_emul_temp) (struct thermal_zone_device *, unsigned long); int (*get_trend) (struct thermal_zone_device *, int, enum thermal_trend *); int (*notify) (struct thermal_zone_device *, int, @@ -165,6 +166,7 @@ struct thermal_zone_device { int polling_delay; int temperature; int last_temperature; + int emul_temperature; int passive; unsigned int forced_passive; const struct thermal_zone_device_ops *ops; -- cgit v1.2.3 From a8b8a88a9e3042d41326c854272c881664acba1c Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 29 Jan 2013 14:36:31 +0100 Subject: iommu: Make sure DOMAIN_ATTR_MAX is really the maximum Move it to the end of the list. Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index f3b99e1c1042..7e6ce7260b1c 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -58,8 +58,8 @@ struct iommu_domain { #define IOMMU_CAP_INTR_REMAP 0x2 /* isolates device intrs */ enum iommu_attr { - DOMAIN_ATTR_MAX, DOMAIN_ATTR_GEOMETRY, + DOMAIN_ATTR_MAX, }; #ifdef CONFIG_IOMMU_API -- cgit v1.2.3 From d2e121601619631517409cba34e50db3cbff5852 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 29 Jan 2013 13:49:04 +0100 Subject: iommu: Implement DOMAIN_ATTR_PAGING attribute This attribute of a domain can be queried to find out if the domain supports setting up page-tables using the iommu_map() and iommu_unmap() functions. Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7e6ce7260b1c..26066f54a849 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -59,6 +59,7 @@ struct iommu_domain { enum iommu_attr { DOMAIN_ATTR_GEOMETRY, + DOMAIN_ATTR_PAGING, DOMAIN_ATTR_MAX, }; -- cgit v1.2.3 From d7787d579cbef9f8079104759a2259fc916c688c Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 29 Jan 2013 14:26:20 +0100 Subject: iommu: Add domain window handling functions Add the iommu_domain_window_enable() and iommu_domain_window_disable() functions to the IOMMU-API. These functions will be used to setup domains that are based on subwindows and not on paging. Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 26066f54a849..5ea3d7250917 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -101,6 +101,12 @@ struct iommu_ops { enum iommu_attr attr, void *data); int (*domain_set_attr)(struct iommu_domain *domain, enum iommu_attr attr, void *data); + + /* Window handling functions */ + int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, + phys_addr_t paddr, u64 size); + void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr); + unsigned long pgsize_bitmap; }; @@ -158,6 +164,10 @@ extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr, extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr, void *data); +/* Window handling function prototypes */ +extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, + phys_addr_t offset, u64 size); +extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr); /** * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework * @domain: the iommu domain where the fault has happened @@ -240,6 +250,18 @@ static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova, return -ENODEV; } +static inline int iommu_domain_window_enable(struct iommu_domain *domain, + u32 wnd_nr, phys_addr_t paddr, + u64 size) +{ + return -ENODEV; +} + +static inline void iommu_domain_window_disable(struct iommu_domain *domain, + u32 wnd_nr) +{ +} + static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, unsigned long iova) { -- cgit v1.2.3 From 693567125bde1966a095267a9d8ca1b8d40f59ee Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 4 Feb 2013 14:00:01 +0100 Subject: iommu: Add DOMAIN_ATTR_WINDOWS domain attribute This attribute can be used to set and get the number of subwindows on IOMMUs that are window-based. Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 5ea3d7250917..ba3b8a98a049 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -60,6 +60,7 @@ struct iommu_domain { enum iommu_attr { DOMAIN_ATTR_GEOMETRY, DOMAIN_ATTR_PAGING, + DOMAIN_ATTR_WINDOWS, DOMAIN_ATTR_MAX, }; @@ -106,6 +107,10 @@ struct iommu_ops { int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size); void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr); + /* Set the numer of window per domain */ + int (*domain_set_windows)(struct iommu_domain *domain, u32 w_count); + /* Get the numer of window per domain */ + u32 (*domain_get_windows)(struct iommu_domain *domain); unsigned long pgsize_bitmap; }; -- cgit v1.2.3 From c2c460f7c148aa1a59630f61dac2481f1efb4f4e Mon Sep 17 00:00:00 2001 From: Hideki EIRAKU Date: Mon, 21 Jan 2013 19:54:26 +0900 Subject: iommu/shmobile: Add iommu driver for Renesas IPMMU modules This is the Renesas IPMMU driver and IOMMU API implementation. The IPMMU module supports the MMU function and the PMB function. The MMU function provides address translation by pagetable compatible with ARMv6. The PMB function provides address translation including tile-linear translation. This patch implements the MMU function. The iommu driver does not register a platform driver directly because: - the register space of the MMU function and the PMB function have a common register (used for settings flush), so they should ideally have a way to appropriately share this register. - the MMU function uses the IOMMU API while the PMB function does not. - the two functions may be used independently. Signed-off-by: Hideki EIRAKU Signed-off-by: Joerg Roedel --- include/linux/platform_data/sh_ipmmu.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/platform_data/sh_ipmmu.h (limited to 'include/linux') diff --git a/include/linux/platform_data/sh_ipmmu.h b/include/linux/platform_data/sh_ipmmu.h new file mode 100644 index 000000000000..39f7405cdac5 --- /dev/null +++ b/include/linux/platform_data/sh_ipmmu.h @@ -0,0 +1,18 @@ +/* sh_ipmmu.h + * + * Copyright (C) 2012 Hideki EIRAKU + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + */ + +#ifndef __SH_IPMMU_H__ +#define __SH_IPMMU_H__ + +struct shmobile_ipmmu_platform_data { + const char * const *dev_names; + unsigned int num_dev_names; +}; + +#endif /* __SH_IPMMU_H__ */ -- cgit v1.2.3 From c93d08fa75020835741c7b1d0523ff854e8acde1 Mon Sep 17 00:00:00 2001 From: "Milo(Woogyom) Kim" Date: Tue, 5 Feb 2013 18:01:23 +0900 Subject: leds-lp55xx: add new common driver for lp5521/5523 This patch supports basic common driver code for LP5521, LP5523/55231 devices. ( Driver Structure Data ) lp55xx_led and lp55xx_chip In lp55xx common driver, two different data structure is used. o lp55xx_led control multi output LED channels such as led current, channel index. o lp55xx_chip general chip control such like the I2C and platform data. For example, LP5521 has maximum 3 LED channels. LP5523/55231 has 9 output channels. lp55xx_chip for LP5521 ... lp55xx_led #1 lp55xx_led #2 lp55xx_led #3 lp55xx_chip for LP5523 ... lp55xx_led #1 lp55xx_led #2 . . lp55xx_led #9 ( Platform Data ) LP5521 and LP5523/55231 have own specific platform data. However, this data can be handled with just one platform data structure. The lp55xx platform data is declared in the header. This structure is derived from leds-lp5521.h and leds-lp5523.h Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Bryan Wu --- include/linux/platform_data/leds-lp55xx.h | 87 +++++++++++++++++++++++++++++++ 1 file changed, 87 insertions(+) create mode 100644 include/linux/platform_data/leds-lp55xx.h (limited to 'include/linux') diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h new file mode 100644 index 000000000000..1509570d5a3f --- /dev/null +++ b/include/linux/platform_data/leds-lp55xx.h @@ -0,0 +1,87 @@ +/* + * LP55XX Platform Data Header + * + * Copyright (C) 2012 Texas Instruments + * + * Author: Milo(Woogyom) Kim + * + * 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. + * + * Derived from leds-lp5521.h, leds-lp5523.h + */ + +#ifndef _LEDS_LP55XX_H +#define _LEDS_LP55XX_H + +/* Clock configuration */ +#define LP55XX_CLOCK_AUTO 0 +#define LP55XX_CLOCK_INT 1 +#define LP55XX_CLOCK_EXT 2 + +/* Bits in LP5521 CONFIG register. 'update_config' in lp55xx_platform_data */ +#define LP5521_PWM_HF 0x40 /* PWM: 0 = 256Hz, 1 = 558Hz */ +#define LP5521_PWRSAVE_EN 0x20 /* 1 = Power save mode */ +#define LP5521_CP_MODE_OFF 0 /* Charge pump (CP) off */ +#define LP5521_CP_MODE_BYPASS 8 /* CP forced to bypass mode */ +#define LP5521_CP_MODE_1X5 0x10 /* CP forced to 1.5x mode */ +#define LP5521_CP_MODE_AUTO 0x18 /* Automatic mode selection */ +#define LP5521_R_TO_BATT 4 /* R out: 0 = CP, 1 = Vbat */ +#define LP5521_CLK_SRC_EXT 0 /* Ext-clk source (CLK_32K) */ +#define LP5521_CLK_INT 1 /* Internal clock */ +#define LP5521_CLK_AUTO 2 /* Automatic clock selection */ + +struct lp55xx_led_config { + const char *name; + u8 chan_nr; + u8 led_current; /* mA x10, 0 if led is not connected */ + u8 max_current; +}; + +struct lp55xx_predef_pattern { + u8 *r; + u8 *g; + u8 *b; + u8 size_r; + u8 size_g; + u8 size_b; +}; + +/* + * struct lp55xx_platform_data + * @led_config : Configurable led class device + * @num_channels : Number of LED channels + * @label : Used for naming LEDs + * @clock_mode : Input clock mode. LP55XX_CLOCK_AUTO or _INT or _EXT + * @setup_resources : Platform specific function before enabling the chip + * @release_resources : Platform specific function after disabling the chip + * @enable : EN pin control by platform side + * @patterns : Predefined pattern data for RGB channels + * @num_patterns : Number of patterns + * @update_config : Value of CONFIG register + */ +struct lp55xx_platform_data { + + /* LED channel configuration */ + struct lp55xx_led_config *led_config; + u8 num_channels; + const char *label; + + /* Clock configuration */ + u8 clock_mode; + + /* Platform specific functions */ + int (*setup_resources)(void); + void (*release_resources)(void); + void (*enable)(bool state); + + /* Predefined pattern data */ + struct lp55xx_predef_pattern *patterns; + unsigned int num_patterns; + + /* _CONFIG register */ + u8 update_config; +}; + +#endif /* _LEDS_LP55XX_H */ -- cgit v1.2.3 From df4094d24e6328824a2dfe8e6f641bff9a484d68 Mon Sep 17 00:00:00 2001 From: "Milo(Woogyom) Kim" Date: Tue, 5 Feb 2013 19:26:59 +0900 Subject: leds-lp5521/5523: use new lp55xx common header The LP55xx common driver provides a new header, leds-lp55xx.h. This driver enables removing duplicate code for both drivers and making coherent driver structure. LP5521 and LP5523/55231 platform data were merged into one common file. Therefore, the LP5521/5523 platform code need to be fixed. This patch has been already acked. For ux500: https://lkml.org/lkml/2012/10/11/417 Acked-by: Linus Walleij For omap: https://lkml.org/lkml/2012/10/11/334 Acked-by: Tony Lindgren Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Bryan Wu --- include/linux/leds-lp5521.h | 73 --------------------------------------------- include/linux/leds-lp5523.h | 49 ------------------------------ 2 files changed, 122 deletions(-) delete mode 100644 include/linux/leds-lp5521.h delete mode 100644 include/linux/leds-lp5523.h (limited to 'include/linux') diff --git a/include/linux/leds-lp5521.h b/include/linux/leds-lp5521.h deleted file mode 100644 index 3f071ec019b2..000000000000 --- a/include/linux/leds-lp5521.h +++ /dev/null @@ -1,73 +0,0 @@ -/* - * LP5521 LED chip driver. - * - * Copyright (C) 2010 Nokia Corporation - * - * Contact: Samu Onkalo - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA - */ - -#ifndef __LINUX_LP5521_H -#define __LINUX_LP5521_H - -/* See Documentation/leds/leds-lp5521.txt */ - -struct lp5521_led_config { - char *name; - u8 chan_nr; - u8 led_current; /* mA x10, 0 if led is not connected */ - u8 max_current; -}; - -struct lp5521_led_pattern { - u8 *r; - u8 *g; - u8 *b; - u8 size_r; - u8 size_g; - u8 size_b; -}; - -#define LP5521_CLOCK_AUTO 0 -#define LP5521_CLOCK_INT 1 -#define LP5521_CLOCK_EXT 2 - -/* Bits in CONFIG register */ -#define LP5521_PWM_HF 0x40 /* PWM: 0 = 256Hz, 1 = 558Hz */ -#define LP5521_PWRSAVE_EN 0x20 /* 1 = Power save mode */ -#define LP5521_CP_MODE_OFF 0 /* Charge pump (CP) off */ -#define LP5521_CP_MODE_BYPASS 8 /* CP forced to bypass mode */ -#define LP5521_CP_MODE_1X5 0x10 /* CP forced to 1.5x mode */ -#define LP5521_CP_MODE_AUTO 0x18 /* Automatic mode selection */ -#define LP5521_R_TO_BATT 4 /* R out: 0 = CP, 1 = Vbat */ -#define LP5521_CLK_SRC_EXT 0 /* Ext-clk source (CLK_32K) */ -#define LP5521_CLK_INT 1 /* Internal clock */ -#define LP5521_CLK_AUTO 2 /* Automatic clock selection */ - -struct lp5521_platform_data { - struct lp5521_led_config *led_config; - u8 num_channels; - u8 clock_mode; - int (*setup_resources)(void); - void (*release_resources)(void); - void (*enable)(bool state); - const char *label; - u8 update_config; - struct lp5521_led_pattern *patterns; - int num_patterns; -}; - -#endif /* __LINUX_LP5521_H */ diff --git a/include/linux/leds-lp5523.h b/include/linux/leds-lp5523.h deleted file mode 100644 index 727877fb406d..000000000000 --- a/include/linux/leds-lp5523.h +++ /dev/null @@ -1,49 +0,0 @@ -/* - * LP5523 LED Driver - * - * Copyright (C) 2010 Nokia Corporation - * - * Contact: Samu Onkalo - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA - */ - -#ifndef __LINUX_LP5523_H -#define __LINUX_LP5523_H - -/* See Documentation/leds/leds-lp5523.txt */ - -struct lp5523_led_config { - const char *name; - u8 chan_nr; - u8 led_current; /* mA x10, 0 if led is not connected */ - u8 max_current; -}; - -#define LP5523_CLOCK_AUTO 0 -#define LP5523_CLOCK_INT 1 -#define LP5523_CLOCK_EXT 2 - -struct lp5523_platform_data { - struct lp5523_led_config *led_config; - u8 num_channels; - u8 clock_mode; - int (*setup_resources)(void); - void (*release_resources)(void); - void (*enable)(bool state); - const char *label; -}; - -#endif /* __LINUX_LP5523_H */ -- cgit v1.2.3 From 2a2483072393b27f4336ab068a1f48ca19ff1c1e Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Thu, 24 Jan 2013 14:14:19 +1000 Subject: vgacon/vt: clear buffer attributes when we load a 512 character font (v2) When we switch from 256->512 byte font rendering mode, it means the current contents of the screen is being reinterpreted. The bit that holds the high bit of the 9-bit font, may have been previously set, and thus the new font misrenders. The problem case we see is grub2 writes spaces with the bit set, so it ends up with data like 0x820, which gets reinterpreted into 0x120 char which the font translates into G with a circumflex. This flashes up on screen at boot and is quite ugly. A current side effect of this patch though is that any rendering on the screen changes color to a slightly darker color, but at least the screen no longer corrupts. v2: as suggested by hpa, always clear the attribute space, whether we are are going to or from 512 chars. Cc: stable@vger.kernel.org Signed-off-by: Dave Airlie --- include/linux/vt_kern.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 50ae7d0c279e..1f55665d7b49 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -47,6 +47,7 @@ int con_set_cmap(unsigned char __user *cmap); int con_get_cmap(unsigned char __user *cmap); void scrollback(struct vc_data *vc, int lines); void scrollfront(struct vc_data *vc, int lines); +void clear_buffer_attributes(struct vc_data *vc); void update_region(struct vc_data *vc, unsigned long start, int count); void redraw_screen(struct vc_data *vc, int is_switch); #define update_screen(x) redraw_screen(x, 0) -- cgit v1.2.3 From 9fff24aa2c5c504aadead1ff9599e813604c2e53 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 6 Feb 2013 22:30:23 -0500 Subject: jbd2: track request delay statistics Track the delay between when we first request that the commit begin and when it actually begins, so we can see how much of a gap exists. In theory, this should just be the remaining scheduling quantuum of the thread which requested the commit (assuming it was not a synchronous operation which triggered the commit request) plus scheduling overhead; however, it's possible that real time processes might get in the way of letting the kjournald thread from executing. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index e30b66346942..e0aafc46064f 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -580,6 +580,11 @@ struct transaction_s */ unsigned long t_start; + /* + * When commit was requested + */ + unsigned long t_requested; + /* * Checkpointing stats [j_checkpoint_sem] */ @@ -637,6 +642,7 @@ struct transaction_s struct transaction_run_stats_s { unsigned long rs_wait; + unsigned long rs_request_delay; unsigned long rs_running; unsigned long rs_locked; unsigned long rs_flushing; @@ -649,6 +655,7 @@ struct transaction_run_stats_s { struct transaction_stats_s { unsigned long ts_tid; + unsigned long ts_requested; struct transaction_run_stats_s run; }; -- cgit v1.2.3 From 078d5039a13dedbd2ed14153a6d764fd75baae07 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 7 Feb 2013 00:02:15 -0500 Subject: jbd2: revert "jbd2: add COW fields to struct jbd2_journal_handle" This reverts commit 93737456d68ddcb86232f669b83da673dd12e351. The cow-snapshots effort is no longer active, so remove these extra fields to shrink down the handle structure. Signed-off-by: "Theodore Ts'o" Reviewed-by: Jan Kara --- include/linux/jbd2.h | 28 +++------------------------- 1 file changed, 3 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index e0aafc46064f..24db7256a5ff 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -397,35 +397,13 @@ struct jbd2_journal_handle int h_err; /* Flags [no locking] */ - unsigned int h_sync:1; /* sync-on-close */ - unsigned int h_jdata:1; /* force data journaling */ - unsigned int h_aborted:1; /* fatal error on handle */ - unsigned int h_cowing:1; /* COWing block to snapshot */ - - /* Number of buffers requested by user: - * (before adding the COW credits factor) */ - unsigned int h_base_credits:14; - - /* Number of buffers the user is allowed to dirty: - * (counts only buffers dirtied when !h_cowing) */ - unsigned int h_user_credits:14; - + unsigned int h_sync: 1; /* sync-on-close */ + unsigned int h_jdata: 1; /* force data journaling */ + unsigned int h_aborted: 1; /* fatal error on handle */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map h_lockdep_map; #endif - -#ifdef CONFIG_JBD2_DEBUG - /* COW debugging counters: */ - unsigned int h_cow_moved; /* blocks moved to snapshot */ - unsigned int h_cow_copied; /* blocks copied to snapshot */ - unsigned int h_cow_ok_jh; /* blocks already COWed during current - transaction */ - unsigned int h_cow_ok_bitmap; /* blocks not set in COW bitmap */ - unsigned int h_cow_ok_mapped;/* blocks already mapped in snapshot */ - unsigned int h_cow_bitmaps; /* COW bitmaps created */ - unsigned int h_cow_excluded; /* blocks set in exclude bitmap */ -#endif }; -- cgit v1.2.3 From 50e244cc793d511b86adea24972f3a7264cae114 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Fri, 25 Jan 2013 10:28:15 +1000 Subject: fb: rework locking to fix lock ordering on takeover Adjust the console layer to allow a take over call where the caller already holds the locks. Make the fb layer lock in order. This is partly a band aid, the fb layer is terminally confused about the locking rules it uses for its notifiers it seems. [akpm@linux-foundation.org: remove stray non-ascii char, tidy comment] [akpm@linux-foundation.org: export do_take_over_console()] [airlied: cleanup another non-ascii char] Signed-off-by: Alan Cox Cc: Florian Tobias Schandinat Cc: Stephen Rothwell Cc: Jiri Kosina Cc: stable Tested-by: Sedat Dilek Reviewed-by: Daniel Vetter Signed-off-by: Andrew Morton Signed-off-by: Dave Airlie --- include/linux/console.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index dedb082fe50f..4ef4307dfb82 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -78,6 +78,7 @@ int con_is_bound(const struct consw *csw); int register_con_driver(const struct consw *csw, int first, int last); int unregister_con_driver(const struct consw *csw); int take_over_console(const struct consw *sw, int first, int last, int deflt); +int do_take_over_console(const struct consw *sw, int first, int last, int deflt); void give_up_console(const struct consw *sw); #ifdef CONFIG_HW_CONSOLE int con_debug_enter(struct vc_data *vc); -- cgit v1.2.3 From e93a9a868792ad71cdd09d75e5a02d8067473c4e Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 25 Jan 2013 10:28:18 +1000 Subject: fb: Yet another band-aid for fixing lockdep mess I've still got lockdep warnings even after Alan's patch, and it seems that yet more band aids are required to paper over similar paths for unbind_con_driver() and unregister_con_driver(). After this hack, lockdep warnings are finally gone. Signed-off-by: Takashi Iwai Cc: Alan Cox Cc: Florian Tobias Schandinat Cc: Jiri Kosina Cc: stable Tested-by: Sedat Dilek Signed-off-by: Andrew Morton Signed-off-by: Dave Airlie --- include/linux/console.h | 1 + include/linux/vt_kern.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 4ef4307dfb82..47b858cffc47 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -77,6 +77,7 @@ extern const struct consw prom_con; /* SPARC PROM console */ int con_is_bound(const struct consw *csw); int register_con_driver(const struct consw *csw, int first, int last); int unregister_con_driver(const struct consw *csw); +int do_unregister_con_driver(const struct consw *csw); int take_over_console(const struct consw *sw, int first, int last, int deflt); int do_take_over_console(const struct consw *sw, int first, int last, int deflt); void give_up_console(const struct consw *sw); diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 50ae7d0c279e..dbbc6bfee71f 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -130,6 +130,8 @@ void vt_event_post(unsigned int event, unsigned int old, unsigned int new); int vt_waitactive(int n); void change_console(struct vc_data *new_vc); void reset_vc(struct vc_data *vc); +extern int do_unbind_con_driver(const struct consw *csw, int first, int last, + int deflt); extern int unbind_con_driver(const struct consw *csw, int first, int last, int deflt); int vty_init(const struct file_operations *console_fops); -- cgit v1.2.3 From 4f0a6847815837b63b05fc23878ba391701d8f6a Mon Sep 17 00:00:00 2001 From: Jonghwa Lee Date: Fri, 8 Feb 2013 01:13:06 +0000 Subject: Thermal: exynos: Add support for temperature falling interrupt. This patch introduces using temperature falling interrupt in exynos thermal driver. Former patch, it only use polling way to check whether if system themperature is fallen. However, exynos SOC also provides temperature falling interrupt way to do same things by hw. This feature is not supported in exynos4210. Acked-by: Kukjin Kim Signed-off-by: Jonghwa Lee Signed-off-by: Amit Daniel Kachhap Signed-off-by: Zhang Rui --- include/linux/platform_data/exynos_thermal.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/exynos_thermal.h b/include/linux/platform_data/exynos_thermal.h index a7bdb2f63b73..da7e6274b175 100644 --- a/include/linux/platform_data/exynos_thermal.h +++ b/include/linux/platform_data/exynos_thermal.h @@ -53,6 +53,8 @@ struct freq_clip_table { * struct exynos_tmu_platform_data * @threshold: basic temperature for generating interrupt * 25 <= threshold <= 125 [unit: degree Celsius] + * @threshold_falling: differntial value for setting threshold + * of temperature falling interrupt. * @trigger_levels: array for each interrupt levels * [unit: degree Celsius] * 0: temperature for trigger_level0 interrupt @@ -97,6 +99,7 @@ struct freq_clip_table { */ struct exynos_tmu_platform_data { u8 threshold; + u8 threshold_falling; u8 trigger_levels[4]; bool trigger_level0_en; bool trigger_level1_en; -- cgit v1.2.3 From 343d9c283c9847da043fda3e76e3197f27b667dd Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 8 Feb 2013 13:00:22 -0500 Subject: jbd2: add tracepoints which provide per-handle statistics Handles which stay open a long time are problematic when it comes time to close down a transaction so it can be committed. These tracepoints will help us determine which ones are the problematic ones, and to validate whether changes makes things better or worse. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 24db7256a5ff..fa5fea17b619 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -400,6 +400,11 @@ struct jbd2_journal_handle unsigned int h_sync: 1; /* sync-on-close */ unsigned int h_jdata: 1; /* force data journaling */ unsigned int h_aborted: 1; /* fatal error on handle */ + unsigned int h_type: 8; /* for handle statistics */ + unsigned int h_line_no: 16; /* for handle statistics */ + + unsigned long h_start_jiffies; + unsigned int h_requested_credits; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map h_lockdep_map; @@ -1071,7 +1076,8 @@ static inline handle_t *journal_current_handle(void) */ extern handle_t *jbd2_journal_start(journal_t *, int nblocks); -extern handle_t *jbd2__journal_start(journal_t *, int nblocks, gfp_t gfp_mask); +extern handle_t *jbd2__journal_start(journal_t *, int nblocks, gfp_t gfp_mask, + unsigned int type, unsigned int line_no); extern int jbd2_journal_restart(handle_t *, int nblocks); extern int jbd2__journal_restart(handle_t *, int nblocks, gfp_t gfp_mask); extern int jbd2_journal_extend (handle_t *, int nblocks); -- cgit v1.2.3 From 4c190e2f913f038c9c91ee63b59cd037260ba353 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 6 Feb 2013 08:28:55 -0500 Subject: sunrpc: trim off trailing checksum before returning decrypted or integrity authenticated buffer When GSSAPI integrity signatures are in use, or when we're using GSSAPI privacy with the v2 token format, there is a trailing checksum on the xdr_buf that is returned. It's checked during the authentication stage, and afterward nothing cares about it. Ordinarily, it's not a problem since the XDR code generally ignores it, but it will be when we try to compute a checksum over the buffer to help prevent XID collisions in the duplicate reply cache. Fix the code to trim off the checksums after verifying them. Note that in unwrap_integ_data, we must avoid trying to reverify the checksum if the request was deferred since it will no longer be present when it's revisited. Signed-off-by: Jeff Layton --- include/linux/sunrpc/xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 224d06047e45..15f9204ee70b 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -152,6 +152,7 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p) extern void xdr_shift_buf(struct xdr_buf *, size_t); extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *); extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int); +extern void xdr_buf_trim(struct xdr_buf *, unsigned int); extern int xdr_buf_read_netobj(struct xdr_buf *, struct xdr_netobj *, unsigned int); extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); -- cgit v1.2.3 From b6e96d0067d81f6a300bedee661b5ece8164e210 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 9 Feb 2013 16:29:20 -0500 Subject: jbd2: use module parameters instead of debugfs for jbd_debug There are multiple reasons to move away from debugfs. First of all, we are only using it for a single parameter, and it is much more complicated to set up (some 30 lines of code compared to 3), and one more thing that might fail while loading the jbd2 module. Secondly, as a module paramter it can be specified as a boot option if jbd2 is built into the kernel, or as a parameter when the module is loaded, and it can also be manipulated dynamically under /sys/module/jbd2/parameters/jbd2_debug. So it is more flexible. Ultimately we want to move away from using jbd_debug() towards tracepoints, but for now this is still a useful simplification of the code base. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index fa5fea17b619..50e5a5e6a712 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -20,7 +20,6 @@ #ifndef __KERNEL__ #include "jfs_compat.h" #define JBD2_DEBUG -#define jfs_debug jbd_debug #else #include @@ -57,7 +56,7 @@ * CONFIG_JBD2_DEBUG is on. */ #define JBD2_EXPENSIVE_CHECKING -extern u8 jbd2_journal_enable_debug; +extern ushort jbd2_journal_enable_debug; #define jbd_debug(n, f, a...) \ do { \ -- cgit v1.2.3 From 9350393239153c4a98cbed4d69b9ed81e37d5e74 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sun, 10 Feb 2013 15:57:38 +1030 Subject: virtio: make config_ops const It is just a table of function pointers, make it const for cleanliness and security reasons. Signed-off-by: Stephen Hemminger Signed-off-by: Rusty Russell --- include/linux/virtio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index cf8adb1f5b2c..eb34cf774473 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -78,7 +78,7 @@ struct virtio_device { int index; struct device dev; struct virtio_device_id id; - struct virtio_config_ops *config; + const struct virtio_config_ops *config; struct list_head vqs; /* Note that this is a Linux set_bit-style bitmap. */ unsigned long features[1]; -- cgit v1.2.3 From 7a905b1485adf863607b5fc9e32a3fa3838bcc23 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Thu, 7 Feb 2013 18:55:57 +0900 Subject: KVM: Remove user_alloc from struct kvm_memory_slot This field was needed to differentiate memory slots created by the new API, KVM_SET_USER_MEMORY_REGION, from those by the old equivalent, KVM_SET_MEMORY_REGION, whose support was dropped long before: commit b74a07beed0e64bfba413dcb70dd6749c57f43dc KVM: Remove kernel-allocated memory regions Although we also have private memory slots to which KVM allocates memory with vm_mmap(), !user_alloc slots in other words, the slot id should be enough for differentiating them. Note: corresponding function parameters will be removed later. Reviewed-by: Marcelo Tosatti Signed-off-by: Takuya Yoshikawa Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0350e0d5e031..722cae78bbc4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -273,7 +273,6 @@ struct kvm_memory_slot { unsigned long userspace_addr; u32 flags; short id; - bool user_alloc; }; static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) -- cgit v1.2.3 From 41875e388401ad97c33252d5fa39d52e0b70ee9b Mon Sep 17 00:00:00 2001 From: Sujit Reddy Thumma Date: Tue, 4 Dec 2012 17:06:19 +0530 Subject: mmc: sdio: Fix SDIO 3.0 UHS-I initialization sequence According to UHS-I initialization sequence for SDIO 3.0 cards, the host must set bit[24] (S18R) of OCR register during OCR handshake to know whether the SDIO card is capable of doing 1.8V I/O. Signed-off-by: Sujit Reddy Thumma Signed-off-by: Subhash Jadavani Reviewed-by: Johan Rudholm Reviewed-by: Ulf Hansson Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 61a10c17aabd..c89a1bb87fa5 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -434,6 +434,14 @@ static inline int mmc_boot_partition_access(struct mmc_host *host) return !(host->caps2 & MMC_CAP2_BOOTPART_NOACC); } +static inline int mmc_host_uhs(struct mmc_host *host) +{ + return host->caps & + (MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25 | + MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 | + MMC_CAP_UHS_DDR50); +} + #ifdef CONFIG_MMC_CLKGATE void mmc_host_clk_hold(struct mmc_host *host); void mmc_host_clk_release(struct mmc_host *host); -- cgit v1.2.3 From 2220eedfd7aea69008173a224975e10284fbe854 Mon Sep 17 00:00:00 2001 From: Konstantin Dorfman Date: Mon, 14 Jan 2013 14:28:17 -0500 Subject: mmc: fix async request mechanism for sequential read scenarios When current request is running on the bus and if next request fetched by mmcqd is NULL, mmc context (mmcqd thread) gets blocked until the current request completes. This means that if new request comes in while the mmcqd thread is blocked, this new request can not be prepared in parallel to current ongoing request. This may result in delaying the new request execution and increase it's latency. This change allows to wake up the MMC thread on new request arrival. Now once the MMC thread is woken up, a new request can be fetched and prepared in parallel to the current running request which means this new request can be started immediately after the current running request completes. With this change read throughput is improved by 16%. Signed-off-by: Konstantin Dorfman Reviewed-by: Seungwon Jeon Signed-off-by: Chris Ball --- include/linux/mmc/card.h | 12 ++++++++++++ include/linux/mmc/core.h | 3 ++- include/linux/mmc/host.h | 17 +++++++++++++++++ 3 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 5c69315d60cc..be2500a49925 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -187,6 +187,18 @@ struct sdio_func_tuple; #define SDIO_MAX_FUNCS 7 +enum mmc_blk_status { + MMC_BLK_SUCCESS = 0, + MMC_BLK_PARTIAL, + MMC_BLK_CMD_ERR, + MMC_BLK_RETRY, + MMC_BLK_ABORT, + MMC_BLK_DATA_ERR, + MMC_BLK_ECC_ERR, + MMC_BLK_NOMEDIUM, + MMC_BLK_NEW_REQUEST, +}; + /* The number of MMC physical partitions. These consist of: * boot partitions (2), general purpose partitions (4) in MMC v4.4. */ diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 5bf7c2274fcb..495d1336149c 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -120,6 +120,7 @@ struct mmc_data { s32 host_cookie; /* host private data */ }; +struct mmc_host; struct mmc_request { struct mmc_command *sbc; /* SET_BLOCK_COUNT for multiblock */ struct mmc_command *cmd; @@ -128,9 +129,9 @@ struct mmc_request { struct completion completion; void (*done)(struct mmc_request *);/* completion function */ + struct mmc_host *host; }; -struct mmc_host; struct mmc_card; struct mmc_async_req; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index c89a1bb87fa5..523d570f58ad 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -170,6 +170,22 @@ struct mmc_slot { void *handler_priv; }; +/** + * mmc_context_info - synchronization details for mmc context + * @is_done_rcv wake up reason was done request + * @is_new_req wake up reason was new request + * @is_waiting_last_req mmc context waiting for single running request + * @wait wait queue + * @lock lock to protect data fields + */ +struct mmc_context_info { + bool is_done_rcv; + bool is_new_req; + bool is_waiting_last_req; + wait_queue_head_t wait; + spinlock_t lock; +}; + struct regulator; struct mmc_supply { @@ -331,6 +347,7 @@ struct mmc_host { struct dentry *debugfs_root; struct mmc_async_req *areq; /* active async req */ + struct mmc_context_info context_info; /* async synchronization info */ #ifdef CONFIG_FAIL_MMC_REQUEST struct fault_attr fail_mmc_request; -- cgit v1.2.3 From 6e105e0593055dc4aae21df7bca3868045754148 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sjur=20Br=C3=A6ndeland?= Date: Wed, 13 Feb 2013 15:52:36 +1030 Subject: virtio: Add module driver macro for virtio drivers. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add helper macro for drivers that don't do anything special in module init/exit. Signed-off-by: Sjur Brændeland Signed-off-by: Rusty Russell --- include/linux/virtio.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index eb34cf774473..ff6714e6d0f5 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -126,4 +126,13 @@ static inline struct virtio_driver *drv_to_virtio(struct device_driver *drv) int register_virtio_driver(struct virtio_driver *drv); void unregister_virtio_driver(struct virtio_driver *drv); + +/* module_virtio_driver() - Helper macro for drivers that don't do + * anything special in module init/exit. This eliminates a lot of + * boilerplate. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit() + */ +#define module_virtio_driver(__virtio_driver) \ + module_driver(__virtio_driver, register_virtio_driver, \ + unregister_virtio_driver) #endif /* _LINUX_VIRTIO_H */ -- cgit v1.2.3 From ccac71a7f063ad31eb99fac37e95b70ff57f1354 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Thu, 8 Nov 2012 19:18:08 +0200 Subject: mfd: omap-usb-host: override number of ports from platform data Both OMAP4 and 5 exhibit the same revision ID in the REVISION register but they have different number of ports i.e. 2 and 3 respectively. So we can't rely on REVISION register for number of ports on OMAP5 and depend on platform data (or device tree) instead. Signed-off-by: Roger Quadros Reviewed-by: Felipe Balbi --- include/linux/platform_data/usb-omap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/usb-omap.h b/include/linux/platform_data/usb-omap.h index e697c85ad3bc..fa579b4c666b 100644 --- a/include/linux/platform_data/usb-omap.h +++ b/include/linux/platform_data/usb-omap.h @@ -55,6 +55,7 @@ struct ohci_hcd_omap_platform_data { }; struct usbhs_omap_platform_data { + int nports; enum usbhs_omap_port_mode port_mode[OMAP3_HS_USB_PORTS]; int reset_gpio_port[OMAP3_HS_USB_PORTS]; struct regulator *regulator[OMAP3_HS_USB_PORTS]; -- cgit v1.2.3 From d83f5901bc0cd7131a3b8534169ee889efc4c257 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 30 Jan 2013 19:21:14 -0800 Subject: coda: Restrict coda messages to the initial user namespace Remove the slight chance that uids and gids in coda messages will be interpreted in the wrong user namespace. - Only allow processes in the initial user namespace to open the coda character device to communicate with coda filesystems. - Explicitly convert the uids in the coda header into the initial user namespace. - In coda_vattr_to_attr make kuids and kgids from the initial user namespace uids and gids in struct coda_vattr that just came from userspace. - In coda_iattr_to_vattr convert kuids and kgids into uids and gids in the intial user namespace and store them in struct coda_vattr for sending to coda userspace programs. Nothing needs to be changed with mounts as coda does not support being mounted in anything other than the initial user namespace. Cc: Jan Harkes Signed-off-by: "Eric W. Biederman" --- include/linux/coda_psdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/coda_psdev.h b/include/linux/coda_psdev.h index 8031d6eef102..5b8721efa948 100644 --- a/include/linux/coda_psdev.h +++ b/include/linux/coda_psdev.h @@ -34,7 +34,7 @@ int venus_lookup(struct super_block *sb, struct CodaFid *fid, const char *name, int length, int *type, struct CodaFid *resfid); int venus_close(struct super_block *sb, struct CodaFid *fid, int flags, - vuid_t uid); + kuid_t uid); int venus_open(struct super_block *sb, struct CodaFid *fid, int flags, struct file **f); int venus_mkdir(struct super_block *sb, struct CodaFid *dirfid, -- cgit v1.2.3 From 7eaf040b720bc8c0ce5cd49151ca194ca2d56842 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 1 Feb 2013 16:31:17 -0800 Subject: sunrpc: Use kuid_t and kgid_t where appropriate Convert variables that store uids and gids to be of type kuid_t and kgid_t instead of type uid_t and gid_t. Cc: "J. Bruce Fields" Cc: Trond Myklebust Signed-off-by: "Eric W. Biederman" --- include/linux/sunrpc/auth.h | 7 ++++--- include/linux/sunrpc/svcauth.h | 4 ++-- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index f25ba922baaf..58fda1c3c783 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -17,14 +17,15 @@ #include #include +#include /* size of the nodename buffer */ #define UNX_MAXNODENAME 32 /* Work around the lack of a VFS credential */ struct auth_cred { - uid_t uid; - gid_t gid; + kuid_t uid; + kgid_t gid; struct group_info *group_info; const char *principal; unsigned char machine_cred : 1; @@ -48,7 +49,7 @@ struct rpc_cred { unsigned long cr_flags; /* various flags */ atomic_t cr_count; /* ref count */ - uid_t cr_uid; + kuid_t cr_uid; /* per-flavor data */ }; diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index dd74084a9799..ff374ab30839 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -18,8 +18,8 @@ #include struct svc_cred { - uid_t cr_uid; - gid_t cr_gid; + kuid_t cr_uid; + kgid_t cr_gid; struct group_info *cr_group_info; u32 cr_flavor; /* pseudoflavor */ char *cr_principal; /* for gss */ -- cgit v1.2.3 From 54f834cd5501fb5fc801e4719a3ad0c894a3af2c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 1 Feb 2013 14:16:29 -0800 Subject: nfs: Convert struct nfs_fattr to Use kuid_t and kgid_t Cc: "J. Bruce Fields" Cc: Trond Myklebust Signed-off-by: "Eric W. Biederman" --- include/linux/nfs_xdr.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 29adb12c7ecf..13441ddac33d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -48,8 +48,8 @@ struct nfs_fattr { unsigned int valid; /* which fields are valid */ umode_t mode; __u32 nlink; - __u32 uid; - __u32 gid; + kuid_t uid; + kgid_t gid; dev_t rdev; __u64 size; union { -- cgit v1.2.3 From 9f309c86cf343c59c79d25d9bde5d4a895d2e81f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 1 Feb 2013 03:21:47 -0800 Subject: nfs: Convert idmap to use kuids and kgids Convert nfs_map_name_to_uid to return a kuid_t value. Convert nfs_map_name_to_gid to return a kgid_t value. Convert nfs_map_uid_to_name to take a kuid_t paramater. Convert nfs_map_gid_to_name to take a kgid_t paramater. Tweak nfs_fattr_map_owner_to_name to use a kuid_t intermediate value. Tweak nfs_fattr_map_group_to_name to use a kgid_t intermediate value. Which makes these functions properly handle kuids and kgids, including erroring of the generated kuid or kgid is invalid. Cc: "J. Bruce Fields" Cc: Trond Myklebust Signed-off-by: "Eric W. Biederman" --- include/linux/nfs_idmap.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_idmap.h b/include/linux/nfs_idmap.h index 2dcef3ab58b6..0f4b79da6584 100644 --- a/include/linux/nfs_idmap.h +++ b/include/linux/nfs_idmap.h @@ -36,6 +36,7 @@ #ifndef NFS_IDMAP_H #define NFS_IDMAP_H +#include #include @@ -67,10 +68,10 @@ void nfs_fattr_init_names(struct nfs_fattr *fattr, void nfs_fattr_free_names(struct nfs_fattr *); void nfs_fattr_map_and_free_names(struct nfs_server *, struct nfs_fattr *); -int nfs_map_name_to_uid(const struct nfs_server *, const char *, size_t, __u32 *); -int nfs_map_group_to_gid(const struct nfs_server *, const char *, size_t, __u32 *); -int nfs_map_uid_to_name(const struct nfs_server *, __u32, char *, size_t); -int nfs_map_gid_to_group(const struct nfs_server *, __u32, char *, size_t); +int nfs_map_name_to_uid(const struct nfs_server *, const char *, size_t, kuid_t *); +int nfs_map_group_to_gid(const struct nfs_server *, const char *, size_t, kgid_t *); +int nfs_map_uid_to_name(const struct nfs_server *, kuid_t, char *, size_t); +int nfs_map_gid_to_group(const struct nfs_server *, kgid_t, char *, size_t); extern unsigned int nfs_idmap_cache_timeout; #endif /* NFS_IDMAP_H */ -- cgit v1.2.3 From ab8e4aee0a3f73d1b12e6d63b42075f0586ad4fd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 2 Feb 2013 05:18:08 -0800 Subject: nfsd: Handle kuids and kgids in the nfs4acl to posix_acl conversion In struct nfs4_ace remove the member who and replace it with an anonymous union holding who_uid and who_gid. Allowing typesafe storage uids and gids. Add a helper pace_gt for sorting posix_acl_entries. In struct posix_user_ace_state to replace uid with a union of kuid_t uid and kgid_t gid. Remove all initializations of the deprecated posic_acl_entry e_id field. Which is not present when user namespaces are enabled. Split find_uid into two functions find_uid and find_gid that work in a typesafe manner. In nfs4xdr update nfsd4_encode_fattr to deal with the changes in struct nfs4_ace. Rewrite nfsd4_encode_name to take a kuid_t and a kgid_t instead of a generic id and flag if it is a group or a uid. Replace the group flag with a test for a valid gid. Modify nfsd4_encode_user to take a kuid_t and call the modifed nfsd4_encode_name. Modify nfsd4_encode_group to take a kgid_t and call the modified nfsd4_encode_name. Modify nfsd4_encode_aclname to take an ace instead of taking the fields of an ace broken out. This allows it to detect if the ace is for a user or a group and to pass the appropriate value while still being typesafe. Cc: "J. Bruce Fields" Cc: Trond Myklebust Signed-off-by: "Eric W. Biederman" --- include/linux/nfs4.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index e111fa419a4e..7b8fc73810ad 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -13,6 +13,7 @@ #define _LINUX_NFS4_H #include +#include #include struct nfs4_ace { @@ -20,7 +21,10 @@ struct nfs4_ace { uint32_t flag; uint32_t access_mask; int whotype; - uid_t who; + union { + kuid_t who_uid; + kgid_t who_gid; + }; }; struct nfs4_acl { -- cgit v1.2.3 From 4c1e1b34d5c800ad3ac9a7e2805b0bea70ad2278 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 2 Feb 2013 06:42:53 -0800 Subject: nfsd: Store ex_anon_uid and ex_anon_gid as kuids and kgids Cc: "J. Bruce Fields" Cc: Trond Myklebust Signed-off-by: "Eric W. Biederman" --- include/linux/nfsd/export.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 24c139288db4..7898c997dfea 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -49,8 +49,8 @@ struct svc_export { struct auth_domain * ex_client; int ex_flags; struct path ex_path; - uid_t ex_anon_uid; - gid_t ex_anon_gid; + kuid_t ex_anon_uid; + kgid_t ex_anon_gid; int ex_fsid; unsigned char * ex_uuid; /* 16 byte fsid */ struct nfsd4_fs_locations ex_fslocs; -- cgit v1.2.3 From 60c185f059c88ad4b9b170b1f9322e3adcccca07 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Thu, 3 Jan 2013 16:16:58 +0530 Subject: mfd: palmas: Add APIs to access the Palmas' registers Palmas register set is divided into different blocks (base and offset) and hence different i2c addresses. The i2c address offsets are derived from base address of block of registers. Add inline APIs to access the Palma's registers which takes the base of register block and register offset. The i2c address offset is derived from the base address of register blocks. Signed-off-by: Laxman Dewangan Signed-off-by: Samuel Ortiz --- include/linux/mfd/palmas.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 29f6616e12f0..a4d13d7cd001 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -2789,4 +2789,56 @@ enum usb_irq_events { #define PALMAS_GPADC_TRIM15 0xE #define PALMAS_GPADC_TRIM16 0xF +static inline int palmas_read(struct palmas *palmas, unsigned int base, + unsigned int reg, unsigned int *val) +{ + unsigned int addr = PALMAS_BASE_TO_REG(base, reg); + int slave_id = PALMAS_BASE_TO_SLAVE(base); + + return regmap_read(palmas->regmap[slave_id], addr, val); +} + +static inline int palmas_write(struct palmas *palmas, unsigned int base, + unsigned int reg, unsigned int value) +{ + unsigned int addr = PALMAS_BASE_TO_REG(base, reg); + int slave_id = PALMAS_BASE_TO_SLAVE(base); + + return regmap_write(palmas->regmap[slave_id], addr, value); +} + +static inline int palmas_bulk_write(struct palmas *palmas, unsigned int base, + unsigned int reg, const void *val, size_t val_count) +{ + unsigned int addr = PALMAS_BASE_TO_REG(base, reg); + int slave_id = PALMAS_BASE_TO_SLAVE(base); + + return regmap_bulk_write(palmas->regmap[slave_id], addr, + val, val_count); +} + +static inline int palmas_bulk_read(struct palmas *palmas, unsigned int base, + unsigned int reg, void *val, size_t val_count) +{ + unsigned int addr = PALMAS_BASE_TO_REG(base, reg); + int slave_id = PALMAS_BASE_TO_SLAVE(base); + + return regmap_bulk_read(palmas->regmap[slave_id], addr, + val, val_count); +} + +static inline int palmas_update_bits(struct palmas *palmas, unsigned int base, + unsigned int reg, unsigned int mask, unsigned int val) +{ + unsigned int addr = PALMAS_BASE_TO_REG(base, reg); + int slave_id = PALMAS_BASE_TO_SLAVE(base); + + return regmap_update_bits(palmas->regmap[slave_id], addr, mask, val); +} + +static inline int palmas_irq_get_virq(struct palmas *palmas, int irq) +{ + return regmap_irq_get_virq(palmas->irq_data, irq); +} + #endif /* __LINUX_MFD_PALMAS_H */ -- cgit v1.2.3 From 3d91f8282c66d9edafa3980385324ce6a48edcda Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 29 Jan 2013 00:47:37 +0800 Subject: mfd: arizona: Provide platform data for MICBIAS configuration Allow the MICBIAS voltages and other attributes to be configured by the platform. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/arizona/pdata.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 8b1d1daaae16..37894d6a4f6f 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -56,6 +56,8 @@ #define ARIZONA_DMIC_MICBIAS2 2 #define ARIZONA_DMIC_MICBIAS3 3 +#define ARIZONA_MAX_MICBIAS 3 + #define ARIZONA_INMODE_DIFF 0 #define ARIZONA_INMODE_SE 1 #define ARIZONA_INMODE_DMIC 2 @@ -69,6 +71,13 @@ struct regulator_init_data; +struct arizona_micbias { + int mV; /** Regulated voltage */ + unsigned int ext_cap:1; /** External capacitor fitted */ + unsigned int discharge:1; /** Actively discharge */ + unsigned int fast_start:1; /** Enable aggressive startup ramp rate */ +}; + struct arizona_micd_config { unsigned int src; unsigned int bias; @@ -106,6 +115,9 @@ struct arizona_pdata { /** Reference voltage for DMIC inputs */ int dmic_ref[ARIZONA_MAX_INPUT]; + /** MICBIAS configurations */ + struct arizona_micbias micbias[ARIZONA_MAX_MICBIAS]; + /** Mode of input structures */ int inmode[ARIZONA_MAX_INPUT]; -- cgit v1.2.3 From 5d4e9bd79a5ab5bd4695d3becaa71da447a76a94 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Wed, 16 Jan 2013 14:53:50 +0100 Subject: mfd: twl-core: Clean up module id lookup and definitions Use enums for all module definitions: twl_module_ids for common functionality among twl4030/twl6030 twl4030_module_ids for twl4030 specific ids twl6030_module_ids for twl6030 specific ids In this way the list can be managed easier when new functionality going to be implemented. Signed-off-by: Peter Ujfalusi Signed-off-by: Samuel Ortiz --- include/linux/i2c/twl.h | 66 ++++++++++++++++++++++++++----------------------- 1 file changed, 35 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h index 1ff54b114efc..72adc8807912 100644 --- a/include/linux/i2c/twl.h +++ b/include/linux/i2c/twl.h @@ -39,51 +39,55 @@ * address each module uses within a given i2c slave. */ +/* Module IDs for similar functionalities found in twl4030/twl6030 */ +enum twl_module_ids { + TWL_MODULE_USB, + TWL_MODULE_PIH, + TWL_MODULE_MAIN_CHARGE, + TWL_MODULE_PM_MASTER, + TWL_MODULE_PM_RECEIVER, + + TWL_MODULE_RTC, + TWL_MODULE_PWM, + TWL_MODULE_LED, + TWL_MODULE_SECURED_REG, + + TWL_MODULE_LAST, +}; + +/* Modules only available in twl4030 series */ enum twl4030_module_ids { - TWL4030_MODULE_USB = 0, /* Slave 0 (i2c address 0x48) */ - TWL4030_MODULE_AUDIO_VOICE, /* Slave 1 (i2c address 0x49) */ + TWL4030_MODULE_AUDIO_VOICE = TWL_MODULE_LAST, TWL4030_MODULE_GPIO, TWL4030_MODULE_INTBR, - TWL4030_MODULE_PIH, - TWL4030_MODULE_TEST, - TWL4030_MODULE_KEYPAD, /* Slave 2 (i2c address 0x4a) */ + TWL4030_MODULE_KEYPAD, + TWL4030_MODULE_MADC, TWL4030_MODULE_INTERRUPTS, - TWL4030_MODULE_LED, - - TWL4030_MODULE_MAIN_CHARGE, TWL4030_MODULE_PRECHARGE, - TWL4030_MODULE_PWM0, - TWL4030_MODULE_PWM1, - TWL4030_MODULE_PWMA, + TWL4030_MODULE_BACKUP, + TWL4030_MODULE_INT, - TWL4030_MODULE_PWMB, TWL5031_MODULE_ACCESSORY, TWL5031_MODULE_INTERRUPTS, - TWL4030_MODULE_BACKUP, /* Slave 3 (i2c address 0x4b) */ - TWL4030_MODULE_INT, - TWL4030_MODULE_PM_MASTER, - TWL4030_MODULE_PM_RECEIVER, - TWL4030_MODULE_RTC, - TWL4030_MODULE_SECURED_REG, TWL4030_MODULE_LAST, }; -/* Similar functionalities implemented in TWL4030/6030 */ -#define TWL_MODULE_USB TWL4030_MODULE_USB -#define TWL_MODULE_PIH TWL4030_MODULE_PIH -#define TWL_MODULE_MAIN_CHARGE TWL4030_MODULE_MAIN_CHARGE -#define TWL_MODULE_PM_MASTER TWL4030_MODULE_PM_MASTER -#define TWL_MODULE_PM_RECEIVER TWL4030_MODULE_PM_RECEIVER -#define TWL_MODULE_RTC TWL4030_MODULE_RTC -#define TWL_MODULE_PWM TWL4030_MODULE_PWM0 -#define TWL_MODULE_LED TWL4030_MODULE_LED - -#define TWL6030_MODULE_ID0 13 -#define TWL6030_MODULE_ID1 14 -#define TWL6030_MODULE_ID2 15 +/* Modules only available in twl6030 series */ +enum twl6030_module_ids { + TWL6030_MODULE_ID0 = TWL_MODULE_LAST, + TWL6030_MODULE_ID1, + TWL6030_MODULE_ID2, + TWL6030_MODULE_GPADC, + TWL6030_MODULE_GASGAUGE, + + TWL6030_MODULE_LAST, +}; + +/* Until the clients has been converted to use TWL_MODULE_LED */ +#define TWL4030_MODULE_LED TWL_MODULE_LED #define GPIO_INTR_OFFSET 0 #define KEYPAD_INTR_OFFSET 1 -- cgit v1.2.3 From ac7bc5a953c38c32513d1825decf336c4909ce3b Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Wed, 16 Jan 2013 14:53:58 +0100 Subject: mfd: twl-core: Remove no longer valid comment regarding to write buffer size With the regmap conversion there is no longeer a need to allocate bigger buffer for writes Signed-off-by: Peter Ujfalusi Signed-off-by: Samuel Ortiz --- include/linux/i2c/twl.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h index 72adc8807912..e441fd8e7c86 100644 --- a/include/linux/i2c/twl.h +++ b/include/linux/i2c/twl.h @@ -182,9 +182,6 @@ int twl_i2c_read_u8(u8 mod_no, u8 *val, u8 reg); /* * Read and write several 8-bit registers at once. - * - * IMPORTANT: For twl_i2c_write(), allocate num_bytes + 1 - * for the value, and populate your data starting at offset 1. */ int twl_i2c_write(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes); int twl_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes); -- cgit v1.2.3 From fbc6ae363e5e589a28135c051a2ff835e6236d5f Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Wed, 16 Jan 2013 14:53:59 +0100 Subject: mfd: twl-core: Move twl_i2c_read/write_u8 to header as inline function twl_i2c_read/write_u8 become as a simple wrapper over the twl_i2c_read/write. Signed-off-by: Peter Ujfalusi Signed-off-by: Samuel Ortiz --- include/linux/i2c/twl.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h index e441fd8e7c86..488debbef895 100644 --- a/include/linux/i2c/twl.h +++ b/include/linux/i2c/twl.h @@ -174,18 +174,23 @@ static inline int twl_class_is_ ##class(void) \ TWL_CLASS_IS(4030, TWL4030_CLASS_ID) TWL_CLASS_IS(6030, TWL6030_CLASS_ID) -/* - * Read and write single 8-bit registers - */ -int twl_i2c_write_u8(u8 mod_no, u8 val, u8 reg); -int twl_i2c_read_u8(u8 mod_no, u8 *val, u8 reg); - /* * Read and write several 8-bit registers at once. */ int twl_i2c_write(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes); int twl_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes); +/* + * Read and write single 8-bit registers + */ +static inline int twl_i2c_write_u8(u8 mod_no, u8 val, u8 reg) { + return twl_i2c_write(mod_no, &val, reg, 1); +} + +static inline int twl_i2c_read_u8(u8 mod_no, u8 *val, u8 reg) { + return twl_i2c_read(mod_no, val, reg, 1); +} + int twl_get_type(void); int twl_get_version(void); int twl_get_hfclk_rate(void); -- cgit v1.2.3 From 98c60a0d3afc8f68e6e4b85b93df14e238fec3cb Mon Sep 17 00:00:00 2001 From: Fabio Baltieri Date: Fri, 18 Jan 2013 12:40:11 +0100 Subject: mfd: dbx500-prcmu: Add watchdog ID definitions Add definition of watchdog IDs to be used by ux500_wdt driver. Acked-by: Lee Jones Acked-by: Linus Walleij Signed-off-by: Fabio Baltieri Signed-off-by: Samuel Ortiz --- include/linux/mfd/dbx500-prcmu.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index c202d6c4d879..c6e0608a21b5 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -146,6 +146,18 @@ enum prcmu_clock { PRCMU_DSI2ESCCLK, }; +/** + * enum prcmu_wdog_id - PRCMU watchdog IDs + * @PRCMU_WDOG_ALL: use all timers + * @PRCMU_WDOG_CPU1: use first CPU timer only + * @PRCMU_WDOG_CPU2: use second CPU timer conly + */ +enum prcmu_wdog_id { + PRCMU_WDOG_ALL = 0x00, + PRCMU_WDOG_CPU1 = 0x01, + PRCMU_WDOG_CPU2 = 0x02, +}; + /** * enum ape_opp - APE OPP states definition * @APE_OPP_INIT: -- cgit v1.2.3 From f0e5bd412fde30de3839c8dfa93a3e19e71ee462 Mon Sep 17 00:00:00 2001 From: Fabio Baltieri Date: Tue, 29 Jan 2013 09:57:19 +0100 Subject: watchdog: Add support for ux500_wdt watchdog This patch adds support for the ux500_wdt watchdog that is found in ST-Ericsson Ux500 platform. The driver is based on PRCMU APIs. Acked-by: Linus Walleij Acked-by: Lee Jones Acked-by: Wim Van Sebroeck Signed-off-by: Fabio Baltieri Signed-off-by: Samuel Ortiz --- include/linux/platform_data/ux500_wdt.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/platform_data/ux500_wdt.h (limited to 'include/linux') diff --git a/include/linux/platform_data/ux500_wdt.h b/include/linux/platform_data/ux500_wdt.h new file mode 100644 index 000000000000..1689ff4c3bfd --- /dev/null +++ b/include/linux/platform_data/ux500_wdt.h @@ -0,0 +1,19 @@ +/* + * Copyright (C) ST Ericsson SA 2011 + * + * License Terms: GNU General Public License v2 + * + * STE Ux500 Watchdog platform data + */ +#ifndef __UX500_WDT_H +#define __UX500_WDT_H + +/** + * struct ux500_wdt_data + */ +struct ux500_wdt_data { + unsigned int timeout; + bool has_28_bits_resolution; +}; + +#endif /* __UX500_WDT_H */ -- cgit v1.2.3 From 306df798507d8e009a7d4a5e8ce238a3b107de20 Mon Sep 17 00:00:00 2001 From: Yi Zhang Date: Tue, 22 Jan 2013 10:43:45 +0800 Subject: mfd: 88pm80x: Remove redundant devm_* calls devm_* functions are device managed and make error handling and code simpler; it also fix error exit paths Signed-off-by: Yi Zhang Signed-off-by: Samuel Ortiz --- include/linux/mfd/88pm80x.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/88pm80x.h b/include/linux/mfd/88pm80x.h index 478672ed0c3d..e94537befabd 100644 --- a/include/linux/mfd/88pm80x.h +++ b/include/linux/mfd/88pm80x.h @@ -365,5 +365,5 @@ static inline int pm80x_dev_resume(struct device *dev) extern int pm80x_init(struct i2c_client *client, const struct i2c_device_id *id); -extern int pm80x_deinit(struct i2c_client *client); +extern int pm80x_deinit(void); #endif /* __LINUX_MFD_88PM80X_H */ -- cgit v1.2.3 From 5f384c1f8be19487f904731d7232120dcfeca8e1 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 25 Jan 2013 17:09:23 +0800 Subject: mfd: wm5102: Make DSP scratch registers readable Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/arizona/registers.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h index 1f6fe31a4d5c..718126084ad1 100644 --- a/include/linux/mfd/arizona/registers.h +++ b/include/linux/mfd/arizona/registers.h @@ -982,18 +982,34 @@ #define ARIZONA_DSP1_STATUS_1 0x1104 #define ARIZONA_DSP1_STATUS_2 0x1105 #define ARIZONA_DSP1_STATUS_3 0x1106 +#define ARIZONA_DSP1_SCRATCH_0 0x1140 +#define ARIZONA_DSP1_SCRATCH_1 0x1141 +#define ARIZONA_DSP1_SCRATCH_2 0x1142 +#define ARIZONA_DSP1_SCRATCH_3 0x1143 #define ARIZONA_DSP2_CONTROL_1 0x1200 #define ARIZONA_DSP2_CLOCKING_1 0x1201 #define ARIZONA_DSP2_STATUS_1 0x1204 #define ARIZONA_DSP2_STATUS_2 0x1205 +#define ARIZONA_DSP2_SCRATCH_0 0x1240 +#define ARIZONA_DSP2_SCRATCH_1 0x1241 +#define ARIZONA_DSP2_SCRATCH_2 0x1242 +#define ARIZONA_DSP2_SCRATCH_3 0x1243 #define ARIZONA_DSP3_CONTROL_1 0x1300 #define ARIZONA_DSP3_CLOCKING_1 0x1301 #define ARIZONA_DSP3_STATUS_1 0x1304 #define ARIZONA_DSP3_STATUS_2 0x1305 +#define ARIZONA_DSP3_SCRATCH_0 0x1340 +#define ARIZONA_DSP3_SCRATCH_1 0x1341 +#define ARIZONA_DSP3_SCRATCH_2 0x1342 +#define ARIZONA_DSP3_SCRATCH_3 0x1343 #define ARIZONA_DSP4_CONTROL_1 0x1400 #define ARIZONA_DSP4_CLOCKING_1 0x1401 #define ARIZONA_DSP4_STATUS_1 0x1404 #define ARIZONA_DSP4_STATUS_2 0x1405 +#define ARIZONA_DSP4_SCRATCH_0 0x1440 +#define ARIZONA_DSP4_SCRATCH_1 0x1441 +#define ARIZONA_DSP4_SCRATCH_2 0x1442 +#define ARIZONA_DSP4_SCRATCH_3 0x1443 /* * Field Definitions. -- cgit v1.2.3 From 3730bb8b65f9ee8b7097021f8073b80511af770d Mon Sep 17 00:00:00 2001 From: Wei WANG Date: Tue, 29 Jan 2013 15:21:32 +0800 Subject: mfd: rtsx: Fix typo in comment Fix a misspelling word in comment Signed-off-by: Wei WANG Signed-off-by: Samuel Ortiz --- include/linux/mfd/rtsx_pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 4b117a3f54d4..3f2bf26ca0d1 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -465,7 +465,7 @@ #define SD_RSP_TYPE_R6 0x01 #define SD_RSP_TYPE_R7 0x01 -/* SD_CONFIURE3 */ +/* SD_CONFIGURE3 */ #define SD_RSP_80CLK_TIMEOUT_EN 0x01 /* Card Transfer Reset Register */ -- cgit v1.2.3 From 8ea402f5646e6e36c8cd0a62053ba8939204dceb Mon Sep 17 00:00:00 2001 From: Pawel Moll Date: Wed, 30 Jan 2013 10:33:16 +0000 Subject: mfd: vexpress: Add pseudo-GPIO based LEDs The LEDs on the Versatile Express motherboard are controlled through simple memory-mapped register. This patch extends the pseudo-GPIO controller definition for these lines and creates generic "leds-gpio" device using them Signed-off-by: Pawel Moll Signed-off-by: Samuel Ortiz --- include/linux/vexpress.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h index c52215ff4245..75818744ab59 100644 --- a/include/linux/vexpress.h +++ b/include/linux/vexpress.h @@ -27,6 +27,14 @@ #define VEXPRESS_GPIO_MMC_CARDIN 0 #define VEXPRESS_GPIO_MMC_WPROT 1 #define VEXPRESS_GPIO_FLASH_WPn 2 +#define VEXPRESS_GPIO_LED0 3 +#define VEXPRESS_GPIO_LED1 4 +#define VEXPRESS_GPIO_LED2 5 +#define VEXPRESS_GPIO_LED3 6 +#define VEXPRESS_GPIO_LED4 7 +#define VEXPRESS_GPIO_LED5 8 +#define VEXPRESS_GPIO_LED6 9 +#define VEXPRESS_GPIO_LED7 10 #define VEXPRESS_RES_FUNC(_site, _func) \ { \ -- cgit v1.2.3 From e12379320b2e1ceffc4211ad174989bc042149d9 Mon Sep 17 00:00:00 2001 From: Roger Tseng Date: Mon, 4 Feb 2013 15:45:59 +0800 Subject: mfd: rtsx: Support RTS5227 Support new model RTS5227. Signed-off-by: Roger Tseng Reviewed-by: Wei WANG Signed-off-by: Samuel Ortiz --- include/linux/mfd/rtsx_pci.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 3f2bf26ca0d1..5d9b81e8aff4 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -581,8 +581,11 @@ #define CARD_GPIO_DIR 0xFD57 #define CARD_GPIO 0xFD58 #define CARD_DATA_SOURCE 0xFD5B +#define SD30_CLK_DRIVE_SEL 0xFD5A #define CARD_SELECT 0xFD5C #define SD30_DRIVE_SEL 0xFD5E +#define SD30_CMD_DRIVE_SEL 0xFD5E +#define SD30_DAT_DRIVE_SEL 0xFD5F #define CARD_CLK_EN 0xFD69 #define SDIO_CTRL 0xFD6B #define CD_PAD_CTL 0xFD73 @@ -655,6 +658,8 @@ #define MSGTXDATA3 0xFE47 #define MSGTXCTL 0xFE48 #define PETXCFG 0xFE49 +#define LTR_CTL 0xFE4A +#define OBFF_CFG 0xFE4C #define CDRESUMECTL 0xFE52 #define WAKE_SEL_CTL 0xFE54 -- cgit v1.2.3 From 4e405ae256b7e04f7c1213136f3bfd9fb76e2023 Mon Sep 17 00:00:00 2001 From: Qing Xu Date: Mon, 4 Feb 2013 23:40:42 +0800 Subject: mfd: max8925: Add irqdomain for dt Add irqdomains for max8925's main irq, wrap irq register operations into irqdomain's map func. it is necessary for dt support. Also, add dt support for max8925 driver. Signed-off-by: Qing Xu Signed-off-by: Haojian Zhuang Signed-off-by: Samuel Ortiz --- include/linux/mfd/max8925.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/max8925.h b/include/linux/mfd/max8925.h index 74d8e2969630..ce8502e9e7dc 100644 --- a/include/linux/mfd/max8925.h +++ b/include/linux/mfd/max8925.h @@ -190,6 +190,8 @@ enum { MAX8925_NR_IRQS, }; + + struct max8925_chip { struct device *dev; struct i2c_client *i2c; @@ -201,7 +203,6 @@ struct max8925_chip { int irq_base; int core_irq; int tsc_irq; - unsigned int wakeup_flag; }; -- cgit v1.2.3 From c3481955f6c78c8dd99921759306d7469c999ec2 Mon Sep 17 00:00:00 2001 From: Wei WANG Date: Fri, 8 Feb 2013 15:24:27 +0800 Subject: mfd: rtsx: Fix issue that booting OS with SD card inserted Realtek card reader supports both SD and MS card. According to the settings of rtsx MFD driver, SD host will be probed before MS host. If we boot/reboot Linux with SD card inserted, the resetting flow of SD card will succeed, and the following resetting flow of MS is sure to fail. Then MS upper-level driver will ask rtsx driver to turn power off. This request leads to the result that the following SD commands fail and SD card can't be accessed again. In this commit, Realtek's SD and MS host driver will check whether the card that upper driver requesting is the one existing in the slot. If not, Realtek's host driver will refuse the operation to make sure the exlusive accessing at the same time. Signed-off-by: Wei WANG Signed-off-by: Samuel Ortiz --- include/linux/mfd/rtsx_pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 5d9b81e8aff4..26ea7f1b7caf 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -740,6 +740,7 @@ struct rtsx_pcr { unsigned int card_inserted; unsigned int card_removed; + unsigned int card_exist; struct delayed_work carddet_work; struct delayed_work idle_work; @@ -804,6 +805,7 @@ int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock, u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk); int rtsx_pci_card_power_on(struct rtsx_pcr *pcr, int card); int rtsx_pci_card_power_off(struct rtsx_pcr *pcr, int card); +int rtsx_pci_card_exclusive_check(struct rtsx_pcr *pcr, int card); int rtsx_pci_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage); unsigned int rtsx_pci_card_exist(struct rtsx_pcr *pcr); void rtsx_pci_complete_unfinished_transfer(struct rtsx_pcr *pcr); -- cgit v1.2.3 From 3ebc21f7bc2f9c0145bbbf0f12430b766a200f9f Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 31 Jan 2013 16:02:01 -0600 Subject: libceph: fix messenger CONFIG_BLOCK dependencies The ceph messenger has a few spots that are only used when bio messages are supported, and that's only when CONFIG_BLOCK is defined. This surrounds a couple of spots with #ifdef's that would cause a problem if CONFIG_BLOCK were not present in the kernel configuration. This resolves: http://tracker.ceph.com/issues/3976 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 14ba5ee738a9..60903e0f665c 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -83,9 +83,11 @@ struct ceph_msg { struct list_head list_head; struct kref kref; +#ifdef CONFIG_BLOCK struct bio *bio; /* instead of pages/pagelist */ struct bio *bio_iter; /* bio iterator */ int bio_seg; /* current bio segment */ +#endif /* CONFIG_BLOCK */ struct ceph_pagelist *trail; /* the trailing part of the data */ bool front_is_vmalloc; bool more_to_follow; -- cgit v1.2.3 From 72fe25e3460c8673984370208e0e6261101372d6 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 30 Jan 2013 11:13:33 -0600 Subject: libceph: add a compatibility check interface An upcoming change implements semantic change that could lead to a crash if an old version of the libceph kernel module is used with a new version of the rbd kernel module. In order to preclude that possibility, this adds a compatibilty check interface. If this interface doesn't exist, the modules are obviously not compatible. But if it does exist, this provides a way of letting the caller know whether it will operate properly with this libceph module. Perhaps confusingly, it returns false right now. The semantic change mentioned above will make it return true. This resolves: http://tracker.ceph.com/issues/3800 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/libceph.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 084d3c622b12..c44275ab375c 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -193,6 +193,8 @@ static inline int calc_pages_for(u64 off, u64 len) } /* ceph_common.c */ +extern bool libceph_compatible(void *data); + extern const char *ceph_msg_type_name(int type); extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); extern struct kmem_cache *ceph_inode_cachep; -- cgit v1.2.3 From e9b04b5b67ec628a5e9a312e14b6864f8f73ba12 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 20 Nov 2012 11:14:10 -0500 Subject: make do_sigaltstack() static Signed-off-by: Al Viro --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8f983293b403..6dd06494997a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2259,7 +2259,6 @@ extern struct sigqueue *sigqueue_alloc(void); extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); -extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long); static inline void restore_saved_sigmask(void) { -- cgit v1.2.3 From d64008a8f30e0b381b292788ec6f3ee509b3bb40 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 25 Nov 2012 23:12:10 -0500 Subject: burying unused conditionals __ARCH_WANT_SYS_RT_SIGACTION, __ARCH_WANT_SYS_RT_SIGSUSPEND, __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND, __ARCH_WANT_COMPAT_SYS_SCHED_RR_GET_INTERVAL - not used anymore CONFIG_GENERIC_{SIGALTSTACK,COMPAT_RT_SIG{ACTION,QUEUEINFO,PENDING,PROCMASK}} - can be assumed always set. --- include/linux/compat.h | 14 -------------- include/linux/syscalls.h | 2 -- 2 files changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 8de903587fb9..de095b0462a7 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -68,7 +68,6 @@ #ifndef compat_user_stack_pointer #define compat_user_stack_pointer() current_user_stack_pointer() #endif -#ifdef CONFIG_GENERIC_SIGALTSTACK #ifndef compat_sigaltstack /* we'll need that for MIPS */ typedef struct compat_sigaltstack { compat_uptr_t ss_sp; @@ -76,7 +75,6 @@ typedef struct compat_sigaltstack { compat_size_t ss_size; } compat_stack_t; #endif -#endif #define compat_jiffies_to_clock_t(x) \ (((unsigned long)(x) * COMPAT_USER_HZ) / HZ) @@ -142,7 +140,6 @@ typedef struct { compat_sigset_word sig[_COMPAT_NSIG_WORDS]; } compat_sigset_t; -#ifdef CONFIG_GENERIC_COMPAT_RT_SIGACTION struct compat_sigaction { #ifndef __ARCH_HAS_ODD_SIGACTION compat_uptr_t sa_handler; @@ -156,7 +153,6 @@ struct compat_sigaction { #endif compat_sigset_t sa_mask __packed; }; -#endif /* * These functions operate strictly on struct compat_time* @@ -623,27 +619,19 @@ asmlinkage long compat_sys_rt_sigtimedwait(compat_sigset_t __user *uthese, struct compat_timespec __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat_size_t sigsetsize); -#ifdef CONFIG_GENERIC_COMPAT_RT_SIGPROCMASK asmlinkage long compat_sys_rt_sigprocmask(int how, compat_sigset_t __user *set, compat_sigset_t __user *oset, compat_size_t sigsetsize); -#endif -#ifdef CONFIG_GENERIC_COMPAT_RT_SIGPENDING asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, compat_size_t sigsetsize); -#endif #ifndef CONFIG_ODD_RT_SIGACTION -#ifdef CONFIG_GENERIC_COMPAT_RT_SIGACTION asmlinkage long compat_sys_rt_sigaction(int, const struct compat_sigaction __user *, struct compat_sigaction __user *, compat_size_t); #endif -#endif -#ifdef CONFIG_GENERIC_COMPAT_RT_SIGQUEUEINFO asmlinkage long compat_sys_rt_sigqueueinfo(compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); -#endif asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info); asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); @@ -694,13 +682,11 @@ asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid, asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, compat_size_t count); -#ifdef CONFIG_GENERIC_SIGALTSTACK asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, compat_stack_t __user *uoss_ptr); int compat_restore_altstack(const compat_stack_t __user *uss); int __compat_save_altstack(compat_stack_t __user *, unsigned long); -#endif asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, struct compat_timespec __user *interval); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 66d298f69f98..313a8e0a6553 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -300,10 +300,8 @@ asmlinkage long sys_personality(unsigned int personality); asmlinkage long sys_sigpending(old_sigset_t __user *set); asmlinkage long sys_sigprocmask(int how, old_sigset_t __user *set, old_sigset_t __user *oset); -#ifdef CONFIG_GENERIC_SIGALTSTACK asmlinkage long sys_sigaltstack(const struct sigaltstack __user *uss, struct sigaltstack __user *uoss); -#endif asmlinkage long sys_getitimer(int which, struct itimerval __user *value); asmlinkage long sys_setitimer(int which, -- cgit v1.2.3 From 978c4172af48f0adc082f8b1d94acb817d947730 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 14 Feb 2013 11:00:16 +0200 Subject: dmaengine.h: remove redundant else keyword dmaengine_device_control returns -ENOSYS in case the dma driver doesn't have such functionality. Signed-off-by: Andy Shevchenko Acked-by: Viresh Kumar Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index bfcdecb5d87a..f5939999cb65 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -610,8 +610,8 @@ static inline int dmaengine_device_control(struct dma_chan *chan, { if (chan->device->device_control) return chan->device->device_control(chan, cmd, arg); - else - return -ENOSYS; + + return -ENOSYS; } static inline int dmaengine_slave_config(struct dma_chan *chan, -- cgit v1.2.3 From abf09bed3cceadd809f0356065c2ada6cee90d4a Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Wed, 7 Nov 2012 13:17:37 +0100 Subject: s390/mm: implement software dirty bits The s390 architecture is unique in respect to dirty page detection, it uses the change bit in the per-page storage key to track page modifications. All other architectures track dirty bits by means of page table entries. This property of s390 has caused numerous problems in the past, e.g. see git commit ef5d437f71afdf4a "mm: fix XFS oops due to dirty pages without buffers on s390". To avoid future issues in regard to per-page dirty bits convert s390 to a fault based software dirty bit detection mechanism. All user page table entries which are marked as clean will be hardware read-only, even if the pte is supposed to be writable. A write by the user process will trigger a protection fault which will cause the user pte to be marked as dirty and the hardware read-only bit is removed. With this change the dirty bit in the storage key is irrelevant for Linux as a host, but the storage key is still required for KVM guests. The effect is that page_test_and_clear_dirty and the related code can be removed. The referenced bit in the storage key is still used by the page_test_and_clear_young primitive to provide page age information. For page cache pages of mappings with mapping_cap_account_dirty there will not be any change in behavior as the dirty bit tracking already uses read-only ptes to control the amount of dirty pages. Only for swap cache pages and pages of mappings without mapping_cap_account_dirty there can be additional protection faults. To avoid an excessive number of additional faults the mk_pte primitive checks for PageDirty if the pgprot value allows for writes and pre-dirties the pte. That avoids all additional faults for tmpfs and shmem pages until these pages are added to the swap cache. Signed-off-by: Martin Schwidefsky --- include/linux/page-flags.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 70473da47b3f..6d53675c2b54 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -303,21 +303,13 @@ static inline void __SetPageUptodate(struct page *page) static inline void SetPageUptodate(struct page *page) { -#ifdef CONFIG_S390 - if (!test_and_set_bit(PG_uptodate, &page->flags)) - page_set_storage_key(page_to_phys(page), PAGE_DEFAULT_KEY, 0); -#else /* * Memory barrier must be issued before setting the PG_uptodate bit, * so that all previous stores issued in order to bring the page * uptodate are actually visible before PageUptodate becomes true. - * - * s390 doesn't need an explicit smp_wmb here because the test and - * set bit already provides full barriers. */ smp_wmb(); set_bit(PG_uptodate, &(page)->flags); -#endif } CLEARPAGEFLAG(Uptodate, uptodate) -- cgit v1.2.3 From 73fb847a44224d5708550e4be7baba9da75e00af Mon Sep 17 00:00:00 2001 From: Stanislav Kinsbursky Date: Mon, 4 Feb 2013 14:02:45 +0300 Subject: SUNRPC: introduce cache_detail->cache_request callback This callback will allow to simplify upcalls in further patches in this series. Signed-off-by: Stanislav Kinsbursky Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 5dc9ee4d616e..4f1c8582053c 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -83,6 +83,10 @@ struct cache_detail { int (*cache_upcall)(struct cache_detail *, struct cache_head *); + void (*cache_request)(struct cache_detail *cd, + struct cache_head *ch, + char **bpp, int *blen); + int (*cache_parse)(struct cache_detail *, char *buf, int len); -- cgit v1.2.3 From 21cd1254d3402a72927ed744e8ac1a7cf532f1ea Mon Sep 17 00:00:00 2001 From: Stanislav Kinsbursky Date: Mon, 4 Feb 2013 14:02:55 +0300 Subject: SUNRPC: remove "cache_request" argument in sunrpc_cache_pipe_upcall() function Passing this pointer is redundant since it's stored on cache_detail structure, which is also passed to sunrpc_cache_pipe_upcall () function. Signed-off-by: Stanislav Kinsbursky Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 4f1c8582053c..303399b1ba59 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -161,11 +161,7 @@ sunrpc_cache_update(struct cache_detail *detail, struct cache_head *new, struct cache_head *old, int hash); extern int -sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h, - void (*cache_request)(struct cache_detail *, - struct cache_head *, - char **, - int *)); +sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h); extern void cache_clean_deferred(void *owner); -- cgit v1.2.3 From 686855f5d833178e518d79e7912cdb3268a9fa69 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 14 Feb 2013 18:19:58 +0400 Subject: sched: add wait_for_completion_io[_timeout] The only difference between wait_for_completion[_timeout]() and wait_for_completion_io[_timeout]() is that the latter calls io_schedule_timeout() instead of schedule_timeout() so that the caller is accounted as waiting for IO, not just sleeping. These functions can be used for correct iowait time accounting when the completion struct is actually used for waiting for IO (e.g. completion of a bio request in the block layer). Signed-off-by: Vladimir Davydov Acked-by: Ingo Molnar Signed-off-by: Jens Axboe --- include/linux/completion.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/completion.h b/include/linux/completion.h index 51494e6b5548..33f0280fd533 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -77,10 +77,13 @@ static inline void init_completion(struct completion *x) } extern void wait_for_completion(struct completion *); +extern void wait_for_completion_io(struct completion *); extern int wait_for_completion_interruptible(struct completion *x); extern int wait_for_completion_killable(struct completion *x); extern unsigned long wait_for_completion_timeout(struct completion *x, unsigned long timeout); +extern unsigned long wait_for_completion_io_timeout(struct completion *x, + unsigned long timeout); extern long wait_for_completion_interruptible_timeout( struct completion *x, unsigned long timeout); extern long wait_for_completion_killable_timeout( -- cgit v1.2.3 From f25cc71e634edcf8a15bc60a48f2b5f3ec9fbb1d Mon Sep 17 00:00:00 2001 From: Tim Gardner Date: Wed, 13 Feb 2013 08:40:16 -0700 Subject: lockd: nlmclnt_reclaim(): avoid stack overflow Even though nlmclnt_reclaim() is only one call into the stack frame, 928 bytes on the stack seems like a lot. Recode to dynamically allocate the request structure once from within the reclaimer task, then pass this pointer into nlmclnt_reclaim() for reuse on subsequent calls. smatch analysis: fs/lockd/clntproc.c:620 nlmclnt_reclaim() warn: 'reqst' puts 928 bytes on stack Also remove redundant assignment of 0 after memset. Cc: Trond Myklebust Signed-off-by: Tim Gardner Reviewed-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/linux/lockd/lockd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index f5a051a79273..a395f1e7998f 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -212,7 +212,8 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout) __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock); void nlmclnt_recovery(struct nlm_host *); -int nlmclnt_reclaim(struct nlm_host *, struct file_lock *); +int nlmclnt_reclaim(struct nlm_host *, struct file_lock *, + struct nlm_rqst *); void nlmclnt_next_cookie(struct nlm_cookie *); /* -- cgit v1.2.3 From e7e319a9c51409c7effe34333ea26facf2fab9e1 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Feb 2013 12:16:43 -0600 Subject: libceph: improve packing in struct ceph_osd_req_op The layout of struct ceph_osd_req_op leaves lots of holes. Rearranging things a little for better field alignment reduces the size by a third. This resolves: http://tracker.ceph.com/issues/4163 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 69287ccfe68a..82bf6338d6c1 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -157,6 +157,7 @@ struct ceph_osd_client { struct ceph_osd_req_op { u16 op; /* CEPH_OSD_OP_* */ + u32 payload_len; union { struct { u64 offset, length; @@ -165,23 +166,24 @@ struct ceph_osd_req_op { } extent; struct { const char *name; - u32 name_len; const char *val; + u32 name_len; u32 value_len; __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */ } xattr; struct { const char *class_name; - __u8 class_len; const char *method_name; - __u8 method_len; - __u8 argc; const char *indata; u32 indata_len; + __u8 class_len; + __u8 method_len; + __u8 argc; } cls; struct { - u64 cookie, count; + u64 cookie; + u64 count; } pgls; struct { u64 snapid; @@ -189,12 +191,11 @@ struct ceph_osd_req_op { struct { u64 cookie; u64 ver; - __u8 flag; u32 prot_ver; u32 timeout; + __u8 flag; } watch; }; - u32 payload_len; }; extern int ceph_osdc_init(struct ceph_osd_client *osdc, -- cgit v1.2.3 From 87f979d390f9ecfa3d0038a9f9a002a62f8a1895 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 15 Feb 2013 11:42:29 -0600 Subject: ceph: kill ceph_osdc_writepages() "nofail" parameter There is only one caller of ceph_osdc_writepages(), and it always passes the value true as its "nofail" argument. Get rid of that argument and replace its use in ceph_osdc_writepages() with the constant value true. This and a number of cleanup patches that follow resolve: http://tracker.ceph.com/issues/4126 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 82bf6338d6c1..afcb255b016a 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -275,7 +275,7 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, u32 truncate_seq, u64 truncate_size, struct timespec *mtime, struct page **pages, int nr_pages, - int flags, int do_sync, bool nofail); + int flags, int do_sync); /* watch/notify events */ extern int ceph_osdc_create_event(struct ceph_osd_client *osdc, -- cgit v1.2.3 From fbf8685fb155e12a9f4d4b966c7b3442ed557687 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 15 Feb 2013 11:42:29 -0600 Subject: ceph: kill ceph_osdc_writepages() "dosync" parameter There is only one caller of ceph_osdc_writepages(), and it always passes 0 as its "dosync" argument. Get rid of that argument and replace its use in ceph_osdc_writepages() with 0. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index afcb255b016a..7a63100a3e69 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -275,7 +275,7 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, u32 truncate_seq, u64 truncate_size, struct timespec *mtime, struct page **pages, int nr_pages, - int flags, int do_sync); + int flags); /* watch/notify events */ extern int ceph_osdc_create_event(struct ceph_osd_client *osdc, -- cgit v1.2.3 From 2480882611e3ab844563dd3d0a822227604ab8fe Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 15 Feb 2013 11:42:29 -0600 Subject: ceph: kill ceph_osdc_writepages() "flags" parameter There is only one caller of ceph_osdc_writepages(), and it always passes 0 as its "flags" argument. Get rid of that argument and replace its use in ceph_osdc_writepages() with 0. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 7a63100a3e69..6540e8861998 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -274,8 +274,7 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, u64 off, u64 len, u32 truncate_seq, u64 truncate_size, struct timespec *mtime, - struct page **pages, int nr_pages, - int flags); + struct page **pages, int nr_pages); /* watch/notify events */ extern int ceph_osdc_create_event(struct ceph_osd_client *osdc, -- cgit v1.2.3 From a3bea47e8bdd51d921e5b2045720d60140612c7c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 15 Feb 2013 11:42:29 -0600 Subject: ceph: kill ceph_osdc_new_request() "num_reply" parameter The "num_reply" parameter to ceph_osdc_new_request() is never used inside that function, so get rid of it. Note that ceph_sync_write() passes 2 for that argument, while all other callers pass 1. It doesn't matter, but perhaps someone should verify this doesn't indicate a problem. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 6540e8861998..5812802bd8ae 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -234,8 +234,7 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, int do_sync, u32 truncate_seq, u64 truncate_size, struct timespec *mtime, - bool use_mempool, int num_reply, - int page_align); + bool use_mempool, int page_align); extern void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc, struct ceph_osd_request *req); -- cgit v1.2.3 From 60e56f138180e72fa8487d4b9c1c916013494f46 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 15 Feb 2013 11:42:29 -0600 Subject: libceph: kill ceph_calc_raw_layout() There is no caller of ceph_calc_raw_layout() outside of libceph, so there's no need to export from the module. Furthermore, there is only one caller, in calc_layout(), and it is not much more than a simple wrapper for that function. So get rid of ceph_calc_raw_layout() and embed it instead within calc_layout(). While touching "osd_client.c", get rid of the unnecessary forward declaration of __send_request(). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 5812802bd8ae..c39e7ed4b203 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -207,11 +207,6 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); -extern int ceph_calc_raw_layout(struct ceph_file_layout *layout, - u64 off, u64 *plen, u64 *bno, - struct ceph_osd_request *req, - struct ceph_osd_req_op *op); - extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, unsigned int num_op, -- cgit v1.2.3 From 3c663bbdcdf9296e0fe3362acb9e81f49d7b72c6 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 15 Feb 2013 11:42:30 -0600 Subject: libceph: kill ceph_osdc_create_event() "one_shot" parameter There is only one caller of ceph_osdc_create_event(), and it provides 0 as its "one_shot" argument. Get rid of that argument and just use 0 in its place. Replace the code in handle_watch_notify() that executes if one_shot is nonzero in the event with a BUG_ON() call. While modifying "osd_client.c", give handle_watch_notify() static scope. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index c39e7ed4b203..39c55d61e159 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -273,8 +273,7 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, /* watch/notify events */ extern int ceph_osdc_create_event(struct ceph_osd_client *osdc, void (*event_cb)(u64, u64, u8, void *), - int one_shot, void *data, - struct ceph_osd_event **pevent); + void *data, struct ceph_osd_event **pevent); extern void ceph_osdc_cancel_event(struct ceph_osd_event *event); extern int ceph_osdc_wait_event(struct ceph_osd_event *event, unsigned long timeout); -- cgit v1.2.3 From 2d2f522699fe8b827087941eb31b9a12cf465f17 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 15 Feb 2013 11:42:30 -0600 Subject: libceph: kill ceph_osdc_wait_event() There are no actual users of ceph_osdc_wait_event(). This would have been one-shot events, but we no longer support those so just get rid of this function. Since this leaves nothing else that waits for the completion of an event, we can get rid of the completion in a struct ceph_osd_event. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 39c55d61e159..388158ff0cbc 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -107,7 +107,6 @@ struct ceph_osd_event { struct rb_node node; struct list_head osd_node; struct kref kref; - struct completion completion; }; struct ceph_osd_event_work { @@ -275,8 +274,6 @@ extern int ceph_osdc_create_event(struct ceph_osd_client *osdc, void (*event_cb)(u64, u64, u8, void *), void *data, struct ceph_osd_event **pevent); extern void ceph_osdc_cancel_event(struct ceph_osd_event *event); -extern int ceph_osdc_wait_event(struct ceph_osd_event *event, - unsigned long timeout); extern void ceph_osdc_put_event(struct ceph_osd_event *event); #endif -- cgit v1.2.3 From 0315a7770983bbe69211efed1aaee08324acd54c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 15 Feb 2013 11:42:30 -0600 Subject: libceph: update rados.h Update most of "include/linux/ceph/rados.h" to match its user space counterpart in "src/include/rados.h" in the ceph tree. Almost everything that has changed is either: - added or revised comments - added definitions (therefore no real effect on existing code) - defining the same value a different way (e.g., "1 << 0" vs "1") The only exceptions are: - The declaration of ceph_osd_state_name() was excluded; that will be inserted in the next patch. - ceph_osd_op_mode_read() and ceph_osd_op_mode_modify() are defined differently, but they were never used in the kernel - CEPH_OSD_FLAG_PEERSTAT is now CEPH_OSD_FLAG_PEERSTAT_OLD, but that was never used in the kernel Anything that was present in this file but not in its user space counterpart was left intact here. I left the definitions of EOLDSNAPC and EBLACKLISTED using numerical values here; I'm not sure the right way to go with those. This and the next two commits resolve: http://tracker.ceph.com/issues/4164 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/rados.h | 91 ++++++++++++++++++++++++++++++++++++---------- 1 file changed, 71 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 2c04afeead1c..9c3b4aaf516b 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -145,8 +145,10 @@ struct ceph_eversion { */ /* status bits */ -#define CEPH_OSD_EXISTS 1 -#define CEPH_OSD_UP 2 +#define CEPH_OSD_EXISTS (1<<0) +#define CEPH_OSD_UP (1<<1) +#define CEPH_OSD_AUTOOUT (1<<2) /* osd was automatically marked out */ +#define CEPH_OSD_NEW (1<<3) /* osd is new, never marked in */ /* osd weights. fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */ #define CEPH_OSD_IN 0x10000 @@ -161,9 +163,25 @@ struct ceph_eversion { #define CEPH_OSDMAP_PAUSERD (1<<2) /* pause all reads */ #define CEPH_OSDMAP_PAUSEWR (1<<3) /* pause all writes */ #define CEPH_OSDMAP_PAUSEREC (1<<4) /* pause recovery */ +#define CEPH_OSDMAP_NOUP (1<<5) /* block osd boot */ +#define CEPH_OSDMAP_NODOWN (1<<6) /* block osd mark-down/failure */ +#define CEPH_OSDMAP_NOOUT (1<<7) /* block osd auto mark-out */ +#define CEPH_OSDMAP_NOIN (1<<8) /* block osd auto mark-in */ +#define CEPH_OSDMAP_NOBACKFILL (1<<9) /* block osd backfill */ +#define CEPH_OSDMAP_NORECOVER (1<<10) /* block osd recovery and backfill */ + +/* + * The error code to return when an OSD can't handle a write + * because it is too large. + */ +#define OSD_WRITETOOBIG EMSGSIZE /* * osd ops + * + * WARNING: do not use these op codes directly. Use the helpers + * defined below instead. In certain cases, op code behavior was + * redefined, resulting in special-cases in the helpers. */ #define CEPH_OSD_OP_MODE 0xf000 #define CEPH_OSD_OP_MODE_RD 0x1000 @@ -177,6 +195,7 @@ struct ceph_eversion { #define CEPH_OSD_OP_TYPE_ATTR 0x0300 #define CEPH_OSD_OP_TYPE_EXEC 0x0400 #define CEPH_OSD_OP_TYPE_PG 0x0500 +#define CEPH_OSD_OP_TYPE_MULTI 0x0600 /* multiobject */ enum { /** data **/ @@ -217,6 +236,23 @@ enum { CEPH_OSD_OP_WATCH = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 15, + /* omap */ + CEPH_OSD_OP_OMAPGETKEYS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 17, + CEPH_OSD_OP_OMAPGETVALS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 18, + CEPH_OSD_OP_OMAPGETHEADER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 19, + CEPH_OSD_OP_OMAPGETVALSBYKEYS = + CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 20, + CEPH_OSD_OP_OMAPSETVALS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 21, + CEPH_OSD_OP_OMAPSETHEADER = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 22, + CEPH_OSD_OP_OMAPCLEAR = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 23, + CEPH_OSD_OP_OMAPRMKEYS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 24, + CEPH_OSD_OP_OMAP_CMP = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 25, + + /** multi **/ + CEPH_OSD_OP_CLONERANGE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_MULTI | 1, + CEPH_OSD_OP_ASSERT_SRC_VERSION = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 2, + CEPH_OSD_OP_SRC_CMPXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 3, + /** attrs **/ /* read */ CEPH_OSD_OP_GETXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1, @@ -238,6 +274,7 @@ enum { CEPH_OSD_OP_SCRUB_RESERVE = CEPH_OSD_OP_MODE_SUB | 6, CEPH_OSD_OP_SCRUB_UNRESERVE = CEPH_OSD_OP_MODE_SUB | 7, CEPH_OSD_OP_SCRUB_STOP = CEPH_OSD_OP_MODE_SUB | 8, + CEPH_OSD_OP_SCRUB_MAP = CEPH_OSD_OP_MODE_SUB | 9, /** lock **/ CEPH_OSD_OP_WRLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1, @@ -248,10 +285,12 @@ enum { CEPH_OSD_OP_DNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6, /** exec **/ + /* note: the RD bit here is wrong; see special-case below in helper */ CEPH_OSD_OP_CALL = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_EXEC | 1, /** pg **/ CEPH_OSD_OP_PGLS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 1, + CEPH_OSD_OP_PGLS_FILTER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 2, }; static inline int ceph_osd_op_type_lock(int op) @@ -274,6 +313,10 @@ static inline int ceph_osd_op_type_pg(int op) { return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_PG; } +static inline int ceph_osd_op_type_multi(int op) +{ + return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_MULTI; +} static inline int ceph_osd_op_mode_subop(int op) { @@ -281,11 +324,12 @@ static inline int ceph_osd_op_mode_subop(int op) } static inline int ceph_osd_op_mode_read(int op) { - return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_RD; + return (op & CEPH_OSD_OP_MODE_RD) && + op != CEPH_OSD_OP_CALL; } static inline int ceph_osd_op_mode_modify(int op) { - return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_WR; + return op & CEPH_OSD_OP_MODE_WR; } /* @@ -294,34 +338,38 @@ static inline int ceph_osd_op_mode_modify(int op) */ #define CEPH_OSD_TMAP_HDR 'h' #define CEPH_OSD_TMAP_SET 's' +#define CEPH_OSD_TMAP_CREATE 'c' /* create key */ #define CEPH_OSD_TMAP_RM 'r' +#define CEPH_OSD_TMAP_RMSLOPPY 'R' extern const char *ceph_osd_op_name(int op); - /* * osd op flags * * An op may be READ, WRITE, or READ|WRITE. */ enum { - CEPH_OSD_FLAG_ACK = 1, /* want (or is) "ack" ack */ - CEPH_OSD_FLAG_ONNVRAM = 2, /* want (or is) "onnvram" ack */ - CEPH_OSD_FLAG_ONDISK = 4, /* want (or is) "ondisk" ack */ - CEPH_OSD_FLAG_RETRY = 8, /* resend attempt */ - CEPH_OSD_FLAG_READ = 16, /* op may read */ - CEPH_OSD_FLAG_WRITE = 32, /* op may write */ - CEPH_OSD_FLAG_ORDERSNAP = 64, /* EOLDSNAP if snapc is out of order */ - CEPH_OSD_FLAG_PEERSTAT = 128, /* msg includes osd_peer_stat */ - CEPH_OSD_FLAG_BALANCE_READS = 256, - CEPH_OSD_FLAG_PARALLELEXEC = 512, /* execute op in parallel */ - CEPH_OSD_FLAG_PGOP = 1024, /* pg op, no object */ - CEPH_OSD_FLAG_EXEC = 2048, /* op may exec */ - CEPH_OSD_FLAG_EXEC_PUBLIC = 4096, /* op may exec (public) */ + CEPH_OSD_FLAG_ACK = 0x0001, /* want (or is) "ack" ack */ + CEPH_OSD_FLAG_ONNVRAM = 0x0002, /* want (or is) "onnvram" ack */ + CEPH_OSD_FLAG_ONDISK = 0x0004, /* want (or is) "ondisk" ack */ + CEPH_OSD_FLAG_RETRY = 0x0008, /* resend attempt */ + CEPH_OSD_FLAG_READ = 0x0010, /* op may read */ + CEPH_OSD_FLAG_WRITE = 0x0020, /* op may write */ + CEPH_OSD_FLAG_ORDERSNAP = 0x0040, /* EOLDSNAP if snapc is out of order */ + CEPH_OSD_FLAG_PEERSTAT_OLD = 0x0080, /* DEPRECATED msg includes osd_peer_stat */ + CEPH_OSD_FLAG_BALANCE_READS = 0x0100, + CEPH_OSD_FLAG_PARALLELEXEC = 0x0200, /* execute op in parallel */ + CEPH_OSD_FLAG_PGOP = 0x0400, /* pg op, no object */ + CEPH_OSD_FLAG_EXEC = 0x0800, /* op may exec */ + CEPH_OSD_FLAG_EXEC_PUBLIC = 0x1000, /* DEPRECATED op may exec (public) */ + CEPH_OSD_FLAG_LOCALIZE_READS = 0x2000, /* read from nearby replica, if any */ + CEPH_OSD_FLAG_RWORDERED = 0x4000, /* order wrt concurrent reads */ }; enum { CEPH_OSD_OP_FLAG_EXCL = 1, /* EXCL object create */ + CEPH_OSD_OP_FLAG_FAILOK = 2, /* continue despite failure */ }; #define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/ @@ -381,7 +429,11 @@ struct ceph_osd_op { __le64 ver; __u8 flag; /* 0 = unwatch, 1 = watch */ } __attribute__ ((packed)) watch; -}; + struct { + __le64 offset, length; + __le64 src_offset; + } __attribute__ ((packed)) clonerange; + }; __le32 payload_len; } __attribute__ ((packed)); @@ -424,5 +476,4 @@ struct ceph_osd_reply_head { } __attribute__ ((packed)); - #endif -- cgit v1.2.3 From 4b568b1aaf23d0ce64b98d01d5ad1bcc7694440a Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 15 Feb 2013 11:42:30 -0600 Subject: libceph: add ceph_osd_state_name() Add the definition of ceph_osd_state_name(), to match its counterpart in user space. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/rados.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 9c3b4aaf516b..b65182aba6f7 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -150,6 +150,8 @@ struct ceph_eversion { #define CEPH_OSD_AUTOOUT (1<<2) /* osd was automatically marked out */ #define CEPH_OSD_NEW (1<<3) /* osd is new, never marked in */ +extern const char *ceph_osd_state_name(int s); + /* osd weights. fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */ #define CEPH_OSD_IN 0x10000 #define CEPH_OSD_OUT 0 -- cgit v1.2.3 From dd6f5e105d85e02bc41db0891eb07152b1746ad9 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 15 Feb 2013 11:42:30 -0600 Subject: libceph: update ceph_fs.h Update most of "include/linux/ceph/ceph_fs.h" to match its user space counterpart in "src/include/ceph_fs.h" in the ceph tree. Everything that has changed is either: - added definitions (therefore no real effect on existing code) - deleting unused symbols - added or revised comments There were some differences between the struct definitions for ceph_mon_subscribe_item and the open field of ceph_mds_request_args; those differences remain. This and the next commit resolve: http://tracker.ceph.com/issues/4165 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/ceph_fs.h | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index cf6f4d998a76..2ad7b860f062 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -21,16 +21,14 @@ * internal cluster protocols separately from the public, * client-facing protocol. */ -#define CEPH_OSD_PROTOCOL 8 /* cluster internal */ -#define CEPH_MDS_PROTOCOL 12 /* cluster internal */ -#define CEPH_MON_PROTOCOL 5 /* cluster internal */ #define CEPH_OSDC_PROTOCOL 24 /* server/client */ #define CEPH_MDSC_PROTOCOL 32 /* server/client */ #define CEPH_MONC_PROTOCOL 15 /* server/client */ -#define CEPH_INO_ROOT 1 -#define CEPH_INO_CEPH 2 /* hidden .ceph dir */ +#define CEPH_INO_ROOT 1 +#define CEPH_INO_CEPH 2 /* hidden .ceph dir */ +#define CEPH_INO_DOTDOT 3 /* used by ceph fuse for parent (..) */ /* arbitrary limit on max # of monitors (cluster of 3 is typical) */ #define CEPH_MAX_MON 31 @@ -51,7 +49,7 @@ struct ceph_file_layout { __le32 fl_object_stripe_unit; /* UNUSED. for per-object parity, if any */ /* object -> pg layout */ - __le32 fl_unused; /* unused; used to be preferred primary (-1) */ + __le32 fl_unused; /* unused; used to be preferred primary for pg (-1 for none) */ __le32 fl_pg_pool; /* namespace, crush ruleset, rep level */ } __attribute__ ((packed)); @@ -101,6 +99,8 @@ struct ceph_dir_layout { #define CEPH_MSG_MON_SUBSCRIBE_ACK 16 #define CEPH_MSG_AUTH 17 #define CEPH_MSG_AUTH_REPLY 18 +#define CEPH_MSG_MON_GET_VERSION 19 +#define CEPH_MSG_MON_GET_VERSION_REPLY 20 /* client <-> mds */ #define CEPH_MSG_MDS_MAP 21 @@ -220,6 +220,11 @@ struct ceph_mon_subscribe_ack { struct ceph_fsid fsid; } __attribute__ ((packed)); +/* + * mdsmap flags + */ +#define CEPH_MDSMAP_DOWN (1<<0) /* cluster deliberately down */ + /* * mds states * > 0 -> in @@ -233,6 +238,7 @@ struct ceph_mon_subscribe_ack { #define CEPH_MDS_STATE_CREATING -6 /* up, creating MDS instance. */ #define CEPH_MDS_STATE_STARTING -7 /* up, starting previously stopped mds */ #define CEPH_MDS_STATE_STANDBY_REPLAY -8 /* up, tailing active node's journal */ +#define CEPH_MDS_STATE_REPLAYONCE -9 /* up, replaying an active node's journal */ #define CEPH_MDS_STATE_REPLAY 8 /* up, replaying journal. */ #define CEPH_MDS_STATE_RESOLVE 9 /* up, disambiguating distributed @@ -264,6 +270,7 @@ extern const char *ceph_mds_state_name(int s); #define CEPH_LOCK_IXATTR 2048 #define CEPH_LOCK_IFLOCK 4096 /* advisory file locks */ #define CEPH_LOCK_INO 8192 /* immutable inode bits; not a lock */ +#define CEPH_LOCK_IPOLICY 16384 /* policy lock on dirs. MDS internal */ /* client_session ops */ enum { @@ -338,6 +345,12 @@ extern const char *ceph_mds_op_name(int op); #define CEPH_SETATTR_SIZE 32 #define CEPH_SETATTR_CTIME 64 +/* + * Ceph setxattr request flags. + */ +#define CEPH_XATTR_CREATE 1 +#define CEPH_XATTR_REPLACE 2 + union ceph_mds_request_args { struct { __le32 mask; /* CEPH_CAP_* */ @@ -522,14 +535,17 @@ int ceph_flags_to_mode(int flags); #define CEPH_CAP_GWREXTEND 64 /* (file) client can extend EOF */ #define CEPH_CAP_GLAZYIO 128 /* (file) client can perform lazy io */ +#define CEPH_CAP_SIMPLE_BITS 2 +#define CEPH_CAP_FILE_BITS 8 + /* per-lock shift */ #define CEPH_CAP_SAUTH 2 #define CEPH_CAP_SLINK 4 #define CEPH_CAP_SXATTR 6 #define CEPH_CAP_SFILE 8 -#define CEPH_CAP_SFLOCK 20 +#define CEPH_CAP_SFLOCK 20 -#define CEPH_CAP_BITS 22 +#define CEPH_CAP_BITS 22 /* composed values */ #define CEPH_CAP_AUTH_SHARED (CEPH_CAP_GSHARED << CEPH_CAP_SAUTH) -- cgit v1.2.3 From 5cd3f5affad2109fd1458aab3f6216f2181e26ea Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Thu, 24 Jan 2013 21:53:17 +0100 Subject: lockdep: Silence warning if CONFIG_LOCKDEP isn't set MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit c9a4962881929df7f1ef6e63e1b9da304faca4dd ("nfsd: make client_lock per net") compiling nfs4state.o without CONFIG_LOCKDEP set, triggers this GCC warning: fs/nfsd/nfs4state.c: In function ‘free_client’: fs/nfsd/nfs4state.c:1051:19: warning: unused variable ‘nn’ [-Wunused-variable] The cause of that warning is that lockdep_assert_held() compiles away if CONFIG_LOCKDEP is not set. Silence this warning by using the argument to lockdep_assert_held() as a nop if CONFIG_LOCKDEP is not set. Signed-off-by: Paul Bolle Cc: Peter Zijlstra Cc: Stanislav Kinsbursky Cc: J. Bruce Fields Link: http://lkml.kernel.org/r/1359060797.1325.33.camel@x61.thuisdomein Signed-off-by: Ingo Molnar -- include/linux/lockdep.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- include/linux/lockdep.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 2bca44b0893c..f05631effc73 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -410,7 +410,7 @@ struct lock_class_key { }; #define lockdep_depth(tsk) (0) -#define lockdep_assert_held(l) do { } while (0) +#define lockdep_assert_held(l) do { (void)(l); } while (0) #define lockdep_recursing(tsk) (0) -- cgit v1.2.3 From eece09ec213e93333010bf4c6bb9175b32229c54 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 17 Jul 2011 21:25:03 +0200 Subject: locking: Various static lock initializer fixes The static lock initializers want to be fed the proper name of the lock and not some random string. In mainline random strings are obfuscating the readability of debug output, but for RT they prevent the spinlock substitution. Fix it up. Signed-off-by: Thomas Gleixner --- include/linux/idr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index de7e190f1af4..e5eb125effe6 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -136,7 +136,7 @@ struct ida { struct ida_bitmap *free_bitmap; }; -#define IDA_INIT(name) { .idr = IDR_INIT(name), .free_bitmap = NULL, } +#define IDA_INIT(name) { .idr = IDR_INIT((name).idr), .free_bitmap = NULL, } #define DEFINE_IDA(name) struct ida name = IDA_INIT(name) int ida_pre_get(struct ida *ida, gfp_t gfp_mask); -- cgit v1.2.3 From 65c9d1bbc9f32c568a4f7ad154c9a10b0028df52 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 16 Jul 2011 18:38:22 +0200 Subject: seqlock: Remove unused functions Signed-off-by: Thomas Gleixner --- include/linux/seqlock.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 600060e25ec6..cb0599ca049c 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -69,17 +69,6 @@ static inline void write_sequnlock(seqlock_t *sl) spin_unlock(&sl->lock); } -static inline int write_tryseqlock(seqlock_t *sl) -{ - int ret = spin_trylock(&sl->lock); - - if (ret) { - ++sl->sequence; - smp_wmb(); - } - return ret; -} - /* Start of read calculation -- fetch last complete writer token */ static __always_inline unsigned read_seqbegin(const seqlock_t *sl) { @@ -269,14 +258,4 @@ static inline void write_seqcount_barrier(seqcount_t *s) #define write_sequnlock_bh(lock) \ do { write_sequnlock(lock); local_bh_enable(); } while(0) -#define read_seqbegin_irqsave(lock, flags) \ - ({ local_irq_save(flags); read_seqbegin(lock); }) - -#define read_seqretry_irqrestore(lock, iv, flags) \ - ({ \ - int ret = read_seqretry(lock, iv); \ - local_irq_restore(flags); \ - ret; \ - }) - #endif /* __LINUX_SEQLOCK_H */ -- cgit v1.2.3 From 6617feca15c68aad12f4a1edd8d8e2ef8d5b4ae5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 16 Jul 2011 18:40:26 +0200 Subject: seqlock: Use seqcount infrastructure No point in having different implementations for the same thing. Change the macro mess to inline functions where possible. Signed-off-by: Thomas Gleixner --- include/linux/seqlock.h | 174 +++++++++++++++++++++++++----------------------- 1 file changed, 92 insertions(+), 82 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index cb0599ca049c..18299057402f 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -30,81 +30,12 @@ #include #include -typedef struct { - unsigned sequence; - spinlock_t lock; -} seqlock_t; - -/* - * These macros triggered gcc-3.x compile-time problems. We think these are - * OK now. Be cautious. - */ -#define __SEQLOCK_UNLOCKED(lockname) \ - { 0, __SPIN_LOCK_UNLOCKED(lockname) } - -#define seqlock_init(x) \ - do { \ - (x)->sequence = 0; \ - spin_lock_init(&(x)->lock); \ - } while (0) - -#define DEFINE_SEQLOCK(x) \ - seqlock_t x = __SEQLOCK_UNLOCKED(x) - -/* Lock out other writers and update the count. - * Acts like a normal spin_lock/unlock. - * Don't need preempt_disable() because that is in the spin_lock already. - */ -static inline void write_seqlock(seqlock_t *sl) -{ - spin_lock(&sl->lock); - ++sl->sequence; - smp_wmb(); -} - -static inline void write_sequnlock(seqlock_t *sl) -{ - smp_wmb(); - sl->sequence++; - spin_unlock(&sl->lock); -} - -/* Start of read calculation -- fetch last complete writer token */ -static __always_inline unsigned read_seqbegin(const seqlock_t *sl) -{ - unsigned ret; - -repeat: - ret = ACCESS_ONCE(sl->sequence); - if (unlikely(ret & 1)) { - cpu_relax(); - goto repeat; - } - smp_rmb(); - - return ret; -} - -/* - * Test if reader processed invalid data. - * - * If sequence value changed then writer changed data while in section. - */ -static __always_inline int read_seqretry(const seqlock_t *sl, unsigned start) -{ - smp_rmb(); - - return unlikely(sl->sequence != start); -} - - /* * Version using sequence counter only. * This can be used when code has its own mutex protecting the * updating starting before the write_seqcountbeqin() and ending * after the write_seqcount_end(). */ - typedef struct seqcount { unsigned sequence; } seqcount_t; @@ -207,7 +138,6 @@ static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start) static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) { smp_rmb(); - return __read_seqcount_retry(s, start); } @@ -241,21 +171,101 @@ static inline void write_seqcount_barrier(seqcount_t *s) s->sequence+=2; } +typedef struct { + struct seqcount seqcount; + spinlock_t lock; +} seqlock_t; + +/* + * These macros triggered gcc-3.x compile-time problems. We think these are + * OK now. Be cautious. + */ +#define __SEQLOCK_UNLOCKED(lockname) \ + { \ + .seqcount = SEQCNT_ZERO, \ + .lock = __SPIN_LOCK_UNLOCKED(lockname) \ + } + +#define seqlock_init(x) \ + do { \ + seqcount_init(&(x)->seqcount); \ + spin_lock_init(&(x)->lock); \ + } while (0) + +#define DEFINE_SEQLOCK(x) \ + seqlock_t x = __SEQLOCK_UNLOCKED(x) + +/* + * Read side functions for starting and finalizing a read side section. + */ +static inline unsigned read_seqbegin(const seqlock_t *sl) +{ + return read_seqcount_begin(&sl->seqcount); +} + +static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) +{ + return read_seqcount_retry(&sl->seqcount, start); +} + /* - * Possible sw/hw IRQ protected versions of the interfaces. + * Lock out other writers and update the count. + * Acts like a normal spin_lock/unlock. + * Don't need preempt_disable() because that is in the spin_lock already. */ +static inline void write_seqlock(seqlock_t *sl) +{ + spin_lock(&sl->lock); + write_seqcount_begin(&sl->seqcount); +} + +static inline void write_sequnlock(seqlock_t *sl) +{ + write_seqcount_end(&sl->seqcount); + spin_unlock(&sl->lock); +} + +static inline void write_seqlock_bh(seqlock_t *sl) +{ + spin_lock_bh(&sl->lock); + write_seqcount_begin(&sl->seqcount); +} + +static inline void write_sequnlock_bh(seqlock_t *sl) +{ + write_seqcount_end(&sl->seqcount); + spin_unlock_bh(&sl->lock); +} + +static inline void write_seqlock_irq(seqlock_t *sl) +{ + spin_lock_irq(&sl->lock); + write_seqcount_begin(&sl->seqcount); +} + +static inline void write_sequnlock_irq(seqlock_t *sl) +{ + write_seqcount_end(&sl->seqcount); + spin_unlock_irq(&sl->lock); +} + +static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) +{ + unsigned long flags; + + spin_lock_irqsave(&sl->lock, flags); + write_seqcount_begin(&sl->seqcount); + return flags; +} + #define write_seqlock_irqsave(lock, flags) \ - do { local_irq_save(flags); write_seqlock(lock); } while (0) -#define write_seqlock_irq(lock) \ - do { local_irq_disable(); write_seqlock(lock); } while (0) -#define write_seqlock_bh(lock) \ - do { local_bh_disable(); write_seqlock(lock); } while (0) + do { flags = __write_seqlock_irqsave(lock); } while (0) -#define write_sequnlock_irqrestore(lock, flags) \ - do { write_sequnlock(lock); local_irq_restore(flags); } while(0) -#define write_sequnlock_irq(lock) \ - do { write_sequnlock(lock); local_irq_enable(); } while(0) -#define write_sequnlock_bh(lock) \ - do { write_sequnlock(lock); local_bh_enable(); } while(0) +static inline void +write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) +{ + write_seqcount_end(&sl->seqcount); + spin_unlock_irqrestore(&sl->lock, flags); +} #endif /* __LINUX_SEQLOCK_H */ -- cgit v1.2.3 From f84adf4921ae3115502f44ff467b04bf2f88cf04 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Wed, 13 Feb 2013 13:01:55 -0500 Subject: xen-blkfront: drop the use of llist_for_each_entry_safe Replace llist_for_each_entry_safe with a while loop. llist_for_each_entry_safe can trigger a bug in GCC 4.1, so it's best to remove it and use a while loop and do the deletion manually. Specifically this bug can be triggered by hot-unplugging a disk, either by doing xm block-detach or by save/restore cycle. BUG: unable to handle kernel paging request at fffffffffffffff0 IP: [] blkif_free+0x63/0x130 [xen_blkfront] The crash call trace is: ... bad_area_nosemaphore+0x13/0x20 do_page_fault+0x25e/0x4b0 page_fault+0x25/0x30 ? blkif_free+0x63/0x130 [xen_blkfront] blkfront_resume+0x46/0xa0 [xen_blkfront] xenbus_dev_resume+0x6c/0x140 pm_op+0x192/0x1b0 device_resume+0x82/0x1e0 dpm_resume+0xc9/0x1a0 dpm_resume_end+0x15/0x30 do_suspend+0x117/0x1e0 When drilling down to the assembler code, on newer GCC it does .L29: cmpq $-16, %r12 #, persistent_gnt check je .L30 #, out of the loop .L25: ... code in the loop testq %r13, %r13 # n je .L29 #, back to the top of the loop cmpq $-16, %r12 #, persistent_gnt check movq 16(%r12), %r13 # .node.next, n jne .L25 #, back to the top of the loop .L30: While on GCC 4.1, it is: L78: ... code in the loop testq %r13, %r13 # n je .L78 #, back to the top of the loop movq 16(%rbx), %r13 # .node.next, n jmp .L78 #, back to the top of the loop Which basically means that the exit loop condition instead of being: &(pos)->member != NULL; is: ; which makes the loop unbound. Since xen-blkfront is the only user of the llist_for_each_entry_safe macro remove it from llist.h. Orabug: 16263164 CC: stable@vger.kernel.org Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/llist.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h index d0ab98f73d38..a5199f6d0e82 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -124,31 +124,6 @@ static inline void init_llist_head(struct llist_head *list) &(pos)->member != NULL; \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) -/** - * llist_for_each_entry_safe - iterate safely against remove over some entries - * of lock-less list of given type. - * @pos: the type * to use as a loop cursor. - * @n: another type * to use as a temporary storage. - * @node: the fist entry of deleted list entries. - * @member: the name of the llist_node with the struct. - * - * In general, some entries of the lock-less list can be traversed - * safely only after being removed from list, so start with an entry - * instead of list head. This variant allows removal of entries - * as we iterate. - * - * If being used on entries deleted from lock-less list directly, the - * traverse order is from the newest to the oldest added entry. If - * you want to traverse from the oldest to the newest, you must - * reverse the order by yourself before traversing. - */ -#define llist_for_each_entry_safe(pos, n, node, member) \ - for ((pos) = llist_entry((node), typeof(*(pos)), member), \ - (n) = (pos)->member.next; \ - &(pos)->member != NULL; \ - (pos) = llist_entry(n, typeof(*(pos)), member), \ - (n) = (&(pos)->member != NULL) ? (pos)->member.next : NULL) - /** * llist_empty - tests whether a lock-less list is empty * @head: the list to test -- cgit v1.2.3 From b324814e8436772cb3367b14149ba003a9954525 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 6 Feb 2013 13:11:38 -0600 Subject: libceph: use void pointers in page vector functions The functions used for working with ceph page vectors are defined with char pointers, but they're really intended to operate on untyped data. Change the types of these function parameters to (void *) to reflect this. (Note that the functions now assume void pointer arithmetic works like arithmetic on char pointers.) Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/libceph.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index c44275ab375c..2250f8bb2490 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -222,7 +222,7 @@ extern int ceph_open_session(struct ceph_client *client); /* pagevec.c */ extern void ceph_release_page_vector(struct page **pages, int num_pages); -extern struct page **ceph_get_direct_page_vector(const char __user *data, +extern struct page **ceph_get_direct_page_vector(const void __user *data, int num_pages, bool write_page); extern void ceph_put_page_vector(struct page **pages, int num_pages, @@ -230,15 +230,15 @@ extern void ceph_put_page_vector(struct page **pages, int num_pages, extern void ceph_release_page_vector(struct page **pages, int num_pages); extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); extern int ceph_copy_user_to_page_vector(struct page **pages, - const char __user *data, + const void __user *data, loff_t off, size_t len); extern int ceph_copy_to_page_vector(struct page **pages, - const char *data, + const void *data, loff_t off, size_t len); extern int ceph_copy_from_page_vector(struct page **pages, - char *data, + void *data, loff_t off, size_t len); -extern int ceph_copy_page_vector_to_user(struct page **pages, char __user *data, +extern int ceph_copy_page_vector_to_user(struct page **pages, void __user *data, loff_t off, size_t len); extern void ceph_zero_page_vector_range(int off, int len, struct page **pages); -- cgit v1.2.3 From 903bb32e890237ca43ab847e561e5377cfe0fdb3 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 6 Feb 2013 13:11:38 -0600 Subject: libceph: drop return value from page vector copy routines The return values provided for ceph_copy_to_page_vector() and ceph_copy_from_page_vector() serve no purpose, so get rid of them. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/libceph.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 2250f8bb2490..29818fc3fa49 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -232,10 +232,10 @@ extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); extern int ceph_copy_user_to_page_vector(struct page **pages, const void __user *data, loff_t off, size_t len); -extern int ceph_copy_to_page_vector(struct page **pages, +extern void ceph_copy_to_page_vector(struct page **pages, const void *data, loff_t off, size_t len); -extern int ceph_copy_from_page_vector(struct page **pages, +extern void ceph_copy_from_page_vector(struct page **pages, void *data, loff_t off, size_t len); extern int ceph_copy_page_vector_to_user(struct page **pages, void __user *data, -- cgit v1.2.3 From 1c3e826482ab698e418c7a894440e62c76aac893 Mon Sep 17 00:00:00 2001 From: Sha Zhengju Date: Wed, 20 Feb 2013 17:14:38 +0800 Subject: sched/core: Remove the obsolete and unused nr_uninterruptible() function Signed-off-by: Sha Zhengju Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1361351678-8065-1-git-send-email-handai.szj@taobao.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 33cc42130371..f9ca237df7e8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -98,7 +98,6 @@ extern int nr_threads; DECLARE_PER_CPU(unsigned long, process_counts); extern int nr_processes(void); extern unsigned long nr_running(void); -extern unsigned long nr_uninterruptible(void); extern unsigned long nr_iowait(void); extern unsigned long nr_iowait_cpu(int cpu); extern unsigned long this_cpu_load(void); -- cgit v1.2.3 From 55e301fd57a6239ec14b91a1cf2e70b3dd135194 Mon Sep 17 00:00:00 2001 From: Filipe Brandenburger Date: Tue, 29 Jan 2013 06:04:50 +0000 Subject: Btrfs: move fs/btrfs/ioctl.h to include/uapi/linux/btrfs.h The header file will then be installed under /usr/include/linux so that userspace applications can refer to Btrfs ioctls by name and use the same structs used internally in the kernel. Signed-off-by: Filipe Brandenburger Signed-off-by: Josef Bacik --- include/linux/btrfs.h | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 include/linux/btrfs.h (limited to 'include/linux') diff --git a/include/linux/btrfs.h b/include/linux/btrfs.h new file mode 100644 index 000000000000..22d799147db2 --- /dev/null +++ b/include/linux/btrfs.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_BTRFS_H +#define _LINUX_BTRFS_H + +#include + +#endif /* _LINUX_BTRFS_H */ -- cgit v1.2.3 From 8b975bd3f9089f8ee5d7bbfd798537b992bbc7e7 Mon Sep 17 00:00:00 2001 From: "Markus F.X.J. Oberhumer" Date: Mon, 13 Aug 2012 17:25:44 +0200 Subject: lib/lzo: Update LZO compression to current upstream version This commit updates the kernel LZO code to the current upsteam version which features a significant speed improvement - benchmarking the Calgary and Silesia test corpora typically shows a doubled performance in both compression and decompression on modern i386/x86_64/powerpc machines. Signed-off-by: Markus F.X.J. Oberhumer --- include/linux/lzo.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lzo.h b/include/linux/lzo.h index d793497ec1ca..a0848d9377e5 100644 --- a/include/linux/lzo.h +++ b/include/linux/lzo.h @@ -4,28 +4,28 @@ * LZO Public Kernel Interface * A mini subset of the LZO real-time data compression library * - * Copyright (C) 1996-2005 Markus F.X.J. Oberhumer + * Copyright (C) 1996-2012 Markus F.X.J. Oberhumer * * The full LZO package can be found at: * http://www.oberhumer.com/opensource/lzo/ * - * Changed for kernel use by: + * Changed for Linux kernel use by: * Nitin Gupta * Richard Purdie */ -#define LZO1X_MEM_COMPRESS (16384 * sizeof(unsigned char *)) -#define LZO1X_1_MEM_COMPRESS LZO1X_MEM_COMPRESS +#define LZO1X_1_MEM_COMPRESS (8192 * sizeof(unsigned short)) +#define LZO1X_MEM_COMPRESS LZO1X_1_MEM_COMPRESS #define lzo1x_worst_compress(x) ((x) + ((x) / 16) + 64 + 3) -/* This requires 'workmem' of size LZO1X_1_MEM_COMPRESS */ +/* This requires 'wrkmem' of size LZO1X_1_MEM_COMPRESS */ int lzo1x_1_compress(const unsigned char *src, size_t src_len, - unsigned char *dst, size_t *dst_len, void *wrkmem); + unsigned char *dst, size_t *dst_len, void *wrkmem); /* safe decompression with overrun testing */ int lzo1x_decompress_safe(const unsigned char *src, size_t src_len, - unsigned char *dst, size_t *dst_len); + unsigned char *dst, size_t *dst_len); /* * Return values (< 0 = Error) @@ -40,5 +40,6 @@ int lzo1x_decompress_safe(const unsigned char *src, size_t src_len, #define LZO_E_EOF_NOT_FOUND (-7) #define LZO_E_INPUT_NOT_CONSUMED (-8) #define LZO_E_NOT_YET_IMPLEMENTED (-9) +#define LZO_E_INVALID_ARGUMENT (-10) #endif -- cgit v1.2.3 From 52608ba20546139dc76cca8a46c1d901455d5450 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Wed, 8 Aug 2012 12:30:56 -0300 Subject: i5100_edac: probe for device 19 function 0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Probe and store the device handle for the device 19 function 0 during driver initialization. The device is used during fault injection. Signed-off-by: Niklas Söderlund Signed-off-by: Mauro Carvalho Chehab --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 0eb65796bcb9..d0d1e801e350 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2776,6 +2776,7 @@ #define PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX 0x3ce0 #define PCI_DEVICE_ID_INTEL_IOAT_SNB 0x402f #define PCI_DEVICE_ID_INTEL_5100_16 0x65f0 +#define PCI_DEVICE_ID_INTEL_5100_19 0x65f3 #define PCI_DEVICE_ID_INTEL_5100_21 0x65f5 #define PCI_DEVICE_ID_INTEL_5100_22 0x65f6 #define PCI_DEVICE_ID_INTEL_5400_ERR 0x4030 -- cgit v1.2.3 From c66b5a79a9348ccd6d1cd81416027d0e12da965d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 15 Feb 2013 07:21:08 -0300 Subject: edac: add a new memory layer type There are some cases where the memory controller layout is completely hidden. This is the case of firmware-driven error code, like the one provided by GHES. Add a new layer to be used on such memory error report mechanisms. Signed-off-by: Mauro Carvalho Chehab --- include/linux/edac.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 4784213c819d..1b7744c219b8 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -375,6 +375,9 @@ enum scrub_type { * @EDAC_MC_LAYER_CHANNEL: memory layer is named "channel" * @EDAC_MC_LAYER_SLOT: memory layer is named "slot" * @EDAC_MC_LAYER_CHIP_SELECT: memory layer is named "chip select" + * @EDAC_MC_LAYER_ALL_MEM: memory layout is unknown. All memory is mapped + * as a single memory area. This is used when + * retrieving errors from a firmware driven driver. * * This enum is used by the drivers to tell edac_mc_sysfs what name should * be used when describing a memory stick location. @@ -384,6 +387,7 @@ enum edac_mc_layer_type { EDAC_MC_LAYER_CHANNEL, EDAC_MC_LAYER_SLOT, EDAC_MC_LAYER_CHIP_SELECT, + EDAC_MC_LAYER_ALL_MEM, }; /** -- cgit v1.2.3 From c2c93dbc97622e26dc19edc71e50ebaa996d7804 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 19 Feb 2013 06:50:05 -0300 Subject: edac: remove proc_name from mci structure proc_name isn't used anywhere. Remove it. Signed-off-by: Mauro Carvalho Chehab --- include/linux/edac.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 1b7744c219b8..ff18efc754f3 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -48,7 +48,6 @@ static inline void opstate_init(void) } #define EDAC_MC_LABEL_LEN 31 -#define MC_PROC_NAME_MAX_LEN 7 /** * enum dev_type - describe the type of memory DRAM chips used at the stick @@ -633,7 +632,6 @@ struct mem_ctl_info { const char *mod_ver; const char *ctl_name; const char *dev_name; - char proc_name[MC_PROC_NAME_MAX_LEN + 1]; void *pvt_info; unsigned long start_time; /* mci load start time (in jiffies) */ -- cgit v1.2.3 From cf1c4a094f46ace5bf00078e2db73491ddf018fe Mon Sep 17 00:00:00 2001 From: Josh Hunt Date: Tue, 19 Feb 2013 11:35:59 -0800 Subject: netfilter: ipset: timeout values corrupted on set resize If a resize is triggered on a set with timeouts enabled, the timeout values will get corrupted when copying them to the new set. This occured b/c the wrong timeout value is supplied to type_pf_elem_tadd(). This also adds simple debug statement similar to the one in type_pf_resize(). Signed-off-by: Josh Hunt Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set_ahash.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index ef9acd3c8450..01d25e6fc792 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -854,6 +854,8 @@ type_pf_tresize(struct ip_set *set, bool retried) retry: ret = 0; htable_bits++; + pr_debug("attempt to resize set %s from %u to %u, t %p\n", + set->name, orig->htable_bits, htable_bits, orig); if (!htable_bits) { /* In case we have plenty of memory :-) */ pr_warning("Cannot increase the hashsize of set %s further\n", @@ -873,7 +875,7 @@ retry: data = ahash_tdata(n, j); m = hbucket(t, HKEY(data, h->initval, htable_bits)); ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), 0, - type_pf_data_timeout(data)); + ip_set_timeout_get(type_pf_data_timeout(data))); if (ret < 0) { read_unlock_bh(&set->lock); ahash_destroy(t); -- cgit v1.2.3 From c7ef7645544131b0750478d1cf94cdfa945c809d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 21 Feb 2013 13:36:45 -0300 Subject: edac: reduce stack pressure by using a pre-allocated buffer The number of variables at the stack is too big. Reduces the stack usage by using a pre-allocated error buffer. Signed-off-by: Mauro Carvalho Chehab --- include/linux/edac.h | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index ff18efc754f3..096b7fcdf484 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -47,8 +47,18 @@ static inline void opstate_init(void) return; } +/* Max length of a DIMM label*/ #define EDAC_MC_LABEL_LEN 31 +/* Maximum size of the location string */ +#define LOCATION_SIZE 80 + +/* Defines the maximum number of labels that can be reported */ +#define EDAC_MAX_LABELS 8 + +/* String used to join two or more labels */ +#define OTHER_LABEL " or " + /** * enum dev_type - describe the type of memory DRAM chips used at the stick * @DEV_UNKNOWN: Can't be determined, or MC doesn't support detect it @@ -553,6 +563,46 @@ struct errcount_attribute_data { int layer0, layer1, layer2; }; +/** + * edac_raw_error_desc - Raw error report structure + * @grain: minimum granularity for an error report, in bytes + * @error_count: number of errors of the same type + * @top_layer: top layer of the error (layer[0]) + * @mid_layer: middle layer of the error (layer[1]) + * @low_layer: low layer of the error (layer[2]) + * @page_frame_number: page where the error happened + * @offset_in_page: page offset + * @syndrome: syndrome of the error (or 0 if unknown or if + * the syndrome is not applicable) + * @msg: error message + * @location: location of the error + * @label: label of the affected DIMM(s) + * @other_detail: other driver-specific detail about the error + * @enable_per_layer_report: if false, the error affects all layers + * (typically, a memory controller error) + */ +struct edac_raw_error_desc { + /* + * NOTE: everything before grain won't be cleaned by + * edac_raw_error_desc_clean() + */ + char location[LOCATION_SIZE]; + char label[(EDAC_MC_LABEL_LEN + 1 + sizeof(OTHER_LABEL)) * EDAC_MAX_LABELS]; + long grain; + + /* the vars below and grain will be cleaned on every new error report */ + u16 error_count; + int top_layer; + int mid_layer; + int low_layer; + unsigned long page_frame_number; + unsigned long offset_in_page; + unsigned long syndrome; + const char *msg; + const char *other_detail; + bool enable_per_layer_report; +}; + /* MEMORY controller information structure */ struct mem_ctl_info { @@ -660,6 +710,12 @@ struct mem_ctl_info { /* work struct for this MC */ struct delayed_work work; + /* + * Used to report an error - by being at the global struct + * makes the memory allocated by the EDAC core + */ + struct edac_raw_error_desc error_desc; + /* the internal state of this controller instance */ int op_state; -- cgit v1.2.3 From 8dd93d450bff251575c56b8f058393124e1f00fb Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 19 Feb 2013 21:26:22 -0300 Subject: edac: add support for error type "Info" The CPER spec defines a forth type of error: informational logs. Add support for it at the edac API and at the trace event interface. Signed-off-by: Mauro Carvalho Chehab --- include/linux/edac.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 096b7fcdf484..4fd4999ccb5b 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -109,8 +109,24 @@ enum hw_event_mc_err_type { HW_EVENT_ERR_CORRECTED, HW_EVENT_ERR_UNCORRECTED, HW_EVENT_ERR_FATAL, + HW_EVENT_ERR_INFO, }; +static inline char *mc_event_error_type(const unsigned int err_type) +{ + switch (err_type) { + case HW_EVENT_ERR_CORRECTED: + return "Corrected"; + case HW_EVENT_ERR_UNCORRECTED: + return "Uncorrected"; + case HW_EVENT_ERR_FATAL: + return "Fatal"; + default: + case HW_EVENT_ERR_INFO: + return "Info"; + } +} + /** * enum mem_type - memory types. For a more detailed reference, please see * http://en.wikipedia.org/wiki/DRAM -- cgit v1.2.3 From aee38fadd25989c3e6d99fc08752e2d87601ffc1 Mon Sep 17 00:00:00 2001 From: Shani Michaeli Date: Wed, 6 Feb 2013 16:19:07 +0000 Subject: IB/mlx4_ib: Remove local invalidate segment unused fields Remove unused fields from the local invalidate WQE segment structure. Signed-off-by: Haggai Eran Signed-off-by: Shani Michaeli Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/qp.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 4b4ad6ffef92..6c8a68c602be 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -304,12 +304,10 @@ struct mlx4_wqe_fmr_ext_seg { }; struct mlx4_wqe_local_inval_seg { - __be32 flags; - u32 reserved1; + u64 reserved1; __be32 mem_key; - u32 reserved2[2]; - __be32 guest_id; - __be64 pa; + u32 reserved2; + u64 reserved3[2]; }; struct mlx4_wqe_raddr_seg { -- cgit v1.2.3 From 61083720702a329ed5952e32bda384e3bbc9093c Mon Sep 17 00:00:00 2001 From: Shani Michaeli Date: Wed, 6 Feb 2013 16:19:09 +0000 Subject: mlx4_core: Propagate MR deregistration failures to caller MR deregistration fails when memory windows are bound to the MR. Handle such failures by propagating them to the caller ULP. Signed-off-by: Haggai Eran Signed-off-by: Shani Michaeli Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 20ea939c22a6..e9fe8caaf8bb 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -801,7 +801,7 @@ u64 mlx4_mtt_addr(struct mlx4_dev *dev, struct mlx4_mtt *mtt); int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access, int npages, int page_shift, struct mlx4_mr *mr); -void mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr); +int mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr); int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr); int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, int start_index, int npages, u64 *page_list); -- cgit v1.2.3 From 4d4c4e24cf48400a24d33feffc7cca4f4e8cabe1 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 22 Feb 2013 00:05:07 +0100 Subject: irq: Remove IRQ_EXIT_OFFSET workaround The IRQ_EXIT_OFFSET trick was used to make sure the irq doesn't get preempted after we substract the HARDIRQ_OFFSET until we are entirely done with any code in irq_exit(). This workaround was necessary because some archs may call irq_exit() with irqs enabled and there is still some code in the end of this function that is not covered by the HARDIRQ_OFFSET but want to stay non-preemptible. Now that irq are always disabled in irq_exit(), the whole code is guaranteed not to be preempted. We can thus remove this hack. Signed-off-by: Frederic Weisbecker Cc: Linus Torvalds Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Paul E. McKenney --- include/linux/hardirq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 29eb805ea4a6..c1d6555d2567 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -118,10 +118,8 @@ #ifdef CONFIG_PREEMPT_COUNT # define preemptible() (preempt_count() == 0 && !irqs_disabled()) -# define IRQ_EXIT_OFFSET (HARDIRQ_OFFSET-1) #else # define preemptible() 0 -# define IRQ_EXIT_OFFSET HARDIRQ_OFFSET #endif #if defined(CONFIG_SMP) || defined(CONFIG_GENERIC_HARDIRQS) -- cgit v1.2.3 From f142d3bd556c5e82e9bb3d33d07d6708702ea4ce Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 21 Nov 2012 15:29:29 +0100 Subject: video: Add generic HDMI infoframe helpers Add generic helpers to pack HDMI infoframes into binary buffers. Signed-off-by: Thierry Reding Reviewed-by: Alex Deucher --- include/linux/hdmi.h | 231 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 231 insertions(+) create mode 100644 include/linux/hdmi.h (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h new file mode 100644 index 000000000000..3b589440ecfe --- /dev/null +++ b/include/linux/hdmi.h @@ -0,0 +1,231 @@ +/* + * Copyright (C) 2012 Avionic Design GmbH + * + * 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_HDMI_H_ +#define __LINUX_HDMI_H_ + +#include + +enum hdmi_infoframe_type { + HDMI_INFOFRAME_TYPE_VENDOR = 0x81, + HDMI_INFOFRAME_TYPE_AVI = 0x82, + HDMI_INFOFRAME_TYPE_SPD = 0x83, + HDMI_INFOFRAME_TYPE_AUDIO = 0x84, +}; + +#define HDMI_INFOFRAME_HEADER_SIZE 4 +#define HDMI_AVI_INFOFRAME_SIZE 13 +#define HDMI_SPD_INFOFRAME_SIZE 25 +#define HDMI_AUDIO_INFOFRAME_SIZE 10 + +enum hdmi_colorspace { + HDMI_COLORSPACE_RGB, + HDMI_COLORSPACE_YUV422, + HDMI_COLORSPACE_YUV444, +}; + +enum hdmi_scan_mode { + HDMI_SCAN_MODE_NONE, + HDMI_SCAN_MODE_OVERSCAN, + HDMI_SCAN_MODE_UNDERSCAN, +}; + +enum hdmi_colorimetry { + HDMI_COLORIMETRY_NONE, + HDMI_COLORIMETRY_ITU_601, + HDMI_COLORIMETRY_ITU_709, + HDMI_COLORIMETRY_EXTENDED, +}; + +enum hdmi_picture_aspect { + HDMI_PICTURE_ASPECT_NONE, + HDMI_PICTURE_ASPECT_4_3, + HDMI_PICTURE_ASPECT_16_9, +}; + +enum hdmi_active_aspect { + HDMI_ACTIVE_ASPECT_16_9_TOP = 2, + HDMI_ACTIVE_ASPECT_14_9_TOP = 3, + HDMI_ACTIVE_ASPECT_16_9_CENTER = 4, + HDMI_ACTIVE_ASPECT_PICTURE = 8, + HDMI_ACTIVE_ASPECT_4_3 = 9, + HDMI_ACTIVE_ASPECT_16_9 = 10, + HDMI_ACTIVE_ASPECT_14_9 = 11, + HDMI_ACTIVE_ASPECT_4_3_SP_14_9 = 13, + HDMI_ACTIVE_ASPECT_16_9_SP_14_9 = 14, + HDMI_ACTIVE_ASPECT_16_9_SP_4_3 = 15, +}; + +enum hdmi_extended_colorimetry { + HDMI_EXTENDED_COLORIMETRY_XV_YCC_601, + HDMI_EXTENDED_COLORIMETRY_XV_YCC_709, + HDMI_EXTENDED_COLORIMETRY_S_YCC_601, + HDMI_EXTENDED_COLORIMETRY_ADOBE_YCC_601, + HDMI_EXTENDED_COLORIMETRY_ADOBE_RGB, +}; + +enum hdmi_quantization_range { + HDMI_QUANTIZATION_RANGE_DEFAULT, + HDMI_QUANTIZATION_RANGE_LIMITED, + HDMI_QUANTIZATION_RANGE_FULL, +}; + +/* non-uniform picture scaling */ +enum hdmi_nups { + HDMI_NUPS_UNKNOWN, + HDMI_NUPS_HORIZONTAL, + HDMI_NUPS_VERTICAL, + HDMI_NUPS_BOTH, +}; + +enum hdmi_ycc_quantization_range { + HDMI_YCC_QUANTIZATION_RANGE_LIMITED, + HDMI_YCC_QUANTIZATION_RANGE_FULL, +}; + +enum hdmi_content_type { + HDMI_CONTENT_TYPE_NONE, + HDMI_CONTENT_TYPE_PHOTO, + HDMI_CONTENT_TYPE_CINEMA, + HDMI_CONTENT_TYPE_GAME, +}; + +struct hdmi_avi_infoframe { + enum hdmi_infoframe_type type; + unsigned char version; + unsigned char length; + enum hdmi_colorspace colorspace; + bool active_info_valid; + bool horizontal_bar_valid; + bool vertical_bar_valid; + enum hdmi_scan_mode scan_mode; + enum hdmi_colorimetry colorimetry; + enum hdmi_picture_aspect picture_aspect; + enum hdmi_active_aspect active_aspect; + bool itc; + enum hdmi_extended_colorimetry extended_colorimetry; + enum hdmi_quantization_range quantization_range; + enum hdmi_nups nups; + unsigned char video_code; + enum hdmi_ycc_quantization_range ycc_quantization_range; + enum hdmi_content_type content_type; + unsigned char pixel_repeat; + unsigned short top_bar; + unsigned short bottom_bar; + unsigned short left_bar; + unsigned short right_bar; +}; + +int hdmi_avi_infoframe_init(struct hdmi_avi_infoframe *frame); +ssize_t hdmi_avi_infoframe_pack(struct hdmi_avi_infoframe *frame, void *buffer, + size_t size); + +enum hdmi_spd_sdi { + HDMI_SPD_SDI_UNKNOWN, + HDMI_SPD_SDI_DSTB, + HDMI_SPD_SDI_DVDP, + HDMI_SPD_SDI_DVHS, + HDMI_SPD_SDI_HDDVR, + HDMI_SPD_SDI_DVC, + HDMI_SPD_SDI_DSC, + HDMI_SPD_SDI_VCD, + HDMI_SPD_SDI_GAME, + HDMI_SPD_SDI_PC, + HDMI_SPD_SDI_BD, + HDMI_SPD_SDI_SACD, + HDMI_SPD_SDI_HDDVD, + HDMI_SPD_SDI_PMP, +}; + +struct hdmi_spd_infoframe { + enum hdmi_infoframe_type type; + unsigned char version; + unsigned char length; + char vendor[8]; + char product[16]; + enum hdmi_spd_sdi sdi; +}; + +int hdmi_spd_infoframe_init(struct hdmi_spd_infoframe *frame, + const char *vendor, const char *product); +ssize_t hdmi_spd_infoframe_pack(struct hdmi_spd_infoframe *frame, void *buffer, + size_t size); + +enum hdmi_audio_coding_type { + HDMI_AUDIO_CODING_TYPE_STREAM, + HDMI_AUDIO_CODING_TYPE_PCM, + HDMI_AUDIO_CODING_TYPE_AC3, + HDMI_AUDIO_CODING_TYPE_MPEG1, + HDMI_AUDIO_CODING_TYPE_MP3, + HDMI_AUDIO_CODING_TYPE_MPEG2, + HDMI_AUDIO_CODING_TYPE_AAC_LC, + HDMI_AUDIO_CODING_TYPE_DTS, + HDMI_AUDIO_CODING_TYPE_ATRAC, + HDMI_AUDIO_CODING_TYPE_DSD, + HDMI_AUDIO_CODING_TYPE_EAC3, + HDMI_AUDIO_CODING_TYPE_DTS_HD, + HDMI_AUDIO_CODING_TYPE_MLP, + HDMI_AUDIO_CODING_TYPE_DST, + HDMI_AUDIO_CODING_TYPE_WMA_PRO, +}; + +enum hdmi_audio_sample_size { + HDMI_AUDIO_SAMPLE_SIZE_STREAM, + HDMI_AUDIO_SAMPLE_SIZE_16, + HDMI_AUDIO_SAMPLE_SIZE_20, + HDMI_AUDIO_SAMPLE_SIZE_24, +}; + +enum hdmi_audio_sample_frequency { + HDMI_AUDIO_SAMPLE_FREQUENCY_STREAM, + HDMI_AUDIO_SAMPLE_FREQUENCY_32000, + HDMI_AUDIO_SAMPLE_FREQUENCY_44100, + HDMI_AUDIO_SAMPLE_FREQUENCY_48000, + HDMI_AUDIO_SAMPLE_FREQUENCY_88200, + HDMI_AUDIO_SAMPLE_FREQUENCY_96000, + HDMI_AUDIO_SAMPLE_FREQUENCY_176400, + HDMI_AUDIO_SAMPLE_FREQUENCY_192000, +}; + +enum hdmi_audio_coding_type_ext { + HDMI_AUDIO_CODING_TYPE_EXT_STREAM, + HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC, + HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC_V2, + HDMI_AUDIO_CODING_TYPE_EXT_MPEG_SURROUND, +}; + +struct hdmi_audio_infoframe { + enum hdmi_infoframe_type type; + unsigned char version; + unsigned char length; + unsigned char channels; + enum hdmi_audio_coding_type coding_type; + enum hdmi_audio_sample_size sample_size; + enum hdmi_audio_sample_frequency sample_frequency; + enum hdmi_audio_coding_type_ext coding_type_ext; + unsigned char channel_allocation; + unsigned char level_shift_value; + bool downmix_inhibit; + +}; + +int hdmi_audio_infoframe_init(struct hdmi_audio_infoframe *frame); +ssize_t hdmi_audio_infoframe_pack(struct hdmi_audio_infoframe *frame, + void *buffer, size_t size); + +struct hdmi_vendor_infoframe { + enum hdmi_infoframe_type type; + unsigned char version; + unsigned char length; + u8 data[27]; +}; + +ssize_t hdmi_vendor_infoframe_pack(struct hdmi_vendor_infoframe *frame, + void *buffer, size_t size); + +#endif /* _DRM_HDMI_H */ -- cgit v1.2.3 From 24dea0c9feccf699749f860fa2f4ccd84d30390d Mon Sep 17 00:00:00 2001 From: Dmitry Eremin-Solenikov Date: Thu, 31 Jan 2013 21:06:34 +0400 Subject: mtd: map: BUG() in non handled cases Several map-related functions look like a serie of ifs, checking widths of map. Those functions do not have any handling for default case. Instead of fiddling with uninitialized_var in those functions, let's just add a (correct) BUG() to the default case on those maps. This will also allow us to catch potential errors in maps setup in future. Signed-off-by: Dmitry Eremin-Solenikov Signed-off-by: Artem Bityutskiy --- include/linux/mtd/map.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index 8b9bfd7dcaa3..4b02512e421c 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -329,7 +329,7 @@ static inline int map_word_bitsset(struct map_info *map, map_word val1, map_word static inline map_word map_word_load(struct map_info *map, const void *ptr) { - map_word r = {{0} }; + map_word r; if (map_bankwidth_is_1(map)) r.x[0] = *(unsigned char *)ptr; @@ -343,6 +343,8 @@ static inline map_word map_word_load(struct map_info *map, const void *ptr) #endif else if (map_bankwidth_is_large(map)) memcpy(r.x, ptr, map->bankwidth); + else + BUG(); return r; } @@ -392,7 +394,7 @@ static inline map_word map_word_ff(struct map_info *map) static inline map_word inline_map_read(struct map_info *map, unsigned long ofs) { - map_word uninitialized_var(r); + map_word r; if (map_bankwidth_is_1(map)) r.x[0] = __raw_readb(map->virt + ofs); @@ -426,6 +428,8 @@ static inline void inline_map_write(struct map_info *map, const map_word datum, #endif else if (map_bankwidth_is_large(map)) memcpy_toio(map->virt+ofs, datum.x, map->bankwidth); + else + BUG(); mb(); } -- cgit v1.2.3 From 45ebd3945b2a3cf4eb89d5fb0090a3cb71af7973 Mon Sep 17 00:00:00 2001 From: Clark Williams Date: Wed, 20 Feb 2013 09:19:09 -0600 Subject: sched: Move RR_TIMESLICE from sysctl.h to rt.h This fixes an ia64 build bug reported by Tony Luck. Reported-by: Tony Luck Signed-off-by: Clark Williams Cc: Peter Zijlstra Cc: Steven Rostedt Link: http://lkml.kernel.org/r/1361373550-4011-2-git-send-email-clark.williams@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched/rt.h | 6 ++++++ include/linux/sched/sysctl.h | 6 ------ 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index 94e19ea28fc3..440434df3627 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -55,4 +55,10 @@ static inline bool tsk_is_pi_blocked(struct task_struct *tsk) extern void normalize_rt_tasks(void); +/* + * default timeslice is 100 msecs (used only for SCHED_RR tasks). + * Timeslices get refilled after they expire. + */ +#define RR_TIMESLICE (100 * HZ / 1000) + #endif /* _SCHED_RT_H */ diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index d2bb0ae979d0..bf8086b2506e 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -91,12 +91,6 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice; extern unsigned int sysctl_sched_autogroup_enabled; #endif -/* - * default timeslice is 100 msecs (used only for SCHED_RR tasks). - * Timeslices get refilled after they expire. - */ -#define RR_TIMESLICE (100 * HZ / 1000) - extern int sched_rr_timeslice; extern int sched_rr_handler(struct ctl_table *table, int write, -- cgit v1.2.3 From bc681593b588786e6326b3e5f78ccc1683e2269c Mon Sep 17 00:00:00 2001 From: Clark Williams Date: Fri, 22 Feb 2013 09:20:11 -0800 Subject: sched: move RR_TIMESLICE from sysctl.h to rt.h Originally submitted by Clark Williams as part of a cleanup, but happens also to fix an ia64 build problem: arch/ia64/kernel/init_task.c:38: error: 'RR_TIMESLICE' undeclared here (not in a function) Signed-off-by: Clark Williams Signed-off-by: Tony Luck --- include/linux/sched/rt.h | 6 ++++++ include/linux/sched/sysctl.h | 6 ------ 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index 94e19ea28fc3..440434df3627 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -55,4 +55,10 @@ static inline bool tsk_is_pi_blocked(struct task_struct *tsk) extern void normalize_rt_tasks(void); +/* + * default timeslice is 100 msecs (used only for SCHED_RR tasks). + * Timeslices get refilled after they expire. + */ +#define RR_TIMESLICE (100 * HZ / 1000) + #endif /* _SCHED_RT_H */ diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index d2bb0ae979d0..bf8086b2506e 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -91,12 +91,6 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice; extern unsigned int sysctl_sched_autogroup_enabled; #endif -/* - * default timeslice is 100 msecs (used only for SCHED_RR tasks). - * Timeslices get refilled after they expire. - */ -#define RR_TIMESLICE (100 * HZ / 1000) - extern int sched_rr_timeslice; extern int sched_rr_handler(struct ctl_table *table, int write, -- cgit v1.2.3 From d6561bb206aae9de8eee4516549339ee96386b87 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Thu, 21 Feb 2013 11:04:45 +0000 Subject: PM / OPP: fix condition for empty of_init_opp_table() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit randconfig build reports the following error which is caused by CONFIG_PM_OPP being unset. CC arch/arm/mach-imx/mach-imx6q.o arch/arm/mach-imx/mach-imx6q.c: In function ‘imx6q_opp_init’: arch/arm/mach-imx/mach-imx6q.c:248:2: error: implicit declaration of function ‘of_init_opp_table’ [-Werror=implicit-function-declaration] Fix the error by giving a more correct condition for empty of_init_opp_table() implementation. Reported-by: Rob Herring Signed-off-by: Shawn Guo Acked-by: Nishanth Menon Signed-off-by: Rafael J. Wysocki --- include/linux/opp.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/opp.h b/include/linux/opp.h index 214e0ebcb84d..3aca2b8def33 100644 --- a/include/linux/opp.h +++ b/include/linux/opp.h @@ -47,15 +47,6 @@ int opp_enable(struct device *dev, unsigned long freq); int opp_disable(struct device *dev, unsigned long freq); struct srcu_notifier_head *opp_get_notifier(struct device *dev); - -#ifdef CONFIG_OF -int of_init_opp_table(struct device *dev); -#else -static inline int of_init_opp_table(struct device *dev) -{ - return -EINVAL; -} -#endif /* CONFIG_OF */ #else static inline unsigned long opp_get_voltage(struct opp *opp) { @@ -112,6 +103,15 @@ static inline struct srcu_notifier_head *opp_get_notifier(struct device *dev) } #endif /* CONFIG_PM_OPP */ +#if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) +int of_init_opp_table(struct device *dev); +#else +static inline int of_init_opp_table(struct device *dev) +{ + return -EINVAL; +} +#endif + #if defined(CONFIG_CPU_FREQ) && defined(CONFIG_PM_OPP) int opp_init_cpufreq_table(struct device *dev, struct cpufreq_frequency_table **table); -- cgit v1.2.3 From 496ad9aa8ef448058e36ca7a787c61f2e63f0f54 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 23 Jan 2013 17:07:38 -0500 Subject: new helper: file_inode(file) Signed-off-by: Al Viro --- include/linux/fs.h | 9 +++++++-- include/linux/fsnotify.h | 2 +- include/linux/hugetlb.h | 2 +- include/linux/lockd/lockd.h | 2 +- 4 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7617ee04f066..3ab69777b4d8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2217,6 +2217,11 @@ static inline bool execute_ok(struct inode *inode) return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } +static inline struct inode *file_inode(struct file *f) +{ + return f->f_path.dentry->d_inode; +} + /* * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. @@ -2239,7 +2244,7 @@ static inline int get_write_access(struct inode *inode) } static inline int deny_write_access(struct file *file) { - struct inode *inode = file->f_path.dentry->d_inode; + struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline void put_write_access(struct inode * inode) @@ -2249,7 +2254,7 @@ static inline void put_write_access(struct inode * inode) static inline void allow_write_access(struct file *file) { if (file) - atomic_inc(&file->f_path.dentry->d_inode->i_writecount); + atomic_inc(&file_inode(file)->i_writecount); } #ifdef CONFIG_IMA static inline void i_readcount_dec(struct inode *inode) diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 0fbfb4646d1b..a78680a92dba 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -244,7 +244,7 @@ static inline void fsnotify_open(struct file *file) static inline void fsnotify_close(struct file *file) { struct path *path = &file->f_path; - struct inode *inode = file->f_path.dentry->d_inode; + struct inode *inode = file_inode(file); fmode_t mode = file->f_mode; __u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0c80d3f57a5b..70832951f97c 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -281,7 +281,7 @@ static inline struct hstate *hstate_inode(struct inode *i) static inline struct hstate *hstate_file(struct file *f) { - return hstate_inode(f->f_dentry->d_inode); + return hstate_inode(file_inode(f)); } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index f5a051a79273..0e62d84f9f7f 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -291,7 +291,7 @@ int nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr); static inline struct inode *nlmsvc_file_inode(struct nlm_file *file) { - return file->f_file->f_path.dentry->d_inode; + return file_inode(file->f_file); } static inline int __nlm_privileged_request4(const struct sockaddr *sap) -- cgit v1.2.3 From ad8ca3743cb7eef0eb8a2e87943c513201685eec Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 15 Jan 2013 12:54:29 -0500 Subject: vfs: remove d_path_with_unreachable The last caller was removed >2 years ago in commit 7b2a69ba7. Signed-off-by: Jeff Layton Signed-off-by: Al Viro --- include/linux/dcache.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c1754b59ddd3..63e96844a8e8 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -333,7 +333,6 @@ extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...); extern char *__d_path(const struct path *, const struct path *, char *, int); extern char *d_absolute_path(const struct path *, char *, int); extern char *d_path(const struct path *, char *, int); -extern char *d_path_with_unreachable(const struct path *, char *, int); extern char *dentry_path_raw(struct dentry *, char *, int); extern char *dentry_path(struct dentry *, char *, int); -- cgit v1.2.3 From a713ca2ab9d14dc5c86634bc445ce1f66552c169 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 24 Jan 2013 18:27:00 -0500 Subject: constify __d_lookup() arguments Signed-off-by: Al Viro --- include/linux/dcache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 63e96844a8e8..969086c03301 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -295,7 +295,7 @@ extern struct dentry *d_ancestor(struct dentry *, struct dentry *); /* appendix may either be NULL or be used for transname suffixes */ extern struct dentry *d_lookup(struct dentry *, struct qstr *); extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); -extern struct dentry *__d_lookup(struct dentry *, struct qstr *); +extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seq, struct inode *inode); -- cgit v1.2.3 From da2d8455ed7eb22d7642ecee43dc463ac42a1256 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 24 Jan 2013 18:29:34 -0500 Subject: constify d_lookup() arguments Signed-off-by: Al Viro --- include/linux/dcache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 969086c03301..03d169288423 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -293,7 +293,7 @@ extern void d_move(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); /* appendix may either be NULL or be used for transname suffixes */ -extern struct dentry *d_lookup(struct dentry *, struct qstr *); +extern struct dentry *d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *__d_lookup_rcu(const struct dentry *parent, -- cgit v1.2.3 From d778df51c09264076fe0208c099ef7d428f21790 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 22 Feb 2013 16:32:12 -0800 Subject: mm: vmscan: save work scanning (almost) empty LRU lists In certain cases (kswapd reclaim, memcg target reclaim), a fixed minimum amount of pages is scanned from the LRU lists on each iteration, to make progress. Do not make this minimum bigger than the respective LRU list size, however, and save some busy work trying to isolate and reclaim pages that are not there. Empty LRU lists are quite common with memory cgroups in NUMA environments because there exists a set of LRU lists for each zone for each memory cgroup, while the memory of a single cgroup is expected to stay on just one node. The number of expected empty LRU lists is thus memcgs * (nodes - 1) * lru types Each attempt to reclaim from an empty LRU list does expensive size comparisons between lists, acquires the zone's lru lock etc. Avoid that. Signed-off-by: Johannes Weiner Reviewed-by: Rik van Riel Acked-by: Mel Gorman Reviewed-by: Michal Hocko Cc: Hugh Dickins Cc: Satoru Moriya Cc: Simon Jeons Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 68df9c17fbbb..8c66486a8ca8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -156,7 +156,7 @@ enum { SWP_SCANNING = (1 << 8), /* refcount in scan_swap_map */ }; -#define SWAP_CLUSTER_MAX 32 +#define SWAP_CLUSTER_MAX 32UL #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* -- cgit v1.2.3 From 7103f16dbff20fa969c9500902d980d17f953fa6 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 22 Feb 2013 16:32:33 -0800 Subject: mm: compaction: make __compact_pgdat() and compact_pgdat() return void These functions always return 0. Formalise this. Cc: Jason Liu Cc: KAMEZAWA Hiroyuki Cc: Mel Gorman Cc: Minchan Kim Cc: Rik van Riel Acked-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index cc7bddeaf553..091d72e70d8a 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -23,7 +23,7 @@ extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask, bool sync, bool *contended); -extern int compact_pgdat(pg_data_t *pgdat, int order); +extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order); @@ -80,9 +80,8 @@ static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, return COMPACT_CONTINUE; } -static inline int compact_pgdat(pg_data_t *pgdat, int order) +static inline void compact_pgdat(pg_data_t *pgdat, int order) { - return COMPACT_CONTINUE; } static inline void reset_isolation_suitable(pg_data_t *pgdat) -- cgit v1.2.3 From bebeb3d68b24bb4132d452c5707fe321208bcbcd Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Fri, 22 Feb 2013 16:32:37 -0800 Subject: mm: introduce mm_populate() for populating new vmas When creating new mappings using the MAP_POPULATE / MAP_LOCKED flags (or with MCL_FUTURE in effect), we want to populate the pages within the newly created vmas. This may take a while as we may have to read pages from disk, so ideally we want to do this outside of the write-locked mmap_sem region. This change introduces mm_populate(), which is used to defer populating such mappings until after the mmap_sem write lock has been released. This is implemented as a generalization of the former do_mlock_pages(), which accomplished the same task but was using during mlock() / mlockall(). Signed-off-by: Michel Lespinasse Reported-by: Andy Lutomirski Acked-by: Rik van Riel Tested-by: Andy Lutomirski Cc: Greg Ungerer Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9d9dcc35d6a1..da0a0fe970c2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1474,11 +1474,23 @@ extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned lo extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff); -extern unsigned long do_mmap_pgoff(struct file *, unsigned long, - unsigned long, unsigned long, - unsigned long, unsigned long); +extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, unsigned long flags, + unsigned long pgoff, bool *populate); extern int do_munmap(struct mm_struct *, unsigned long, size_t); +#ifdef CONFIG_MMU +extern int __mm_populate(unsigned long addr, unsigned long len, + int ignore_errors); +static inline void mm_populate(unsigned long addr, unsigned long len) +{ + /* Ignore errors */ + (void) __mm_populate(addr, len, 1); +} +#else +static inline void mm_populate(unsigned long addr, unsigned long len) {} +#endif + /* These take the mm semaphore themselves */ extern unsigned long vm_brk(unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); -- cgit v1.2.3 From c22c0d6344c362b1dde5d8e160d3d07536aca120 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Fri, 22 Feb 2013 16:32:43 -0800 Subject: mm: remove flags argument to mmap_region After the MAP_POPULATE handling has been moved to mmap_region() call sites, the only remaining use of the flags argument is to pass the MAP_NORESERVE flag. This can be just as easily handled by do_mmap_pgoff(), so do that and remove the mmap_region() flags parameter. [akpm@linux-foundation.org: remove double parens] Signed-off-by: Michel Lespinasse Acked-by: Rik van Riel Tested-by: Andy Lutomirski Cc: Greg Ungerer Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index da0a0fe970c2..8332f3069fe3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1472,8 +1472,7 @@ extern int install_special_mapping(struct mm_struct *mm, extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); extern unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, unsigned long flags, - vm_flags_t vm_flags, unsigned long pgoff); + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff); extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff, bool *populate); -- cgit v1.2.3 From cea10a19b7972a1954c4a2d05a7de8db48b444fb Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Fri, 22 Feb 2013 16:32:44 -0800 Subject: mm: directly use __mlock_vma_pages_range() in find_extend_vma() In find_extend_vma(), we don't need mlock_vma_pages_range() to verify the vma type - we know we're working with a stack. So, we can call directly into __mlock_vma_pages_range(), and remove the last make_pages_present() call site. Note that we don't use mm_populate() here, so we can't release the mmap_sem while allocating new stack pages. This is deemed acceptable, because the stack vmas grow by a bounded number of pages at a time, and these are anon pages so we don't have to read from disk to populate them. Signed-off-by: Michel Lespinasse Acked-by: Rik van Riel Tested-by: Andy Lutomirski Cc: Greg Ungerer Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8332f3069fe3..0c34d3486816 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1035,7 +1035,6 @@ static inline int fixup_user_fault(struct task_struct *tsk, } #endif -extern int make_pages_present(unsigned long addr, unsigned long end); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, int write); -- cgit v1.2.3 From 1869305009857cdeaabe6283bcdc2359c5784543 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Fri, 22 Feb 2013 16:32:46 -0800 Subject: mm: introduce VM_POPULATE flag to better deal with racy userspace programs The vm_populate() code populates user mappings without constantly holding the mmap_sem. This makes it susceptible to racy userspace programs: the user mappings may change while vm_populate() is running, and in this case vm_populate() may end up populating the new mapping instead of the old one. In order to reduce the possibility of userspace getting surprised by this behavior, this change introduces the VM_POPULATE vma flag which gets set on vmas we want vm_populate() to work on. This way vm_populate() may still end up populating the new mapping after such a race, but only if the new mapping is also one that the user has requested (using MAP_SHARED, MAP_LOCKED or mlock) to be populated. Signed-off-by: Michel Lespinasse Acked-by: Rik van Riel Tested-by: Andy Lutomirski Cc: Greg Ungerer Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + include/linux/mman.h | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0c34d3486816..9a5fcdeaa3a0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -87,6 +87,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ +#define VM_POPULATE 0x00001000 #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ diff --git a/include/linux/mman.h b/include/linux/mman.h index 9aa863da287f..61c7a87e5d2b 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -79,6 +79,8 @@ calc_vm_flag_bits(unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) | - _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ); + ((flags & MAP_LOCKED) ? (VM_LOCKED | VM_POPULATE) : 0) | + (((flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE) ? + VM_POPULATE : 0); } #endif /* _LINUX_MMAN_H */ -- cgit v1.2.3 From 41badc15cbad0350de34408c1b0c690f9df76d4b Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Fri, 22 Feb 2013 16:32:47 -0800 Subject: mm: make do_mmap_pgoff return populate as a size in bytes, not as a bool do_mmap_pgoff() rounds up the desired size to the next PAGE_SIZE multiple, however there was no equivalent code in mm_populate(), which caused issues. This could be fixed by introduced the same rounding in mm_populate(), however I think it's preferable to make do_mmap_pgoff() return populate as a size rather than as a boolean, so we don't have to duplicate the size rounding logic in mm_populate(). Signed-off-by: Michel Lespinasse Acked-by: Rik van Riel Tested-by: Andy Lutomirski Cc: Greg Ungerer Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9a5fcdeaa3a0..95db68e34b18 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1475,7 +1475,7 @@ extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff); extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, - unsigned long pgoff, bool *populate); + unsigned long pgoff, unsigned long *populate); extern int do_munmap(struct mm_struct *, unsigned long, size_t); #ifdef CONFIG_MMU -- cgit v1.2.3 From 6677e3eaf4d78abd7b09133414c05dc3ec353e7f Mon Sep 17 00:00:00 2001 From: Yasuaki Ishimatsu Date: Fri, 22 Feb 2013 16:32:52 -0800 Subject: memory-hotplug: check whether all memory blocks are offlined or not when removing memory We remove the memory like this: 1. lock memory hotplug 2. offline a memory block 3. unlock memory hotplug 4. repeat 1-3 to offline all memory blocks 5. lock memory hotplug 6. remove memory(TODO) 7. unlock memory hotplug All memory blocks must be offlined before removing memory. But we don't hold the lock in the whole operation. So we should check whether all memory blocks are offlined before step6. Otherwise, kernel maybe panicked. Offlining a memory block and removing a memory device can be two different operations. Users can just offline some memory blocks without removing the memory device. For this purpose, the kernel has held lock_memory_hotplug() in __offline_pages(). To reuse the code for memory hot-remove, we repeat step 1-3 to offline all the memory blocks, repeatedly lock and unlock memory hotplug, but not hold the memory hotplug lock in the whole operation. Signed-off-by: Wen Congyang Signed-off-by: Yasuaki Ishimatsu Signed-off-by: Tang Chen Acked-by: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Jiang Liu Cc: Jianguo Wu Cc: Kamezawa Hiroyuki Cc: Lai Jiangshan Cc: Wu Jianguo Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 4a45c4e50025..8dd0950a6a7a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -247,6 +247,7 @@ extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern int offline_memory_block(struct memory_block *mem); +extern bool is_memblock_offlined(struct memory_block *mem); extern int remove_memory(u64 start, u64 size); extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, int nr_pages); -- cgit v1.2.3 From 46c66c4b7ba0f9bb3e2ae3a3cfd40cd3472c8f80 Mon Sep 17 00:00:00 2001 From: Yasuaki Ishimatsu Date: Fri, 22 Feb 2013 16:32:56 -0800 Subject: memory-hotplug: remove /sys/firmware/memmap/X sysfs When (hot)adding memory into system, /sys/firmware/memmap/X/{end, start, type} sysfs files are created. But there is no code to remove these files. This patch implements the function to remove them. We cannot free firmware_map_entry which is allocated by bootmem because there is no way to do so when the system is up. But we can at least remember the address of that memory and reuse the storage when the memory is added next time. This patch also introduces a new list map_entries_bootmem to link the map entries allocated by bootmem when they are removed, and a lock to protect it. And these entries will be reused when the memory is hot-added again. The idea is suggestted by Andrew Morton. NOTE: It is unsafe to return an entry pointer and release the map_entries_lock. So we should not hold the map_entries_lock separately in firmware_map_find_entry() and firmware_map_remove_entry(). Hold the map_entries_lock across find and remove /sys/firmware/memmap/X operation. And also, users of these two functions need to be careful to hold the lock when using these two functions. [tangchen@cn.fujitsu.com: Hold spinlock across find|remove /sys operation] [tangchen@cn.fujitsu.com: fix the wrong comments of map_entries] [tangchen@cn.fujitsu.com: reuse the storage of /sys/firmware/memmap/X/ allocated by bootmem] [tangchen@cn.fujitsu.com: fix section mismatch problem] [tangchen@cn.fujitsu.com: fix the doc format in drivers/firmware/memmap.c] Signed-off-by: Wen Congyang Signed-off-by: Yasuaki Ishimatsu Signed-off-by: Tang Chen Reviewed-by: Kamezawa Hiroyuki Cc: KOSAKI Motohiro Cc: Jiang Liu Cc: Jianguo Wu Cc: Lai Jiangshan Cc: Tang Chen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Julian Calaby Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/firmware-map.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware-map.h b/include/linux/firmware-map.h index 43fe52fcef0f..71d4fa721db9 100644 --- a/include/linux/firmware-map.h +++ b/include/linux/firmware-map.h @@ -25,6 +25,7 @@ int firmware_map_add_early(u64 start, u64 end, const char *type); int firmware_map_add_hotplug(u64 start, u64 end, const char *type); +int firmware_map_remove(u64 start, u64 end, const char *type); #else /* CONFIG_FIRMWARE_MEMMAP */ @@ -38,6 +39,11 @@ static inline int firmware_map_add_hotplug(u64 start, u64 end, const char *type) return 0; } +static inline int firmware_map_remove(u64 start, u64 end, const char *type) +{ + return 0; +} + #endif /* CONFIG_FIRMWARE_MEMMAP */ #endif /* _LINUX_FIRMWARE_MAP_H */ -- cgit v1.2.3 From 24d335ca3606b610ec69c66a1e42760c96d89470 Mon Sep 17 00:00:00 2001 From: Wen Congyang Date: Fri, 22 Feb 2013 16:32:58 -0800 Subject: memory-hotplug: introduce new arch_remove_memory() for removing page table For removing memory, we need to remove page tables. But it depends on architecture. So the patch introduce arch_remove_memory() for removing page table. Now it only calls __remove_pages(). Note: __remove_pages() for some archtecuture is not implemented (I don't know how to implement it for s390). Signed-off-by: Wen Congyang Signed-off-by: Tang Chen Acked-by: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Jiang Liu Cc: Jianguo Wu Cc: Kamezawa Hiroyuki Cc: Lai Jiangshan Cc: Wu Jianguo Cc: Yasuaki Ishimatsu Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 8dd0950a6a7a..31a563bbd936 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -96,6 +96,7 @@ extern void __online_page_free(struct page *page); #ifdef CONFIG_MEMORY_HOTREMOVE extern bool is_pageblock_removable_nolock(struct page *page); +extern int arch_remove_memory(u64 start, u64 size); #endif /* CONFIG_MEMORY_HOTREMOVE */ /* reasonably generic interface to expand the physical pages in a zone */ -- cgit v1.2.3 From 46723bfa540f0a1e494476a1734d03626a0bd1e0 Mon Sep 17 00:00:00 2001 From: Yasuaki Ishimatsu Date: Fri, 22 Feb 2013 16:33:00 -0800 Subject: memory-hotplug: implement register_page_bootmem_info_section of sparse-vmemmap For removing memmap region of sparse-vmemmap which is allocated bootmem, memmap region of sparse-vmemmap needs to be registered by get_page_bootmem(). So the patch searches pages of virtual mapping and registers the pages by get_page_bootmem(). NOTE: register_page_bootmem_memmap() is not implemented for ia64, ppc, s390, and sparc. So introduce CONFIG_HAVE_BOOTMEM_INFO_NODE and revert register_page_bootmem_info_node() when platform doesn't support it. It's implemented by adding a new Kconfig option named CONFIG_HAVE_BOOTMEM_INFO_NODE, which will be automatically selected by memory-hotplug feature fully supported archs(currently only on x86_64). Since we have 2 config options called MEMORY_HOTPLUG and MEMORY_HOTREMOVE used for memory hot-add and hot-remove separately, and codes in function register_page_bootmem_info_node() are only used for collecting infomation for hot-remove, so reside it under MEMORY_HOTREMOVE. Besides page_isolation.c selected by MEMORY_ISOLATION under MEMORY_HOTPLUG is also such case, move it too. [mhocko@suse.cz: put register_page_bootmem_memmap inside CONFIG_MEMORY_HOTPLUG_SPARSE] [linfeng@cn.fujitsu.com: introduce CONFIG_HAVE_BOOTMEM_INFO_NODE and revert register_page_bootmem_info_node()] [mhocko@suse.cz: remove the arch specific functions without any implementation] [linfeng@cn.fujitsu.com: mm/Kconfig: move auto selects from MEMORY_HOTPLUG to MEMORY_HOTREMOVE as needed] [rientjes@google.com: fix defined but not used warning] Signed-off-by: Wen Congyang Signed-off-by: Yasuaki Ishimatsu Signed-off-by: Tang Chen Reviewed-by: Wu Jianguo Cc: KOSAKI Motohiro Cc: Jiang Liu Cc: Jianguo Wu Cc: Kamezawa Hiroyuki Cc: Lai Jiangshan Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Michal Hocko Signed-off-by: Lin Feng Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 13 ++++++------- include/linux/mm.h | 3 ++- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 31a563bbd936..4d523fe75ba1 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -174,17 +174,16 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) #endif /* CONFIG_NUMA */ #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ -#ifdef CONFIG_SPARSEMEM_VMEMMAP +#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE +extern void register_page_bootmem_info_node(struct pglist_data *pgdat); +#else static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) { } -static inline void put_page_bootmem(struct page *page) -{ -} -#else -extern void register_page_bootmem_info_node(struct pglist_data *pgdat); -extern void put_page_bootmem(struct page *page); #endif +extern void put_page_bootmem(struct page *page); +extern void get_page_bootmem(unsigned long ingo, struct page *page, + unsigned long type); /* * Lock for memory hotplug guarantees 1) all callbacks for memory hotplug diff --git a/include/linux/mm.h b/include/linux/mm.h index 95db68e34b18..060557b9764f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1718,7 +1718,8 @@ int vmemmap_populate_basepages(struct page *start_page, unsigned long pages, int node); int vmemmap_populate(struct page *start_page, unsigned long pages, int node); void vmemmap_populate_print_last(void); - +void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, + unsigned long size); enum mf_flags { MF_COUNT_INCREASED = 1 << 0, -- cgit v1.2.3 From ae9aae9eda2db71bf4b592f15618b0160eb07731 Mon Sep 17 00:00:00 2001 From: Wen Congyang Date: Fri, 22 Feb 2013 16:33:04 -0800 Subject: memory-hotplug: common APIs to support page tables hot-remove When memory is removed, the corresponding pagetables should alse be removed. This patch introduces some common APIs to support vmemmap pagetable and x86_64 architecture direct mapping pagetable removing. All pages of virtual mapping in removed memory cannot be freed if some pages used as PGD/PUD include not only removed memory but also other memory. So this patch uses the following way to check whether a page can be freed or not. 1) When removing memory, the page structs of the removed memory are filled with 0FD. 2) All page structs are filled with 0xFD on PT/PMD, PT/PMD can be cleared. In this case, the page used as PT/PMD can be freed. For direct mapping pages, update direct_pages_count[level] when we freed their pagetables. And do not free the pages again because they were freed when offlining. For vmemmap pages, free the pages and their pagetables. For larger pages, do not split them into smaller ones because there is no way to know if the larger page has been split. As a result, there is no way to decide when to split. We deal the larger pages in the following way: 1) For direct mapped pages, all the pages were freed when they were offlined. And since menmory offline is done section by section, all the memory ranges being removed are aligned to PAGE_SIZE. So only need to deal with unaligned pages when freeing vmemmap pages. 2) For vmemmap pages being used to store page_struct, if part of the larger page is still in use, just fill the unused part with 0xFD. And when the whole page is fulfilled with 0xFD, then free the larger page. [akpm@linux-foundation.org: fix typo in comment] [tangchen@cn.fujitsu.com: do not calculate direct mapping pages when freeing vmemmap pagetables] [tangchen@cn.fujitsu.com: do not free direct mapping pages twice] [tangchen@cn.fujitsu.com: do not free page split from hugepage one by one] [tangchen@cn.fujitsu.com: do not split pages when freeing pagetable pages] [akpm@linux-foundation.org: use pmd_page_vaddr()] [akpm@linux-foundation.org: fix used-uninitialised bug] Signed-off-by: Yasuaki Ishimatsu Signed-off-by: Jianguo Wu Signed-off-by: Wen Congyang Signed-off-by: Tang Chen Cc: KOSAKI Motohiro Cc: Jiang Liu Cc: Kamezawa Hiroyuki Cc: Lai Jiangshan Cc: Wu Jianguo Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 3cd16ba82f15..cdc3bab01832 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -53,6 +53,7 @@ extern void free_bootmem_node(pg_data_t *pgdat, unsigned long size); extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); +extern void __free_pages_bootmem(struct page *page, unsigned int order); /* * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, -- cgit v1.2.3 From 0197518cd3672029618a16a57597946a094ac7a8 Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Fri, 22 Feb 2013 16:33:08 -0800 Subject: memory-hotplug: remove memmap of sparse-vmemmap Introduce a new API vmemmap_free() to free and remove vmemmap pagetables. Since pagetable implements are different, each architecture has to provide its own version of vmemmap_free(), just like vmemmap_populate(). Note: vmemmap_free() is not implemented for ia64, ppc, s390, and sparc. [mhocko@suse.cz: fix implicit declaration of remove_pagetable] Signed-off-by: Yasuaki Ishimatsu Signed-off-by: Jianguo Wu Signed-off-by: Wen Congyang Signed-off-by: Tang Chen Cc: KOSAKI Motohiro Cc: Jiang Liu Cc: Kamezawa Hiroyuki Cc: Lai Jiangshan Cc: Wu Jianguo Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 060557b9764f..9d659491c0ae 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1718,6 +1718,9 @@ int vmemmap_populate_basepages(struct page *start_page, unsigned long pages, int node); int vmemmap_populate(struct page *start_page, unsigned long pages, int node); void vmemmap_populate_print_last(void); +#ifdef CONFIG_MEMORY_HOTPLUG +void vmemmap_free(struct page *memmap, unsigned long nr_pages); +#endif void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long size); -- cgit v1.2.3 From 60a5a19e7419ba0bc22ed01b3285e8940b42944c Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Fri, 22 Feb 2013 16:33:14 -0800 Subject: memory-hotplug: remove sysfs file of node Introduce a new function try_offline_node() to remove sysfs file of node when all memory sections of this node are removed. If some memory sections of this node are not removed, this function does nothing. Signed-off-by: Wen Congyang Signed-off-by: Tang Chen Cc: KOSAKI Motohiro Cc: Jiang Liu Cc: Jianguo Wu Cc: Kamezawa Hiroyuki Cc: Lai Jiangshan Cc: Wu Jianguo Cc: Yasuaki Ishimatsu Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 4d523fe75ba1..69903ccf549e 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -248,7 +248,7 @@ extern int arch_add_memory(int nid, u64 start, u64 size); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern int offline_memory_block(struct memory_block *mem); extern bool is_memblock_offlined(struct memory_block *mem); -extern int remove_memory(u64 start, u64 size); +extern int remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, int nr_pages); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms); -- cgit v1.2.3 From 90b30cdc1d87450e2ae89c8f8a29102dc2c1992e Mon Sep 17 00:00:00 2001 From: Wen Congyang Date: Fri, 22 Feb 2013 16:33:27 -0800 Subject: memory-hotplug: export the function try_offline_node() try_offline_node() will be needed in the tristate drivers/acpi/processor_driver.c. The node will be offlined when all memory/cpu on the node have been hotremoved. So we need the function try_offline_node() in cpu-hotplug path. If the memory-hotplug is disabled, and cpu-hotplug is enabled 1. no memory no the node we don't online the node, and cpu's node is the nearest node. 2. the node contains some memory the node has been onlined, and cpu's node is still needed to migrate the sleep task on the cpu to the same node. So we do nothing in try_offline_node() in this case. [rientjes@google.com: export the function try_offline_node() fix] Signed-off-by: Wen Congyang Signed-off-by: Tang Chen Cc: Yasuaki Ishimatsu Cc: David Rientjes Cc: Jiang Liu Cc: Minchan Kim Cc: KOSAKI Motohiro Cc: Mel Gorman Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Peter Zijlstra Cc: Len Brown Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 69903ccf549e..b6a3be7d47bf 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -233,6 +233,7 @@ static inline void unlock_memory_hotplug(void) {} #ifdef CONFIG_MEMORY_HOTREMOVE extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages); +extern void try_offline_node(int nid); #else static inline int is_mem_section_removable(unsigned long pfn, @@ -240,6 +241,8 @@ static inline int is_mem_section_removable(unsigned long pfn, { return 0; } + +static inline void try_offline_node(int nid) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ extern int mem_online_node(int nid); -- cgit v1.2.3 From 34b71f1e04fcba578e719e675b4882eeeb2a1f6f Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Fri, 22 Feb 2013 16:33:37 -0800 Subject: page_alloc: add movable_memmap kernel parameter Add functions to parse movablemem_map boot option. Since the option could be specified more then once, all the maps will be stored in the global variable movablemem_map.map array. And also, we keep the array in monotonic increasing order by start_pfn. And merge all overlapped ranges. [akpm@linux-foundation.org: improve comment] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: remove unneeded parens] Signed-off-by: Tang Chen Signed-off-by: Lai Jiangshan Reviewed-by: Wen Congyang Tested-by: Lin Feng Cc: Wu Jianguo Cc: Mel Gorman Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9d659491c0ae..ce9bd3049836 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1359,6 +1359,17 @@ extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); extern void sparse_memory_present_with_active_regions(int nid); +#define MOVABLEMEM_MAP_MAX MAX_NUMNODES +struct movablemem_entry { + unsigned long start_pfn; /* start pfn of memory segment */ + unsigned long end_pfn; /* end pfn of memory segment (exclusive) */ +}; + +struct movablemem_map { + int nr_map; + struct movablemem_entry map[MOVABLEMEM_MAP_MAX]; +}; + #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ -- cgit v1.2.3 From fb06bc8e5f42f38c011de0e59481f464a82380f6 Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Fri, 22 Feb 2013 16:33:42 -0800 Subject: page_alloc: bootmem limit with movablecore_map Ensure the bootmem will not allocate memory from areas that may be ZONE_MOVABLE. The map info is from movablecore_map boot option. Signed-off-by: Tang Chen Reviewed-by: Wen Congyang Reviewed-by: Lai Jiangshan Tested-by: Lin Feng Cc: Wu Jianguo Cc: Mel Gorman Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index f388203db7e8..dfefaf111c0e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -42,6 +42,7 @@ struct memblock { extern struct memblock memblock; extern int memblock_debug; +extern struct movablemem_map movablemem_map; #define memblock_dbg(fmt, ...) \ if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) -- cgit v1.2.3 From e8d1955258091e4c92d5a975ebd7fd8a98f5d30f Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Fri, 22 Feb 2013 16:33:44 -0800 Subject: acpi, memory-hotplug: parse SRAT before memblock is ready On linux, the pages used by kernel could not be migrated. As a result, if a memory range is used by kernel, it cannot be hot-removed. So if we want to hot-remove memory, we should prevent kernel from using it. The way now used to prevent this is specify a memory range by movablemem_map boot option and set it as ZONE_MOVABLE. But when the system is booting, memblock will allocate memory, and reserve the memory for kernel. And before we parse SRAT, and know the node memory ranges, memblock is working. And it may allocate memory in ranges to be set as ZONE_MOVABLE. This memory can be used by kernel, and never be freed. So, let's parse SRAT before memblock is called first. And it is early enough. The first call of memblock_find_in_range_node() is in: setup_arch() |-->setup_real_mode() so, this patch add a function early_parse_srat() to parse SRAT, and call it before setup_real_mode() is called. NOTE: 1) early_parse_srat() is called before numa_init(), and has initialized numa_meminfo. So DO NOT clear numa_nodes_parsed in numa_init() and DO NOT zero numa_meminfo in numa_init(), otherwise we will lose memory numa info. 2) I don't know why using count of memory affinities parsed from SRAT as a return value in original acpi_numa_init(). So I add a static variable srat_mem_cnt to remember this count and use it as the return value of the new acpi_numa_init() [mhocko@suse.cz: parse SRAT before memblock is ready fix] Signed-off-by: Tang Chen Reviewed-by: Wen Congyang Cc: KOSAKI Motohiro Cc: Jiang Liu Cc: Jianguo Wu Cc: Kamezawa Hiroyuki Cc: Lai Jiangshan Cc: Wu Jianguo Cc: Yasuaki Ishimatsu Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Len Brown Cc: "Brown, Len" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/acpi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index bcbdd7484e58..f46cfd73a553 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -485,6 +485,14 @@ static inline bool acpi_driver_match_device(struct device *dev, #endif /* !CONFIG_ACPI */ +#ifdef CONFIG_ACPI_NUMA +void __init early_parse_srat(void); +#else +static inline void early_parse_srat(void) +{ +} +#endif + #ifdef CONFIG_ACPI void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, u32 pm1a_ctrl, u32 pm1b_ctrl)); -- cgit v1.2.3 From 27168d38fa209073219abedbe6a9de7ba9acbfad Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Fri, 22 Feb 2013 16:33:46 -0800 Subject: acpi, memory-hotplug: extend movablemem_map ranges to the end of node When implementing movablemem_map boot option, we introduced an array movablemem_map.map[] to store the memory ranges to be set as ZONE_MOVABLE. Since ZONE_MOVABLE is the latst zone of a node, if user didn't specify the whole node memory range, we need to extend it to the node end so that we can use it to prevent memblock from allocating memory in the ranges user didn't specify. We now implement movablemem_map boot option like this: /* * For movablemem_map=nn[KMG]@ss[KMG]: * * SRAT: |_____| |_____| |_________| |_________| ...... * node id: 0 1 1 2 * user specified: |__| |___| * movablemem_map: |___| |_________| |______| ...... * * Using movablemem_map, we can prevent memblock from allocating memory * on ZONE_MOVABLE at boot time. * * NOTE: In this case, SRAT info will be ingored. */ [akpm@linux-foundation.org: clean up code, fix build warning] Signed-off-by: Tang Chen Cc: KOSAKI Motohiro Cc: Jiang Liu Cc: Jianguo Wu Cc: Kamezawa Hiroyuki Cc: Lai Jiangshan Cc: Wu Jianguo Cc: Yasuaki Ishimatsu Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Len Brown Cc: "Brown, Len" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ce9bd3049836..4d7377a1d084 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1368,8 +1368,13 @@ struct movablemem_entry { struct movablemem_map { int nr_map; struct movablemem_entry map[MOVABLEMEM_MAP_MAX]; + nodemask_t numa_nodes_hotplug; /* on which nodes we specify memory */ }; +extern void __init insert_movablemem_map(unsigned long start_pfn, + unsigned long end_pfn); +extern int __init movablemem_map_overlap(unsigned long start_pfn, + unsigned long end_pfn); #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ -- cgit v1.2.3 From 01a178a94e8eaec351b29ee49fbb3d1c124cb7fb Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Fri, 22 Feb 2013 16:33:49 -0800 Subject: acpi, memory-hotplug: support getting hotplug info from SRAT We now provide an option for users who don't want to specify physical memory address in kernel commandline. /* * For movablemem_map=acpi: * * SRAT: |_____| |_____| |_________| |_________| ...... * node id: 0 1 1 2 * hotpluggable: n y y n * movablemem_map: |_____| |_________| * * Using movablemem_map, we can prevent memblock from allocating memory * on ZONE_MOVABLE at boot time. */ So user just specify movablemem_map=acpi, and the kernel will use hotpluggable info in SRAT to determine which memory ranges should be set as ZONE_MOVABLE. If all the memory ranges in SRAT is hotpluggable, then no memory can be used by kernel. But before parsing SRAT, memblock has already reserve some memory ranges for other purposes, such as for kernel image, and so on. We cannot prevent kernel from using these memory. So we need to exclude these ranges even if these memory is hotpluggable. Furthermore, there could be several memory ranges in the single node which the kernel resides in. We may skip one range that have memory reserved by memblock, but if the rest of memory is too small, then the kernel will fail to boot. So, make the whole node which the kernel resides in un-hotpluggable. Then the kernel has enough memory to use. NOTE: Using this way will cause NUMA performance down because the whole node will be set as ZONE_MOVABLE, and kernel cannot use memory on it. If users don't want to lose NUMA performance, just don't use it. [akpm@linux-foundation.org: fix warning] [akpm@linux-foundation.org: use strcmp()] Signed-off-by: Tang Chen Cc: KOSAKI Motohiro Cc: Jiang Liu Cc: Jianguo Wu Cc: Kamezawa Hiroyuki Cc: Lai Jiangshan Cc: Wu Jianguo Cc: Yasuaki Ishimatsu Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Len Brown Cc: "Brown, Len" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 4d7377a1d084..72a42c0fa633 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1366,9 +1366,11 @@ struct movablemem_entry { }; struct movablemem_map { + bool acpi; /* true if using SRAT info */ int nr_map; struct movablemem_entry map[MOVABLEMEM_MAP_MAX]; nodemask_t numa_nodes_hotplug; /* on which nodes we specify memory */ + nodemask_t numa_nodes_kernel; /* on which nodes kernel resides in */ }; extern void __init insert_movablemem_map(unsigned long start_pfn, -- cgit v1.2.3 From f7210e6c4ac795694106c1c5307134d3fc233e88 Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Fri, 22 Feb 2013 16:33:51 -0800 Subject: mm/memblock.c: use CONFIG_HAVE_MEMBLOCK_NODE_MAP to protect movablecore_map in memblock_overlaps_region(). The definition of struct movablecore_map is protected by CONFIG_HAVE_MEMBLOCK_NODE_MAP but its use in memblock_overlaps_region() is not. So add CONFIG_HAVE_MEMBLOCK_NODE_MAP to protect the use of movablecore_map in memblock_overlaps_region(). Signed-off-by: Tang Chen Reported-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index dfefaf111c0e..3e5ecb2d790e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -61,6 +61,7 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size); void memblock_trim_memory(phys_addr_t align); #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP + void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid); -- cgit v1.2.3 From 194159fbcc0d6ac1351837d3cd7a27a4af0219a6 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Fri, 22 Feb 2013 16:33:58 -0800 Subject: mm: remove MIGRATE_ISOLATE check in hotpath Several functions test MIGRATE_ISOLATE and some of those are hotpath but MIGRATE_ISOLATE is used only if we enable CONFIG_MEMORY_ISOLATION(ie, CMA, memory-hotplug and memory-failure) which are not common config option. So let's not add unnecessary overhead and code when we don't enable CONFIG_MEMORY_ISOLATION. Signed-off-by: Minchan Kim Cc: KOSAKI Motohiro Acked-by: Michal Nazarewicz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 ++ include/linux/page-isolation.h | 19 +++++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 73b64a38b984..4f4c8c26fa9d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -57,7 +57,9 @@ enum { */ MIGRATE_CMA, #endif +#ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ +#endif MIGRATE_TYPES }; diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index a92061e08d48..3fff8e774067 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -1,6 +1,25 @@ #ifndef __LINUX_PAGEISOLATION_H #define __LINUX_PAGEISOLATION_H +#ifdef CONFIG_MEMORY_ISOLATION +static inline bool is_migrate_isolate_page(struct page *page) +{ + return get_pageblock_migratetype(page) == MIGRATE_ISOLATE; +} +static inline bool is_migrate_isolate(int migratetype) +{ + return migratetype == MIGRATE_ISOLATE; +} +#else +static inline bool is_migrate_isolate_page(struct page *page) +{ + return false; +} +static inline bool is_migrate_isolate(int migratetype) +{ + return false; +} +#endif bool has_unmovable_pages(struct zone *zone, struct page *page, int count, bool skip_hwpoisoned_pages); -- cgit v1.2.3 From 293c07e31ab5a0b8df8c19b2a9e5c6fa30308849 Mon Sep 17 00:00:00 2001 From: Xishi Qiu Date: Fri, 22 Feb 2013 16:34:02 -0800 Subject: memory-failure: use num_poisoned_pages instead of mce_bad_pages Since MCE is an x86 concept, and this code is in mm/, it would be better to use the name num_poisoned_pages instead of mce_bad_pages. [akpm@linux-foundation.org: fix mm/sparse.c] Signed-off-by: Xishi Qiu Signed-off-by: Jiang Liu Suggested-by: Borislav Petkov Reviewed-by: Wanpeng Li Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 72a42c0fa633..a114b8eb7676 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1753,7 +1753,7 @@ extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); -extern atomic_long_t mce_bad_pages; +extern atomic_long_t num_poisoned_pages; extern int soft_offline_page(struct page *page, int flags); extern void dump_page(struct page *page); -- cgit v1.2.3 From 258401a60c4df39332f30ef57afbc6dbf29a7e84 Mon Sep 17 00:00:00 2001 From: Zlatko Calusic Date: Fri, 22 Feb 2013 16:34:06 -0800 Subject: mm: don't wait on congested zones in balance_pgdat() From: Zlatko Calusic Commit 92df3a723f84 ("mm: vmscan: throttle reclaim if encountering too many dirty pages under writeback") introduced waiting on congested zones based on a sane algorithm in shrink_inactive_list(). What this means is that there's no more need for throttling and additional heuristics in balance_pgdat(). So, let's remove it and tidy up the code. Signed-off-by: Zlatko Calusic Cc: Mel Gorman Cc: Minchan Kim Cc: Johannes Weiner Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index fce0a2799d43..bd6cf61142be 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -36,7 +36,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL, KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY, - KSWAPD_SKIP_CONGESTION_WAIT, PAGEOUTRUN, ALLOCSTALL, PGROTATED, #ifdef CONFIG_NUMA_BALANCING NUMA_PTE_UPDATES, -- cgit v1.2.3 From 21caf2fc1931b485483ddd254b634fa8f0099963 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 22 Feb 2013 16:34:08 -0800 Subject: mm: teach mm by current context info to not do I/O during memory allocation This patch introduces PF_MEMALLOC_NOIO on process flag('flags' field of 'struct task_struct'), so that the flag can be set by one task to avoid doing I/O inside memory allocation in the task's context. The patch trys to solve one deadlock problem caused by block device, and the problem may happen at least in the below situations: - during block device runtime resume, if memory allocation with GFP_KERNEL is called inside runtime resume callback of any one of its ancestors(or the block device itself), the deadlock may be triggered inside the memory allocation since it might not complete until the block device becomes active and the involed page I/O finishes. The situation is pointed out first by Alan Stern. It is not a good approach to convert all GFP_KERNEL[1] in the path into GFP_NOIO because several subsystems may be involved(for example, PCI, USB and SCSI may be involved for usb mass stoarage device, network devices involved too in the iSCSI case) - during block device runtime suspend, because runtime resume need to wait for completion of concurrent runtime suspend. - during error handling of usb mass storage deivce, USB bus reset will be put on the device, so there shouldn't have any memory allocation with GFP_KERNEL during USB bus reset, otherwise the deadlock similar with above may be triggered. Unfortunately, any usb device may include one mass storage interface in theory, so it requires all usb interface drivers to handle the situation. In fact, most usb drivers don't know how to handle bus reset on the device and don't provide .pre_set() and .post_reset() callback at all, so USB core has to unbind and bind driver for these devices. So it is still not practical to resort to GFP_NOIO for solving the problem. Also the introduced solution can be used by block subsystem or block drivers too, for example, set the PF_MEMALLOC_NOIO flag before doing actual I/O transfer. It is not a good idea to convert all these GFP_KERNEL in the affected path into GFP_NOIO because these functions doing that may be implemented as library and will be called in many other contexts. In fact, memalloc_noio_flags() can convert some of current static GFP_NOIO allocation into GFP_KERNEL back in other non-affected contexts, at least almost all GFP_NOIO in USB subsystem can be converted into GFP_KERNEL after applying the approach and make allocation with GFP_NOIO only happen in runtime resume/bus reset/block I/O transfer contexts generally. [1], several GFP_KERNEL allocation examples in runtime resume path - pci subsystem acpi_os_allocate <-acpi_ut_allocate <-ACPI_ALLOCATE_ZEROED <-acpi_evaluate_object <-__acpi_bus_set_power <-acpi_bus_set_power <-acpi_pci_set_power_state <-platform_pci_set_power_state <-pci_platform_power_transition <-__pci_complete_power_transition <-pci_set_power_state <-pci_restore_standard_config <-pci_pm_runtime_resume - usb subsystem usb_get_status <-finish_port_resume <-usb_port_resume <-generic_resume <-usb_resume_device <-usb_resume_both <-usb_runtime_resume - some individual usb drivers usblp, uvc, gspca, most of dvb-usb-v2 media drivers, cpia2, az6007, .... That is just what I have found. Unfortunately, this allocation can only be found by human being now, and there should be many not found since any function in the resume path(call tree) may allocate memory with GFP_KERNEL. Signed-off-by: Ming Lei Signed-off-by: Minchan Kim Cc: Alan Stern Cc: Oliver Neukum Cc: Jiri Kosina Cc: Mel Gorman Cc: KAMEZAWA Hiroyuki Cc: Michal Hocko Cc: Ingo Molnar Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Greg KH Cc: Jens Axboe Cc: "David S. Miller" Cc: Eric Dumazet Cc: David Decotigny Cc: Tom Herbert Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index e4112aad2964..c2182b53dace 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -51,6 +51,7 @@ struct sched_param { #include #include #include +#include #include @@ -1791,6 +1792,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define PF_FROZEN 0x00010000 /* frozen for system suspend */ #define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */ #define PF_KSWAPD 0x00040000 /* I am kswapd */ +#define PF_MEMALLOC_NOIO 0x00080000 /* Allocating memory without IO involved */ #define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ @@ -1828,6 +1830,26 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) +/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */ +static inline gfp_t memalloc_noio_flags(gfp_t flags) +{ + if (unlikely(current->flags & PF_MEMALLOC_NOIO)) + flags &= ~__GFP_IO; + return flags; +} + +static inline unsigned int memalloc_noio_save(void) +{ + unsigned int flags = current->flags & PF_MEMALLOC_NOIO; + current->flags |= PF_MEMALLOC_NOIO; + return flags; +} + +static inline void memalloc_noio_restore(unsigned int flags) +{ + current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags; +} + /* * task->jobctl flags */ -- cgit v1.2.3 From e823407f7b11fa06ba8e7a2801eb9ed11268a7ec Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 22 Feb 2013 16:34:11 -0800 Subject: pm / runtime: introduce pm_runtime_set_memalloc_noio() Introduce the flag memalloc_noio in 'struct dev_pm_info' to help PM core to teach mm not allocating memory with GFP_KERNEL flag for avoiding probable deadlock. As explained in the comment, any GFP_KERNEL allocation inside runtime_resume() or runtime_suspend() on any one of device in the path from one block or network device to the root device in the device tree may cause deadlock, the introduced pm_runtime_set_memalloc_noio() sets or clears the flag on device in the path recursively. Signed-off-by: Ming Lei Cc: Minchan Kim Cc: Alan Stern Cc: Oliver Neukum Cc: Jiri Kosina Cc: Mel Gorman Cc: KAMEZAWA Hiroyuki Cc: Michal Hocko Cc: Ingo Molnar Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Greg KH Cc: Jens Axboe Cc: "David S. Miller" Cc: Eric Dumazet Cc: David Decotigny Cc: Tom Herbert Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pm.h | 1 + include/linux/pm_runtime.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 97bcf23e045a..e5d7230332a4 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -537,6 +537,7 @@ struct dev_pm_info { unsigned int irq_safe:1; unsigned int use_autosuspend:1; unsigned int timer_autosuspends:1; + unsigned int memalloc_noio:1; enum rpm_request request; enum rpm_status runtime_status; int runtime_error; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index c785c215abfc..7d7e09efff9b 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -47,6 +47,7 @@ extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay); extern unsigned long pm_runtime_autosuspend_expiration(struct device *dev); extern void pm_runtime_update_max_time_suspended(struct device *dev, s64 delta_ns); +extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); static inline bool pm_children_suspended(struct device *dev) { @@ -156,6 +157,8 @@ static inline void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) {} static inline unsigned long pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } +static inline void pm_runtime_set_memalloc_noio(struct device *dev, + bool enable){} #endif /* !CONFIG_PM_RUNTIME */ -- cgit v1.2.3 From cf82f3489cf414fe27c6c5af2b372fdcd2a58b24 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 22 Feb 2013 16:34:24 -0800 Subject: mm: remove unused memclear_highpage_flush() Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index ef788b5b4a35..7fb31da45d03 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -219,12 +219,6 @@ static inline void zero_user(struct page *page, zero_user_segments(page, start, start + size, 0, 0); } -static inline void __deprecated memclear_highpage_flush(struct page *page, - unsigned int offset, unsigned int size) -{ - zero_user(page, offset, size); -} - #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE static inline void copy_user_highpage(struct page *to, struct page *from, -- cgit v1.2.3 From 34f0315adb58af3b01f59d05b2bce267474e71cb Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 22 Feb 2013 16:34:25 -0800 Subject: mm: numa: fix minor typo in numa_next_scan s/me/be/ and clarify the comment a bit when we're changing it anyway. Signed-off-by: Mel Gorman Suggested-by: Simon Jeons Cc: Peter Zijlstra Cc: Andrea Arcangeli Cc: Ingo Molnar Cc: Wanpeng Li Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f8f5162a3571..47047cb4d8e5 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -414,9 +414,9 @@ struct mm_struct { #endif #ifdef CONFIG_NUMA_BALANCING /* - * numa_next_scan is the next time when the PTEs will me marked - * pte_numa to gather statistics and migrate pages to new nodes - * if necessary + * numa_next_scan is the next time that the PTEs will be marked + * pte_numa. NUMA hinting faults will gather statistics and migrate + * pages to new nodes if necessary. */ unsigned long numa_next_scan; -- cgit v1.2.3 From 3c0ff4689630b280704666833e9539d84cddc373 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 22 Feb 2013 16:34:29 -0800 Subject: mm: numa: handle side-effects in count_vm_numa_events() for !CONFIG_NUMA_BALANCING The current definitions for count_vm_numa_events() is wrong for !CONFIG_NUMA_BALANCING as the following would miss the side-effect. count_vm_numa_events(NUMA_FOO, bar++); There are no such users of count_vm_numa_events() but this patch fixes it as it is a potential pitfall. Ideally both would be converted to static inline but NUMA_PTE_UPDATES is not defined if !CONFIG_NUMA_BALANCING and creating dummy constants just to have a static inline would be similarly clumsy. Signed-off-by: Mel Gorman Cc: Peter Zijlstra Cc: Andrea Arcangeli Cc: Ingo Molnar Cc: Simon Jeons Cc: Wanpeng Li Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index a13291f7da88..5fd71a7d0dfd 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -85,7 +85,7 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) -#define count_vm_numa_events(x, y) do {} while (0) +#define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #define __count_zone_vm_events(item, zone, delta) \ -- cgit v1.2.3 From bbeae5b05ef6e40bf54db05ceb8635824153b9e2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Feb 2013 16:34:30 -0800 Subject: mm: move page flags layout to separate header This is a preparation patch for moving page->_last_nid into page->flags that moves page flag layout information to a separate header. This patch is necessary because otherwise there would be a circular dependency between mm_types.h and mm.h. Signed-off-by: Mel Gorman Cc: Peter Zijlstra Cc: Andrea Arcangeli Cc: Ingo Molnar Cc: Simon Jeons Cc: Wanpeng Li Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 40 ---------------------- include/linux/mm_types.h | 1 + include/linux/mmzone.h | 22 +----------- include/linux/page-flags-layout.h | 71 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 73 insertions(+), 61 deletions(-) create mode 100644 include/linux/page-flags-layout.h (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a114b8eb7676..c2d7d5993b14 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -581,51 +581,11 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) * sets it, so none of the operations on it need to be atomic. */ - -/* - * page->flags layout: - * - * There are three possibilities for how page->flags get - * laid out. The first is for the normal case, without - * sparsemem. The second is for sparsemem when there is - * plenty of space for node and section. The last is when - * we have run out of space and have to fall back to an - * alternate (slower) way of determining the node. - * - * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS | - * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS | - * classic sparse no space for node: | SECTION | ZONE | ... | FLAGS | - */ -#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) -#define SECTIONS_WIDTH SECTIONS_SHIFT -#else -#define SECTIONS_WIDTH 0 -#endif - -#define ZONES_WIDTH ZONES_SHIFT - -#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS -#define NODES_WIDTH NODES_SHIFT -#else -#ifdef CONFIG_SPARSEMEM_VMEMMAP -#error "Vmemmap: No space for nodes field in page flags" -#endif -#define NODES_WIDTH 0 -#endif - /* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) -/* - * We are going to use the flags for the page to node mapping if its in - * there. This includes the case where there is no node, so it is implicit. - */ -#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0) -#define NODE_NOT_IN_PAGE_FLAGS -#endif - /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 47047cb4d8e5..d05d632c716e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -12,6 +12,7 @@ #include #include #include +#include #include #include diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4f4c8c26fa9d..6c80d0ac14dd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include @@ -310,24 +310,6 @@ enum zone_type { #ifndef __GENERATING_BOUNDS_H -/* - * When a memory allocation must conform to specific limitations (such - * as being suitable for DMA) the caller will pass in hints to the - * allocator in the gfp_mask, in the zone modifier bits. These bits - * are used to select a priority ordered list of memory zones which - * match the requested limits. See gfp_zone() in include/linux/gfp.h - */ - -#if MAX_NR_ZONES < 2 -#define ZONES_SHIFT 0 -#elif MAX_NR_ZONES <= 2 -#define ZONES_SHIFT 1 -#elif MAX_NR_ZONES <= 4 -#define ZONES_SHIFT 2 -#else -#error ZONES_SHIFT -- too many zones configured adjust calculation -#endif - struct zone { /* Fields commonly accessed by the page allocator */ @@ -1055,8 +1037,6 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn) * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ -#define SECTIONS_SHIFT (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS) - #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h new file mode 100644 index 000000000000..316805d6ba1b --- /dev/null +++ b/include/linux/page-flags-layout.h @@ -0,0 +1,71 @@ +#ifndef PAGE_FLAGS_LAYOUT_H +#define PAGE_FLAGS_LAYOUT_H + +#include +#include + +/* + * When a memory allocation must conform to specific limitations (such + * as being suitable for DMA) the caller will pass in hints to the + * allocator in the gfp_mask, in the zone modifier bits. These bits + * are used to select a priority ordered list of memory zones which + * match the requested limits. See gfp_zone() in include/linux/gfp.h + */ +#if MAX_NR_ZONES < 2 +#define ZONES_SHIFT 0 +#elif MAX_NR_ZONES <= 2 +#define ZONES_SHIFT 1 +#elif MAX_NR_ZONES <= 4 +#define ZONES_SHIFT 2 +#else +#error ZONES_SHIFT -- too many zones configured adjust calculation +#endif + +#ifdef CONFIG_SPARSEMEM +#include + +/* SECTION_SHIFT #bits space required to store a section # */ +#define SECTIONS_SHIFT (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS) + +#endif /* CONFIG_SPARSEMEM */ + +/* + * page->flags layout: + * + * There are three possibilities for how page->flags get + * laid out. The first is for the normal case, without + * sparsemem. The second is for sparsemem when there is + * plenty of space for node and section. The last is when + * we have run out of space and have to fall back to an + * alternate (slower) way of determining the node. + * + * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS | + * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS | + * classic sparse no space for node: | SECTION | ZONE | ... | FLAGS | + */ +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +#define SECTIONS_WIDTH SECTIONS_SHIFT +#else +#define SECTIONS_WIDTH 0 +#endif + +#define ZONES_WIDTH ZONES_SHIFT + +#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#define NODES_WIDTH NODES_SHIFT +#else +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#error "Vmemmap: No space for nodes field in page flags" +#endif +#define NODES_WIDTH 0 +#endif + +/* + * We are going to use the flags for the page to node mapping if its in + * there. This includes the case where there is no node, so it is implicit. + */ +#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0) +#define NODE_NOT_IN_PAGE_FLAGS +#endif + +#endif /* _LINUX_PAGE_FLAGS_LAYOUT */ -- cgit v1.2.3 From 75980e97daccfc6babbac7e180ff118537955f5d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Feb 2013 16:34:32 -0800 Subject: mm: fold page->_last_nid into page->flags where possible page->_last_nid fits into page->flags on 64-bit. The unlikely 32-bit NUMA configuration with NUMA Balancing will still need an extra page field. As Peter notes "Completely dropping 32bit support for CONFIG_NUMA_BALANCING would simplify things, but it would also remove the warning if we grow enough 64bit only page-flags to push the last-cpu out." [mgorman@suse.de: minor modifications] Signed-off-by: Mel Gorman Cc: Peter Zijlstra Cc: Andrea Arcangeli Cc: Ingo Molnar Cc: Simon Jeons Cc: Wanpeng Li Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 33 ++++++++++++++++++++++++++++++++- include/linux/mm_types.h | 2 +- include/linux/page-flags-layout.h | 33 +++++++++++++++++++++++++-------- 3 files changed, 58 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c2d7d5993b14..473abbda942e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -581,10 +581,11 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) * sets it, so none of the operations on it need to be atomic. */ -/* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */ +/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_NID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) +#define LAST_NID_PGOFF (ZONES_PGOFF - LAST_NID_WIDTH) /* * Define the bit shifts to access each section. For non-existent @@ -594,6 +595,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) +#define LAST_NID_PGSHIFT (LAST_NID_PGOFF * (LAST_NID_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS @@ -615,6 +617,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) +#define LAST_NID_MASK ((1UL << LAST_NID_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) @@ -654,6 +657,7 @@ static inline int page_to_nid(const struct page *page) #endif #ifdef CONFIG_NUMA_BALANCING +#ifdef LAST_NID_NOT_IN_PAGE_FLAGS static inline int page_xchg_last_nid(struct page *page, int nid) { return xchg(&page->_last_nid, nid); @@ -668,6 +672,33 @@ static inline void reset_page_last_nid(struct page *page) page->_last_nid = -1; } #else +static inline int page_last_nid(struct page *page) +{ + return (page->flags >> LAST_NID_PGSHIFT) & LAST_NID_MASK; +} + +static inline int page_xchg_last_nid(struct page *page, int nid) +{ + unsigned long old_flags, flags; + int last_nid; + + do { + old_flags = flags = page->flags; + last_nid = page_last_nid(page); + + flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT); + flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT; + } while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags)); + + return last_nid; +} + +static inline void reset_page_last_nid(struct page *page) +{ + page_xchg_last_nid(page, (1 << LAST_NID_SHIFT) - 1); +} +#endif /* LAST_NID_NOT_IN_PAGE_FLAGS */ +#else static inline int page_xchg_last_nid(struct page *page, int nid) { return page_to_nid(page); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index d05d632c716e..ace9a5f01c64 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -174,7 +174,7 @@ struct page { void *shadow; #endif -#ifdef CONFIG_NUMA_BALANCING +#ifdef LAST_NID_NOT_IN_PAGE_FLAGS int _last_nid; #endif } diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index 316805d6ba1b..93506a114034 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -32,15 +32,16 @@ /* * page->flags layout: * - * There are three possibilities for how page->flags get - * laid out. The first is for the normal case, without - * sparsemem. The second is for sparsemem when there is - * plenty of space for node and section. The last is when - * we have run out of space and have to fall back to an - * alternate (slower) way of determining the node. + * There are five possibilities for how page->flags get laid out. The first + * pair is for the normal case without sparsemem. The second pair is for + * sparsemem when there is plenty of space for node and section information. + * The last is when there is insufficient space in page->flags and a separate + * lookup is necessary. * - * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS | - * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS | + * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS | + * " plus space for last_nid: | NODE | ZONE | LAST_NID ... | FLAGS | + * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS | + * " plus space for last_nid: | SECTION | NODE | ZONE | LAST_NID ... | FLAGS | * classic sparse no space for node: | SECTION | ZONE | ... | FLAGS | */ #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) @@ -60,6 +61,18 @@ #define NODES_WIDTH 0 #endif +#ifdef CONFIG_NUMA_BALANCING +#define LAST_NID_SHIFT NODES_SHIFT +#else +#define LAST_NID_SHIFT 0 +#endif + +#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_NID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#define LAST_NID_WIDTH LAST_NID_SHIFT +#else +#define LAST_NID_WIDTH 0 +#endif + /* * We are going to use the flags for the page to node mapping if its in * there. This includes the case where there is no node, so it is implicit. @@ -68,4 +81,8 @@ #define NODE_NOT_IN_PAGE_FLAGS #endif +#if defined(CONFIG_NUMA_BALANCING) && LAST_NID_WIDTH == 0 +#define LAST_NID_NOT_IN_PAGE_FLAGS +#endif + #endif /* _LINUX_PAGE_FLAGS_LAYOUT */ -- cgit v1.2.3 From 9800339b5e0f0e24ab3dac349e0de80d2018832e Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 22 Feb 2013 16:34:35 -0800 Subject: mm: don't inline page_mapping() According to akpm, this saves 1/2k text and makes things simple for the next patch. Numbers from Minchan: add/remove: 1/0 grow/shrink: 6/22 up/down: 92/-516 (-424) function old new delta page_mapping - 48 +48 do_task_stat 2292 2308 +16 page_remove_rmap 240 248 +8 load_elf_binary 4500 4508 +8 update_queue 532 536 +4 scsi_probe_and_add_lun 2892 2896 +4 lookup_fast 644 648 +4 vcs_read 1040 1036 -4 __ip_route_output_key 1904 1900 -4 ip_route_input_noref 2508 2500 -8 shmem_file_aio_read 784 772 -12 __isolate_lru_page 272 256 -16 shmem_replace_page 708 688 -20 mark_buffer_dirty 228 208 -20 __set_page_dirty_buffers 240 220 -20 __remove_mapping 276 256 -20 update_mmu_cache 500 476 -24 set_page_dirty_balance 92 68 -24 set_page_dirty 172 148 -24 page_evictable 88 64 -24 page_cache_pipe_buf_steal 248 224 -24 clear_page_dirty_for_io 340 316 -24 test_set_page_writeback 400 372 -28 test_clear_page_writeback 516 488 -28 invalidate_inode_page 156 128 -28 page_mkclean 432 400 -32 flush_dcache_page 360 328 -32 __set_page_dirty_nobuffers 324 280 -44 shrink_page_list 2412 2356 -56 Signed-off-by: Shaohua Li Suggested-by: Andrew Morton Cc: Hugh Dickins Acked-by: Rik van Riel Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 473abbda942e..1d4122bf6f27 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -809,18 +809,7 @@ void page_address_init(void); #define PAGE_MAPPING_KSM 2 #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM) -extern struct address_space swapper_space; -static inline struct address_space *page_mapping(struct page *page) -{ - struct address_space *mapping = page->mapping; - - VM_BUG_ON(PageSlab(page)); - if (unlikely(PageSwapCache(page))) - mapping = &swapper_space; - else if ((unsigned long)mapping & PAGE_MAPPING_ANON) - mapping = NULL; - return mapping; -} +extern struct address_space *page_mapping(struct page *page); /* Neutral page->mapping pointer to address_space or anon_vma or other */ static inline void *page_rmapping(struct page *page) -- cgit v1.2.3 From 33806f06da654092182410d974b6d3c5396ea3eb Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 22 Feb 2013 16:34:37 -0800 Subject: swap: make each swap partition have one address_space When I use several fast SSD to do swap, swapper_space.tree_lock is heavily contended. This makes each swap partition have one address_space to reduce the lock contention. There is an array of address_space for swap. The swap entry type is the index to the array. In my test with 3 SSD, this increases the swapout throughput 20%. [akpm@linux-foundation.org: revert unneeded change to __add_to_swap_cache] Signed-off-by: Shaohua Li Cc: Hugh Dickins Acked-by: Rik van Riel Acked-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 8c66486a8ca8..235c039892ee 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -8,7 +8,7 @@ #include #include #include - +#include #include #include @@ -330,8 +330,9 @@ 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 +extern struct address_space swapper_spaces[]; +#define swap_address_space(entry) (&swapper_spaces[swp_type(entry)]) +extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); extern int add_to_swap(struct page *); extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); @@ -382,7 +383,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) #define nr_swap_pages 0L #define total_swap_pages 0L -#define total_swapcache_pages 0UL +#define total_swapcache_pages() 0UL #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) -- cgit v1.2.3 From ec8acf20afb8534ed511f6613dd2226b9e301010 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 22 Feb 2013 16:34:38 -0800 Subject: swap: add per-partition lock for swapfile swap_lock is heavily contended when I test swap to 3 fast SSD (even slightly slower than swap to 2 such SSD). The main contention comes from swap_info_get(). This patch tries to fix the gap with adding a new per-partition lock. Global data like nr_swapfiles, total_swap_pages, least_priority and swap_list are still protected by swap_lock. nr_swap_pages is an atomic now, it can be changed without swap_lock. In theory, it's possible get_swap_page() finds no swap pages but actually there are free swap pages. But sounds not a big problem. Accessing partition specific data (like scan_swap_map and so on) is only protected by swap_info_struct.lock. Changing swap_info_struct.flags need hold swap_lock and swap_info_struct.lock, because scan_scan_map() will check it. read the flags is ok with either the locks hold. If both swap_lock and swap_info_struct.lock must be hold, we always hold the former first to avoid deadlock. swap_entry_free() can change swap_list. To delete that code, we add a new highest_priority_index. Whenever get_swap_page() is called, we check it. If it's valid, we use it. It's a pity get_swap_page() still holds swap_lock(). But in practice, swap_lock() isn't heavily contended in my test with this patch (or I can say there are other much more heavier bottlenecks like TLB flush). And BTW, looks get_swap_page() doesn't really need the lock. We never free swap_info[] and we check SWAP_WRITEOK flag. The only risk without the lock is we could swapout to some low priority swap, but we can quickly recover after several rounds of swap, so sounds not a big deal to me. But I'd prefer to fix this if it's a real problem. "swap: make each swap partition have one address_space" improved the swapout speed from 1.7G/s to 2G/s. This patch further improves the speed to 2.3G/s, so around 15% improvement. It's a multi-process test, so TLB flush isn't the biggest bottleneck before the patches. [arnd@arndb.de: fix it for nommu] [hughd@google.com: add missing unlock] [minchan@kernel.org: get rid of lockdep whinge on sys_swapon] Signed-off-by: Shaohua Li Cc: Hugh Dickins Cc: Rik van Riel Cc: Minchan Kim Cc: Greg Kroah-Hartman Cc: Seth Jennings Cc: Konrad Rzeszutek Wilk Cc: Xiao Guangrong Cc: Dan Magenheimer Cc: Stephen Rothwell Signed-off-by: Arnd Bergmann Signed-off-by: Hugh Dickins Signed-off-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 32 +++++++++++++++++++++++++++----- 1 file changed, 27 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 235c039892ee..a3e22d357e91 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -202,6 +202,18 @@ struct swap_info_struct { unsigned long *frontswap_map; /* frontswap in-use, one bit per page */ atomic_t frontswap_pages; /* frontswap pages in-use counter */ #endif + spinlock_t lock; /* + * protect map scan related fields like + * swap_map, lowest_bit, highest_bit, + * inuse_pages, cluster_next, + * cluster_nr, lowest_alloc and + * highest_alloc. other fields are only + * changed at swapon/swapoff, so are + * protected by swap_lock. changing + * flags need hold this lock and + * swap_lock. If both locks need hold, + * hold swap_lock first. + */ }; struct swap_list_t { @@ -209,9 +221,6 @@ struct swap_list_t { int next; /* swapfile to be used next */ }; -/* Swap 50% full? Release swapcache more aggressively.. */ -#define vm_swap_full() (nr_swap_pages*2 < total_swap_pages) - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; @@ -347,8 +356,20 @@ extern struct page *swapin_readahead(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr); /* linux/mm/swapfile.c */ -extern long nr_swap_pages; +extern atomic_long_t nr_swap_pages; extern long total_swap_pages; + +/* Swap 50% full? Release swapcache more aggressively.. */ +static inline bool vm_swap_full(void) +{ + return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages; +} + +static inline long get_nr_swap_pages(void) +{ + return atomic_long_read(&nr_swap_pages); +} + extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(void); extern swp_entry_t get_swap_page_of_type(int); @@ -381,9 +402,10 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) #else /* CONFIG_SWAP */ -#define nr_swap_pages 0L +#define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL +#define vm_swap_full() 0 #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) -- cgit v1.2.3 From 08b52706d505658eac0962d215ff697f898bbc13 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Fri, 22 Feb 2013 16:34:40 -0800 Subject: mm/rmap: rename anon_vma_unlock() => anon_vma_unlock_write() The comment in commit 4fc3f1d66b1e ("mm/rmap, migration: Make rmap_walk_anon() and try_to_unmap_anon() more scalable") says: | Rename anon_vma_[un]lock() => anon_vma_[un]lock_write(), | to make it clearer that it's an exclusive write-lock in | that case - suggested by Rik van Riel. But that commit renames only anon_vma_lock() Signed-off-by: Konstantin Khlebnikov Cc: Ingo Molnar Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 2 +- include/linux/rmap.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 1d76f8ca90f0..ee1c244a62a1 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -113,7 +113,7 @@ extern void __split_huge_page_pmd(struct vm_area_struct *vma, do { \ pmd_t *____pmd = (__pmd); \ anon_vma_lock_write(__anon_vma); \ - anon_vma_unlock(__anon_vma); \ + anon_vma_unlock_write(__anon_vma); \ BUG_ON(pmd_trans_splitting(*____pmd) || \ pmd_trans_huge(*____pmd)); \ } while (0) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index c20635c527a9..6dacb93a6d94 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -123,7 +123,7 @@ static inline void anon_vma_lock_write(struct anon_vma *anon_vma) down_write(&anon_vma->root->rwsem); } -static inline void anon_vma_unlock(struct anon_vma *anon_vma) +static inline void anon_vma_unlock_write(struct anon_vma *anon_vma) { up_write(&anon_vma->root->rwsem); } -- cgit v1.2.3 From 75f7ad8e043d9383337d917584297f7737154bbf Mon Sep 17 00:00:00 2001 From: Paul Szabo Date: Fri, 22 Feb 2013 16:34:42 -0800 Subject: page-writeback.c: subtract min_free_kbytes from dirtyable memory When calculating amount of dirtyable memory, min_free_kbytes should be subtracted because it is not intended for dirty pages. Addresses http://bugs.debian.org/695182 [akpm@linux-foundation.org: fix up min_free_kbytes extern declarations] [akpm@linux-foundation.org: fix min() warning] Signed-off-by: Paul Szabo Acked-by: Rik van Riel Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1d4122bf6f27..437da0ce78c7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1393,6 +1393,9 @@ extern void setup_per_cpu_pageset(void); extern void zone_pcp_update(struct zone *zone); extern void zone_pcp_reset(struct zone *zone); +/* page_alloc.c */ +extern int min_free_kbytes; + /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); -- cgit v1.2.3 From 4468b8f1e2d32ce79ef4bcb8e00d7e88627f1c3a Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 22 Feb 2013 16:34:46 -0800 Subject: mm: uninline page_xchg_last_nid() Andrew Morton pointed out that page_xchg_last_nid() and reset_page_last_nid() were "getting nuttily large" and asked that it be investigated. reset_page_last_nid() is on the page free path and it would be unfortunate to make that path more expensive than it needs to be. Due to the internal use of page_xchg_last_nid() it is already too expensive but fortunately, it should also be impossible for the page->flags to be updated in parallel when we call reset_page_last_nid(). Instead of unlining the function, it uses a simplier implementation that assumes no parallel updates and should now be sufficiently short for inlining. page_xchg_last_nid() is called in paths that are already quite expensive (splitting huge page, fault handling, migration) and it is reasonable to uninline. There was not really a good place to place the function but mm/mmzone.c was the closest fit IMO. This patch saved 128 bytes of text in the vmlinux file for the kernel configuration I used for testing automatic NUMA balancing. Signed-off-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 21 +++++---------------- 1 file changed, 5 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 437da0ce78c7..8a5bbe3b9e56 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -677,25 +677,14 @@ static inline int page_last_nid(struct page *page) return (page->flags >> LAST_NID_PGSHIFT) & LAST_NID_MASK; } -static inline int page_xchg_last_nid(struct page *page, int nid) -{ - unsigned long old_flags, flags; - int last_nid; - - do { - old_flags = flags = page->flags; - last_nid = page_last_nid(page); - - flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT); - flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT; - } while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags)); - - return last_nid; -} +extern int page_xchg_last_nid(struct page *page, int nid); static inline void reset_page_last_nid(struct page *page) { - page_xchg_last_nid(page, (1 << LAST_NID_SHIFT) - 1); + int nid = (1 << LAST_NID_SHIFT) - 1; + + page->flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT); + page->flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT; } #endif /* LAST_NID_NOT_IN_PAGE_FLAGS */ #else -- cgit v1.2.3 From 22b751c3d0376e86a377e3a0aa2ddbbe9d2eefc1 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 22 Feb 2013 16:34:59 -0800 Subject: mm: rename page struct field helpers The function names page_xchg_last_nid(), page_last_nid() and reset_page_last_nid() were judged to be inconsistent so rename them to a struct_field_op style pattern. As it looked jarring to have reset_page_mapcount() and page_nid_reset_last() beside each other in memmap_init_zone(), this patch also renames reset_page_mapcount() to page_mapcount_reset(). There are others like init_page_count() but as it is used throughout the arch code a rename would likely cause more conflicts than it is worth. [akpm@linux-foundation.org: fix zcache] Signed-off-by: Mel Gorman Suggested-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8a5bbe3b9e56..fe039bdba4ed 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -367,7 +367,7 @@ static inline struct page *compound_head(struct page *page) * both from it and to it can be tracked, using atomic_inc_and_test * and atomic_add_negative(-1). */ -static inline void reset_page_mapcount(struct page *page) +static inline void page_mapcount_reset(struct page *page) { atomic_set(&(page)->_mapcount, -1); } @@ -658,28 +658,28 @@ static inline int page_to_nid(const struct page *page) #ifdef CONFIG_NUMA_BALANCING #ifdef LAST_NID_NOT_IN_PAGE_FLAGS -static inline int page_xchg_last_nid(struct page *page, int nid) +static inline int page_nid_xchg_last(struct page *page, int nid) { return xchg(&page->_last_nid, nid); } -static inline int page_last_nid(struct page *page) +static inline int page_nid_last(struct page *page) { return page->_last_nid; } -static inline void reset_page_last_nid(struct page *page) +static inline void page_nid_reset_last(struct page *page) { page->_last_nid = -1; } #else -static inline int page_last_nid(struct page *page) +static inline int page_nid_last(struct page *page) { return (page->flags >> LAST_NID_PGSHIFT) & LAST_NID_MASK; } -extern int page_xchg_last_nid(struct page *page, int nid); +extern int page_nid_xchg_last(struct page *page, int nid); -static inline void reset_page_last_nid(struct page *page) +static inline void page_nid_reset_last(struct page *page) { int nid = (1 << LAST_NID_SHIFT) - 1; @@ -688,17 +688,17 @@ static inline void reset_page_last_nid(struct page *page) } #endif /* LAST_NID_NOT_IN_PAGE_FLAGS */ #else -static inline int page_xchg_last_nid(struct page *page, int nid) +static inline int page_nid_xchg_last(struct page *page, int nid) { return page_to_nid(page); } -static inline int page_last_nid(struct page *page) +static inline int page_nid_last(struct page *page) { return page_to_nid(page); } -static inline void reset_page_last_nid(struct page *page) +static inline void page_nid_reset_last(struct page *page) { } #endif -- cgit v1.2.3 From cbf86cfe04a66471f23b9e62e5eba4e525f38855 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 22 Feb 2013 16:35:08 -0800 Subject: ksm: remove old stable nodes more thoroughly Switching merge_across_nodes after running KSM is liable to oops on stale nodes still left over from the previous stable tree. It's not something that people will often want to do, but it would be lame to demand a reboot when they're trying to determine which merge_across_nodes setting is best. How can this happen? We only permit switching merge_across_nodes when pages_shared is 0, and usually set run 2 to force that beforehand, which ought to unmerge everything: yet oopses still occur when you then run 1. Three causes: 1. The old stable tree (built according to the inverse merge_across_nodes) has not been fully torn down. A stable node lingers until get_ksm_page() notices that the page it references no longer references it: but the page is not necessarily freed as soon as expected, particularly when swapcache. Fix this with a pass through the old stable tree, applying get_ksm_page() to each of the remaining nodes (most found stale and removed immediately), with forced removal of any left over. Unless the page is still mapped: I've not seen that case, it shouldn't occur, but better to WARN_ON_ONCE and EBUSY than BUG. 2. __ksm_enter() has a nice little optimization, to insert the new mm just behind ksmd's cursor, so there's a full pass for it to stabilize (or be removed) before ksmd addresses it. Nice when ksmd is running, but not so nice when we're trying to unmerge all mms: we were missing those mms forked and inserted behind the unmerge cursor. Easily fixed by inserting at the end when KSM_RUN_UNMERGE. 3. It is possible for a KSM page to be faulted back from swapcache into an mm, just after unmerge_and_remove_all_rmap_items() scanned past it. Fix this by copying on fault when KSM_RUN_UNMERGE: but that is private to ksm.c, so dissolve the distinction between ksm_might_need_to_copy() and ksm_does_need_to_copy(), doing it all in the one call into ksm.c. A long outstanding, unrelated bugfix sneaks in with that third fix: ksm_does_need_to_copy() would copy from a !PageUptodate page (implying I/O error when read in from swap) to a page which it then marks Uptodate. Fix this case by not copying, letting do_swap_page() discover the error. Signed-off-by: Hugh Dickins Cc: Rik van Riel Cc: Petr Holasek Cc: Andrea Arcangeli Cc: Izik Eidus Cc: Gerald Schaefer Cc: KOSAKI Motohiro Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ksm.h | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 3319a6967626..45c9b6a17bcb 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -16,9 +16,6 @@ struct stable_node; struct mem_cgroup; -struct page *ksm_does_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address); - #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); @@ -73,15 +70,8 @@ static inline void set_page_stable_node(struct page *page, * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE, * but what if the vma was unmerged while the page was swapped out? */ -static inline int ksm_might_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address) -{ - struct anon_vma *anon_vma = page_anon_vma(page); - - return anon_vma && - (anon_vma->root != vma->anon_vma->root || - page->index != linear_page_index(vma, address)); -} +struct page *ksm_might_need_to_copy(struct page *page, + struct vm_area_struct *vma, unsigned long address); int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg, unsigned long *vm_flags); @@ -113,10 +103,10 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, return 0; } -static inline int ksm_might_need_to_copy(struct page *page, +static inline struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { - return 0; + return page; } static inline int page_referenced_ksm(struct page *page, -- cgit v1.2.3 From 9c620e2bc5aa4256c102ada34e6c76204ed5898b Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 22 Feb 2013 16:35:14 -0800 Subject: mm: remove offlining arg to migrate_pages No functional change, but the only purpose of the offlining argument to migrate_pages() etc, was to ensure that __unmap_and_move() could migrate a KSM page for memory hotremove (which took ksm_thread_mutex) but not for other callers. Now all cases are safe, remove the arg. Signed-off-by: Hugh Dickins Cc: Rik van Riel Cc: Petr Holasek Cc: Andrea Arcangeli Cc: Izik Eidus Cc: Gerald Schaefer Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 1e9f627967a3..a405d3dc0f61 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -40,11 +40,9 @@ extern void putback_movable_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); extern int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, bool offlining, - enum migrate_mode mode, int reason); + unsigned long private, enum migrate_mode mode, int reason); extern int migrate_huge_page(struct page *, new_page_t x, - unsigned long private, bool offlining, - enum migrate_mode mode); + unsigned long private, enum migrate_mode mode); extern int fail_migrate_page(struct address_space *, struct page *, struct page *); @@ -62,11 +60,11 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, static inline void putback_lru_pages(struct list_head *l) {} static inline void putback_movable_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, int reason) { return -ENOSYS; } + unsigned long private, enum migrate_mode mode, int reason) + { return -ENOSYS; } static inline int migrate_huge_page(struct page *page, new_page_t x, - unsigned long private, bool offlining, - enum migrate_mode mode) { return -ENOSYS; } + unsigned long private, enum migrate_mode mode) + { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } static inline int migrate_prep_local(void) { return -ENOSYS; } -- cgit v1.2.3 From e3790144c9091631a18564aa64db8a971da02c41 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 22 Feb 2013 16:35:19 -0800 Subject: mm: refactor inactive_file_is_low() to use get_lru_size() An inactive file list is considered low when its active counterpart is bigger, regardless of whether it is a global zone LRU list or a memcg zone LRU list. The only difference is in how the LRU size is assessed. get_lru_size() does the right thing for both global and memcg reclaim situations. Get rid of inactive_file_is_low_global() and mem_cgroup_inactive_file_is_low() by using get_lru_size() and compare the numbers in common code. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 28bd5fa2ff2e..d6183f06d8c1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -116,7 +116,6 @@ void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); * For memory reclaim. */ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec); -int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec); int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list); void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int); @@ -321,12 +320,6 @@ mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) return 1; } -static inline int -mem_cgroup_inactive_file_is_low(struct lruvec *lruvec) -{ - return 1; -} - static inline unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { -- cgit v1.2.3 From 9127ab4ff92f0ecd7b4671efa9d0edb21c691e9f Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Fri, 22 Feb 2013 16:35:21 -0800 Subject: mm: add SECTION_IN_PAGE_FLAGS Instead of directly utilizing a combination of config options to determine this, add a macro to specifically address it. Signed-off-by: Cody P Schafer Cc: David Hansen Cc: Catalin Marinas Cc: Johannes Weiner Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index fe039bdba4ed..97da0302cf51 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -625,6 +625,10 @@ static inline enum zone_type page_zonenum(const struct page *page) return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +#define SECTION_IN_PAGE_FLAGS +#endif + /* * The identification function is only used by the buddy allocator for * determining if two pages could be buddies. We are not really @@ -708,7 +712,7 @@ static inline struct zone *page_zone(const struct page *page) return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } -#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +#ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); @@ -738,7 +742,7 @@ static inline void set_page_links(struct page *page, enum zone_type zone, { set_page_zone(page, zone); set_page_node(page, node); -#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +#ifdef SECTION_IN_PAGE_FLAGS set_page_section(page, pfn_to_section_nr(pfn)); #endif } -- cgit v1.2.3 From 108bcc96ef7047c02cad4d229f04da38186a3f3f Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Fri, 22 Feb 2013 16:35:23 -0800 Subject: mm: add & use zone_end_pfn() and zone_spans_pfn() Add 2 helpers (zone_end_pfn() and zone_spans_pfn()) to reduce code duplication. This also switches to using them in compaction (where an additional variable needed to be renamed), page_alloc, vmstat, memory_hotplug, and kmemleak. Note that in compaction.c I avoid calling zone_end_pfn() repeatedly because I expect at some point the sycronization issues with start_pfn & spanned_pages will need fixing, either by actually using the seqlock or clever memory barrier usage. Signed-off-by: Cody P Schafer Cc: David Hansen Cc: Catalin Marinas Cc: Johannes Weiner Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6c80d0ac14dd..34343f51e211 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -527,6 +527,16 @@ static inline int zone_is_oom_locked(const struct zone *zone) return test_bit(ZONE_OOM_LOCKED, &zone->flags); } +static inline unsigned zone_end_pfn(const struct zone *zone) +{ + return zone->zone_start_pfn + zone->spanned_pages; +} + +static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) +{ + return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); +} + /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the -- cgit v1.2.3 From 2a6e3ebee2edcade56f836390a5f0c7b76ff5f9e Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Fri, 22 Feb 2013 16:35:24 -0800 Subject: mm: add zone_is_empty() and zone_is_initialized() Factoring out these 2 checks makes it more clear what we are actually checking for. Signed-off-by: Cody P Schafer Cc: David Hansen Cc: Catalin Marinas Cc: Johannes Weiner Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 34343f51e211..cf8925962b68 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -537,6 +537,16 @@ static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } +static inline bool zone_is_initialized(struct zone *zone) +{ + return !!zone->wait_table; +} + +static inline bool zone_is_empty(struct zone *zone) +{ + return zone->spanned_pages == 0; +} + /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the -- cgit v1.2.3 From da3649e133948d8b7d8c57b05a33faf62ac2cc7e Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Fri, 22 Feb 2013 16:35:27 -0800 Subject: mmzone: add pgdat_{end_pfn,is_empty}() helpers & consolidate. Add pgdat_end_pfn() and pgdat_is_empty() helpers which match the similar zone_*() functions. Change node_end_pfn() to be a wrapper of pgdat_end_pfn(). Signed-off-by: Cody P Schafer Cc: David Hansen Cc: Catalin Marinas Cc: Johannes Weiner Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index cf8925962b68..ede274957e05 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -756,11 +756,17 @@ typedef struct pglist_data { #define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) +#define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) -#define node_end_pfn(nid) ({\ - pg_data_t *__pgdat = NODE_DATA(nid);\ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages;\ -}) +static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) +{ + return pgdat->node_start_pfn + pgdat->node_spanned_pages; +} + +static inline bool pgdat_is_empty(pg_data_t *pgdat) +{ + return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; +} #include -- cgit v1.2.3 From ebec3862fd6eefe8301aa55ed2e30c685d831842 Mon Sep 17 00:00:00 2001 From: Zhang Yanfei Date: Fri, 22 Feb 2013 16:35:43 -0800 Subject: mm: fix return type for functions nr_free_*_pages Currently, the amount of RAM that functions nr_free_*_pages return is held in unsigned int. But in machines with big memory (exceeding 16TB), the amount may be incorrect because of overflow, so fix it. Signed-off-by: Zhang Yanfei Cc: Simon Horman Cc: Julian Anastasov Cc: David Miller Cc: Eric Van Hensbergen Cc: Ron Minnich Cc: Latchesar Ionkov Cc: Mel Gorman Cc: Minchan Kim Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index a3e22d357e91..8a15f38ebc5c 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -225,8 +225,8 @@ struct swap_list_t { extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; extern unsigned long dirty_balance_reserve; -extern unsigned int nr_free_buffer_pages(void); -extern unsigned int nr_free_pagecache_pages(void); +extern unsigned long nr_free_buffer_pages(void); +extern unsigned long nr_free_pagecache_pages(void); /* Definition of global_page_state not available yet */ #define nr_free_pages() global_page_state(NR_FREE_PAGES) -- cgit v1.2.3 From b21e0b90ccb99a377bce0167fed1e881bb5065d7 Mon Sep 17 00:00:00 2001 From: Zhang Yanfei Date: Fri, 22 Feb 2013 16:35:48 -0800 Subject: vmscan: change type of vm_total_pages to unsigned long This variable is calculated from nr_free_pagecache_pages so change its type to unsigned long. Signed-off-by: Zhang Yanfei Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 8a15f38ebc5c..2818a123f3ea 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -275,7 +275,7 @@ extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; extern int remove_mapping(struct address_space *mapping, struct page *page); -extern long vm_total_pages; +extern unsigned long vm_total_pages; #ifdef CONFIG_NUMA extern int zone_reclaim_mode; -- cgit v1.2.3 From 28a35716d317980ae9bc2ff2f84c33a3cda9e884 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Fri, 22 Feb 2013 16:35:55 -0800 Subject: mm: use long type for page counts in mm_populate() and get_user_pages() Use long type for page counts in mm_populate() so as to avoid integer overflow when running the following test code: int main(void) { void *p = mmap(NULL, 0x100000000000, PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0); printf("p: %p\n", p); mlockall(MCL_CURRENT); printf("done\n"); return 0; } Signed-off-by: Michel Lespinasse Cc: Andrea Arcangeli Cc: Rik van Riel Cc: Mel Gorman Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 +++--- include/linux/mm.h | 15 ++++++++------- 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0c80d3f57a5b..eedc334fb6f5 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -43,9 +43,9 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, #endif int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); -int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, - struct page **, struct vm_area_struct **, - unsigned long *, int *, int, unsigned int flags); +long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, + struct page **, struct vm_area_struct **, + unsigned long *, unsigned long *, long, unsigned int); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *); void __unmap_hugepage_range_final(struct mmu_gather *tlb, diff --git a/include/linux/mm.h b/include/linux/mm.h index 97da0302cf51..87b0ef253607 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1013,13 +1013,14 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void * extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, int write); -int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int len, unsigned int foll_flags, - struct page **pages, struct vm_area_struct **vmas, - int *nonblocking); -int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int nr_pages, int write, int force, - struct page **pages, struct vm_area_struct **vmas); +long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int foll_flags, struct page **pages, + struct vm_area_struct **vmas, int *nonblocking); +long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, 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; -- cgit v1.2.3 From 240aadeedc4a89fc44623f8ce4ca46bda73db07e Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Fri, 22 Feb 2013 16:35:56 -0800 Subject: mm: accelerate mm_populate() treatment of THP pages This change adds a follow_page_mask function which is equivalent to follow_page, but with an extra page_mask argument. follow_page_mask sets *page_mask to HPAGE_PMD_NR - 1 when it encounters a THP page, and to 0 in other cases. __get_user_pages() makes use of this in order to accelerate populating THP ranges - that is, when both the pages and vmas arrays are NULL, we don't need to iterate HPAGE_PMD_NR times to cover a single THP page (and we also avoid taking mm->page_table_lock that many times). Signed-off-by: Michel Lespinasse Cc: Andrea Arcangeli Cc: Rik van Riel Cc: Mel Gorman Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 87b0ef253607..6124f1db50fe 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1629,8 +1629,17 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); -struct page *follow_page(struct vm_area_struct *, unsigned long address, - unsigned int foll_flags); +struct page *follow_page_mask(struct vm_area_struct *vma, + unsigned long address, unsigned int foll_flags, + unsigned int *page_mask); + +static inline struct page *follow_page(struct vm_area_struct *vma, + unsigned long address, unsigned int foll_flags) +{ + unsigned int unused_page_mask; + return follow_page_mask(vma, address, foll_flags, &unused_page_mask); +} + #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ #define FOLL_GET 0x04 /* do get_page on page */ -- cgit v1.2.3 From 5117b3b835f288314a2d4e5512bc1747e3a7c8ed Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 22 Feb 2013 16:36:07 -0800 Subject: mm,ksm: FOLL_MIGRATION do migration_entry_wait In "ksm: remove old stable nodes more thoroughly" I said that I'd never seen its WARN_ON_ONCE(page_mapped(page)). True at the time of writing, but it soon appeared once I tried fuller tests on the whole series. It turned out to be due to the KSM page migration itself: unmerge_and_ remove_all_rmap_items() failed to locate and replace all the KSM pages, because of that hiatus in page migration when old pte has been replaced by migration entry, but not yet by new pte. follow_page() finds no page at that instant, but a KSM page reappears shortly after, without a fault. Add FOLL_MIGRATION flag, so follow_page() can do migration_entry_wait() for KSM's break_cow(). I'd have preferred to avoid another flag, and do it every time, in case someone else makes the same easy mistake; but did not find another transgressor (the common get_user_pages() is of course safe), and cannot be sure that every follow_page() caller is prepared to sleep - ia64's xencomm_vtop()? Now, THP's wait_split_huge_page() can already sleep there, since anon_vma locking was changed to mutex, but maybe that's somehow excluded. Signed-off-by: Hugh Dickins Cc: Mel Gorman Cc: Petr Holasek Cc: Andrea Arcangeli Cc: Izik Eidus Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6124f1db50fe..e7c3f9a0111a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1651,6 +1651,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma, #define FOLL_SPLIT 0x80 /* don't return transhuge pages, split them */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ +#define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); -- cgit v1.2.3 From da8c87241c26aac81a64c7e4d21d438a33018f4e Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 21 Feb 2013 23:32:27 +0000 Subject: vlan: adjust vlan_set_encap_proto() for its callers There are two places to call vlan_set_encap_proto(): vlan_untag() and __pop_vlan_tci(). vlan_untag() assumes skb->data points after mac addr, otherwise the following code vhdr = (struct vlan_hdr *) skb->data; vlan_tci = ntohs(vhdr->h_vlan_TCI); __vlan_hwaccel_put_tag(skb, vlan_tci); skb_pull_rcsum(skb, VLAN_HLEN); won't be correct. But __pop_vlan_tci() assumes points _before_ mac addr. In vlan_set_encap_proto(), it looks for some magic L2 value after mac addr: rawp = skb->data; if (*(unsigned short *) rawp == 0xFFFF) ... Therefore __pop_vlan_tci() is obviously wrong. A quick fix is avoiding using skb->data in vlan_set_encap_proto(), use 'vhdr+1' is always correct in both cases. Cc: David S. Miller Cc: Jesse Gross Signed-off-by: Cong Wang Acked-by: Jesse Gross Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index d06cc5c8f58c..218a3b686d90 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -331,7 +331,7 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr) { __be16 proto; - unsigned char *rawp; + unsigned short *rawp; /* * Was a VLAN packet, grab the encapsulated protocol, which the layer @@ -344,8 +344,8 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, return; } - rawp = skb->data; - if (*(unsigned short *) rawp == 0xFFFF) + rawp = (unsigned short *)(vhdr + 1); + if (*rawp == 0xFFFF) /* * This is a magic hack to spot IPX packets. Older Novell * breaks the protocol design and runs IPX over 802.3 without -- cgit v1.2.3 From 561c6731978fa128f29342495f47fc3365898b3d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 24 Feb 2013 10:52:26 -0500 Subject: switch lseek to COMPAT_SYSCALL_DEFINE Signed-off-by: Al Viro --- include/linux/compat.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index de095b0462a7..59c72048bf20 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -359,6 +359,7 @@ asmlinkage ssize_t compat_sys_preadv(unsigned long fd, asmlinkage ssize_t compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen, u32 pos_low, u32 pos_high); +asmlinkage long comat_sys_lseek(unsigned int, compat_off_t, unsigned int); asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv, const compat_uptr_t __user *envp); -- cgit v1.2.3 From c148e9ff4bd45f26d3f0253c20efc497672c3c84 Mon Sep 17 00:00:00 2001 From: "Zhang, YiX X" Date: Tue, 8 Jan 2013 06:07:39 +0000 Subject: mmc: correct the EXCEPTION_EVENTS_STATUS value in comment The right value is 54 according to eMMC 4.5 specification. Signed-off-by: ZhangYi Signed-off-by: Chris Ball --- include/linux/mmc/card.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index be2500a49925..7069dcea27c5 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -83,7 +83,7 @@ struct mmc_ext_csd { unsigned int data_tag_unit_size; /* DATA TAG UNIT size */ unsigned int boot_ro_lock; /* ro lock support */ bool boot_ro_lockable; - u8 raw_exception_status; /* 53 */ + u8 raw_exception_status; /* 54 */ u8 raw_partition_support; /* 160 */ u8 raw_rpmb_size_mult; /* 168 */ u8 raw_erased_mem_count; /* 181 */ -- cgit v1.2.3 From a70aaa64da2205d32d1c9362d8f5d4be619cd58f Mon Sep 17 00:00:00 2001 From: Doug Anderson Date: Fri, 11 Jan 2013 17:03:50 +0000 Subject: mmc: dw_mmc: Add "disable-wp" device tree property The "disable-wp" property is used to specify that a given SD card slot doesn't have a concept of write protect. This eliminates the need for special case code for SD slots that should never be write protected (like a micro SD slot or a dev board). The dw_mmc driver is special in needing to specify "disable-wp" because the lack of a "wp-gpios" property means to use the special purpose write protect line. On some other mmc devices the lack of "wp-gpios" means that write protect should be disabled. Signed-off-by: Doug Anderson Acked-by: Seungwon Jeon Acked-by: Will Newton Acked-by: Olof Johansson Signed-off-by: Chris Ball --- include/linux/mmc/dw_mmc.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index 34be4f47293c..de61de5608c9 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -209,9 +209,18 @@ struct dw_mci_dma_ops { #define DW_MCI_QUIRK_HIGHSPEED BIT(2) /* Unreliable card detection */ #define DW_MCI_QUIRK_BROKEN_CARD_DETECTION BIT(3) + /* Write Protect detection not available */ +/* + * NOTE: DW_MCI_QUIRK_NO_WRITE_PROTECT will be removed in a future + * patch in the series once reference to it is removed. + */ #define DW_MCI_QUIRK_NO_WRITE_PROTECT BIT(4) +/* Slot level quirks */ +/* This slot has no write protect */ +#define DW_MCI_SLOT_QUIRK_NO_WRITE_PROTECT BIT(0) + struct dma_pdata; struct block_settings { -- cgit v1.2.3 From 9640639b09313af4cd37a465408643aba927808e Mon Sep 17 00:00:00 2001 From: Doug Anderson Date: Fri, 11 Jan 2013 17:03:54 +0000 Subject: mmc: dw_mmc: Remove DW_MCI_QUIRK_NO_WRITE_PROTECT The original quirk was added in the change 'mmc: dw_mmc: add quirk to indicate missing write protect line'. The original quirk was added at a controller level even though each slot has its own write protect (so the quirk should be at the slot level). A recent change (mmc: dw_mmc: Add "disable-wp" device tree property) added a slot-level quirk and support for the quirk directly to dw_mmc. Signed-off-by: Doug Anderson Acked-by: Will Newton Acked-by: Olof Johansson Signed-off-by: Chris Ball --- include/linux/mmc/dw_mmc.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index de61de5608c9..198f0fa44e9f 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -210,13 +210,6 @@ struct dw_mci_dma_ops { /* Unreliable card detection */ #define DW_MCI_QUIRK_BROKEN_CARD_DETECTION BIT(3) -/* Write Protect detection not available */ -/* - * NOTE: DW_MCI_QUIRK_NO_WRITE_PROTECT will be removed in a future - * patch in the series once reference to it is removed. - */ -#define DW_MCI_QUIRK_NO_WRITE_PROTECT BIT(4) - /* Slot level quirks */ /* This slot has no write protect */ #define DW_MCI_SLOT_QUIRK_NO_WRITE_PROTECT BIT(0) -- cgit v1.2.3 From af51079e68d4759e458b0592df5d1fab373c43ae Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Mon, 21 Jan 2013 19:02:28 +0800 Subject: mmc: sdhci-esdhc-imx: support 8bit mode The i.MX esdhc has a nonstandard bit layout for the SDHCI_HOST_CONTROL register. To support 8bit bus width on i.MX populate the platform_bus_width callback. This is tested on an i.MX25, but should according to the datasheets work on the other i.MX using this hardware aswell. The i.MX6, while having a SDHCI_SPEC_300 controller, still uses the same nonstandard register layout. Signed-off-by: Sascha Hauer Signed-off-by: Shawn Guo Tested-by: Dirk Behme Signed-off-by: Chris Ball --- include/linux/platform_data/mmc-esdhc-imx.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h index aaf97481f413..b4a0521ce411 100644 --- a/include/linux/platform_data/mmc-esdhc-imx.h +++ b/include/linux/platform_data/mmc-esdhc-imx.h @@ -39,5 +39,6 @@ struct esdhc_platform_data { unsigned int cd_gpio; enum wp_types wp_type; enum cd_types cd_type; + int max_bus_width; }; #endif /* __ASM_ARCH_IMX_ESDHC_H */ -- cgit v1.2.3 From d887874e0ead6a0b86b6046b872730c81c121352 Mon Sep 17 00:00:00 2001 From: Johan Rudholm Date: Mon, 28 Jan 2013 15:08:26 +0100 Subject: mmc: core: Add card_busy to host_ops This host_ops member is used to test if the card is signaling busy by pulling dat[0:3] low. Signed-off-by: Johan Rudholm Acked-by: Ulf Hansson Tested-by: Wei WANG Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 523d570f58ad..0373b0a6daac 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -131,6 +131,9 @@ struct mmc_host_ops { int (*start_signal_voltage_switch)(struct mmc_host *host, struct mmc_ios *ios); + /* Check if the card is pulling dat[0:3] low */ + int (*card_busy)(struct mmc_host *host); + /* The tuning command opcode value is different for SD and eMMC cards */ int (*execute_tuning)(struct mmc_host *host, u32 opcode); void (*enable_preset_value)(struct mmc_host *host, bool enable); -- cgit v1.2.3 From 52983382c74f59a3953e622d7661a24e1bc4388a Mon Sep 17 00:00:00 2001 From: Kevin Liu Date: Thu, 31 Jan 2013 11:31:37 +0800 Subject: mmc: sdhci: enhance preset value function 4d55c5a1 ("mmc: sdhci: enable preset value after uhs initialization") added preset value support and enabled it by default during sd card init. Below are the enhancements introduced by this patch: 1. In current code, preset value is enabled after setting clock finished, which means the clock is manually set by driver firstly and then suddenly switched to preset value at this point. So the first setting is useless and unnecessary. What's more, the first clock setting may differ from the preset one. The better way is enable preset value just after switch to UHS mode so the preset value can take effect immediately. So move preset value enable from mmc_sd_init_card to sdhci_set_ios which will be called during set timing. 2. In current code, preset value is disabled at the beginning of mmc_attach_sd. It's too late since low freq (400khz) should be set in mmc_power_up. So move preset value disable to sdhci_set_ios which will be called during power up. 3. host->clock and ios->drv_type should also be updated according to the preset value if it's enabled. Current code missed this. 4. This patch also introduce a quirk to disable preset value in case preset value doesn't work. This patch has been verified on sdhci-pxav3 platform with both preset enabled and disabled. Signed-off-by: Kevin Liu Reviewed-by: Ulf Hansson Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 1 - include/linux/mmc/sdhci.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 0373b0a6daac..6c235e03de29 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -136,7 +136,6 @@ struct mmc_host_ops { /* The tuning command opcode value is different for SD and eMMC cards */ int (*execute_tuning)(struct mmc_host *host, u32 opcode); - void (*enable_preset_value)(struct mmc_host *host, bool enable); int (*select_drive_strength)(unsigned int max_dtr, int host_drv, int card_drv); void (*hw_reset)(struct mmc_host *host); void (*card_event)(struct mmc_host *host); diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index 4bbc3301fbbf..b838ffc49e4a 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -94,6 +94,7 @@ struct sdhci_host { #define SDHCI_QUIRK2_HOST_NO_CMD23 (1<<1) /* The system physically doesn't support 1.8v, even if the host does */ #define SDHCI_QUIRK2_NO_1_8_V (1<<2) +#define SDHCI_QUIRK2_PRESET_VALUE_BROKEN (1<<3) int irq; /* Device IRQ */ void __iomem *ioaddr; /* Mapped address */ -- cgit v1.2.3 From abd9ac144947d9a604beb763339e2f77ce8bec79 Mon Sep 17 00:00:00 2001 From: Seungwon Jeon Date: Wed, 6 Feb 2013 17:01:43 +0900 Subject: mmc: add packed command feature of eMMC4.5 This patch adds packed command feature of eMMC4.5. The maximum number for packing read (or write) is offered and exception event relevant to packed command which is used for error handling is enabled. If host wants to use this feature, MMC_CAP2_PACKED_CMD should be set. Signed-off-by: Seungwon Jeon Reviewed-by: Maya Erez Reviewed-by: Subhash Jadavani Reviewed-by: Namjae Jeon Signed-off-by: Chris Ball --- include/linux/mmc/card.h | 3 +++ include/linux/mmc/host.h | 4 ++++ include/linux/mmc/mmc.h | 15 +++++++++++++-- 3 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 7069dcea27c5..237f253f2fe0 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -53,6 +53,9 @@ struct mmc_ext_csd { u8 part_config; u8 cache_ctrl; u8 rst_n_function; + u8 max_packed_writes; + u8 max_packed_reads; + u8 packed_event_en; unsigned int part_time; /* Units: ms */ unsigned int sa_timeout; /* Units: 100ns */ unsigned int generic_cmd6_time; /* Units: 10ms */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 6c235e03de29..a0466c03f5e1 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -276,6 +276,10 @@ struct mmc_host { #define MMC_CAP2_HC_ERASE_SZ (1 << 9) /* High-capacity erase size */ #define MMC_CAP2_CD_ACTIVE_HIGH (1 << 10) /* Card-detect signal active high */ #define MMC_CAP2_RO_ACTIVE_HIGH (1 << 11) /* Write-protect signal active high */ +#define MMC_CAP2_PACKED_RD (1 << 12) /* Allow packed read */ +#define MMC_CAP2_PACKED_WR (1 << 13) /* Allow packed write */ +#define MMC_CAP2_PACKED_CMD (MMC_CAP2_PACKED_RD | \ + MMC_CAP2_PACKED_WR) mmc_pm_flag_t pm_caps; /* supported pm features */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 94d532e41c61..50bcde3677ca 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -139,7 +139,7 @@ static inline bool mmc_op_multi(u32 opcode) #define R1_CURRENT_STATE(x) ((x & 0x00001E00) >> 9) /* sx, b (4 bits) */ #define R1_READY_FOR_DATA (1 << 8) /* sx, a */ #define R1_SWITCH_ERROR (1 << 7) /* sx, c */ -#define R1_EXCEPTION_EVENT (1 << 6) /* sx, a */ +#define R1_EXCEPTION_EVENT (1 << 6) /* sr, a */ #define R1_APP_CMD (1 << 5) /* sr, c */ #define R1_STATE_IDLE 0 @@ -275,7 +275,10 @@ struct _mmc_csd { #define EXT_CSD_FLUSH_CACHE 32 /* W */ #define EXT_CSD_CACHE_CTRL 33 /* R/W */ #define EXT_CSD_POWER_OFF_NOTIFICATION 34 /* R/W */ -#define EXT_CSD_EXP_EVENTS_STATUS 54 /* RO */ +#define EXT_CSD_PACKED_FAILURE_INDEX 35 /* RO */ +#define EXT_CSD_PACKED_CMD_STATUS 36 /* RO */ +#define EXT_CSD_EXP_EVENTS_STATUS 54 /* RO, 2 bytes */ +#define EXT_CSD_EXP_EVENTS_CTRL 56 /* R/W, 2 bytes */ #define EXT_CSD_DATA_SECTOR_SIZE 61 /* R */ #define EXT_CSD_GP_SIZE_MULT 143 /* R/W */ #define EXT_CSD_PARTITION_ATTRIBUTE 156 /* R/W */ @@ -324,6 +327,8 @@ struct _mmc_csd { #define EXT_CSD_CACHE_SIZE 249 /* RO, 4 bytes */ #define EXT_CSD_TAG_UNIT_SIZE 498 /* RO */ #define EXT_CSD_DATA_TAG_SUPPORT 499 /* RO */ +#define EXT_CSD_MAX_PACKED_WRITES 500 /* RO */ +#define EXT_CSD_MAX_PACKED_READS 501 /* RO */ #define EXT_CSD_BKOPS_SUPPORT 502 /* RO */ #define EXT_CSD_HPI_FEATURES 503 /* RO */ @@ -385,6 +390,9 @@ struct _mmc_csd { #define EXT_CSD_PWR_CL_4BIT_MASK 0x0F /* 8 bit PWR CLS */ #define EXT_CSD_PWR_CL_8BIT_SHIFT 4 #define EXT_CSD_PWR_CL_4BIT_SHIFT 0 + +#define EXT_CSD_PACKED_EVENT_EN BIT(3) + /* * EXCEPTION_EVENT_STATUS field */ @@ -393,6 +401,9 @@ struct _mmc_csd { #define EXT_CSD_SYSPOOL_EXHAUSTED BIT(2) #define EXT_CSD_PACKED_FAILURE BIT(3) +#define EXT_CSD_PACKED_GENERIC_ERROR BIT(0) +#define EXT_CSD_PACKED_INDEXED_ERROR BIT(1) + /* * BKOPS status level */ -- cgit v1.2.3 From ce39f9d17c14e56ea6772aa84393e6e0cc8499c4 Mon Sep 17 00:00:00 2001 From: Seungwon Jeon Date: Wed, 6 Feb 2013 17:02:46 +0900 Subject: mmc: support packed write command for eMMC4.5 devices This patch supports packed write command of eMMC4.5 devices. Several writes can be grouped in packed command and all data of the individual commands can be sent in a single transfer on the bus. Large amounts of data in one transfer rather than several data of small size are effective for eMMC write internally. As a result, packed command help write throughput be improved. The following tables show the results of packed write. Type A: test none | packed iozone 25.8 | 31 tiotest 27.6 | 31.2 lmdd 31.2 | 35.4 Type B: test none | packed iozone 44.1 | 51.1 tiotest 47.9 | 52.5 lmdd 51.6 | 59.2 Type C: test none | packed iozone 19.5 | 32 tiotest 19.9 | 34.5 lmdd 22.8 | 40.7 Signed-off-by: Seungwon Jeon Reviewed-by: Maya Erez Reviewed-by: Namjae Jeon Signed-off-by: Chris Ball --- include/linux/mmc/card.h | 5 +++++ include/linux/mmc/core.h | 4 ++++ include/linux/mmc/host.h | 5 +++++ 3 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 237f253f2fe0..61b2c30c903b 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -310,6 +310,11 @@ static inline void mmc_part_add(struct mmc_card *card, unsigned int size, card->nr_parts++; } +static inline bool mmc_large_sector(struct mmc_card *card) +{ + return card->ext_csd.data_sector_size == 4096; +} + /* * The world is not perfect and supplies us with broken mmc/sdio devices. * For at least some of these bugs we need a work-around. diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 495d1336149c..39613b9a6fc5 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -18,6 +18,9 @@ struct mmc_request; struct mmc_command { u32 opcode; u32 arg; +#define MMC_CMD23_ARG_REL_WR (1 << 31) +#define MMC_CMD23_ARG_PACKED ((0 << 31) | (1 << 30)) +#define MMC_CMD23_ARG_TAG_REQ (1 << 29) u32 resp[4]; unsigned int flags; /* expected response type */ #define MMC_RSP_PRESENT (1 << 0) @@ -148,6 +151,7 @@ extern int mmc_wait_for_app_cmd(struct mmc_host *, struct mmc_card *, extern void mmc_start_bkops(struct mmc_card *card, bool from_exception); extern int __mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int, bool); extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int); +extern int mmc_send_ext_csd(struct mmc_card *card, u8 *ext_csd); #define MMC_ERASE_ARG 0x00000000 #define MMC_SECURE_ERASE_ARG 0x80000000 diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index a0466c03f5e1..fd5fd5a6026f 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -465,6 +465,11 @@ static inline int mmc_host_uhs(struct mmc_host *host) MMC_CAP_UHS_DDR50); } +static inline int mmc_host_packed_wr(struct mmc_host *host) +{ + return host->caps2 & MMC_CAP2_PACKED_WR; +} + #ifdef CONFIG_MMC_CLKGATE void mmc_host_clk_hold(struct mmc_host *host); void mmc_host_clk_release(struct mmc_host *host); -- cgit v1.2.3 From 6c56e7a0fff166904ce2715f7ab1746460c1f11b Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Sat, 16 Feb 2013 16:21:16 +0100 Subject: mmc: provide a standard MMC device-tree binding parser centrally MMC defines a number of standard DT bindings. Having each driver parse them individually adds code redundancy and is error prone. Provide a standard function to unify the parsing. After all drivers are converted to using it instead of their own parsers, this function can be integrated into mmc_alloc_host(). Signed-off-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index fd5fd5a6026f..bf93c9a6d729 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -368,6 +368,7 @@ extern struct mmc_host *mmc_alloc_host(int extra, struct device *); extern int mmc_add_host(struct mmc_host *); extern void mmc_remove_host(struct mmc_host *); extern void mmc_free_host(struct mmc_host *); +void mmc_of_parse(struct mmc_host *host); static inline void *mmc_priv(struct mmc_host *host) { -- cgit v1.2.3 From 8c9beb117bf31cdb757bc80992281004be8a177b Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Fri, 15 Feb 2013 16:13:53 +0100 Subject: mmc: (cosmetic) remove "extern" from function declarations The "extern" keyword isn't required in function declarations, remove it. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index bf93c9a6d729..d6f20cc6415e 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -364,10 +364,10 @@ struct mmc_host { unsigned long private[0] ____cacheline_aligned; }; -extern struct mmc_host *mmc_alloc_host(int extra, struct device *); -extern int mmc_add_host(struct mmc_host *); -extern void mmc_remove_host(struct mmc_host *); -extern void mmc_free_host(struct mmc_host *); +struct mmc_host *mmc_alloc_host(int extra, struct device *); +int mmc_add_host(struct mmc_host *); +void mmc_remove_host(struct mmc_host *); +void mmc_free_host(struct mmc_host *); void mmc_of_parse(struct mmc_host *host); static inline void *mmc_priv(struct mmc_host *host) @@ -381,16 +381,16 @@ static inline void *mmc_priv(struct mmc_host *host) #define mmc_classdev(x) (&(x)->class_dev) #define mmc_hostname(x) (dev_name(&(x)->class_dev)) -extern int mmc_suspend_host(struct mmc_host *); -extern int mmc_resume_host(struct mmc_host *); +int mmc_suspend_host(struct mmc_host *); +int mmc_resume_host(struct mmc_host *); -extern int mmc_power_save_host(struct mmc_host *host); -extern int mmc_power_restore_host(struct mmc_host *host); +int mmc_power_save_host(struct mmc_host *host); +int mmc_power_restore_host(struct mmc_host *host); -extern void mmc_detect_change(struct mmc_host *, unsigned long delay); -extern void mmc_request_done(struct mmc_host *, struct mmc_request *); +void mmc_detect_change(struct mmc_host *, unsigned long delay); +void mmc_request_done(struct mmc_host *, struct mmc_request *); -extern int mmc_cache_ctrl(struct mmc_host *, u8); +int mmc_cache_ctrl(struct mmc_host *, u8); static inline void mmc_signal_sdio_irq(struct mmc_host *host) { -- cgit v1.2.3 From 76a411f9f9423cbc9f62e70173459c5af54323f4 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Fri, 15 Feb 2013 16:13:57 +0100 Subject: mmc: sh_mobile_sdhi: remove unused .pdata field The struct sh_mobile_sdhi_info::pdata field was only used for platform- based card detection and isn't used anymore since the migration to GPIO- based MMC slot functions. Remove it. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mmc/sh_mobile_sdhi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sh_mobile_sdhi.h b/include/linux/mmc/sh_mobile_sdhi.h index b65679ffa880..b76bcf0621f6 100644 --- a/include/linux/mmc/sh_mobile_sdhi.h +++ b/include/linux/mmc/sh_mobile_sdhi.h @@ -4,7 +4,6 @@ #include struct platform_device; -struct tmio_mmc_data; #define SH_MOBILE_SDHI_IRQ_CARD_DETECT "card_detect" #define SH_MOBILE_SDHI_IRQ_SDCARD "sdcard" @@ -26,7 +25,6 @@ struct sh_mobile_sdhi_info { unsigned long tmio_caps2; u32 tmio_ocr_mask; /* available MMC voltages */ unsigned int cd_gpio; - struct tmio_mmc_data *pdata; void (*set_pwr)(struct platform_device *pdev, int state); int (*get_cd)(struct platform_device *pdev); -- cgit v1.2.3 From 27902c14aa2376d53755b6c02e3be671fd890e30 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Fri, 15 Feb 2013 16:13:59 +0100 Subject: mmc: tmio: remove unused and deprecated symbols The tmio_mmc_cd_wakeup() inline function has been deprecated since 3.4 and is unused since 3.4 too. Remove them. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Chris Ball --- include/linux/mfd/tmio.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index d83af39815ab..99bf3e665997 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -64,12 +64,6 @@ * Some controllers can support SDIO IRQ signalling. */ #define TMIO_MMC_SDIO_IRQ (1 << 2) -/* - * Some platforms can detect card insertion events with controller powered - * down, using a GPIO IRQ, in which case they have to fill in cd_irq, cd_gpio, - * and cd_flags fields of struct tmio_mmc_data. - */ -#define TMIO_MMC_HAS_COLD_CD (1 << 3) /* * Some controllers require waiting for the SD bus to become * idle before writing to some registers. @@ -116,18 +110,6 @@ struct tmio_mmc_data { void (*clk_disable)(struct platform_device *pdev); }; -/* - * This function is deprecated and will be removed soon. Please, convert your - * platform to use drivers/mmc/core/cd-gpio.c - */ -#include -static inline void tmio_mmc_cd_wakeup(struct tmio_mmc_data *pdata) -{ - if (pdata) - mmc_detect_change(dev_get_drvdata(pdata->dev), - msecs_to_jiffies(100)); -} - /* * data for the NAND controller */ -- cgit v1.2.3 From 0e786102949d7461859c6ce9f39c2c8d28e42db3 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Fri, 15 Feb 2013 15:07:19 -0700 Subject: mmc: tegra: assume CONFIG_OF, remove platform data Tegra only supports, and always enables, device tree. Remove all ifdefs and runtime checks for DT support from the driver. Platform data is therefore no longer required. Rework the driver to parse the device tree directly into struct sdhci_tegra. Signed-off-by: Stephen Warren Signed-off-by: Chris Ball --- include/linux/platform_data/mmc-sdhci-tegra.h | 28 --------------------------- 1 file changed, 28 deletions(-) delete mode 100644 include/linux/platform_data/mmc-sdhci-tegra.h (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-sdhci-tegra.h b/include/linux/platform_data/mmc-sdhci-tegra.h deleted file mode 100644 index 8f8430697686..000000000000 --- a/include/linux/platform_data/mmc-sdhci-tegra.h +++ /dev/null @@ -1,28 +0,0 @@ -/* - * Copyright (C) 2009 Palm, Inc. - * Author: Yvonne Yip - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ -#ifndef __PLATFORM_DATA_TEGRA_SDHCI_H -#define __PLATFORM_DATA_TEGRA_SDHCI_H - -#include - -struct tegra_sdhci_platform_data { - int cd_gpio; - int wp_gpio; - int power_gpio; - int is_8bit; - int pm_flags; -}; - -#endif -- cgit v1.2.3 From 3f6d078d4accfff8b114f968259a060bfdc7c682 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 24 Feb 2013 13:49:08 -0500 Subject: fix compat truncate/ftruncate Signed-off-by: Al Viro --- include/linux/compat.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 59c72048bf20..76a87fb57ac2 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -536,6 +536,8 @@ asmlinkage long compat_sys_openat(int dfd, const char __user *filename, asmlinkage long compat_sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, int flags); +asmlinkage long compat_sys_truncate(const char __user *, compat_off_t); +asmlinkage long compat_sys_ftruncate(unsigned int, compat_ulong_t); asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, -- cgit v1.2.3 From 446d64e3e1154806092ac27de198dff1225797d9 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Sun, 24 Feb 2013 23:42:37 -0500 Subject: block: fix part_pack_uuid() build error Commit "85865c1 ima: add policy support for file system uuid" introduced a CONFIG_BLOCK dependency. This patch defines a wrapper called blk_part_pack_uuid(), which returns -EINVAL, when CONFIG_BLOCK is not defined. security/integrity/ima/ima_policy.c:538:4: error: implicit declaration of function 'part_pack_uuid' [-Werror=implicit-function-declaration] Changelog v2: - Reference commit number in patch description Changelog v1: - rename ima_part_pack_uuid() to blk_part_pack_uuid() - resolve scripts/checkpatch.pl warnings Changelog v0: - fix UUID scripts/Lindent msgs Reported-by: Randy Dunlap Reported-by: David Rientjes Signed-off-by: Mimi Zohar Acked-by: David Rientjes Acked-by: Randy Dunlap Cc: Jens Axboe Signed-off-by: James Morris --- include/linux/genhd.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 79b8bba19363..9f3c275e053e 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -231,6 +231,12 @@ static inline void part_pack_uuid(const u8 *uuid_str, u8 *to) } } +static inline int blk_part_pack_uuid(const u8 *uuid_str, u8 *to) +{ + part_pack_uuid(uuid_str, to); + return 0; +} + static inline int disk_max_parts(struct gendisk *disk) { if (disk->flags & GENHD_FL_EXT_DEVT) @@ -718,6 +724,10 @@ static inline dev_t blk_lookup_devt(const char *name, int partno) return devt; } +static inline int blk_part_pack_uuid(const u8 *uuid_str, u8 *to) +{ + return -EINVAL; +} #endif /* CONFIG_BLOCK */ #endif /* _LINUX_GENHD_H */ -- cgit v1.2.3 From 804d6a89a5c0b076317966bcbcd7a63d42241831 Mon Sep 17 00:00:00 2001 From: Shani Michaeli Date: Wed, 6 Feb 2013 16:19:14 +0000 Subject: mlx4: Implement memory windows allocation and deallocation Implement MW allocation and deallocation in mlx4_core and mlx4_ib. Pass down the enable bind flag when registering memory regions. Signed-off-by: Haggai Eran Signed-off-by: Shani Michaeli Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index e9fe8caaf8bb..67b4695e5940 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -170,6 +170,7 @@ enum { #define MLX4_ATTR_EXTENDED_PORT_INFO cpu_to_be16(0xff90) enum { + MLX4_BMME_FLAG_WIN_TYPE_2B = 1 << 1, MLX4_BMME_FLAG_LOCAL_INV = 1 << 6, MLX4_BMME_FLAG_REMOTE_INV = 1 << 7, MLX4_BMME_FLAG_TYPE_2_WIN = 1 << 9, @@ -237,7 +238,8 @@ enum { MLX4_PERM_LOCAL_WRITE = 1 << 11, MLX4_PERM_REMOTE_READ = 1 << 12, MLX4_PERM_REMOTE_WRITE = 1 << 13, - MLX4_PERM_ATOMIC = 1 << 14 + MLX4_PERM_ATOMIC = 1 << 14, + MLX4_PERM_BIND_MW = 1 << 15, }; enum { @@ -503,6 +505,18 @@ struct mlx4_mr { int enabled; }; +enum mlx4_mw_type { + MLX4_MW_TYPE_1 = 1, + MLX4_MW_TYPE_2 = 2, +}; + +struct mlx4_mw { + u32 key; + u32 pd; + enum mlx4_mw_type type; + int enabled; +}; + struct mlx4_fmr { struct mlx4_mr mr; struct mlx4_mpt_entry *mpt; @@ -803,6 +817,10 @@ int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access, int npages, int page_shift, struct mlx4_mr *mr); int mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr); int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr); +int mlx4_mw_alloc(struct mlx4_dev *dev, u32 pd, enum mlx4_mw_type type, + struct mlx4_mw *mw); +void mlx4_mw_free(struct mlx4_dev *dev, struct mlx4_mw *mw); +int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw); int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, int start_index, int npages, u64 *page_list); int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, -- cgit v1.2.3 From 6ff63e194066a1f14aee805366a1d79c541fddae Mon Sep 17 00:00:00 2001 From: Shani Michaeli Date: Wed, 6 Feb 2013 16:19:15 +0000 Subject: IB/mlx4: Support memory window binding * Implement memory windows binding in mlx4_ib_post_send. * Implement mlx4_ib_bind_mw by deferring to mlx4_ib_post_send. * Rename MLX4_WQE_FMR_PERM_* flags to MLX4_WQE_FMR_AND_BIND_PERM_*, indicating that they are used both for fast registration work requests, and for memory window bind work requests. Signed-off-by: Haggai Eran Signed-off-by: Shani Michaeli Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/qp.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 6c8a68c602be..67f46ad6920a 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -265,6 +265,11 @@ struct mlx4_wqe_lso_seg { __be32 header[0]; }; +enum mlx4_wqe_bind_seg_flags2 { + MLX4_WQE_BIND_ZERO_BASED = (1 << 30), + MLX4_WQE_BIND_TYPE_2 = (1 << 31), +}; + struct mlx4_wqe_bind_seg { __be32 flags1; __be32 flags2; @@ -277,9 +282,9 @@ struct mlx4_wqe_bind_seg { enum { MLX4_WQE_FMR_PERM_LOCAL_READ = 1 << 27, MLX4_WQE_FMR_PERM_LOCAL_WRITE = 1 << 28, - MLX4_WQE_FMR_PERM_REMOTE_READ = 1 << 29, - MLX4_WQE_FMR_PERM_REMOTE_WRITE = 1 << 30, - MLX4_WQE_FMR_PERM_ATOMIC = 1 << 31 + MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_READ = 1 << 29, + MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_WRITE = 1 << 30, + MLX4_WQE_FMR_AND_BIND_PERM_ATOMIC = 1 << 31 }; struct mlx4_wqe_fmr_seg { -- cgit v1.2.3 From e72837e3e7bae3f182c4ac63c9424e86f1158dd0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 17 Feb 2013 17:47:04 -0500 Subject: default SET_PERSONALITY() in linux/elf.h Signed-off-by: Al Viro --- include/linux/elf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elf.h b/include/linux/elf.h index 8c9048e33463..40a3c0e01b2b 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -10,6 +10,10 @@ Override in asm/elf.h as needed. */ # define elf_read_implies_exec(ex, have_pt_gnu_stack) 0 #endif +#ifndef SET_PERSONALITY +#define SET_PERSONALITY(ex) \ + set_personality(PER_LINUX | (current->personality & (~PER_MASK))) +#endif #if ELF_CLASS == ELFCLASS32 -- cgit v1.2.3 From 3dadecce20603aa380023c65e6f55f108fd5e952 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 24 Jan 2013 02:18:08 -0500 Subject: switch vfs_getattr() to struct path Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3ab69777b4d8..7f471520b88b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2468,7 +2468,7 @@ extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern int generic_readlink(struct dentry *, char __user *, int); extern void generic_fillattr(struct inode *, struct kstat *); -extern int vfs_getattr(struct vfsmount *, struct dentry *, struct kstat *); +extern int vfs_getattr(struct path *, struct kstat *); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); -- cgit v1.2.3 From ecf3d1f1aa74da0d632b651a2e05a911f60e92c0 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 20 Feb 2013 11:19:05 -0500 Subject: vfs: kill FS_REVAL_DOT by adding a d_weak_revalidate dentry op The following set of operations on a NFS client and server will cause server# mkdir a client# cd a server# mv a a.bak client# sleep 30 # (or whatever the dir attrcache timeout is) client# stat . stat: cannot stat `.': Stale NFS file handle Obviously, we should not be getting an ESTALE error back there since the inode still exists on the server. The problem is that the lookup code will call d_revalidate on the dentry that "." refers to, because NFS has FS_REVAL_DOT set. nfs_lookup_revalidate will see that the parent directory has changed and will try to reverify the dentry by redoing a LOOKUP. That of course fails, so the lookup code returns ESTALE. The problem here is that d_revalidate is really a bad fit for this case. What we really want to know at this point is whether the inode is still good or not, but we don't really care what name it goes by or whether the dcache is still valid. Add a new d_op->d_weak_revalidate operation and have complete_walk call that instead of d_revalidate. The intent there is to allow for a "weaker" d_revalidate that just checks to see whether the inode is still good. This is also gives us an opportunity to kill off the FS_REVAL_DOT special casing. [AV: changed method name, added note in porting, fixed confusion re having it possibly called from RCU mode (it won't be)] Cc: NeilBrown Signed-off-by: Jeff Layton Signed-off-by: Al Viro --- include/linux/dcache.h | 3 +++ include/linux/fs.h | 1 - 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 03d169288423..1a6bb81f0fe5 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -145,6 +145,7 @@ enum dentry_d_lock_class struct dentry_operations { int (*d_revalidate)(struct dentry *, unsigned int); + int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, const struct inode *, struct qstr *); int (*d_compare)(const struct dentry *, const struct inode *, @@ -192,6 +193,8 @@ struct dentry_operations { #define DCACHE_GENOCIDE 0x0200 #define DCACHE_SHRINK_LIST 0x0400 +#define DCACHE_OP_WEAK_REVALIDATE 0x0800 + #define DCACHE_NFSFS_RENAMED 0x1000 /* this dentry has been "silly renamed" and has to be deleted on the last * dput() */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 7f471520b88b..da94011ae83c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1807,7 +1807,6 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */ -#define FS_REVAL_DOT 16384 /* Check the paths ".", ".." for staleness */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); -- cgit v1.2.3 From 182be684784334598eee1d90274e7f7aa0063616 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 24 Jan 2013 02:21:54 -0500 Subject: kill f_vfsmnt very few users left... Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index da94011ae83c..c766afd1e684 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -769,7 +769,6 @@ struct file { } f_u; struct path f_path; #define f_dentry f_path.dentry -#define f_vfsmnt f_path.mnt const struct file_operations *f_op; /* -- cgit v1.2.3 From 7bb307e894d51308aa0582a8c4cc5875bbc645b9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Feb 2013 14:51:48 -0500 Subject: export kernel_write(), convert open-coded instances Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c766afd1e684..d858363a7c17 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2277,6 +2277,7 @@ static inline void i_readcount_inc(struct inode *inode) extern int do_pipe_flags(int *, int); extern int kernel_read(struct file *, loff_t, char *, unsigned long); +extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ -- cgit v1.2.3 From 9cc64ceaa8b8e8c874519caee79e18cb35d3ce3e Mon Sep 17 00:00:00 2001 From: Yuanhan Liu Date: Wed, 20 Feb 2013 13:16:01 +1100 Subject: fs/exec.c: make bprm_mm_init() static There is only one user of bprm_mm_init, and it's inside the same file. Signed-off-by: Yuanhan Liu Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/binfmts.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 0530b9860359..c3a09149f793 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -111,7 +111,6 @@ extern int suid_dumpable; extern int setup_arg_pages(struct linux_binprm * bprm, unsigned long stack_top, int executable_stack); -extern int bprm_mm_init(struct linux_binprm *bprm); extern int bprm_change_interp(char *interp, struct linux_binprm *bprm); extern int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm); -- cgit v1.2.3 From 46c498c2cdee5efe44f617bcd4f388179be36115 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 26 Feb 2013 18:44:33 +0100 Subject: stop_machine: Mark per cpu stopper enabled early commit 14e568e78 (stop_machine: Use smpboot threads) introduced the following regression: Before this commit the stopper enabled bit was set in the online notifier. CPU0 CPU1 cpu_up cpu online hotplug_notifier(ONLINE) stopper(CPU1)->enabled = true; ... stop_machine() The conversion to smpboot threads moved the enablement to the wakeup path of the parked thread. The majority of users seem to have the following working order: CPU0 CPU1 cpu_up cpu online unpark_threads() wakeup(stopper[CPU1]) .... stopper thread runs stopper(CPU1)->enabled = true; stop_machine() But Konrad and Sander have observed: CPU0 CPU1 cpu_up cpu online unpark_threads() wakeup(stopper[CPU1]) .... stop_machine() stopper thread runs stopper(CPU1)->enabled = true; Now the stop machinery kicks CPU0 into the stop loop, where it gets stuck forever because the queue code saw stopper(CPU1)->enabled == false, so CPU0 waits for CPU1 to enter stomp_machine, but the CPU1 stopper work got discarded due to enabled == false. Add a pre_unpark function to the smpboot thread descriptor and call it before waking the thread. This fixes the problem at hand, but the stop_machine code should be more robust. The stopper->enabled flag smells fishy at best. Thanks to Konrad for going through a loop of debug patches and providing the information to decode this issue. Reported-and-tested-by: Konrad Rzeszutek Wilk Reported-and-tested-by: Sander Eikelenboom Cc: Srivatsa S. Bhat Cc: Rusty Russell Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1302261843240.22263@ionos Signed-off-by: Thomas Gleixner --- include/linux/smpboot.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index c65dee059913..13e929679550 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -24,6 +24,9 @@ struct smpboot_thread_data; * parked (cpu offline) * @unpark: Optional unpark function, called when the thread is * unparked (cpu online) + * @pre_unpark: Optional unpark function, called before the thread is + * unparked (cpu online). This is not guaranteed to be + * called on the target cpu of the thread. Careful! * @selfparking: Thread is not parked by the park function. * @thread_comm: The base name of the thread */ @@ -37,6 +40,7 @@ struct smp_hotplug_thread { void (*cleanup)(unsigned int cpu, bool online); void (*park)(unsigned int cpu); void (*unpark)(unsigned int cpu); + void (*pre_unpark)(unsigned int cpu); bool selfparking; const char *thread_comm; }; -- cgit v1.2.3 From 12979354a1d6ef25d86f381e4d5f9e103f29913a Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Tue, 8 Jan 2013 09:15:10 -0800 Subject: libceph: rename ceph_pg -> ceph_pg_v1 Rename the old version this type to distinguish it from the new version. Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/osd_client.h | 2 +- include/linux/ceph/osdmap.h | 7 ++++--- include/linux/ceph/rados.h | 4 ++-- 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 388158ff0cbc..be2867330e23 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -56,7 +56,7 @@ struct ceph_osd_request { struct list_head r_linger_item; struct list_head r_linger_osd; struct ceph_osd *r_osd; - struct ceph_pg r_pgid; + struct ceph_pg_v1 r_pgid; int r_pg_osds[CEPH_PG_MAX_SIZE]; int r_num_pg_osds; diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index c83a838f89f5..eb4989aa48e8 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -28,7 +28,7 @@ struct ceph_pg_pool_info { struct ceph_pg_mapping { struct rb_node node; - struct ceph_pg pgid; + struct ceph_pg_v1 pgid; int len; int osds[]; }; @@ -118,10 +118,11 @@ extern int ceph_calc_object_layout(struct ceph_object_layout *ol, const char *oid, struct ceph_file_layout *fl, struct ceph_osdmap *osdmap); -extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, +extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, + struct ceph_pg_v1 pgid, int *acting); extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, - struct ceph_pg pgid); + struct ceph_pg_v1 pgid); extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id); extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name); diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index b65182aba6f7..e7cece69b13f 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -64,7 +64,7 @@ struct ceph_timespec { * placement group. * we encode this into one __le64. */ -struct ceph_pg { +struct ceph_pg_v1 { __le16 preferred; /* preferred primary osd */ __le16 ps; /* placement seed */ __le32 pool; /* object pool */ @@ -128,7 +128,7 @@ static inline int ceph_stable_mod(int x, int b, int bmask) * object layout - how a given object should be stored. */ struct ceph_object_layout { - struct ceph_pg ol_pgid; /* raw pg, with _full_ ps precision. */ + struct ceph_pg_v1 ol_pgid; /* raw pg, with _full_ ps precision. */ __le32 ol_stripe_unit; /* for per-object parity, if any */ } __attribute__ ((packed)); -- cgit v1.2.3 From 5b191d9914eb68257f47de9d5bfe099b77f0687c Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Sat, 23 Feb 2013 10:38:16 -0800 Subject: libceph: decode into cpu-native ceph_pg type Always decode data into our cpu-native ceph_pg type that has the correct field widths. Limit any remaining uses of ceph_pg_v1 to dealing with the legacy protocol. Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/osd_client.h | 2 +- include/linux/ceph/osdmap.h | 11 ++++++++--- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index be2867330e23..388158ff0cbc 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -56,7 +56,7 @@ struct ceph_osd_request { struct list_head r_linger_item; struct list_head r_linger_osd; struct ceph_osd *r_osd; - struct ceph_pg_v1 r_pgid; + struct ceph_pg r_pgid; int r_pg_osds[CEPH_PG_MAX_SIZE]; int r_num_pg_osds; diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index eb4989aa48e8..8a612df4c248 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -18,6 +18,11 @@ * The map can be updated either via an incremental map (diff) describing * the change between two successive epochs, or as a fully encoded map. */ +struct ceph_pg { + uint64_t pool; + uint32_t seed; +}; + struct ceph_pg_pool_info { struct rb_node node; int id; @@ -28,7 +33,7 @@ struct ceph_pg_pool_info { struct ceph_pg_mapping { struct rb_node node; - struct ceph_pg_v1 pgid; + struct ceph_pg pgid; int len; int osds[]; }; @@ -119,10 +124,10 @@ extern int ceph_calc_object_layout(struct ceph_object_layout *ol, struct ceph_file_layout *fl, struct ceph_osdmap *osdmap); extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, - struct ceph_pg_v1 pgid, + struct ceph_pg pgid, int *acting); extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, - struct ceph_pg_v1 pgid); + struct ceph_pg pgid); extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id); extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name); -- cgit v1.2.3 From ec73a754989c27628c9037887df919561280519c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 26 Feb 2013 14:23:07 -0600 Subject: ceph: update "ceph_features.h" This updates "include/linux/ceph/ceph_features.h" so all the feature bits defined in the user space code are defined here. The features supported by this implementation will still differ so that's not updated here. Signed-off-by: Alex Elder Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 2160aab482f6..9e0f5a8ba247 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -12,12 +12,28 @@ #define CEPH_FEATURE_MONNAMES (1<<5) #define CEPH_FEATURE_RECONNECT_SEQ (1<<6) #define CEPH_FEATURE_DIRLAYOUTHASH (1<<7) -/* bits 8-17 defined by user-space; not supported yet here */ +#define CEPH_FEATURE_OBJECTLOCATOR (1<<8) +#define CEPH_FEATURE_PGID64 (1<<9) +#define CEPH_FEATURE_INCSUBOSDMAP (1<<10) +#define CEPH_FEATURE_PGPOOL3 (1<<11) +#define CEPH_FEATURE_OSDREPLYMUX (1<<12) +#define CEPH_FEATURE_OSDENC (1<<13) +#define CEPH_FEATURE_OMAP (1<<14) +#define CEPH_FEATURE_MONENC (1<<15) +#define CEPH_FEATURE_QUERY_T (1<<16) +#define CEPH_FEATURE_INDEP_PG_MAP (1<<17) #define CEPH_FEATURE_CRUSH_TUNABLES (1<<18) -/* bits 19-24 defined by user-space; not supported yet here */ +#define CEPH_FEATURE_CHUNKY_SCRUB (1<<19) +#define CEPH_FEATURE_MON_NULLROUTE (1<<20) +#define CEPH_FEATURE_MON_GV (1<<21) +#define CEPH_FEATURE_BACKFILL_RESERVATION (1<<22) +#define CEPH_FEATURE_MSG_AUTH (1<<23) +#define CEPH_FEATURE_RECOVERY_RESERVATION (1<<24) #define CEPH_FEATURE_CRUSH_TUNABLES2 (1<<25) -/* bit 26 defined by user-space; not supported yet here */ -#define CEPH_FEATURE_REPLY_CREATE_INODE (1<<27) +#define CEPH_FEATURE_CREATEPOOLID (1<<26) +#define CEPH_FEATURE_REPLY_CREATE_INODE (1<<27) +#define CEPH_FEATURE_OSD_HBMSGS (1<<28) +#define CEPH_FEATURE_MDSENC (1<<29) /* * Features supported. -- cgit v1.2.3 From 4f6a7e5ee1393ec4b243b39dac9f36992d161540 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Sat, 23 Feb 2013 10:41:09 -0800 Subject: ceph: update support for PGID64, PGPOOL3, OSDENC protocol features Support (and require) the PGID64, PGPOOL3, and OSDENC protocol features. These have been present in ceph.git since v0.42, Feb 2012. Require these features to simplify support; nobody is running older userspace. Note that the new request and reply encoding is still not in place, so the new code is not yet functional. Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/ceph_features.h | 14 ++++++++++---- include/linux/ceph/mdsmap.h | 4 ++-- include/linux/ceph/osdmap.h | 16 +++++++++++++--- include/linux/ceph/rados.h | 23 ----------------------- 4 files changed, 25 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 9e0f5a8ba247..ab0a54286e0d 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -39,11 +39,17 @@ * Features supported. */ #define CEPH_FEATURES_SUPPORTED_DEFAULT \ - (CEPH_FEATURE_NOSRCADDR | \ - CEPH_FEATURE_CRUSH_TUNABLES | \ - CEPH_FEATURE_CRUSH_TUNABLES2 | \ + (CEPH_FEATURE_NOSRCADDR | \ + CEPH_FEATURE_PGID64 | \ + CEPH_FEATURE_PGPOOL3 | \ + CEPH_FEATURE_OSDENC | \ + CEPH_FEATURE_CRUSH_TUNABLES | \ + CEPH_FEATURE_CRUSH_TUNABLES2 | \ CEPH_FEATURE_REPLY_CREATE_INODE) #define CEPH_FEATURES_REQUIRED_DEFAULT \ - (CEPH_FEATURE_NOSRCADDR) + (CEPH_FEATURE_NOSRCADDR | \ + CEPH_FEATURE_PGID64 | \ + CEPH_FEATURE_PGPOOL3 | \ + CEPH_FEATURE_OSDENC) #endif diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h index cb15b5d867c7..87ed09f54800 100644 --- a/include/linux/ceph/mdsmap.h +++ b/include/linux/ceph/mdsmap.h @@ -29,8 +29,8 @@ struct ceph_mdsmap { /* which object pools file data can be stored in */ int m_num_data_pg_pools; - u32 *m_data_pg_pools; - u32 m_cas_pg_pool; + u64 *m_data_pg_pools; + u64 m_cas_pg_pool; }; static inline struct ceph_entity_addr * diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 8a612df4c248..8587746b7f0e 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -25,12 +25,22 @@ struct ceph_pg { struct ceph_pg_pool_info { struct rb_node node; - int id; - struct ceph_pg_pool v; - int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask; + s64 id; + u8 type; + u8 size; + u8 crush_ruleset; + u8 object_hash; + u32 pg_num, pgp_num; + int pg_num_mask, pgp_num_mask; + u64 flags; char *name; }; +struct ceph_object_locator { + uint64_t pool; + char *key; +}; + struct ceph_pg_mapping { struct rb_node node; struct ceph_pg pgid; diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index e7cece69b13f..d784c8dfb09a 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -8,14 +8,6 @@ #include -/* - * osdmap encoding versions - */ -#define CEPH_OSDMAP_INC_VERSION 5 -#define CEPH_OSDMAP_INC_VERSION_EXT 6 -#define CEPH_OSDMAP_VERSION 5 -#define CEPH_OSDMAP_VERSION_EXT 6 - /* * fs id */ @@ -91,21 +83,6 @@ struct ceph_pg_v1 { #define CEPH_PG_TYPE_REP 1 #define CEPH_PG_TYPE_RAID4 2 -#define CEPH_PG_POOL_VERSION 2 -struct ceph_pg_pool { - __u8 type; /* CEPH_PG_TYPE_* */ - __u8 size; /* number of osds in each pg */ - __u8 crush_ruleset; /* crush placement rule */ - __u8 object_hash; /* hash mapping object name to ps */ - __le32 pg_num, pgp_num; /* number of pg's */ - __le32 lpg_num, lpgp_num; /* number of localized pg's */ - __le32 last_change; /* most recent epoch changed */ - __le64 snap_seq; /* seq for per-pool snapshot */ - __le32 snap_epoch; /* epoch of last snap */ - __le32 num_snaps; - __le32 num_removed_snap_intervals; /* if non-empty, NO per-pool snaps */ - __le64 auid; /* who owns the pg */ -} __attribute__ ((packed)); /* * stable_mod func is used to control number of placement groups. -- cgit v1.2.3 From 2169aea649c08374bec7d220a3b8f64712275356 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 25 Feb 2013 16:13:08 -0800 Subject: libceph: calculate placement based on the internal data types Instead of using the old ceph_object_layout struct, update our internal ceph_calc_object_layout method to use the ceph_pg type. This allows us to pass the full 32-bit precision of the pgid.seed to the callers. It also allows some callers to avoid reaching into the request structures for the struct ceph_object_layout fields. Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/osd_client.h | 1 + include/linux/ceph/osdmap.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 388158ff0cbc..ad8899fc3157 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -82,6 +82,7 @@ struct ceph_osd_request { char r_oid[MAX_OBJ_NAME_SIZE]; /* object name */ int r_oid_len; + u64 r_snapid; unsigned long r_stamp; /* send OR check time */ struct ceph_file_layout r_file_layout; diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 8587746b7f0e..35985125f118 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -129,7 +129,7 @@ extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, u64 *bno, u64 *oxoff, u64 *oxlen); /* calculate mapping of object to a placement group */ -extern int ceph_calc_object_layout(struct ceph_object_layout *ol, +extern int ceph_calc_object_layout(struct ceph_pg *pg, const char *oid, struct ceph_file_layout *fl, struct ceph_osdmap *osdmap); -- cgit v1.2.3 From 1b83bef24c6746a146d39915a18fb5425f2facb0 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 25 Feb 2013 16:11:12 -0800 Subject: libceph: update osd request/reply encoding Use the new version of the encoding for osd requests and replies. In the process, update the way we are tracking request ops and reply lengths and results in the struct ceph_osd_request. Update the rbd and fs/ceph users appropriately. The main changes are: - we keep pointers into the request memory for fields we need to update each time the request is sent out over the wire - we keep information about the result in an array in the request struct where the users can easily get at it. Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/osd_client.h | 19 ++++++++++++++++++- include/linux/ceph/rados.h | 38 -------------------------------------- 2 files changed, 18 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index ad8899fc3157..1dd5d466b6f9 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -47,6 +47,9 @@ struct ceph_osd { struct list_head o_keepalive_item; }; + +#define CEPH_OSD_MAX_OP 10 + /* an in-flight request */ struct ceph_osd_request { u64 r_tid; /* unique for this client */ @@ -63,9 +66,23 @@ struct ceph_osd_request { struct ceph_connection *r_con_filling_msg; struct ceph_msg *r_request, *r_reply; - int r_result; int r_flags; /* any additional flags for the osd */ u32 r_sent; /* >0 if r_request is sending/sent */ + int r_num_ops; + + /* encoded message content */ + struct ceph_osd_op *r_request_ops; + /* these are updated on each send */ + __le32 *r_request_osdmap_epoch; + __le32 *r_request_flags; + __le64 *r_request_pool; + void *r_request_pgid; + __le32 *r_request_attempts; + struct ceph_eversion *r_request_reassert_version; + + int r_result; + int r_reply_op_len[CEPH_OSD_MAX_OP]; + s32 r_reply_op_result[CEPH_OSD_MAX_OP]; int r_got_reply; int r_linger; diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index d784c8dfb09a..68c96a508ac2 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -416,43 +416,5 @@ struct ceph_osd_op { __le32 payload_len; } __attribute__ ((packed)); -/* - * osd request message header. each request may include multiple - * ceph_osd_op object operations. - */ -struct ceph_osd_request_head { - __le32 client_inc; /* client incarnation */ - struct ceph_object_layout layout; /* pgid */ - __le32 osdmap_epoch; /* client's osdmap epoch */ - - __le32 flags; - - struct ceph_timespec mtime; /* for mutations only */ - struct ceph_eversion reassert_version; /* if we are replaying op */ - - __le32 object_len; /* length of object name */ - - __le64 snapid; /* snapid to read */ - __le64 snap_seq; /* writer's snap context */ - __le32 num_snaps; - - __le16 num_ops; - struct ceph_osd_op ops[]; /* followed by ops[], obj, ticket, snaps */ -} __attribute__ ((packed)); - -struct ceph_osd_reply_head { - __le32 client_inc; /* client incarnation */ - __le32 flags; - struct ceph_object_layout layout; - __le32 osdmap_epoch; - struct ceph_eversion reassert_version; /* for replaying uncommitted */ - - __le32 result; /* result code */ - - __le32 object_len; /* length of object name */ - __le32 num_ops; - struct ceph_osd_op ops[0]; /* ops[], object */ -} __attribute__ ((packed)); - #endif -- cgit v1.2.3 From 83ca14fdd35821554058e5fd4fa7b118ee504a33 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Tue, 26 Feb 2013 10:39:09 -0800 Subject: libceph: add support for HASHPSPOOL pool flag The legacy behavior adds the pgid seed and pool together as the input for CRUSH. That is problematic because each pool's PGs end up mapping to the same OSDs: 1.5 == 2.4 == 3.3 == ... Instead, if the HASHPSPOOL flag is set, we has the ps and pool together and feed that into CRUSH. This ensures that two adjacent pools will map to an independent pseudorandom set of OSDs. Advertise our support for this via a protocol feature flag. Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/ceph_features.h | 4 +++- include/linux/ceph/osdmap.h | 2 ++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index ab0a54286e0d..76554cecaab2 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -34,6 +34,7 @@ #define CEPH_FEATURE_REPLY_CREATE_INODE (1<<27) #define CEPH_FEATURE_OSD_HBMSGS (1<<28) #define CEPH_FEATURE_MDSENC (1<<29) +#define CEPH_FEATURE_OSDHASHPSPOOL (1<<30) /* * Features supported. @@ -45,7 +46,8 @@ CEPH_FEATURE_OSDENC | \ CEPH_FEATURE_CRUSH_TUNABLES | \ CEPH_FEATURE_CRUSH_TUNABLES2 | \ - CEPH_FEATURE_REPLY_CREATE_INODE) + CEPH_FEATURE_REPLY_CREATE_INODE | \ + CEPH_FEATURE_OSDHASHPSPOOL) #define CEPH_FEATURES_REQUIRED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 35985125f118..c819190d1642 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -23,6 +23,8 @@ struct ceph_pg { uint32_t seed; }; +#define CEPH_POOL_FLAG_HASHPSPOOL 1 + struct ceph_pg_pool_info { struct rb_node node; s64 id; -- cgit v1.2.3 From f00b4dad9d9eb001a04cf72e8351a2a1b9e99322 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 20 Dec 2012 14:14:23 +0100 Subject: dma-buf: implement vmap refcounting in the interface logic All drivers which implement this need to have some sort of refcount to allow concurrent vmap usage. Hence implement this in the dma-buf core. To protect against concurrent calls we need a lock, which potentially causes new funny locking inversions. But this shouldn't be a problem for exporters with statically allocated backing storage, and more dynamic drivers have decent issues already anyway. Inspired by some refactoring patches from Aaron Plattner, who implemented the same idea, but only for drm/prime drivers. v2: Check in dma_buf_release that no dangling vmaps are left. Suggested by Aaron Plattner. We might want to do similar checks for attachments, but that's for another patch. Also fix up ERR_PTR return for vmap. v3: Check whether the passed-in vmap address matches with the cached one for vunmap. Eventually we might want to remove that parameter - compared to the kmap functions there's no need for the vaddr for unmapping. Suggested by Chris Wilson. v4: Fix a brown-paper-bag bug spotted by Aaron Plattner. Cc: Aaron Plattner Reviewed-by: Aaron Plattner Tested-by: Aaron Plattner Reviewed-by: Rob Clark Signed-off-by: Daniel Vetter Signed-off-by: Sumit Semwal --- include/linux/dma-buf.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 3d754a394e92..9978b614a1aa 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -119,8 +119,10 @@ struct dma_buf { struct file *file; struct list_head attachments; const struct dma_buf_ops *ops; - /* mutex to serialize list manipulation and attach/detach */ + /* mutex to serialize list manipulation, attach/detach and vmap/unmap */ struct mutex lock; + unsigned vmapping_counter; + void *vmap_ptr; void *priv; }; -- cgit v1.2.3 From 864ef69b2d9b34e7c85baa9c5c601d5e735b208a Mon Sep 17 00:00:00 2001 From: Matt Porter Date: Fri, 1 Feb 2013 18:22:52 +0000 Subject: dmaengine: add dma_request_slave_channel_compat() Adds a dma_request_slave_channel_compat() wrapper which accepts both the arguments from dma_request_channel() and dma_request_slave_channel(). Based on whether the driver is instantiated via DT, the appropriate channel request call will be made. This allows for a much cleaner migration of drivers to the dmaengine DT API as platforms continue to be mixed between those that boot using DT and those that do not. Suggested-by: Tony Lindgren Signed-off-by: Matt Porter Acked-by: Tony Lindgren Acked-by: Arnd Bergmann Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index f5939999cb65..91ac8da25020 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1001,6 +1001,22 @@ void dma_run_dependencies(struct dma_async_tx_descriptor *tx); struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type); struct dma_chan *net_dma_find_channel(void); #define dma_request_channel(mask, x, y) __dma_request_channel(&(mask), x, y) +#define dma_request_slave_channel_compat(mask, x, y, dev, name) \ + __dma_request_slave_channel_compat(&(mask), x, y, dev, name) + +static inline struct dma_chan +*__dma_request_slave_channel_compat(dma_cap_mask_t *mask, dma_filter_fn fn, + void *fn_param, struct device *dev, + char *name) +{ + struct dma_chan *chan; + + chan = dma_request_slave_channel(dev, name); + if (chan) + return chan; + + return __dma_request_channel(mask, fn, fn_param); +} /* --- Helper iov-locking functions --- */ -- cgit v1.2.3 From c5a51053cf3b499ddba60a89ab067ea05ad15840 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Wed, 27 Feb 2013 17:02:43 -0800 Subject: backlight: add new lp8788 backlight driver TI LP8788 PMU supports regulators, battery charger, RTC, ADC, backlight dri= ver and current sinks. This patch enables LP8788 backlight module. (Brightness mode) The brightness is controlled by PWM input or I2C register. All modes are supported in the driver. (Platform data) Configurable data can be defined in the platform side. name : backlight driver name. (default: "lcd-backlight") initial_brightness : initial value of backlight brightness bl_mode : brightness control by PWM or lp8788 register dim_mode : dimming mode selection full_scale : full scale current setting rise_time : brightness ramp up step time fall_time : brightness ramp down step time pwm_pol : PWM polarity setting when bl_mode is PWM based period_ns : platform specific PWM period value. unit is nano. The default values are set in case no platform data is defined. [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Milo(Woogyom) Kim Cc: Richard Purdie Cc: Samuel Ortiz Cc: Thierry Reding Cc: "devendra.aaru" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mfd/lp8788.h | 24 +++++------------------- 1 file changed, 5 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/lp8788.h b/include/linux/mfd/lp8788.h index 2a32b16f79cb..786bf6679a28 100644 --- a/include/linux/mfd/lp8788.h +++ b/include/linux/mfd/lp8788.h @@ -16,6 +16,7 @@ #include #include +#include #include #define LP8788_DEV_BUCK "lp8788-buck" @@ -124,11 +125,6 @@ enum lp8788_bl_ramp_step { LP8788_RAMP_65538us, }; -enum lp8788_bl_pwm_polarity { - LP8788_PWM_ACTIVE_HIGH, - LP8788_PWM_ACTIVE_LOW, -}; - enum lp8788_isink_scale { LP8788_ISINK_SCALE_100mA, LP8788_ISINK_SCALE_120mA, @@ -228,16 +224,6 @@ struct lp8788_charger_platform_data { enum lp8788_charger_event event); }; -/* - * struct lp8788_bl_pwm_data - * @pwm_set_intensity : set duty of pwm - * @pwm_get_intensity : get current duty of pwm - */ -struct lp8788_bl_pwm_data { - void (*pwm_set_intensity) (int brightness, int max_brightness); - int (*pwm_get_intensity) (int max_brightness); -}; - /* * struct lp8788_backlight_platform_data * @name : backlight driver name. (default: "lcd-backlight") @@ -248,8 +234,8 @@ struct lp8788_bl_pwm_data { * @rise_time : brightness ramp up step time * @fall_time : brightness ramp down step time * @pwm_pol : pwm polarity setting when bl_mode is pwm based - * @pwm_data : platform specific pwm generation functions - * only valid when bl_mode is pwm based + * @period_ns : platform specific pwm period value. unit is nano. + Only valid when bl_mode is LP8788_BL_COMB_PWM_BASED */ struct lp8788_backlight_platform_data { char *name; @@ -259,8 +245,8 @@ struct lp8788_backlight_platform_data { enum lp8788_bl_full_scale_current full_scale; enum lp8788_bl_ramp_step rise_time; enum lp8788_bl_ramp_step fall_time; - enum lp8788_bl_pwm_polarity pwm_pol; - struct lp8788_bl_pwm_data pwm_data; + enum pwm_polarity pwm_pol; + unsigned int period_ns; }; /* -- cgit v1.2.3 From a321e91b6d73ed011ffceed384c40d2785cf723b Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Wed, 27 Feb 2013 17:02:56 -0800 Subject: lib/scatterlist: add simple page iterator Add an iterator to walk through a scatter list a page at a time starting at a specific page offset. As opposed to the mapping iterator this is meant to be small, performing well even in simple loops like collecting all pages on the scatterlist into an array or setting up an iommu table based on the pages' DMA address. Signed-off-by: Imre Deak Cc: Maxim Levitsky Cc: Tejun Heo Cc: Daniel Vetter Tested-by: Stephen Warren Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/scatterlist.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 4bd6c06eb28e..788a853aa7a7 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -231,6 +231,41 @@ size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents, */ #define SG_MAX_SINGLE_ALLOC (PAGE_SIZE / sizeof(struct scatterlist)) +/* + * sg page iterator + * + * Iterates over sg entries page-by-page. On each successful iteration, + * @piter->page points to the current page, @piter->sg to the sg holding this + * page and @piter->sg_pgoffset to the page's page offset within the sg. The + * iteration will stop either when a maximum number of sg entries was reached + * or a terminating sg (sg_last(sg) == true) was reached. + */ +struct sg_page_iter { + struct page *page; /* current page */ + struct scatterlist *sg; /* sg holding the page */ + unsigned int sg_pgoffset; /* page offset within the sg */ + + /* these are internal states, keep away */ + unsigned int __nents; /* remaining sg entries */ + int __pg_advance; /* nr pages to advance at the + * next step */ +}; + +bool __sg_page_iter_next(struct sg_page_iter *piter); +void __sg_page_iter_start(struct sg_page_iter *piter, + struct scatterlist *sglist, unsigned int nents, + unsigned long pgoffset); + +/** + * for_each_sg_page - iterate over the pages of the given sg list + * @sglist: sglist to iterate over + * @piter: page iterator to hold current page, sg, sg_pgoffset + * @nents: maximum number of sg entries to iterate over + * @pgoffset: starting page offset + */ +#define for_each_sg_page(sglist, piter, nents, pgoffset) \ + for (__sg_page_iter_start((piter), (sglist), (nents), (pgoffset)); \ + __sg_page_iter_next(piter);) /* * Mapping sg iterator -- cgit v1.2.3 From 4225fc8555a992c7f91d174ef424384d6781e144 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Wed, 27 Feb 2013 17:02:57 -0800 Subject: lib/scatterlist: use page iterator in the mapping iterator For better code reuse use the newly added page iterator to iterate through the pages. The offset, length within the page is still calculated by the mapping iterator as well as the actual mapping. Idea from Tejun Heo. Signed-off-by: Imre Deak Cc: Maxim Levitsky Cc: Tejun Heo Cc: Daniel Vetter Cc: James Hogan Cc: Stephen Warren Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/scatterlist.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 788a853aa7a7..2d8bdaef9611 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -293,11 +293,11 @@ struct sg_mapping_iter { void *addr; /* pointer to the mapped area */ size_t length; /* length of the mapped area */ size_t consumed; /* number of consumed bytes */ + struct sg_page_iter piter; /* page iterator */ /* these are internal states, keep away */ - struct scatterlist *__sg; /* current entry */ - unsigned int __nents; /* nr of remaining entries */ - unsigned int __offset; /* offset within sg */ + unsigned int __offset; /* offset within page */ + unsigned int __remaining; /* remaining bytes on page */ unsigned int __flags; }; -- cgit v1.2.3 From e579d2c259be42b6f29458327e5153b22414b031 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 27 Feb 2013 17:03:15 -0800 Subject: coredump: remove redundant defines for dumpable states The existing SUID_DUMP_* defines duplicate the newer SUID_DUMPABLE_* defines introduced in 54b501992dd2 ("coredump: warn about unsafe suid_dumpable / core_pattern combo"). Remove the new ones, and use the prior values instead. Signed-off-by: Kees Cook Reported-by: Chen Gang Cc: Alexander Viro Cc: Alan Cox Cc: "Eric W. Biederman" Cc: Doug Ledford Cc: Serge Hallyn Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6853bf947fde..d35d2b6ddbfb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -346,11 +346,6 @@ static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} extern void set_dumpable(struct mm_struct *mm, int value); extern int get_dumpable(struct mm_struct *mm); -/* get/set_dumpable() values */ -#define SUID_DUMPABLE_DISABLED 0 -#define SUID_DUMPABLE_ENABLED 1 -#define SUID_DUMPABLE_SAFE 2 - /* mm flags */ /* dumpable bits */ #define MMF_DUMPABLE 0 /* core dump is permitted */ -- cgit v1.2.3 From 6aa9707099c4b25700940eb3d016f16c4434360d Mon Sep 17 00:00:00 2001 From: Mandeep Singh Baines Date: Wed, 27 Feb 2013 17:03:18 -0800 Subject: lockdep: check that no locks held at freeze time We shouldn't try_to_freeze if locks are held. Holding a lock can cause a deadlock if the lock is later acquired in the suspend or hibernate path (e.g. by dpm). Holding a lock can also cause a deadlock in the case of cgroup_freezer if a lock is held inside a frozen cgroup that is later acquired by a process outside that group. [akpm@linux-foundation.org: export debug_check_no_locks_held] Signed-off-by: Mandeep Singh Baines Cc: Ben Chan Cc: Oleg Nesterov Cc: Tejun Heo Cc: Rafael J. Wysocki Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/debug_locks.h | 4 ++-- include/linux/freezer.h | 3 +++ 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 3bd46f766751..a975de1ff59f 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -51,7 +51,7 @@ struct task_struct; extern void debug_show_all_locks(void); extern void debug_show_held_locks(struct task_struct *task); extern void debug_check_no_locks_freed(const void *from, unsigned long len); -extern void debug_check_no_locks_held(struct task_struct *task); +extern void debug_check_no_locks_held(void); #else static inline void debug_show_all_locks(void) { @@ -67,7 +67,7 @@ debug_check_no_locks_freed(const void *from, unsigned long len) } static inline void -debug_check_no_locks_held(struct task_struct *task) +debug_check_no_locks_held(void) { } #endif diff --git a/include/linux/freezer.h b/include/linux/freezer.h index e70df40d84f6..043a5cf8b5ba 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -3,6 +3,7 @@ #ifndef FREEZER_H_INCLUDED #define FREEZER_H_INCLUDED +#include #include #include #include @@ -48,6 +49,8 @@ extern void thaw_kernel_threads(void); static inline bool try_to_freeze(void) { + if (!(current->flags & PF_NOFREEZE)) + debug_check_no_locks_held(); might_sleep(); if (likely(!freezing(current))) return false; -- cgit v1.2.3 From fe6e24ec90b753392c3f9ec1fbca196c4e88e511 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 27 Feb 2013 17:03:50 -0800 Subject: idr: deprecate idr_remove_all() There was only one legitimate use of idr_remove_all() and a lot more of incorrect uses (or lack of it). Now that idr_destroy() implies idr_remove_all() and all the in-kernel users updated not to use it, there's no reason to keep it around. Mark it deprecated so that we can later unexport it. idr_remove_all() is made an inline function calling __idr_remove_all() to avoid triggering deprecated warning on EXPORT_SYMBOL(). Signed-off-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index e5eb125effe6..4cf042da3892 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -110,10 +110,22 @@ int idr_for_each(struct idr *idp, void *idr_get_next(struct idr *idp, int *nextid); void *idr_replace(struct idr *idp, void *ptr, int id); void idr_remove(struct idr *idp, int id); -void idr_remove_all(struct idr *idp); void idr_destroy(struct idr *idp); void idr_init(struct idr *idp); +void __idr_remove_all(struct idr *idp); /* don't use */ + +/** + * idr_remove_all - remove all ids from the given idr tree + * @idp: idr handle + * + * If you're trying to destroy @idp, calling idr_destroy() is enough. + * This is going away. Don't use. + */ +static inline void __deprecated idr_remove_all(struct idr *idp) +{ + __idr_remove_all(idp); +} /* * IDA - IDR based id allocator, use when translation from id to -- cgit v1.2.3 From 4106ecaf59b79efff3f9b466baf9e8c67e19ac5a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 27 Feb 2013 17:03:51 -0800 Subject: idr: cosmetic updates to struct / initializer definitions * Tab align fields like a normal person. * Drop the unnecessary 0 inits from IDR_INIT(). This patch is purely cosmetic. Signed-off-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 4cf042da3892..8f4980db3524 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -49,28 +49,24 @@ #define MAX_IDR_FREE (MAX_IDR_LEVEL * 2) struct idr_layer { - unsigned long bitmap; /* A zero bit means "space here" */ + unsigned long bitmap; /* A zero bit means "space here" */ struct idr_layer __rcu *ary[1< Date: Wed, 27 Feb 2013 17:03:52 -0800 Subject: idr: relocate idr_for_each_entry() and reorganize id[r|a]_get_new() * Move idr_for_each_entry() definition next to other idr related definitions. * Make id[r|a]_get_new() inline wrappers of id[r|a]_get_new_above(). This changes the implementation of idr_get_new() but the new implementation is trivial. This patch doesn't introduce any functional change. Signed-off-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 47 +++++++++++++++++++++++++++++++++++------------ 1 file changed, 35 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 8f4980db3524..ff44bc83f3cb 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -99,7 +99,6 @@ struct idr { void *idr_find(struct idr *idp, int id); int idr_pre_get(struct idr *idp, gfp_t gfp_mask); -int idr_get_new(struct idr *idp, void *ptr, int *id); int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id); int idr_for_each(struct idr *idp, int (*fn)(int id, void *p, void *data), void *data); @@ -109,6 +108,30 @@ void idr_remove(struct idr *idp, int id); void idr_destroy(struct idr *idp); void idr_init(struct idr *idp); +/** + * idr_get_new - allocate new idr entry + * @idp: idr handle + * @ptr: pointer you want associated with the id + * @id: pointer to the allocated handle + * + * Simple wrapper around idr_get_new_above() w/ @starting_id of zero. + */ +static inline int idr_get_new(struct idr *idp, void *ptr, int *id) +{ + return idr_get_new_above(idp, ptr, 0, id); +} + +/** + * idr_for_each_entry - iterate over an idr's elements of a given type + * @idp: idr handle + * @entry: the type * to use as cursor + * @id: id entry's key + */ +#define idr_for_each_entry(idp, entry, id) \ + for (id = 0, entry = (typeof(entry))idr_get_next((idp), &(id)); \ + entry != NULL; \ + ++id, entry = (typeof(entry))idr_get_next((idp), &(id))) + void __idr_remove_all(struct idr *idp); /* don't use */ /** @@ -149,7 +172,6 @@ struct ida { int ida_pre_get(struct ida *ida, gfp_t gfp_mask); int ida_get_new_above(struct ida *ida, int starting_id, int *p_id); -int ida_get_new(struct ida *ida, int *p_id); void ida_remove(struct ida *ida, int id); void ida_destroy(struct ida *ida); void ida_init(struct ida *ida); @@ -158,17 +180,18 @@ int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end, gfp_t gfp_mask); void ida_simple_remove(struct ida *ida, unsigned int id); -void __init idr_init_cache(void); - /** - * idr_for_each_entry - iterate over an idr's elements of a given type - * @idp: idr handle - * @entry: the type * to use as cursor - * @id: id entry's key + * ida_get_new - allocate new ID + * @ida: idr handle + * @p_id: pointer to the allocated handle + * + * Simple wrapper around ida_get_new_above() w/ @starting_id of zero. */ -#define idr_for_each_entry(idp, entry, id) \ - for (id = 0, entry = (typeof(entry))idr_get_next((idp), &(id)); \ - entry != NULL; \ - ++id, entry = (typeof(entry))idr_get_next((idp), &(id))) +static inline int ida_get_new(struct ida *ida, int *p_id) +{ + return ida_get_new_above(ida, 0, p_id); +} + +void __init idr_init_cache(void); #endif /* __IDR_H__ */ -- cgit v1.2.3 From 12d1b4393e0d8df36b2646a5e512f0513fb532d2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 27 Feb 2013 17:03:53 -0800 Subject: idr: remove _idr_rc_to_errno() hack idr uses -1, IDR_NEED_TO_GROW and IDR_NOMORE_SPACE to communicate exception conditions internally. The return value is later translated to errno values using _idr_rc_to_errno(). This is confusing. Drop the custom ones and consistently use -EAGAIN for "tree needs to grow", -ENOMEM for "need more memory" and -ENOSPC for "ran out of ID space". Due to the weird memory preloading mechanism, [ra]_get_new*() return -EAGAIN on memory shortage, so we need to substitute -ENOMEM w/ -EAGAIN on those interface functions. They'll eventually be cleaned up and the translations will go away. This patch doesn't introduce any functional changes. Signed-off-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index ff44bc83f3cb..837f152b1383 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -70,12 +70,6 @@ struct idr { } #define DEFINE_IDR(name) struct idr name = IDR_INIT(name) -/* Actions to be taken after a call to _idr_sub_alloc */ -#define IDR_NEED_TO_GROW -2 -#define IDR_NOMORE_SPACE -3 - -#define _idr_rc_to_errno(rc) ((rc) == -1 ? -EAGAIN : -ENOSPC) - /** * DOC: idr sync * idr synchronization (stolen from radix-tree.h) -- cgit v1.2.3 From d5c7409f79e14db49d00785692334657592c07ff Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 27 Feb 2013 17:03:55 -0800 Subject: idr: implement idr_preload[_end]() and idr_alloc() The current idr interface is very cumbersome. * For all allocations, two function calls - idr_pre_get() and idr_get_new*() - should be made. * idr_pre_get() doesn't guarantee that the following idr_get_new*() will not fail from memory shortage. If idr_get_new*() returns -EAGAIN, the caller is expected to retry pre_get and allocation. * idr_get_new*() can't enforce upper limit. Upper limit can only be enforced by allocating and then freeing if above limit. * idr_layer buffer is unnecessarily per-idr. Each idr ends up keeping around MAX_IDR_FREE idr_layers. The memory consumed per idr is under two pages but it makes it difficult to make idr_layer larger. This patch implements the following new set of allocation functions. * idr_preload[_end]() - Similar to radix preload but doesn't fail. The first idr_alloc() inside preload section can be treated as if it were called with @gfp_mask used for idr_preload(). * idr_alloc() - Allocate an ID w/ lower and upper limits. Takes @gfp_flags and can be used w/o preloading. When used inside preloaded section, the allocation mask of preloading can be assumed. If idr_alloc() can be called from a context which allows sufficiently relaxed @gfp_mask, it can be used by itself. If, for example, idr_alloc() is called inside spinlock protected region, preloading can be used like the following. idr_preload(GFP_KERNEL); spin_lock(lock); id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT); spin_unlock(lock); idr_preload_end(); if (id < 0) error; which is much simpler and less error-prone than idr_pre_get and idr_get_new*() loop. The new interface uses per-pcu idr_layer buffer and thus the number of idr's in the system doesn't affect the amount of memory used for preloading. idr_layer_alloc() is introduced to handle idr_layer allocations for both old and new ID allocation paths. This is a bit hairy now but the new interface is expected to replace the old and the internal implementation eventually will become simpler. Signed-off-by: Tejun Heo Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 837f152b1383..6dcf133f208a 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -94,14 +94,28 @@ struct idr { void *idr_find(struct idr *idp, int id); int idr_pre_get(struct idr *idp, gfp_t gfp_mask); int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id); +void idr_preload(gfp_t gfp_mask); +int idr_alloc(struct idr *idp, void *ptr, int start, int end, gfp_t gfp_mask); int idr_for_each(struct idr *idp, int (*fn)(int id, void *p, void *data), void *data); void *idr_get_next(struct idr *idp, int *nextid); void *idr_replace(struct idr *idp, void *ptr, int id); void idr_remove(struct idr *idp, int id); +void idr_free(struct idr *idp, int id); void idr_destroy(struct idr *idp); void idr_init(struct idr *idp); +/** + * idr_preload_end - end preload section started with idr_preload() + * + * Each idr_preload() should be matched with an invocation of this + * function. See idr_preload() for details. + */ +static inline void idr_preload_end(void) +{ + preempt_enable(); +} + /** * idr_get_new - allocate new idr entry * @idp: idr handle -- cgit v1.2.3 From e8c8d1bc063bc88cfa1356266027b5075d3a82d7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 27 Feb 2013 17:05:04 -0800 Subject: idr: remove MAX_IDR_MASK and move left MAX_IDR_* into idr.c MAX_IDR_MASK is another weirdness in the idr interface. As idr covers whole positive integer range, it's defined as 0x7fffffff or INT_MAX. Its usage in idr_find(), idr_replace() and idr_remove() is bizarre. They basically mask off the sign bit and operate on the rest, so if the caller, by accident, passes in a negative number, the sign bit will be masked off and the remaining part will be used as if that was the input, which is worse than crashing. The constant is visible in idr.h and there are several users in the kernel. * drivers/i2c/i2c-core.c:i2c_add_numbered_adapter() Basically used to test if adap->nr is a negative number which isn't -1 and returns -EINVAL if so. idr_alloc() already has negative @start checking (w/ WARN_ON_ONCE), so this can go away. * drivers/infiniband/core/cm.c:cm_alloc_id() drivers/infiniband/hw/mlx4/cm.c:id_map_alloc() Used to wrap cyclic @start. Can be replaced with max(next, 0). Note that this type of cyclic allocation using idr is buggy. These are prone to spurious -ENOSPC failure after the first wraparound. * fs/super.c:get_anon_bdev() The ID allocated from ida is masked off before being tested whether it's inside valid range. ida allocated ID can never be a negative number and the masking is unnecessary. Update idr_*() functions to fail with -EINVAL when negative @id is specified and update other MAX_IDR_MASK users as described above. This leaves MAX_IDR_MASK without any user, remove it and relocate other MAX_IDR_* constants to lib/idr.c. Signed-off-by: Tejun Heo Cc: Jean Delvare Cc: Roland Dreier Cc: Sean Hefty Cc: Hal Rosenstock Cc: "Marciniszyn, Mike" Cc: Jack Morgenstein Cc: Or Gerlitz Cc: Al Viro Acked-by: Wolfram Sang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 6dcf133f208a..99b0ce533f0e 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -38,16 +38,6 @@ #define IDR_SIZE (1 << IDR_BITS) #define IDR_MASK ((1 << IDR_BITS)-1) -#define MAX_IDR_SHIFT (sizeof(int)*8 - 1) -#define MAX_IDR_BIT (1U << MAX_IDR_SHIFT) -#define MAX_IDR_MASK (MAX_IDR_BIT - 1) - -/* Leave the possibility of an incomplete final layer */ -#define MAX_IDR_LEVEL ((MAX_IDR_SHIFT + IDR_BITS - 1) / IDR_BITS) - -/* Number of id_layer structs to leave in free list */ -#define MAX_IDR_FREE (MAX_IDR_LEVEL * 2) - struct idr_layer { unsigned long bitmap; /* A zero bit means "space here" */ struct idr_layer __rcu *ary[1< Date: Wed, 27 Feb 2013 17:05:05 -0800 Subject: idr: remove length restriction from idr_layer->bitmap Currently, idr->bitmap is declared as an unsigned long which restricts the number of bits an idr_layer can contain. All bitops can handle arbitrary positive integer bit number and there's no reason for this restriction. Declare idr_layer->bitmap using DECLARE_BITMAP() instead of a single unsigned long. * idr_layer->bitmap is now an array. '&' dropped from params to bitops. * Replaced "== IDR_FULL" tests with bitmap_full() and removed IDR_FULL. * Replaced find_next_bit() on ~bitmap with find_next_zero_bit(). * Replaced "bitmap = 0" with bitmap_clear(). This patch doesn't (or at least shouldn't) introduce any behavior changes. [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 99b0ce533f0e..63aa542da49b 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -19,18 +19,8 @@ #if BITS_PER_LONG == 32 # define IDR_BITS 5 -# define IDR_FULL 0xfffffffful -/* We can only use two of the bits in the top level because there is - only one possible bit in the top level (5 bits * 7 levels = 35 - bits, but you only use 31 bits in the id). */ -# define TOP_LEVEL_FULL (IDR_FULL >> 30) #elif BITS_PER_LONG == 64 # define IDR_BITS 6 -# define IDR_FULL 0xfffffffffffffffful -/* We can only use two of the bits in the top level because there is - only one possible bit in the top level (6 bits * 6 levels = 36 - bits, but you only use 31 bits in the id). */ -# define TOP_LEVEL_FULL (IDR_FULL >> 62) #else # error "BITS_PER_LONG is not 32 or 64" #endif @@ -39,7 +29,7 @@ #define IDR_MASK ((1 << IDR_BITS)-1) struct idr_layer { - unsigned long bitmap; /* A zero bit means "space here" */ + DECLARE_BITMAP(bitmap, IDR_SIZE); /* A zero bit means "space here" */ struct idr_layer __rcu *ary[1< Date: Wed, 27 Feb 2013 17:05:06 -0800 Subject: idr: make idr_layer larger With recent preloading changes, idr no longer keeps full layer cache per each idr instance (used to be ~6.5k per idr on 64bit) and the previous patch removed restriction on the bitmap size. Both now allow us to have larger layers. Increase IDR_BITS to 8 regardless of BITS_PER_LONG. Each layer is slightly larger than 2k on 64bit and 1k on 32bit and carries 256 entries. The size isn't too large, especially compared to what we used to waste on per-idr caches, and 256 entries should be able to serve most use cases with single layer. The max tree depth is 4 which is much better than the previous 6 on 64bit and 7 on 32bit. Signed-off-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 63aa542da49b..43b87b1c77a3 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -17,14 +17,13 @@ #include #include -#if BITS_PER_LONG == 32 -# define IDR_BITS 5 -#elif BITS_PER_LONG == 64 -# define IDR_BITS 6 -#else -# error "BITS_PER_LONG is not 32 or 64" -#endif - +/* + * We want shallower trees and thus more bits covered at each layer. 8 + * bits gives us large enough first layer for most use cases and maximum + * tree depth of 4. Each idr_layer is slightly larger than 2k on 64bit and + * 1k on 32bit. + */ +#define IDR_BITS 8 #define IDR_SIZE (1 << IDR_BITS) #define IDR_MASK ((1 << IDR_BITS)-1) -- cgit v1.2.3 From 54616283c2948812a44240858ced610e7cacbde1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 27 Feb 2013 17:05:07 -0800 Subject: idr: add idr_layer->prefix Add a field which carries the prefix of ID the idr_layer covers. This will be used to implement lookup hint. This patch doesn't make use of the new field and doesn't introduce any behavior difference. Signed-off-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 43b87b1c77a3..7b1c5c6f9a06 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -28,6 +28,7 @@ #define IDR_MASK ((1 << IDR_BITS)-1) struct idr_layer { + int prefix; /* the ID prefix of this idr_layer */ DECLARE_BITMAP(bitmap, IDR_SIZE); /* A zero bit means "space here" */ struct idr_layer __rcu *ary[1< Date: Wed, 27 Feb 2013 17:05:08 -0800 Subject: idr: implement lookup hint While idr lookup isn't a particularly heavy operation, it still is too substantial to use in hot paths without worrying about the performance implications. With recent changes, each idr_layer covers 256 slots which should be enough to cover most use cases with single idr_layer making lookup hint very attractive. This patch adds idr->hint which points to the idr_layer which allocated an ID most recently and the fast path lookup becomes if (look up target's prefix matches that of the hinted layer) return hint->ary[ID's offset in the leaf layer]; which can be inlined. idr->hint is set to the leaf node on idr_fill_slot() and cleared from free_layer(). [andriy.shevchenko@linux.intel.com: always do slow path when hint is uninitialized] Signed-off-by: Tejun Heo Cc: Kirill A. Shutemov Cc: Sasha Levin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 7b1c5c6f9a06..a6f38b5c34e4 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -37,6 +37,7 @@ struct idr_layer { }; struct idr { + struct idr_layer __rcu *hint; /* the last layer allocated from */ struct idr_layer __rcu *top; struct idr_layer *id_free; int layers; /* only valid w/o concurrent changes */ @@ -71,7 +72,7 @@ struct idr { * This is what we export. */ -void *idr_find(struct idr *idp, int id); +void *idr_find_slowpath(struct idr *idp, int id); int idr_pre_get(struct idr *idp, gfp_t gfp_mask); int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id); void idr_preload(gfp_t gfp_mask); @@ -96,6 +97,28 @@ static inline void idr_preload_end(void) preempt_enable(); } +/** + * idr_find - return pointer for given id + * @idp: idr handle + * @id: lookup key + * + * Return the pointer given the id it has been registered with. A %NULL + * return indicates that @id is not valid or you passed %NULL in + * idr_get_new(). + * + * This function can be called under rcu_read_lock(), given that the leaf + * pointers lifetimes are correctly managed. + */ +static inline void *idr_find(struct idr *idr, int id) +{ + struct idr_layer *hint = rcu_dereference_raw(idr->hint); + + if (hint && (id & ~IDR_MASK) == hint->prefix) + return rcu_dereference_raw(hint->ary[id & IDR_MASK]); + + return idr_find_slowpath(idr, id); +} + /** * idr_get_new - allocate new idr entry * @idp: idr handle -- cgit v1.2.3 From 59fb1b9f5d9910c2eb97107dd0eb7e3bce8f0dde Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Wed, 27 Feb 2013 17:05:11 -0800 Subject: ipmi: remove superfluous kernel/userspace explanation Given the obvious distinction between kernel and userspace supported by uapi/, it seems unnecessary to comment on that. Signed-off-by: Robert P. J. Day Signed-off-by: Corey Minyard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipmi.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 1487e7906bbd..1f9f56e28851 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -35,10 +35,6 @@ #include - -/* - * The in-kernel interface. - */ #include #include -- cgit v1.2.3 From 1d730c49a91dc5b7660269b98ad76e5a9b85740f Mon Sep 17 00:00:00 2001 From: Martin Sustrik Date: Wed, 27 Feb 2013 17:05:42 -0800 Subject: include/linux/eventfd.h: fix incorrect filename is a comment Comment in eventfd.h referred to 'include/asm-generic/fcntl.h' while the correct path is 'include/uapi/asm-generic/fcntl.h'. Signed-off-by: Martin Sustrik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/eventfd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 3c3ef19a625a..cf5d2af61b81 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -13,7 +13,7 @@ #include /* - * CAREFUL: Check include/asm-generic/fcntl.h when defining + * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining * new flags, since they might collide with O_* ones. We want * to re-use O_* flags that couldn't possibly have a meaning * from eventfd, in order to leave a free define-space for -- cgit v1.2.3 From b67bfe0d42cac56c512dd5da4b1b347a23f4b70a Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Wed, 27 Feb 2013 17:06:00 -0800 Subject: hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin Acked-by: Paul E. McKenney Signed-off-by: Sasha Levin Cc: Wu Fengguang Cc: Marcelo Tosatti Cc: Gleb Natapov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hashtable.h | 40 ++++++++++++++++----------------- include/linux/if_team.h | 6 ++--- include/linux/list.h | 49 +++++++++++++++++++---------------------- include/linux/pid.h | 3 +-- include/linux/rculist.h | 56 +++++++++++++++++++++++------------------------ 5 files changed, 72 insertions(+), 82 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hashtable.h b/include/linux/hashtable.h index 227c62424f3c..a9df51f5d54c 100644 --- a/include/linux/hashtable.h +++ b/include/linux/hashtable.h @@ -115,51 +115,50 @@ static inline void hash_del_rcu(struct hlist_node *node) * hash_for_each - iterate over a hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor - * @node: the &struct list_head to use as a loop cursor for each entry * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ -#define hash_for_each(name, bkt, node, obj, member) \ - for ((bkt) = 0, node = NULL; node == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\ - hlist_for_each_entry(obj, node, &name[bkt], member) +#define hash_for_each(name, bkt, obj, member) \ + for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ + (bkt)++)\ + hlist_for_each_entry(obj, &name[bkt], member) /** * hash_for_each_rcu - iterate over a rcu enabled hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor - * @node: the &struct list_head to use as a loop cursor for each entry * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ -#define hash_for_each_rcu(name, bkt, node, obj, member) \ - for ((bkt) = 0, node = NULL; node == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\ - hlist_for_each_entry_rcu(obj, node, &name[bkt], member) +#define hash_for_each_rcu(name, bkt, obj, member) \ + for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ + (bkt)++)\ + hlist_for_each_entry_rcu(obj, &name[bkt], member) /** * hash_for_each_safe - iterate over a hashtable safe against removal of * hash entry * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor - * @node: the &struct list_head to use as a loop cursor for each entry * @tmp: a &struct used for temporary storage * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ -#define hash_for_each_safe(name, bkt, node, tmp, obj, member) \ - for ((bkt) = 0, node = NULL; node == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\ - hlist_for_each_entry_safe(obj, node, tmp, &name[bkt], member) +#define hash_for_each_safe(name, bkt, tmp, obj, member) \ + for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ + (bkt)++)\ + hlist_for_each_entry_safe(obj, tmp, &name[bkt], member) /** * hash_for_each_possible - iterate over all possible objects hashing to the * same bucket * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry - * @node: the &struct list_head to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ -#define hash_for_each_possible(name, obj, node, member, key) \ - hlist_for_each_entry(obj, node, &name[hash_min(key, HASH_BITS(name))], member) +#define hash_for_each_possible(name, obj, member, key) \ + hlist_for_each_entry(obj, &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_rcu - iterate over all possible objects hashing to the @@ -167,25 +166,24 @@ static inline void hash_del_rcu(struct hlist_node *node) * in a rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry - * @node: the &struct list_head to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ -#define hash_for_each_possible_rcu(name, obj, node, member, key) \ - hlist_for_each_entry_rcu(obj, node, &name[hash_min(key, HASH_BITS(name))], member) +#define hash_for_each_possible_rcu(name, obj, member, key) \ + hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))],\ + member) /** * hash_for_each_possible_safe - iterate over all possible objects hashing to the * same bucket safe against removals * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry - * @node: the &struct list_head to use as a loop cursor for each entry * @tmp: a &struct used for temporary storage * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ -#define hash_for_each_possible_safe(name, obj, node, tmp, member, key) \ - hlist_for_each_entry_safe(obj, node, tmp, \ +#define hash_for_each_possible_safe(name, obj, tmp, member, key) \ + hlist_for_each_entry_safe(obj, tmp,\ &name[hash_min(key, HASH_BITS(name))], member) diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 4648d8021244..cfd21e3d5506 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -216,11 +216,10 @@ static inline struct hlist_head *team_port_index_hash(struct team *team, static inline struct team_port *team_get_port_by_index(struct team *team, int port_index) { - struct hlist_node *p; struct team_port *port; struct hlist_head *head = team_port_index_hash(team, port_index); - hlist_for_each_entry(port, p, head, hlist) + hlist_for_each_entry(port, head, hlist) if (port->index == port_index) return port; return NULL; @@ -228,11 +227,10 @@ static inline struct team_port *team_get_port_by_index(struct team *team, static inline struct team_port *team_get_port_by_index_rcu(struct team *team, int port_index) { - struct hlist_node *p; struct team_port *port; struct hlist_head *head = team_port_index_hash(team, port_index); - hlist_for_each_entry_rcu(port, p, head, hlist) + hlist_for_each_entry_rcu(port, head, hlist) if (port->index == port_index) return port; return NULL; diff --git a/include/linux/list.h b/include/linux/list.h index cc6d2aa6b415..d991cc147c98 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -666,54 +666,49 @@ static inline void hlist_move_list(struct hlist_head *old, for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ pos = n) +#define hlist_entry_safe(ptr, type, member) \ + (ptr) ? hlist_entry(ptr, type, member) : NULL + /** * hlist_for_each_entry - iterate over list of given type - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ -#define hlist_for_each_entry(tpos, pos, head, member) \ - for (pos = (head)->first; \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = pos->next) +#define hlist_for_each_entry(pos, head, member) \ + for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\ + pos; \ + pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_continue - iterate over a hlist continuing after current point - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ -#define hlist_for_each_entry_continue(tpos, pos, member) \ - for (pos = (pos)->next; \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = pos->next) +#define hlist_for_each_entry_continue(pos, member) \ + for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\ + pos; \ + pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_from - iterate over a hlist continuing from current point - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ -#define hlist_for_each_entry_from(tpos, pos, member) \ - for (; pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = pos->next) +#define hlist_for_each_entry_from(pos, member) \ + for (; pos; \ + pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @n: another &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ -#define hlist_for_each_entry_safe(tpos, pos, n, head, member) \ - for (pos = (head)->first; \ - pos && ({ n = pos->next; 1; }) && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = n) +#define hlist_for_each_entry_safe(pos, n, head, member) \ + for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\ + pos && ({ n = pos->member.next; 1; }); \ + pos = hlist_entry_safe(n, typeof(*pos), member)) #endif diff --git a/include/linux/pid.h b/include/linux/pid.h index 2381c973d897..a089a3c447fc 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -176,9 +176,8 @@ pid_t pid_vnr(struct pid *pid); #define do_each_pid_task(pid, type, task) \ do { \ - struct hlist_node *pos___; \ if ((pid) != NULL) \ - hlist_for_each_entry_rcu((task), pos___, \ + hlist_for_each_entry_rcu((task), \ &(pid)->tasks[type], pids[type].node) { /* diff --git a/include/linux/rculist.h b/include/linux/rculist.h index c92dd28eaa6c..8089e35d47ac 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -445,8 +445,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, /** * hlist_for_each_entry_rcu - iterate over rcu list of given type - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @@ -454,16 +453,16 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ -#define hlist_for_each_entry_rcu(tpos, pos, head, member) \ - for (pos = rcu_dereference_raw(hlist_first_rcu(head)); \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ - pos = rcu_dereference_raw(hlist_next_rcu(pos))) +#define hlist_for_each_entry_rcu(pos, head, member) \ + for (pos = hlist_entry_safe (rcu_dereference_raw(hlist_first_rcu(head)),\ + typeof(*(pos)), member); \ + pos; \ + pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ + &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @@ -471,35 +470,36 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ -#define hlist_for_each_entry_rcu_bh(tpos, pos, head, member) \ - for (pos = rcu_dereference_bh((head)->first); \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ - pos = rcu_dereference_bh(pos->next)) +#define hlist_for_each_entry_rcu_bh(pos, head, member) \ + for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\ + typeof(*(pos)), member); \ + pos; \ + pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\ + &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ -#define hlist_for_each_entry_continue_rcu(tpos, pos, member) \ - for (pos = rcu_dereference((pos)->next); \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ - pos = rcu_dereference(pos->next)) +#define hlist_for_each_entry_continue_rcu(pos, member) \ + for (pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\ + typeof(*(pos)), member); \ + pos; \ + pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\ + typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ -#define hlist_for_each_entry_continue_rcu_bh(tpos, pos, member) \ - for (pos = rcu_dereference_bh((pos)->next); \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ - pos = rcu_dereference_bh(pos->next)) +#define hlist_for_each_entry_continue_rcu_bh(pos, member) \ + for (pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\ + typeof(*(pos)), member); \ + pos; \ + pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\ + typeof(*(pos)), member)) #endif /* __KERNEL__ */ -- cgit v1.2.3 From f9c6a655a94042f94c0adb30d07d93cfd8915e95 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 27 Feb 2013 21:36:03 +0000 Subject: dmaengine: dw_dmac: move to generic DMA binding The original device tree binding for this driver, from Viresh Kumar unfortunately conflicted with the generic DMA binding, and did not allow to completely seperate slave device configuration from the controller. This is an attempt to replace it with an implementation of the generic binding, but it is currently completely untested, because I do not have any hardware with this particular controller. The patch applies on top of the slave-dma tree, which contains both the base support for the generic DMA binding, as well as the earlier attempt from Viresh. Both of these are currently not merged upstream however. This version incorporates feedback from Viresh Kumar, Andy Shevchenko and Russell King. Signed-off-by: Arnd Bergmann Acked-by: Viresh Kumar Acked-by: Andy Shevchenko Cc: Vinod Koul Cc: devicetree-discuss@lists.ozlabs.org Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Vinod Koul --- include/linux/dw_dmac.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h index 41766de66e33..481ab2345d6b 100644 --- a/include/linux/dw_dmac.h +++ b/include/linux/dw_dmac.h @@ -27,7 +27,6 @@ */ struct dw_dma_slave { struct device *dma_dev; - const char *bus_id; u32 cfg_hi; u32 cfg_lo; u8 src_master; @@ -60,9 +59,6 @@ struct dw_dma_platform_data { unsigned short block_size; unsigned char nr_masters; unsigned char data_width[4]; - - struct dw_dma_slave *sd; - unsigned int sd_count; }; /* bursts size */ @@ -114,6 +110,5 @@ void dw_dma_cyclic_stop(struct dma_chan *chan); dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan); dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan); -bool dw_dma_generic_filter(struct dma_chan *chan, void *param); #endif /* DW_DMAC_H */ -- cgit v1.2.3 From edddbb1eda61753c886a3c5e159293a7b3a9e30a Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Thu, 28 Feb 2013 20:30:09 -0500 Subject: SUNRPC: add call to get configured timeout Returns the configured timeout for the xprt of the rpc client. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 34206b84d8da..21d52d0dc15c 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,6 +160,7 @@ void rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int); int rpc_protocol(struct rpc_clnt *); struct net * rpc_net_ns(struct rpc_clnt *); size_t rpc_max_payload(struct rpc_clnt *); +unsigned long rpc_get_timeout(struct rpc_clnt *clnt); void rpc_force_rebind(struct rpc_clnt *); size_t rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t); const char *rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t); -- cgit v1.2.3 From 3000512137602b84d1ad5fd89d62984993a19bb6 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Thu, 28 Feb 2013 20:30:10 -0500 Subject: NFSv4.1: LAYOUTGET EDELAY loops timeout to the MDS The client will currently try LAYOUTGETs forever if a server is returning NFS4ERR_LAYOUTTRYLATER or NFS4ERR_RECALLCONFLICT - even if the client no longer needs the layout (ie process killed, unmounted). This patch uses the DS timeout value (module parameter 'dataserver_timeo' via rpc layer) to set an upper limit of how long the client tries LATOUTGETs in this situation. Once the timeout is reached, IO is redirected to the MDS. This also changes how the client checks if a layout is on the clp list to avoid a double list_add. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 29adb12c7ecf..2250cab6fc4b 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -233,6 +233,7 @@ struct nfs4_layoutget_args { struct inode *inode; struct nfs_open_context *ctx; nfs4_stateid stateid; + unsigned long timestamp; struct nfs4_layoutdriver_data layout; }; -- cgit v1.2.3 From 5838b032fd69ae47565ddc50062decf9055e1628 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Thu, 28 Feb 2013 18:12:47 -0600 Subject: regulator: core: update kernel documentation for regulator_desc commit df367931 (regulator: core: Provide regmap get/set bypass operations) introduced regulator_[gs]et_bypass_regmap However structure documentation for regulator_desc needs an update. ./scripts/kernel-doc include/linux/regulator/driver.h >/dev/null generates: Warning(include/linux/regulator/driver.h:233): No description found for parameter 'bypass_reg' Warning(include/linux/regulator/driver.h:233): No description found for parameter 'bypass_mask' Cc: Liam Girdwood Cc: Mark Brown Cc: linux-kernel@vger.kernel.org Signed-off-by: Nishanth Menon Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 23070fd83872..7df93f52db08 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -199,6 +199,8 @@ enum regulator_type { * output when using regulator_set_voltage_sel_regmap * @enable_reg: Register for control when using regmap enable/disable ops * @enable_mask: Mask for control when using regmap enable/disable ops + * @bypass_reg: Register for control when using regmap set_bypass + * @bypass_mask: Mask for control when using regmap set_bypass * * @enable_time: Time taken for initial enable of regulator (in uS). */ -- cgit v1.2.3 From 1a71fb84fda651105e1e194c2d3a3a13a38210a9 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 27 Sep 2011 22:21:37 +0200 Subject: rtc: stmp3xxx: add wdt-accessor function This RTC also includes a watchdog timer. Provide an accessor function for setting the watchdog timeout value which will be picked up by a watchdog driver. Also register the platform_device for the watchdog here to get the boot-time dependencies right. Signed-off-by: Wolfram Sang Acked-by: Andrew Morton Signed-off-by: Wim Van Sebroeck --- include/linux/stmp3xxx_rtc_wdt.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/linux/stmp3xxx_rtc_wdt.h (limited to 'include/linux') diff --git a/include/linux/stmp3xxx_rtc_wdt.h b/include/linux/stmp3xxx_rtc_wdt.h new file mode 100644 index 000000000000..1dd12c96231b --- /dev/null +++ b/include/linux/stmp3xxx_rtc_wdt.h @@ -0,0 +1,15 @@ +/* + * stmp3xxx_rtc_wdt.h + * + * Copyright (C) 2011 Wolfram Sang, Pengutronix e.K. + * + * This file is released under the GPLv2. + */ +#ifndef __LINUX_STMP3XXX_RTC_WDT_H +#define __LINUX_STMP3XXX_RTC_WDT_H + +struct stmp3xxx_wdt_pdata { + void (*wdt_set_timeout)(struct device *dev, u32 timeout); +}; + +#endif /* __LINUX_STMP3XXX_RTC_WDT_H */ -- cgit v1.2.3 From f82dedf812ecdf0c19c6c240e85a4a487ab62016 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Thu, 24 Jan 2013 18:13:34 +0100 Subject: watchdog: bcm47xx_wdt.c: use platform device Instead of accessing the function to set the watchdog timer directly, register a platform driver the platform could register to use this watchdog driver. Signed-off-by: Hauke Mehrtens Signed-off-by: Wim Van Sebroeck --- include/linux/bcm47xx_wdt.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcm47xx_wdt.h b/include/linux/bcm47xx_wdt.h index e5dfc256485b..b708786d4cbf 100644 --- a/include/linux/bcm47xx_wdt.h +++ b/include/linux/bcm47xx_wdt.h @@ -1,7 +1,10 @@ #ifndef LINUX_BCM47XX_WDT_H_ #define LINUX_BCM47XX_WDT_H_ +#include +#include #include +#include struct bcm47xx_wdt { @@ -10,6 +13,12 @@ struct bcm47xx_wdt { u32 max_timer_ms; void *driver_data; + + struct watchdog_device wdd; + struct notifier_block notifier; + + struct timer_list soft_timer; + atomic_t soft_ticks; }; static inline void *bcm47xx_wdt_get_drvdata(struct bcm47xx_wdt *wdt) -- cgit v1.2.3 From 3048253ed957fc6cdc34599178408559aa1e0062 Mon Sep 17 00:00:00 2001 From: Fabio Porcedda Date: Tue, 8 Jan 2013 11:04:10 +0100 Subject: watchdog: core: dt: add support for the timeout-sec dt property Add support for watchdog drivers to initialize/set the timeout field of the watchdog_device structure. The timeout field is initialised either with the module timeout parameter value (if valid) or with the timeout-sec dt property (if valid). If both are invalid the initial value is unchanged. Signed-off-by: Fabio Porcedda Acked-by: Nicolas Ferre Signed-off-by: Wim Van Sebroeck --- include/linux/watchdog.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 3a9df2f43be6..2a3038ee17a3 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -118,6 +118,13 @@ static inline void watchdog_set_nowayout(struct watchdog_device *wdd, bool noway set_bit(WDOG_NO_WAY_OUT, &wdd->status); } +/* Use the following function to check if a timeout value is invalid */ +static inline bool watchdog_timeout_invalid(struct watchdog_device *wdd, unsigned int t) +{ + return ((wdd->max_timeout != 0) && + (t < wdd->min_timeout || t > wdd->max_timeout)); +} + /* Use the following functions to manipulate watchdog driver specific data */ static inline void watchdog_set_drvdata(struct watchdog_device *wdd, void *data) { @@ -130,6 +137,8 @@ static inline void *watchdog_get_drvdata(struct watchdog_device *wdd) } /* drivers/watchdog/watchdog_core.c */ +extern int watchdog_init_timeout(struct watchdog_device *wdd, + unsigned int timeout_parm, struct device *dev); extern int watchdog_register_device(struct watchdog_device *); extern void watchdog_unregister_device(struct watchdog_device *); -- cgit v1.2.3 From 8eae508b7c6ff502a71d0293b69e97c5505d5840 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 1 Mar 2013 11:11:47 -0800 Subject: hsi: fix kernel-doc warnings Fix kernel-doc warnings in hsi files: Warning(include/linux/hsi/hsi.h:136): Excess struct/union/enum/typedef member 'e_handler' description in 'hsi_client' Warning(include/linux/hsi/hsi.h:136): Excess struct/union/enum/typedef member 'pclaimed' description in 'hsi_client' Warning(include/linux/hsi/hsi.h:136): Excess struct/union/enum/typedef member 'nb' description in 'hsi_client' Warning(drivers/hsi/hsi.c:434): No description found for parameter 'handler' Warning(drivers/hsi/hsi.c:434): Excess function parameter 'cb' description in 'hsi_register_port_event' Don't document "private:" fields with kernel-doc notation. If you want to leave them fully documented, that's OK, but then don't mark them as "private:". Signed-off-by: Randy Dunlap Cc: Carlos Chinea Cc: Linus Walleij Cc: Greg Kroah-Hartman Cc: linux-kernel@vger.kernel.org Cc: linux-omap@vger.kernel.org Acked-by: Nishanth Menon Signed-off-by: Linus Torvalds --- include/linux/hsi/hsi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hsi/hsi.h b/include/linux/hsi/hsi.h index 56fae865e272..0dca785288cf 100644 --- a/include/linux/hsi/hsi.h +++ b/include/linux/hsi/hsi.h @@ -121,9 +121,9 @@ static inline int hsi_register_board_info(struct hsi_board_info const *info, * @device: Driver model representation of the device * @tx_cfg: HSI TX configuration * @rx_cfg: HSI RX configuration - * @e_handler: Callback for handling port events (RX Wake High/Low) - * @pclaimed: Keeps tracks if the clients claimed its associated HSI port - * @nb: Notifier block for port events + * e_handler: Callback for handling port events (RX Wake High/Low) + * pclaimed: Keeps tracks if the clients claimed its associated HSI port + * nb: Notifier block for port events */ struct hsi_client { struct device device; -- cgit v1.2.3 From fd7c092e711ebab55b2688d3859d95dfd0301f73 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Fri, 1 Mar 2013 22:45:44 +0000 Subject: dm: fix truncated status strings Avoid returning a truncated table or status string instead of setting the DM_BUFFER_FULL_FLAG when the last target of a table fills the buffer. When processing a table or status request, the function retrieve_status calls ti->type->status. If ti->type->status returns non-zero, retrieve_status assumes that the buffer overflowed and sets DM_BUFFER_FULL_FLAG. However, targets don't return non-zero values from their status method on overflow. Most targets returns always zero. If a buffer overflow happens in a target that is not the last in the table, it gets noticed during the next iteration of the loop in retrieve_status; but if a buffer overflow happens in the last target, it goes unnoticed and erroneously truncated data is returned. In the current code, the targets behave in the following way: * dm-crypt returns -ENOMEM if there is not enough space to store the key, but it returns 0 on all other overflows. * dm-thin returns errors from the status method if a disk error happened. This is incorrect because retrieve_status doesn't check the error code, it assumes that all non-zero values mean buffer overflow. * all the other targets always return 0. This patch changes the ti->type->status function to return void (because most targets don't use the return code). Overflow is detected in retrieve_status: if the status method fills up the remaining space completely, it is assumed that buffer overflow happened. Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index bf6afa2fc432..a5cda3ea6b88 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -68,8 +68,8 @@ typedef void (*dm_postsuspend_fn) (struct dm_target *ti); typedef int (*dm_preresume_fn) (struct dm_target *ti); typedef void (*dm_resume_fn) (struct dm_target *ti); -typedef int (*dm_status_fn) (struct dm_target *ti, status_type_t status_type, - unsigned status_flags, char *result, unsigned maxlen); +typedef void (*dm_status_fn) (struct dm_target *ti, status_type_t status_type, + unsigned status_flags, char *result, unsigned maxlen); typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv); -- cgit v1.2.3 From 55a62eef8d1b50ceff3b7bf46851103bdcc7e5b0 Mon Sep 17 00:00:00 2001 From: Alasdair G Kergon Date: Fri, 1 Mar 2013 22:45:47 +0000 Subject: dm: rename request variables to bios Use 'bio' in the name of variables and functions that deal with bios rather than 'request' to avoid confusion with the normal block layer use of 'request'. No functional changes. Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index a5cda3ea6b88..d5f984b07466 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -187,26 +187,26 @@ struct dm_target { uint32_t max_io_len; /* - * A number of zero-length barrier requests that will be submitted + * A number of zero-length barrier bios that will be submitted * to the target for the purpose of flushing cache. * - * The request number can be accessed with dm_bio_get_target_request_nr. - * It is a responsibility of the target driver to remap these requests + * The bio number can be accessed with dm_bio_get_target_bio_nr. + * It is a responsibility of the target driver to remap these bios * to the real underlying devices. */ - unsigned num_flush_requests; + unsigned num_flush_bios; /* - * The number of discard requests that will be submitted to the target. - * The request number can be accessed with dm_bio_get_target_request_nr. + * The number of discard bios that will be submitted to the target. + * The bio number can be accessed with dm_bio_get_target_bio_nr. */ - unsigned num_discard_requests; + unsigned num_discard_bios; /* - * The number of WRITE SAME requests that will be submitted to the target. - * The request number can be accessed with dm_bio_get_target_request_nr. + * The number of WRITE SAME bios that will be submitted to the target. + * The bio number can be accessed with dm_bio_get_target_bio_nr. */ - unsigned num_write_same_requests; + unsigned num_write_same_bios; /* * The minimum number of extra bytes allocated in each bio for the @@ -233,10 +233,10 @@ struct dm_target { bool discards_supported:1; /* - * Set if the target required discard request to be split + * Set if the target required discard bios to be split * on max_io_len boundary. */ - bool split_discard_requests:1; + bool split_discard_bios:1; /* * Set if this target does not return zeroes on discarded blocks. @@ -261,7 +261,7 @@ struct dm_target_io { struct dm_io *io; struct dm_target *ti; union map_info info; - unsigned target_request_nr; + unsigned target_bio_nr; struct bio clone; }; @@ -275,9 +275,9 @@ static inline struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size) return (struct bio *)((char *)data + data_size + offsetof(struct dm_target_io, clone)); } -static inline unsigned dm_bio_get_target_request_nr(const struct bio *bio) +static inline unsigned dm_bio_get_target_bio_nr(const struct bio *bio) { - return container_of(bio, struct dm_target_io, clone)->target_request_nr; + return container_of(bio, struct dm_target_io, clone)->target_bio_nr; } int dm_register_target(struct target_type *t); -- cgit v1.2.3 From df5d2e9089c7d5b8c46f767e4278610ea3e815b9 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Fri, 1 Mar 2013 22:45:49 +0000 Subject: dm kcopyd: introduce configurable throttling This patch allows the administrator to reduce the rate at which kcopyd issues I/O. Each module that uses kcopyd acquires a throttle parameter that can be set in /sys/module/*/parameters. We maintain a history of kcopyd usage by each module in the variables io_period and total_period in struct dm_kcopyd_throttle. The actual kcopyd activity is calculated as a percentage of time equal to "(100 * io_period / total_period)". This is compared with the user-defined throttle percentage threshold and if it is exceeded, we sleep. Signed-off-by: Mikulas Patocka Signed-off-by: Alasdair G Kergon --- include/linux/dm-kcopyd.h | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index 47d9d376e4e7..f486d636b82e 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -21,11 +21,34 @@ #define DM_KCOPYD_IGNORE_ERROR 1 +struct dm_kcopyd_throttle { + unsigned throttle; + unsigned num_io_jobs; + unsigned io_period; + unsigned total_period; + unsigned last_jiffies; +}; + +/* + * kcopyd clients that want to support throttling must pass an initialised + * dm_kcopyd_throttle struct into dm_kcopyd_client_create(). + * Two or more clients may share the same instance of this struct between + * them if they wish to be throttled as a group. + * + * This macro also creates a corresponding module parameter to configure + * the amount of throttling. + */ +#define DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(name, description) \ +static struct dm_kcopyd_throttle dm_kcopyd_throttle = { 100, 0, 0, 0, 0 }; \ +module_param_named(name, dm_kcopyd_throttle.throttle, uint, 0644); \ +MODULE_PARM_DESC(name, description) + /* * To use kcopyd you must first create a dm_kcopyd_client object. + * throttle can be NULL if you don't want any throttling. */ struct dm_kcopyd_client; -struct dm_kcopyd_client *dm_kcopyd_client_create(void); +struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *throttle); void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc); /* -- cgit v1.2.3 From b0d8ed4d96a26ef3ac54a4aa8911c9413070662e Mon Sep 17 00:00:00 2001 From: Alasdair G Kergon Date: Fri, 1 Mar 2013 22:45:49 +0000 Subject: dm: add target num_write_bios fn Add a num_write_bios function to struct target. If an instance of a target sets this, it will be queried before the target's mapping function is called on a write bio, and the response controls the number of copies of the write bio that the target will receive. This provides a convenient way for a target to send the same data to more than one device. The new cache target uses this in writethrough mode, to send the data both to the cache and the backing device. Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index d5f984b07466..1e483fa7afb4 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -175,6 +175,14 @@ struct target_type { #define DM_TARGET_IMMUTABLE 0x00000004 #define dm_target_is_immutable(type) ((type)->features & DM_TARGET_IMMUTABLE) +/* + * Some targets need to be sent the same WRITE bio severals times so + * that they can send copies of it to different devices. This function + * examines any supplied bio and returns the number of copies of it the + * target requires. + */ +typedef unsigned (*dm_num_write_bios_fn) (struct dm_target *ti, struct bio *bio); + struct dm_target { struct dm_table *table; struct target_type *type; @@ -214,6 +222,13 @@ struct dm_target { */ unsigned per_bio_data_size; + /* + * If defined, this function is called to find out how many + * duplicate bios should be sent to the target when writing + * data. + */ + dm_num_write_bios_fn num_write_bios; + /* target specific data */ void *private; -- cgit v1.2.3 From dd37978c50bc8b354e5c4633f69387f16572fdac Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 1 Mar 2013 19:48:30 -0500 Subject: cache the value of file_inode() in struct file Note that this thing does *not* contribute to inode refcount; it's pinned down by dentry. Signed-off-by: Al Viro --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4e686a099465..74a907b8b950 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -769,6 +769,7 @@ struct file { } f_u; struct path f_path; #define f_dentry f_path.dentry + struct inode *f_inode; /* cached value */ const struct file_operations *f_op; /* @@ -2217,7 +2218,7 @@ static inline bool execute_ok(struct inode *inode) static inline struct inode *file_inode(struct file *f) { - return f->f_path.dentry->d_inode; + return f->f_inode; } /* -- cgit v1.2.3 From dcf787f39162ce32ca325b3e784aba2d2444619a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 1 Mar 2013 23:51:07 -0500 Subject: constify path_get/path_put and fs_struct.c stuff Signed-off-by: Al Viro --- include/linux/fs_struct.h | 4 ++-- include/linux/path.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index d0ae3a84bcfb..729eded4b24f 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -17,8 +17,8 @@ struct fs_struct { extern struct kmem_cache *fs_cachep; extern void exit_fs(struct task_struct *); -extern void set_fs_root(struct fs_struct *, struct path *); -extern void set_fs_pwd(struct fs_struct *, struct path *); +extern void set_fs_root(struct fs_struct *, const struct path *); +extern void set_fs_pwd(struct fs_struct *, const struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); extern void free_fs_struct(struct fs_struct *); extern int unshare_fs_struct(void); diff --git a/include/linux/path.h b/include/linux/path.h index edc98dec6266..d1372186f431 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -9,8 +9,8 @@ struct path { struct dentry *dentry; }; -extern void path_get(struct path *); -extern void path_put(struct path *); +extern void path_get(const struct path *); +extern void path_put(const struct path *); static inline int path_equal(const struct path *path1, const struct path *path2) { -- cgit v1.2.3 From 20e6926dcbafa1b361f1c29d967688be14b6ca4b Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 1 Mar 2013 14:51:27 -0800 Subject: x86, ACPI, mm: Revert movablemem_map support Tim found: WARNING: at arch/x86/kernel/smpboot.c:324 topology_sane.isra.2+0x6f/0x80() Hardware name: S2600CP sched: CPU #1's llc-sibling CPU #0 is not on the same node! [node: 1 != 0]. Ignoring dependency. smpboot: Booting Node 1, Processors #1 Modules linked in: Pid: 0, comm: swapper/1 Not tainted 3.9.0-0-generic #1 Call Trace: set_cpu_sibling_map+0x279/0x449 start_secondary+0x11d/0x1e5 Don Morris reproduced on a HP z620 workstation, and bisected it to commit e8d195525809 ("acpi, memory-hotplug: parse SRAT before memblock is ready") It turns out movable_map has some problems, and it breaks several things 1. numa_init is called several times, NOT just for srat. so those nodes_clear(numa_nodes_parsed) memset(&numa_meminfo, 0, sizeof(numa_meminfo)) can not be just removed. Need to consider sequence is: numaq, srat, amd, dummy. and make fall back path working. 2. simply split acpi_numa_init to early_parse_srat. a. that early_parse_srat is NOT called for ia64, so you break ia64. b. for (i = 0; i < MAX_LOCAL_APIC; i++) set_apicid_to_node(i, NUMA_NO_NODE) still left in numa_init. So it will just clear result from early_parse_srat. it should be moved before that.... c. it breaks ACPI_TABLE_OVERIDE...as the acpi table scan is moved early before override from INITRD is settled. 3. that patch TITLE is total misleading, there is NO x86 in the title, but it changes critical x86 code. It caused x86 guys did not pay attention to find the problem early. Those patches really should be routed via tip/x86/mm. 4. after that commit, following range can not use movable ram: a. real_mode code.... well..funny, legacy Node0 [0,1M) could be hot-removed? b. initrd... it will be freed after booting, so it could be on movable... c. crashkernel for kdump...: looks like we can not put kdump kernel above 4G anymore. d. init_mem_mapping: can not put page table high anymore. e. initmem_init: vmemmap can not be high local node anymore. That is not good. If node is hotplugable, the mem related range like page table and vmemmap could be on the that node without problem and should be on that node. We have workaround patch that could fix some problems, but some can not be fixed. So just remove that offending commit and related ones including: f7210e6c4ac7 ("mm/memblock.c: use CONFIG_HAVE_MEMBLOCK_NODE_MAP to protect movablecore_map in memblock_overlaps_region().") 01a178a94e8e ("acpi, memory-hotplug: support getting hotplug info from SRAT") 27168d38fa20 ("acpi, memory-hotplug: extend movablemem_map ranges to the end of node") e8d195525809 ("acpi, memory-hotplug: parse SRAT before memblock is ready") fb06bc8e5f42 ("page_alloc: bootmem limit with movablecore_map") 42f47e27e761 ("page_alloc: make movablemem_map have higher priority") 6981ec31146c ("page_alloc: introduce zone_movable_limit[] to keep movable limit for nodes") 34b71f1e04fc ("page_alloc: add movable_memmap kernel parameter") 4d59a75125d5 ("x86: get pg_data_t's memory from other node") Later we should have patches that will make sure kernel put page table and vmemmap on local node ram instead of push them down to node0. Also need to find way to put other kernel used ram to local node ram. Reported-by: Tim Gardner Reported-by: Don Morris Bisected-by: Don Morris Tested-by: Don Morris Signed-off-by: Yinghai Lu Cc: Tony Luck Cc: Thomas Renninger Cc: Tejun Heo Cc: Tang Chen Cc: Yasuaki Ishimatsu Signed-off-by: Linus Torvalds --- include/linux/acpi.h | 8 -------- include/linux/memblock.h | 2 -- include/linux/mm.h | 18 ------------------ 3 files changed, 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index f46cfd73a553..bcbdd7484e58 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -485,14 +485,6 @@ static inline bool acpi_driver_match_device(struct device *dev, #endif /* !CONFIG_ACPI */ -#ifdef CONFIG_ACPI_NUMA -void __init early_parse_srat(void); -#else -static inline void early_parse_srat(void) -{ -} -#endif - #ifdef CONFIG_ACPI void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, u32 pm1a_ctrl, u32 pm1b_ctrl)); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 3e5ecb2d790e..f388203db7e8 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -42,7 +42,6 @@ struct memblock { extern struct memblock memblock; extern int memblock_debug; -extern struct movablemem_map movablemem_map; #define memblock_dbg(fmt, ...) \ if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) @@ -61,7 +60,6 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size); void memblock_trim_memory(phys_addr_t align); #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid); diff --git a/include/linux/mm.h b/include/linux/mm.h index e7c3f9a0111a..1ede55f292c2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1333,24 +1333,6 @@ extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); extern void sparse_memory_present_with_active_regions(int nid); -#define MOVABLEMEM_MAP_MAX MAX_NUMNODES -struct movablemem_entry { - unsigned long start_pfn; /* start pfn of memory segment */ - unsigned long end_pfn; /* end pfn of memory segment (exclusive) */ -}; - -struct movablemem_map { - bool acpi; /* true if using SRAT info */ - int nr_map; - struct movablemem_entry map[MOVABLEMEM_MAP_MAX]; - nodemask_t numa_nodes_hotplug; /* on which nodes we specify memory */ - nodemask_t numa_nodes_kernel; /* on which nodes kernel resides in */ -}; - -extern void __init insert_movablemem_map(unsigned long start_pfn, - unsigned long end_pfn); -extern int __init movablemem_map_overlap(unsigned long start_pfn, - unsigned long end_pfn); #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ -- cgit v1.2.3 From 5698c50d9da4ab2f57d98c64ea97675dcaf2a608 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Tue, 9 Oct 2012 10:54:47 +0100 Subject: metag: Internal and external irqchips Meta core internal interrupts (from HWSTATMETA and friends) are vectored onto the TR1 core trigger for the current thread. This is demultiplexed in irq-metag.c to individual Linux IRQs for each internal interrupt. External SoC interrupts (from HWSTATEXT and friends) are vectored onto the TR2 core trigger for the current thread. This is demultiplexed in irq-metag-ext.c to individual Linux IRQs for each external SoC interrupt. The external irqchip has devicetree bindings for configuring the number of irq banks and the type of masking available. Signed-off-by: James Hogan Cc: Arnd Bergmann Cc: Grant Likely Cc: Rob Herring Cc: Rob Landley Cc: Dom Cobley Cc: Simon Arlott Cc: Viresh Kumar Cc: Maxime Ripard Cc: devicetree-discuss@lists.ozlabs.org Cc: linux-doc@vger.kernel.org --- include/linux/irqchip/metag-ext.h | 33 +++++++++++++++++++++++++++++++++ include/linux/irqchip/metag.h | 24 ++++++++++++++++++++++++ 2 files changed, 57 insertions(+) create mode 100644 include/linux/irqchip/metag-ext.h create mode 100644 include/linux/irqchip/metag.h (limited to 'include/linux') diff --git a/include/linux/irqchip/metag-ext.h b/include/linux/irqchip/metag-ext.h new file mode 100644 index 000000000000..697af0fe7c5a --- /dev/null +++ b/include/linux/irqchip/metag-ext.h @@ -0,0 +1,33 @@ +/* + * Copyright (C) 2012 Imagination Technologies + */ + +#ifndef _LINUX_IRQCHIP_METAG_EXT_H_ +#define _LINUX_IRQCHIP_METAG_EXT_H_ + +struct irq_data; +struct platform_device; + +/* called from core irq code at init */ +int init_external_IRQ(void); + +/* + * called from SoC init_irq() callback to dynamically indicate the lack of + * HWMASKEXT registers. + */ +void meta_intc_no_mask(void); + +/* + * These allow SoCs to specialise the interrupt controller from their init_irq + * callbacks. + */ + +extern struct irq_chip meta_intc_edge_chip; +extern struct irq_chip meta_intc_level_chip; + +/* this should be called in the mask callback */ +void meta_intc_mask_irq_simple(struct irq_data *data); +/* this should be called in the unmask callback */ +void meta_intc_unmask_irq_simple(struct irq_data *data); + +#endif /* _LINUX_IRQCHIP_METAG_EXT_H_ */ diff --git a/include/linux/irqchip/metag.h b/include/linux/irqchip/metag.h new file mode 100644 index 000000000000..4ebdfb3101ab --- /dev/null +++ b/include/linux/irqchip/metag.h @@ -0,0 +1,24 @@ +/* + * Copyright (C) 2011 Imagination Technologies + */ + +#ifndef _LINUX_IRQCHIP_METAG_H_ +#define _LINUX_IRQCHIP_METAG_H_ + +#include + +#ifdef CONFIG_METAG_PERFCOUNTER_IRQS +extern int init_internal_IRQ(void); +extern int internal_irq_map(unsigned int hw); +#else +static inline int init_internal_IRQ(void) +{ + return 0; +} +static inline int internal_irq_map(unsigned int hw) +{ + return -EINVAL; +} +#endif + +#endif /* _LINUX_IRQCHIP_METAG_H_ */ -- cgit v1.2.3 From 9ca52ed979b6b45ae480a5fc56d593efb3bf16e8 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Tue, 16 Oct 2012 10:16:14 +0100 Subject: mm: define VM_GROWSUP for CONFIG_METAG Commit cc2383ec06be093789469852e1fe96e1148e9a2c ("mm: introduce arch-specific vma flag VM_ARCH_1") merged in v3.7-rc1. The above commit combined several arch-specific vma flags into one, and in the process it changed the VM_GROWSUP definition to depend on specific architectures rather than CONFIG_STACK_GROWSUP. Therefore add an ifdef for CONFIG_METAG to also set VM_GROWSUP. Signed-off-by: James Hogan Cc: Konstantin Khlebnikov Cc: Andrew Morton Cc: Mel Gorman Cc: Michel Lespinasse Cc: Al Viro Cc: linux-mm@kvack.org --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 66e2f7c61e5c..44ac3dc363e7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -114,6 +114,8 @@ extern unsigned int kobjsize(const void *objp); # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 +#elif defined(CONFIG_METAG) +# define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_IA64) # define VM_GROWSUP VM_ARCH_1 #elif !defined(CONFIG_MMU) -- cgit v1.2.3 From 290502bee239062499297916bb7d21d205e99d62 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 28 Feb 2013 00:39:37 -0800 Subject: eCryptfs: allow userspace messaging to be disabled When the userspace messaging (for the less common case of userspace key wrap/unwrap via ecryptfsd) is not needed, allow eCryptfs to build with it removed. This saves on kernel code size and reduces potential attack surface by removing the /dev/ecryptfs node. Signed-off-by: Kees Cook Signed-off-by: Tyler Hicks --- include/linux/ecryptfs.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ecryptfs.h b/include/linux/ecryptfs.h index 2224a8c0cb64..8d5ab998a222 100644 --- a/include/linux/ecryptfs.h +++ b/include/linux/ecryptfs.h @@ -6,9 +6,8 @@ #define ECRYPTFS_VERSION_MINOR 0x04 #define ECRYPTFS_SUPPORTED_FILE_VERSION 0x03 /* These flags indicate which features are supported by the kernel - * module; userspace tools such as the mount helper read - * ECRYPTFS_VERSIONING_MASK from a sysfs handle in order to determine - * how to behave. */ + * module; userspace tools such as the mount helper read the feature + * bits from a sysfs handle in order to determine how to behave. */ #define ECRYPTFS_VERSIONING_PASSPHRASE 0x00000001 #define ECRYPTFS_VERSIONING_PUBKEY 0x00000002 #define ECRYPTFS_VERSIONING_PLAINTEXT_PASSTHROUGH 0x00000004 @@ -19,13 +18,6 @@ #define ECRYPTFS_VERSIONING_HMAC 0x00000080 #define ECRYPTFS_VERSIONING_FILENAME_ENCRYPTION 0x00000100 #define ECRYPTFS_VERSIONING_GCM 0x00000200 -#define ECRYPTFS_VERSIONING_MASK (ECRYPTFS_VERSIONING_PASSPHRASE \ - | ECRYPTFS_VERSIONING_PLAINTEXT_PASSTHROUGH \ - | ECRYPTFS_VERSIONING_PUBKEY \ - | ECRYPTFS_VERSIONING_XATTR \ - | ECRYPTFS_VERSIONING_MULTKEY \ - | ECRYPTFS_VERSIONING_DEVMISC \ - | ECRYPTFS_VERSIONING_FILENAME_ENCRYPTION) #define ECRYPTFS_MAX_PASSWORD_LENGTH 64 #define ECRYPTFS_MAX_PASSPHRASE_BYTES ECRYPTFS_MAX_PASSWORD_LENGTH #define ECRYPTFS_SALT_SIZE 8 -- cgit v1.2.3