From 1449c5d0e8f25af6c903797a636696901122e4e8 Mon Sep 17 00:00:00 2001 From: H Hartley Sweeten Date: Fri, 15 Jan 2010 11:09:32 -0700 Subject: mtd: quiet sparse noise in cfi.h In the inline function cfi_build_cmd_addr, the cast of cmd_ofs to an uint8_t produces a sparse warning of the type: warning: cast truncates bits from constant value (2aa becomes aa) Quiet the warning by masking cmd_ofs with 0xff and remove the cast. Signed-off-by: H Hartley Sweeten Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/cfi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index df89f4275232..a4eefc5810dc 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -297,7 +297,7 @@ static inline uint32_t cfi_build_cmd_addr(uint32_t cmd_ofs, * and 32bit devices on 16 bit busses * set the low bit of the alternating bit sequence of the address. */ - if (((type * interleave) > bankwidth) && ((uint8_t)cmd_ofs == 0xaa)) + if (((type * interleave) > bankwidth) && ((cmd_ofs & 0xff) == 0xaa)) addr |= (type >> 1)*interleave; return addr; -- cgit v1.2.3 From b520e412faaaad35641aeedd6059179f9f1b393c Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 29 Jan 2010 20:59:42 +0000 Subject: mtd: Replace static array of devices with an idr structure Signed-off-by: Ben Hutchings Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 0f32a9b6ff55..ba53ecca107c 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -20,7 +20,6 @@ #define MTD_CHAR_MAJOR 90 #define MTD_BLOCK_MAJOR 31 -#define MAX_MTD_DEVICES 32 #define MTD_ERASE_PENDING 0x01 #define MTD_ERASING 0x02 -- cgit v1.2.3 From 91f8026603d4443d1b24ee3552c5a58682bbae27 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 2 Feb 2010 14:43:10 -0800 Subject: JFFS2: avoid using C++ keyword `new' in userspace-visible header Addresses http://bugzilla.kernel.org/show_bug.cgi?id=14995 Reported-by: R. Diez Signed-off-by: Andrew Morton Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/jffs2.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jffs2.h b/include/linux/jffs2.h index 2b32d638147d..0874ab59ffef 100644 --- a/include/linux/jffs2.h +++ b/include/linux/jffs2.h @@ -215,8 +215,8 @@ union jffs2_node_union /* Data payload for device nodes. */ union jffs2_device_node { - jint16_t old; - jint32_t new; + jint16_t old_id; + jint32_t new_id; }; #endif /* __LINUX_JFFS2_H__ */ -- cgit v1.2.3 From 7d70f334ad2bf1b3aaa1f0699c0f442e14bcc9e0 Mon Sep 17 00:00:00 2001 From: Vimal Singh Date: Mon, 8 Feb 2010 15:50:49 +0530 Subject: mtd: nand: add lock/unlock routines Add nand lock / unlock routines. At least 'micron' parts support this. Signed-off-by: Vimal Singh Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index ccab9dfc5217..48bc2c54302c 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -38,6 +38,12 @@ extern void nand_release (struct mtd_info *mtd); /* Internal helper for board drivers which need to override command function */ extern void nand_wait_ready(struct mtd_info *mtd); +/* locks all blockes present in the device */ +extern int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len); + +/* unlocks specified locked blockes */ +extern int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); + /* The maximum number of NAND chips in an array */ #define NAND_MAX_CHIPS 8 @@ -82,6 +88,10 @@ extern void nand_wait_ready(struct mtd_info *mtd); #define NAND_CMD_ERASE2 0xd0 #define NAND_CMD_RESET 0xff +#define NAND_CMD_LOCK 0x2a +#define NAND_CMD_UNLOCK1 0x23 +#define NAND_CMD_UNLOCK2 0x24 + /* Extended commands for large page devices */ #define NAND_CMD_READSTART 0x30 #define NAND_CMD_RNDOUTSTART 0xE0 -- cgit v1.2.3 From f3e69c6584be2db1ccd5292d6a1d7c566d265701 Mon Sep 17 00:00:00 2001 From: Guillaume LECERF Date: Tue, 15 Dec 2009 23:01:06 +0100 Subject: mtd: move more manufacturers to the common cfi.h header file Move MANUFACTURER_MACRONIX and MANUFACTURER_SST definitions to the include/linux/mtd/cfi.h header file and rename them to CFI_MFR_MACRONIX and CFI_MFR_SST. All references in drivers/mtd/chips/cfi_cmdset_0002.c are updated to reflect this. Signed-off-by: Guillaume LECERF Signed-off-by: David Woodhouse --- include/linux/mtd/cfi.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index a4eefc5810dc..cee05b1e62b1 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -518,11 +518,13 @@ struct cfi_fixup { #define CFI_MFR_ANY 0xffff #define CFI_ID_ANY 0xffff -#define CFI_MFR_AMD 0x0001 -#define CFI_MFR_INTEL 0x0089 -#define CFI_MFR_ATMEL 0x001F -#define CFI_MFR_SAMSUNG 0x00EC -#define CFI_MFR_ST 0x0020 /* STMicroelectronics */ +#define CFI_MFR_AMD 0x0001 +#define CFI_MFR_ATMEL 0x001F +#define CFI_MFR_INTEL 0x0089 +#define CFI_MFR_MACRONIX 0x00C2 +#define CFI_MFR_SAMSUNG 0x00EC +#define CFI_MFR_SST 0x00BF +#define CFI_MFR_ST 0x0020 /* STMicroelectronics */ void cfi_fixup(struct mtd_info *mtd, struct cfi_fixup* fixups); -- cgit v1.2.3 From 3bd456576f22acd55fb6c3d3d4261131821f5a3b Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 22 Feb 2010 20:39:28 +0200 Subject: mtd: create unlocked versions of {get,put}_mtd_device Use these only if you know that you already hold mtd_table_mutex Signed-off-by: Maxim Levitsky Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index ba53ecca107c..11d8e68d17c0 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -289,8 +289,9 @@ extern int add_mtd_device(struct mtd_info *mtd); extern int del_mtd_device (struct mtd_info *mtd); extern struct mtd_info *get_mtd_device(struct mtd_info *mtd, int num); +extern int __get_mtd_device(struct mtd_info *mtd); +extern void __put_mtd_device(struct mtd_info *mtd); extern struct mtd_info *get_mtd_device_nm(const char *name); - extern void put_mtd_device(struct mtd_info *mtd); -- cgit v1.2.3 From a863862257b7dd08d855bafcb0aedd9ad848ed91 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 22 Feb 2010 20:39:29 +0200 Subject: mtd: blktrans: remove mtd_blkcore_priv, switch to per device queue and thread This is the biggest change. To make hotplug possible, and this layer clean, the mtd_blktrans_dev now contains everything for a single mtd block translation device. Also removed some very old leftovers. Signed-off-by: Maxim Levitsky Signed-off-by: David Woodhouse --- include/linux/mtd/blktrans.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index 8b4aa0523db7..a4b392868b54 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -24,11 +24,13 @@ struct mtd_blktrans_dev { int devnum; unsigned long size; int readonly; - void *blkcore_priv; /* gendisk in 2.5, devfs_handle in 2.4 */ + struct gendisk *disk; + struct task_struct *thread; + struct request_queue *rq; + spinlock_t queue_lock; + void *priv; }; -struct blkcore_priv; /* Differs for 2.4 and 2.5 kernels; private */ - struct mtd_blktrans_ops { char *name; int major; @@ -60,8 +62,6 @@ struct mtd_blktrans_ops { struct list_head devs; struct list_head list; struct module *owner; - - struct mtd_blkcore_priv *blkcore_priv; }; extern int register_mtd_blktrans(struct mtd_blktrans_ops *tr); -- cgit v1.2.3 From 048d87199566663e4edc4880df3703c04bcf41d9 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 22 Feb 2010 20:39:30 +0200 Subject: mtd: blktrans: Hotplug fixes * Add locking where it was missing. * Don't do a get_mtd_device in blktrans_open because it would lead to a deadlock; instead do that in add_mtd_blktrans_dev. * Only free the mtd_blktrans_dev structure when the last user exits. * Flush request queue on device removal. * Track users, and call tr->release in del_mtd_blktrans_dev Due to that ->open and release aren't called more that once. Now it is safe to call del_mtd_blktrans_dev while the device is still in use. Signed-off-by: Maxim Levitsky Signed-off-by: David Woodhouse --- include/linux/mtd/blktrans.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index a4b392868b54..d89b8fbba4c9 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -9,6 +9,7 @@ #define __MTD_TRANS_H__ #include +#include struct hd_geometry; struct mtd_info; @@ -24,6 +25,8 @@ struct mtd_blktrans_dev { int devnum; unsigned long size; int readonly; + int open; + struct kref ref; struct gendisk *disk; struct task_struct *thread; struct request_queue *rq; -- cgit v1.2.3 From 026ec57886b67c092bf7baecd029a7c1c4998c28 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 22 Feb 2010 20:39:33 +0200 Subject: mtd: blktrans: allow FTL drivers to export sysfs attributes This patch adds an ability to export sysfs attributes below the block disk device. This can be used to pass the udev an information about the FTL and could include the vendor, serial, version, etc... Signed-off-by: Maxim Levitsky Signed-off-by: David Woodhouse --- include/linux/mtd/blktrans.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index d89b8fbba4c9..b481ccd7ff3c 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -10,6 +10,7 @@ #include #include +#include struct hd_geometry; struct mtd_info; @@ -28,6 +29,7 @@ struct mtd_blktrans_dev { int open; struct kref ref; struct gendisk *disk; + struct attribute_group *disk_attributes; struct task_struct *thread; struct request_queue *rq; spinlock_t queue_lock; -- cgit v1.2.3 From b64d39d8b03fea88417d53715ccbebf71d4dcc9f Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 22 Feb 2010 20:39:37 +0200 Subject: mtd: nand: make reads using MTD_OOB_RAW affect only ECC validation This changes the behavier of MTD_OOB_RAW. It used to read both OOB and data to the data buffer, however you would still need to specify the dummy oob buffer. This is only used in one place, but makes it hard to read data+oob without ECC test, thus I removed that behavier, and fixed the user. Now MTD_OOB_RAW behaves just like MTD_OOB_PLACE, but doesn't do ECC validation Signed-off-by: Maxim Levitsky Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 11d8e68d17c0..5326435a7571 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -60,9 +60,7 @@ struct mtd_erase_region_info { * MTD_OOB_PLACE: oob data are placed at the given offset * MTD_OOB_AUTO: oob data are automatically placed at the free areas * which are defined by the ecclayout - * MTD_OOB_RAW: mode to read raw data+oob in one chunk. The oob data - * is inserted into the data. Thats a raw image of the - * flash contents. + * MTD_OOB_RAW: mode to read oob and data without doing ECC checking */ typedef enum { MTD_OOB_PLACE, -- cgit v1.2.3 From e0b58d0a7005cd4b9c7fa4694a437a2d86719c13 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 22 Feb 2010 20:39:38 +0200 Subject: mtd: nand: add ->badblockbits for minimum number of set bits in bad block byte This can be used to protect against bitflips in that field, but now mostly for smartmedia. Signed-off-by: Maxim Levitsky Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 48bc2c54302c..f2d4a1ac14b8 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -401,6 +401,7 @@ struct nand_chip { int subpagesize; uint8_t cellinfo; int badblockpos; + int badblockbits; flstate_t state; -- cgit v1.2.3 From 5e81e88a4c140586d9212999cea683bcd66a15c6 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 26 Feb 2010 18:32:56 +0000 Subject: mtd: nand: Allow caller to pass alternative ID table to nand_scan_ident() Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index f2d4a1ac14b8..d152bdf9161f 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -25,11 +25,13 @@ #include struct mtd_info; +struct nand_flash_dev; /* Scan and identify a NAND device */ extern int nand_scan (struct mtd_info *mtd, int max_chips); /* Separate phases of nand_scan(), allowing board driver to intervene * and override command or ECC setup according to flash type */ -extern int nand_scan_ident(struct mtd_info *mtd, int max_chips); +extern int nand_scan_ident(struct mtd_info *mtd, int max_chips, + struct nand_flash_dev *table); extern int nand_scan_tail(struct mtd_info *mtd); /* Free resources held by the NAND device */ -- cgit v1.2.3 From 93edbad69b0491d794c2ec86bcc65c69eac676e3 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 22 Feb 2010 20:39:40 +0200 Subject: mtd: Workaround wrong write protect status on some xD cards Signed-off-by: Maxim Levitsky Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index d152bdf9161f..8bdacb885f90 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -182,6 +182,12 @@ typedef enum { /* Chip does not allow subpage writes */ #define NAND_NO_SUBPAGE_WRITE 0x00000200 +/* Device is one of 'new' xD cards that expose fake nand command set */ +#define NAND_BROKEN_XD 0x00000400 + +/* Device behaves just like nand, but is readonly */ +#define NAND_ROM 0x00000800 + /* Options valid for Samsung large page devices */ #define NAND_SAMSUNG_LP_OPTIONS \ (NAND_NO_PADDING | NAND_CACHEPRG | NAND_COPYBACK) -- cgit v1.2.3 From de5d4453c5b224eefd02b6a141ed411a76d458af Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Richard=20R=C3=B6jfors?= Date: Thu, 25 Mar 2010 19:44:21 +0100 Subject: dma: Add timb-dma MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adds the support for the DMA engine withing the timberdale FPGA. The DMA channels are strict device to host, or host to device and can not be used for generic memcpy. Signed-off-by: Richard Röjfors Signed-off-by: Dan Williams --- include/linux/timb_dma.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) create mode 100644 include/linux/timb_dma.h (limited to 'include/linux') diff --git a/include/linux/timb_dma.h b/include/linux/timb_dma.h new file mode 100644 index 000000000000..bb043e970b96 --- /dev/null +++ b/include/linux/timb_dma.h @@ -0,0 +1,55 @@ +/* + * timb_dma.h timberdale FPGA DMA driver defines + * Copyright (c) 2010 Intel Corporation + * + * 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., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +/* Supports: + * Timberdale FPGA DMA engine + */ + +#ifndef _LINUX_TIMB_DMA_H +#define _LINUX_TIMB_DMA_H + +/** + * struct timb_dma_platform_data_channel - Description of each individual + * DMA channel for the timberdale DMA driver + * @rx: true if this channel handles data in the direction to + * the CPU. + * @bytes_per_line: Number of bytes per line, this is specific for channels + * handling video data. For other channels this shall be left to 0. + * @descriptors: Number of descriptors to allocate for this channel. + * @descriptor_elements: Number of elements in each descriptor. + * + */ +struct timb_dma_platform_data_channel { + bool rx; + unsigned int bytes_per_line; + unsigned int descriptors; + unsigned int descriptor_elements; +}; + +/** + * struct timb_dma_platform_data - Platform data of the timberdale DMA driver + * @nr_channels: Number of defined channels in the channels array. + * @channels: Definition of the each channel. + * + */ +struct timb_dma_platform_data { + unsigned nr_channels; + struct timb_dma_platform_data_channel channels[32]; +}; + +#endif -- cgit v1.2.3 From c3635c78e500a52c9fcd55de381a72928d9e054d Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 26 Mar 2010 16:44:01 -0700 Subject: DMAENGINE: generic slave control v2 Convert the device_terminate_all() operation on the DMA engine to a generic device_control() operation which can now optionally support also pausing and resuming DMA on a certain channel. Implemented for the COH 901 318 DMAC as an example. [dan.j.williams@intel.com: update for timberdale] Signed-off-by: Linus Walleij Acked-by: Mark Brown Cc: Maciej Sosnowski Cc: Nicolas Ferre Cc: Pavel Machek Cc: Li Yang Cc: Guennadi Liakhovetski Cc: Paul Mundt Cc: Ralf Baechle Cc: Haavard Skinnemoen Cc: Magnus Damm Cc: Liam Girdwood Cc: Joe Perches Cc: Roland Dreier Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 20ea12c86fd0..0731802f876f 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -106,6 +106,19 @@ enum dma_ctrl_flags { DMA_PREP_FENCE = (1 << 9), }; +/** + * enum dma_ctrl_cmd - DMA operations that can optionally be exercised + * on a running channel. + * @DMA_TERMINATE_ALL: terminate all ongoing transfers + * @DMA_PAUSE: pause ongoing transfers + * @DMA_RESUME: resume paused transfer + */ +enum dma_ctrl_cmd { + DMA_TERMINATE_ALL, + DMA_PAUSE, + DMA_RESUME, +}; + /** * enum sum_check_bits - bit position of pq_check_flags */ @@ -261,7 +274,8 @@ struct dma_async_tx_descriptor { * @device_prep_dma_memset: prepares a memset operation * @device_prep_dma_interrupt: prepares an end of chain interrupt operation * @device_prep_slave_sg: prepares a slave dma operation - * @device_terminate_all: terminate all pending operations + * @device_control: manipulate all pending operations on a channel, returns + * zero or error code * @device_is_tx_complete: poll for transaction completion * @device_issue_pending: push pending transactions to hardware */ @@ -313,7 +327,7 @@ struct dma_device { struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, enum dma_data_direction direction, unsigned long flags); - void (*device_terminate_all)(struct dma_chan *chan); + int (*device_control)(struct dma_chan *chan, enum dma_ctrl_cmd cmd); enum dma_status (*device_is_tx_complete)(struct dma_chan *chan, dma_cookie_t cookie, dma_cookie_t *last, -- cgit v1.2.3 From 0793448187643b50af89d36b08470baf45a3cab4 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 26 Mar 2010 16:50:49 -0700 Subject: DMAENGINE: generic channel status v2 Convert the device_is_tx_complete() operation on the DMA engine to a generic device_tx_status()operation which can return three states, DMA_TX_RUNNING, DMA_TX_COMPLETE, DMA_TX_PAUSED. [dan.j.williams@intel.com: update for timberdale] Signed-off-by: Linus Walleij Acked-by: Mark Brown Cc: Maciej Sosnowski Cc: Nicolas Ferre Cc: Pavel Machek Cc: Li Yang Cc: Guennadi Liakhovetski Cc: Paul Mundt Cc: Ralf Baechle Cc: Haavard Skinnemoen Cc: Magnus Damm Cc: Liam Girdwood Cc: Joe Perches Cc: Roland Dreier Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 38 +++++++++++++++++++++++++++++++++----- 1 file changed, 33 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 0731802f876f..55b08e84ac8d 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -40,11 +40,13 @@ typedef s32 dma_cookie_t; * enum dma_status - DMA transaction status * @DMA_SUCCESS: transaction completed successfully * @DMA_IN_PROGRESS: transaction not yet processed + * @DMA_PAUSED: transaction is paused * @DMA_ERROR: transaction failed */ enum dma_status { DMA_SUCCESS, DMA_IN_PROGRESS, + DMA_PAUSED, DMA_ERROR, }; @@ -248,6 +250,21 @@ struct dma_async_tx_descriptor { spinlock_t lock; }; +/** + * struct dma_tx_state - filled in to report the status of + * a transfer. + * @last: last completed DMA cookie + * @used: last issued DMA cookie (i.e. the one in progress) + * @residue: the remaining number of bytes left to transmit + * on the selected transfer for states DMA_IN_PROGRESS and + * DMA_PAUSED if this is implemented in the driver, else 0 + */ +struct dma_tx_state { + dma_cookie_t last; + dma_cookie_t used; + u32 residue; +}; + /** * struct dma_device - info on the entity supplying DMA services * @chancnt: how many DMA channels are supported @@ -276,7 +293,10 @@ struct dma_async_tx_descriptor { * @device_prep_slave_sg: prepares a slave dma operation * @device_control: manipulate all pending operations on a channel, returns * zero or error code - * @device_is_tx_complete: poll for transaction completion + * @device_tx_status: poll for transaction completion, the optional + * txstate parameter can be supplied with a pointer to get a + * struct with auxilary transfer status information, otherwise the call + * will just return a simple status code * @device_issue_pending: push pending transactions to hardware */ struct dma_device { @@ -329,9 +349,9 @@ struct dma_device { unsigned long flags); int (*device_control)(struct dma_chan *chan, enum dma_ctrl_cmd cmd); - enum dma_status (*device_is_tx_complete)(struct dma_chan *chan, - dma_cookie_t cookie, dma_cookie_t *last, - dma_cookie_t *used); + enum dma_status (*device_tx_status)(struct dma_chan *chan, + dma_cookie_t cookie, + struct dma_tx_state *txstate); void (*device_issue_pending)(struct dma_chan *chan); }; @@ -572,7 +592,15 @@ static inline void dma_async_issue_pending(struct dma_chan *chan) static inline enum dma_status dma_async_is_tx_complete(struct dma_chan *chan, dma_cookie_t cookie, dma_cookie_t *last, dma_cookie_t *used) { - return chan->device->device_is_tx_complete(chan, cookie, last, used); + struct dma_tx_state state; + enum dma_status status; + + status = chan->device->device_tx_status(chan, cookie, &state); + if (last) + *last = state.last; + if (used) + *used = state.used; + return status; } #define dma_async_memcpy_complete(chan, cookie, last, used)\ -- cgit v1.2.3 From bca3469205402d9fb14060d255d8786ae2256640 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 26 Mar 2010 16:52:10 -0700 Subject: dmaengine: provide helper for setting txstate Simple conditional struct filler to cut out some duplicated code. Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 55b08e84ac8d..50b7b3e0d572 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -628,6 +628,16 @@ static inline enum dma_status dma_async_is_complete(dma_cookie_t cookie, return DMA_IN_PROGRESS; } +static inline void +dma_set_tx_state(struct dma_tx_state *st, dma_cookie_t last, dma_cookie_t used, u32 residue) +{ + if (st) { + st->last = last; + st->used = used; + st->residue = residue; + } +} + enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); #ifdef CONFIG_DMA_ENGINE enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); -- cgit v1.2.3 From 9195291e5f05e01d67f9a09c756b8aca8f009089 Mon Sep 17 00:00:00 2001 From: Divyesh Shah Date: Thu, 1 Apr 2010 15:01:41 -0700 Subject: blkio: Increment the blkio cgroup stats for real now We also add start_time_ns and io_start_time_ns fields to struct request here to record the time when a request is created and when it is dispatched to device. We use ns uints here as ms and jiffies are not very useful for non-rotational media. Signed-off-by: Divyesh Shah Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6690e8bae7bb..f3fff8bf85ee 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -194,7 +194,10 @@ struct request { struct gendisk *rq_disk; unsigned long start_time; - +#ifdef CONFIG_BLK_CGROUP + unsigned long long start_time_ns; + unsigned long long io_start_time_ns; /* when passed to hardware */ +#endif /* Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ @@ -1196,6 +1199,21 @@ static inline void put_dev_sector(Sector p) struct work_struct; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); +#ifdef CONFIG_BLK_CGROUP +static inline void set_start_time_ns(struct request *req) +{ + req->start_time_ns = sched_clock(); +} + +static inline void set_io_start_time_ns(struct request *req) +{ + req->io_start_time_ns = sched_clock(); +} +#else +static inline void set_start_time_ns(struct request *req) {} +static inline void set_io_start_time_ns(struct request *req) {} +#endif + #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ -- cgit v1.2.3 From 31373d09da5b7fe21fe6f781e92bd534a3495f00 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Tue, 6 Apr 2010 14:25:14 +0200 Subject: laptop-mode: Make flushes per-device One of the features of laptop-mode is that it forces a writeout of dirty pages if something else triggers a physical read or write from a device. The current implementation flushes pages on all devices, rather than only the one that triggered the flush. This patch alters the behaviour so that only the recently accessed block device is flushed, preventing other disks being spun up for no terribly good reason. Signed-off-by: Matthew Garrett Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 3 +++ include/linux/writeback.h | 4 +++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index fcbc26af00e4..2742e1adfc30 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -88,6 +89,8 @@ struct backing_dev_info { struct device *dev; + struct timer_list laptop_mode_wb_timer; + #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; struct dentry *debug_stats; diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 36520ded3e06..eb38a2c645f6 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -96,8 +96,10 @@ static inline void inode_sync_wait(struct inode *inode) /* * mm/page-writeback.c */ -void laptop_io_completion(void); +void laptop_io_completion(struct backing_dev_info *info); void laptop_sync_completion(void); +void laptop_mode_sync(struct work_struct *work); +void laptop_mode_timer_fn(unsigned long data); void throttle_vm_writeout(gfp_t gfp_mask); /* These are exported to sysctl. */ -- cgit v1.2.3 From e3e8d1c93f9e6b766424b05f23f2416f22a0329d Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 28 Feb 2010 12:47:49 +0100 Subject: Driver for Zipit Z2 battery chip This patch adds driver for Zipit Z2 battery chip called AER915. No details are known about the chip. The chip is available through I2C bus at address 0x55 and it's register 0x02 contains battery voltage. Signed-off-by: Marek Vasut Signed-off-by: Anton Vorontsov --- include/linux/z2_battery.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/linux/z2_battery.h (limited to 'include/linux') diff --git a/include/linux/z2_battery.h b/include/linux/z2_battery.h new file mode 100644 index 000000000000..7b9750404d22 --- /dev/null +++ b/include/linux/z2_battery.h @@ -0,0 +1,17 @@ +#ifndef _LINUX_Z2_BATTERY_H +#define _LINUX_Z2_BATTERY_H + +struct z2_battery_info { + int batt_I2C_bus; + int batt_I2C_addr; + int batt_I2C_reg; + int charge_gpio; + int min_voltage; + int max_voltage; + int batt_div; + int batt_mult; + int batt_tech; + char *batt_name; +}; + +#endif -- cgit v1.2.3 From a244b25217978ffd54d2cd87013b3cd564689462 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Wed, 7 Apr 2010 10:08:49 +1000 Subject: Remove unused HDPU driver This driver seems to be specific to a "Sky CPU" board for which we don't appear to have upstream support (or not any more). No Kconfig file in the kernel ever enables it. So remove it. Signed-off-by: Benjamin Herrenschmidt --- include/linux/hdpu_features.h | 26 -------------------------- 1 file changed, 26 deletions(-) delete mode 100644 include/linux/hdpu_features.h (limited to 'include/linux') diff --git a/include/linux/hdpu_features.h b/include/linux/hdpu_features.h deleted file mode 100644 index 6a8715431ae4..000000000000 --- a/include/linux/hdpu_features.h +++ /dev/null @@ -1,26 +0,0 @@ -#include - -struct cpustate_t { - spinlock_t lock; - int excl; - int open_count; - unsigned char cached_val; - int inited; - unsigned long *set_addr; - unsigned long *clr_addr; -}; - - -#define HDPU_CPUSTATE_NAME "hdpu cpustate" -#define HDPU_NEXUS_NAME "hdpu nexus" - -#define CPUSTATE_KERNEL_MAJOR 0x10 - -#define CPUSTATE_KERNEL_INIT_DRV 0 /* CPU State Driver Initialized */ -#define CPUSTATE_KERNEL_INIT_PCI 1 /* 64360 PCI Busses Init */ -#define CPUSTATE_KERNEL_INIT_REG 2 /* 64360 Bridge Init */ -#define CPUSTATE_KERNEL_CPU1_KICK 3 /* Boot cpu 1 */ -#define CPUSTATE_KERNEL_CPU1_OK 4 /* Cpu 1 has checked in */ -#define CPUSTATE_KERNEL_OK 5 /* Terminal state */ -#define CPUSTATE_KERNEL_RESET 14 /* Board reset via SW*/ -#define CPUSTATE_KERNEL_HALT 15 /* Board halted via SW*/ -- cgit v1.2.3 From 84c124da9ff50bd71fab9c939ee5b7cd8bef2bd9 Mon Sep 17 00:00:00 2001 From: Divyesh Shah Date: Fri, 9 Apr 2010 08:31:19 +0200 Subject: blkio: Changes to IO controller additional stats patches that include some minor fixes and addresses all comments. Changelog: (most based on Vivek Goyal's comments) o renamed blkiocg_reset_write to blkiocg_reset_stats o more clarification in the documentation on io_service_time and io_wait_time o Initialize blkg->stats_lock o rename io_add_stat to blkio_add_stat and declare it static o use bool for direction and sync o derive direction and sync info from existing rq methods o use 12 for major:minor string length o define io_service_time better to cover the NCQ case o add a separate reset_stats interface o make the indexed stats a 2d array to simplify macro and function pointer code o blkio.time now exports in jiffies as before o Added stats description in patch description and Documentation/cgroup/blkio-controller.txt o Prefix all stats functions with blkio and make them static as applicable o replace IO_TYPE_MAX with IO_TYPE_TOTAL o Moved #define constant to top of blk-cgroup.c o Pass dev_t around instead of char * o Add note to documentation file about resetting stats o use BLK_CGROUP_MODULE in addition to BLK_CGROUP config option in #ifdef statements o Avoid struct request specific knowledge in blk-cgroup. blk-cgroup.h now has rq_direction() and rq_sync() functions which are used by CFQ and when using io-controller at a higher level, bio_* functions can be added. Signed-off-by: Divyesh Shah Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f3fff8bf85ee..d483c494672a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1209,9 +1209,27 @@ static inline void set_io_start_time_ns(struct request *req) { req->io_start_time_ns = sched_clock(); } + +static inline uint64_t rq_start_time_ns(struct request *req) +{ + return req->start_time_ns; +} + +static inline uint64_t rq_io_start_time_ns(struct request *req) +{ + return req->io_start_time_ns; +} #else static inline void set_start_time_ns(struct request *req) {} static inline void set_io_start_time_ns(struct request *req) {} +static inline uint64_t rq_start_time_ns(struct request *req) +{ + return 0; +} +static inline uint64_t rq_io_start_time_ns(struct request *req) +{ + return 0; +} #endif #define MODULE_ALIAS_BLOCKDEV(major,minor) \ -- cgit v1.2.3 From 812d402648f4fc1ab1091b2172a46fc1b367c724 Mon Sep 17 00:00:00 2001 From: Divyesh Shah Date: Thu, 8 Apr 2010 21:14:23 -0700 Subject: blkio: Add io_merged stat This includes both the number of bios merged into requests belonging to this cgroup as well as the number of requests merged together. In the past, we've observed different merging behavior across upstream kernels, some by design some actual bugs. This stat helps a lot in debugging such problems when applications report decreased throughput with a new kernel version. This needed adding an extra elevator function to capture bios being merged as I did not want to pollute elevator code with blkiocg knowledge and hence needed the accounting invocation to come from CFQ. Signed-off-by: Divyesh Shah Signed-off-by: Jens Axboe --- include/linux/elevator.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 1cb3372e65d8..2c958f4fce1e 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -14,6 +14,9 @@ typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int typedef int (elevator_allow_merge_fn) (struct request_queue *, struct request *, struct bio *); +typedef void (elevator_bio_merged_fn) (struct request_queue *, + struct request *, struct bio *); + typedef int (elevator_dispatch_fn) (struct request_queue *, int); typedef void (elevator_add_req_fn) (struct request_queue *, struct request *); @@ -36,6 +39,7 @@ struct elevator_ops elevator_merged_fn *elevator_merged_fn; elevator_merge_req_fn *elevator_merge_req_fn; elevator_allow_merge_fn *elevator_allow_merge_fn; + elevator_bio_merged_fn *elevator_bio_merged_fn; elevator_dispatch_fn *elevator_dispatch_fn; elevator_add_req_fn *elevator_add_req_fn; @@ -103,6 +107,8 @@ extern int elv_merge(struct request_queue *, struct request **, struct bio *); extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); extern void elv_merged_request(struct request_queue *, struct request *, int); +extern void elv_bio_merged(struct request_queue *q, struct request *, + struct bio *); extern void elv_requeue_request(struct request_queue *, struct request *); extern int elv_queue_empty(struct request_queue *); extern struct request *elv_former_request(struct request_queue *, struct request *); -- cgit v1.2.3 From dda565492776b7dff5f8507298d868745e734aab Mon Sep 17 00:00:00 2001 From: Yinghai Date: Fri, 9 Apr 2010 01:07:55 +0100 Subject: intel-iommu: use physfn to search drhd for VF When virtfn is used, we should use physfn to find correct drhd -v2: add pci_physfn() Suggested by Roland Dreier do can remove ifdef in dmar.c -v3: Chris pointed out we need that for dma_find_matched_atsr_unit too also change dmar_pci_device_match() static Signed-off-by: Yinghai Lu Acked-by: Roland Dreier Acked-by: Chris Wright Acked-by: Jesse Barnes Signed-off-by: David Woodhouse --- include/linux/pci.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index a788fa12ff31..a327322a33ab 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -334,6 +334,16 @@ struct pci_dev { #endif }; +static inline struct pci_dev *pci_physfn(struct pci_dev *dev) +{ +#ifdef CONFIG_PCI_IOV + if (dev->is_virtfn) + dev = dev->physfn; +#endif + + return dev; +} + extern struct pci_dev *alloc_pci_dev(void); #define pci_dev_b(n) list_entry(n, struct pci_dev, bus_list) -- cgit v1.2.3 From 3fcb027d7fd749569665d34a79ce2a8e00bc2ed6 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Thu, 1 Apr 2010 10:03:25 +0200 Subject: ARM: MXC: mxcmmc: work around a bug in the SDHC busy line handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit MX3 SoCs have a silicon bug which corrupts CRC calculation of multi-block transfers when connected SDIO peripheral doesn't drive the BUSY line as required by the specs. One way to prevent this is to only allow 1-bit transfers. Another way is playing tricks with the DMA engine, but this isn't mainline yet. So for now, we live with the performance drawback of 1-bit transfers until a nicer solution is found. This patch introduces a new host controller callback 'init_card' which is for now only called from mmc_sdio_init_card(). Signed-off-by: Daniel Mack Cc: Sascha Hauer Cc: Dan Williams Cc: Volker Ernst Cc: Jiri Kosina Cc: Michał Mirosław Signed-off-by: Sascha Hauer --- 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 43eaf5ca5848..3196c84cc630 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -108,6 +108,9 @@ struct mmc_host_ops { int (*get_cd)(struct mmc_host *host); void (*enable_sdio_irq)(struct mmc_host *host, int enable); + + /* optional callback for HC quirks */ + void (*init_card)(struct mmc_host *host, struct mmc_card *card); }; struct mmc_card; -- cgit v1.2.3 From 54a4ec469dd6067f0b604bef8ca01a2b1fdb4dcd Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Thu, 15 Apr 2010 02:17:25 -0700 Subject: ide: fix comment typo in ide.h Fix typo in the comment to the 'dma_mode' field of the 'struct ide_drive_s' introduced by the commit 3fccaa192b9501e79a57e02e62b6bf420d2b461e (ide: add drive->dma_mode field). Whilt at it, convert spaces to a tab in the declaration of the neighbouring 'dn' field... Signed-off-by: Sergei Shtylyov Signed-off-by: David S. Miller --- include/linux/ide.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 3239d1c10acb..5acdbe51348a 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -516,8 +516,8 @@ struct ide_drive_s { u8 current_speed; /* current transfer rate set */ u8 desired_speed; /* desired transfer rate set */ u8 pio_mode; /* for ->set_pio_mode _only_ */ - u8 dma_mode; /* for ->dma_pio_mode _only_ */ - u8 dn; /* now wide spread use */ + u8 dma_mode; /* for ->set_dma_mode _only_ */ + u8 dn; /* now wide spread use */ u8 acoustic; /* acoustic management */ u8 media; /* disk, cdrom, tape, floppy, ... */ u8 ready_stat; /* min status value for drive ready */ -- cgit v1.2.3 From a3bcbbee83f55cbaec9b2ad748e7300c7feb2192 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Mon, 12 Apr 2010 23:33:22 +0200 Subject: pda_power: Add function callbacks for suspend and resume Add function prototypes for power management events so they can be handled and used by platform implementations. Signed-off-by: Daniel Mack Cc: Dmitry Baryshkov Cc: David Woodhouse Signed-off-by: Anton Vorontsov --- include/linux/pda_power.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pda_power.h b/include/linux/pda_power.h index d4cf7a2ceb3e..c9e4d814ff77 100644 --- a/include/linux/pda_power.h +++ b/include/linux/pda_power.h @@ -24,6 +24,8 @@ struct pda_power_pdata { int (*is_usb_online)(void); void (*set_charge)(int flags); void (*exit)(struct device *dev); + int (*suspend)(pm_message_t state); + int (*resume)(void); char **supplied_to; size_t num_supplicants; -- cgit v1.2.3 From b5e5a37e36cd4d355b875665312d7aaae4e5833c Mon Sep 17 00:00:00 2001 From: Bastien Nocera Date: Fri, 16 Apr 2010 17:19:50 +0100 Subject: HID: add HID_QUIRK_HIDDEV_FORCE and HID_QUIRK_NO_IGNORE Add two quirks to make it possible for usbhid module options to override whether a device is ignored (HID_QUIRK_NO_IGNORE) and whether to connect a hiddev device (HID_QUIRK_HIDDEV_FORCE). Passing HID_QUIRK_NO_IGNORE for your device means that it will not be ignored by the HID layer, even if present in a blacklist. HID_QUIRK_HIDDEV_FORCE will force the creation of a hiddev for that device, making it accessible from user-space. Tested with an Apple IR Receiver, switching it from using appleir to using lirc's macmini driver. Signed-off-by: Bastien Nocera Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index b1344ec4b7fc..f1f2b6f0d1c4 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -308,11 +308,13 @@ struct hid_item { #define HID_QUIRK_NOTOUCH 0x00000002 #define HID_QUIRK_IGNORE 0x00000004 #define HID_QUIRK_NOGET 0x00000008 +#define HID_QUIRK_HIDDEV_FORCE 0x00000010 #define HID_QUIRK_BADPAD 0x00000020 #define HID_QUIRK_MULTI_INPUT 0x00000040 #define HID_QUIRK_SKIP_OUTPUT_REPORTS 0x00010000 #define HID_QUIRK_FULLSPEED_INTERVAL 0x10000000 #define HID_QUIRK_NO_INIT_REPORTS 0x20000000 +#define HID_QUIRK_NO_IGNORE 0x40000000 /* * This is the global environment of the parser. This information is -- cgit v1.2.3 From edd5bdaf128e04066caac84fcb21377197ea0d64 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Wed, 14 Apr 2010 22:30:18 +0200 Subject: firewire: core: clean up config ROM related defined constants Clemens Ladisch pointed out that - BIB_IMC is not named like the field is called in the standard, - readers of the code may get worried about the magic 0x0c0083c0, - a CSR_NODE_CAPABILITIES key is there in the header but not put to good use. So let's rename BIB_IMC, add a defined constant for Node_Capabilities and a comment which reassures people that somebody thought about it and they don't have to (or if they still do, tell them where they have to look for confirmation), and prune our incomplete and arbitrary set of defined constants of CSR key IDs. And there is a nother magic number, that of Bus_Information_Block.Bus_Name, to be defined and commented. Signed-off-by: Stefan Richter --- include/linux/firewire.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 4bd94bf5e739..a527d73f9966 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -55,13 +55,11 @@ #define CSR_DESCRIPTOR 0x01 #define CSR_VENDOR 0x03 #define CSR_HARDWARE_VERSION 0x04 -#define CSR_NODE_CAPABILITIES 0x0c #define CSR_UNIT 0x11 #define CSR_SPECIFIER_ID 0x12 #define CSR_VERSION 0x13 #define CSR_DEPENDENT_INFO 0x14 #define CSR_MODEL 0x17 -#define CSR_INSTANCE 0x18 #define CSR_DIRECTORY_ID 0x20 struct fw_csr_iterator { -- cgit v1.2.3 From 7f1dc8a2d2f45fc557b27fd56115338b1d34fc24 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Wed, 21 Apr 2010 17:44:16 +0200 Subject: blkio: Fix blkio crash during rq stat update blkio + cfq was crashing even when two sequential readers were put in two separate cgroups (group_isolation=0). The reason being that cfqq can migrate across groups based on its being sync-noidle or not, it can happen that at request insertion time, cfqq belonged to one cfqg and at request dispatch time, it belonged to root group. In this case request stats per cgroup can go wrong and it also runs into BUG_ON(). This patch implements rq stashing away a cfq group pointer and not relying on cfqq->cfqg pointer alone for rq stat accounting. [ 65.163523] ------------[ cut here ]------------ [ 65.164301] kernel BUG at block/blk-cgroup.c:117! [ 65.164301] invalid opcode: 0000 [#1] SMP [ 65.164301] last sysfs file: /sys/devices/pci0000:00/0000:00:05.0/0000:60:00.1/host9/rport-9:0-0/target9:0:0/9:0:0:2/block/sde/stat [ 65.164301] CPU 1 [ 65.164301] Modules linked in: dm_round_robin dm_multipath qla2xxx scsi_transport_fc dm_zero dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan] [ 65.164301] [ 65.164301] Pid: 4505, comm: fio Not tainted 2.6.34-rc4-blk-for-35 #34 0A98h/HP xw8600 Workstation [ 65.164301] RIP: 0010:[] [] blkiocg_update_io_remove_stats+0x5b/0xaf [ 65.164301] RSP: 0018:ffff8800ba5a79e8 EFLAGS: 00010046 [ 65.164301] RAX: 0000000000000096 RBX: ffff8800bb268d60 RCX: 0000000000000000 [ 65.164301] RDX: ffff8800bb268eb8 RSI: 0000000000000000 RDI: ffff8800bb268e00 [ 65.164301] RBP: ffff8800ba5a7a08 R08: 0000000000000064 R09: 0000000000000001 [ 65.164301] R10: 0000000000079640 R11: ffff8800a0bd5bf0 R12: ffff8800bab4af01 [ 65.164301] R13: ffff8800bab4af00 R14: ffff8800bb1d8928 R15: 0000000000000000 [ 65.164301] FS: 00007f18f75056f0(0000) GS:ffff880001e40000(0000) knlGS:0000000000000000 [ 65.164301] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 65.164301] CR2: 000000000040e7f0 CR3: 00000000ba52b000 CR4: 00000000000006e0 [ 65.164301] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 65.164301] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 65.164301] Process fio (pid: 4505, threadinfo ffff8800ba5a6000, task ffff8800ba45ae80) [ 65.164301] Stack: [ 65.164301] ffff8800ba5a7a08 ffff8800ba722540 ffff8800bab4af68 ffff8800bab4af68 [ 65.164301] <0> ffff8800ba5a7a38 ffffffff8121d814 ffff8800ba722540 ffff8800bab4af68 [ 65.164301] <0> ffff8800ba722540 ffff8800a08f6800 ffff8800ba5a7a68 ffffffff8121d8ca [ 65.164301] Call Trace: [ 65.164301] [] cfq_remove_request+0xe4/0x116 [ 65.164301] [] cfq_dispatch_insert+0x84/0xe1 [ 65.164301] [] cfq_dispatch_requests+0x767/0x8e8 [ 65.164301] [] ? submit_bio+0xc3/0xcc [ 65.164301] [] ? sync_page_killable+0x0/0x35 [ 65.164301] [] blk_peek_request+0x191/0x1a7 [ 65.164301] [] ? dm_get_live_table+0x44/0x4f [dm_mod] [ 65.164301] [] dm_request_fn+0x38/0x14c [dm_mod] [ 65.164301] [] ? sync_page_killable+0x0/0x35 [ 65.164301] [] __generic_unplug_device+0x32/0x37 [ 65.164301] [] generic_unplug_device+0x2e/0x3c [ 65.164301] [] dm_unplug_all+0x42/0x5b [dm_mod] [ 65.164301] [] blk_unplug+0x29/0x2d [ 65.164301] [] blk_backing_dev_unplug+0x12/0x14 [ 65.164301] [] block_sync_page+0x35/0x39 [ 65.164301] [] sync_page+0x41/0x4a [ 65.164301] [] sync_page_killable+0xe/0x35 [ 65.164301] [] __wait_on_bit_lock+0x46/0x8f [ 65.164301] [] __lock_page_killable+0x66/0x6d [ 65.164301] [] ? wake_bit_function+0x0/0x33 [ 65.164301] [] lock_page_killable+0x2c/0x2e [ 65.164301] [] generic_file_aio_read+0x361/0x4f0 [ 65.164301] [] do_sync_read+0xcb/0x108 [ 65.164301] [] ? security_file_permission+0x16/0x18 [ 65.164301] [] vfs_read+0xab/0x108 [ 65.164301] [] sys_read+0x4a/0x6e [ 65.164301] [] system_call_fastpath+0x16/0x1b [ 65.164301] Code: 00 74 1c 48 8b 8b 60 01 00 00 48 85 c9 75 04 0f 0b eb fe 48 ff c9 48 89 8b 60 01 00 00 eb 1a 48 8b 8b 58 01 00 00 48 85 c9 75 04 <0f> 0b eb fe 48 ff c9 48 89 8b 58 01 00 00 45 84 e4 74 16 48 8b [ 65.164301] RIP [] blkiocg_update_io_remove_stats+0x5b/0xaf [ 65.164301] RSP [ 65.164301] ---[ end trace 1b2b828753032e68 ]--- Signed-off-by: Vivek Goyal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d483c494672a..5cf17a49ce38 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -186,11 +186,12 @@ struct request { }; /* - * two pointers are available for the IO schedulers, if they need + * Three pointers are available for the IO schedulers, if they need * more they have to dynamically allocate it. */ void *elevator_private; void *elevator_private2; + void *elevator_private3; struct gendisk *rq_disk; unsigned long start_time; -- cgit v1.2.3 From c10207fe86b1761c3ad135eb922fdb41bbde3025 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 19 Feb 2010 11:00:45 +0100 Subject: KVM: PPC: Add capability for paired singles We need to tell userspace that we can emulate paired single instructions. So let's add a capability export. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 60df9c84ecae..360f85e8c435 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -501,6 +501,7 @@ struct kvm_ioeventfd { #define KVM_CAP_HYPERV_VAPIC 45 #define KVM_CAP_HYPERV_SPIN 46 #define KVM_CAP_PCI_SEGMENT 47 +#define KVM_CAP_PPC_PAIRED_SINGLES 48 #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 48005f64d0ea965d454e38b5181af4aba9bdef5b Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Fri, 19 Feb 2010 19:38:07 +0100 Subject: KVM: x86: Save&restore interrupt shadow mask The interrupt shadow created by STI or MOV-SS-like operations is part of the VCPU state and must be preserved across migration. Transfer it in the spare padding field of kvm_vcpu_events.interrupt. As a side effect we now have to make vmx_set_interrupt_shadow robust against both shadow types being set. Give MOV SS a higher priority and skip STI in that case to avoid that VMX throws a fault on next entry. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- include/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 360f85e8c435..48516a2a0b84 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -502,6 +502,7 @@ struct kvm_ioeventfd { #define KVM_CAP_HYPERV_SPIN 46 #define KVM_CAP_PCI_SEGMENT 47 #define KVM_CAP_PPC_PAIRED_SINGLES 48 +#define KVM_CAP_INTR_SHADOW 49 #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From a1efbe77c1fd7c34a97a76a61520bf23fb3663f6 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 15 Feb 2010 10:45:43 +0100 Subject: KVM: x86: Add support for saving&restoring debug registers So far user space was not able to save and restore debug registers for migration or after reset. Plug this hole. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- include/linux/kvm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 48516a2a0b84..ce2876717a8b 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -503,6 +503,9 @@ struct kvm_ioeventfd { #define KVM_CAP_PCI_SEGMENT 47 #define KVM_CAP_PPC_PAIRED_SINGLES 48 #define KVM_CAP_INTR_SHADOW 49 +#ifdef __KVM_HAVE_DEBUGREGS +#define KVM_CAP_DEBUGREGS 50 +#endif #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 #ifdef KVM_CAP_IRQ_ROUTING @@ -690,6 +693,9 @@ struct kvm_clock_data { /* Available with KVM_CAP_VCPU_EVENTS */ #define KVM_GET_VCPU_EVENTS _IOR(KVMIO, 0x9f, struct kvm_vcpu_events) #define KVM_SET_VCPU_EVENTS _IOW(KVMIO, 0xa0, struct kvm_vcpu_events) +/* Available with KVM_CAP_DEBUGREGS */ +#define KVM_GET_DEBUGREGS _IOR(KVMIO, 0xa1, struct kvm_debugregs) +#define KVM_SET_DEBUGREGS _IOW(KVMIO, 0xa2, struct kvm_debugregs) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -- cgit v1.2.3 From 9b9ade6b612e562c4a5bd02ef38cc32e10f3f9ba Mon Sep 17 00:00:00 2001 From: Yulia Vilensky Date: Mon, 26 Apr 2010 14:05:25 +0300 Subject: ds2782_battery: Add support for ds2786 battery gas gauge Signed-off-by: Yulia Vilensky Signed-off-by: Mike Rapoport Signed-off-by: Anton Vorontsov --- include/linux/ds2782_battery.h | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 include/linux/ds2782_battery.h (limited to 'include/linux') diff --git a/include/linux/ds2782_battery.h b/include/linux/ds2782_battery.h new file mode 100644 index 000000000000..b4e281f65c15 --- /dev/null +++ b/include/linux/ds2782_battery.h @@ -0,0 +1,8 @@ +#ifndef __LINUX_DS2782_BATTERY_H +#define __LINUX_DS2782_BATTERY_H + +struct ds278x_platform_data { + int rsns; +}; + +#endif -- cgit v1.2.3 From 6b4517a7913a09d3259bb1d21c9cb300f12294bd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 7 Apr 2010 18:53:59 +0900 Subject: block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo Reported-by: Matthias-Christian Ott Cc: Kay Sievers Signed-off-by: Jens Axboe --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 39d57bc6cc71..31ee31be51e9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -651,6 +651,7 @@ struct block_device { int bd_openers; struct mutex bd_mutex; /* open/close mutex */ struct list_head bd_inodes; + void * bd_claiming; void * bd_holder; int bd_holders; #ifdef CONFIG_SYSFS -- cgit v1.2.3 From 6a740aa4f47b9f29bad5292cf51f008f3edad9b1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bruno=20Pr=C3=A9mont?= Date: Sun, 25 Apr 2010 21:40:03 +0200 Subject: HID: add suspend/resume hooks for hid drivers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add suspend/resume hooks for HID drivers so these can do some additional state adjustment when device gets suspended/resumed. Signed-off-by: Bruno Prémont Signed-off-by: Jiri Kosina --- include/linux/hid.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index b1344ec4b7fc..069e587ae8e6 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -589,6 +589,9 @@ struct hid_usage_id { * @report_fixup: called before report descriptor parsing (NULL means nop) * @input_mapping: invoked on input registering before mapping an usage * @input_mapped: invoked on input registering after mapping an usage + * @suspend: invoked on suspend (NULL means nop) + * @resume: invoked on resume if device was not reset (NULL means nop) + * @reset_resume: invoked on resume if device was reset (NULL means nop) * * raw_event and event should return 0 on no action performed, 1 when no * further processing should be done and negative on error @@ -629,6 +632,11 @@ struct hid_driver { int (*input_mapped)(struct hid_device *hdev, struct hid_input *hidinput, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max); +#ifdef CONFIG_PM + int (*suspend)(struct hid_device *hdev, pm_message_t message); + int (*resume)(struct hid_device *hdev); + int (*reset_resume)(struct hid_device *hdev); +#endif /* private: */ struct device_driver driver; }; -- cgit v1.2.3 From fbd9b09a177a481eda256447c881f014f29034fe Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Wed, 28 Apr 2010 17:55:06 +0400 Subject: blkdev: generalize flags for blkdev_issue_fn functions The patch just convert all blkdev_issue_xxx function to common set of flags. Wait/allocation semantics preserved. Signed-off-by: Dmitry Monakhov Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5cf17a49ce38..59b9aed0ee7d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -998,12 +998,16 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, return NULL; return bqt->tag_index[tag]; } - -extern int blkdev_issue_flush(struct block_device *, sector_t *); -#define DISCARD_FL_WAIT 0x01 /* wait for completion */ -#define DISCARD_FL_BARRIER 0x02 /* issue DISCARD_BARRIER request */ -extern int blkdev_issue_discard(struct block_device *, sector_t sector, - sector_t nr_sects, gfp_t, int flags); +enum{ + BLKDEV_WAIT, /* wait for completion */ + BLKDEV_BARRIER, /*issue request with barrier */ +}; +#define BLKDEV_IFL_WAIT (1 << BLKDEV_WAIT) +#define BLKDEV_IFL_BARRIER (1 << BLKDEV_BARRIER) +extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *, + unsigned long); +extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks) @@ -1011,7 +1015,7 @@ static inline int sb_issue_discard(struct super_block *sb, block <<= (sb->s_blocksize_bits - 9); nr_blocks <<= (sb->s_blocksize_bits - 9); return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL, - DISCARD_FL_BARRIER); + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); } extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); -- cgit v1.2.3 From 3f14d792f9a8fede64ce918dbb517f934497a4f8 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Wed, 28 Apr 2010 17:55:09 +0400 Subject: blkdev: add blkdev_issue_zeroout helper function - Add bio_batch helper primitive. This is rather generic primitive for submitting/waiting a complex request which consists of several bios. - blkdev_issue_zeroout() generate number of zero filed write bios. Signed-off-by: Dmitry Monakhov Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 59b9aed0ee7d..3ac2bd2fc485 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1008,7 +1008,8 @@ extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *, unsigned long); extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); - +extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks) { -- cgit v1.2.3 From da6df07794d92cd159e28e2cb1947d8b33913e2f Mon Sep 17 00:00:00 2001 From: Daniel Walker Date: Fri, 23 Apr 2010 16:04:20 -0700 Subject: drivers: video: msm: add include msm_mdp.h Needed to get the driver to compile ;( Signed-off-by: Daniel Walker --- include/linux/msm_mdp.h | 78 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) create mode 100644 include/linux/msm_mdp.h (limited to 'include/linux') diff --git a/include/linux/msm_mdp.h b/include/linux/msm_mdp.h new file mode 100644 index 000000000000..d11fe0f2f956 --- /dev/null +++ b/include/linux/msm_mdp.h @@ -0,0 +1,78 @@ +/* include/linux/msm_mdp.h + * + * Copyright (C) 2007 Google Incorporated + * + * 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 _MSM_MDP_H_ +#define _MSM_MDP_H_ + +#include + +#define MSMFB_IOCTL_MAGIC 'm' +#define MSMFB_GRP_DISP _IOW(MSMFB_IOCTL_MAGIC, 1, unsigned int) +#define MSMFB_BLIT _IOW(MSMFB_IOCTL_MAGIC, 2, unsigned int) + +enum { + MDP_RGB_565, /* RGB 565 planar */ + MDP_XRGB_8888, /* RGB 888 padded */ + MDP_Y_CBCR_H2V2, /* Y and CbCr, pseudo planar w/ Cb is in MSB */ + MDP_ARGB_8888, /* ARGB 888 */ + MDP_RGB_888, /* RGB 888 planar */ + MDP_Y_CRCB_H2V2, /* Y and CrCb, pseudo planar w/ Cr is in MSB */ + MDP_YCRYCB_H2V1, /* YCrYCb interleave */ + MDP_Y_CRCB_H2V1, /* Y and CrCb, pseduo planar w/ Cr is in MSB */ + MDP_Y_CBCR_H2V1, /* Y and CrCb, pseduo planar w/ Cr is in MSB */ + MDP_RGBA_8888, /* ARGB 888 */ + MDP_BGRA_8888, /* ABGR 888 */ + MDP_IMGTYPE_LIMIT /* Non valid image type after this enum */ +}; + +enum { + PMEM_IMG, + FB_IMG, +}; + +/* flag values */ +#define MDP_ROT_NOP 0 +#define MDP_FLIP_LR 0x1 +#define MDP_FLIP_UD 0x2 +#define MDP_ROT_90 0x4 +#define MDP_ROT_180 (MDP_FLIP_UD|MDP_FLIP_LR) +#define MDP_ROT_270 (MDP_ROT_90|MDP_FLIP_UD|MDP_FLIP_LR) +#define MDP_DITHER 0x8 +#define MDP_BLUR 0x10 + +#define MDP_TRANSP_NOP 0xffffffff +#define MDP_ALPHA_NOP 0xff + +struct mdp_rect { + u32 x, y, w, h; +}; + +struct mdp_img { + u32 width, height, format, offset; + int memory_id; /* the file descriptor */ +}; + +struct mdp_blit_req { + struct mdp_img src; + struct mdp_img dst; + struct mdp_rect src_rect; + struct mdp_rect dst_rect; + u32 alpha, transp_mask, flags; +}; + +struct mdp_blit_req_list { + u32 count; + struct mdp_blit_req req[]; +}; + +#endif /* _MSM_MDP_H_ */ -- cgit v1.2.3 From cf32eb89cb4e674f88e4af5025839d85d02485c6 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 13 Apr 2010 16:12:25 -0700 Subject: of/flattree: make of_fdt.h safe to unconditionally include. If CONFIG_OF_FLATTREE is not set, then don't process the body of linux/of_fdt.h Signed-off-by: Grant Likely --- include/linux/of_fdt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index a1ca92ccb0ff..f0fdd1f43688 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -57,6 +57,7 @@ struct boot_param_header { __be32 dt_struct_size; /* size of the DT structure block */ }; +#if defined(CONFIG_OF_FLATTREE) /* TBD: Temporary export of fdt globals - remove when code fully merged */ extern int __initdata dt_root_addr_cells; extern int __initdata dt_root_size_cells; @@ -98,6 +99,7 @@ extern int early_init_dt_scan_root(unsigned long node, const char *uname, /* Other Prototypes */ extern void unflatten_device_tree(void); extern void early_init_devtree(void *); +#endif /* CONFIG_OF_FLATTREE */ #endif /* __ASSEMBLY__ */ #endif /* _LINUX_OF_FDT_H */ -- cgit v1.2.3 From 8bfe9b5c3a684fe39eb58a65e466c103d1c32c9a Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 13 Apr 2010 16:12:26 -0700 Subject: of/flattree: Make unflatten_device_tree() safe to call from any arch This patch makes unflatten_device_tree() safe to call from any arch setup code with the following changes: - Make sure initial_boot_params actually points to a device tree blob before unflattening - Make sure the initial_boot_params->magic field is correct - If CONFIG_OF_FLATTREE is not set, then make unflatten_device_tree() an empty static inline function. This patch also adds some additional debug output to the top of unflatten_device_tree(). Signed-off-by: Grant Likely --- include/linux/of_fdt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index f0fdd1f43688..71e1a916d3fa 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -99,6 +99,8 @@ extern int early_init_dt_scan_root(unsigned long node, const char *uname, /* Other Prototypes */ extern void unflatten_device_tree(void); extern void early_init_devtree(void *); +#else /* CONFIG_OF_FLATTREE */ +static inline void unflatten_device_tree(void) {} #endif /* CONFIG_OF_FLATTREE */ #endif /* __ASSEMBLY__ */ -- cgit v1.2.3 From efb2e014fc4f2675011b802e1a84bf9a58756004 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 13 Apr 2010 16:12:27 -0700 Subject: of: protect contents of of_platform.h and of_device.h Only process contents of of_platform.h and of_device.h if CONFIG_OF_DEVICE is set. Signed-off-by: Grant Likely --- include/linux/of_device.h | 2 ++ include/linux/of_platform.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index d3a74e00a3e1..e7904a9cd3a3 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -1,6 +1,7 @@ #ifndef _LINUX_OF_DEVICE_H #define _LINUX_OF_DEVICE_H +#ifdef CONFIG_OF_DEVICE #include #include #include @@ -26,5 +27,6 @@ static inline void of_device_free(struct of_device *dev) extern ssize_t of_device_get_modalias(struct of_device *ofdev, char *str, ssize_t len); +#endif /* CONFIG_OF_DEVICE */ #endif /* _LINUX_OF_DEVICE_H */ diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 908406651330..ac3ae0758fbe 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -11,6 +11,7 @@ * */ +#ifdef CONFIG_OF_DEVICE #include #include #include @@ -66,5 +67,6 @@ static inline void of_unregister_platform_driver(struct of_platform_driver *drv) extern struct of_device *of_find_device_by_node(struct device_node *np); extern int of_bus_type_init(struct bus_type *bus, const char *name); +#endif /* CONFIG_OF_DEVICE */ #endif /* _LINUX_OF_PLATFORM_H */ -- cgit v1.2.3 From d706c1b050274b3bf97d7cb0542c0d070c9ccb8b Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 13 Apr 2010 16:12:28 -0700 Subject: driver-core: Add device node pointer to struct device Currently, platforms using CONFIG_OF add a 'struct device_node *of_node' to dev->archdata. However, with CONFIG_OF becoming generic for all architectures, it makes sense for commonality to move it out of archdata and into struct device proper. This patch adds a struct device_node *of_node member to struct device and updates all locations which currently write the device_node pointer into archdata to also update dev->of_node. Subsequent patches will modify callers to use the archdata location and ultimately remove the archdata member entirely. Signed-off-by: Grant Likely Acked-by: Greg Kroah-Hartman CC: Michal Simek CC: Greg Kroah-Hartman CC: Benjamin Herrenschmidt CC: "David S. Miller" CC: Stephen Rothwell CC: Jeremy Kerr CC: microblaze-uclinux@itee.uq.edu.au CC: linux-kernel@vger.kernel.org CC: linuxppc-dev@ozlabs.org CC: sparclinux@vger.kernel.org --- include/linux/device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 182192892d45..7a968bdb02e2 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -34,6 +34,7 @@ struct class; struct class_private; struct bus_type; struct bus_type_private; +struct device_node; struct bus_attribute { struct attribute attr; @@ -433,6 +434,9 @@ struct device { override */ /* arch specific additions */ struct dev_archdata archdata; +#ifdef CONFIG_OF + struct device_node *of_node; +#endif dev_t devt; /* dev_t, creates the sysfs "dev" */ -- cgit v1.2.3 From d12d42f744f805a9ccc33cd76f04b237cd83ce56 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 13 Apr 2010 16:12:28 -0700 Subject: i2c/of: Allow device node to be passed via i2c_board_info The struct device_node *of_node pointer is moving out of dev->archdata and into the struct device proper. of_i2c.c needs to set the of_node pointer before the device is registered. Since the i2c subsystem doesn't allow 2 stage allocation and registration of i2c devices, the of_node pointer needs to be passed via the i2c_board_info structure so that it is set prior to registration. This patch adds of_node to struct i2c_board_info (conditional on CONFIG_OF), sets of_node in i2c_new_device(), and modifies of_i2c.c to use the new parameter. The calling of dev_archdata_set_node() from of_i2c will be removed in a subsequent patch when of_node is removed from archdata and all users are converted over. Signed-off-by: Grant Likely --- include/linux/i2c.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 0a5da639b327..4f37ff1de7e1 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -34,6 +34,7 @@ #include /* for struct device */ #include /* for completion */ #include +#include /* for struct device_node */ extern struct bus_type i2c_bus_type; @@ -251,6 +252,9 @@ struct i2c_board_info { unsigned short addr; void *platform_data; struct dev_archdata *archdata; +#ifdef CONFIG_OF + struct device_node *of_node; +#endif int irq; }; -- cgit v1.2.3 From 5a2e3995951176e1aaa63d17ae2e1d26ac99003d Mon Sep 17 00:00:00 2001 From: Kei Tokunaga Date: Thu, 1 Apr 2010 20:40:58 +0900 Subject: [SCSI] ftrace: add __print_hex() __print_hex() prints values in an array in hex (w/o '0x') (space separated) EX) 92 33 32 f3 ee 4d Signed-off-by: Li Zefan Signed-off-by: Tomohiro Kusumi Signed-off-by: Kei Tokunaga Acked-by: Steven Rostedt Signed-off-by: James Bottomley --- include/linux/ftrace_event.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index c0f4b364c711..c3c5aaaae53a 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -25,6 +25,9 @@ const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim, const char *ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val, const struct trace_print_flags *symbol_array); +const char *ftrace_print_hex_seq(struct trace_seq *p, + const unsigned char *buf, int len); + /* * The trace entry - the most basic unit of tracing. This is what * is printed in the end as a single line in the trace output, such as: -- cgit v1.2.3 From 37e11f3397fab21604bff506cb31ffbf70fb255a Mon Sep 17 00:00:00 2001 From: Qinghuang Feng Date: Sun, 25 Apr 2010 20:17:25 +0800 Subject: nilfs2: update comment for struct nilfs_dat_entry The comment of struct nilfs_dat_entry is mismatched, fix it. Signed-off-by: Qinghuang Feng Signed-off-by: Ryusuke Konishi --- include/linux/nilfs2_fs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index 640702e97457..478ee34e9d65 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -437,10 +437,10 @@ struct nilfs_palloc_group_desc { /** * struct nilfs_dat_entry - disk address translation entry - * @dt_blocknr: block number - * @dt_start: start checkpoint number - * @dt_end: end checkpoint number - * @dt_rsv: reserved for future use + * @de_blocknr: block number + * @de_start: start checkpoint number + * @de_end: end checkpoint number + * @de_rsv: reserved for future use */ struct nilfs_dat_entry { __le64 de_blocknr; -- cgit v1.2.3 From 0d9cc2332df24d3e81060c782b2ecb87c28443f9 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Mon, 26 Apr 2010 01:17:48 +0900 Subject: nilfs2: fix style problems in nilfs2_fs.h This kills the following checkpatch warnings: WARNING: please, no space before tabs +^I__le32^Is_first_ino; ^I^I/* First non-reserved inode */$ WARNING: please, no space before tabs +^I__le16 s_inode_size; ^I^I/* Size of an inode */$ WARNING: please, no space before tabs +^Ichar^Is_volume_name[16]; ^I/* volume name */$ WARNING: please, no space before tabs +^Ichar^Is_last_mounted[64]; ^I/* directory where last mounted */$ Signed-off-by: Ryusuke Konishi --- include/linux/nilfs2_fs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index 478ee34e9d65..f960e1d264e8 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -199,16 +199,16 @@ struct nilfs_super_block { __le32 s_creator_os; /* OS */ __le16 s_def_resuid; /* Default uid for reserved blocks */ __le16 s_def_resgid; /* Default gid for reserved blocks */ - __le32 s_first_ino; /* First non-reserved inode */ + __le32 s_first_ino; /* First non-reserved inode */ - __le16 s_inode_size; /* Size of an inode */ + __le16 s_inode_size; /* Size of an inode */ __le16 s_dat_entry_size; /* Size of a dat entry */ __le16 s_checkpoint_size; /* Size of a checkpoint */ __le16 s_segment_usage_size; /* Size of a segment usage */ __u8 s_uuid[16]; /* 128-bit uuid for volume */ - char s_volume_name[16]; /* volume name */ - char s_last_mounted[64]; /* directory where last mounted */ + char s_volume_name[16]; /* volume name */ + char s_last_mounted[64]; /* directory where last mounted */ __le32 s_c_interval; /* Commit interval of segment */ __le32 s_c_block_max; /* Threshold of data amount for -- cgit v1.2.3 From 50614bcf29d0cec6df5b84c0d8331e8b8c7d72a7 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Sat, 10 Apr 2010 17:59:15 +0900 Subject: nilfs2: insert checkpoint number in segment summary header This adds a field to record the latest checkpoint number in the nilfs_segment_summary structure. This will help to recover the latest checkpoint number from logs on disk. This field is intended for crucial cases in which super blocks have lost pointer to the latest log. Even though this will change the disk format, both backward and forward compatibility is preserved by a size field prepared in the segment summary header. Signed-off-by: Ryusuke Konishi --- include/linux/nilfs2_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index f960e1d264e8..6505c00f1fc1 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -377,6 +377,7 @@ union nilfs_binfo { * @ss_nfinfo: number of finfo structures * @ss_sumbytes: total size of segment summary in bytes * @ss_pad: padding + * @ss_cno: checkpoint number */ struct nilfs_segment_summary { __le32 ss_datasum; @@ -391,6 +392,7 @@ struct nilfs_segment_summary { __le32 ss_nfinfo; __le32 ss_sumbytes; __le32 ss_pad; + __le64 ss_cno; /* array of finfo structures */ }; -- cgit v1.2.3 From 400ade845cb9930552e791bbd658a0953f68499d Mon Sep 17 00:00:00 2001 From: Jiro SEKIBA Date: Sun, 2 May 2010 23:29:04 +0900 Subject: nilfs2: enlarge s_volume_name member in nilfs_super_block Current s_volume_name has 16 bytes, which is too small as modern filesystem. s_last_mounted resides just after s_volume_name and has 64 bytes. s_last_mounted is historically came from ext2, but not used in nilfs2 at all. Deleting s_last_mounted member and merging that space with s_volume_name enlarge s_volume_name upto 80 bytes for volume label. When user land tools see the old header for new disk, it will just ignore additional bytes stored in s_last_mounted. While, old disk format has only 16 bytes label, it doesn't affects in case seeing the new header for old disk. Signed-off-by: Jiro SEKIBA Signed-off-by: Ryusuke Konishi --- include/linux/nilfs2_fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index 6505c00f1fc1..8c2c6116e788 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -207,8 +207,7 @@ struct nilfs_super_block { __le16 s_segment_usage_size; /* Size of a segment usage */ __u8 s_uuid[16]; /* 128-bit uuid for volume */ - char s_volume_name[16]; /* volume name */ - char s_last_mounted[64]; /* directory where last mounted */ + char s_volume_name[80]; /* volume name */ __le32 s_c_interval; /* Commit interval of segment */ __le32 s_c_block_max; /* Threshold of data amount for -- cgit v1.2.3 From 0a382a74b677360096857bcb5288c340fca671ed Mon Sep 17 00:00:00 2001 From: Andrea Gelmini Date: Sat, 27 Feb 2010 17:51:37 +0100 Subject: mtd: mtdram.h: checkpatch cleanup include/linux/mtd/mtdram.h:6: ERROR: code indent should use tabs where possible Signed-off-by: Andrea Gelmini Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/mtdram.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtdram.h b/include/linux/mtd/mtdram.h index 04fdc07b7353..68891313875d 100644 --- a/include/linux/mtd/mtdram.h +++ b/include/linux/mtd/mtdram.h @@ -3,6 +3,6 @@ #include int mtdram_init_device(struct mtd_info *mtd, void *mapped_address, - unsigned long size, char *name); + unsigned long size, char *name); #endif /* __MTD_MTDRAM_H__ */ -- cgit v1.2.3 From 67026418f534045525a7c39f506006cd7fbd197f Mon Sep 17 00:00:00 2001 From: Ferenc Wagner Date: Tue, 23 Mar 2010 18:09:09 +0100 Subject: mtd/nand/sh_flctl: Replace the dangerous mtd_to_flctl macro The original macro worked only when applied to variables named 'mtd'. While this could have been fixed by simply renaming the macro argument, a more type-safe replacement is preferred. Signed-off-by: Ferenc Wagner Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/sh_flctl.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h index ab77609ec337..178b5c26c995 100644 --- a/include/linux/mtd/sh_flctl.h +++ b/include/linux/mtd/sh_flctl.h @@ -93,7 +93,10 @@ #define INIT_FL4ECCRESULT_VAL 0x03FF03FF #define LOOP_TIMEOUT_MAX 0x00010000 -#define mtd_to_flctl(mtd) container_of(mtd, struct sh_flctl, mtd) +static inline struct sh_flctl *mtd_to_flctl(struct mtd_info *mtdinfo) +{ + return container_of(mtdinfo, struct sh_flctl, mtd); +} struct sh_flctl { struct mtd_info mtd; -- cgit v1.2.3 From c4e773764cead9358fd4b036d1b883fff3968513 Mon Sep 17 00:00:00 2001 From: Stefani Seibold Date: Sun, 18 Apr 2010 22:46:44 +0200 Subject: mtd: fix a huge latency problem in the MTD CFI and LPDDR flash drivers. The use of a memcpy() during a spinlock operation will cause very long thread context switch delays if the flash chip bandwidth is low and the data to be copied large, because a spinlock will disable preemption. For example: A flash with 6,5 MB/s bandwidth will cause under ubifs, which request sometimes 128 KiB (the flash erase size), a preemption delay of 20 milliseconds. High priority threads will not be served during this time, regardless whether this threads access the flash or not. This behavior breaks real time. The patch changes all the use of spin_lock operations for xxxx->mutex into mutex operations, which is exact what the name says and means. I have checked the code of the drivers and there is no use of atomic pathes like interrupt or timers. The mtdoops facility will also not be used by this drivers. So it is dave to replace the spin_lock against mutex. There is no performance regression since the mutex is normally not acquired. Changelog: 06.03.2010 First release 26.03.2010 Fix mutex[1] issue and tested it for compile failure Signed-off-by: Stefani Seibold Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/flashchip.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h index d0bf422ae374..f43e9b49b751 100644 --- a/include/linux/mtd/flashchip.h +++ b/include/linux/mtd/flashchip.h @@ -15,6 +15,7 @@ * has asm/spinlock.h, or 2.4, which has linux/spinlock.h */ #include +#include typedef enum { FL_READY, @@ -74,8 +75,7 @@ struct flchip { unsigned int erase_suspended:1; unsigned long in_progress_block_addr; - spinlock_t *mutex; - spinlock_t _spinlock; /* We do it like this because sometimes they'll be shared. */ + struct mutex mutex; wait_queue_head_t wq; /* Wait on here when we're waiting for the chip to be ready */ int word_write_time; -- cgit v1.2.3 From 01effb0dc1451fad55925873ffbfb88fa4eadce0 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 11 May 2010 08:57:42 +0200 Subject: block: allow initialization of previously allocated request_queue blk_init_queue() allocates the request_queue structure and then initializes it as needed (request_fn, elevator, etc). Split initialization out to blk_init_allocated_queue_node. Introduce blk_init_allocated_queue wrapper function to model existing blk_init_queue and blk_init_queue_node interfaces. Export elv_register_queue to allow a newly added elevator to be registered with sysfs. Export elv_unregister_queue for symmetry. These changes allow DM to initialize a device's request_queue with more precision. In particular, DM no longer unconditionally initializes a full request_queue (elevator et al). It only does so for a request-based DM device. Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3ac2bd2fc485..346fd4856733 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -921,7 +921,12 @@ extern void blk_abort_queue(struct request_queue *); */ extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id); +extern struct request_queue *blk_init_allocated_queue_node(struct request_queue *, + request_fn_proc *, + spinlock_t *, int node_id); extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *); +extern struct request_queue *blk_init_allocated_queue(struct request_queue *, + request_fn_proc *, spinlock_t *); extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); -- cgit v1.2.3 From 8b6d043b7ee2d1b819dc833d677ea2aead71a0c0 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Mon, 29 Mar 2010 19:38:00 +0200 Subject: resource: shared I/O region support SuperIO devices share regions and use lock/unlock operations to chip select. We therefore need to be able to request a resource and wait for it to be freed by whichever other SuperIO device currently hogs it. Right now you have to poll which is horrible. Add a MUXED field to IO port resources. If the MUXED field is set on the resource and on the request (via request_muxed_region) then we block until the previous owner of the muxed resource releases their region. This allows us to implement proper resource sharing and locking for superio chips using code of the form enable_my_superio_dev() { request_muxed_region(0x44, 0x02, "superio:watchdog"); outb() ..sequence to enable chip } disable_my_superio_dev() { outb() .. sequence of disable chip release_region(0x44, 0x02); } Signed-off-by: Giel van Schijndel Signed-off-by: Alan Cox Signed-off-by: Jesse Barnes --- include/linux/ioport.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 26fad187d661..b22790268b64 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -52,6 +52,7 @@ struct resource_list { #define IORESOURCE_MEM_64 0x00100000 #define IORESOURCE_WINDOW 0x00200000 /* forwarded by bridge */ +#define IORESOURCE_MUXED 0x00400000 /* Resource is software muxed */ #define IORESOURCE_EXCLUSIVE 0x08000000 /* Userland may not map this resource */ #define IORESOURCE_DISABLED 0x10000000 @@ -143,7 +144,8 @@ static inline unsigned long resource_type(const struct resource *res) } /* Convenience shorthand with allocation */ -#define request_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name), 0) +#define request_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name), 0) +#define request_muxed_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name), IORESOURCE_MUXED) #define __request_mem_region(start,n,name, excl) __request_region(&iomem_resource, (start), (n), (name), excl) #define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name), 0) #define request_mem_region_exclusive(start,n,name) \ -- cgit v1.2.3 From f647a44f5725b0e6c8211096f4b49900164123ee Mon Sep 17 00:00:00 2001 From: Hidetoshi Seto Date: Thu, 15 Apr 2010 13:17:33 +0900 Subject: PCI: aerdrv: redefine PCI_ERR_ROOT_*_SRC The Error Source Identification Register (Offset 34h) is 4 byte which contains a couple of 2 byte field, "[15:0] ERR_COR Source Identification" and "[31:16] ERR_FATAL/NONFATAL Source Identification." This patch defines PCI_ERR_ROOT_ERR_SRC to make dword access sensible. Signed-off-by: Hidetoshi Seto Reviewed-by: Kenji Kaneshige Signed-off-by: Jesse Barnes --- include/linux/pci_regs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index c8f302991b66..dd0dd873f637 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -563,8 +563,7 @@ #define PCI_ERR_ROOT_FIRST_FATAL 0x00000010 /* First Fatal */ #define PCI_ERR_ROOT_NONFATAL_RCV 0x00000020 /* Non-Fatal Received */ #define PCI_ERR_ROOT_FATAL_RCV 0x00000040 /* Fatal Received */ -#define PCI_ERR_ROOT_COR_SRC 52 -#define PCI_ERR_ROOT_SRC 54 +#define PCI_ERR_ROOT_ERR_SRC 52 /* Error Source Identification */ /* Virtual Channel */ #define PCI_VC_PORT_REG1 4 -- cgit v1.2.3 From 33852cb03ee4cdb05dc6e3a21ec19a4ee63511a4 Mon Sep 17 00:00:00 2001 From: Seth Heasley Date: Thu, 25 Mar 2010 16:11:37 -0700 Subject: x86/PCI: irq and pci_ids patch for additional Intel Cougar Point DeviceIDs This patch adds additional LPC Controller DeviceIDs for the Intel Cougar Point PCH. The DeviceIDs are defined and referenced as a range of values, the same way Ibex Peak was implemented. Signed-off-by: Seth Heasley Signed-off-by: Jesse Barnes --- include/linux/pci_ids.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 9f688d243b86..ae66851870be 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2419,8 +2419,8 @@ #define PCI_DEVICE_ID_INTEL_82845_HB 0x1a30 #define PCI_DEVICE_ID_INTEL_IOAT 0x1a38 #define PCI_DEVICE_ID_INTEL_CPT_SMBUS 0x1c22 -#define PCI_DEVICE_ID_INTEL_CPT_LPC1 0x1c42 -#define PCI_DEVICE_ID_INTEL_CPT_LPC2 0x1c43 +#define PCI_DEVICE_ID_INTEL_CPT_LPC_MIN 0x1c41 +#define PCI_DEVICE_ID_INTEL_CPT_LPC_MAX 0x1c5f #define PCI_DEVICE_ID_INTEL_82801AA_0 0x2410 #define PCI_DEVICE_ID_INTEL_82801AA_1 0x2411 #define PCI_DEVICE_ID_INTEL_82801AA_3 0x2413 -- cgit v1.2.3 From b6dacf63e9fb2e7a1369843d6cef332f76fca6a3 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Tue, 11 May 2010 13:49:25 -0400 Subject: ACPI: Unconditionally set SCI_EN on resume The ACPI spec tells us that the firmware will reenable SCI_EN on resume. Reality disagrees in some cases. The ACPI spec tells us that the only way to set SCI_EN is via an SMM call. https://bugzilla.kernel.org/show_bug.cgi?id=13745 shows us that doing so may break machines. Tracing the ACPI calls made by Windows shows that it unconditionally sets SCI_EN on resume with a direct register write, and therefore the overwhelming probability is that everything is fine with this behaviour. Signed-off-by: Matthew Garrett Tested-by: Rafael J. Wysocki Signed-off-by: Len Brown --- include/linux/acpi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index b926afe8c03e..87ca4913294c 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -251,7 +251,6 @@ int acpi_check_mem_region(resource_size_t start, resource_size_t n, void __init acpi_no_s4_hw_signature(void); void __init acpi_old_suspend_ordering(void); void __init acpi_s4_no_nvs(void); -void __init acpi_set_sci_en_on_resume(void); #endif /* CONFIG_PM_SLEEP */ struct acpi_osc_context { -- cgit v1.2.3 From 1cd2620ca9332943c9fff84c0c9240982534d840 Mon Sep 17 00:00:00 2001 From: Peter Huewe Date: Thu, 13 May 2010 00:06:54 +0200 Subject: mtd/nand/sh_flctl: Move function mtd_to_flctl to fix build failure This patch fixes a build failure[1] by simply moving the function mtd_to_flctl beneath the definition of sh_flctl which it uses. BF introduced by patch 'mtd/nand/sh_flctl: Replace the dangerous mtd_to_flctl macro' (67026418) Signed-off-by: Peter Huewe Signed-off-by: David Woodhouse --- include/linux/mtd/sh_flctl.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h index 178b5c26c995..9cf4c4c79555 100644 --- a/include/linux/mtd/sh_flctl.h +++ b/include/linux/mtd/sh_flctl.h @@ -93,11 +93,6 @@ #define INIT_FL4ECCRESULT_VAL 0x03FF03FF #define LOOP_TIMEOUT_MAX 0x00010000 -static inline struct sh_flctl *mtd_to_flctl(struct mtd_info *mtdinfo) -{ - return container_of(mtdinfo, struct sh_flctl, mtd); -} - struct sh_flctl { struct mtd_info mtd; struct nand_chip chip; @@ -128,4 +123,9 @@ struct sh_flctl_platform_data { unsigned has_hwecc:1; }; +static inline struct sh_flctl *mtd_to_flctl(struct mtd_info *mtdinfo) +{ + return container_of(mtdinfo, struct sh_flctl, mtd); +} + #endif /* __SH_FLCTL_H__ */ -- cgit v1.2.3 From 54b93a49d8dd90dfb658f21a3316527fe6195106 Mon Sep 17 00:00:00 2001 From: Guillaume LECERF Date: Sat, 24 Apr 2010 17:58:02 +0200 Subject: mtd: cfi_probe: add support for SST 0x0701 vendorname SST 39VF160x and 39VF320x chips use vendorname id 0x0701 and alternative unlock addresses. Add support for them in cfi_probe.c. Signed-off-by: Guillaume LECERF Reviewed-by: Wolfram Sang Signed-off-by: David Woodhouse --- include/linux/mtd/cfi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index cee05b1e62b1..5716fc78ca8e 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -253,6 +253,7 @@ struct cfi_bri_query { #define P_ID_MITSUBISHI_STD 0x0100 #define P_ID_MITSUBISHI_EXT 0x0101 #define P_ID_SST_PAGE 0x0102 +#define P_ID_SST_OLD 0x0701 #define P_ID_INTEL_PERFORMANCE 0x0200 #define P_ID_INTEL_DATA 0x0210 #define P_ID_RESERVED 0xffff -- cgit v1.2.3 From ae731822294468f213f2b56a0ddfc425148c873b Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 27 Apr 2010 04:19:34 +0200 Subject: mtd: chips: use common manufacturer codes in jedec_probe() Factor out old manufacturers and use the generic ones from cfi.h Signed-off-by: Wolfram Sang Signed-off-by: David Woodhouse --- include/linux/mtd/cfi.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index 5716fc78ca8e..574d9ee066f1 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -516,16 +516,25 @@ struct cfi_fixup { void* param; }; -#define CFI_MFR_ANY 0xffff -#define CFI_ID_ANY 0xffff +#define CFI_MFR_ANY 0xFFFF +#define CFI_ID_ANY 0xFFFF +#define CFI_MFR_CONTINUATION 0x007F #define CFI_MFR_AMD 0x0001 #define CFI_MFR_ATMEL 0x001F +#define CFI_MFR_EON 0x001C +#define CFI_MFR_FUJITSU 0x0004 +#define CFI_MFR_HYUNDAI 0x00AD #define CFI_MFR_INTEL 0x0089 #define CFI_MFR_MACRONIX 0x00C2 +#define CFI_MFR_NEC 0x0010 +#define CFI_MFR_PMC 0x009D #define CFI_MFR_SAMSUNG 0x00EC +#define CFI_MFR_SHARP 0x00B0 #define CFI_MFR_SST 0x00BF #define CFI_MFR_ST 0x0020 /* STMicroelectronics */ +#define CFI_MFR_TOSHIBA 0x0098 +#define CFI_MFR_WINBOND 0x00DA void cfi_fixup(struct mtd_info *mtd, struct cfi_fixup* fixups); -- cgit v1.2.3 From 6a88c47bd528cb0f82692986a3ca57b3695d9c60 Mon Sep 17 00:00:00 2001 From: Kyungmin Park Date: Wed, 28 Apr 2010 17:46:45 +0200 Subject: mtd: onenand: add support for chips with 4KiB page size This patch adds support for OneNAND chips that have 4KiB page size. Signed-off-by: Kyungmin Park Signed-off-by: Marek Szyprowski Signed-off-by: David Woodhouse --- include/linux/mtd/onenand.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/onenand.h b/include/linux/mtd/onenand.h index 5509eb06b326..c9a3c3596b68 100644 --- a/include/linux/mtd/onenand.h +++ b/include/linux/mtd/onenand.h @@ -175,10 +175,14 @@ struct onenand_chip { #define ONENAND_HAS_CONT_LOCK (0x0001) #define ONENAND_HAS_UNLOCK_ALL (0x0002) #define ONENAND_HAS_2PLANE (0x0004) +#define ONENAND_HAS_4KB_PAGE (0x0008) #define ONENAND_SKIP_UNLOCK_CHECK (0x0100) #define ONENAND_PAGEBUF_ALLOC (0x1000) #define ONENAND_OOBBUF_ALLOC (0x2000) +#define ONENAND_IS_4KB_PAGE(this) \ + (this->options & ONENAND_HAS_4KB_PAGE) + /* * OneNAND Flash Manufacturer ID Codes */ -- cgit v1.2.3 From 4a8ce0b030716b95004a4ace969953bc3ad7d2fe Mon Sep 17 00:00:00 2001 From: Kyungmin Park Date: Wed, 28 Apr 2010 17:46:46 +0200 Subject: mtd: onenand: allocate verify buffer in the core This patch extends OneNAND core code with support for OneNAND verify write check. This is done by allocating the buffer for verify read directly from the core code. Signed-off-by: Kyungmin Park Signed-off-by: Marek Szyprowski Signed-off-by: David Woodhouse --- include/linux/mtd/onenand.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/onenand.h b/include/linux/mtd/onenand.h index c9a3c3596b68..9b43268224a7 100644 --- a/include/linux/mtd/onenand.h +++ b/include/linux/mtd/onenand.h @@ -125,6 +125,9 @@ struct onenand_chip { flstate_t state; unsigned char *page_buf; unsigned char *oob_buf; +#ifdef CONFIG_MTD_ONENAND_VERIFY_WRITE + unsigned char *verify_buf; +#endif int subpagesize; struct nand_ecclayout *ecclayout; -- cgit v1.2.3 From 3328dc315914aa6db486da2ceb021b6f0b36b877 Mon Sep 17 00:00:00 2001 From: Kyungmin Park Date: Wed, 28 Apr 2010 17:46:47 +0200 Subject: mtd: onenand: add new callback for bufferram read This patch adds a new callback for the underlying drivers, which is called instead of accessing the buffer ram directly. This callback will be used by Samsung OneNAND driver to implement DMA transfers on S5PC110 SoC. Signed-off-by: Kyungmin Park Signed-off-by: Marek Szyprowski Signed-off-by: David Woodhouse --- include/linux/mtd/onenand.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/onenand.h b/include/linux/mtd/onenand.h index 9b43268224a7..c26ff86ad08a 100644 --- a/include/linux/mtd/onenand.h +++ b/include/linux/mtd/onenand.h @@ -212,6 +212,8 @@ struct mtd_partition; struct onenand_platform_data { void (*mmcontrol)(struct mtd_info *mtd, int sync_read); + int (*read_bufferram)(struct mtd_info *mtd, int area, + unsigned char *buffer, int offset, size_t count); struct mtd_partition *parts; unsigned int nr_parts; }; -- cgit v1.2.3 From 709c4efb68cccd2de9a7d63b1f90276b1617e613 Mon Sep 17 00:00:00 2001 From: Kevin Cernekee Date: Tue, 4 May 2010 12:51:34 -0700 Subject: mtd: map.h: add missing bug.h include Signed-off-by: Kevin Cernekee Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- 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 b981b8772217..01703d425986 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -7,6 +7,7 @@ #include #include #include +#include #include -- cgit v1.2.3 From 9ea5973883bbe26372f45d99eb3a500f08d966f9 Mon Sep 17 00:00:00 2001 From: Kevin Cernekee Date: Sat, 10 Apr 2010 11:18:58 -0700 Subject: mtd: suppress warnings in inline_map_read() With gcc 4.4.3 -O2 on MIPS32: drivers/mtd/chips/cfi_util.c: In function 'cfi_qry_present': include/linux/mtd/map.h:390: warning: 'r' may be used uninitialized in this function include/linux/mtd/map.h:375: note: 'r' was declared here include/linux/mtd/map.h:390: warning: 'r' may be used uninitialized in this function include/linux/mtd/map.h:375: note: 'r' was declared here Signed-off-by: Kevin Cernekee Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/map.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index 01703d425986..de89eca864ce 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -387,6 +387,8 @@ static inline map_word inline_map_read(struct map_info *map, unsigned long ofs) #endif else if (map_bankwidth_is_large(map)) memcpy_fromio(r.x, map->virt+ofs, map->bankwidth); + else + BUG(); return r; } -- cgit v1.2.3 From 426c457a3216fac74e3d44dd39729b0689f4c7ab Mon Sep 17 00:00:00 2001 From: Kevin Cernekee Date: Tue, 4 May 2010 20:58:03 -0700 Subject: mtd: nand: extend NAND flash detection to new MLC chips Some of the newer MLC devices have a 6-byte ID sequence in which several field definitions differ from older chips in a manner that is not backward compatible. For instance: Samsung K9GAG08U0M (5-byte sequence): ec d5 14 b6 74 4th byte, bits 1:0 encode the page size: 0=1KiB, 1=2KiB, 2=4KiB, 3=8KiB 4th byte, bits 5:4 encode the block size: 0=64KiB, 1=128KiB, ... 4th byte, bit 6 encodes the OOB size: 0=8B/512B, 1=16B/512B Samsung K9GAG08U0D (6-byte sequence): ec d5 94 29 34 41 4th byte, bits 1:0 encode the page size: 0=2KiB, 1=4KiB, 3=8KiB, 4=rsvd 4th byte, bits 7;5:4 encode the block size: 0=128KiB, 1=256KiB, ... 4th byte, bits 6;3:2 encode the OOB size: 1=128B/page, 2=218B/page This patch uses the new 6-byte scheme if the following conditions are all true: 1) The ID code wraps around after exactly 6 bytes 2) Manufacturer is Samsung 3) 6th byte is zero The patch also extends the maximum OOB size from 128B to 256B. Signed-off-by: Kevin Cernekee Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 8bdacb885f90..50f3aa00a452 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -53,7 +53,7 @@ extern int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); * is supported now. If you add a chip with bigger oobsize/page * adjust this accordingly. */ -#define NAND_MAX_OOBSIZE 128 +#define NAND_MAX_OOBSIZE 256 #define NAND_MAX_PAGESIZE 4096 /* -- cgit v1.2.3 From b60b08b02ca8d9575985ae6711bd656dd67e9039 Mon Sep 17 00:00:00 2001 From: Kevin Cernekee Date: Tue, 4 May 2010 20:58:10 -0700 Subject: mtd: nand: support alternate BB marker locations on MLC This is a slightly modified version of a patch submitted last year by Reuben Dowle . His original comments follow: This patch adds support for some MLC NAND flashes that place the BB marker in the LAST page of the bad block rather than the FIRST page used for SLC NAND and other types of MLC nand. Lifted from Samsung datasheet for K9LG8G08U0A (1Gbyte MLC NAND): " Identifying Initial Invalid Block(s) All device locations are erased(FFh) except locations where the initial invalid block(s) information is written prior to shipping. The initial invalid block(s) status is defined by the 1st byte in the spare area. Samsung makes sure that the last page of every initial invalid block has non-FFh data at the column address of 2,048. ... " As far as I can tell, this is the same for all Samsung MLC nand, and in fact the samsung bsp for the processor used in our project (s3c6410) actually contained a hack similar to this patch but less portable to enable use of their NAND parts. I discovered this problem when trying to use a Micron NAND which does not used this layout - I wish samsung would put their stuff in main-line to avoid this type of problem. Currently this patch causes all MLC nand with manufacturer codes from Samsung and ST(Numonyx) to use this alternative location, since these are the manufactures that I know of that use this layout. Signed-off-by: Kevin Cernekee Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 50f3aa00a452..a81b185e23a7 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -181,6 +181,8 @@ typedef enum { #define NAND_NO_READRDY 0x00000100 /* Chip does not allow subpage writes */ #define NAND_NO_SUBPAGE_WRITE 0x00000200 +/* Chip stores bad block marker on the last page of the eraseblock */ +#define NAND_BB_LAST_PAGE 0x00000400 /* Device is one of 'new' xD cards that expose fake nand command set */ #define NAND_BROKEN_XD 0x00000400 -- cgit v1.2.3 From 8f0820183056ad26dabc0202115848a92f1143fc Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 20 Apr 2010 10:47:33 -0400 Subject: tracing: Create class struct for events This patch creates a ftrace_event_class struct that event structs point to. This class struct will be made to hold information to modify the events. Currently the class struct only holds the events system name. This patch slightly increases the size, but this change lays the ground work of other changes to make the footprint of tracepoints smaller. With 82 standard tracepoints, and 618 system call tracepoints (two tracepoints per syscall: enter and exit): text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class This patch also cleans up some stale comments in ftrace.h. v2: Fixed missing semi-colon in macro. Acked-by: Frederic Weisbecker Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 6 +++++- include/linux/syscalls.h | 6 ++++-- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 39e71b0a3bfd..496eea898ee4 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -113,10 +113,14 @@ void tracing_record_cmdline(struct task_struct *tsk); struct event_filter; +struct ftrace_event_class { + char *system; +}; + struct ftrace_event_call { struct list_head list; + struct ftrace_event_class *class; char *name; - char *system; struct dentry *dir; struct trace_event *event; int enabled; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 057929b0a651..ac5791df2506 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -134,6 +134,8 @@ struct perf_event_attr; #define __SC_STR_TDECL5(t, a, ...) #t, __SC_STR_TDECL4(__VA_ARGS__) #define __SC_STR_TDECL6(t, a, ...) #t, __SC_STR_TDECL5(__VA_ARGS__) +extern struct ftrace_event_class event_class_syscalls; + #define SYSCALL_TRACE_ENTER_EVENT(sname) \ static const struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call \ @@ -146,7 +148,7 @@ struct perf_event_attr; __attribute__((section("_ftrace_events"))) \ event_enter_##sname = { \ .name = "sys_enter"#sname, \ - .system = "syscalls", \ + .class = &event_class_syscalls, \ .event = &enter_syscall_print_##sname, \ .raw_init = init_syscall_trace, \ .define_fields = syscall_enter_define_fields, \ @@ -168,7 +170,7 @@ struct perf_event_attr; __attribute__((section("_ftrace_events"))) \ event_exit_##sname = { \ .name = "sys_exit"#sname, \ - .system = "syscalls", \ + .class = &event_class_syscalls, \ .event = &exit_syscall_print_##sname, \ .raw_init = init_syscall_trace, \ .define_fields = syscall_exit_define_fields, \ -- cgit v1.2.3 From 53da59aa6dd881fd0bbdd058a8a299d90ce9dd1d Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 30 Apr 2010 12:59:59 -0400 Subject: tracepoints: Add check trace callback type This check is meant to be used by tracepoint users which do a direct cast of callbacks to (void *) for direct registration, thus bypassing the register_trace_##name and unregister_trace_##name checks. This permits to ensure that the callback type matches the function type at the call site, but without generating any code. Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Signed-off-by: Mathieu Desnoyers LKML-Reference: <20100430165959.GA25605@Krystal> CC: Ingo Molnar CC: Andrew Morton CC: Thomas Gleixner CC: Peter Zijlstra CC: Arnaldo Carvalho de Melo CC: Lai Jiangshan CC: Li Zefan CC: Christoph Hellwig Signed-off-by: Steven Rostedt --- include/linux/tracepoint.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 1d85f9a6a199..8d5e4f6d96d0 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -137,9 +137,11 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, static inline int unregister_trace_##name(void (*probe)(proto)) \ { \ return tracepoint_probe_unregister(#name, (void *)probe);\ + } \ + static inline void check_trace_callback_type_##name(void (*cb)(proto)) \ + { \ } - #define DEFINE_TRACE_FN(name, reg, unreg) \ static const char __tpstrtab_##name[] \ __attribute__((section("__tracepoints_strings"))) = #name; \ @@ -168,6 +170,9 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, static inline int unregister_trace_##name(void (*probe)(proto)) \ { \ return -ENOSYS; \ + } \ + static inline void check_trace_callback_type_##name(void (*cb)(proto)) \ + { \ } #define DEFINE_TRACE_FN(name, reg, unreg) -- cgit v1.2.3 From 38516ab59fbc5b3bb278cf5e1fe2867c70cff32e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 20 Apr 2010 17:04:50 -0400 Subject: tracing: Let tracepoints have data passed to tracepoint callbacks This patch adds data to be passed to tracepoint callbacks. The created functions from DECLARE_TRACE() now need a mandatory data parameter. For example: DECLARE_TRACE(mytracepoint, int value, value) Will create the register function: int register_trace_mytracepoint((void(*)(void *data, int value))probe, void *data); As the first argument, all callbacks (probes) must take a (void *data) parameter. So a callback for the above tracepoint will look like: void myprobe(void *data, int value) { } The callback may choose to ignore the data parameter. This change allows callbacks to register a private data pointer along with the function probe. void mycallback(void *data, int value); register_trace_mytracepoint(mycallback, mydata); Then the mycallback() will receive the "mydata" as the first parameter before the args. A more detailed example: DECLARE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status)); /* In the C file */ DEFINE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status)); [...] trace_mytracepoint(status); /* In a file registering this tracepoint */ int my_callback(void *data, int status) { struct my_struct my_data = data; [...] } [...] my_data = kmalloc(sizeof(*my_data), GFP_KERNEL); init_my_data(my_data); register_trace_mytracepoint(my_callback, my_data); The same callback can also be registered to the same tracepoint as long as the data registered is different. Note, the data must also be used to unregister the callback: unregister_trace_mytracepoint(my_callback, my_data); Because of the data parameter, tracepoints declared this way can not have no args. That is: DECLARE_TRACE(mytracepoint, TP_PROTO(void), TP_ARGS()); will cause an error. If no arguments are needed, a new macro can be used instead: DECLARE_TRACE_NOARGS(mytracepoint); Since there are no arguments, the proto and args fields are left out. This is part of a series to make the tracepoint footprint smaller: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint Again, this patch also increases the size of the kernel, but lays the ground work for decreasing it. v5: Fixed net/core/drop_monitor.c to handle these updates. v4: Moved the DECLARE_TRACE() DECLARE_TRACE_NOARGS out of the #ifdef CONFIG_TRACE_POINTS, since the two are the same in both cases. The __DECLARE_TRACE() is what changes. Thanks to Frederic Weisbecker for pointing this out. v3: Made all register_* functions require data to be passed and all callbacks to take a void * parameter as its first argument. This makes the calling functions comply with C standards. Also added more comments to the modifications of DECLARE_TRACE(). v2: Made the DECLARE_TRACE() have the ability to pass arguments and added a new DECLARE_TRACE_NOARGS() for tracepoints that do not need any arguments. Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Cc: Neil Horman Cc: David S. Miller Signed-off-by: Steven Rostedt --- include/linux/tracepoint.h | 95 +++++++++++++++++++++++++++++++++++----------- 1 file changed, 72 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 8d5e4f6d96d0..9a59d1f98cd4 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -20,12 +20,17 @@ struct module; struct tracepoint; +struct tracepoint_func { + void *func; + void *data; +}; + struct tracepoint { const char *name; /* Tracepoint name */ int state; /* State. */ void (*regfunc)(void); void (*unregfunc)(void); - void **funcs; + struct tracepoint_func *funcs; } __attribute__((aligned(32))); /* * Aligned on 32 bytes because it is * globally visible and gcc happily @@ -37,16 +42,19 @@ struct tracepoint { * Connect a probe to a tracepoint. * Internal API, should not be used directly. */ -extern int tracepoint_probe_register(const char *name, void *probe); +extern int tracepoint_probe_register(const char *name, void *probe, void *data); /* * Disconnect a probe from a tracepoint. * Internal API, should not be used directly. */ -extern int tracepoint_probe_unregister(const char *name, void *probe); +extern int +tracepoint_probe_unregister(const char *name, void *probe, void *data); -extern int tracepoint_probe_register_noupdate(const char *name, void *probe); -extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe); +extern int tracepoint_probe_register_noupdate(const char *name, void *probe, + void *data); +extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe, + void *data); extern void tracepoint_probe_update_all(void); struct tracepoint_iter { @@ -102,17 +110,27 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, /* * it_func[0] is never NULL because there is at least one element in the array * when the array itself is non NULL. + * + * Note, the proto and args passed in includes "__data" as the first parameter. + * The reason for this is to handle the "void" prototype. If a tracepoint + * has a "void" prototype, then it is invalid to declare a function + * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just + * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto". */ #define __DO_TRACE(tp, proto, args) \ do { \ - void **it_func; \ + struct tracepoint_func *it_func_ptr; \ + void *it_func; \ + void *__data; \ \ rcu_read_lock_sched_notrace(); \ - it_func = rcu_dereference_sched((tp)->funcs); \ - if (it_func) { \ + it_func_ptr = rcu_dereference_sched((tp)->funcs); \ + if (it_func_ptr) { \ do { \ - ((void(*)(proto))(*it_func))(args); \ - } while (*(++it_func)); \ + it_func = (it_func_ptr)->func; \ + __data = (it_func_ptr)->data; \ + ((void(*)(proto))(it_func))(args); \ + } while ((++it_func_ptr)->func); \ } \ rcu_read_unlock_sched_notrace(); \ } while (0) @@ -122,23 +140,29 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. */ -#define DECLARE_TRACE(name, proto, args) \ +#define __DECLARE_TRACE(name, proto, args, data_proto, data_args) \ extern struct tracepoint __tracepoint_##name; \ static inline void trace_##name(proto) \ { \ if (unlikely(__tracepoint_##name.state)) \ __DO_TRACE(&__tracepoint_##name, \ - TP_PROTO(proto), TP_ARGS(args)); \ + TP_PROTO(data_proto), \ + TP_ARGS(data_args)); \ } \ - static inline int register_trace_##name(void (*probe)(proto)) \ + static inline int \ + register_trace_##name(void (*probe)(data_proto), void *data) \ { \ - return tracepoint_probe_register(#name, (void *)probe); \ + return tracepoint_probe_register(#name, (void *)probe, \ + data); \ } \ - static inline int unregister_trace_##name(void (*probe)(proto)) \ + static inline int \ + unregister_trace_##name(void (*probe)(data_proto), void *data) \ { \ - return tracepoint_probe_unregister(#name, (void *)probe);\ + return tracepoint_probe_unregister(#name, (void *)probe, \ + data); \ } \ - static inline void check_trace_callback_type_##name(void (*cb)(proto)) \ + static inline void \ + check_trace_callback_type_##name(void (*cb)(data_proto)) \ { \ } @@ -158,20 +182,22 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, EXPORT_SYMBOL(__tracepoint_##name) #else /* !CONFIG_TRACEPOINTS */ -#define DECLARE_TRACE(name, proto, args) \ - static inline void _do_trace_##name(struct tracepoint *tp, proto) \ - { } \ +#define __DECLARE_TRACE(name, proto, args, data_proto, data_args) \ static inline void trace_##name(proto) \ { } \ - static inline int register_trace_##name(void (*probe)(proto)) \ + static inline int \ + register_trace_##name(void (*probe)(data_proto), \ + void *data) \ { \ return -ENOSYS; \ } \ - static inline int unregister_trace_##name(void (*probe)(proto)) \ + static inline int \ + unregister_trace_##name(void (*probe)(data_proto), \ + void *data) \ { \ return -ENOSYS; \ } \ - static inline void check_trace_callback_type_##name(void (*cb)(proto)) \ + static inline void check_trace_callback_type_##name(void (*cb)(data_proto)) \ { \ } @@ -181,6 +207,29 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, #define EXPORT_TRACEPOINT_SYMBOL(name) #endif /* CONFIG_TRACEPOINTS */ + +/* + * The need for the DECLARE_TRACE_NOARGS() is to handle the prototype + * (void). "void" is a special value in a function prototype and can + * not be combined with other arguments. Since the DECLARE_TRACE() + * macro adds a data element at the beginning of the prototype, + * we need a way to differentiate "(void *data, proto)" from + * "(void *data, void)". The second prototype is invalid. + * + * DECLARE_TRACE_NOARGS() passes "void" as the tracepoint prototype + * and "void *__data" as the callback prototype. + * + * DECLARE_TRACE() passes "proto" as the tracepoint protoype and + * "void *__data, proto" as the callback prototype. + */ +#define DECLARE_TRACE_NOARGS(name) \ + __DECLARE_TRACE(name, void, , void *__data, __data) + +#define DECLARE_TRACE(name, proto, args) \ + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ + PARAMS(void *__data, proto), \ + PARAMS(__data, args)) + #endif /* DECLARE_TRACE */ #ifndef TRACE_EVENT -- cgit v1.2.3 From 2239291aeb0379fe47980b0e560e0eb9fd7e82ec Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 21 Apr 2010 12:27:06 -0400 Subject: tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 19 +++++++++++++++---- include/linux/syscalls.h | 29 ++++------------------------- 2 files changed, 19 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 496eea898ee4..e665ed38b4bf 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -113,8 +113,23 @@ void tracing_record_cmdline(struct task_struct *tsk); struct event_filter; +enum trace_reg { + TRACE_REG_REGISTER, + TRACE_REG_UNREGISTER, + TRACE_REG_PERF_REGISTER, + TRACE_REG_PERF_UNREGISTER, +}; + +struct ftrace_event_call; + struct ftrace_event_class { char *system; + void *probe; +#ifdef CONFIG_PERF_EVENTS + void *perf_probe; +#endif + int (*reg)(struct ftrace_event_call *event, + enum trace_reg type); }; struct ftrace_event_call { @@ -124,8 +139,6 @@ struct ftrace_event_call { struct dentry *dir; struct trace_event *event; int enabled; - int (*regfunc)(struct ftrace_event_call *); - void (*unregfunc)(struct ftrace_event_call *); int id; const char *print_fmt; int (*raw_init)(struct ftrace_event_call *); @@ -137,8 +150,6 @@ struct ftrace_event_call { void *data; int perf_refcount; - int (*perf_event_enable)(struct ftrace_event_call *); - void (*perf_event_disable)(struct ftrace_event_call *); }; #define PERF_MAX_TRACE_SIZE 2048 diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index ac5791df2506..e3348c4c22e8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -103,22 +103,6 @@ struct perf_event_attr; #define __SC_TEST5(t5, a5, ...) __SC_TEST(t5); __SC_TEST4(__VA_ARGS__) #define __SC_TEST6(t6, a6, ...) __SC_TEST(t6); __SC_TEST5(__VA_ARGS__) -#ifdef CONFIG_PERF_EVENTS - -#define TRACE_SYS_ENTER_PERF_INIT(sname) \ - .perf_event_enable = perf_sysenter_enable, \ - .perf_event_disable = perf_sysenter_disable, - -#define TRACE_SYS_EXIT_PERF_INIT(sname) \ - .perf_event_enable = perf_sysexit_enable, \ - .perf_event_disable = perf_sysexit_disable, -#else -#define TRACE_SYS_ENTER_PERF(sname) -#define TRACE_SYS_ENTER_PERF_INIT(sname) -#define TRACE_SYS_EXIT_PERF(sname) -#define TRACE_SYS_EXIT_PERF_INIT(sname) -#endif /* CONFIG_PERF_EVENTS */ - #ifdef CONFIG_FTRACE_SYSCALLS #define __SC_STR_ADECL1(t, a) #a #define __SC_STR_ADECL2(t, a, ...) #a, __SC_STR_ADECL1(__VA_ARGS__) @@ -134,7 +118,8 @@ struct perf_event_attr; #define __SC_STR_TDECL5(t, a, ...) #t, __SC_STR_TDECL4(__VA_ARGS__) #define __SC_STR_TDECL6(t, a, ...) #t, __SC_STR_TDECL5(__VA_ARGS__) -extern struct ftrace_event_class event_class_syscalls; +extern struct ftrace_event_class event_class_syscall_enter; +extern struct ftrace_event_class event_class_syscall_exit; #define SYSCALL_TRACE_ENTER_EVENT(sname) \ static const struct syscall_metadata __syscall_meta_##sname; \ @@ -148,14 +133,11 @@ extern struct ftrace_event_class event_class_syscalls; __attribute__((section("_ftrace_events"))) \ event_enter_##sname = { \ .name = "sys_enter"#sname, \ - .class = &event_class_syscalls, \ + .class = &event_class_syscall_enter, \ .event = &enter_syscall_print_##sname, \ .raw_init = init_syscall_trace, \ .define_fields = syscall_enter_define_fields, \ - .regfunc = reg_event_syscall_enter, \ - .unregfunc = unreg_event_syscall_enter, \ .data = (void *)&__syscall_meta_##sname,\ - TRACE_SYS_ENTER_PERF_INIT(sname) \ } #define SYSCALL_TRACE_EXIT_EVENT(sname) \ @@ -170,14 +152,11 @@ extern struct ftrace_event_class event_class_syscalls; __attribute__((section("_ftrace_events"))) \ event_exit_##sname = { \ .name = "sys_exit"#sname, \ - .class = &event_class_syscalls, \ + .class = &event_class_syscall_exit, \ .event = &exit_syscall_print_##sname, \ .raw_init = init_syscall_trace, \ .define_fields = syscall_exit_define_fields, \ - .regfunc = reg_event_syscall_exit, \ - .unregfunc = unreg_event_syscall_exit, \ .data = (void *)&__syscall_meta_##sname,\ - TRACE_SYS_EXIT_PERF_INIT(sname) \ } #define SYSCALL_METADATA(sname, nb) \ -- cgit v1.2.3 From 2e33af029556cb8bd22bf4f86f42d540249177ea Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 22 Apr 2010 10:35:55 -0400 Subject: tracing: Move fields from event to class structure Move the defined fields from the event to the class structure. Since the fields of the event are defined by the class they belong to, it makes sense to have the class hold the information instead of the individual events. The events of the same class would just hold duplicate information. After this change the size of the kernel dropped another 3K: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4900252 1057412 861512 6819176 680d68 vmlinux.regs 4900375 1053380 861512 6815267 67fe23 vmlinux.fields Although the text increased, this was mainly due to the C files having to adapt to the change. This is a constant increase, where new tracepoints will not increase the Text. But the big drop is in the data size (as well as needed allocations to hold the fields). This will give even more savings as more tracepoints are created. Note, if just TRACE_EVENT()s are used and not DECLARE_EVENT_CLASS() with several DEFINE_EVENT()s, then the savings will be lost. But we are pushing developers to consolidate events with DEFINE_EVENT() so this should not be an issue. The kprobes define a unique class to every new event, but are dynamic so it should not be a issue. The syscalls however have a single class but the fields for the individual events are different. The syscalls use a metadata to define the fields. I moved the fields list from the event to the metadata and added a "get_fields()" function to the class. This function is used to find the fields. For normal events and kprobes, get_fields() just returns a pointer to the fields list_head in the class. For syscall events, it returns the fields list_head in the metadata for the event. v2: Fixed the syscall fields. The syscall metadata needs a list of fields for both enter and exit. Acked-by: Frederic Weisbecker Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Cc: Tom Zanussi Cc: Peter Zijlstra Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 5 +++-- include/linux/syscalls.h | 14 ++++++++------ 2 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index e665ed38b4bf..479c3c1876e6 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -130,6 +130,9 @@ struct ftrace_event_class { #endif int (*reg)(struct ftrace_event_call *event, enum trace_reg type); + int (*define_fields)(struct ftrace_event_call *); + struct list_head *(*get_fields)(struct ftrace_event_call *); + struct list_head fields; }; struct ftrace_event_call { @@ -142,8 +145,6 @@ struct ftrace_event_call { int id; const char *print_fmt; int (*raw_init)(struct ftrace_event_call *); - int (*define_fields)(struct ftrace_event_call *); - struct list_head fields; int filter_active; struct event_filter *filter; void *mod; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e3348c4c22e8..fd0f1f248cd8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -122,7 +122,7 @@ extern struct ftrace_event_class event_class_syscall_enter; extern struct ftrace_event_class event_class_syscall_exit; #define SYSCALL_TRACE_ENTER_EVENT(sname) \ - static const struct syscall_metadata __syscall_meta_##sname; \ + static struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call \ __attribute__((__aligned__(4))) event_enter_##sname; \ static struct trace_event enter_syscall_print_##sname = { \ @@ -136,12 +136,11 @@ extern struct ftrace_event_class event_class_syscall_exit; .class = &event_class_syscall_enter, \ .event = &enter_syscall_print_##sname, \ .raw_init = init_syscall_trace, \ - .define_fields = syscall_enter_define_fields, \ .data = (void *)&__syscall_meta_##sname,\ } #define SYSCALL_TRACE_EXIT_EVENT(sname) \ - static const struct syscall_metadata __syscall_meta_##sname; \ + static struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call \ __attribute__((__aligned__(4))) event_exit_##sname; \ static struct trace_event exit_syscall_print_##sname = { \ @@ -155,14 +154,13 @@ extern struct ftrace_event_class event_class_syscall_exit; .class = &event_class_syscall_exit, \ .event = &exit_syscall_print_##sname, \ .raw_init = init_syscall_trace, \ - .define_fields = syscall_exit_define_fields, \ .data = (void *)&__syscall_meta_##sname,\ } #define SYSCALL_METADATA(sname, nb) \ SYSCALL_TRACE_ENTER_EVENT(sname); \ SYSCALL_TRACE_EXIT_EVENT(sname); \ - static const struct syscall_metadata __used \ + static struct syscall_metadata __used \ __attribute__((__aligned__(4))) \ __attribute__((section("__syscalls_metadata"))) \ __syscall_meta_##sname = { \ @@ -172,12 +170,14 @@ extern struct ftrace_event_class event_class_syscall_exit; .args = args_##sname, \ .enter_event = &event_enter_##sname, \ .exit_event = &event_exit_##sname, \ + .enter_fields = LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \ + .exit_fields = LIST_HEAD_INIT(__syscall_meta_##sname.exit_fields), \ }; #define SYSCALL_DEFINE0(sname) \ SYSCALL_TRACE_ENTER_EVENT(_##sname); \ SYSCALL_TRACE_EXIT_EVENT(_##sname); \ - static const struct syscall_metadata __used \ + static struct syscall_metadata __used \ __attribute__((__aligned__(4))) \ __attribute__((section("__syscalls_metadata"))) \ __syscall_meta__##sname = { \ @@ -185,6 +185,8 @@ extern struct ftrace_event_class event_class_syscall_exit; .nb_args = 0, \ .enter_event = &event_enter__##sname, \ .exit_event = &event_exit__##sname, \ + .enter_fields = LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \ + .exit_fields = LIST_HEAD_INIT(__syscall_meta__##sname.exit_fields), \ }; \ asmlinkage long sys_##sname(void) #else -- cgit v1.2.3 From 0405ab80aa94afb13bf9ac4a6fc9f2923d4b9114 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 22 Apr 2010 11:46:44 -0400 Subject: tracing: Move raw_init from events to class The raw_init function pointer in the event is used to initialize various kinds of events. The type of initialization needed is usually classed to the kind of event it is. Two events with the same class will always have the same initialization function, so it makes sense to move this to the class structure. Perhaps even making a special system structure would work since the initialization is the same for all events within a system. But since there's no system structure (yet), this will just move it to the class. text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4900375 1053380 861512 6815267 67fe23 vmlinux.fields 4900382 1048964 861512 6810858 67ecea vmlinux.init The text grew very slightly, but this is a constant growth that happened with the changing of the C files that call the init code. The bigger savings is the data which will be saved the more events share a class. Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 2 +- include/linux/syscalls.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 479c3c1876e6..393a8394df0e 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -133,6 +133,7 @@ struct ftrace_event_class { int (*define_fields)(struct ftrace_event_call *); struct list_head *(*get_fields)(struct ftrace_event_call *); struct list_head fields; + int (*raw_init)(struct ftrace_event_call *); }; struct ftrace_event_call { @@ -144,7 +145,6 @@ struct ftrace_event_call { int enabled; int id; const char *print_fmt; - int (*raw_init)(struct ftrace_event_call *); int filter_active; struct event_filter *filter; void *mod; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index fd0f1f248cd8..211c704a71ed 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -135,7 +135,6 @@ extern struct ftrace_event_class event_class_syscall_exit; .name = "sys_enter"#sname, \ .class = &event_class_syscall_enter, \ .event = &enter_syscall_print_##sname, \ - .raw_init = init_syscall_trace, \ .data = (void *)&__syscall_meta_##sname,\ } @@ -153,7 +152,6 @@ extern struct ftrace_event_class event_class_syscall_exit; .name = "sys_exit"#sname, \ .class = &event_class_syscall_exit, \ .event = &exit_syscall_print_##sname, \ - .raw_init = init_syscall_trace, \ .data = (void *)&__syscall_meta_##sname,\ } -- cgit v1.2.3 From a9a5776380208a3e48a92d0c763ee1a3b486fb73 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 22 Apr 2010 18:46:14 -0400 Subject: tracing: Allow events to share their print functions Multiple events may use the same method to print their data. Instead of having all events have a pointer to their print funtions, the trace_event structure now points to a trace_event_functions structure that will hold the way to print ouf the event. The event itself is now passed to the print function to let the print function know what kind of event it should print. This opens the door to consolidating the way several events print their output. text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4900382 1048964 861512 6810858 67ecea vmlinux.init 4900446 1049028 861512 6810986 67ed6a vmlinux.preprint This change slightly increases the size but is needed for the next change. v3: Fix the branch tracer events to handle this change. v2: Fix the new function graph tracer event calls to handle this change. Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 17 ++++++++++++----- include/linux/syscalls.h | 10 ++++++++-- 2 files changed, 20 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 393a8394df0e..4f77932b0983 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -70,18 +70,25 @@ struct trace_iterator { }; +struct trace_event; + typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter, - int flags); -struct trace_event { - struct hlist_node node; - struct list_head list; - int type; + int flags, struct trace_event *event); + +struct trace_event_functions { trace_print_func trace; trace_print_func raw; trace_print_func hex; trace_print_func binary; }; +struct trace_event { + struct hlist_node node; + struct list_head list; + int type; + struct trace_event_functions *funcs; +}; + extern int register_ftrace_event(struct trace_event *event); extern int unregister_ftrace_event(struct trace_event *event); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 211c704a71ed..f7256770a20f 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -125,9 +125,12 @@ extern struct ftrace_event_class event_class_syscall_exit; static struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call \ __attribute__((__aligned__(4))) event_enter_##sname; \ - static struct trace_event enter_syscall_print_##sname = { \ + static struct trace_event_functions enter_syscall_print_funcs_##sname = { \ .trace = print_syscall_enter, \ }; \ + static struct trace_event enter_syscall_print_##sname = { \ + .funcs = &enter_syscall_print_funcs_##sname, \ + }; \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) \ @@ -142,9 +145,12 @@ extern struct ftrace_event_class event_class_syscall_exit; static struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call \ __attribute__((__aligned__(4))) event_exit_##sname; \ - static struct trace_event exit_syscall_print_##sname = { \ + static struct trace_event_functions exit_syscall_print_funcs_##sname = { \ .trace = print_syscall_exit, \ }; \ + static struct trace_event exit_syscall_print_##sname = { \ + .funcs = &exit_syscall_print_funcs_##sname, \ + }; \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) \ -- cgit v1.2.3 From 80decc70afc57c87eee9d6b836aec2ecacba3457 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 23 Apr 2010 10:00:22 -0400 Subject: tracing: Move print functions into event class Currently, every event has its own trace_event structure. This is fine since the structure is needed anyway. But the print function structure (trace_event_functions) is now separate. Since the output of the trace event is done by the class (with the exception of events defined by DEFINE_EVENT_PRINT), it makes sense to have the class define the print functions that all events in the class can use. This makes a bigger deal with the syscall events since all syscall events use the same class. The savings here is another 30K. text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4900382 1048964 861512 6810858 67ecea vmlinux.init 4900446 1049028 861512 6810986 67ed6a vmlinux.preprint 4895024 1023812 861512 6780348 6775bc vmlinux.print To accomplish this, and to let the class know what event is being printed, the event structure is embedded in the ftrace_event_call structure. This should not be an issues since the event structure was created for each event anyway. Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 2 +- include/linux/syscalls.h | 18 ++++-------------- 2 files changed, 5 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 4f77932b0983..b1a007d6e8fd 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -148,7 +148,7 @@ struct ftrace_event_call { struct ftrace_event_class *class; char *name; struct dentry *dir; - struct trace_event *event; + struct trace_event event; int enabled; int id; const char *print_fmt; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f7256770a20f..a1a86a53bc73 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -120,24 +120,20 @@ struct perf_event_attr; extern struct ftrace_event_class event_class_syscall_enter; extern struct ftrace_event_class event_class_syscall_exit; +extern struct trace_event_functions enter_syscall_print_funcs; +extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_TRACE_ENTER_EVENT(sname) \ static struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call \ __attribute__((__aligned__(4))) event_enter_##sname; \ - static struct trace_event_functions enter_syscall_print_funcs_##sname = { \ - .trace = print_syscall_enter, \ - }; \ - static struct trace_event enter_syscall_print_##sname = { \ - .funcs = &enter_syscall_print_funcs_##sname, \ - }; \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) \ event_enter_##sname = { \ .name = "sys_enter"#sname, \ .class = &event_class_syscall_enter, \ - .event = &enter_syscall_print_##sname, \ + .event.funcs = &enter_syscall_print_funcs, \ .data = (void *)&__syscall_meta_##sname,\ } @@ -145,19 +141,13 @@ extern struct ftrace_event_class event_class_syscall_exit; static struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call \ __attribute__((__aligned__(4))) event_exit_##sname; \ - static struct trace_event_functions exit_syscall_print_funcs_##sname = { \ - .trace = print_syscall_exit, \ - }; \ - static struct trace_event exit_syscall_print_##sname = { \ - .funcs = &exit_syscall_print_funcs_##sname, \ - }; \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) \ event_exit_##sname = { \ .name = "sys_exit"#sname, \ .class = &event_class_syscall_exit, \ - .event = &exit_syscall_print_##sname, \ + .event.funcs = &exit_syscall_print_funcs, \ .data = (void *)&__syscall_meta_##sname,\ } -- cgit v1.2.3 From 32c0edaeaad74a7883e736ae0f3798784cfc2a80 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 23 Apr 2010 10:38:03 -0400 Subject: tracing: Remove duplicate id information in event structure Now that the trace_event structure is embedded in the ftrace_event_call structure, there is no need for the ftrace_event_call id field. The id field is the same as the trace_event type field. Removing the id and re-arranging the structure brings down the tracepoint footprint by another 5K. text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4895024 1023812 861512 6780348 6775bc vmlinux.print 4894944 1018052 861512 6774508 675eec vmlinux.id Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index b1a007d6e8fd..0be028527633 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -149,14 +149,13 @@ struct ftrace_event_call { char *name; struct dentry *dir; struct trace_event event; - int enabled; - int id; const char *print_fmt; - int filter_active; struct event_filter *filter; void *mod; void *data; + int enabled; + int filter_active; int perf_refcount; }; -- cgit v1.2.3 From 553552ce1796c32cf4e3d4f45cd5b537de91dd1d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 23 Apr 2010 11:12:36 -0400 Subject: tracing: Combine event filter_active and enable into single flags field The filter_active and enable both use an int (4 bytes each) to set a single flag. We can save 4 bytes per event by combining the two into a single integer. text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4894944 1018052 861512 6774508 675eec vmlinux.id 4894871 1012292 861512 6768675 674823 vmlinux.flags This gives us another 5K in savings. The modification of both the enable and filter fields are done under the event_mutex, so it is still safe to combine the two. Note: Although Mathieu gave his Acked-by, he would like it documented that the reads of flags are not protected by the mutex. The way the code works, these reads will not break anything, but will have a residual effect. Since this behavior is the same even before this patch, describing this situation is left to another patch, as this patch does not change the behavior, but just brought it to Mathieu's attention. v2: Updated the event trace self test to for this change. Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Cc: Tom Zanussi Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 0be028527633..5ac97a42950d 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -143,6 +143,16 @@ struct ftrace_event_class { int (*raw_init)(struct ftrace_event_call *); }; +enum { + TRACE_EVENT_FL_ENABLED_BIT, + TRACE_EVENT_FL_FILTERED_BIT, +}; + +enum { + TRACE_EVENT_FL_ENABLED = (1 << TRACE_EVENT_FL_ENABLED_BIT), + TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), +}; + struct ftrace_event_call { struct list_head list; struct ftrace_event_class *class; @@ -154,8 +164,15 @@ struct ftrace_event_call { void *mod; void *data; - int enabled; - int filter_active; + /* + * 32 bit flags: + * bit 1: enabled + * bit 2: filter_active + * + * Must hold event_mutex to change. + */ + unsigned int flags; + int perf_refcount; }; -- cgit v1.2.3 From 1eaa4787a774c4896518c81f24e8bccaa2244924 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 14 May 2010 10:19:13 -0400 Subject: tracing: Comment the use of event_mutex with trace event flags The flags variable is protected by the event_mutex when modifying, but the event_mutex is not held when reading the variable. This is due to the fact that the reads occur in critical sections where taking a mutex (or even a spinlock) is not wanted. But the two flags that exist (enable and filter_active) have the code written as such to handle the reads to not need a lock. The enable flag is used just to know if the event is enabled or not and its use is always under the event_mutex. Whether or not the event is actually enabled is really determined by the tracepoint being registered. The flag is just a way to let the code know if the tracepoint is registered. The filter_active is different. It is read without the lock. If it is set, then the event probes jump to the filter code. There can be a slight mismatch between filters available and filter_active. If the flag is set but no filters are available, the code safely jumps to a filter nop. If the flag is not set and the filters are available, then the filters are skipped. This is acceptable since filters are usually set before tracing or they are set by humans, which would not notice the slight delay that this causes. v2: Fixed typo: "cacheing" -> "caching" Reported-by: Mathieu Desnoyers Acked-by: Mathieu Desnoyers Cc: Tom Zanussi Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 5ac97a42950d..dc7fc646fa2e 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -169,7 +169,14 @@ struct ftrace_event_call { * bit 1: enabled * bit 2: filter_active * - * Must hold event_mutex to change. + * Changes to flags must hold the event_mutex. + * + * Note: Reads of flags do not hold the event_mutex since + * they occur in critical sections. But the way flags + * is currently used, these changes do no affect the code + * except that when a change is made, it may have a slight + * delay in propagating the changes to other CPUs due to + * caching and such. */ unsigned int flags; -- cgit v1.2.3 From 56246f9ae4cfa95b460f9dfbcfb1b772d85db046 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Sun, 16 May 2010 09:00:00 -0400 Subject: quota: use flags interface for dquot alloc/free space Switch __dquot_alloc_space and __dquot_free_space to take flags to indicate whether to warn and/or to reserve (or free reserve). This is slightly more readable at the callpoints, and makes it cleaner to add a "nofail" option in the next patch. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- include/linux/quotaops.h | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index e6fa7acce290..9edd53c24984 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -9,6 +9,9 @@ #include +#define DQUOT_SPACE_WARN 0x1 +#define DQUOT_SPACE_RESERVE 0x2 + static inline struct quota_info *sb_dqopt(struct super_block *sb) { return &sb->s_dquot; @@ -33,9 +36,8 @@ int dquot_scan_active(struct super_block *sb, struct dquot *dquot_alloc(struct super_block *sb, int type); void dquot_destroy(struct dquot *dquot); -int __dquot_alloc_space(struct inode *inode, qsize_t number, - int warn, int reserve); -void __dquot_free_space(struct inode *inode, qsize_t number, int reserve); +int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags); +void __dquot_free_space(struct inode *inode, qsize_t number, int flags); int dquot_alloc_inode(const struct inode *inode); @@ -231,17 +233,17 @@ static inline int dquot_transfer(struct inode *inode, struct iattr *iattr) } static inline int __dquot_alloc_space(struct inode *inode, qsize_t number, - int warn, int reserve) + int flags) { - if (!reserve) + if (!(flags & DQUOT_SPACE_RESERVE)) inode_add_bytes(inode, number); return 0; } static inline void __dquot_free_space(struct inode *inode, qsize_t number, - int reserve) + int flags) { - if (!reserve) + if (!(flags & DQUOT_SPACE_RESERVE)) inode_sub_bytes(inode, number); } @@ -257,7 +259,7 @@ static inline int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) static inline int dquot_alloc_space_nodirty(struct inode *inode, qsize_t nr) { - return __dquot_alloc_space(inode, nr, 1, 0); + return __dquot_alloc_space(inode, nr, DQUOT_SPACE_WARN); } static inline int dquot_alloc_space(struct inode *inode, qsize_t nr) @@ -282,7 +284,7 @@ static inline int dquot_alloc_block(struct inode *inode, qsize_t nr) static inline int dquot_prealloc_block_nodirty(struct inode *inode, qsize_t nr) { - return __dquot_alloc_space(inode, nr << inode->i_blkbits, 0, 0); + return __dquot_alloc_space(inode, nr << inode->i_blkbits, 0); } static inline int dquot_prealloc_block(struct inode *inode, qsize_t nr) @@ -297,7 +299,8 @@ static inline int dquot_prealloc_block(struct inode *inode, qsize_t nr) static inline int dquot_reserve_block(struct inode *inode, qsize_t nr) { - return __dquot_alloc_space(inode, nr << inode->i_blkbits, 1, 1); + return __dquot_alloc_space(inode, nr << inode->i_blkbits, + DQUOT_SPACE_WARN|DQUOT_SPACE_RESERVE); } static inline int dquot_claim_block(struct inode *inode, qsize_t nr) @@ -334,7 +337,7 @@ static inline void dquot_free_block(struct inode *inode, qsize_t nr) static inline void dquot_release_reservation_block(struct inode *inode, qsize_t nr) { - __dquot_free_space(inode, nr << inode->i_blkbits, 1); + __dquot_free_space(inode, nr << inode->i_blkbits, DQUOT_SPACE_RESERVE); } #endif /* _LINUX_QUOTAOPS_ */ -- cgit v1.2.3 From 0e05842bc117ea70ceb979cca798fd026879951b Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Sun, 16 May 2010 10:00:00 -0400 Subject: quota: add the option to not fail with EDQUOT in block To simplify metadata tracking for delalloc writes, ext4 will simply claim metadata blocks at allocation time, without first speculatively reserving the worst case and then freeing what was not used. To do this, we need a mechanism to track allocations in the quota subsystem, but potentially allow that allocation to actually go over quota. This patch adds a DQUOT_SPACE_NOFAIL flag and function variants for this purpose. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- include/linux/quotaops.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 9edd53c24984..f8dbeb0fe0c9 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -11,6 +11,7 @@ #define DQUOT_SPACE_WARN 0x1 #define DQUOT_SPACE_RESERVE 0x2 +#define DQUOT_SPACE_NOFAIL 0x4 static inline struct quota_info *sb_dqopt(struct super_block *sb) { @@ -262,6 +263,12 @@ static inline int dquot_alloc_space_nodirty(struct inode *inode, qsize_t nr) return __dquot_alloc_space(inode, nr, DQUOT_SPACE_WARN); } +static inline void dquot_alloc_space_nofail(struct inode *inode, qsize_t nr) +{ + __dquot_alloc_space(inode, nr, DQUOT_SPACE_WARN|DQUOT_SPACE_NOFAIL); + mark_inode_dirty(inode); +} + static inline int dquot_alloc_space(struct inode *inode, qsize_t nr) { int ret; @@ -277,6 +284,11 @@ static inline int dquot_alloc_block_nodirty(struct inode *inode, qsize_t nr) return dquot_alloc_space_nodirty(inode, nr << inode->i_blkbits); } +static inline void dquot_alloc_block_nofail(struct inode *inode, qsize_t nr) +{ + dquot_alloc_space_nofail(inode, nr << inode->i_blkbits); +} + static inline int dquot_alloc_block(struct inode *inode, qsize_t nr) { return dquot_alloc_space(inode, nr << inode->i_blkbits); -- cgit v1.2.3 From 93d84b6d99f5ddb911b318990c759a0fefa0f7ea Mon Sep 17 00:00:00 2001 From: John Kacur Date: Wed, 5 May 2010 15:15:37 +0200 Subject: ncpfs: BKL ioctl pushdown Convert ncp_ioctl to an unlocked_ioctl and push down the bkl into it. Signed-off-by: John Kacur Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Petr Vandrovec Signed-off-by: Frederic Weisbecker --- include/linux/ncp_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ncp_fs.h b/include/linux/ncp_fs.h index 30b06c893944..4522aed00906 100644 --- a/include/linux/ncp_fs.h +++ b/include/linux/ncp_fs.h @@ -210,7 +210,7 @@ int ncp_date_dos2unix(__le16 time, __le16 date); void ncp_date_unix2dos(int unix_date, __le16 * time, __le16 * date); /* linux/fs/ncpfs/ioctl.c */ -int ncp_ioctl(struct inode *, struct file *, unsigned int, unsigned long); +long ncp_ioctl(struct file *, unsigned int, unsigned long); long ncp_compat_ioctl(struct file *, unsigned int, unsigned long); /* linux/fs/ncpfs/sock.c */ -- cgit v1.2.3 From 18978768d89f638165646718c50ced19f2a10164 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Wed, 24 Mar 2010 21:48:18 +0100 Subject: KVM: PPC: Allow userspace to unset the IRQ line Userspace can tell us that it wants to trigger an interrupt. But so far it can't tell us that it wants to stop triggering one. So let's interpret the parameter to the ioctl that we have anyways to tell us if we want to raise or lower the interrupt line. Signed-off-by: Alexander Graf v2 -> v3: - Add CAP for unset irq Signed-off-by: Avi Kivity --- include/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index ce2876717a8b..c36d093e9806 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -507,6 +507,7 @@ struct kvm_ioeventfd { #define KVM_CAP_DEBUGREGS 50 #endif #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 +#define KVM_CAP_PPC_UNSET_IRQ 53 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 71fbfd5f38f73515f1516a68fbe04dba198b70f0 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Wed, 24 Mar 2010 21:48:29 +0100 Subject: KVM: Add support for enabling capabilities per-vcpu Some times we don't want all capabilities to be available to all our vcpus. One example for that is the OSI interface, implemented in the next patch. In order to have a generic mechanism in how to enable capabilities individually, this patch introduces a new ioctl that can be used for this purpose. That way features we don't want in all guests or userspace configurations can just not be enabled and we're good. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index c36d093e9806..ecb68e433558 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -400,6 +400,15 @@ struct kvm_ioeventfd { __u8 pad[36]; }; +/* for KVM_ENABLE_CAP */ +struct kvm_enable_cap { + /* in */ + __u32 cap; + __u32 flags; + __u64 args[4]; + __u8 pad[64]; +}; + #define KVMIO 0xAE /* @@ -508,6 +517,7 @@ struct kvm_ioeventfd { #endif #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 #define KVM_CAP_PPC_UNSET_IRQ 53 +#define KVM_CAP_ENABLE_CAP 54 #ifdef KVM_CAP_IRQ_ROUTING @@ -697,6 +707,7 @@ struct kvm_clock_data { /* Available with KVM_CAP_DEBUGREGS */ #define KVM_GET_DEBUGREGS _IOR(KVMIO, 0xa1, struct kvm_debugregs) #define KVM_SET_DEBUGREGS _IOW(KVMIO, 0xa2, struct kvm_debugregs) +#define KVM_ENABLE_CAP _IOW(KVMIO, 0xa3, struct kvm_enable_cap) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -- cgit v1.2.3 From ad0a048b096ac819f28667602285453468a8d8f9 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Wed, 24 Mar 2010 21:48:30 +0100 Subject: KVM: PPC: Add OSI hypercall interface MOL uses its own hypercall interface to call back into userspace when the guest wants to do something. So let's implement that as an exit reason, specify it with a CAP and only really use it when userspace wants us to. The only user of it so far is MOL. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index ecb68e433558..23ea02253900 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -160,6 +160,7 @@ struct kvm_pit_config { #define KVM_EXIT_DCR 15 #define KVM_EXIT_NMI 16 #define KVM_EXIT_INTERNAL_ERROR 17 +#define KVM_EXIT_OSI 18 /* For KVM_EXIT_INTERNAL_ERROR */ #define KVM_INTERNAL_ERROR_EMULATION 1 @@ -259,6 +260,10 @@ struct kvm_run { __u32 ndata; __u64 data[16]; } internal; + /* KVM_EXIT_OSI */ + struct { + __u64 gprs[32]; + } osi; /* Fix the size of the union. */ char padding[256]; }; @@ -516,6 +521,7 @@ struct kvm_enable_cap { #define KVM_CAP_DEBUGREGS 50 #endif #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 +#define KVM_CAP_PPC_OSI 52 #define KVM_CAP_PPC_UNSET_IRQ 53 #define KVM_CAP_ENABLE_CAP 54 -- cgit v1.2.3 From 660c22c425cbe14badfb3b0a0206862577701ab7 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 13 Apr 2010 22:47:24 +0900 Subject: KVM: limit the number of pages per memory slot This patch limits the number of pages per memory slot to make us free from extra care about type issues. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 169d07758ee5..55830638aeb1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -105,6 +105,12 @@ struct kvm_vcpu { struct kvm_vcpu_arch arch; }; +/* + * Some of the bitops functions do not support too long bitmaps. + * This number must be determined not to exceed such limits. + */ +#define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) + struct kvm_memory_slot { gfn_t base_gfn; unsigned long npages; -- cgit v1.2.3 From 90d83dc3d49f5101addae962ccc1b4aff66b68d8 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Mon, 19 Apr 2010 17:41:23 +0800 Subject: KVM: use the correct RCU API for PROVE_RCU=y The RCU/SRCU API have already changed for proving RCU usage. I got the following dmesg when PROVE_RCU=y because we used incorrect API. This patch coverts rcu_deference() to srcu_dereference() or family API. =================================================== [ INFO: suspicious rcu_dereference_check() usage. ] --------------------------------------------------- arch/x86/kvm/mmu.c:3020 invoked rcu_dereference_check() without protection! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 0 2 locks held by qemu-system-x86/8550: #0: (&kvm->slots_lock){+.+.+.}, at: [] kvm_set_memory_region+0x29/0x50 [kvm] #1: (&(&kvm->mmu_lock)->rlock){+.+...}, at: [] kvm_arch_commit_memory_region+0xa6/0xe2 [kvm] stack backtrace: Pid: 8550, comm: qemu-system-x86 Not tainted 2.6.34-rc4-tip-01028-g939eab1 #27 Call Trace: [] lockdep_rcu_dereference+0xaa/0xb3 [] kvm_mmu_calculate_mmu_pages+0x44/0x7d [kvm] [] kvm_arch_commit_memory_region+0xb7/0xe2 [kvm] [] __kvm_set_memory_region+0x636/0x6e2 [kvm] [] kvm_set_memory_region+0x37/0x50 [kvm] [] vmx_set_tss_addr+0x46/0x5a [kvm_intel] [] kvm_arch_vm_ioctl+0x17a/0xcf8 [kvm] [] ? unlock_page+0x27/0x2c [] ? __do_fault+0x3a9/0x3e1 [] kvm_vm_ioctl+0x364/0x38d [kvm] [] ? up_read+0x23/0x3d [] vfs_ioctl+0x32/0xa6 [] do_vfs_ioctl+0x495/0x4db [] ? fget_light+0xc2/0x241 [] ? do_sys_open+0x104/0x116 [] ? retint_swapgs+0xe/0x13 [] sys_ioctl+0x47/0x6a [] system_call_fastpath+0x16/0x1b Signed-off-by: Lai Jiangshan Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 55830638aeb1..1ed030bad59e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -250,6 +250,13 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); +static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) +{ + return rcu_dereference_check(kvm->memslots, + srcu_read_lock_held(&kvm->srcu) + || lockdep_is_held(&kvm->slots_lock)); +} + #define HPA_MSB ((sizeof(hpa_t) * 8) - 1) #define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB) static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; } -- cgit v1.2.3 From 2a059bf444dd7758ccf48f217cd981570132be85 Mon Sep 17 00:00:00 2001 From: Gui Jianfeng Date: Fri, 16 Apr 2010 17:19:48 +0800 Subject: KVM: Get rid of dead function gva_to_page() Nobody use gva_to_page() anymore, get rid of it. Signed-off-by: Gui Jianfeng Signed-off-by: Avi Kivity --- 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 1ed030bad59e..ce027d518096 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -260,7 +260,6 @@ static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) #define HPA_MSB ((sizeof(hpa_t) * 8) - 1) #define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB) static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; } -struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva); extern struct page *bad_page; extern pfn_t bad_pfn; -- cgit v1.2.3 From e913fc825dc685a444cb4c1d0f9d32f372f59861 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 17 May 2010 12:55:07 +0200 Subject: writeback: fix WB_SYNC_NONE writeback from umount When umount calls sync_filesystem(), we first do a WB_SYNC_NONE writeback to kick off writeback of pending dirty inodes, then follow that up with a WB_SYNC_ALL to wait for it. Since umount already holds the sb s_umount mutex, WB_SYNC_NONE ends up doing nothing and all writeback happens as WB_SYNC_ALL. This can greatly slow down umount, since WB_SYNC_ALL writeback is a data integrity operation and thus a bigger hammer than simple WB_SYNC_NONE. For barrier aware file systems it's a lot slower. Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 2 +- include/linux/writeback.h | 10 ++++++++++ 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 7534979d83bd..ff8bac63213f 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -106,7 +106,7 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); void bdi_unregister(struct backing_dev_info *bdi); int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, - long nr_pages); + long nr_pages, int sb_locked); int bdi_writeback_task(struct bdi_writeback *wb); int bdi_has_dirty_io(struct backing_dev_info *bdi); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index eb38a2c645f6..47e1c686cb02 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -65,6 +65,15 @@ struct writeback_control { * so we use a single control to update them */ unsigned no_nrwrite_index_update:1; + + /* + * For WB_SYNC_ALL, the sb must always be pinned. For WB_SYNC_NONE, + * the writeback code will pin the sb for the caller. However, + * for eg umount, the caller does WB_SYNC_NONE but already has + * the sb pinned. If the below is set, caller already has the + * sb pinned. + */ + unsigned sb_pinned:1; }; /* @@ -73,6 +82,7 @@ struct writeback_control { struct bdi_writeback; int inode_wait(void *); void writeback_inodes_sb(struct super_block *); +void writeback_inodes_sb_locked(struct super_block *); int writeback_inodes_sb_if_idle(struct super_block *); void sync_inodes_sb(struct super_block *); void writeback_inodes_wbc(struct writeback_control *wbc); -- cgit v1.2.3 From 6495d2c6d04f4c45411fdb1b40527c24015f39d6 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Wed, 24 Mar 2010 16:07:04 +0100 Subject: drbd: Implemented the --assume-clean option for drbdsetup resize Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- include/linux/drbd.h | 3 ++- include/linux/drbd_nl.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 4341b1a97a34..7944dd36ee3e 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -56,7 +56,7 @@ extern const char *drbd_buildtag(void); #define REL_VERSION "8.3.7" #define API_VERSION 88 #define PRO_VERSION_MIN 86 -#define PRO_VERSION_MAX 92 +#define PRO_VERSION_MAX 93 enum drbd_io_error_p { @@ -139,6 +139,7 @@ enum drbd_ret_codes { ERR_DATA_NOT_CURRENT = 150, ERR_CONNECTED = 151, /* DRBD 8.3 only */ ERR_PERM = 152, + ERR_NEED_APV_93 = 153, /* insert new ones above this line */ AFTER_LAST_ERR_CODE diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h index f7431a4ca608..de055c07c2ba 100644 --- a/include/linux/drbd_nl.h +++ b/include/linux/drbd_nl.h @@ -71,6 +71,7 @@ NL_PACKET(disconnect, 6, ) NL_PACKET(resize, 7, NL_INT64( 29, T_MAY_IGNORE, resize_size) NL_BIT( 68, T_MAY_IGNORE, resize_force) + NL_BIT( 69, T_MANDATORY, no_resync) ) NL_PACKET(syncer_conf, 8, -- cgit v1.2.3 From caa20d974c86af496b419eef70010e63b7fab7ac Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 17 May 2010 16:24:16 -0700 Subject: async_tx: trim dma_async_tx_descriptor in 'no channel switch' case Saves 24 bytes per descriptor (64-bit) when the channel-switching capabilities of async_tx are not required. Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 60 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 20ea12c86fd0..cb234979fc6b 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -230,11 +230,71 @@ struct dma_async_tx_descriptor { dma_cookie_t (*tx_submit)(struct dma_async_tx_descriptor *tx); dma_async_tx_callback callback; void *callback_param; +#ifndef CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH struct dma_async_tx_descriptor *next; struct dma_async_tx_descriptor *parent; spinlock_t lock; +#endif }; +#ifdef CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH +static inline void txd_lock(struct dma_async_tx_descriptor *txd) +{ +} +static inline void txd_unlock(struct dma_async_tx_descriptor *txd) +{ +} +static inline void txd_chain(struct dma_async_tx_descriptor *txd, struct dma_async_tx_descriptor *next) +{ + BUG(); +} +static inline void txd_clear_parent(struct dma_async_tx_descriptor *txd) +{ +} +static inline void txd_clear_next(struct dma_async_tx_descriptor *txd) +{ +} +static inline struct dma_async_tx_descriptor *txd_next(struct dma_async_tx_descriptor *txd) +{ + return NULL; +} +static inline struct dma_async_tx_descriptor *txd_parent(struct dma_async_tx_descriptor *txd) +{ + return NULL; +} + +#else +static inline void txd_lock(struct dma_async_tx_descriptor *txd) +{ + spin_lock_bh(&txd->lock); +} +static inline void txd_unlock(struct dma_async_tx_descriptor *txd) +{ + spin_unlock_bh(&txd->lock); +} +static inline void txd_chain(struct dma_async_tx_descriptor *txd, struct dma_async_tx_descriptor *next) +{ + txd->next = next; + next->parent = txd; +} +static inline void txd_clear_parent(struct dma_async_tx_descriptor *txd) +{ + txd->parent = NULL; +} +static inline void txd_clear_next(struct dma_async_tx_descriptor *txd) +{ + txd->next = NULL; +} +static inline struct dma_async_tx_descriptor *txd_parent(struct dma_async_tx_descriptor *txd) +{ + return txd->parent; +} +static inline struct dma_async_tx_descriptor *txd_next(struct dma_async_tx_descriptor *txd) +{ + return txd->next; +} +#endif + /** * struct dma_device - info on the entity supplying DMA services * @chancnt: how many DMA channels are supported -- cgit v1.2.3 From 67c7ddd055c794f0d8e9466ca2d6b5cc0b73d4df Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Tue, 4 May 2010 11:12:00 +0200 Subject: drbd: Four new configuration settings for resync speed control To reasonably control resync speed over drbd-proxy connections, drbd has to measure the current delay of packets transmitted over the (possibly congested) data socket vs the meta-data socket. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- include/linux/drbd_limits.h | 16 ++++++++++++++++ include/linux/drbd_nl.h | 4 ++++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index 51f47a586ad8..440b42e38e89 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -133,5 +133,21 @@ #define DRBD_MAX_BIO_BVECS_MAX 128 #define DRBD_MAX_BIO_BVECS_DEF 0 +#define DRBD_DP_VOLUME_MIN 4 +#define DRBD_DP_VOLUME_MAX 1048576 +#define DRBD_DP_VOLUME_DEF 16384 + +#define DRBD_DP_INTERVAL_MIN 1 +#define DRBD_DP_INTERVAL_MAX 600 +#define DRBD_DP_INTERVAL_DEF 5 + +#define DRBD_RS_THROTTLE_TH_MIN 1 +#define DRBD_RS_THROTTLE_TH_MAX 600 +#define DRBD_RS_THROTTLE_TH_DEF 20 + +#define DRBD_RS_HOLD_OFF_TH_MIN 1 +#define DRBD_RS_HOLD_OFF_TH_MAX 6000 +#define DRBD_RS_HOLD_OFF_TH_DEF 100 + #undef RANGE #endif diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h index de055c07c2ba..ce77a746fc9d 100644 --- a/include/linux/drbd_nl.h +++ b/include/linux/drbd_nl.h @@ -78,6 +78,10 @@ NL_PACKET(syncer_conf, 8, NL_INTEGER( 30, T_MAY_IGNORE, rate) NL_INTEGER( 31, T_MAY_IGNORE, after) NL_INTEGER( 32, T_MAY_IGNORE, al_extents) + NL_INTEGER( 71, T_MAY_IGNORE, dp_volume) + NL_INTEGER( 72, T_MAY_IGNORE, dp_interval) + NL_INTEGER( 73, T_MAY_IGNORE, throttle_th) + NL_INTEGER( 74, T_MAY_IGNORE, hold_off_th) NL_STRING( 52, T_MAY_IGNORE, verify_alg, SHARED_SECRET_MAX) NL_STRING( 51, T_MAY_IGNORE, cpu_mask, 32) NL_STRING( 64, T_MAY_IGNORE, csums_alg, SHARED_SECRET_MAX) -- cgit v1.2.3 From 058276303dbc4ed089c1f7dad0871810b1f5ddf1 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 17 May 2010 16:30:42 -0700 Subject: DMAENGINE: extend the control command to include an arg This adds an argument to the DMAengine control function, so that we can later provide control commands that need some external data passed in through an argument akin to the ioctl() operation prototype. [dan.j.williams@intel.com: fix up some missed conversions] Signed-off-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 50b7b3e0d572..17456571ff7a 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -347,7 +347,8 @@ struct dma_device { struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, enum dma_data_direction direction, unsigned long flags); - int (*device_control)(struct dma_chan *chan, enum dma_ctrl_cmd cmd); + int (*device_control)(struct dma_chan *chan, enum dma_ctrl_cmd cmd, + unsigned long arg); enum dma_status (*device_tx_status)(struct dma_chan *chan, dma_cookie_t cookie, -- cgit v1.2.3 From 1471ca9aa71cd37b6a7476bb6f06a3a8622ea1bd Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Sun, 16 May 2010 17:27:03 +0200 Subject: fbdev: allow passing more than one aperture for handoff It removes a hack from nouveau code which had to detect which region to pass to kick vesafb/efifb. Signed-off-by: Marcin Slusarz Cc: Eric Anholt Cc: Ben Skeggs Cc: Thomas Hellstrom Cc: Dave Airlie Cc: Peter Jones Cc: Benjamin Herrenschmidt Signed-off-by: Dave Airlie --- include/linux/fb.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index c10163b4c40e..de5ff5fa8380 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -403,6 +403,7 @@ struct fb_cursor { #include #include #include +#include #include struct vm_area_struct; @@ -862,10 +863,22 @@ struct fb_info { /* we need the PCI or similiar aperture base/size not smem_start/size as smem_start may just be an object allocated inside the aperture so may not actually overlap */ - resource_size_t aperture_base; - resource_size_t aperture_size; + struct apertures_struct { + unsigned int count; + struct aperture { + resource_size_t base; + resource_size_t size; + } ranges[0]; + } *apertures; }; +static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { + struct apertures_struct *a = kzalloc(sizeof(struct apertures_struct) + + max_num * sizeof(struct aperture), GFP_KERNEL); + a->count = max_num; + return a; +} + #ifdef MODULE #define FBINFO_DEFAULT FBINFO_MODULE #else -- cgit v1.2.3 From 06415c564fb98562a4d6b6215615deb2d1cc0dae Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Sun, 16 May 2010 17:29:56 +0200 Subject: fbmem, drm/nouveau: kick firmware framebuffers as soon as possible Currently vesafb/efifb/... is kicked when hardware driver is registering framebuffer. To do it hardware must be fully functional, so there's a short window between start of initialisation and framebuffer registration when two drivers touch the hardware. Unfortunately sometimes it breaks nouveau initialisation. Fix it by kicking firmware driver(s) before we start touching the hardware. Reported-by: Didier Spaier Tested-by: Didier Spaier Signed-off-by: Marcin Slusarz Cc: Ben Skeggs Cc: Peter Jones Cc: Andrew Morton Signed-off-by: Dave Airlie --- include/linux/fb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index de5ff5fa8380..f88e2549123d 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -971,6 +971,7 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf, /* drivers/video/fbmem.c */ extern int register_framebuffer(struct fb_info *fb_info); extern int unregister_framebuffer(struct fb_info *fb_info); +extern void remove_conflicting_framebuffers(struct apertures_struct *a, const char *name); extern int fb_prepare_logo(struct fb_info *fb_info, int rotate); extern int fb_show_logo(struct fb_info *fb_info, int rotate); extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size); -- cgit v1.2.3 From 3b9676e7ac6eff4f50f1b48b6c36664f55b79507 Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Sun, 16 May 2010 17:33:09 +0200 Subject: vga16fb, drm: vga16fb->drm handoff let vga16fb claim 0xA0000+0x10000 region as its aperture; drm drivers don't use it, so we have to detect it and kick vga16fb manually - but only if drm is driving the primary card Signed-off-by: Marcin Slusarz Cc: James Simmons Cc: Dave Airlie Cc: Ben Skeggs Signed-off-by: Dave Airlie --- include/linux/fb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index f88e2549123d..1296af45169d 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -971,7 +971,8 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf, /* drivers/video/fbmem.c */ extern int register_framebuffer(struct fb_info *fb_info); extern int unregister_framebuffer(struct fb_info *fb_info); -extern void remove_conflicting_framebuffers(struct apertures_struct *a, const char *name); +extern void remove_conflicting_framebuffers(struct apertures_struct *a, + const char *name, bool primary); extern int fb_prepare_logo(struct fb_info *fb_info, int rotate); extern int fb_show_logo(struct fb_info *fb_info, int rotate); extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size); -- cgit v1.2.3 From 4f41c013f553957765902fb01475972f0af3e8e7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 May 2010 18:08:32 +0200 Subject: perf/ftrace: Optimize perf/tracepoint interaction for single events When we've got but a single event per tracepoint there is no reason to try and multiplex it so don't. Signed-off-by: Peter Zijlstra Tested-by: Ingo Molnar Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/ftrace_event.h | 8 +++++--- include/linux/perf_event.h | 2 +- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index c0f4b364c711..c8091001b943 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -132,6 +132,7 @@ struct ftrace_event_call { void *data; int perf_refcount; + void *perf_data; int (*perf_event_enable)(struct ftrace_event_call *); void (*perf_event_disable)(struct ftrace_event_call *); }; @@ -190,7 +191,7 @@ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); -extern int perf_trace_enable(int event_id); +extern int perf_trace_enable(int event_id, void *data); extern void perf_trace_disable(int event_id); extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); @@ -201,11 +202,12 @@ perf_trace_buf_prepare(int size, unsigned short type, int *rctxp, static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, - u64 count, unsigned long irq_flags, struct pt_regs *regs) + u64 count, unsigned long irq_flags, struct pt_regs *regs, + void *event) { struct trace_entry *entry = raw_data; - perf_tp_event(entry->type, addr, count, raw_data, size, regs); + perf_tp_event(entry->type, addr, count, raw_data, size, regs, event); perf_swevent_put_recursion_context(rctx); local_irq_restore(irq_flags); } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 3fd5c82e0e18..0b521fc8f5b0 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -994,7 +994,7 @@ static inline bool perf_paranoid_kernel(void) extern void perf_event_init(void); extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, - int entry_size, struct pt_regs *regs); + int entry_size, struct pt_regs *regs, void *event); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags -- cgit v1.2.3 From ef60777c9abd999db5eb4e338aae3eb593ae8e10 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 May 2010 10:50:41 +0200 Subject: perf: Optimize the perf_output() path by removing IRQ-disables Since we can now assume there is only a single writer to each buffer, we can remove per-cpu lock thingy and use a simply nest-count to the same effect. This removes the need to disable IRQs. Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0b521fc8f5b0..f1f853a9d5eb 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -597,12 +597,12 @@ struct perf_mmap_data { atomic_t events; /* event_id limit */ atomic_long_t head; /* write position */ - atomic_long_t done_head; /* completed head */ - atomic_t lock; /* concurrent writes */ atomic_t wakeup; /* needs a wakeup */ atomic_t lost; /* nr records lost */ + atomic_t nest; /* nested writers */ + long watermark; /* wakeup watermark */ struct perf_event_mmap_page *user_page; @@ -807,7 +807,6 @@ struct perf_output_handle { unsigned long offset; int nmi; int sample; - int locked; }; #ifdef CONFIG_PERF_EVENTS -- cgit v1.2.3 From fa5881514ef9c9bcb29319aad85cf2d8889d91f1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 May 2010 10:54:20 +0200 Subject: perf: Optimize the hotpath by converting the perf output buffer to local_t Since there is now only a single writer, we can use local_t instead and avoid all these pesky LOCK insn. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f1f853a9d5eb..ce7667616fcb 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -485,6 +485,7 @@ struct perf_guest_info_callbacks { #include #include #include +#include #define PERF_MAX_STACK_DEPTH 255 @@ -588,20 +589,18 @@ struct perf_mmap_data { #ifdef CONFIG_PERF_USE_VMALLOC struct work_struct work; #endif - int data_order; + int data_order; /* allocation order */ int nr_pages; /* nr of data pages */ int writable; /* are we writable */ int nr_locked; /* nr pages mlocked */ atomic_t poll; /* POLL_ for wakeups */ - atomic_t events; /* event_id limit */ - atomic_long_t head; /* write position */ - - atomic_t wakeup; /* needs a wakeup */ - atomic_t lost; /* nr records lost */ - - atomic_t nest; /* nested writers */ + local_t head; /* write position */ + local_t nest; /* nested writers */ + local_t events; /* event limit */ + local_t wakeup; /* needs a wakeup */ + local_t lost; /* nr records lost */ long watermark; /* wakeup watermark */ -- cgit v1.2.3 From 6d1acfd5c6bfd5231c13a8f2858d7f2afbaa1b62 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 May 2010 11:12:48 +0200 Subject: perf: Optimize perf_output_*() by avoiding local_xchg() Since the x86 XCHG ins implies LOCK, avoid the use by using a sequence count instead. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ce7667616fcb..fe50347dc645 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -804,6 +804,7 @@ struct perf_output_handle { struct perf_mmap_data *data; unsigned long head; unsigned long offset; + unsigned long wakeup; int nmi; int sample; }; -- cgit v1.2.3 From b27256439568950f30864ccecaeb6dfb588089d5 Mon Sep 17 00:00:00 2001 From: Nitin Gupta Date: Mon, 17 May 2010 11:02:42 +0530 Subject: swap: Add flag to identify block swap devices Added SWP_BLKDEV flag to distinguish block and regular file backed swap devices. We could also check if a swap is entire block device, rather than a file, by: S_ISBLK(swap_info_struct->swap_file->f_mapping->host->i_mode) but, I think, simply checking this flag is more convenient. Signed-off-by: Nitin Gupta Acked-by: Linus Torvalds Acked-by: Nigel Cunningham Acked-by: Pekka Enberg Reviewed-by: Minchan Kim Signed-off-by: Greg Kroah-Hartman --- include/linux/swap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 1f59d9340c4d..ec2b7a42b45f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -146,6 +146,7 @@ enum { SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */ SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ + SWP_BLKDEV = (1 << 6), /* its a block device */ /* add others here before... */ SWP_SCANNING = (1 << 8), /* refcount in scan_swap_map */ }; -- cgit v1.2.3 From b3a27d0529c6e5206f1b60f60263e3ecfd0d77cb Mon Sep 17 00:00:00 2001 From: Nitin Gupta Date: Mon, 17 May 2010 11:02:43 +0530 Subject: swap: Add swap slot free callback to block_device_operations This callback is required when RAM based devices are used as swap disks. One such device is ramzswap which is used as compressed in-memory swap disk. For such devices, we need a callback as soon as a swap slot is no longer used to allow freeing memory allocated for this slot. Without this callback, stale data can quickly accumulate in memory defeating the whole purpose of such devices. Signed-off-by: Nitin Gupta Acked-by: Linus Torvalds Acked-by: Nigel Cunningham Acked-by: Pekka Enberg Reviewed-by: Minchan Kim Signed-off-by: Greg Kroah-Hartman --- 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 6690e8bae7bb..413284a51ccc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1287,6 +1287,8 @@ struct block_device_operations { unsigned long long); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); + /* this callback is with swap_lock and sometimes page table lock held */ + void (*swap_slot_free_notify) (struct block_device *, unsigned long); struct module *owner; }; -- cgit v1.2.3 From 5c40cbfefa828208c671e2f58789e4dd04f79563 Mon Sep 17 00:00:00 2001 From: Clemens Ladisch Date: Tue, 27 Apr 2010 09:07:00 +0200 Subject: firewire: core: use separate timeout for each transaction Using a single timeout for all transaction that need to be flushed does not work if the submission of new transactions can defer the timeout indefinitely into the future. We need to have timeouts that do not change due to other transactions; the simplest way to do this is with a separate timer for each transaction. Signed-off-by: Clemens Ladisch Signed-off-by: Stefan Richter (+ one lockdep annotation) --- include/linux/firewire.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index a527d73f9966..72e2b8ac2a5a 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -87,7 +87,6 @@ struct fw_card { int current_tlabel; u64 tlabel_mask; struct list_head transaction_list; - struct timer_list flush_timer; unsigned long reset_jiffies; unsigned long long guid; @@ -288,6 +287,8 @@ struct fw_transaction { int tlabel; int timestamp; struct list_head link; + struct fw_card *card; + struct timer_list split_timeout_timer; struct fw_packet packet; -- cgit v1.2.3 From d46a5ac7a7e2045e33c6ad6ffb8cf18a7e86a15a Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Wed, 19 May 2010 13:43:14 +1000 Subject: padata: Use a timer to handle remaining objects in the reorder queues padata_get_next needs to check whether the next object that need serialization must be parallel processed by the local cpu. This check was wrong implemented and returned always true, so the try_again loop in padata_reorder was never taken. This can lead to object leaks in some rare cases due to a race that appears with the trylock in padata_reorder. The try_again loop was not a good idea after all, because a cpu could take that loop frequently, so we handle this with a timer instead. This patch adds a timer to handle the race that appears with the trylock. If cpu1 queues an object to the reorder queue while cpu2 holds the pd->lock but left the while loop in padata_reorder already, cpu2 can't care for this object and cpu1 exits because it can't get the lock. Usually the next cpu that takes the lock cares for this object too. We need the timer just if this object was the last one that arrives to the reorder queues. The timer function sends it out in this case. Signed-off-by: Steffen Klassert Signed-off-by: Herbert Xu --- include/linux/padata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index 51611da9c498..64836a63bd17 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -24,6 +24,7 @@ #include #include #include +#include struct padata_priv { struct list_head list; @@ -60,6 +61,7 @@ struct parallel_data { unsigned int max_seq_nr; cpumask_var_t cpumask; spinlock_t lock; + struct timer_list timer; }; struct padata_instance { -- cgit v1.2.3 From 0198ffd135f51d4fbb0c50036395716c06632ed9 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Wed, 19 May 2010 13:44:27 +1000 Subject: padata: Add some code comments Signed-off-by: Steffen Klassert Signed-off-by: Herbert Xu --- include/linux/padata.h | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index 64836a63bd17..8d8406246eef 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -26,6 +26,17 @@ #include #include +/** + * struct padata_priv - Embedded to the users data structure. + * + * @list: List entry, to attach to the padata lists. + * @pd: Pointer to the internal control structure. + * @cb_cpu: Callback cpu for serializatioon. + * @seq_nr: Sequence number of the parallelized data object. + * @info: Used to pass information from the parallel to the serial function. + * @parallel: Parallel execution function. + * @serial: Serial complete function. + */ struct padata_priv { struct list_head list; struct parallel_data *pd; @@ -36,11 +47,29 @@ struct padata_priv { void (*serial)(struct padata_priv *padata); }; +/** + * struct padata_list + * + * @list: List head. + * @lock: List lock. + */ struct padata_list { struct list_head list; spinlock_t lock; }; +/** + * struct padata_queue - The percpu padata queues. + * + * @parallel: List to wait for parallelization. + * @reorder: List to wait for reordering after parallel processing. + * @serial: List to wait for serialization after reordering. + * @pwork: work struct for parallelization. + * @swork: work struct for serialization. + * @pd: Backpointer to the internal control structure. + * @num_obj: Number of objects that are processed by this cpu. + * @cpu_index: Index of the cpu. + */ struct padata_queue { struct padata_list parallel; struct padata_list reorder; @@ -52,6 +81,20 @@ struct padata_queue { int cpu_index; }; +/** + * struct parallel_data - Internal control structure, covers everything + * that depends on the cpumask in use. + * + * @pinst: padata instance. + * @queue: percpu padata queues. + * @seq_nr: The sequence number that will be attached to the next object. + * @reorder_objects: Number of objects waiting in the reorder queues. + * @refcnt: Number of objects holding a reference on this parallel_data. + * @max_seq_nr: Maximal used sequence number. + * @cpumask: cpumask in use. + * @lock: Reorder lock. + * @timer: Reorder timer. + */ struct parallel_data { struct padata_instance *pinst; struct padata_queue *queue; @@ -64,6 +107,16 @@ struct parallel_data { struct timer_list timer; }; +/** + * struct padata_instance - The overall control structure. + * + * @cpu_notifier: cpu hotplug notifier. + * @wq: The workqueue in use. + * @pd: The internal control structure. + * @cpumask: User supplied cpumask. + * @lock: padata instance lock. + * @flags: padata flags. + */ struct padata_instance { struct notifier_block cpu_notifier; struct workqueue_struct *wq; -- cgit v1.2.3 From 92946bc72f2e74c3281b7fc12be9704d455fb3ed Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sat, 3 Apr 2010 19:36:42 +0100 Subject: panic: Add taint flag TAINT_FIRMWARE_WORKAROUND ('I') This taint flag will initially be used when warning about invalid ACPI DMAR tables. Signed-off-by: Ben Hutchings Signed-off-by: David Woodhouse --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7f0707463360..7f2f7b34dd08 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -344,6 +344,7 @@ extern enum system_states { #define TAINT_OVERRIDDEN_ACPI_TABLE 8 #define TAINT_WARN 9 #define TAINT_CRAP 10 +#define TAINT_FIRMWARE_WORKAROUND 11 extern void dump_stack(void) __cold; -- cgit v1.2.3 From 90def62df67b423c4c976bc30eccb5957b7befda Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 19 May 2010 17:33:38 -0600 Subject: isapnp: move definitions to mod_devicetable.h so file2alias can reach them. Signed-off-by: Rusty Russell --- include/linux/isapnp.h | 8 +------- include/linux/mod_devicetable.h | 7 +++++++ 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/isapnp.h b/include/linux/isapnp.h index cd5a269fdb5e..e2d28b026a8c 100644 --- a/include/linux/isapnp.h +++ b/include/linux/isapnp.h @@ -43,10 +43,10 @@ */ #ifdef __KERNEL__ +#include #define DEVICE_COUNT_COMPATIBLE 4 -#define ISAPNP_ANY_ID 0xffff #define ISAPNP_CARD_DEVS 8 #define ISAPNP_CARD_ID(_va, _vb, _vc, _device) \ @@ -74,12 +74,6 @@ struct isapnp_card_id { #define ISAPNP_DEVICE_SINGLE_END \ .card_vendor = 0, .card_device = 0 -struct isapnp_device_id { - unsigned short card_vendor, card_device; - unsigned short vendor, function; - unsigned long driver_data; /* data private to the driver */ -}; - #if defined(CONFIG_ISAPNP) || (defined(CONFIG_ISAPNP_MODULE) && defined(MODULE)) #define __ISAPNP__ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 56fde4364e4c..d7707004b4b0 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -483,4 +483,11 @@ struct zorro_device_id { #define ZORRO_DEVICE_MODALIAS_FMT "zorro:i%08X" +#define ISAPNP_ANY_ID 0xffff +struct isapnp_device_id { + unsigned short card_vendor, card_device; + unsigned short vendor, function; + kernel_ulong_t driver_data; /* data private to the driver */ +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ -- cgit v1.2.3 From 5f487cd34f4337f9bc27ca19da72a39d1b0a0ab4 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Tue, 18 May 2010 21:49:51 +0200 Subject: power_supply: Use attribute groups This fixes a race between power supply device and initial attributes creation, plus makes it possible to implement writable properties. [Daniel Mack - removed superflous return statement and dropped .mode attribute from POWER_SUPPLY_ATTR] Suggested-by: Greg KH Suggested-by: Kay Sievers Signed-off-by: Anton Vorontsov Tested-by: Daniel Mack --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index ebd2b8fb00d0..c5f73a3ab3ab 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -114,6 +114,7 @@ enum power_supply_property { POWER_SUPPLY_PROP_TIME_TO_EMPTY_AVG, POWER_SUPPLY_PROP_TIME_TO_FULL_NOW, POWER_SUPPLY_PROP_TIME_TO_FULL_AVG, + POWER_SUPPLY_PROP_TYPE, /* use power_supply.type instead */ /* Properties of type `const char *' */ POWER_SUPPLY_PROP_MODEL_NAME, POWER_SUPPLY_PROP_MANUFACTURER, -- cgit v1.2.3 From 0011d2d4a5f7bb5666dcfb9f9b3dbdb084ab98f1 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Tue, 18 May 2010 21:49:52 +0200 Subject: power_supply: Add support for writeable properties This patch adds support for writeable power supply properties and exposes them as writeable to sysfs. A power supply implementation must implement two new function calls in order to use that feature: int set_property(struct power_supply *psy, enum power_supply_property psp, const union power_supply_propval *val); int property_is_writeable(struct power_supply *psy, enum power_supply_property psp); Signed-off-by: Daniel Mack Cc: David Woodhouse Cc: Alexey Starikovskiy Cc: Len Brown Cc: Mark Brown Cc: Matt Reimer Cc: Evgeniy Polyakov Cc: Tejun Heo Signed-off-by: Anton Vorontsov --- include/linux/power_supply.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index c5f73a3ab3ab..30083a896f36 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -145,6 +145,11 @@ struct power_supply { int (*get_property)(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val); + int (*set_property)(struct power_supply *psy, + enum power_supply_property psp, + const union power_supply_propval *val); + int (*property_is_writeable)(struct power_supply *psy, + enum power_supply_property psp); void (*external_power_changed)(struct power_supply *psy); void (*set_charged)(struct power_supply *psy); -- cgit v1.2.3 From 0ee75bead83da4791e5cbf659806c54d8ee40f12 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 28 Apr 2010 15:39:01 +0300 Subject: KVM: Let vcpu structure alignment be determined at runtime vmx and svm vcpus have different contents and therefore may have different alignmment requirements. Let each specify its required alignment. Signed-off-by: Avi Kivity --- 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 ce027d518096..7cb116afa1cd 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -243,7 +243,7 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); -int kvm_init(void *opaque, unsigned int vcpu_size, +int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, struct module *module); void kvm_exit(void); -- cgit v1.2.3 From cafd66595d92591e4bd25c3904e004fc6f897e2d Mon Sep 17 00:00:00 2001 From: Shane Wang Date: Thu, 29 Apr 2010 12:09:01 -0400 Subject: KVM: VMX: enable VMXON check with SMX enabled (Intel TXT) Per document, for feature control MSR: Bit 1 enables VMXON in SMX operation. If the bit is clear, execution of VMXON in SMX operation causes a general-protection exception. Bit 2 enables VMXON outside SMX operation. If the bit is clear, execution of VMXON outside SMX operation causes a general-protection exception. This patch is to enable this kind of check with SMX for VMXON in KVM. Signed-off-by: Shane Wang Signed-off-by: Avi Kivity --- include/linux/tboot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tboot.h b/include/linux/tboot.h index bf2a0c748878..1dba6ee55203 100644 --- a/include/linux/tboot.h +++ b/include/linux/tboot.h @@ -150,6 +150,7 @@ extern int tboot_force_iommu(void); #else +#define tboot_enabled() 0 #define tboot_probe() do { } while (0) #define tboot_shutdown(shutdown_type) do { } while (0) #define tboot_sleep(sleep_state, pm1a_control, pm1b_control) \ -- cgit v1.2.3 From 4cb2ea28c55cf5e5ef83aec535099ffce3c583df Mon Sep 17 00:00:00 2001 From: john cooper Date: Thu, 25 Mar 2010 01:33:33 -0400 Subject: Add virtio disk identification support Add virtio-blk device id (s/n) support via virtio request. Signed-off-by: john cooper Signed-off-by: Rusty Russell --- include/linux/virtio_blk.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h index e52029e98919..167720d695ed 100644 --- a/include/linux/virtio_blk.h +++ b/include/linux/virtio_blk.h @@ -17,6 +17,8 @@ #define VIRTIO_BLK_F_FLUSH 9 /* Cache flush command support */ #define VIRTIO_BLK_F_TOPOLOGY 10 /* Topology information is available */ +#define VIRTIO_BLK_ID_BYTES 20 /* ID string length */ + struct virtio_blk_config { /* The capacity (in 512-byte sectors). */ __u64 capacity; @@ -67,6 +69,9 @@ struct virtio_blk_config { /* Cache flush command */ #define VIRTIO_BLK_T_FLUSH 4 +/* Get device ID command */ +#define VIRTIO_BLK_T_GET_ID 8 + /* Barrier before this op. */ #define VIRTIO_BLK_T_BARRIER 0x80000000 -- cgit v1.2.3 From 316f25f5b3d547ce892d370f99f08a27276896ff Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 12 Apr 2010 16:18:25 +0300 Subject: virtio: add virtqueue_ vq_ops wrappers Add inline functions that wrap vq->vq_ops-> calls Signed-off-by: Michael S. Tsirkin Signed-off-by: Rusty Russell --- include/linux/virtio.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 40d1709bdbf4..18ccc686a429 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -77,6 +77,40 @@ struct virtqueue_ops { void *(*detach_unused_buf)(struct virtqueue *vq); }; +static inline int virtqueue_add_buf(struct virtqueue *vq, + struct scatterlist sg[], + unsigned int out_num, + unsigned int in_num, + void *data) +{ + return vq->vq_ops->add_buf(vq, sg, out_num, in_num, data); +} + +static inline int void virtqueue_kick(struct virtqueue *vq) +{ + return vq->vq_ops->kick(vq); +} + +static inline void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len) +{ + return vq->vq_ops->get_buf(vq, len); +} + +static inline void virtqueue_disable_cb(struct virtqueue *vq) +{ + vq->vq_ops->disable_cb(vq); +} + +static inline bool virtqueue_enable_cb(struct virtqueue *vq) +{ + return vq->vq_ops->enable_cb(vq); +} + +static inline void *virtqueue_detach_unused_buf(struct virtqueue *vq) +{ + return vq->vq_ops->detach_unused_buf(vq); +} + /** * virtio_device - representation of a device using virtio * @index: unique position on the virtio bus -- cgit v1.2.3 From 7c5e9ed0c84e7d70d887878574590638d5572659 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 12 Apr 2010 16:19:07 +0300 Subject: virtio_ring: remove a level of indirection We have a single virtqueue_ops implementation, and it seems unlikely we'll get another one at this point. So let's remove an unnecessary level of indirection: it would be very easy to re-add it if another implementation surfaces. Signed-off-by: Michael S. Tsirkin Signed-off-by: Rusty Russell --- include/linux/virtio.h | 71 +++++++++++++------------------------------------- 1 file changed, 18 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 18ccc686a429..5b0fce0d2aa2 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -14,7 +14,6 @@ * @callback: the function to call when buffers are consumed (can be NULL). * @name: the name of this virtqueue (mainly for debugging) * @vdev: the virtio device this queue was created for. - * @vq_ops: the operations for this virtqueue (see below). * @priv: a pointer for the virtqueue implementation to use. */ struct virtqueue { @@ -22,94 +21,60 @@ struct virtqueue { void (*callback)(struct virtqueue *vq); const char *name; struct virtio_device *vdev; - struct virtqueue_ops *vq_ops; void *priv; }; /** - * virtqueue_ops - operations for virtqueue abstraction layer - * @add_buf: expose buffer to other end + * operations for virtqueue + * virtqueue_add_buf: expose buffer to other end * vq: the struct virtqueue we're talking about. * sg: the description of the buffer(s). * out_num: the number of sg readable by other side * in_num: the number of sg which are writable (after readable ones) * data: the token identifying the buffer. * Returns remaining capacity of queue (sg segments) or a negative error. - * @kick: update after add_buf + * virtqueue_kick: update after add_buf * vq: the struct virtqueue * After one or more add_buf calls, invoke this to kick the other side. - * @get_buf: get the next used buffer + * virtqueue_get_buf: get the next used buffer * vq: the struct virtqueue we're talking about. * len: the length written into the buffer * Returns NULL or the "data" token handed to add_buf. - * @disable_cb: disable callbacks + * virtqueue_disable_cb: disable callbacks * vq: the struct virtqueue we're talking about. * Note that this is not necessarily synchronous, hence unreliable and only * useful as an optimization. - * @enable_cb: restart callbacks after disable_cb. + * virtqueue_enable_cb: restart callbacks after disable_cb. * vq: the struct virtqueue we're talking about. * This re-enables callbacks; it returns "false" if there are pending * buffers in the queue, to detect a possible race between the driver * checking for more work, and enabling callbacks. - * @detach_unused_buf: detach first unused buffer + * virtqueue_detach_unused_buf: detach first unused buffer * vq: the struct virtqueue we're talking about. * Returns NULL or the "data" token handed to add_buf * * Locking rules are straightforward: the driver is responsible for * locking. No two operations may be invoked simultaneously, with the exception - * of @disable_cb. + * of virtqueue_disable_cb. * * All operations can be called in any context. */ -struct virtqueue_ops { - int (*add_buf)(struct virtqueue *vq, - struct scatterlist sg[], - unsigned int out_num, - unsigned int in_num, - void *data); - void (*kick)(struct virtqueue *vq); +int virtqueue_add_buf(struct virtqueue *vq, + struct scatterlist sg[], + unsigned int out_num, + unsigned int in_num, + void *data); - void *(*get_buf)(struct virtqueue *vq, unsigned int *len); +void virtqueue_kick(struct virtqueue *vq); - void (*disable_cb)(struct virtqueue *vq); - bool (*enable_cb)(struct virtqueue *vq); - void *(*detach_unused_buf)(struct virtqueue *vq); -}; - -static inline int virtqueue_add_buf(struct virtqueue *vq, - struct scatterlist sg[], - unsigned int out_num, - unsigned int in_num, - void *data) -{ - return vq->vq_ops->add_buf(vq, sg, out_num, in_num, data); -} - -static inline int void virtqueue_kick(struct virtqueue *vq) -{ - return vq->vq_ops->kick(vq); -} - -static inline void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len) -{ - return vq->vq_ops->get_buf(vq, len); -} +void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len); -static inline void virtqueue_disable_cb(struct virtqueue *vq) -{ - vq->vq_ops->disable_cb(vq); -} +void virtqueue_disable_cb(struct virtqueue *vq); -static inline bool virtqueue_enable_cb(struct virtqueue *vq) -{ - return vq->vq_ops->enable_cb(vq); -} +bool virtqueue_enable_cb(struct virtqueue *vq); -static inline void *virtqueue_detach_unused_buf(struct virtqueue *vq) -{ - return vq->vq_ops->detach_unused_buf(vq); -} +void *virtqueue_detach_unused_buf(struct virtqueue *vq); /** * virtio_device - representation of a device using virtio -- cgit v1.2.3 From bbd603efb4238cf78083c00f0a81adfa8994aa33 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 29 Apr 2010 17:26:37 +0300 Subject: virtio: add_buf_gfp Add an add_buf variant that gets gfp parameter. Use that to allocate indirect buffers. Signed-off-by: Michael S. Tsirkin Signed-off-by: Rusty Russell --- include/linux/virtio.h | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 5b0fce0d2aa2..aff5b4f74041 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -7,6 +7,7 @@ #include #include #include +#include /** * virtqueue - a queue to register buffers for sending or receiving. @@ -32,6 +33,7 @@ struct virtqueue { * out_num: the number of sg readable by other side * in_num: the number of sg which are writable (after readable ones) * data: the token identifying the buffer. + * gfp: how to do memory allocations (if necessary). * Returns remaining capacity of queue (sg segments) or a negative error. * virtqueue_kick: update after add_buf * vq: the struct virtqueue @@ -60,11 +62,21 @@ struct virtqueue { * All operations can be called in any context. */ -int virtqueue_add_buf(struct virtqueue *vq, - struct scatterlist sg[], - unsigned int out_num, - unsigned int in_num, - void *data); +int virtqueue_add_buf_gfp(struct virtqueue *vq, + struct scatterlist sg[], + unsigned int out_num, + unsigned int in_num, + void *data, + gfp_t gfp); + +static inline int virtqueue_add_buf(struct virtqueue *vq, + struct scatterlist sg[], + unsigned int out_num, + unsigned int in_num, + void *data) +{ + return virtqueue_add_buf_gfp(vq, sg, out_num, in_num, data, GFP_ATOMIC); +} void virtqueue_kick(struct virtqueue *vq); -- cgit v1.2.3 From b99fa815d71023b2e330d63cd7f47d6247ffa321 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Wed, 19 May 2010 22:15:46 -0600 Subject: virtio: Revert "virtio: disable multiport console support." This reverts commit b7a413015d2986edf020fba765c906cc9cbcbfc9. Multiport support was disabled for 2.6.34 because we wanted to introduce a new ABI and since we didn't have any released kernel with the older ABI and were out of the merge window, it didn't make sense keeping the older ABI around. Now we revert the patch disabling multiport and rework the ABI in the following patches. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- include/linux/virtio_console.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h index 92228a8fbcbc..ae4f039515b4 100644 --- a/include/linux/virtio_console.h +++ b/include/linux/virtio_console.h @@ -12,14 +12,37 @@ /* Feature bits */ #define VIRTIO_CONSOLE_F_SIZE 0 /* Does host provide console size? */ +#define VIRTIO_CONSOLE_F_MULTIPORT 1 /* Does host provide multiple ports? */ struct virtio_console_config { /* colums of the screens */ __u16 cols; /* rows of the screens */ __u16 rows; + /* max. number of ports this device can hold */ + __u32 max_nr_ports; + /* number of ports added so far */ + __u32 nr_ports; } __attribute__((packed)); +/* + * A message that's passed between the Host and the Guest for a + * particular port. + */ +struct virtio_console_control { + __u32 id; /* Port number */ + __u16 event; /* The kind of control event (see below) */ + __u16 value; /* Extra information for the key */ +}; + +/* Some events for control messages */ +#define VIRTIO_CONSOLE_PORT_READY 0 +#define VIRTIO_CONSOLE_CONSOLE_PORT 1 +#define VIRTIO_CONSOLE_RESIZE 2 +#define VIRTIO_CONSOLE_PORT_OPEN 3 +#define VIRTIO_CONSOLE_PORT_NAME 4 +#define VIRTIO_CONSOLE_PORT_REMOVE 5 + #ifdef __KERNEL__ int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int)); #endif /* __KERNEL__ */ -- cgit v1.2.3 From eaeff9608a8cf43a676b6f4b6235ea9d76192230 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Wed, 19 May 2010 22:15:47 -0600 Subject: virtio: console: Let host know of port or device add failures The host may want to know and let management apps notify of port or device add failures. Send a control message saying the device or port is not ready in this case. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- include/linux/virtio_console.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h index ae4f039515b4..015736113c25 100644 --- a/include/linux/virtio_console.h +++ b/include/linux/virtio_console.h @@ -14,6 +14,8 @@ #define VIRTIO_CONSOLE_F_SIZE 0 /* Does host provide console size? */ #define VIRTIO_CONSOLE_F_MULTIPORT 1 /* Does host provide multiple ports? */ +#define VIRTIO_CONSOLE_BAD_ID (~(u32)0) + struct virtio_console_config { /* colums of the screens */ __u16 cols; @@ -42,6 +44,7 @@ struct virtio_console_control { #define VIRTIO_CONSOLE_PORT_OPEN 3 #define VIRTIO_CONSOLE_PORT_NAME 4 #define VIRTIO_CONSOLE_PORT_REMOVE 5 +#define VIRTIO_CONSOLE_DEVICE_READY 6 #ifdef __KERNEL__ int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int)); -- cgit v1.2.3 From f909f850d666e3dbac1ee7c9d5d83416bd02f84e Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Wed, 19 May 2010 22:15:48 -0600 Subject: virtio: console: Use a control message to add ports Instead of the host and guest independently enumerating ports, switch to a control message to add ports where the host supplies the port number so there's no ambiguity or a possibility of a race between the host and the guest port numbers. We now no longer need the 'nr_ports' config value. Since no kernel has been released with the MULTIPORT changes yet, we have a chance to fiddle with the config space without adding compatibility features. This is beneficial for management software, which would now be able to instantiate ports at known locations and avoid problems that arise with implicit numbering in the host and the guest. This removes the 'guessing game' part of it, and management software can now actually indicate which id to spawn a particular port on. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- include/linux/virtio_console.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h index 015736113c25..a85064db8f94 100644 --- a/include/linux/virtio_console.h +++ b/include/linux/virtio_console.h @@ -23,8 +23,6 @@ struct virtio_console_config { __u16 rows; /* max. number of ports this device can hold */ __u32 max_nr_ports; - /* number of ports added so far */ - __u32 nr_ports; } __attribute__((packed)); /* @@ -38,13 +36,14 @@ struct virtio_console_control { }; /* Some events for control messages */ -#define VIRTIO_CONSOLE_PORT_READY 0 -#define VIRTIO_CONSOLE_CONSOLE_PORT 1 -#define VIRTIO_CONSOLE_RESIZE 2 -#define VIRTIO_CONSOLE_PORT_OPEN 3 -#define VIRTIO_CONSOLE_PORT_NAME 4 -#define VIRTIO_CONSOLE_PORT_REMOVE 5 -#define VIRTIO_CONSOLE_DEVICE_READY 6 +#define VIRTIO_CONSOLE_DEVICE_READY 0 +#define VIRTIO_CONSOLE_PORT_ADD 1 +#define VIRTIO_CONSOLE_PORT_REMOVE 2 +#define VIRTIO_CONSOLE_PORT_READY 3 +#define VIRTIO_CONSOLE_CONSOLE_PORT 4 +#define VIRTIO_CONSOLE_RESIZE 5 +#define VIRTIO_CONSOLE_PORT_OPEN 6 +#define VIRTIO_CONSOLE_PORT_NAME 7 #ifdef __KERNEL__ int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int)); -- cgit v1.2.3 From 1f0ce8b3dd667dca720a47869f8110c298f0e5b8 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Wed, 19 May 2010 12:01:42 +0100 Subject: mm: Move ARCH_SLAB_MINALIGN and ARCH_KMALLOC_MINALIGN to Acked-by: Herbert Xu Signed-off-by: David Woodhouse Signed-off-by: Pekka Enberg --- include/linux/slab_def.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index ca6b2b317991..1812dac8c496 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -16,6 +16,30 @@ #include #include +#ifndef ARCH_KMALLOC_MINALIGN +/* + * Enforce a minimum alignment for the kmalloc caches. + * Usually, the kmalloc caches are cache_line_size() aligned, except when + * DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned. + * Some archs want to perform DMA into kmalloc caches and need a guaranteed + * alignment larger than the alignment of a 64-bit integer. + * ARCH_KMALLOC_MINALIGN allows that. + * Note that increasing this value may disable some debug features. + */ +#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) +#endif + +#ifndef ARCH_SLAB_MINALIGN +/* + * Enforce a minimum alignment for all caches. + * Intended for archs that get misalignment faults even for BYTES_PER_WORD + * aligned buffers. Includes ARCH_KMALLOC_MINALIGN. + * If possible: Do not enable this flag for CONFIG_DEBUG_SLAB, it disables + * some debug features. + */ +#define ARCH_SLAB_MINALIGN 0 +#endif + /* * struct kmem_cache * -- cgit v1.2.3 From bac49ce42a33f53beb7cf04e9a0600879d6265ca Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Wed, 19 May 2010 12:01:43 +0100 Subject: mm: Move ARCH_SLAB_MINALIGN and ARCH_KMALLOC_MINALIGN to Acked-by: Herbert Xu Signed-off-by: David Woodhouse Signed-off-by: Pekka Enberg --- include/linux/slob_def.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slob_def.h b/include/linux/slob_def.h index 0ec00b39d006..62667f72c2ef 100644 --- a/include/linux/slob_def.h +++ b/include/linux/slob_def.h @@ -1,6 +1,14 @@ #ifndef __LINUX_SLOB_DEF_H #define __LINUX_SLOB_DEF_H +#ifndef ARCH_KMALLOC_MINALIGN +#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long) +#endif + +#ifndef ARCH_SLAB_MINALIGN +#define ARCH_SLAB_MINALIGN __alignof__(unsigned long) +#endif + void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); static __always_inline void *kmem_cache_alloc(struct kmem_cache *cachep, -- cgit v1.2.3 From 4581ced379736fd76432c754f999d26deb83fbb7 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Wed, 19 May 2010 12:02:14 +0100 Subject: mm: Move ARCH_SLAB_MINALIGN and ARCH_KMALLOC_MINALIGN to Acked-by: Herbert Xu Signed-off-by: David Woodhouse Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 0249d4175bac..55695c8d2f8a 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -116,6 +116,14 @@ struct kmem_cache { #define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) +#ifndef ARCH_KMALLOC_MINALIGN +#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) +#endif + +#ifndef ARCH_SLAB_MINALIGN +#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) +#endif + /* * Maximum kmalloc object size handled by SLUB. Larger object allocations * are passed through to the page allocator. The page allocator "fastpath" -- cgit v1.2.3 From ec49fdbd354cb133340e25ff84d88284bb17e99a Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Wed, 19 May 2010 12:02:17 +0100 Subject: crypto: Use ARCH_KMALLOC_MINALIGN for CRYPTO_MINALIGN now that it's exposed Acked-by: Herbert Xu Signed-off-by: David Woodhouse Signed-off-by: Pekka Enberg --- include/linux/crypto.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 24d2e30f1b46..a6a7a1c83f54 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -99,13 +99,7 @@ * as arm where pointers are 32-bit aligned but there are data types such as * u64 which require 64-bit alignment. */ -#if defined(ARCH_KMALLOC_MINALIGN) #define CRYPTO_MINALIGN ARCH_KMALLOC_MINALIGN -#elif defined(ARCH_SLAB_MINALIGN) -#define CRYPTO_MINALIGN ARCH_SLAB_MINALIGN -#else -#define CRYPTO_MINALIGN __alignof__(unsigned long long) -#endif #define CRYPTO_MINALIGN_ATTR __attribute__ ((__aligned__(CRYPTO_MINALIGN))) -- cgit v1.2.3 From affb72c3a8984ba55e055b0a0228c3ea1a056758 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Tue, 18 May 2010 14:35:16 +0800 Subject: ACPI, APEI, PCIE AER, use general HEST table parsing in AER firmware_first setup Now, a dedicated HEST tabling parsing code is used for PCIE AER firmware_first setup. It is rebased on general HEST tabling parsing code of APEI. The firmware_first setup code is moved from PCI core to AER driver too, because it is only AER related. Signed-off-by: Huang Ying Signed-off-by: Andi Kleen Reviewed-by: Hidetoshi Seto Acked-by: Jesse Barnes Signed-off-by: Len Brown --- include/linux/pci.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index a788fa12ff31..63967e877f20 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -311,7 +311,8 @@ struct pci_dev { unsigned int is_virtfn:1; unsigned int reset_fn:1; unsigned int is_hotplug_bridge:1; - unsigned int aer_firmware_first:1; + unsigned int __aer_firmware_first_valid:1; + unsigned int __aer_firmware_first:1; pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ -- cgit v1.2.3 From fab1c23242528771a955c475ef23d99156a71a7f Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Tue, 18 May 2010 14:35:18 +0800 Subject: Unified UUID/GUID definition There are many different UUID/GUID definitions in kernel, such as that in EFI, many file systems, some drivers, etc. Every kernel components need UUID/GUID has its own definition. This patch provides a unified definition for UUID/GUID. UUID is defined via typedef. This makes that UUID appears more like a preliminary type, and makes the data type explicit (comparing with implicit "u8 uuid[16]"). The binary representation of UUID/GUID can be little-endian (used by EFI, etc) or big-endian (defined by RFC4122), so both is defined. Signed-off-by: Huang Ying Signed-off-by: Andi Kleen Signed-off-by: Len Brown --- include/linux/uuid.h | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) create mode 100644 include/linux/uuid.h (limited to 'include/linux') diff --git a/include/linux/uuid.h b/include/linux/uuid.h new file mode 100644 index 000000000000..5b7efbfcee4e --- /dev/null +++ b/include/linux/uuid.h @@ -0,0 +1,70 @@ +/* + * UUID/GUID definition + * + * Copyright (C) 2010, Intel Corp. + * Huang Ying + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation; + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef _LINUX_UUID_H_ +#define _LINUX_UUID_H_ + +#include +#include + +typedef struct { + __u8 b[16]; +} uuid_le; + +typedef struct { + __u8 b[16]; +} uuid_be; + +#define UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ +((uuid_le) \ +{{ (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ + (b) & 0xff, ((b) >> 8) & 0xff, \ + (c) & 0xff, ((c) >> 8) & 0xff, \ + (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) + +#define UUID_BE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ +((uuid_be) \ +{{ ((a) >> 24) & 0xff, ((a) >> 16) & 0xff, ((a) >> 8) & 0xff, (a) & 0xff, \ + ((b) >> 8) & 0xff, (b) & 0xff, \ + ((c) >> 8) & 0xff, (c) & 0xff, \ + (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) + +#define NULL_UUID_LE \ + UUID_LE(0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00) + +#define NULL_UUID_BE \ + UUID_BE(0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00) + +static inline int uuid_le_cmp(const uuid_le u1, const uuid_le u2) +{ + return memcmp(&u1, &u2, sizeof(uuid_le)); +} + +static inline int uuid_be_cmp(const uuid_be u1, const uuid_be u2) +{ + return memcmp(&u1, &u2, sizeof(uuid_be)); +} + +extern void uuid_le_gen(uuid_le *u); +extern void uuid_be_gen(uuid_be *u); + +#endif -- cgit v1.2.3 From 06d65deade9aabba58e0518df86dcd324e86b832 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Tue, 18 May 2010 14:35:19 +0800 Subject: ACPI, APEI, UEFI Common Platform Error Record (CPER) header CPER stands for Common Platform Error Record, it is the hardware error record format used to describe platform hardware error by various APEI tables, such as ERST, BERT and HEST etc. For more information about CPER, please refer to Appendix N of UEFI Specification version 2.3. This patch mainly includes the data structure difinition header file used by other files. Signed-off-by: Huang Ying Signed-off-by: Andi Kleen Signed-off-by: Len Brown --- include/linux/cper.h | 314 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 314 insertions(+) create mode 100644 include/linux/cper.h (limited to 'include/linux') diff --git a/include/linux/cper.h b/include/linux/cper.h new file mode 100644 index 000000000000..4b38f905b705 --- /dev/null +++ b/include/linux/cper.h @@ -0,0 +1,314 @@ +/* + * UEFI Common Platform Error Record + * + * Copyright (C) 2010, Intel Corp. + * Author: Huang Ying + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef LINUX_CPER_H +#define LINUX_CPER_H + +#include + +/* CPER record signature and the size */ +#define CPER_SIG_RECORD "CPER" +#define CPER_SIG_SIZE 4 +/* Used in signature_end field in struct cper_record_header */ +#define CPER_SIG_END 0xffffffff + +/* + * CPER record header revision, used in revision field in struct + * cper_record_header + */ +#define CPER_RECORD_REV 0x0100 + +/* + * Severity difinition for error_severity in struct cper_record_header + * and section_severity in struct cper_section_descriptor + */ +#define CPER_SER_RECOVERABLE 0x0 +#define CPER_SER_FATAL 0x1 +#define CPER_SER_CORRECTED 0x2 +#define CPER_SER_INFORMATIONAL 0x3 + +/* + * Validation bits difinition for validation_bits in struct + * cper_record_header. If set, corresponding fields in struct + * cper_record_header contain valid information. + * + * corresponds platform_id + */ +#define CPER_VALID_PLATFORM_ID 0x0001 +/* corresponds timestamp */ +#define CPER_VALID_TIMESTAMP 0x0002 +/* corresponds partition_id */ +#define CPER_VALID_PARTITION_ID 0x0004 + +/* + * Notification type used to generate error record, used in + * notification_type in struct cper_record_header + * + * Corrected Machine Check + */ +#define CPER_NOTIFY_CMC \ + UUID_LE(0x2DCE8BB1, 0xBDD7, 0x450e, 0xB9, 0xAD, 0x9C, 0xF4, \ + 0xEB, 0xD4, 0xF8, 0x90) +/* Corrected Platform Error */ +#define CPER_NOTIFY_CPE \ + UUID_LE(0x4E292F96, 0xD843, 0x4a55, 0xA8, 0xC2, 0xD4, 0x81, \ + 0xF2, 0x7E, 0xBE, 0xEE) +/* Machine Check Exception */ +#define CPER_NOTIFY_MCE \ + UUID_LE(0xE8F56FFE, 0x919C, 0x4cc5, 0xBA, 0x88, 0x65, 0xAB, \ + 0xE1, 0x49, 0x13, 0xBB) +/* PCI Express Error */ +#define CPER_NOTIFY_PCIE \ + UUID_LE(0xCF93C01F, 0x1A16, 0x4dfc, 0xB8, 0xBC, 0x9C, 0x4D, \ + 0xAF, 0x67, 0xC1, 0x04) +/* INIT Record (for IPF) */ +#define CPER_NOTIFY_INIT \ + UUID_LE(0xCC5263E8, 0x9308, 0x454a, 0x89, 0xD0, 0x34, 0x0B, \ + 0xD3, 0x9B, 0xC9, 0x8E) +/* Non-Maskable Interrupt */ +#define CPER_NOTIFY_NMI \ + UUID_LE(0x5BAD89FF, 0xB7E6, 0x42c9, 0x81, 0x4A, 0xCF, 0x24, \ + 0x85, 0xD6, 0xE9, 0x8A) +/* BOOT Error Record */ +#define CPER_NOTIFY_BOOT \ + UUID_LE(0x3D61A466, 0xAB40, 0x409a, 0xA6, 0x98, 0xF3, 0x62, \ + 0xD4, 0x64, 0xB3, 0x8F) +/* DMA Remapping Error */ +#define CPER_NOTIFY_DMAR \ + UUID_LE(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E, \ + 0x72, 0x2D, 0xEB, 0x41) + +/* + * Flags bits definitions for flags in struct cper_record_header + * If set, the error has been recovered + */ +#define CPER_HW_ERROR_FLAGS_RECOVERED 0x1 +/* If set, the error is for previous boot */ +#define CPER_HW_ERROR_FLAGS_PREVERR 0x2 +/* If set, the error is injected for testing */ +#define CPER_HW_ERROR_FLAGS_SIMULATED 0x4 + +/* + * CPER section header revision, used in revision field in struct + * cper_section_descriptor + */ +#define CPER_SEC_REV 0x0100 + +/* + * Validation bits difinition for validation_bits in struct + * cper_section_descriptor. If set, corresponding fields in struct + * cper_section_descriptor contain valid information. + * + * corresponds fru_id + */ +#define CPER_SEC_VALID_FRU_ID 0x1 +/* corresponds fru_text */ +#define CPER_SEC_VALID_FRU_TEXT 0x2 + +/* + * Flags bits definitions for flags in struct cper_section_descriptor + * + * If set, the section is associated with the error condition + * directly, and should be focused on + */ +#define CPER_SEC_PRIMARY 0x0001 +/* + * If set, the error was not contained within the processor or memory + * hierarchy and the error may have propagated to persistent storage + * or network + */ +#define CPER_SEC_CONTAINMENT_WARNING 0x0002 +/* If set, the component must be re-initialized or re-enabled prior to use */ +#define CPER_SEC_RESET 0x0004 +/* If set, Linux may choose to discontinue use of the resource */ +#define CPER_SEC_ERROR_THRESHOLD_EXCEEDED 0x0008 +/* + * If set, resource could not be queried for error information due to + * conflicts with other system software or resources. Some fields of + * the section will be invalid + */ +#define CPER_SEC_RESOURCE_NOT_ACCESSIBLE 0x0010 +/* + * If set, action has been taken to ensure error containment (such as + * poisoning data), but the error has not been fully corrected and the + * data has not been consumed. Linux may choose to take further + * corrective action before the data is consumed + */ +#define CPER_SEC_LATENT_ERROR 0x0020 + +/* + * Section type definitions, used in section_type field in struct + * cper_section_descriptor + * + * Processor Generic + */ +#define CPER_SEC_PROC_GENERIC \ + UUID_LE(0x9876CCAD, 0x47B4, 0x4bdb, 0xB6, 0x5E, 0x16, 0xF1, \ + 0x93, 0xC4, 0xF3, 0xDB) +/* Processor Specific: X86/X86_64 */ +#define CPER_SEC_PROC_IA \ + UUID_LE(0xDC3EA0B0, 0xA144, 0x4797, 0xB9, 0x5B, 0x53, 0xFA, \ + 0x24, 0x2B, 0x6E, 0x1D) +/* Processor Specific: IA64 */ +#define CPER_SEC_PROC_IPF \ + UUID_LE(0xE429FAF1, 0x3CB7, 0x11D4, 0x0B, 0xCA, 0x07, 0x00, \ + 0x80, 0xC7, 0x3C, 0x88, 0x81) +/* Platform Memory */ +#define CPER_SEC_PLATFORM_MEM \ + UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \ + 0xED, 0x7C, 0x83, 0xB1) +#define CPER_SEC_PCIE \ + UUID_LE(0xD995E954, 0xBBC1, 0x430F, 0xAD, 0x91, 0xB4, 0x4D, \ + 0xCB, 0x3C, 0x6F, 0x35) +/* Firmware Error Record Reference */ +#define CPER_SEC_FW_ERR_REC_REF \ + UUID_LE(0x81212A96, 0x09ED, 0x4996, 0x94, 0x71, 0x8D, 0x72, \ + 0x9C, 0x8E, 0x69, 0xED) +/* PCI/PCI-X Bus */ +#define CPER_SEC_PCI_X_BUS \ + UUID_LE(0xC5753963, 0x3B84, 0x4095, 0xBF, 0x78, 0xED, 0xDA, \ + 0xD3, 0xF9, 0xC9, 0xDD) +/* PCI Component/Device */ +#define CPER_SEC_PCI_DEV \ + UUID_LE(0xEB5E4685, 0xCA66, 0x4769, 0xB6, 0xA2, 0x26, 0x06, \ + 0x8B, 0x00, 0x13, 0x26) +#define CPER_SEC_DMAR_GENERIC \ + UUID_LE(0x5B51FEF7, 0xC79D, 0x4434, 0x8F, 0x1B, 0xAA, 0x62, \ + 0xDE, 0x3E, 0x2C, 0x64) +/* Intel VT for Directed I/O specific DMAr */ +#define CPER_SEC_DMAR_VT \ + UUID_LE(0x71761D37, 0x32B2, 0x45cd, 0xA7, 0xD0, 0xB0, 0xFE, \ + 0xDD, 0x93, 0xE8, 0xCF) +/* IOMMU specific DMAr */ +#define CPER_SEC_DMAR_IOMMU \ + UUID_LE(0x036F84E1, 0x7F37, 0x428c, 0xA7, 0x9E, 0x57, 0x5F, \ + 0xDF, 0xAA, 0x84, 0xEC) + +/* + * All tables and structs must be byte-packed to match CPER + * specification, since the tables are provided by the system BIOS + */ +#pragma pack(1) + +struct cper_record_header { + char signature[CPER_SIG_SIZE]; /* must be CPER_SIG_RECORD */ + __u16 revision; /* must be CPER_RECORD_REV */ + __u32 signature_end; /* must be CPER_SIG_END */ + __u16 section_count; + __u32 error_severity; + __u32 validation_bits; + __u32 record_length; + __u64 timestamp; + uuid_le platform_id; + uuid_le partition_id; + uuid_le creator_id; + uuid_le notification_type; + __u64 record_id; + __u32 flags; + __u64 persistence_information; + __u8 reserved[12]; /* must be zero */ +}; + +struct cper_section_descriptor { + __u32 section_offset; /* Offset in bytes of the + * section body from the base + * of the record header */ + __u32 section_length; + __u16 revision; /* must be CPER_RECORD_REV */ + __u8 validation_bits; + __u8 reserved; /* must be zero */ + __u32 flags; + uuid_le section_type; + uuid_le fru_id; + __u32 section_severity; + __u8 fru_text[20]; +}; + +/* Generic Processor Error Section */ +struct cper_sec_proc_generic { + __u64 validation_bits; + __u8 proc_type; + __u8 proc_isa; + __u8 proc_error_type; + __u8 operation; + __u8 flags; + __u8 level; + __u16 reserved; + __u64 cpu_version; + char cpu_brand[128]; + __u64 proc_id; + __u64 target_addr; + __u64 requestor_id; + __u64 responder_id; + __u64 ip; +}; + +/* IA32/X64 Processor Error Section */ +struct cper_sec_proc_ia { + __u64 validation_bits; + __u8 lapic_id; + __u8 cpuid[48]; +}; + +/* IA32/X64 Processor Error Infomation Structure */ +struct cper_ia_err_info { + uuid_le err_type; + __u64 validation_bits; + __u64 check_info; + __u64 target_id; + __u64 requestor_id; + __u64 responder_id; + __u64 ip; +}; + +/* IA32/X64 Processor Context Information Structure */ +struct cper_ia_proc_ctx { + __u16 reg_ctx_type; + __u16 reg_arr_size; + __u32 msr_addr; + __u64 mm_reg_addr; +}; + +/* Memory Error Section */ +struct cper_sec_mem_err { + __u64 validation_bits; + __u64 error_status; + __u64 physical_addr; + __u64 physical_addr_mask; + __u16 node; + __u16 card; + __u16 module; + __u16 bank; + __u16 device; + __u16 row; + __u16 column; + __u16 bit_pos; + __u64 requestor_id; + __u64 responder_id; + __u64 target_id; + __u8 error_type; +}; + +/* Reset to default packing */ +#pragma pack() + +u64 cper_next_record_id(void); + +#endif -- cgit v1.2.3 From 15b0beaa332b3923cce2ed109e0fb141ec1425d9 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Tue, 18 May 2010 14:35:23 +0800 Subject: Add x64 support to debugfs Add debugfs_create_x64. This is needed by ACPI APEI EINJ parameters support. Signed-off-by: Huang Ying Signed-off-by: Andi Kleen Acked-by: Greg Kroah-Hartman Signed-off-by: Len Brown --- include/linux/debugfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index fc1b930f246c..e7d9b20ddc5b 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -63,6 +63,8 @@ struct dentry *debugfs_create_x16(const char *name, mode_t mode, struct dentry *parent, u16 *value); struct dentry *debugfs_create_x32(const char *name, mode_t mode, struct dentry *parent, u32 *value); +struct dentry *debugfs_create_x64(const char *name, mode_t mode, + struct dentry *parent, u64 *value); struct dentry *debugfs_create_size_t(const char *name, mode_t mode, struct dentry *parent, size_t *value); struct dentry *debugfs_create_bool(const char *name, mode_t mode, -- cgit v1.2.3 From 53197fc49549240f6c6a963b2713a4cd9517964b Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Fri, 2 Apr 2010 11:48:03 -0500 Subject: Separate the gdbstub from the debug core Split the former kernel/kgdb.c into debug_core.c which contains the kernel debugger exception logic and to the gdbstub.c which contains the logic for allowing gdb to talk to the debug core. This also created a private include file called debug_core.h which contains all the definitions to glue the debug_core to any other debugger connections. CC: Ingo Molnar Signed-off-by: Jason Wessel --- include/linux/kgdb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 19ec41a183f5..4830142ec339 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -264,6 +264,7 @@ extern unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs); extern int kgdb_register_io_module(struct kgdb_io *local_kgdb_io_ops); extern void kgdb_unregister_io_module(struct kgdb_io *local_kgdb_io_ops); +extern struct kgdb_io *dbg_io_ops; extern int kgdb_hex2long(char **ptr, unsigned long *long_val); extern int kgdb_mem2hex(char *mem, char *buf, int count); -- cgit v1.2.3 From 5d5314d6795f3c1c0f415348ff8c51f7de042b77 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 20 May 2010 21:04:20 -0500 Subject: kdb: core for kgdb back end (1 of 2) This patch contains only the kdb core. Because the change set was large, it was split. The next patch in the series includes the instrumentation into the core kernel which are mainly helper functions for kdb. This work is directly derived from kdb v4.4 found at: ftp://oss.sgi.com/projects/kdb/download/v4.4/ The kdb internals have been re-organized to make them mostly platform independent and to connect everything to the debug core which is used by gdbstub (which has long been known as kgdb). The original version of kdb was 58,000 lines worth of changes to support x86. From that implementation only the kdb shell, and basic commands for memory access, runcontrol, lsmod, and dmesg where carried forward. This is a generic implementation which aims to cover all the current architectures using the kgdb core: ppc, arm, x86, mips, sparc, sh and blackfin. More archictectures can be added by implementing the architecture specific kgdb functions. [mort@sgi.com: Compile fix with hugepages enabled] [mort@sgi.com: Clean breakpoint code renaming kdba_ -> kdb_] [mort@sgi.com: fix new line after printing registers] [mort@sgi.com: Remove the concept of global vs. local breakpoints] [mort@sgi.com: Rework kdb_si_swapinfo to use more generic name] [mort@sgi.com: fix the information dump macros, remove 'arch' from the names] [sfr@canb.auug.org.au: include fixup to include linux/slab.h] CC: linux-arch@vger.kernel.org Signed-off-by: Jason Wessel Signed-off-by: Martin Hicks --- include/linux/kdb.h | 113 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 113 insertions(+) create mode 100644 include/linux/kdb.h (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h new file mode 100644 index 000000000000..4d93790faec3 --- /dev/null +++ b/include/linux/kdb.h @@ -0,0 +1,113 @@ +#ifndef _KDB_H +#define _KDB_H + +/* + * Kernel Debugger Architecture Independent Global Headers + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (c) 2000-2007 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (C) 2000 Stephane Eranian + * Copyright (C) 2009 Jason Wessel + */ + +#ifdef CONFIG_KGDB_KDB +#include +#include +#include + +#define KDB_POLL_FUNC_MAX 5 + +/* + * kdb_initial_cpu is initialized to -1, and is set to the cpu + * number whenever the kernel debugger is entered. + */ +extern int kdb_initial_cpu; +extern atomic_t kdb_event; + +/* + * kdb_diemsg + * + * Contains a pointer to the last string supplied to the + * kernel 'die' panic function. + */ +extern const char *kdb_diemsg; + +#define KDB_FLAG_EARLYKDB (1 << 0) /* set from boot parameter kdb=early */ +#define KDB_FLAG_CATASTROPHIC (1 << 1) /* A catastrophic event has occurred */ +#define KDB_FLAG_CMD_INTERRUPT (1 << 2) /* Previous command was interrupted */ +#define KDB_FLAG_NOIPI (1 << 3) /* Do not send IPIs */ +#define KDB_FLAG_ONLY_DO_DUMP (1 << 4) /* Only do a dump, used when + * kdb is off */ +#define KDB_FLAG_NO_CONSOLE (1 << 5) /* No console is available, + * kdb is disabled */ +#define KDB_FLAG_NO_VT_CONSOLE (1 << 6) /* No VT console is available, do + * not use keyboard */ +#define KDB_FLAG_NO_I8042 (1 << 7) /* No i8042 chip is available, do + * not use keyboard */ + +extern int kdb_flags; /* Global flags, see kdb_state for per cpu state */ + +extern void kdb_save_flags(void); +extern void kdb_restore_flags(void); + +#define KDB_FLAG(flag) (kdb_flags & KDB_FLAG_##flag) +#define KDB_FLAG_SET(flag) ((void)(kdb_flags |= KDB_FLAG_##flag)) +#define KDB_FLAG_CLEAR(flag) ((void)(kdb_flags &= ~KDB_FLAG_##flag)) + +/* + * External entry point for the kernel debugger. The pt_regs + * at the time of entry are supplied along with the reason for + * entry to the kernel debugger. + */ + +typedef enum { + KDB_REASON_ENTER = 1, /* KDB_ENTER() trap/fault - regs valid */ + KDB_REASON_ENTER_SLAVE, /* KDB_ENTER_SLAVE() trap/fault - regs valid */ + KDB_REASON_BREAK, /* Breakpoint inst. - regs valid */ + KDB_REASON_DEBUG, /* Debug Fault - regs valid */ + KDB_REASON_OOPS, /* Kernel Oops - regs valid */ + KDB_REASON_SWITCH, /* CPU switch - regs valid*/ + KDB_REASON_KEYBOARD, /* Keyboard entry - regs valid */ + KDB_REASON_NMI, /* Non-maskable interrupt; regs valid */ + KDB_REASON_RECURSE, /* Recursive entry to kdb; + * regs probably valid */ + KDB_REASON_SSTEP, /* Single Step trap. - regs valid */ +} kdb_reason_t; + +extern int kdb_printf(const char *, ...) + __attribute__ ((format (printf, 1, 2))); +typedef int (*kdb_printf_t)(const char *, ...) + __attribute__ ((format (printf, 1, 2))); + +extern void kdb_init(int level); + +/* Access to kdb specific polling devices */ +typedef int (*get_char_func)(void); +extern get_char_func kdb_poll_funcs[]; +extern int kdb_get_kbd_char(void); + +static inline +int kdb_process_cpu(const struct task_struct *p) +{ + unsigned int cpu = task_thread_info(p)->cpu; + if (cpu > num_possible_cpus()) + cpu = 0; + return cpu; +} + +/* kdb access to register set for stack dumping */ +extern struct pt_regs *kdb_current_regs; + +#else /* ! CONFIG_KGDB_KDB */ +#define kdb_printf(...) +#define kdb_init(x) +#endif /* CONFIG_KGDB_KDB */ +enum { + KDB_NOT_INITIALIZED, + KDB_INIT_EARLY, + KDB_INIT_FULL, +}; +#endif /* !_KDB_H */ -- cgit v1.2.3 From dcc7871128e99458ca86186b7bc8bf27ff0c47b5 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 20 May 2010 21:04:21 -0500 Subject: kgdb: core changes to support kdb These are the minimum changes to the kgdb core in order to enable an API to connect a new front end (kdb) to the debug core. This patch introduces the dbg_kdb_mode variable controls where the user level I/O is routed. It will be routed to the gdbstub (kgdb) or to the kdb front end which is a simple shell available over the kgdboc connection. You can switch back and forth between kdb or the gdb stub mode of operation dynamically. From gdb stub mode you can blindly type "$3#33", or from the kdb mode you can enter "kgdb" to switch to the gdb stub. The logic in the debug core depends on kdb to look for the typical gdb connection sequences and return immediately with KGDB_PASS_EVENT if a gdb serial command sequence is detected. That should allow a reasonably seamless transition between kdb -> gdb without leaving the kernel exception state. The two gdb serial queries that kdb is responsible for detecting are the "?" and "qSupported" packets. CC: Ingo Molnar Signed-off-by: Jason Wessel Acked-by: Martin Hicks --- include/linux/kgdb.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 4830142ec339..5b37df00000d 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -16,10 +16,12 @@ #include #include #include - #include +#ifdef CONFIG_HAVE_ARCH_KGDB #include +#endif +#ifdef CONFIG_KGDB struct pt_regs; /** @@ -262,6 +264,7 @@ extern struct kgdb_arch arch_kgdb_ops; extern unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs); +extern void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc); extern int kgdb_register_io_module(struct kgdb_io *local_kgdb_io_ops); extern void kgdb_unregister_io_module(struct kgdb_io *local_kgdb_io_ops); extern struct kgdb_io *dbg_io_ops; @@ -279,5 +282,9 @@ extern int kgdb_nmicallback(int cpu, void *regs); extern int kgdb_single_step; extern atomic_t kgdb_active; - +#define in_dbg_master() \ + (raw_smp_processor_id() == atomic_read(&kgdb_active)) +#else /* ! CONFIG_KGDB */ +#define in_dbg_master() (0) +#endif /* ! CONFIG_KGDB */ #endif /* _KGDB_H_ */ -- cgit v1.2.3 From f5316b4aea024da9266d740322a5481657f6ce59 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 20 May 2010 21:04:22 -0500 Subject: kgdb,8250,pl011: Return immediately from console poll The design of the kdb shell requires that every device that can provide input to kdb have a polling routine that exits immediately if there is no character available. This is required in order to get the page scrolling mechanism working. Changing the kernel debugger I/O API to require all polling character routines to exit immediately if there is no data allows the kernel debugger to process multiple input channels. NO_POLL_CHAR will be the return code to the polling routine when ever there is no character available. CC: linux-serial@vger.kernel.org Signed-off-by: Jason Wessel --- include/linux/kdb.h | 1 + include/linux/serial_core.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 4d93790faec3..d72fa3908128 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -19,6 +19,7 @@ #include #define KDB_POLL_FUNC_MAX 5 +extern int kdb_poll_idx; /* * kdb_initial_cpu is initialized to -1, and is set to the cpu diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 78dd1e7120a9..ad839963fa68 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -246,6 +246,7 @@ struct uart_ops { #endif }; +#define NO_POLL_CHAR 0x00ff0000 #define UART_CONFIG_TYPE (1 << 0) #define UART_CONFIG_IRQ (1 << 1) -- cgit v1.2.3 From 84c08fd61e2d21702337e9fe366e97cdf09bf797 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 20 May 2010 21:04:24 -0500 Subject: kgdb,docs: Update the kgdb docs to include kdb Update the kgdb docs to reflect the new directory structure and API. Merge in the kdb shell information. [Randy Dunlap : grammatical corrections] CC: Randy Dunlap Signed-off-by: Jason Wessel --- include/linux/kgdb.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 5b37df00000d..407edb1e0c4d 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -204,6 +204,17 @@ kgdb_arch_handle_exception(int vector, int signo, int err_code, */ extern void kgdb_roundup_cpus(unsigned long flags); +/** + * kgdb_arch_set_pc - Generic call back to the program counter + * @regs: Current &struct pt_regs. + * @pc: The new value for the program counter + * + * This function handles updating the program counter and requires an + * architecture specific implementation. + */ +extern void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc); + + /* Optional functions. */ extern int kgdb_validate_break_address(unsigned long addr); extern int kgdb_arch_set_breakpoint(unsigned long addr, char *saved_instr); @@ -264,7 +275,6 @@ extern struct kgdb_arch arch_kgdb_ops; extern unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs); -extern void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc); extern int kgdb_register_io_module(struct kgdb_io *local_kgdb_io_ops); extern void kgdb_unregister_io_module(struct kgdb_io *local_kgdb_io_ops); extern struct kgdb_io *dbg_io_ops; -- cgit v1.2.3 From 98ec1878cacb393975cba64f7392eece81716cb4 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Mon, 27 Apr 2009 10:58:06 -0500 Subject: kgdb: remove post_primary_code references Remove all the references to the kgdb_post_primary_code. This function serves no useful purpose because you can obtain the same information from the "struct kgdb_state *ks" from with in the debugger, if for some reason you want the data. Also remove the unintentional duplicate assignment for ks->ex_vector. Signed-off-by: Jason Wessel --- include/linux/kgdb.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 407edb1e0c4d..406f6f9286f3 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -35,20 +35,6 @@ struct pt_regs; */ extern int kgdb_skipexception(int exception, struct pt_regs *regs); -/** - * kgdb_post_primary_code - (optional) Save error vector/code numbers. - * @regs: Original pt_regs. - * @e_vector: Original error vector. - * @err_code: Original error code. - * - * This is usually needed on architectures which support SMP and - * KGDB. This function is called after all the secondary cpus have - * been put to a know spin state and the primary CPU has control over - * KGDB. - */ -extern void kgdb_post_primary_code(struct pt_regs *regs, int e_vector, - int err_code); - /** * kgdb_disable_hw_debug - (optional) Disable hardware debugging hook * @regs: Current &struct pt_regs. -- cgit v1.2.3 From f503b5ae53cb557ac351a668fcac1baab1cef0db Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 20 May 2010 21:04:25 -0500 Subject: x86,kgdb: Add low level debug hook The only way the debugger can handle a trap in inside rcu_lock, notify_die, or atomic_notifier_call_chain without a triple fault is to have a low level "first opportunity handler" in the int3 exception handler. Generally this will be something the vast majority of folks will not need, but for those who need it, it is added as a kernel .config option called KGDB_LOW_LEVEL_TRAP. CC: Ingo Molnar CC: Thomas Gleixner CC: H. Peter Anvin CC: x86@kernel.org Signed-off-by: Jason Wessel --- include/linux/kgdb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 406f6f9286f3..19d1b29a2694 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -60,6 +60,7 @@ struct uart_port; void kgdb_breakpoint(void); extern int kgdb_connected; +extern int kgdb_io_module_registered; extern atomic_t kgdb_setting_breakpoint; extern atomic_t kgdb_cpu_doing_single_step; -- cgit v1.2.3 From 1cee5e35f15d0893be1ba944f1aec8676e43ab76 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Wed, 3 Jun 2009 14:06:57 -0500 Subject: kgdb: Add the ability to schedule a breakpoint via a tasklet Some kgdb I/O modules require the ability to create a breakpoint tasklet, such as kgdboc and external modules such as kgdboe. The breakpoint tasklet is used as an asynchronous entry point into the debugger which will have a different function scope than the current execution path where it might not be safe to have an inline breakpoint. This is true of some of the kgdb I/O drivers which share code with kgdb and rest of the kernel users. Signed-off-by: Jason Wessel --- include/linux/kgdb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 19d1b29a2694..ee007ea341b8 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -271,6 +271,7 @@ extern int kgdb_mem2hex(char *mem, char *buf, int count); extern int kgdb_hex2mem(char *buf, char *mem, int count); extern int kgdb_isremovedbreak(unsigned long addr); +extern void kgdb_schedule_breakpoint(void); extern int kgdb_handle_exception(int ex_vector, int signo, int err_code, -- cgit v1.2.3 From efe2f29e324fd20e0449bcd6dc6dbe4734c2ba94 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 20 May 2010 21:04:26 -0500 Subject: kgdboc,kdb: Allow kdb to work on a non open console port If kdb is open on a serial port that is not actually a console make sure to call the poll routines to emit and receive characters. Signed-off-by: Jason Wessel Acked-by: Martin Hicks --- include/linux/kgdb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index ee007ea341b8..6c784ab6856a 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -247,6 +247,8 @@ struct kgdb_arch { * the I/O driver. * @post_exception: Pointer to a function that will do any cleanup work * for the I/O driver. + * @is_console: 1 if the end device is a console 0 if the I/O device is + * not a console */ struct kgdb_io { const char *name; @@ -256,6 +258,7 @@ struct kgdb_io { int (*init) (void); void (*pre_exception) (void); void (*post_exception) (void); + int is_console; }; extern struct kgdb_arch arch_kgdb_ops; -- cgit v1.2.3 From d37d39ae3b4a8f9a21114921fb344fe7cadb1abd Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 20 May 2010 21:04:27 -0500 Subject: printk,kdb: capture printk() when in kdb shell Certain calls from the kdb shell will call out to printk(), and any of these calls should get vectored back to the kdb_printf() so that the kdb pager and processing can be used, as well as to properly channel I/O to the polled I/O devices. CC: Randy Dunlap Signed-off-by: Jason Wessel Acked-by: Andrew Morton --- include/linux/kdb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index d72fa3908128..ccb2b3ec0fe8 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -78,6 +78,9 @@ typedef enum { KDB_REASON_SSTEP, /* Single Step trap. - regs valid */ } kdb_reason_t; +extern int kdb_trap_printk; +extern int vkdb_printf(const char *fmt, va_list args) + __attribute__ ((format (printf, 1, 0))); extern int kdb_printf(const char *, ...) __attribute__ ((format (printf, 1, 2))); typedef int (*kdb_printf_t)(const char *, ...) -- cgit v1.2.3 From 0b4b3827db386ec6034a5aba1261025b039440c2 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 20 May 2010 21:04:29 -0500 Subject: x86, kgdb, init: Add early and late debug states The kernel debugger can operate well before mm_init(), but the x86 hardware breakpoint code which uses the perf api requires that the kernel allocators are initialized. This means the kernel debug core needs to provide an optional arch specific call back to allow the initialization functions to run after the kernel has been further initialized. The kdb shell already had a similar restriction with an early initialization and late initialization. The kdb_init() was moved into the debug core's version of the late init which is called dbg_late_init(); CC: kgdb-bugreport@lists.sourceforge.net Signed-off-by: Jason Wessel --- include/linux/kgdb.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 6c784ab6856a..9340f34d1bb5 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -207,6 +207,17 @@ extern int kgdb_validate_break_address(unsigned long addr); extern int kgdb_arch_set_breakpoint(unsigned long addr, char *saved_instr); extern int kgdb_arch_remove_breakpoint(unsigned long addr, char *bundle); +/** + * kgdb_arch_late - Perform any architecture specific initalization. + * + * This function will handle the late initalization of any + * architecture specific callbacks. This is an optional function for + * handling things like late initialization of hw breakpoints. The + * default implementation does nothing. + */ +extern void kgdb_arch_late(void); + + /** * struct kgdb_arch - Describe architecture specific values. * @gdb_bpt_instr: The instruction to trigger a breakpoint. @@ -285,7 +296,10 @@ extern int kgdb_single_step; extern atomic_t kgdb_active; #define in_dbg_master() \ (raw_smp_processor_id() == atomic_read(&kgdb_active)) +extern bool dbg_is_early; +extern void __init dbg_late_init(void); #else /* ! CONFIG_KGDB */ #define in_dbg_master() (0) +#define dbg_late_init() #endif /* ! CONFIG_KGDB */ #endif /* _KGDB_H_ */ -- cgit v1.2.3 From 81c2a3ba497835797332b517ebf2de7b7f2a7c80 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Thu, 20 May 2010 22:52:58 -0700 Subject: Input: use ABS_CNT rather than (ABS_MAX + 1) Signed-off-by: Daniel Mack Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 12 ++++++------ include/linux/joystick.h | 4 ++-- include/linux/uinput.h | 10 +++++----- 3 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 83524e4f3290..6fcc9101beeb 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -1155,7 +1155,7 @@ struct input_dev { int sync; - int abs[ABS_MAX + 1]; + int abs[ABS_CNT]; int rep[REP_MAX + 1]; unsigned long key[BITS_TO_LONGS(KEY_CNT)]; @@ -1163,11 +1163,11 @@ struct input_dev { unsigned long snd[BITS_TO_LONGS(SND_CNT)]; unsigned long sw[BITS_TO_LONGS(SW_CNT)]; - int absmax[ABS_MAX + 1]; - int absmin[ABS_MAX + 1]; - int absfuzz[ABS_MAX + 1]; - int absflat[ABS_MAX + 1]; - int absres[ABS_MAX + 1]; + int absmax[ABS_CNT]; + int absmin[ABS_CNT]; + int absfuzz[ABS_CNT]; + int absflat[ABS_CNT]; + int absres[ABS_CNT]; int (*open)(struct input_dev *dev); void (*close)(struct input_dev *dev); diff --git a/include/linux/joystick.h b/include/linux/joystick.h index 9e20c29c1e14..47199b13e0eb 100644 --- a/include/linux/joystick.h +++ b/include/linux/joystick.h @@ -64,8 +64,8 @@ struct js_event { #define JSIOCSCORR _IOW('j', 0x21, struct js_corr) /* set correction values */ #define JSIOCGCORR _IOR('j', 0x22, struct js_corr) /* get correction values */ -#define JSIOCSAXMAP _IOW('j', 0x31, __u8[ABS_MAX + 1]) /* set axis mapping */ -#define JSIOCGAXMAP _IOR('j', 0x32, __u8[ABS_MAX + 1]) /* get axis mapping */ +#define JSIOCSAXMAP _IOW('j', 0x31, __u8[ABS_CNT]) /* set axis mapping */ +#define JSIOCGAXMAP _IOR('j', 0x32, __u8[ABS_CNT]) /* get axis mapping */ #define JSIOCSBTNMAP _IOW('j', 0x33, __u16[KEY_MAX - BTN_MISC + 1]) /* set button mapping */ #define JSIOCGBTNMAP _IOR('j', 0x34, __u16[KEY_MAX - BTN_MISC + 1]) /* get button mapping */ diff --git a/include/linux/uinput.h b/include/linux/uinput.h index 15ddd4483b09..60c81da77f0f 100644 --- a/include/linux/uinput.h +++ b/include/linux/uinput.h @@ -166,11 +166,11 @@ struct uinput_ff_erase { struct uinput_user_dev { char name[UINPUT_MAX_NAME_SIZE]; struct input_id id; - int ff_effects_max; - int absmax[ABS_MAX + 1]; - int absmin[ABS_MAX + 1]; - int absfuzz[ABS_MAX + 1]; - int absflat[ABS_MAX + 1]; + int ff_effects_max; + int absmax[ABS_CNT]; + int absmin[ABS_CNT]; + int absfuzz[ABS_CNT]; + int absflat[ABS_CNT]; }; #endif /* __UINPUT_H_ */ -- cgit v1.2.3 From b7e2ecef92d2e7785e6d76b41e5ba8bcbc45259d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 May 2010 10:52:27 +0200 Subject: perf, trace: Optimize tracepoints by removing IRQ-disable from perf/tracepoint interaction Improves performance. Acked-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <1274259525.5605.10352.camel@twins> Signed-off-by: Ingo Molnar --- include/linux/ftrace_event.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index a9775dd7f7fe..126071bc90ab 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -197,20 +197,17 @@ extern void perf_trace_disable(int event_id); extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); extern void ftrace_profile_free_filter(struct perf_event *event); -extern void * -perf_trace_buf_prepare(int size, unsigned short type, int *rctxp, - unsigned long *irq_flags); +extern void *perf_trace_buf_prepare(int size, unsigned short type, + struct pt_regs *regs, int *rctxp); static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, - u64 count, unsigned long irq_flags, struct pt_regs *regs, - void *event) + u64 count, struct pt_regs *regs, void *event) { struct trace_entry *entry = raw_data; perf_tp_event(entry->type, addr, count, raw_data, size, regs, event); perf_swevent_put_recursion_context(rctx); - local_irq_restore(irq_flags); } #endif -- cgit v1.2.3 From 1c024eca51fdc965290acf342ae16a476c2189d0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 May 2010 14:02:22 +0200 Subject: perf, trace: Optimize tracepoints by using per-tracepoint-per-cpu hlist to track events Avoid the swevent hash-table by using per-tracepoint hlists. Also, avoid conditionals on the fast path by ordering with probe unregister so that we should never get on the callback path without the data being there. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <20100521090710.473188012@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/ftrace_event.h | 16 ++++++++-------- include/linux/perf_event.h | 6 ++++-- 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 126071bc90ab..7024b7d1126f 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -133,7 +133,7 @@ struct ftrace_event_call { void *data; int perf_refcount; - void *perf_data; + struct hlist_head *perf_events; int (*perf_event_enable)(struct ftrace_event_call *); void (*perf_event_disable)(struct ftrace_event_call *); }; @@ -192,9 +192,11 @@ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); -extern int perf_trace_enable(int event_id, void *data); -extern void perf_trace_disable(int event_id); -extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, +extern int perf_trace_init(struct perf_event *event); +extern void perf_trace_destroy(struct perf_event *event); +extern int perf_trace_enable(struct perf_event *event); +extern void perf_trace_disable(struct perf_event *event); +extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); extern void ftrace_profile_free_filter(struct perf_event *event); extern void *perf_trace_buf_prepare(int size, unsigned short type, @@ -202,11 +204,9 @@ extern void *perf_trace_buf_prepare(int size, unsigned short type, static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, - u64 count, struct pt_regs *regs, void *event) + u64 count, struct pt_regs *regs, void *head) { - struct trace_entry *entry = raw_data; - - perf_tp_event(entry->type, addr, count, raw_data, size, regs, event); + perf_tp_event(addr, count, raw_data, size, regs, head); perf_swevent_put_recursion_context(rctx); } #endif diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fe50347dc645..7cd7b356447d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -727,6 +727,7 @@ struct perf_event { perf_overflow_handler_t overflow_handler; #ifdef CONFIG_EVENT_TRACING + struct ftrace_event_call *tp_event; struct event_filter *filter; #endif @@ -992,8 +993,9 @@ static inline bool perf_paranoid_kernel(void) } extern void perf_event_init(void); -extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, - int entry_size, struct pt_regs *regs, void *event); +extern void perf_tp_event(u64 addr, u64 count, void *record, + int entry_size, struct pt_regs *regs, + struct hlist_head *head); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags -- cgit v1.2.3 From adb8e118f288dc4c569ac9a89010b81a4745fbf0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 May 2010 16:21:55 +0200 Subject: perf: Fix wakeup storm for RO mmap()s RO mmap()s don't update the tail pointer, so comparing against it for determining the written data size doesn't really do any good. Keep track of when we last did a wakeup, and compare against that. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <20100521090710.684479310@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 7cd7b356447d..7098ebbb3b3a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -599,7 +599,7 @@ struct perf_mmap_data { local_t head; /* write position */ local_t nest; /* nested writers */ local_t events; /* event limit */ - local_t wakeup; /* needs a wakeup */ + local_t wakeup; /* wakeup stamp */ local_t lost; /* nr records lost */ long watermark; /* wakeup watermark */ -- cgit v1.2.3 From 5d967a8be636a4f301a8daad642bd1007299d9ec Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 May 2010 16:46:39 +0200 Subject: perf: Optimize perf_output_copy() Reduce the clutter in perf_output_copy() by keeping an interator in perf_output_handle. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <20100521090710.742809176@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 7098ebbb3b3a..7bd17f0488f8 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -806,6 +806,9 @@ struct perf_output_handle { unsigned long head; unsigned long offset; unsigned long wakeup; + unsigned long size; + void *addr; + int page; int nmi; int sample; }; -- cgit v1.2.3 From 3cafa9fbb5c1d564b7b8e7224f493effbf04ffee Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 May 2010 19:07:56 +0200 Subject: perf: Optimize the !vmalloc backed buffer Reduce code and data by using the knowledge that for !PERF_USE_VMALLOC data_order is always 0. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <20100521090710.795019386@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 7bd17f0488f8..09cd9c1abfda 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -588,8 +588,8 @@ struct perf_mmap_data { struct rcu_head rcu_head; #ifdef CONFIG_PERF_USE_VMALLOC struct work_struct work; + int page_order; /* allocation order */ #endif - int data_order; /* allocation order */ int nr_pages; /* nr of data pages */ int writable; /* are we writable */ int nr_locked; /* nr pages mlocked */ -- cgit v1.2.3 From a94ffaaf55552769af328eaca9260fe6291c66c7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 May 2010 19:50:07 +0200 Subject: perf: Remove more code from the fastpath Sanity checks cost instructions. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <20100521090710.852926930@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 09cd9c1abfda..fb6c91eac7e3 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -803,8 +803,6 @@ struct perf_cpu_context { struct perf_output_handle { struct perf_event *event; struct perf_mmap_data *data; - unsigned long head; - unsigned long offset; unsigned long wakeup; unsigned long size; void *addr; -- cgit v1.2.3 From 1ff454ef9b1e852e8f4d295a68a715b1dddf233c Mon Sep 17 00:00:00 2001 From: Pavan Savoy Date: Thu, 8 Apr 2010 13:16:52 -0500 Subject: serial: TTY: new ldiscs for staging Push the max ldiscs by a few number to allow ldiscs to exist in the staging directory and elsewhere. Signed-off-by: Pavan Savoy Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index bb44fa9ae135..7e605e4b3da3 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -23,7 +23,7 @@ */ #define NR_UNIX98_PTY_DEFAULT 4096 /* Default maximum for Unix98 ptys */ #define NR_UNIX98_PTY_MAX (1 << MINORBITS) /* Absolute limit */ -#define NR_LDISCS 21 +#define NR_LDISCS 30 /* line disciplines */ #define N_TTY 0 -- cgit v1.2.3 From e1eaea46bb4020b38a141b84f88565d4603f8dd0 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Fri, 26 Mar 2010 11:32:54 +0000 Subject: tty: n_gsm line discipline Add an implementation of GSM 0710 MUX. The implementation currently supports - Basic and advanced framing (as either end of the link) - UI or UIH data frames - Adaption layer 1-4 (1 and 2 via tty, 3 and 4 as skbuff lists) - Modem and control messages including the correct retry process - Flow control and exposes the MUX channels as a set of virtual tty devices including modem signals. This is an experimental driver. Signed-off-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/gsmmux.h | 25 +++++++++++++++++++++++++ include/linux/tty.h | 1 + 2 files changed, 26 insertions(+) create mode 100644 include/linux/gsmmux.h (limited to 'include/linux') diff --git a/include/linux/gsmmux.h b/include/linux/gsmmux.h new file mode 100644 index 000000000000..378de4195caf --- /dev/null +++ b/include/linux/gsmmux.h @@ -0,0 +1,25 @@ +#ifndef _LINUX_GSMMUX_H +#define _LINUX_GSMMUX_H + +struct gsm_config +{ + unsigned int adaption; + unsigned int encapsulation; + unsigned int initiator; + unsigned int t1; + unsigned int t2; + unsigned int t3; + unsigned int n2; + unsigned int mru; + unsigned int mtu; + unsigned int k; + unsigned int i; + unsigned int unused[8]; /* Padding for expansion without + breaking stuff */ +}; + +#define GSMIOC_GETCONF _IOR('G', 0, struct gsm_config) +#define GSMIOC_SETCONF _IOW('G', 1, struct gsm_config) + + +#endif diff --git a/include/linux/tty.h b/include/linux/tty.h index 7e605e4b3da3..931078b73226 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -48,6 +48,7 @@ #define N_PPS 18 /* Pulse per Second */ #define N_V253 19 /* Codec control over voice modem */ #define N_CAIF 20 /* CAIF protocol for talking to modems */ +#define N_GSM0710 21 /* GSM 0710 Mux */ /* * This character is the same as _POSIX_VDISABLE: it cannot be used as -- cgit v1.2.3 From 5bcd601049c6b2ad52733d4cd2794bfbaf1b9314 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Wed, 5 May 2010 10:35:22 +0200 Subject: serial: Add driver for the Altera JTAG UART Add an UART driver for the JTAG UART component available as a SOPC (System on Programmable Chip) component for Altera FPGAs. Signed-off-by: Tobias Klauser Signed-off-by: Greg Kroah-Hartman --- include/linux/altera_jtaguart.h | 16 ++++++++++++++++ include/linux/serial_core.h | 3 +++ 2 files changed, 19 insertions(+) create mode 100644 include/linux/altera_jtaguart.h (limited to 'include/linux') diff --git a/include/linux/altera_jtaguart.h b/include/linux/altera_jtaguart.h new file mode 100644 index 000000000000..953b178a1650 --- /dev/null +++ b/include/linux/altera_jtaguart.h @@ -0,0 +1,16 @@ +/* + * altera_jtaguart.h -- Altera JTAG UART driver defines. + */ + +#ifndef __ALTJUART_H +#define __ALTJUART_H + +#define ALTERA_JTAGUART_MAJOR 204 +#define ALTERA_JTAGUART_MINOR 186 + +struct altera_jtaguart_platform_uart { + unsigned long mapbase; /* Physical address base */ + unsigned int irq; /* Interrupt vector */ +}; + +#endif /* __ALTJUART_H */ diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 78dd1e7120a9..ade1536e1a48 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -182,6 +182,9 @@ /* Aeroflex Gaisler GRLIB APBUART */ #define PORT_APBUART 90 +/* Altera UARTs */ +#define PORT_ALTERA_JTAGUART 91 + #ifdef __KERNEL__ #include -- cgit v1.2.3 From 6b7d8f8b5c43f7bedda750d8a9dab0658da1d2ba Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Wed, 5 May 2010 10:35:23 +0200 Subject: serial: Add driver for the Altera UART Add an UART driver for the UART component available as a SOPC (System on Programmable Chip) component for Altera FPGAs. Signed-off-by: Tobias Klauser Signed-off-by: Greg Kroah-Hartman --- include/linux/altera_uart.h | 14 ++++++++++++++ include/linux/serial_core.h | 1 + 2 files changed, 15 insertions(+) create mode 100644 include/linux/altera_uart.h (limited to 'include/linux') diff --git a/include/linux/altera_uart.h b/include/linux/altera_uart.h new file mode 100644 index 000000000000..8d441064a30d --- /dev/null +++ b/include/linux/altera_uart.h @@ -0,0 +1,14 @@ +/* + * altera_uart.h -- Altera UART driver defines. + */ + +#ifndef __ALTUART_H +#define __ALTUART_H + +struct altera_uart_platform_uart { + unsigned long mapbase; /* Physical address base */ + unsigned int irq; /* Interrupt vector */ + unsigned int uartclk; /* UART clock rate */ +}; + +#endif /* __ALTUART_H */ diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index ade1536e1a48..09d0d2d5a08b 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -184,6 +184,7 @@ /* Altera UARTs */ #define PORT_ALTERA_JTAGUART 91 +#define PORT_ALTERA_UART 92 #ifdef __KERNEL__ -- cgit v1.2.3 From dd336c554d8926c3348a2d5f2a5ef5597f6d1a06 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sun, 2 May 2010 11:21:21 +0300 Subject: firmware_class: fix memory leak - free allocated pages fix memory leak introduced by the patch 6e03a201bbe: firmware: speed up request_firmware() 1. vfree won't release pages there were allocated explicitly and mapped using vmap. The memory has to be vunmap-ed and the pages needs to be freed explicitly 2. page array is moved into the 'struct firmware' so that we can free it from release_firmware() and not only in fw_dev_release() The fix doesn't break the firmware load speed. Cc: Johannes Berg Cc: Ming Lei Cc: Catalin Marinas Singed-off-by: Kay Sievers Signed-off-by: David Woodhouse Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 043811f0d277..53d1e6c4f848 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -12,6 +12,7 @@ struct firmware { size_t size; const u8 *data; + struct page **pages; }; struct device; -- cgit v1.2.3 From db1afffab0b5d9f6d31f8f4bea44c9cb3bc59351 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 16 Mar 2010 15:14:51 +1100 Subject: kref: remove kref_set Of the three uses of kref_set in the kernel: One really should be kref_put as the code is letting go of a reference, Two really should be kref_init because the kref is being initialised. This suggests that making kref_set available encourages bad code. So fix the three uses and remove kref_set completely. Signed-off-by: NeilBrown Acked-by: Mimi Zohar Acked-by: Serge Hallyn Signed-off-by: Greg Kroah-Hartman --- include/linux/kref.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kref.h b/include/linux/kref.h index baf4b9e4b194..6cc38fc07ab7 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -21,7 +21,6 @@ struct kref { atomic_t refcount; }; -void kref_set(struct kref *kref, int num); void kref_init(struct kref *kref); void kref_get(struct kref *kref); int kref_put(struct kref *kref, void (*release) (struct kref *kref)); -- cgit v1.2.3 From da5e4ef7fdb8f2fb0878dee3bd9d4dd10cea8cf1 Mon Sep 17 00:00:00 2001 From: Peter Korsgaard Date: Tue, 16 Mar 2010 21:55:21 +0100 Subject: devtmpfs: support !CONFIG_TMPFS Make devtmpfs available on (embedded) configurations without SHMEM/TMPFS, using ramfs instead. Saves ~15KB. Signed-off-by: Peter Korsgaard Acked-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/ramfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index 4e768dda87b0..8600508c77a6 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -20,4 +20,6 @@ extern const struct file_operations ramfs_file_operations; extern const struct vm_operations_struct generic_file_vm_ops; extern int __init init_rootfs(void); +int ramfs_fill_super(struct super_block *sb, void *data, int silent); + #endif -- cgit v1.2.3 From 3142788b7967ccfd2f1813ee9e11aeb1e1cf7de2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 29 Jan 2010 20:39:02 +0000 Subject: drivers/base: Convert dev->sem to mutex The semaphore is semantically a mutex. Convert it to a real mutex and fix up a few places where code was relying on semaphore.h to be included by device.h, as well as the users of the trylock function, as that value is now reversed. Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 241b96bcd7ad..6f9619190aaf 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -22,7 +22,6 @@ #include #include #include -#include #include #include @@ -404,7 +403,7 @@ struct device { const char *init_name; /* initial name of the device */ struct device_type *type; - struct semaphore sem; /* semaphore to synchronize calls to + struct mutex mutex; /* mutex to synchronize calls to * its driver. */ @@ -514,17 +513,17 @@ static inline bool device_async_suspend_enabled(struct device *dev) static inline void device_lock(struct device *dev) { - down(&dev->sem); + mutex_lock(&dev->mutex); } static inline int device_trylock(struct device *dev) { - return down_trylock(&dev->sem); + return mutex_trylock(&dev->mutex); } static inline void device_unlock(struct device *dev) { - up(&dev->sem); + mutex_unlock(&dev->mutex); } void driver_init(void); -- cgit v1.2.3 From 1704f47b50b5d9e1b825e43e1baaf2c5897baf03 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 19 Mar 2010 01:37:42 +0100 Subject: lockdep: Add novalidate class for dev->mutex conversion The conversion of device->sem to device->mutex resulted in lockdep warnings. Create a novalidate class for now until the driver folks come up with separate classes. That way we have at least the basic mutex debugging coverage. Add a checkpatch error so the usage is reserved for device->mutex. [ tglx: checkpatch and compile fix for LOCKDEP=n ] Signed-off-by: Peter Zijlstra Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- include/linux/lockdep.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index a03977a96d7e..06aed8305bf3 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -44,6 +44,8 @@ struct lock_class_key { struct lockdep_subclass_key subkeys[MAX_LOCKDEP_SUBCLASSES]; }; +extern struct lock_class_key __lockdep_no_validate__; + #define LOCKSTAT_POINTS 4 /* @@ -270,6 +272,9 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name, #define lockdep_set_subclass(lock, sub) \ lockdep_init_map(&(lock)->dep_map, #lock, \ (lock)->dep_map.key, sub) + +#define lockdep_set_novalidate_class(lock) \ + lockdep_set_class(lock, &__lockdep_no_validate__) /* * Compare locking classes */ @@ -354,6 +359,9 @@ static inline void lockdep_on(void) #define lockdep_set_class_and_subclass(lock, key, sub) \ do { (void)(key); } while (0) #define lockdep_set_subclass(lock, sub) do { } while (0) + +#define lockdep_set_novalidate_class(lock) do { } while (0) + /* * We don't define lockdep_match_class() and lockdep_match_key() for !LOCKDEP * case since the result is not well defined and the caller should rather -- cgit v1.2.3 From bc451f2058238013e1cdf4acd443c01734d332f0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 30 Mar 2010 11:31:25 -0700 Subject: kobj: Add basic infrastructure for dealing with namespaces. Move complete knowledge of namespaces into the kobject layer so we can use that information when reporting kobjects to userspace. Signed-off-by: Eric W. Biederman Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 3 +++ include/linux/kobject.h | 26 ++++++++++++++++++++++++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 6f9619190aaf..7bb9f426f3e6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -202,6 +202,9 @@ struct class { int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); + const struct kobj_ns_type_operations *ns_type; + const void *(*namespace)(struct device *dev); + const struct dev_pm_ops *pm; struct class_private *p; diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 3950d3c2850d..d9456f69904f 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -108,6 +108,8 @@ struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; struct attribute **default_attrs; + const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); + const void *(*namespace)(struct kobject *kobj); }; struct kobj_uevent_env { @@ -134,6 +136,30 @@ struct kobj_attribute { extern const struct sysfs_ops kobj_sysfs_ops; +enum kobj_ns_type { + KOBJ_NS_TYPE_NONE = 0, + KOBJ_NS_TYPES +}; + +struct sock; +struct kobj_ns_type_operations { + enum kobj_ns_type type; + const void *(*current_ns)(void); + const void *(*netlink_ns)(struct sock *sk); + const void *(*initial_ns)(void); +}; + +int kobj_ns_type_register(const struct kobj_ns_type_operations *ops); +int kobj_ns_type_registered(enum kobj_ns_type type); +const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent); +const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj); + +const void *kobj_ns_current(enum kobj_ns_type type); +const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk); +const void *kobj_ns_initial(enum kobj_ns_type type); +void kobj_ns_exit(enum kobj_ns_type type, const void *ns); + + /** * struct kset - a set of kobjects of a specific type, belonging to a specific subsystem. * -- cgit v1.2.3 From 3ff195b011d7decf501a4d55aeed312731094796 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 30 Mar 2010 11:31:26 -0700 Subject: sysfs: Implement sysfs tagged directory support. The problem. When implementing a network namespace I need to be able to have multiple network devices with the same name. Currently this is a problem for /sys/class/net/*, /sys/devices/virtual/net/*, and potentially a few other directories of the form /sys/ ... /net/*. What this patch does is to add an additional tag field to the sysfs dirent structure. For directories that should show different contents depending on the context such as /sys/class/net/, and /sys/devices/virtual/net/ this tag field is used to specify the context in which those directories should be visible. Effectively this is the same as creating multiple distinct directories with the same name but internally to sysfs the result is nicer. I am calling the concept of a single directory that looks like multiple directories all at the same path in the filesystem tagged directories. For the networking namespace the set of directories whose contents I need to filter with tags can depend on the presence or absence of hotplug hardware or which modules are currently loaded. Which means I need a simple race free way to setup those directories as tagged. To achieve a reace free design all tagged directories are created and managed by sysfs itself. Users of this interface: - define a type in the sysfs_tag_type enumeration. - call sysfs_register_ns_types with the type and it's operations - sysfs_exit_ns when an individual tag is no longer valid - Implement mount_ns() which returns the ns of the calling process so we can attach it to a sysfs superblock. - Implement ktype.namespace() which returns the ns of a syfs kobject. Everything else is left up to sysfs and the driver layer. For the network namespace mount_ns and namespace() are essentially one line functions, and look to remain that. Tags are currently represented a const void * pointers as that is both generic, prevides enough information for equality comparisons, and is trivial to create for current users, as it is just the existing namespace pointer. The work needed in sysfs is more extensive. At each directory or symlink creating I need to check if the directory it is being created in is a tagged directory and if so generate the appropriate tag to place on the sysfs_dirent. Likewise at each symlink or directory removal I need to check if the sysfs directory it is being removed from is a tagged directory and if so figure out which tag goes along with the name I am deleting. Currently only directories which hold kobjects, and symlinks are supported. There is not enough information in the current file attribute interfaces to give us anything to discriminate on which makes it useless, and there are no potential users which makes it an uninteresting problem to solve. Signed-off-by: Eric W. Biederman Signed-off-by: Benjamin Thery Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index f0496b3d1811..1885d21b0c80 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -20,6 +20,7 @@ struct kobject; struct module; +enum kobj_ns_type; /* FIXME * The *owner field is no longer used. @@ -168,10 +169,14 @@ void sysfs_remove_file_from_group(struct kobject *kobj, void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr); void sysfs_notify_dirent(struct sysfs_dirent *sd); struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd, + const void *ns, const unsigned char *name); struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd); void sysfs_put(struct sysfs_dirent *sd); void sysfs_printk_last_file(void); + +void sysfs_exit_ns(enum kobj_ns_type type, const void *tag); + int __must_check sysfs_init(void); #else /* CONFIG_SYSFS */ @@ -301,6 +306,7 @@ static inline void sysfs_notify_dirent(struct sysfs_dirent *sd) } static inline struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd, + const void *ns, const unsigned char *name) { return NULL; @@ -313,6 +319,10 @@ static inline void sysfs_put(struct sysfs_dirent *sd) { } +static inline void sysfs_exit_ns(enum kobj_ns_type type, const void *tag) +{ +} + static inline int __must_check sysfs_init(void) { return 0; -- cgit v1.2.3 From 746edb7ae8a1abdd39be2b28c03aa073183340db Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 30 Mar 2010 11:31:28 -0700 Subject: sysfs: Implement sysfs_delete_link When removing a symlink sysfs_remove_link does not provide enough information to figure out which tagged directory the symlink falls in. So I need sysfs_delete_link which is passed the target of the symlink to delete. sysfs_rename_link is updated to call sysfs_delete_link instead of sysfs_remove_link as we have all of the information necessary and the callers are interesting. Both of these functions now have enough information to find a symlink in a tagged directory. The only restriction is that they must be called before the target kobject is renamed or deleted. If they are called later I loose track of which tag the target kobject was marked with and can no longer find the old symlink to remove it. This patch was split from an earlier patch. Signed-off-by: Eric W. Biederman Signed-off-by: Benjamin Thery Signed-off-by: Daniel Lezcano Acked-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 1885d21b0c80..976c4664b216 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -155,6 +155,9 @@ void sysfs_remove_link(struct kobject *kobj, const char *name); int sysfs_rename_link(struct kobject *kobj, struct kobject *target, const char *old_name, const char *new_name); +void sysfs_delete_link(struct kobject *dir, struct kobject *targ, + const char *name); + int __must_check sysfs_create_group(struct kobject *kobj, const struct attribute_group *grp); int sysfs_update_group(struct kobject *kobj, @@ -269,6 +272,11 @@ static inline int sysfs_rename_link(struct kobject *k, struct kobject *t, return 0; } +static inline void sysfs_delete_link(struct kobject *k, struct kobject *t, + const char *name) +{ +} + static inline int sysfs_create_group(struct kobject *kobj, const struct attribute_group *grp) { -- cgit v1.2.3 From be867b194a3ae3c680c29521287ae49b4d44d420 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 3 May 2010 16:23:15 -0500 Subject: sysfs: Comment sysfs directory tagging logic Add some in-line comments to explain the new infrastructure, which was introduced to support sysfs directory tagging with namespaces. I think an overall description someplace might be good too, but it didn't really seem to fit into Documentation/filesystems/sysfs.txt, which appears more geared toward users, rather than maintainers, of sysfs. (Tejun, please let me know if I can make anything clearer or failed altogether to comment something that should be commented.) Signed-off-by: Serge E. Hallyn Cc: Eric W. Biederman Cc: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 11 +++++++++++ include/linux/sysfs.h | 1 + 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index d9456f69904f..b60d2dfe4e69 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -136,12 +136,23 @@ struct kobj_attribute { extern const struct sysfs_ops kobj_sysfs_ops; +/* + * Namespace types which are used to tag kobjects and sysfs entries. + * Network namespace will likely be the first. + */ enum kobj_ns_type { KOBJ_NS_TYPE_NONE = 0, KOBJ_NS_TYPES }; struct sock; + +/* + * Callbacks so sysfs can determine namespaces + * @current_ns: return calling task's namespace + * @netlink_ns: return namespace to which a sock belongs (right?) + * @initial_ns: return the initial namespace (i.e. init_net_ns) + */ struct kobj_ns_type_operations { enum kobj_ns_type type; const void *(*current_ns)(void); diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 976c4664b216..47f1c95b5298 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -178,6 +178,7 @@ struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd); void sysfs_put(struct sysfs_dirent *sd); void sysfs_printk_last_file(void); +/* Called to clear a ns tag when it is no longer valid */ void sysfs_exit_ns(enum kobj_ns_type type, const void *tag); int __must_check sysfs_init(void); -- cgit v1.2.3 From 27eabc7cb4b357c68e4ce77d0b014f7a23add752 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 5 May 2010 14:54:00 -0700 Subject: sysfs: Don't use enums in inline function declaration. It appears gcc can't cope with using an enum that is only declared in an inline function declaration, that doesn't even use the variable that is so declared. Avoid the silliness and replace the enum with an int, and make gcc happy. Signed-off-by: Eric W. Biederman Acked-by: Randy Dunlap Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 47f1c95b5298..6903e9204032 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -328,7 +328,7 @@ static inline void sysfs_put(struct sysfs_dirent *sd) { } -static inline void sysfs_exit_ns(enum kobj_ns_type type, const void *tag) +static inline void sysfs_exit_ns(int type, const void *tag) { } -- cgit v1.2.3 From 2c3c8bea608866d8bd9dcf92657d57fdcac011c5 Mon Sep 17 00:00:00 2001 From: Chris Wright Date: Wed, 12 May 2010 18:28:57 -0700 Subject: sysfs: add struct file* to bin_attr callbacks This allows bin_attr->read,write,mmap callbacks to check file specific data (such as inode owner) as part of any privilege validation. Signed-off-by: Chris Wright Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 6903e9204032..f2694eb4dd3d 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -87,17 +87,18 @@ struct attribute_group { #define attr_name(_attr) (_attr).attr.name +struct file; struct vm_area_struct; struct bin_attribute { struct attribute attr; size_t size; void *private; - ssize_t (*read)(struct kobject *, struct bin_attribute *, + ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); - ssize_t (*write)(struct kobject *, struct bin_attribute *, + ssize_t (*write)(struct file *,struct kobject *, struct bin_attribute *, char *, loff_t, size_t); - int (*mmap)(struct kobject *, struct bin_attribute *attr, + int (*mmap)(struct file *, struct kobject *, struct bin_attribute *attr, struct vm_area_struct *vma); }; -- cgit v1.2.3 From 608b4b9548dedf4185ca47edcaae4bff2ceb62de Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 4 May 2010 17:36:45 -0700 Subject: netns: Teach network device kobjects which namespace they are in. The problem. Network devices show up in sysfs and with the network namespace active multiple devices with the same name can show up in the same directory, ouch! To avoid that problem and allow existing applications in network namespaces to see the same interface that is currently presented in sysfs, this patch enables the tagging directory support in sysfs. By using the network namespace pointers as tags to separate out the the sysfs directory entries we ensure that we don't have conflicts in the directories and applications only see a limited set of the network devices. Signed-off-by: Eric W. Biederman Acked-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index b60d2dfe4e69..cf343a852534 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -142,6 +142,7 @@ extern const struct sysfs_ops kobj_sysfs_ops; */ enum kobj_ns_type { KOBJ_NS_TYPE_NONE = 0, + KOBJ_NS_TYPE_NET, KOBJ_NS_TYPES }; -- cgit v1.2.3 From 910a7e905f36e51a17d6e8bb4ad6dcd5ac5f1d53 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 4 May 2010 17:36:46 -0700 Subject: netlink: Implment netlink_broadcast_filtered When netlink sockets are used to convey data that is in a namespace we need a way to select a subset of the listening sockets to deliver the packet to. For the network namespace we have been doing this by only transmitting packets in the correct network namespace. For data belonging to other namespaces netlink_bradcast_filtered provides a mechanism that allows us to examine the destination socket and to decide if we should transmit the specified packet to it. Signed-off-by: Eric W. Biederman Acked-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/netlink.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 6eaca5e1e8ca..59d066936ab9 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -188,6 +188,10 @@ extern int netlink_has_listeners(struct sock *sk, unsigned int group); extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid, __u32 group, gfp_t allocation); +extern int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, + __u32 pid, __u32 group, gfp_t allocation, + int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data), + void *filter_data); extern int netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code); extern int netlink_register_notifier(struct notifier_block *nb); extern int netlink_unregister_notifier(struct notifier_block *nb); -- cgit v1.2.3 From c15271f4e74cd6dbdf461335d6d1450949c4b956 Mon Sep 17 00:00:00 2001 From: Jan Blunck Date: Wed, 14 Apr 2010 14:38:38 +0200 Subject: ext2: Add ext2_sb_info s_lock spinlock Add a spinlock that protects against concurrent modifications of s_mount_state, s_blocks_last, s_overhead_last and the content of the superblock's buffer pointed to by sbi->s_es. The spinlock is now used in ext2_xattr_update_super_block() which was setting the EXT2_FEATURE_COMPAT_EXT_ATTR flag on the superblock without protection before. Likewise the spinlock is used in ext2_show_options() to have a consistent view of the mount options. This is a preparation patch for removing the BKL from ext2 in the next patch. Signed-off-by: Jan Blunck Cc: Andi Kleen Cc: Jan Kara Cc: OGAWA Hirofumi Signed-off-by: Jan Kara --- include/linux/ext2_fs_sb.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ext2_fs_sb.h b/include/linux/ext2_fs_sb.h index 1cdb66367c98..db4d9f586bb6 100644 --- a/include/linux/ext2_fs_sb.h +++ b/include/linux/ext2_fs_sb.h @@ -106,6 +106,15 @@ struct ext2_sb_info { spinlock_t s_rsv_window_lock; struct rb_root s_rsv_window_root; struct ext2_reserve_window_node s_rsv_window_head; + /* + * s_lock protects against concurrent modifications of s_mount_state, + * s_blocks_last, s_overhead_last and the content of superblock's + * buffer pointed to by sbi->s_es. + * + * Note: It is used in ext2_show_options() to provide a consistent view + * of the mount options. + */ + spinlock_t s_lock; }; static inline spinlock_t * -- cgit v1.2.3 From 03f4d804a1b4748885dc4613a4afe10089a731c8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 15 Apr 2010 22:16:24 +0200 Subject: jbd: Provide function to check whether transaction will issue data barrier Provide a function which returns whether a transaction with given tid will send a barrier to the filesystem device. The function will be used by ext3 to detect whether fsync needs to send a separate barrier or not. Signed-off-by: Jan Kara --- include/linux/jbd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 516a2a27e87a..e06965081ba5 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -427,9 +427,9 @@ struct transaction_s enum { T_RUNNING, T_LOCKED, - T_RUNDOWN, T_FLUSH, T_COMMIT, + T_COMMIT_RECORD, T_FINISHED } t_state; @@ -991,6 +991,7 @@ int journal_start_commit(journal_t *journal, tid_t *tid); int journal_force_commit_nested(journal_t *journal); int log_wait_commit(journal_t *journal, tid_t tid); int log_do_checkpoint(journal_t *journal); +int journal_trans_will_send_data_barrier(journal_t *journal, tid_t tid); void __log_wait_for_space(journal_t *journal); extern void __journal_drop_transaction(journal_t *, transaction_t *); -- cgit v1.2.3 From dde9588853b1bde542eab247f8838c472806688f Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Mon, 26 Apr 2010 20:03:33 +0400 Subject: quota: Make quota stat accounting lockless. Quota stats is mostly writable data structure. Let's alloc percpu bucket for each value. NOTE: dqstats_read() function is racy against dqstats_{inc,dec} and may return inconsistent value. But this is ok since absolute accuracy is not required. Signed-off-by: Dmitry Monakhov Signed-off-by: Jan Kara --- include/linux/quota.h | 42 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index b462916b2a0a..cdfde10481b7 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -174,6 +174,8 @@ enum { #include #include #include +#include +#include #include #include @@ -238,19 +240,43 @@ static inline int info_dirty(struct mem_dqinfo *info) return test_bit(DQF_INFO_DIRTY_B, &info->dqi_flags); } +enum { + DQST_LOOKUPS, + DQST_DROPS, + DQST_READS, + DQST_WRITES, + DQST_CACHE_HITS, + DQST_ALLOC_DQUOTS, + DQST_FREE_DQUOTS, + DQST_SYNCS, + _DQST_DQSTAT_LAST +}; + struct dqstats { - int lookups; - int drops; - int reads; - int writes; - int cache_hits; - int allocated_dquots; - int free_dquots; - int syncs; + int stat[_DQST_DQSTAT_LAST]; }; +extern struct dqstats *dqstats_pcpu; extern struct dqstats dqstats; +static inline void dqstats_inc(unsigned int type) +{ +#ifdef CONFIG_SMP + per_cpu_ptr(dqstats_pcpu, smp_processor_id())->stat[type]++; +#else + dqstats.stat[type]++; +#endif +} + +static inline void dqstats_dec(unsigned int type) +{ +#ifdef CONFIG_SMP + per_cpu_ptr(dqstats_pcpu, smp_processor_id())->stat[type]--; +#else + dqstats.stat[type]--; +#endif +} + #define DQ_MOD_B 0 /* dquot modified since read */ #define DQ_BLKS_B 1 /* uid/gid has been warned about blk limit */ #define DQ_INODES_B 2 /* uid/gid has been warned about inode limit */ -- cgit v1.2.3 From b9b2dd36c1bc64430f8e13990ab135cbecc10076 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 May 2010 17:04:58 -0400 Subject: quota: unify ->get_dqblk Pass the larger struct fs_disk_quota to the ->get_dqblk operation so that the Q_GETQUOTA and Q_XGETQUOTA operations can be implemented with a single filesystem operation and we can retire the ->get_xquota operation. The additional information (RT-subvolume accounting and warn counts) are left zero for the VFS quota implementation. Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/quota.h | 3 +-- include/linux/quotaops.h | 3 ++- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index cdfde10481b7..42364219dc9b 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -337,11 +337,10 @@ struct quotactl_ops { int (*quota_sync)(struct super_block *, int, int); int (*get_info)(struct super_block *, int, struct if_dqinfo *); int (*set_info)(struct super_block *, int, struct if_dqinfo *); - int (*get_dqblk)(struct super_block *, int, qid_t, struct if_dqblk *); + int (*get_dqblk)(struct super_block *, int, qid_t, struct fs_disk_quota *); int (*set_dqblk)(struct super_block *, int, qid_t, struct if_dqblk *); int (*get_xstate)(struct super_block *, struct fs_quota_stat *); int (*set_xstate)(struct super_block *, unsigned int, int); - int (*get_xquota)(struct super_block *, int, qid_t, struct fs_disk_quota *); int (*set_xquota)(struct super_block *, int, qid_t, struct fs_disk_quota *); }; diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index e6fa7acce290..d32a48631b0d 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -63,7 +63,8 @@ int vfs_quota_disable(struct super_block *sb, int type, unsigned int flags); int vfs_quota_sync(struct super_block *sb, int type, int wait); int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); -int vfs_get_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *di); +int vfs_get_dqblk(struct super_block *sb, int type, qid_t id, + struct fs_disk_quota *di); int vfs_set_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *di); int dquot_transfer(struct inode *inode, struct iattr *iattr); -- cgit v1.2.3 From c472b43275976512e4c1c32da5ced03f339cb380 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 May 2010 17:05:17 -0400 Subject: quota: unify ->set_dqblk Pass the larger struct fs_disk_quota to the ->set_dqblk operation so that the Q_SETQUOTA and Q_XSETQUOTA operations can be implemented with a single filesystem operation and we can retire the ->set_xquota operation. The additional information (RT-subvolume accounting and warn counts) are left zero for the VFS quota implementation. Add new fieldmask values for setting the numer of blocks and inodes values which is required for the VFS quota, but wasn't for XFS. Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/dqblk_xfs.h | 9 +++++++++ include/linux/quota.h | 3 +-- include/linux/quotaops.h | 3 ++- 3 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dqblk_xfs.h b/include/linux/dqblk_xfs.h index 527504c11c5e..4389ae72024e 100644 --- a/include/linux/dqblk_xfs.h +++ b/include/linux/dqblk_xfs.h @@ -109,6 +109,15 @@ typedef struct fs_disk_quota { #define FS_DQ_RTBWARNS (1<<11) #define FS_DQ_WARNS_MASK (FS_DQ_BWARNS | FS_DQ_IWARNS | FS_DQ_RTBWARNS) +/* + * Accounting values. These can only be set for filesystem with + * non-transactional quotas that require quotacheck(8) in userspace. + */ +#define FS_DQ_BCOUNT (1<<12) +#define FS_DQ_ICOUNT (1<<13) +#define FS_DQ_RTBCOUNT (1<<14) +#define FS_DQ_ACCT_MASK (FS_DQ_BCOUNT | FS_DQ_ICOUNT | FS_DQ_RTBCOUNT) + /* * Various flags related to quotactl(2). Only relevant to XFS filesystems. */ diff --git a/include/linux/quota.h b/include/linux/quota.h index 42364219dc9b..7126a15467f1 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -338,10 +338,9 @@ struct quotactl_ops { int (*get_info)(struct super_block *, int, struct if_dqinfo *); int (*set_info)(struct super_block *, int, struct if_dqinfo *); int (*get_dqblk)(struct super_block *, int, qid_t, struct fs_disk_quota *); - int (*set_dqblk)(struct super_block *, int, qid_t, struct if_dqblk *); + int (*set_dqblk)(struct super_block *, int, qid_t, struct fs_disk_quota *); int (*get_xstate)(struct super_block *, struct fs_quota_stat *); int (*set_xstate)(struct super_block *, unsigned int, int); - int (*set_xquota)(struct super_block *, int, qid_t, struct fs_disk_quota *); }; struct quota_format_type { diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index d32a48631b0d..82c70c42d035 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -65,7 +65,8 @@ int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); int vfs_get_dqblk(struct super_block *sb, int type, qid_t id, struct fs_disk_quota *di); -int vfs_set_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *di); +int vfs_set_dqblk(struct super_block *sb, int type, qid_t id, + struct fs_disk_quota *di); int dquot_transfer(struct inode *inode, struct iattr *iattr); int vfs_dq_quota_on_remount(struct super_block *sb); -- cgit v1.2.3 From 12755627bdcddcdb30a1bfb9a09395a52b1d6838 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Thu, 8 Apr 2010 22:04:20 +0400 Subject: quota: unify quota init condition in setattr Quota must being initialized if size or uid/git changes requested. But initialization performed in two different places: in case of i_size file system is responsible for dquot init , but in case of uid/gid init will be called internally in dquot_transfer(). This ambiguity makes code harder to understand. Let's move this logic to one common helper function. Signed-off-by: Dmitry Monakhov Signed-off-by: Jan Kara --- include/linux/quotaops.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 82c70c42d035..8a7818764a67 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -14,6 +14,14 @@ static inline struct quota_info *sb_dqopt(struct super_block *sb) return &sb->s_dquot; } +/* i_mutex must being held */ +static inline bool is_quota_modification(struct inode *inode, struct iattr *ia) +{ + return (ia->ia_valid & ATTR_SIZE && ia->ia_size != inode->i_size) || + (ia->ia_valid & ATTR_UID && ia->ia_uid != inode->i_uid) || + (ia->ia_valid & ATTR_GID && ia->ia_gid != inode->i_gid); +} + #if defined(CONFIG_QUOTA) /* -- cgit v1.2.3 From bc8e5f07392f05c47c8bdeff4f7098db440d065c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 13 May 2010 19:58:50 +0200 Subject: quota: Refactor dquot_transfer code so that OCFS2 can pass in its references Currently, __dquot_transfer() acquires its own references of dquot structures that will be put into inode. But for OCFS2, this creates a lock inversion between dq_lock (waited on in dqget) and transaction start (started in ocfs2_setattr). Currently, deadlock is impossible because dq_lock is acquired only during dquot_acquire and dquot_release and we already hold a reference to dquot structures in ocfs2_setattr so neither of these functions can be called while we call dquot_transfer. But this is rather subtle and it is hard to teach lockdep about it. So provide __dquot_transfer function that can be passed dquot references directly. OCFS2 can then pass acquired dquot references directly to __dquot_transfer with proper locking. Signed-off-by: Jan Kara --- include/linux/quotaops.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 8a7818764a67..370abb1e99cb 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -76,6 +76,7 @@ int vfs_get_dqblk(struct super_block *sb, int type, qid_t id, int vfs_set_dqblk(struct super_block *sb, int type, qid_t id, struct fs_disk_quota *di); +int __dquot_transfer(struct inode *inode, struct dquot **transfer_to); int dquot_transfer(struct inode *inode, struct iattr *iattr); int vfs_dq_quota_on_remount(struct super_block *sb); -- cgit v1.2.3 From b4e6b09738fde057ce885703705f71cc953d0512 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 21 May 2010 09:03:01 -0700 Subject: interrupt.h: fix fatal kernel-doc error Fix kernel-doc fatal error: /** beginning a non-kernel-doc comment block: (That alone does not kill kernel-doc, but the 'enum' was totally confusing to it.) Error(/lnx/src/TMP/linux-2.6.34-git6//include/linux/interrupt.h:88): cannot understand prototype: 'enum ' make[2]: *** [Documentation/DocBook/genericirq.xml] Error 1 Signed-off-by: Randy Dunlap Signed-off-by: Linus Torvalds --- include/linux/interrupt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 5137db3317f9..c2331138ca1b 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -78,7 +78,7 @@ enum { IRQTF_AFFINITY, }; -/** +/* * These values can be returned by request_any_context_irq() and * describe the context the interrupt will be run in. * -- cgit v1.2.3 From 6423104b6a1e6f0c18be60e8c33f02d263331d5e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 21 May 2010 20:00:35 +0200 Subject: writeback: fixups for !dirty_writeback_centisecs Commit 69b62d01 fixed up most of the places where we would enter busy schedule() spins when disabling the periodic background writeback. This fixes up the sb timer so that it doesn't get hammered on with the delay disabled, and ensures that it gets rearmed if needed when /proc/sys/vm/dirty_writeback_centisecs gets modified. bdi_forker_task() also needs to check for !dirty_writeback_centisecs and use schedule() appropriately, fix that up too. Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ff8bac63213f..e6e0cb5437e6 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -109,6 +109,7 @@ void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, long nr_pages, int sb_locked); int bdi_writeback_task(struct bdi_writeback *wb); int bdi_has_dirty_io(struct backing_dev_info *bdi); +void bdi_arm_supers_timer(void); extern spinlock_t bdi_lock; extern struct list_head bdi_list; -- cgit v1.2.3 From c3e33e043f5e9c583aa59d5591a614b2a8243d3a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 15 May 2010 20:09:29 +0200 Subject: block,ide: simplify bdops->set_capacity() to ->unlock_native_capacity() bdops->set_capacity() is unnecessarily generic. All that's required is a simple one way notification to lower level driver telling it to try to unlock native capacity. There's no reason to pass in target capacity or return the new capacity. The former is always the inherent native capacity and the latter can be handled via the usual device resize / revalidation path. In fact, the current API is always used that way. Replace ->set_capacity() with ->unlock_native_capacity() which take only @disk and doesn't return anything. IDE which is the only current user of the API is converted accordingly. Signed-off-by: Tejun Heo Cc: Ben Hutchings Cc: Bartlomiej Zolnierkiewicz Acked-by: David S. Miller Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +-- include/linux/ide.h | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 346fd4856733..be411c12ebbe 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1330,8 +1330,7 @@ struct block_device_operations { int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *); int (*media_changed) (struct gendisk *); - unsigned long long (*set_capacity) (struct gendisk *, - unsigned long long); + void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); struct module *owner; diff --git a/include/linux/ide.h b/include/linux/ide.h index 3239d1c10acb..b6d448048ae2 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -362,7 +362,7 @@ struct ide_drive_s; struct ide_disk_ops { int (*check)(struct ide_drive_s *, const char *); int (*get_capacity)(struct ide_drive_s *); - u64 (*set_capacity)(struct ide_drive_s *, u64); + void (*unlock_native_capacity)(struct ide_drive_s *); void (*setup)(struct ide_drive_s *); void (*flush)(struct ide_drive_s *); int (*init_media)(struct ide_drive_s *, struct gendisk *); -- cgit v1.2.3 From c2c4986eddaa7dc3d036cb2bfa5c8c5f1f2492a0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 20 May 2010 09:18:47 +0200 Subject: writeback: fix problem with !CONFIG_BLOCK compilation When CONFIG_BLOCK isn't enabled: mm/page-writeback.c: In function 'laptop_mode_timer_fn': mm/page-writeback.c:708: error: dereferencing pointer to incomplete type mm/page-writeback.c:709: error: dereferencing pointer to incomplete type Fix this by essentially eliminating the laptop sync handlers when CONFIG_BLOCK isn't set, as most are only used from the block layer code. The exception is laptop_sync_completion() which is used from sys_sync(), make that an empty declaration in that case. Reported-by: Randy Dunlap Signed-off-by: Jens Axboe --- include/linux/writeback.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 47e1c686cb02..cc97d6caf2b3 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -106,10 +106,14 @@ static inline void inode_sync_wait(struct inode *inode) /* * mm/page-writeback.c */ +#ifdef CONFIG_BLOCK void laptop_io_completion(struct backing_dev_info *info); void laptop_sync_completion(void); void laptop_mode_sync(struct work_struct *work); void laptop_mode_timer_fn(unsigned long data); +#else +static inline void laptop_sync_completion(void) { } +#endif void throttle_vm_writeout(gfp_t gfp_mask); /* These are exported to sysctl. */ -- cgit v1.2.3 From 3d42b3612891baecf709d93f28655a6882a65d41 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Thu, 20 May 2010 12:14:54 +0200 Subject: drbd: This is now equivalent to drbd release 8.3.8rc1 Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 7944dd36ee3e..68530521ad00 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -53,10 +53,10 @@ extern const char *drbd_buildtag(void); -#define REL_VERSION "8.3.7" +#define REL_VERSION "8.3.8rc1" #define API_VERSION 88 #define PRO_VERSION_MIN 86 -#define PRO_VERSION_MAX 93 +#define PRO_VERSION_MAX 94 enum drbd_io_error_p { -- cgit v1.2.3 From 35f3d14dbbc58447c61e38a162ea10add6b31dc7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 20 May 2010 10:43:18 +0200 Subject: pipe: add support for shrinking and growing pipes This patch adds F_GETPIPE_SZ and F_SETPIPE_SZ fcntl() actions for growing and shrinking the size of a pipe and adjusts pipe.c and splice.c (and relay and network splice) usage to work with these larger (or smaller) pipes. Signed-off-by: Jens Axboe --- include/linux/fcntl.h | 6 ++++++ include/linux/pipe_fs_i.h | 11 +++++++---- include/linux/splice.h | 7 +++++++ 3 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index 86037400a6e3..afc00af3229b 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -21,6 +21,12 @@ */ #define F_NOTIFY (F_LINUX_SPECIFIC_BASE+2) +/* + * Set and get of pipe page size array + */ +#define F_SETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 7) +#define F_GETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 8) + /* * Types of directory notifications that may be requested. */ diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index b43a9e039059..65f4282fcbaf 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -3,7 +3,7 @@ #define PIPEFS_MAGIC 0x50495045 -#define PIPE_BUFFERS (16) +#define PIPE_DEF_BUFFERS 16 #define PIPE_BUF_FLAG_LRU 0x01 /* page is on the LRU */ #define PIPE_BUF_FLAG_ATOMIC 0x02 /* was atomically mapped */ @@ -44,17 +44,17 @@ struct pipe_buffer { **/ struct pipe_inode_info { wait_queue_head_t wait; - unsigned int nrbufs, curbuf; - struct page *tmp_page; + unsigned int nrbufs, curbuf, buffers; unsigned int readers; unsigned int writers; unsigned int waiting_writers; unsigned int r_counter; unsigned int w_counter; + struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; struct inode *inode; - struct pipe_buffer bufs[PIPE_BUFFERS]; + struct pipe_buffer *bufs; }; /* @@ -154,4 +154,7 @@ int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); +/* for F_SETPIPE_SZ and F_GETPIPE_SZ */ +long pipe_fcntl(struct file *, unsigned int, unsigned long arg); + #endif diff --git a/include/linux/splice.h b/include/linux/splice.h index 18e7c7c0cae6..997c3b4c212b 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -82,4 +82,11 @@ extern ssize_t splice_to_pipe(struct pipe_inode_info *, extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, splice_direct_actor *); +/* + * for dynamic pipe sizing + */ +extern int splice_grow_spd(struct pipe_inode_info *, struct splice_pipe_desc *); +extern void splice_shrink_spd(struct pipe_inode_info *, + struct splice_pipe_desc *); + #endif -- cgit v1.2.3 From b492e95be0ae672922f4734acf3f5d35c30be948 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 19 May 2010 21:03:16 +0200 Subject: pipe: set lower and upper limit on max pages in the pipe page array We need at least two to guarantee proper POSIX behaviour, so never allow a smaller limit than that. Also expose a /proc/sys/fs/pipe-max-pages sysctl file that allows root to define a sane upper limit. Make it default to 16 times the default size, which is 16 pages. Signed-off-by: Jens Axboe --- include/linux/pipe_fs_i.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 65f4282fcbaf..16de3933c45e 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -139,6 +139,8 @@ void pipe_lock(struct pipe_inode_info *); void pipe_unlock(struct pipe_inode_info *); void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); +extern unsigned int pipe_max_pages; + /* Drop the inode semaphore and wait for a pipe event, atomically */ void pipe_wait(struct pipe_inode_info *pipe); -- cgit v1.2.3 From 79d7e39ee1d4b423206f6cfd2cd2eed6253d95fe Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 21 Mar 2010 19:24:23 -0400 Subject: sb_entry() has been killed a couple of years ago and resurrected on mismerge 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 4079ef99900f..d13a6b83ad0c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1314,7 +1314,6 @@ extern int send_sigurg(struct fown_struct *fown); extern struct list_head super_blocks; extern spinlock_t sb_lock; -#define sb_entry(list) list_entry((list), struct super_block, s_list) #define S_BIAS (1<<30) struct super_block { struct list_head s_list; /* Keep this first */ -- cgit v1.2.3 From b20bd1a5e78af267dc4b6e1ffed48d5d776302c5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 22 Mar 2010 08:53:19 -0400 Subject: get rid of S_BIAS use atomic_inc_not_zero(&sb->s_active) instead of playing games with checking ->s_count > S_BIAS 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 d13a6b83ad0c..62f84d955b83 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1314,7 +1314,6 @@ extern int send_sigurg(struct fown_struct *fown); extern struct list_head super_blocks; extern spinlock_t sb_lock; -#define S_BIAS (1<<30) struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ -- cgit v1.2.3 From 8edd64bd6089e21f47dcdebb14b598b713213ddc Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 22 Mar 2010 19:56:42 -0400 Subject: get rid of restarts in sync_filesystems() At the same time we can kill s_need_restart and local mutex in there. __put_super() made public for a while; will be gone later. 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 62f84d955b83..e1c7427802b8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1332,7 +1332,6 @@ struct super_block { struct rw_semaphore s_umount; struct mutex s_lock; int s_count; - int s_need_sync; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; @@ -1780,6 +1779,7 @@ extern int get_sb_pseudo(struct file_system_type *, char *, struct vfsmount *mnt); extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb); int __put_super_and_need_restart(struct super_block *sb); +int __put_super(struct super_block *sb); void put_super(struct super_block *sb); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ -- cgit v1.2.3 From 35cf7ba0b46dc3582a01c3860b14bff122662aa3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 22 Mar 2010 21:13:53 -0400 Subject: Bury __put_super_and_need_restart() Signed-off-by: Al Viro --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e1c7427802b8..523086714c74 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1778,9 +1778,6 @@ extern int get_sb_pseudo(struct file_system_type *, char *, const struct super_operations *ops, unsigned long, struct vfsmount *mnt); extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb); -int __put_super_and_need_restart(struct super_block *sb); -int __put_super(struct super_block *sb); -void put_super(struct super_block *sb); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) \ -- cgit v1.2.3 From 01a05b337a5b647909e1d6670f57e7202318a5fb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 23 Mar 2010 06:06:58 -0400 Subject: new helper: iterate_supers() ... and switch the simple "loop over superblocks and do something" loops to it. 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 523086714c74..eeb04ba17b63 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2324,6 +2324,7 @@ extern struct super_block *get_super(struct block_device *); extern struct super_block *get_active_super(struct block_device *bdev); extern struct super_block *user_get_super(dev_t); extern void drop_super(struct super_block *sb); +extern void iterate_supers(void (*)(struct super_block *, void *), void *); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); -- cgit v1.2.3 From 18e9e5104fcd9a973ffe3eed3816c87f2a1b6cd2 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 23 Mar 2010 10:34:56 -0400 Subject: Introduce freeze_super and thaw_super for the fsfreeze ioctl Currently the way we do freezing is by passing sb>s_bdev to freeze_bdev and then letting it do all the work. But freezing is more of an fs thing, and doesn't really have much to do with the bdev at all, all the work gets done with the super. In btrfs we do not populate s_bdev, since we can have multiple bdev's for one fs and setting s_bdev makes removing devices from a pool kind of tricky. This means that freezing a btrfs filesystem fails, which causes us to corrupt with things like tux-on-ice which use the fsfreeze mechanism. So instead of populating sb->s_bdev with a random bdev in our pool, I've broken the actual fs freezing stuff into freeze_super and thaw_super. These just take the super_block that we're freezing and does the appropriate work. It's basically just copy and pasted from freeze_bdev. I've then converted freeze_bdev over to use the new super helpers. I've tested this with ext4 and btrfs and verified everything continues to work the same as before. The only new gotcha is multiple calls to the fsfreeze ioctl will return EBUSY if the fs is already frozen. I thought this was a better solution than adding a freeze counter to the super_block, but if everybody hates this idea I'm open to suggestions. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Al Viro --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index eeb04ba17b63..d51256bc6328 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1797,6 +1797,8 @@ extern void drop_collected_mounts(struct vfsmount *); extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, struct vfsmount *); extern int vfs_statfs(struct dentry *, struct kstatfs *); +extern int freeze_super(struct super_block *super); +extern int thaw_super(struct super_block *super); extern int current_umask(void); -- cgit v1.2.3 From bb4354538eb7b92f32cfedbad68c7be266c0b467 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 13 May 2010 17:53:14 -0700 Subject: fs: xattr_handler table should be const The entries in xattr handler table should be immutable (ie const) like other operation tables. Later patches convert common filesystems. Uncoverted filesystems will still work, but will generate a compiler warning. Signed-off-by: Stephen Hemminger Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- include/linux/generic_acl.h | 4 ++-- include/linux/xattr.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d51256bc6328..6660db898c41 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1336,7 +1336,7 @@ struct super_block { #ifdef CONFIG_SECURITY void *s_security; #endif - struct xattr_handler **s_xattr; + const struct xattr_handler **s_xattr; struct list_head s_inodes; /* all inodes */ struct hlist_head s_anon; /* anonymous dentries for (nfs) exporting */ diff --git a/include/linux/generic_acl.h b/include/linux/generic_acl.h index ca666d18ed67..574bea4013b6 100644 --- a/include/linux/generic_acl.h +++ b/include/linux/generic_acl.h @@ -5,8 +5,8 @@ struct inode; -extern struct xattr_handler generic_acl_access_handler; -extern struct xattr_handler generic_acl_default_handler; +extern const struct xattr_handler generic_acl_access_handler; +extern const struct xattr_handler generic_acl_default_handler; int generic_acl_init(struct inode *, struct inode *); int generic_acl_chmod(struct inode *); diff --git a/include/linux/xattr.h b/include/linux/xattr.h index fb9b7e6e1e2d..0cfa1e9c4cc1 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -37,7 +37,7 @@ struct inode; struct dentry; struct xattr_handler { - char *prefix; + const char *prefix; int flags; /* fs private flags passed back to the handlers */ size_t (*list)(struct dentry *dentry, char *list, size_t list_size, const char *name, size_t name_len, int handler_flags); -- cgit v1.2.3 From 94d09a98cdb163be12fb5c76841fa295f0bee22a Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 13 May 2010 17:53:19 -0700 Subject: reiserfs: constify xattr_handler Signed-off-by: Stephen Hemminger Signed-off-by: Al Viro --- include/linux/reiserfs_acl.h | 4 ++-- include/linux/reiserfs_xattr.h | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_acl.h b/include/linux/reiserfs_acl.h index b4448853900e..3fd8c4506bbb 100644 --- a/include/linux/reiserfs_acl.h +++ b/include/linux/reiserfs_acl.h @@ -53,8 +53,8 @@ int reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, struct inode *dir, struct dentry *dentry, struct inode *inode); int reiserfs_cache_default_acl(struct inode *dir); -extern struct xattr_handler reiserfs_posix_acl_default_handler; -extern struct xattr_handler reiserfs_posix_acl_access_handler; +extern const struct xattr_handler reiserfs_posix_acl_default_handler; +extern const struct xattr_handler reiserfs_posix_acl_access_handler; #else diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 7fa02b4af838..b2cf2089769b 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -58,9 +58,9 @@ int reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *, struct inode *, const char *, const void *, size_t, int); -extern struct xattr_handler reiserfs_xattr_user_handler; -extern struct xattr_handler reiserfs_xattr_trusted_handler; -extern struct xattr_handler reiserfs_xattr_security_handler; +extern const struct xattr_handler reiserfs_xattr_user_handler; +extern const struct xattr_handler reiserfs_xattr_trusted_handler; +extern const struct xattr_handler reiserfs_xattr_security_handler; #ifdef CONFIG_REISERFS_FS_SECURITY int reiserfs_security_init(struct inode *dir, struct inode *inode, struct reiserfs_security_handle *sec); -- cgit v1.2.3 From 8018ab057480974e7f26a387bf4ce040e9a5f6f1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 22 Mar 2010 17:32:25 +0100 Subject: sanitize vfs_fsync calling conventions Now that the last user passing a NULL file pointer is gone we can remove the redundant dentry argument and associated hacks inside vfs_fsynmc_range. The next step will be removig the dentry argument from ->fsync, but given the luck with the last round of method prototype changes I'd rather defer this until after the main merge window. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6660db898c41..f3e108314c93 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2084,9 +2084,9 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping, extern int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); -extern int vfs_fsync_range(struct file *file, struct dentry *dentry, - loff_t start, loff_t end, int datasync); -extern int vfs_fsync(struct file *file, struct dentry *dentry, int datasync); +extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, + int datasync); +extern int vfs_fsync(struct file *file, int datasync); extern int generic_write_sync(struct file *file, loff_t pos, loff_t count); extern void sync_supers(void); extern void emergency_sync(void); -- cgit v1.2.3 From 51ee049e771c14a29aaee8ecd6cbbe14db088f3a Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Tue, 27 Apr 2010 14:23:57 -0700 Subject: vfs: add lockdep annotation to s_vfs_rename_key for ecryptfs > ============================================= > [ INFO: possible recursive locking detected ] > 2.6.31-2-generic #14~rbd3 > --------------------------------------------- > firefox-3.5/4162 is trying to acquire lock: > (&s->s_vfs_rename_mutex){+.+.+.}, at: [] lock_rename+0x41/0xf0 > > but task is already holding lock: > (&s->s_vfs_rename_mutex){+.+.+.}, at: [] lock_rename+0x41/0xf0 > > other info that might help us debug this: > 3 locks held by firefox-3.5/4162: > #0: (&s->s_vfs_rename_mutex){+.+.+.}, at: [] lock_rename+0x41/0xf0 > #1: (&sb->s_type->i_mutex_key#11/1){+.+.+.}, at: [] lock_rename+0x6a/0xf0 > #2: (&sb->s_type->i_mutex_key#11/2){+.+.+.}, at: [] lock_rename+0x7f/0xf0 > > stack backtrace: > Pid: 4162, comm: firefox-3.5 Tainted: G C 2.6.31-2-generic #14~rbd3 > Call Trace: > [] print_deadlock_bug+0xf4/0x100 > [] validate_chain+0x4c6/0x750 > [] __lock_acquire+0x237/0x430 > [] lock_acquire+0xa5/0x150 > [] ? lock_rename+0x41/0xf0 > [] __mutex_lock_common+0x4d/0x3d0 > [] ? lock_rename+0x41/0xf0 > [] ? lock_rename+0x41/0xf0 > [] ? ecryptfs_rename+0x99/0x170 > [] mutex_lock_nested+0x46/0x60 > [] lock_rename+0x41/0xf0 > [] ecryptfs_rename+0xca/0x170 > [] vfs_rename_dir+0x13e/0x160 > [] vfs_rename+0xee/0x290 > [] ? __lookup_hash+0x102/0x160 > [] sys_renameat+0x252/0x280 > [] ? cp_new_stat+0xe4/0x100 > [] ? sysret_check+0x2e/0x69 > [] ? trace_hardirqs_on_caller+0x14d/0x190 > [] sys_rename+0x1b/0x20 > [] system_call_fastpath+0x16/0x1b The trace above is totally reproducible by doing a cross-directory rename on an ecryptfs directory. The issue seems to be that sys_renameat() does lock_rename() then calls into the filesystem; if the filesystem is ecryptfs, then ecryptfs_rename() again does lock_rename() on the lower filesystem, and lockdep can't tell that the two s_vfs_rename_mutexes are different. It seems an annotation like the following is sufficient to fix this (it does get rid of the lockdep trace in my simple tests); however I would like to make sure I'm not misunderstanding the locking, hence the CC list... Signed-off-by: Roland Dreier Cc: Tyler Hicks Cc: Dustin Kirkland Cc: Al Viro Signed-off-by: Andrew Morton 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 f3e108314c93..9626c5fbb0e1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1741,6 +1741,7 @@ struct file_system_type { struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; + struct lock_class_key s_vfs_rename_key; struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; -- cgit v1.2.3 From a1bd120d13e586ea1c424048fd2c8420a442852a Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Thu, 4 Mar 2010 17:29:14 +0300 Subject: vfs: Add inode uid,gid,mode init helper Signed-off-by: Dmitry Monakhov 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 9626c5fbb0e1..8a733862a411 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1428,7 +1428,8 @@ extern void dentry_unhash(struct dentry *dentry); * VFS file helper functions. */ extern int file_permission(struct file *, int); - +extern void inode_init_owner(struct inode *inode, const struct inode *dir, + mode_t mode); /* * VFS FS_IOC_FIEMAP helper definitions. */ -- cgit v1.2.3 From 454abafe9d8beb3fe7da06131b3d81d6d352a959 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Thu, 4 Mar 2010 17:32:18 +0300 Subject: ramfs: replace inode uid,gid,mode initialization with helper function - seems what ramfs_get_inode is only locally, make it static. [AV: the hell it is; it's used by shmem, so shmem needed conversion too and no, that function can't be made static] Signed-off-by: Dmitry Monakhov Signed-off-by: Al Viro --- include/linux/ramfs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index 8600508c77a6..e7320b5e82fb 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -1,7 +1,8 @@ #ifndef _LINUX_RAMFS_H #define _LINUX_RAMFS_H -struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev); +struct inode *ramfs_get_inode(struct super_block *sb, const struct inode *dir, + int mode, dev_t dev); extern int ramfs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt); -- cgit v1.2.3 From 2faa4cf76e7d229016240b79b50a43d81f458323 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 21 May 2010 20:16:50 -0700 Subject: linux/elfcore.h: hide kernel functions The declarations for elf_core_extra_phdrs() et al got added on the wrong side of #ifdef __KERNEL__ in linux/elfcore.h so they leak into the user header copy and we get a warning at build time about it. Signed-off-by: Roland McGrath Signed-off-by: Linus Torvalds --- include/linux/elfcore.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index e687bc3ba4da..394a3e0e4a6b 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -150,8 +150,6 @@ static inline int elf_core_copy_task_xfpregs(struct task_struct *t, elf_fpxregse } #endif -#endif /* __KERNEL__ */ - /* * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out * extra segments containing the gate DSO contents. Dumping its @@ -168,4 +166,6 @@ extern int elf_core_write_extra_data(struct file *file, size_t *size, unsigned long limit); extern size_t elf_core_extra_data_size(void); +#endif /* __KERNEL__ */ + #endif /* _LINUX_ELFCORE_H */ -- cgit v1.2.3 From 597b9d1e44e9ba69f2454a5318bbe7a6d5e6930a Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 13 Apr 2010 16:13:01 -0700 Subject: drivercore: Add of_match_table to the common device drivers OF-style matching can be available to any device, on any type of bus. This patch allows any driver to provide an OF match table when CONFIG_OF is enabled so that drivers can be bound against devices described in the device tree. Signed-off-by: Grant Likely Acked-by: Greg Kroah-Hartman --- include/linux/device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 7a968bdb02e2..cd7534cc42ab 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -129,6 +129,10 @@ struct device_driver { bool suppress_bind_attrs; /* disables bind/unbind via sysfs */ +#if defined(CONFIG_OF) + const struct of_device_id *of_match_table; +#endif + int (*probe) (struct device *dev); int (*remove) (struct device *dev); void (*shutdown) (struct device *dev); -- cgit v1.2.3 From 4018294b53d1dae026880e45f174c1cc63b5d435 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 13 Apr 2010 16:13:02 -0700 Subject: of: Remove duplicate fields from of_platform_driver .name, .match_table and .owner are duplicated in both of_platform_driver and device_driver. This patch is a removes the extra copies from struct of_platform_driver and converts all users to the device_driver members. This patch is a pretty mechanical change. The usage model doesn't change and if any drivers have been missed, or if anything has been fixed up incorrectly, then it will fail with a compile time error, and the fixup will be trivial. This patch looks big and scary because it touches so many files, but it should be pretty safe. Signed-off-by: Grant Likely Acked-by: Sean MacLennan --- include/linux/of_platform.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index ac3ae0758fbe..1643d3761eb4 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -31,10 +31,6 @@ extern struct bus_type of_platform_bus_type; */ struct of_platform_driver { - const char *name; - const struct of_device_id *match_table; - struct module *owner; - int (*probe)(struct of_device* dev, const struct of_device_id *match); int (*remove)(struct of_device* dev); -- cgit v1.2.3 From 44504b2bebf8b5823c59484e73096a7d6574471d Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 13 Apr 2010 16:13:22 -0700 Subject: of: change of_match_device to work with struct device The of_node pointer is now stored directly in struct device, so of_match_device() should work with any device, not just struct of_device. This patch changes the interface to of_match_device() to accept a struct device instead of struct of_device. Signed-off-by: Grant Likely --- include/linux/of_device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index e7904a9cd3a3..11651facc5f1 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -11,7 +11,7 @@ #define to_of_device(d) container_of(d, struct of_device, dev) extern const struct of_device_id *of_match_device( - const struct of_device_id *matches, const struct of_device *dev); + const struct of_device_id *matches, const struct device *dev); extern struct of_device *of_dev_get(struct of_device *dev); extern void of_dev_put(struct of_device *dev); -- cgit v1.2.3 From 42a4533976d922ff3272fad17dd52fe3682899dd Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 19 May 2010 18:34:11 +0000 Subject: mmc: prepare tmio_mmc for passing of DMA configuration from the MFD cell After this patch, if the "dma" pointer in struct tmio_mmc_data is not NULL, it points to a struct, containing two tokens, that have to be passed to the dmaengine driver for channel configuration. Signed-off-by: Guennadi Liakhovetski Acked-by: Samuel Ortiz Signed-off-by: Paul Mundt --- include/linux/mfd/tmio.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index c3f7dff8effc..360fc953d7bb 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -55,12 +55,18 @@ int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base); void tmio_core_mmc_pwr(void __iomem *cnf, int shift, int state); void tmio_core_mmc_clk_div(void __iomem *cnf, int shift, int state); +struct tmio_mmc_dma { + void *chan_priv_tx; + void *chan_priv_rx; +}; + /* * data for the MMC controller */ struct tmio_mmc_data { unsigned int hclk; unsigned long capabilities; + struct tmio_mmc_dma *dma; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); }; -- cgit v1.2.3 From 056676dabd9f4c69a6adcad208e9aa2ca7241400 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 19 May 2010 18:34:16 +0000 Subject: sh: prepare the SDHI MFD driver to pass DMA configuration to tmio_mmc.c Pass DMA slave IDs from platform down to the tmio_mmc driver, to be used for dmaengine configuration. Signed-off-by: Guennadi Liakhovetski Acked-by: Samuel Ortiz Signed-off-by: Paul Mundt --- include/linux/mfd/sh_mobile_sdhi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/sh_mobile_sdhi.h b/include/linux/mfd/sh_mobile_sdhi.h index 3bcd7163485c..c305461e7f47 100644 --- a/include/linux/mfd/sh_mobile_sdhi.h +++ b/include/linux/mfd/sh_mobile_sdhi.h @@ -2,6 +2,8 @@ #define __SH_MOBILE_SDHI_H__ struct sh_mobile_sdhi_info { + int dma_slave_tx; + int dma_slave_rx; void (*set_pwr)(struct platform_device *pdev, int state); }; -- cgit v1.2.3 From ac8fb3e8627d5494f3d2221925a82be4c1778b0e Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 19 May 2010 18:36:02 +0000 Subject: tmio: add a platform flag to disable card write-protection detection Write-protection status is not always available, e.g., micro-SD cards do not have a write-protection switch at all. This patch adds a flag to let platforms force tmio_mmc to consider the card writable. Signed-off-by: Guennadi Liakhovetski Acked-by: Ian Molton Signed-off-by: Paul Mundt --- include/linux/mfd/tmio.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 360fc953d7bb..feeed0b9ee70 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -50,6 +50,9 @@ tmio_iowrite16((val) >> 16, (base) + ((reg + 2) << (shift))); \ } while (0) +/* tmio MMC platform flags */ +#define TMIO_MMC_WRPROTECT_DISABLE (1 << 0) + int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base); int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base); void tmio_core_mmc_pwr(void __iomem *cnf, int shift, int state); @@ -66,6 +69,7 @@ struct tmio_mmc_dma { struct tmio_mmc_data { unsigned int hclk; unsigned long capabilities; + unsigned long flags; struct tmio_mmc_dma *dma; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); -- cgit v1.2.3 From f87c20a9db43f6f731270eeef616e1bcc266c2d4 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 19 May 2010 18:36:08 +0000 Subject: mfd: pass platform flags down to the tmio_mmc driver Signed-off-by: Guennadi Liakhovetski Acked-by: Ian Molton Signed-off-by: Paul Mundt --- include/linux/mfd/sh_mobile_sdhi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/sh_mobile_sdhi.h b/include/linux/mfd/sh_mobile_sdhi.h index c305461e7f47..c7b47f8ad650 100644 --- a/include/linux/mfd/sh_mobile_sdhi.h +++ b/include/linux/mfd/sh_mobile_sdhi.h @@ -4,6 +4,7 @@ struct sh_mobile_sdhi_info { int dma_slave_tx; int dma_slave_rx; + unsigned long tmio_flags; void (*set_pwr)(struct platform_device *pdev, int state); }; -- cgit v1.2.3 From a2b14dc9615c215a8cf4f2041f6c0c3fff5fc486 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 19 May 2010 18:37:25 +0000 Subject: mmc: let MFD's provide supported Vdd card voltages to tmio_mmc Signed-off-by: Guennadi Liakhovetski Acked-by: Ian Molton Signed-off-by: Paul Mundt --- include/linux/mfd/tmio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index feeed0b9ee70..f07425bc3dcd 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -70,6 +70,7 @@ struct tmio_mmc_data { unsigned int hclk; unsigned long capabilities; unsigned long flags; + u32 ocr_mask; /* available voltages */ struct tmio_mmc_dma *dma; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); -- cgit v1.2.3 From bb0fe533514c1d480c6c16f8bad070270a73a96c Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 19 May 2010 18:37:36 +0000 Subject: sh: allow platforms to specify SD-card supported voltages Boards can have different supplied voltages on different SD card slots. This information has to be passed down to the SD/MMC driver. Signed-off-by: Guennadi Liakhovetski Acked-by: Ian Molton Signed-off-by: Paul Mundt --- include/linux/mfd/sh_mobile_sdhi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/sh_mobile_sdhi.h b/include/linux/mfd/sh_mobile_sdhi.h index c7b47f8ad650..49067802a6d7 100644 --- a/include/linux/mfd/sh_mobile_sdhi.h +++ b/include/linux/mfd/sh_mobile_sdhi.h @@ -1,10 +1,13 @@ #ifndef __SH_MOBILE_SDHI_H__ #define __SH_MOBILE_SDHI_H__ +#include + struct sh_mobile_sdhi_info { int dma_slave_tx; int dma_slave_rx; unsigned long tmio_flags; + u32 tmio_ocr_mask; /* available MMC voltages */ void (*set_pwr)(struct platform_device *pdev, int state); }; -- cgit v1.2.3 From b3040e40675ec2c43542331cd30d4ee3dae797e8 Mon Sep 17 00:00:00 2001 From: Jassi Brar Date: Sun, 23 May 2010 20:28:19 -0700 Subject: DMA: PL330: Add dma api driver Add DMA Engine API driver for the PL330 DMAC. This driver is supposed to be reusable by various platforms that have one or more PL330 DMACs. Atm, DMA_SLAVE and DMA_MEMCPY capabilities have been implemented. Signed-off-by: Jassi Brar Reviewed-by: Linus Walleij [dan.j.williams@intel.com: missing slab.h and ->device_control() fixups] Signed-off-by: Dan Williams --- include/linux/amba/pl330.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 include/linux/amba/pl330.h (limited to 'include/linux') diff --git a/include/linux/amba/pl330.h b/include/linux/amba/pl330.h new file mode 100644 index 000000000000..cbee7de7dd36 --- /dev/null +++ b/include/linux/amba/pl330.h @@ -0,0 +1,45 @@ +/* linux/include/linux/amba/pl330.h + * + * Copyright (C) 2010 Samsung Electronics Co. Ltd. + * Jaswinder Singh + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __AMBA_PL330_H_ +#define __AMBA_PL330_H_ + +#include + +struct dma_pl330_peri { + /* + * Peri_Req i/f of the DMAC that is + * peripheral could be reached from. + */ + u8 peri_id; /* {0, 31} */ + enum pl330_reqtype rqtype; + + /* For M->D and D->M Channels */ + int burst_sz; /* in power of 2 */ + dma_addr_t fifo_addr; +}; + +struct dma_pl330_platdata { + /* + * Number of valid peripherals connected to DMAC. + * This may be different from the value read from + * CR0, as the PL330 implementation might have 'holes' + * in the peri list or the peri could also be reached + * from another DMAC which the platform prefers. + */ + u8 nr_valid_peri; + /* Array of valid peripherals */ + struct dma_pl330_peri *peri; + /* Bytes to allocate for MC buffer */ + unsigned mcbuf_sz; +}; + +#endif /* __AMBA_PL330_H_ */ -- cgit v1.2.3 From 0f0dd62fddcbd0f6830ed8ef3d3426ccc46b9250 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 19 May 2010 07:16:41 -0400 Subject: quota: kill the vfs_dq_off and vfs_dq_quota_on_remount wrappers Instead of having wrappers in the VFS namespace export the dquot_suspend and dquot_resume helpers directly. Also rename vfs_quota_disable to dquot_disable while we're at it. [Jan Kara: Moved dquot_suspend to quotaops.h and made it inline] Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/quotaops.h | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 370abb1e99cb..811529241e33 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -50,6 +50,14 @@ int dquot_alloc_inode(const struct inode *inode); int dquot_claim_space_nodirty(struct inode *inode, qsize_t number); void dquot_free_inode(const struct inode *inode); +int dquot_disable(struct super_block *sb, int type, unsigned int flags); +/* Suspend quotas on remount RO */ +static inline int dquot_suspend(struct super_block *sb, int type) +{ + return dquot_disable(sb, type, DQUOT_SUSPENDED); +} +int dquot_resume(struct super_block *sb, int type); + int dquot_commit(struct dquot *dquot); int dquot_acquire(struct dquot *dquot); int dquot_release(struct dquot *dquot); @@ -67,7 +75,6 @@ int vfs_quota_on_path(struct super_block *sb, int type, int format_id, int vfs_quota_on_mount(struct super_block *sb, char *qf_name, int format_id, int type); int vfs_quota_off(struct super_block *sb, int type, int remount); -int vfs_quota_disable(struct super_block *sb, int type, unsigned int flags); int vfs_quota_sync(struct super_block *sb, int type, int wait); int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); @@ -78,7 +85,6 @@ int vfs_set_dqblk(struct super_block *sb, int type, qid_t id, int __dquot_transfer(struct inode *inode, struct dquot **transfer_to); int dquot_transfer(struct inode *inode, struct iattr *iattr); -int vfs_dq_quota_on_remount(struct super_block *sb); static inline struct mem_dqinfo *sb_dqinfo(struct super_block *sb, int type) { @@ -231,11 +237,6 @@ static inline int vfs_dq_off(struct super_block *sb, int remount) return 0; } -static inline int vfs_dq_quota_on_remount(struct super_block *sb) -{ - return 0; -} - static inline int dquot_transfer(struct inode *inode, struct iattr *iattr) { return 0; @@ -262,6 +263,22 @@ static inline int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) return 0; } +static inline int dquot_disable(struct super_block *sb, int type, + unsigned int flags) +{ + return 0; +} + +static inline int dquot_suspend(struct super_block *sb, int type) +{ + return 0; +} + +static inline int dquot_resume(struct super_block *sb, int type) +{ + return 0; +} + #define dquot_file_open generic_file_open #endif /* CONFIG_QUOTA */ -- cgit v1.2.3 From e0ccfd959cd8907bcb66cc2042e0f4fd7fcbff2b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 19 May 2010 07:16:42 -0400 Subject: quota: move unmount handling into the filesystem Currently the VFS calls into the quotactl interface for unmounting filesystems. This means filesystems with their own quota handling can't easily distinguish between user-space originating quotaoff and an unount. Instead move the responsibily of the unmount handling into the filesystem to be consistent with all other dquot handling. Note that we do call dquot_disable a lot later now, e.g. after a sync_filesystem. But this is fine as the quota code does all its writes via blockdev's mapping and that is synced even later. Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/quotaops.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 811529241e33..cfa2abb1b6d1 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -156,16 +156,6 @@ extern const struct quotactl_ops vfs_quotactl_ops; #define sb_dquot_ops (&dquot_operations) #define sb_quotactl_ops (&vfs_quotactl_ops) -/* Cannot be called inside a transaction */ -static inline int vfs_dq_off(struct super_block *sb, int remount) -{ - int ret = -ENOSYS; - - if (sb->s_qcop && sb->s_qcop->quota_off) - ret = sb->s_qcop->quota_off(sb, -1, remount); - return ret; -} - #else static inline int sb_has_quota_usage_enabled(struct super_block *sb, int type) @@ -232,11 +222,6 @@ static inline void dquot_free_inode(const struct inode *inode) { } -static inline int vfs_dq_off(struct super_block *sb, int remount) -{ - return 0; -} - static inline int dquot_transfer(struct inode *inode, struct iattr *iattr) { return 0; -- cgit v1.2.3 From 307ae18a56e5b706056a2050d52e8cc01b5171c0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 19 May 2010 07:16:43 -0400 Subject: quota: drop remount argument to ->quota_on and ->quota_off Remount handling has fully moved into the filesystem, so all this is superflous now. Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/quota.h | 4 ++-- include/linux/quotaops.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 7126a15467f1..2789d07c37be 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -332,8 +332,8 @@ struct dquot_operations { /* Operations handling requests from userspace */ struct quotactl_ops { - int (*quota_on)(struct super_block *, int, int, char *, int); - int (*quota_off)(struct super_block *, int, int); + int (*quota_on)(struct super_block *, int, int, char *); + int (*quota_off)(struct super_block *, int); int (*quota_sync)(struct super_block *, int, int); int (*get_info)(struct super_block *, int, struct if_dqinfo *); int (*set_info)(struct super_block *, int, struct if_dqinfo *); diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index cfa2abb1b6d1..a6592ddc349f 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -67,14 +67,14 @@ int dquot_mark_dquot_dirty(struct dquot *dquot); int dquot_file_open(struct inode *inode, struct file *file); int vfs_quota_on(struct super_block *sb, int type, int format_id, - char *path, int remount); + char *path); int vfs_quota_enable(struct inode *inode, int type, int format_id, unsigned int flags); int vfs_quota_on_path(struct super_block *sb, int type, int format_id, struct path *path); int vfs_quota_on_mount(struct super_block *sb, char *qf_name, int format_id, int type); -int vfs_quota_off(struct super_block *sb, int type, int remount); +int vfs_quota_off(struct super_block *sb, int type); int vfs_quota_sync(struct super_block *sb, int type, int wait); int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); -- cgit v1.2.3 From 123e9caf1e85008ab7eb5f6cd58c44f9a5d73b2b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 19 May 2010 07:16:44 -0400 Subject: quota: explicitly set ->dq_op and ->s_qcop Only set the quota operation vectors if the filesystem actually supports quota instead of doing it for all filesystems in alloc_super(). [Jan Kara: Export dquot_operations and vfs_quotactl_ops] Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/quotaops.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index a6592ddc349f..84b8dbf59c03 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -153,9 +153,6 @@ static inline unsigned sb_any_quota_active(struct super_block *sb) extern const struct dquot_operations dquot_operations; extern const struct quotactl_ops vfs_quotactl_ops; -#define sb_dquot_ops (&dquot_operations) -#define sb_quotactl_ops (&vfs_quotactl_ops) - #else static inline int sb_has_quota_usage_enabled(struct super_block *sb, int type) @@ -199,12 +196,6 @@ static inline int sb_any_quota_active(struct super_block *sb) return 0; } -/* - * NO-OP when quota not configured. - */ -#define sb_dquot_ops (NULL) -#define sb_quotactl_ops (NULL) - static inline void dquot_initialize(struct inode *inode) { } -- cgit v1.2.3 From 287a80958cf63fc5c68d5bf6e89a3669dd66234a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 19 May 2010 07:16:45 -0400 Subject: quota: rename default quotactl methods to dquot_ Follow the dquot_* style used elsewhere in dquot.c. [Jan Kara: Fixed up missing conversion of ext2] Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/quotaops.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 84b8dbf59c03..0c77cd8d2822 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -66,21 +66,21 @@ int dquot_mark_dquot_dirty(struct dquot *dquot); int dquot_file_open(struct inode *inode, struct file *file); -int vfs_quota_on(struct super_block *sb, int type, int format_id, +int dquot_quota_on(struct super_block *sb, int type, int format_id, char *path); -int vfs_quota_enable(struct inode *inode, int type, int format_id, +int dquot_enable(struct inode *inode, int type, int format_id, unsigned int flags); -int vfs_quota_on_path(struct super_block *sb, int type, int format_id, +int dquot_quota_on_path(struct super_block *sb, int type, int format_id, struct path *path); -int vfs_quota_on_mount(struct super_block *sb, char *qf_name, +int dquot_quota_on_mount(struct super_block *sb, char *qf_name, int format_id, int type); -int vfs_quota_off(struct super_block *sb, int type); -int vfs_quota_sync(struct super_block *sb, int type, int wait); -int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); -int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); -int vfs_get_dqblk(struct super_block *sb, int type, qid_t id, +int dquot_quota_off(struct super_block *sb, int type); +int dquot_quota_sync(struct super_block *sb, int type, int wait); +int dquot_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); +int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); +int dquot_get_dqblk(struct super_block *sb, int type, qid_t id, struct fs_disk_quota *di); -int vfs_set_dqblk(struct super_block *sb, int type, qid_t id, +int dquot_set_dqblk(struct super_block *sb, int type, qid_t id, struct fs_disk_quota *di); int __dquot_transfer(struct inode *inode, struct dquot **transfer_to); @@ -151,7 +151,7 @@ static inline unsigned sb_any_quota_active(struct super_block *sb) * Operations supported for diskquotas. */ extern const struct dquot_operations dquot_operations; -extern const struct quotactl_ops vfs_quotactl_ops; +extern const struct quotactl_ops dquot_quotactl_ops; #else -- cgit v1.2.3 From 73367bd8eef4f4eb311005886aaa916013073265 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 21 May 2010 14:41:35 -0700 Subject: slub: move kmem_cache_node into it's own cacheline This patch is meant to improve the performance of SLUB by moving the local kmem_cache_node lock into it's own cacheline separate from kmem_cache. This is accomplished by simply removing the local_node when NUMA is enabled. On my system with 2 nodes I saw around a 5% performance increase w/ hackbench times dropping from 6.2 seconds to 5.9 seconds on average. I suspect the performance gain would increase as the number of nodes increases, but I do not have the data to currently back that up. Bugzilla-Reference: http://bugzilla.kernel.org/show_bug.cgi?id=15713 Cc: Reported-by: Alex Shi Tested-by: Alex Shi Acked-by: Yanmin Zhang Acked-by: Christoph Lameter Signed-off-by: Alexander Duyck Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 55695c8d2f8a..6ac37664e8fe 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -75,12 +75,6 @@ struct kmem_cache { int offset; /* Free pointer offset. */ struct kmem_cache_order_objects oo; - /* - * Avoid an extra cache line for UP, SMP and for the node local to - * struct kmem_cache. - */ - struct kmem_cache_node local_node; - /* Allocation and freeing of slabs */ struct kmem_cache_order_objects max; struct kmem_cache_order_objects min; @@ -102,6 +96,9 @@ struct kmem_cache { */ int remote_node_defrag_ratio; struct kmem_cache_node *node[MAX_NUMNODES]; +#else + /* Avoid an extra cache line for UP */ + struct kmem_cache_node local_node; #endif }; -- cgit v1.2.3 From 556f4aeb7d9dfac8573d0281dd555bd3210d8366 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 5 May 2010 09:28:15 +0000 Subject: spi/pl022: fix up differences between ARM and ST versions The PL022 SPI driver did not cleanly separate between the original unmodified ARM version and the ST Microelectronics versions. Split this more cleanly and fix some whitespace moaning from checkpatch at the same time. Signed-off-by: Linus Walleij Signed-off-by: Grant Likely --- include/linux/amba/pl022.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/amba/pl022.h b/include/linux/amba/pl022.h index e4836c6b3dd7..612f39913340 100644 --- a/include/linux/amba/pl022.h +++ b/include/linux/amba/pl022.h @@ -71,6 +71,7 @@ struct ssp_clock_params { /** * enum ssp_rx_endian - endianess of Rx FIFO Data + * this feature is only available in ST versionf of PL022 */ enum ssp_rx_endian { SSP_RX_MSB, @@ -181,7 +182,8 @@ enum ssp_microwire_wait_state { }; /** - * enum Microwire - whether Full/Half Duplex + * enum Microwire - whether Full/Half Duplex, only available + * in the ST Micro variant. * @SSP_MICROWIRE_CHANNEL_FULL_DUPLEX: SSPTXD becomes bi-directional, * SSPRXD not used * @SSP_MICROWIRE_CHANNEL_HALF_DUPLEX: SSPTXD is an output, SSPRXD is -- cgit v1.2.3 From 781c7b129b1beb876905f7212927aa0ee1b022e5 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 7 May 2010 08:40:53 +0000 Subject: spi/pl022: add support for the PL023 derivate This adds support for a further ST variant of the PL022 called PL023. Some differences in the control registers due to being stripped down to SPI mode only, and a new clock feedback sample delay config setting is available. Signed-off-by: Linus Walleij Signed-off-by: Grant Likely --- include/linux/amba/pl022.h | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/amba/pl022.h b/include/linux/amba/pl022.h index 612f39913340..abf26cc47a2b 100644 --- a/include/linux/amba/pl022.h +++ b/include/linux/amba/pl022.h @@ -182,8 +182,8 @@ enum ssp_microwire_wait_state { }; /** - * enum Microwire - whether Full/Half Duplex, only available - * in the ST Micro variant. + * enum ssp_duplex - whether Full/Half Duplex on microwire, only + * available in the ST Micro variant. * @SSP_MICROWIRE_CHANNEL_FULL_DUPLEX: SSPTXD becomes bi-directional, * SSPRXD not used * @SSP_MICROWIRE_CHANNEL_HALF_DUPLEX: SSPTXD is an output, SSPRXD is @@ -194,6 +194,31 @@ enum ssp_duplex { SSP_MICROWIRE_CHANNEL_HALF_DUPLEX }; +/** + * enum ssp_clkdelay - an optional clock delay on the feedback clock + * only available in the ST Micro PL023 variant. + * @SSP_FEEDBACK_CLK_DELAY_NONE: no delay, the data coming in from the + * slave is sampled directly + * @SSP_FEEDBACK_CLK_DELAY_1T: the incoming slave data is sampled with + * a delay of T-dt + * @SSP_FEEDBACK_CLK_DELAY_2T: dito with a delay if 2T-dt + * @SSP_FEEDBACK_CLK_DELAY_3T: dito with a delay if 3T-dt + * @SSP_FEEDBACK_CLK_DELAY_4T: dito with a delay if 4T-dt + * @SSP_FEEDBACK_CLK_DELAY_5T: dito with a delay if 5T-dt + * @SSP_FEEDBACK_CLK_DELAY_6T: dito with a delay if 6T-dt + * @SSP_FEEDBACK_CLK_DELAY_7T: dito with a delay if 7T-dt + */ +enum ssp_clkdelay { + SSP_FEEDBACK_CLK_DELAY_NONE, + SSP_FEEDBACK_CLK_DELAY_1T, + SSP_FEEDBACK_CLK_DELAY_2T, + SSP_FEEDBACK_CLK_DELAY_3T, + SSP_FEEDBACK_CLK_DELAY_4T, + SSP_FEEDBACK_CLK_DELAY_5T, + SSP_FEEDBACK_CLK_DELAY_6T, + SSP_FEEDBACK_CLK_DELAY_7T +}; + /** * CHIP select/deselect commands */ @@ -237,6 +262,8 @@ struct pl022_ssp_controller { * @ctrl_len: Microwire interface: Control length * @wait_state: Microwire interface: Wait state * @duplex: Microwire interface: Full/Half duplex + * @clkdelay: on the PL023 variant, the delay in feeback clock cycles + * before sampling the incoming line * @cs_control: function pointer to board-specific function to * assert/deassert I/O port to control HW generation of devices chip-select. * @dma_xfer_type: Type of DMA xfer (Mem-to-periph or Periph-to-Periph) @@ -260,6 +287,7 @@ struct pl022_config_chip { enum ssp_microwire_ctrl_len ctrl_len; enum ssp_microwire_wait_state wait_state; enum ssp_duplex duplex; + enum ssp_clkdelay clkdelay; void (*cs_control) (u32 control); }; -- cgit v1.2.3 From 41c4221ca6b9db8ea63d2c2323c0e7a8865eba6e Mon Sep 17 00:00:00 2001 From: hartleys Date: Thu, 6 May 2010 20:51:04 +0000 Subject: spi: move bitbang txrx utility functions to private header A number of files in drivers/spi fail checkincludes.pl due to the double include of . The first include is needed to get the struct spi_bitbang definition and the spi_bitbang_* function prototypes. The second include happens after defining EXPAND_BITBANG_TXRX to get the inlined bitbang_txrx_* utility functions. The header is also included by a number of other spi drivers, as well as some arch/ code, in order to use struct spi_bitbang and the associated functions. To fix the double include, and remove any potential confusion about it, move the inlined bitbang_txrx_* functions to a new private header in drivers/spi and also remove the need to define EXPAND_BITBANG_TXRX. Signed-off-by: H Hartley Sweeten Signed-off-by: Grant Likely --- include/linux/spi/spi_bitbang.h | 101 ---------------------------------------- 1 file changed, 101 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index 3274c507b8a9..f987a2bee16a 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -1,24 +1,6 @@ #ifndef __SPI_BITBANG_H #define __SPI_BITBANG_H -/* - * Mix this utility code with some glue code to get one of several types of - * simple SPI master driver. Two do polled word-at-a-time I/O: - * - * - GPIO/parport bitbangers. Provide chipselect() and txrx_word[](), - * expanding the per-word routines from the inline templates below. - * - * - Drivers for controllers resembling bare shift registers. Provide - * chipselect() and txrx_word[](), with custom setup()/cleanup() methods - * that use your controller's clock and chipselect registers. - * - * Some hardware works well with requests at spi_transfer scope: - * - * - Drivers leveraging smarter hardware, with fifos or DMA; or for half - * duplex (MicroWire) controllers. Provide chipselect() and txrx_bufs(), - * and custom setup()/cleanup() methods. - */ - #include struct spi_bitbang { @@ -68,86 +50,3 @@ extern int spi_bitbang_start(struct spi_bitbang *spi); extern int spi_bitbang_stop(struct spi_bitbang *spi); #endif /* __SPI_BITBANG_H */ - -/*-------------------------------------------------------------------------*/ - -#ifdef EXPAND_BITBANG_TXRX - -/* - * The code that knows what GPIO pins do what should have declared four - * functions, ideally as inlines, before #defining EXPAND_BITBANG_TXRX - * and including this header: - * - * void setsck(struct spi_device *, int is_on); - * void setmosi(struct spi_device *, int is_on); - * int getmiso(struct spi_device *); - * void spidelay(unsigned); - * - * setsck()'s is_on parameter is a zero/nonzero boolean. - * - * setmosi()'s is_on parameter is a zero/nonzero boolean. - * - * getmiso() is required to return 0 or 1 only. Any other value is invalid - * and will result in improper operation. - * - * A non-inlined routine would call bitbang_txrx_*() routines. The - * main loop could easily compile down to a handful of instructions, - * especially if the delay is a NOP (to run at peak speed). - * - * Since this is software, the timings may not be exactly what your board's - * chips need ... there may be several reasons you'd need to tweak timings - * in these routines, not just make to make it faster or slower to match a - * particular CPU clock rate. - */ - -static inline u32 -bitbang_txrx_be_cpha0(struct spi_device *spi, - unsigned nsecs, unsigned cpol, - u32 word, u8 bits) -{ - /* if (cpol == 0) this is SPI_MODE_0; else this is SPI_MODE_2 */ - - /* clock starts at inactive polarity */ - for (word <<= (32 - bits); likely(bits); bits--) { - - /* setup MSB (to slave) on trailing edge */ - setmosi(spi, word & (1 << 31)); - spidelay(nsecs); /* T(setup) */ - - setsck(spi, !cpol); - spidelay(nsecs); - - /* sample MSB (from slave) on leading edge */ - word <<= 1; - word |= getmiso(spi); - setsck(spi, cpol); - } - return word; -} - -static inline u32 -bitbang_txrx_be_cpha1(struct spi_device *spi, - unsigned nsecs, unsigned cpol, - u32 word, u8 bits) -{ - /* if (cpol == 0) this is SPI_MODE_1; else this is SPI_MODE_3 */ - - /* clock starts at inactive polarity */ - for (word <<= (32 - bits); likely(bits); bits--) { - - /* setup MSB (to slave) on leading edge */ - setsck(spi, !cpol); - setmosi(spi, word & (1 << 31)); - spidelay(nsecs); /* T(setup) */ - - setsck(spi, cpol); - spidelay(nsecs); - - /* sample MSB (from slave) on trailing edge */ - word <<= 1; - word |= getmiso(spi); - } - return word; -} - -#endif /* EXPAND_BITBANG_TXRX */ -- cgit v1.2.3 From 0178f3e28e2166664916265c5d4922b1376b9fa1 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 26 Apr 2010 15:18:14 +0100 Subject: regulator: Allow regulator-regulator supplies to be specified by name When one regulator supplies another allow the relationship to be specified using names rather than struct regulators, in a similar manner to that allowed for consumer supplies. This allows static configuration at compile time, reducing the need for dynamic init code. Also change the references to LINE supply to be system supply since line is sometimes used for actual supplies and therefore potentially confusing. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/machine.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 234a8476cba8..e2980287245e 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -157,7 +157,11 @@ struct regulator_consumer_supply { * * Initialisation constraints, our supply and consumers supplies. * - * @supply_regulator_dev: Parent regulator (if any). + * @supply_regulator: Parent regulator. Specified using the regulator name + * as it appears in the name field in sysfs, which can + * be explicitly set using the constraints field 'name'. + * @supply_regulator_dev: Parent regulator (if any) - DEPRECATED in favour + * of supply_regulator. * * @constraints: Constraints. These must be specified for the regulator to * be usable. @@ -168,7 +172,8 @@ struct regulator_consumer_supply { * @driver_data: Data passed to regulator_init. */ struct regulator_init_data { - struct device *supply_regulator_dev; /* or NULL for LINE */ + const char *supply_regulator; /* or NULL for system supply */ + struct device *supply_regulator_dev; /* or NULL for system supply */ struct regulation_constraints constraints; -- cgit v1.2.3 From 9f79e9db2e282857912bcfe7f741bcdd5c46e860 Mon Sep 17 00:00:00 2001 From: Haojian Zhuang Date: Tue, 4 May 2010 09:54:51 -0400 Subject: regulator: use voltage number array in 88pm860x A lot of condition comparision statements are used in original driver. These statements are used to check the boundary of voltage numbers since voltage number isn't linear. Now use array of voltage numbers instead. Clean code with simpler way. Signed-off-by: Haojian Zhuang Acked-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/mfd/88pm860x.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/88pm860x.h b/include/linux/mfd/88pm860x.h index 73f92c5feea2..e3c4ff8c3e38 100644 --- a/include/linux/mfd/88pm860x.h +++ b/include/linux/mfd/88pm860x.h @@ -132,6 +132,7 @@ enum { PM8607_ID_LDO9, PM8607_ID_LDO10, PM8607_ID_LDO12, + PM8607_ID_LDO13, PM8607_ID_LDO14, PM8607_ID_RG_MAX, @@ -309,7 +310,7 @@ struct pm860x_chip { }; -#define PM8607_MAX_REGULATOR 15 /* 3 Bucks, 12 LDOs */ +#define PM8607_MAX_REGULATOR PM8607_ID_RG_MAX /* 3 Bucks, 13 LDOs */ enum { GI2C_PORT = 0, -- cgit v1.2.3 From dd3bb14f44a6382de2508ec387c7e5569ad2d4f1 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 25 May 2010 15:06:06 +0200 Subject: fuse: support splice() writing to fuse device Allow userspace filesystem implementation to use splice() to write to the fuse device. The semantics of using splice() are: 1) buffer the message header and data in a temporary pipe 2) with a *single* splice() call move the message from the temporary pipe to the fuse device The READ reply message has the most interesting use for this, since now the data from an arbitrary file descriptor (which could be a regular file, a block device or a socket) can be tranferred into the fuse device without having to go through a userspace buffer. It will also allow zero copy moving of pages. One caveat is that the protocol on the fuse device requires the length of the whole message to be written into the header. But the length of the data transferred into the temporary pipe may not be known in advance. The current library implementation works around this by using vmplice to write the header and modifying the header after splicing the data into the pipe (error handling omitted): struct fuse_out_header out; iov.iov_base = &out; iov.iov_len = sizeof(struct fuse_out_header); vmsplice(pip[1], &iov, 1, 0); len = splice(input_fd, input_offset, pip[1], NULL, len, 0); /* retrospectively modify the header: */ out.len = len + sizeof(struct fuse_out_header); splice(pip[0], NULL, fuse_chan_fd(req->ch), NULL, out.len, flags); This works since vmsplice only saves a pointer to the data, it does not copy the data itself. Since pipes are currently limited to 16 pages and messages need to be spliced atomically, the length of the data is limited to 15 pages (or 60kB for 4k pages). Signed-off-by: Miklos Szeredi --- include/linux/fuse.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index 3e2925a34bf0..88e0eb596919 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -34,6 +34,9 @@ * 7.13 * - make max number of background requests and congestion threshold * tunables + * + * 7.14 + * - add splice support to fuse device */ #ifndef _LINUX_FUSE_H @@ -65,7 +68,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 13 +#define FUSE_KERNEL_MINOR_VERSION 14 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 -- cgit v1.2.3 From facd07b07d2a7988f5ce849558838cc953847637 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Sun, 23 May 2010 11:00:55 -0400 Subject: direct-io: add a hook for the fs to provide its own submit_bio function Because BTRFS can do RAID and such, we need our own submit hook so we can setup the bio's in the correct fashion, and handle checksum errors properly. So there are a few changes here 1) The submit_io hook. This is straightforward, just call this instead of submit_bio. 2) Allow the fs to return -ENOTBLK for reads. Usually this has only worked for writes, since writes can fallback onto buffered IO. But BTRFS needs the option of falling back on buffered IO if it encounters a compressed extent, since we need to read the entire extent in and decompress it. So if we get -ENOTBLK back from get_block we'll return back and fallback on buffered just like the write case. I've tested these changes with fsx and everything seems to work. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- include/linux/fs.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 44f35aea2f1f..10704f0086c8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2250,10 +2250,15 @@ static inline int xip_truncate_page(struct address_space *mapping, loff_t from) #endif #ifdef CONFIG_BLOCK +struct bio; +typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, + loff_t file_offset); +void dio_end_io(struct bio *bio, int error); + ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, loff_t offset, unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, - int lock_type); + dio_submit_t submit_io, int lock_type); enum { /* need locking between buffered and direct access */ @@ -2269,7 +2274,7 @@ static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, dio_iodone_t end_io) { return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, + nr_segs, get_block, end_io, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } @@ -2279,7 +2284,7 @@ static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb, dio_iodone_t end_io) { return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, 0); + nr_segs, get_block, end_io, NULL, 0); } #endif -- cgit v1.2.3 From e9d6c157385e4efa61cb8293e425c9d8beba70d3 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Mon, 24 May 2010 14:31:48 -0700 Subject: tmpfs: insert tmpfs cache pages to inactive list at first Shaohua Li reported parallel file copy on tmpfs can lead to OOM killer. This is regression of caused by commit 9ff473b9a7 ("vmscan: evict streaming IO first"). Wow, It is 2 years old patch! Currently, tmpfs file cache is inserted active list at first. This means that the insertion doesn't only increase numbers of pages in anon LRU, but it also reduces anon scanning ratio. Therefore, vmscan will get totally confused. It scans almost only file LRU even though the system has plenty unused tmpfs pages. Historically, lru_cache_add_active_anon() was used for two reasons. 1) Intend to priotize shmem page rather than regular file cache. 2) Intend to avoid reclaim priority inversion of used once pages. But we've lost both motivation because (1) Now we have separate anon and file LRU list. then, to insert active list doesn't help such priotize. (2) In past, one pte access bit will cause page activation. then to insert inactive list with pte access bit mean higher priority than to insert active list. Its priority inversion may lead to uninteded lru chun. but it was already solved by commit 645747462 (vmscan: detect mapped file pages used only once). (Thanks Hannes, you are great!) Thus, now we can use lru_cache_add_anon() instead. Signed-off-by: KOSAKI Motohiro Reported-by: Shaohua Li Reviewed-by: Wu Fengguang Reviewed-by: Johannes Weiner Reviewed-by: Rik van Riel Reviewed-by: Minchan Kim Acked-by: Hugh Dickins Cc: Henrique de Moraes Holschuh Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index ec2b7a42b45f..600b03b7732e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -224,21 +224,11 @@ static inline void lru_cache_add_anon(struct page *page) __lru_cache_add(page, LRU_INACTIVE_ANON); } -static inline void lru_cache_add_active_anon(struct page *page) -{ - __lru_cache_add(page, LRU_ACTIVE_ANON); -} - static inline void lru_cache_add_file(struct page *page) { __lru_cache_add(page, LRU_INACTIVE_FILE); } -static inline void lru_cache_add_active_file(struct page *page) -{ - __lru_cache_add(page, LRU_ACTIVE_FILE); -} - /* linux/mm/vmscan.c */ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); -- cgit v1.2.3 From e13861d822f8f443ca0c020ea8fc2dc01039cd63 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Mon, 24 May 2010 14:31:59 -0700 Subject: mm: remove return value of putback_lru_pages() putback_lru_page() never can fail. So it doesn't matter count of "the number of pages put back". In addition, users of this functions don't use return value. Let's remove unnecessary code. Signed-off-by: Minchan Kim Reviewed-by: Rik van Riel Reviewed-by: KOSAKI Motohiro Reviewed-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 7f085c97c799..7a07b17d27c5 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -9,7 +9,7 @@ typedef struct page *new_page_t(struct page *, unsigned long private, int **); #ifdef CONFIG_MIGRATION #define PAGE_MIGRATION 1 -extern int putback_lru_pages(struct list_head *l); +extern void putback_lru_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *); extern int migrate_pages(struct list_head *l, new_page_t x, @@ -25,7 +25,7 @@ extern int migrate_vmas(struct mm_struct *mm, #else #define PAGE_MIGRATION 0 -static inline int putback_lru_pages(struct list_head *l) { return 0; } +static inline void putback_lru_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t x, unsigned long private, int offlining) { return -ENOSYS; } -- cgit v1.2.3 From 708c1bbc9d0c3e57f40501794d9b0eed29d10fce Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Mon, 24 May 2010 14:32:07 -0700 Subject: mempolicy: restructure rebinding-mempolicy functions Nick Piggin reported that the allocator may see an empty nodemask when changing cpuset's mems[1]. It happens only on the kernel that do not do atomic nodemask_t stores. (MAX_NUMNODES > BITS_PER_LONG) But I found that there is also a problem on the kernel that can do atomic nodemask_t stores. The problem is that the allocator can't find a node to alloc page when changing cpuset's mems though there is a lot of free memory. The reason is like this: (mpol: mempolicy) task1 task1's mpol task2 alloc page 1 alloc on node0? NO 1 1 change mems from 1 to 0 1 rebind task1's mpol 0-1 set new bits 0 clear disallowed bits alloc on node1? NO 0 ... can't alloc page goto oom I can use the attached program reproduce it by the following step: # mkdir /dev/cpuset # mount -t cpuset cpuset /dev/cpuset # mkdir /dev/cpuset/1 # echo `cat /dev/cpuset/cpus` > /dev/cpuset/1/cpus # echo `cat /dev/cpuset/mems` > /dev/cpuset/1/mems # echo $$ > /dev/cpuset/1/tasks # numactl --membind=`cat /dev/cpuset/mems` ./cpuset_mem_hog & = max(nr_cpus - 1, 1) # killall -s SIGUSR1 cpuset_mem_hog # ./change_mems.sh several hours later, oom will happen though there is a lot of free memory. This patchset fixes this problem by expanding the nodes range first(set newly allowed bits) and shrink it lazily(clear newly disallowed bits). So we use a variable to tell the write-side task that read-side task is reading nodemask, and the write-side task clears newly disallowed nodes after read-side task ends the current memory allocation. This patch: In order to fix no node to alloc memory, when we want to update mempolicy and mems_allowed, we expand the set of nodes first (set all the newly nodes) and shrink the set of nodes lazily(clean disallowed nodes), But the mempolicy's rebind functions may breaks the expanding. So we restructure the mempolicy's rebind functions and split the rebind work to two steps, just like the update of cpuset's mems: The 1st step: expand the set of the mempolicy's nodes. The 2nd step: shrink the set of the mempolicy's nodes. It is used when there is no real lock to protect the mempolicy in the read-side. Otherwise we can do rebind work at once. In order to implement it, we define enum mpol_rebind_step { MPOL_REBIND_ONCE, MPOL_REBIND_STEP1, MPOL_REBIND_STEP2, MPOL_REBIND_NSTEP, }; If the mempolicy needn't be updated by two steps, we can pass MPOL_REBIND_ONCE to the rebind functions. Or we can pass MPOL_REBIND_STEP1 to do the first step of the rebind work and pass MPOL_REBIND_STEP2 to do the second step work. Besides that, it maybe long time between these two step and we have to release the lock that protects mempolicy and mems_allowed. If we hold the lock once again, we must check whether the current mempolicy is under the rebinding (the first step has been done) or not, because the task may alloc a new mempolicy when we don't hold the lock. So we defined the following flag to identify it: #define MPOL_F_REBINDING (1 << 2) The new functions will be used in the next patch. Signed-off-by: Miao Xie Cc: David Rientjes Cc: Nick Piggin Cc: Paul Menage Cc: Lee Schermerhorn Cc: Hugh Dickins Cc: Ravikiran Thirumalai Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 1cc966cd3e5f..7b9ef6bf45aa 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -23,6 +23,13 @@ enum { MPOL_MAX, /* always last member of enum */ }; +enum mpol_rebind_step { + MPOL_REBIND_ONCE, /* do rebind work at once(not by two step) */ + MPOL_REBIND_STEP1, /* first step(set all the newly nodes) */ + MPOL_REBIND_STEP2, /* second step(clean all the disallowed nodes)*/ + MPOL_REBIND_NSTEP, +}; + /* Flags for set_mempolicy */ #define MPOL_F_STATIC_NODES (1 << 15) #define MPOL_F_RELATIVE_NODES (1 << 14) @@ -51,6 +58,7 @@ enum { */ #define MPOL_F_SHARED (1 << 0) /* identify shared policies */ #define MPOL_F_LOCAL (1 << 1) /* preferred local allocation */ +#define MPOL_F_REBINDING (1 << 2) /* identify policies in rebinding */ #ifdef __KERNEL__ @@ -193,8 +201,8 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, extern void numa_default_policy(void); extern void numa_policy_init(void); -extern void mpol_rebind_task(struct task_struct *tsk, - const nodemask_t *new); +extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new, + enum mpol_rebind_step step); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern void mpol_fix_fork_child_flag(struct task_struct *p); @@ -308,7 +316,8 @@ static inline void numa_default_policy(void) } static inline void mpol_rebind_task(struct task_struct *tsk, - const nodemask_t *new) + const nodemask_t *new, + enum mpol_rebind_step step) { } -- cgit v1.2.3 From c0ff7453bb5c7c98e0885fb94279f2571946f280 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Mon, 24 May 2010 14:32:08 -0700 Subject: cpuset,mm: fix no node to alloc memory when changing cpuset's mems Before applying this patch, cpuset updates task->mems_allowed and mempolicy by setting all new bits in the nodemask first, and clearing all old unallowed bits later. But in the way, the allocator may find that there is no node to alloc memory. The reason is that cpuset rebinds the task's mempolicy, it cleans the nodes which the allocater can alloc pages on, for example: (mpol: mempolicy) task1 task1's mpol task2 alloc page 1 alloc on node0? NO 1 1 change mems from 1 to 0 1 rebind task1's mpol 0-1 set new bits 0 clear disallowed bits alloc on node1? NO 0 ... can't alloc page goto oom This patch fixes this problem by expanding the nodes range first(set newly allowed bits) and shrink it lazily(clear newly disallowed bits). So we use a variable to tell the write-side task that read-side task is reading nodemask, and the write-side task clears newly disallowed nodes after read-side task ends the current memory allocation. [akpm@linux-foundation.org: fix spello] Signed-off-by: Miao Xie Cc: David Rientjes Cc: Nick Piggin Cc: Paul Menage Cc: Lee Schermerhorn Cc: Hugh Dickins Cc: Ravikiran Thirumalai Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 43 +++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 1 + 2 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index a73454aec333..20b51cab6593 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -86,9 +86,44 @@ extern void rebuild_sched_domains(void); extern void cpuset_print_task_mems_allowed(struct task_struct *p); +/* + * reading current mems_allowed and mempolicy in the fastpath must protected + * by get_mems_allowed() + */ +static inline void get_mems_allowed(void) +{ + current->mems_allowed_change_disable++; + + /* + * ensure that reading mems_allowed and mempolicy happens after the + * update of ->mems_allowed_change_disable. + * + * the write-side task finds ->mems_allowed_change_disable is not 0, + * and knows the read-side task is reading mems_allowed or mempolicy, + * so it will clear old bits lazily. + */ + smp_mb(); +} + +static inline void put_mems_allowed(void) +{ + /* + * ensure that reading mems_allowed and mempolicy before reducing + * mems_allowed_change_disable. + * + * the write-side task will know that the read-side task is still + * reading mems_allowed or mempolicy, don't clears old bits in the + * nodemask. + */ + smp_mb(); + --ACCESS_ONCE(current->mems_allowed_change_disable); +} + static inline void set_mems_allowed(nodemask_t nodemask) { + task_lock(current); current->mems_allowed = nodemask; + task_unlock(current); } #else /* !CONFIG_CPUSETS */ @@ -187,6 +222,14 @@ static inline void set_mems_allowed(nodemask_t nodemask) { } +static inline void get_mems_allowed(void) +{ +} + +static inline void put_mems_allowed(void) +{ +} + #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index b55e988988b5..415b8f8a3f45 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1421,6 +1421,7 @@ struct task_struct { #endif #ifdef CONFIG_CPUSETS nodemask_t mems_allowed; /* Protected by alloc_lock */ + int mems_allowed_change_disable; int cpuset_mem_spread_rotor; #endif #ifdef CONFIG_CGROUPS -- cgit v1.2.3 From 3f6c82728f4e31a97c3a1b32abccb512fed0b573 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:17 -0700 Subject: mm: migration: take a reference to the anon_vma before migrating This patchset is a memory compaction mechanism that reduces external fragmentation memory by moving GFP_MOVABLE pages to a fewer number of pageblocks. The term "compaction" was chosen as there are is a number of mechanisms that are not mutually exclusive that can be used to defragment memory. For example, lumpy reclaim is a form of defragmentation as was slub "defragmentation" (really a form of targeted reclaim). Hence, this is called "compaction" to distinguish it from other forms of defragmentation. In this implementation, a full compaction run involves two scanners operating within a zone - a migration and a free scanner. The migration scanner starts at the beginning of a zone and finds all movable pages within one pageblock_nr_pages-sized area and isolates them on a migratepages list. The free scanner begins at the end of the zone and searches on a per-area basis for enough free pages to migrate all the pages on the migratepages list. As each area is respectively migrated or exhausted of free pages, the scanners are advanced one area. A compaction run completes within a zone when the two scanners meet. This method is a bit primitive but is easy to understand and greater sophistication would require maintenance of counters on a per-pageblock basis. This would have a big impact on allocator fast-paths to improve compaction which is a poor trade-off. It also does not try relocate virtually contiguous pages to be physically contiguous. However, assuming transparent hugepages were in use, a hypothetical khugepaged might reuse compaction code to isolate free pages, split them and relocate userspace pages for promotion. Memory compaction can be triggered in one of three ways. It may be triggered explicitly by writing any value to /proc/sys/vm/compact_memory and compacting all of memory. It can be triggered on a per-node basis by writing any value to /sys/devices/system/node/nodeN/compact where N is the node ID to be compacted. When a process fails to allocate a high-order page, it may compact memory in an attempt to satisfy the allocation instead of entering direct reclaim. Explicit compaction does not finish until the two scanners meet and direct compaction ends if a suitable page becomes available that would meet watermarks. The series is in 14 patches. The first three are not "core" to the series but are important pre-requisites. Patch 1 reference counts anon_vma for rmap_walk_anon(). Without this patch, it's possible to use anon_vma after free if the caller is not holding a VMA or mmap_sem for the pages in question. While there should be no existing user that causes this problem, it's a requirement for memory compaction to be stable. The patch is at the start of the series for bisection reasons. Patch 2 merges the KSM and migrate counts. It could be merged with patch 1 but would be slightly harder to review. Patch 3 skips over unmapped anon pages during migration as there are no guarantees about the anon_vma existing. There is a window between when a page was isolated and migration started during which anon_vma could disappear. Patch 4 notes that PageSwapCache pages can still be migrated even if they are unmapped. Patch 5 allows CONFIG_MIGRATION to be set without CONFIG_NUMA Patch 6 exports a "unusable free space index" via debugfs. It's a measure of external fragmentation that takes the size of the allocation request into account. It can also be calculated from userspace so can be dropped if requested Patch 7 exports a "fragmentation index" which only has meaning when an allocation request fails. It determines if an allocation failure would be due to a lack of memory or external fragmentation. Patch 8 moves the definition for LRU isolation modes for use by compaction Patch 9 is the compaction mechanism although it's unreachable at this point Patch 10 adds a means of compacting all of memory with a proc trgger Patch 11 adds a means of compacting a specific node with a sysfs trigger Patch 12 adds "direct compaction" before "direct reclaim" if it is determined there is a good chance of success. Patch 13 adds a sysctl that allows tuning of the threshold at which the kernel will compact or direct reclaim Patch 14 temporarily disables compaction if an allocation failure occurs after compaction. Testing of compaction was in three stages. For the test, debugging, preempt, the sleep watchdog and lockdep were all enabled but nothing nasty popped out. min_free_kbytes was tuned as recommended by hugeadm to help fragmentation avoidance and high-order allocations. It was tested on X86, X86-64 and PPC64. Ths first test represents one of the easiest cases that can be faced for lumpy reclaim or memory compaction. 1. Machine freshly booted and configured for hugepage usage with a) hugeadm --create-global-mounts b) hugeadm --pool-pages-max DEFAULT:8G c) hugeadm --set-recommended-min_free_kbytes d) hugeadm --set-recommended-shmmax The min_free_kbytes here is important. Anti-fragmentation works best when pageblocks don't mix. hugeadm knows how to calculate a value that will significantly reduce the worst of external-fragmentation-related events as reported by the mm_page_alloc_extfrag tracepoint. 2. Load up memory a) Start updatedb b) Create in parallel a X files of pagesize*128 in size. Wait until files are created. By parallel, I mean that 4096 instances of dd were launched, one after the other using &. The crude objective being to mix filesystem metadata allocations with the buffer cache. c) Delete every second file so that pageblocks are likely to have holes d) kill updatedb if it's still running At this point, the system is quiet, memory is full but it's full with clean filesystem metadata and clean buffer cache that is unmapped. This is readily migrated or discarded so you'd expect lumpy reclaim to have no significant advantage over compaction but this is at the POC stage. 3. In increments, attempt to allocate 5% of memory as hugepages. Measure how long it took, how successful it was, how many direct reclaims took place and how how many compactions. Note the compaction figures might not fully add up as compactions can take place for orders other than the hugepage size X86 vanilla compaction Final page count 913 916 (attempted 1002) pages reclaimed 68296 9791 X86-64 vanilla compaction Final page count: 901 902 (attempted 1002) Total pages reclaimed: 112599 53234 PPC64 vanilla compaction Final page count: 93 94 (attempted 110) Total pages reclaimed: 103216 61838 There was not a dramatic improvement in success rates but it wouldn't be expected in this case either. What was important is that fewer pages were reclaimed in all cases reducing the amount of IO required to satisfy a huge page allocation. The second tests were all performance related - kernbench, netperf, iozone and sysbench. None showed anything too remarkable. The last test was a high-order allocation stress test. Many kernel compiles are started to fill memory with a pressured mix of unmovable and movable allocations. During this, an attempt is made to allocate 90% of memory as huge pages - one at a time with small delays between attempts to avoid flooding the IO queue. vanilla compaction Percentage of request allocated X86 98 99 Percentage of request allocated X86-64 95 98 Percentage of request allocated PPC64 55 70 This patch: rmap_walk_anon() does not use page_lock_anon_vma() for looking up and locking an anon_vma and it does not appear to have sufficient locking to ensure the anon_vma does not disappear from under it. This patch copies an approach used by KSM to take a reference on the anon_vma while pages are being migrated. This should prevent rmap_walk() running into nasty surprises later because anon_vma has been freed. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Cc: Minchan Kim Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index d25bd224d370..567d43f29a10 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -28,6 +28,9 @@ struct anon_vma { spinlock_t lock; /* Serialize access to vma list */ #ifdef CONFIG_KSM atomic_t ksm_refcount; +#endif +#ifdef CONFIG_MIGRATION + atomic_t migrate_refcount; #endif /* * NOTE: the LSB of the head.next is set by @@ -81,6 +84,26 @@ static inline int ksm_refcount(struct anon_vma *anon_vma) return 0; } #endif /* CONFIG_KSM */ +#ifdef CONFIG_MIGRATION +static inline void migrate_refcount_init(struct anon_vma *anon_vma) +{ + atomic_set(&anon_vma->migrate_refcount, 0); +} + +static inline int migrate_refcount(struct anon_vma *anon_vma) +{ + return atomic_read(&anon_vma->migrate_refcount); +} +#else +static inline void migrate_refcount_init(struct anon_vma *anon_vma) +{ +} + +static inline int migrate_refcount(struct anon_vma *anon_vma) +{ + return 0; +} +#endif /* CONFIG_MIGRATE */ static inline struct anon_vma *page_anon_vma(struct page *page) { -- cgit v1.2.3 From 7f60c214fd3a360461f3286c6908084f7f8b1950 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:18 -0700 Subject: mm: migration: share the anon_vma ref counts between KSM and page migration For clarity of review, KSM and page migration have separate refcounts on the anon_vma. While clear, this is a waste of memory. This patch gets KSM and page migration to share their toys in a spirit of harmony. Signed-off-by: Mel Gorman Reviewed-by: Minchan Kim Reviewed-by: KOSAKI Motohiro Reviewed-by: Christoph Lameter Reviewed-by: KAMEZAWA Hiroyuki Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 50 ++++++++++++++++++-------------------------------- 1 file changed, 18 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 567d43f29a10..77216742c178 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -26,11 +26,17 @@ */ struct anon_vma { spinlock_t lock; /* Serialize access to vma list */ -#ifdef CONFIG_KSM - atomic_t ksm_refcount; -#endif -#ifdef CONFIG_MIGRATION - atomic_t migrate_refcount; +#if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION) + + /* + * The external_refcount is taken by either KSM or page migration + * to take a reference to an anon_vma when there is no + * guarantee that the vma of page tables will exist for + * the duration of the operation. A caller that takes + * the reference is responsible for clearing up the + * anon_vma if they are the last user on release + */ + atomic_t external_refcount; #endif /* * NOTE: the LSB of the head.next is set by @@ -64,46 +70,26 @@ struct anon_vma_chain { }; #ifdef CONFIG_MMU -#ifdef CONFIG_KSM -static inline void ksm_refcount_init(struct anon_vma *anon_vma) +#if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION) +static inline void anonvma_external_refcount_init(struct anon_vma *anon_vma) { - atomic_set(&anon_vma->ksm_refcount, 0); + atomic_set(&anon_vma->external_refcount, 0); } -static inline int ksm_refcount(struct anon_vma *anon_vma) +static inline int anonvma_external_refcount(struct anon_vma *anon_vma) { - return atomic_read(&anon_vma->ksm_refcount); + return atomic_read(&anon_vma->external_refcount); } #else -static inline void ksm_refcount_init(struct anon_vma *anon_vma) +static inline void anonvma_external_refcount_init(struct anon_vma *anon_vma) { } -static inline int ksm_refcount(struct anon_vma *anon_vma) +static inline int anonvma_external_refcount(struct anon_vma *anon_vma) { return 0; } #endif /* CONFIG_KSM */ -#ifdef CONFIG_MIGRATION -static inline void migrate_refcount_init(struct anon_vma *anon_vma) -{ - atomic_set(&anon_vma->migrate_refcount, 0); -} - -static inline int migrate_refcount(struct anon_vma *anon_vma) -{ - return atomic_read(&anon_vma->migrate_refcount); -} -#else -static inline void migrate_refcount_init(struct anon_vma *anon_vma) -{ -} - -static inline int migrate_refcount(struct anon_vma *anon_vma) -{ - return 0; -} -#endif /* CONFIG_MIGRATE */ static inline struct anon_vma *page_anon_vma(struct page *page) { -- cgit v1.2.3 From a8bef8ff6ea15fa4c67433cab0f5f3484574ef7c Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:24 -0700 Subject: mm: migration: avoid race between shift_arg_pages() and rmap_walk() during migration by not migrating temporary stacks Page migration requires rmap to be able to find all ptes mapping a page at all times, otherwise the migration entry can be instantiated, but it is possible to leave one behind if the second rmap_walk fails to find the page. If this page is later faulted, migration_entry_to_page() will call BUG because the page is locked indicating the page was migrated by the migration PTE not cleaned up. For example kernel BUG at include/linux/swapops.h:105! invalid opcode: 0000 [#1] PREEMPT SMP ... Call Trace: [] handle_mm_fault+0x3f8/0x76a [] do_page_fault+0x44a/0x46e [] page_fault+0x25/0x30 [] load_elf_binary+0x152a/0x192b [] search_binary_handler+0x173/0x313 [] do_execve+0x219/0x30a [] sys_execve+0x43/0x5e [] stub_execve+0x6a/0xc0 RIP [] migration_entry_wait+0xc1/0x129 There is a race between shift_arg_pages and migration that triggers this bug. A temporary stack is setup during exec and later moved. If migration moves a page in the temporary stack and the VMA is then removed before migration completes, the migration PTE may not be found leading to a BUG when the stack is faulted. This patch causes pages within the temporary stack during exec to be skipped by migration. It does this by marking the VMA covering the temporary stack with an otherwise impossible combination of VMA flags. These flags are cleared when the temporary stack is moved to its final location. [kamezawa.hiroyu@jp.fujitsu.com: idea for having migration skip temporary stacks] Signed-off-by: Mel Gorman Reviewed-by: KAMEZAWA Hiroyuki Reviewed-by: Rik van Riel Acked-by: Linus Torvalds Cc: Minchan Kim Cc: Christoph Lameter Cc: Andrea Arcangeli Cc: Rik van Riel Cc: Peter Zijlstra Reviewed-by: KOSAKI Motohiro 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 fb19bb92b809..98ea5bab963e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -106,6 +106,9 @@ extern unsigned int kobjsize(const void *objp); #define VM_PFN_AT_MMAP 0x40000000 /* PFNMAP vma that is fully mapped at mmap time */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ +/* Bits set in the VMA until the stack is in its final location */ +#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) + #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS #endif -- cgit v1.2.3 From c175a0ce7584e5b498fff8cbdb9aa7912aa9fbba Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:26 -0700 Subject: mm: move definition for LRU isolation modes to a header Currently, vmscan.c defines the isolation modes for __isolate_lru_page(). Memory compaction needs access to these modes for isolating pages for migration. This patch exports them. Signed-off-by: Mel Gorman Acked-by: Christoph Lameter Cc: Rik van Riel Cc: Minchan Kim Cc: KOSAKI Motohiro Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 600b03b7732e..1e8ce148d058 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -229,6 +229,11 @@ static inline void lru_cache_add_file(struct page *page) __lru_cache_add(page, LRU_INACTIVE_FILE); } +/* LRU Isolation modes. */ +#define ISOLATE_INACTIVE 0 /* Isolate inactive pages. */ +#define ISOLATE_ACTIVE 1 /* Isolate active pages. */ +#define ISOLATE_BOTH 2 /* Isolate both active and inactive pages. */ + /* linux/mm/vmscan.c */ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); -- cgit v1.2.3 From 748446bb6b5a9390b546af38ec899c868a9dbcf0 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:27 -0700 Subject: mm: compaction: memory compaction core This patch is the core of a mechanism which compacts memory in a zone by relocating movable pages towards the end of the zone. A single compaction run involves a migration scanner and a free scanner. Both scanners operate on pageblock-sized areas in the zone. The migration scanner starts at the bottom of the zone and searches for all movable pages within each area, isolating them onto a private list called migratelist. The free scanner starts at the top of the zone and searches for suitable areas and consumes the free pages within making them available for the migration scanner. The pages isolated for migration are then migrated to the newly isolated free pages. [aarcange@redhat.com: Fix unsafe optimisation] [mel@csn.ul.ie: do not schedule work on other CPUs for compaction] Signed-off-by: Mel Gorman Acked-by: Rik van Riel Reviewed-by: Minchan Kim Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 9 +++++++++ include/linux/migrate.h | 2 ++ include/linux/mm.h | 1 + include/linux/swap.h | 1 + include/linux/vmstat.h | 3 +++ 5 files changed, 16 insertions(+) create mode 100644 include/linux/compaction.h (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h new file mode 100644 index 000000000000..465ca88615ed --- /dev/null +++ b/include/linux/compaction.h @@ -0,0 +1,9 @@ +#ifndef _LINUX_COMPACTION_H +#define _LINUX_COMPACTION_H + +/* Return values for compact_zone() */ +#define COMPACT_CONTINUE 0 +#define COMPACT_PARTIAL 1 +#define COMPACT_COMPLETE 2 + +#endif /* _LINUX_COMPACTION_H */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 7a07b17d27c5..7238231b8dd4 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -19,6 +19,7 @@ extern int fail_migrate_page(struct address_space *, struct page *, struct page *); extern int migrate_prep(void); +extern int migrate_prep_local(void); extern int migrate_vmas(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, unsigned long flags); @@ -30,6 +31,7 @@ static inline int migrate_pages(struct list_head *l, new_page_t x, unsigned long private, int offlining) { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } +static inline int migrate_prep_local(void) { return -ENOSYS; } static inline int migrate_vmas(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, diff --git a/include/linux/mm.h b/include/linux/mm.h index 98ea5bab963e..963f908af9d0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -337,6 +337,7 @@ void put_page(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); +int split_free_page(struct page *page); /* * Compound pages have a destructor function. Provide a diff --git a/include/linux/swap.h b/include/linux/swap.h index 1e8ce148d058..b6b614364dd8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -152,6 +152,7 @@ enum { }; #define SWAP_CLUSTER_MAX 32 +#define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX #define SWAP_MAP_MAX 0x3e /* Max duplication count, in first swap_map */ #define SWAP_MAP_BAD 0x3f /* Note pageblock is bad, in first swap_map */ diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 117f0dd8ad03..b421d1b22b62 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -43,6 +43,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY, KSWAPD_SKIP_CONGESTION_WAIT, PAGEOUTRUN, ALLOCSTALL, PGROTATED, +#ifdef CONFIG_COMPACTION + COMPACTBLOCKS, COMPACTPAGES, COMPACTPAGEFAILED, +#endif #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, #endif -- cgit v1.2.3 From 76ab0f530e4a01d4dc20cdc1d5e87753c579dc18 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:28 -0700 Subject: mm: compaction: add /proc trigger for memory compaction Add a proc file /proc/sys/vm/compact_memory. When an arbitrary value is written to the file, all zones are compacted. The expected user of such a trigger is a job scheduler that prepares the system before the target application runs. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Reviewed-by: KAMEZAWA Hiroyuki Reviewed-by: Minchan Kim Reviewed-by: KOSAKI Motohiro Reviewed-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 465ca88615ed..572388880ba8 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -6,4 +6,10 @@ #define COMPACT_PARTIAL 1 #define COMPACT_COMPLETE 2 +#ifdef CONFIG_COMPACTION +extern int sysctl_compact_memory; +extern int sysctl_compaction_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos); +#endif /* CONFIG_COMPACTION */ + #endif /* _LINUX_COMPACTION_H */ -- cgit v1.2.3 From ed4a6d7f0676db50b5023cc01f6cda82a2f2a307 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:29 -0700 Subject: mm: compaction: add /sys trigger for per-node memory compaction Add a per-node sysfs file called compact. When the file is written to, each zone in that node is compacted. The intention that this would be used by something like a job scheduler in a batch system before a job starts so that the job can allocate the maximum number of hugepages without significant start-up cost. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Reviewed-by: KOSAKI Motohiro Reviewed-by: Christoph Lameter Reviewed-by: Minchan Kim Reviewed-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 572388880ba8..ba98cfe0ae15 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -12,4 +12,20 @@ extern int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); #endif /* CONFIG_COMPACTION */ +#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) +extern int compaction_register_node(struct node *node); +extern void compaction_unregister_node(struct node *node); + +#else + +static inline int compaction_register_node(struct node *node) +{ + return 0; +} + +static inline void compaction_unregister_node(struct node *node) +{ +} +#endif /* CONFIG_COMPACTION && CONFIG_SYSFS && CONFIG_NUMA */ + #endif /* _LINUX_COMPACTION_H */ -- cgit v1.2.3 From 56de7263fcf3eb10c8dcdf8d59a9cec831795f3f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:30 -0700 Subject: mm: compaction: direct compact when a high-order allocation fails Ordinarily when a high-order allocation fails, direct reclaim is entered to free pages to satisfy the allocation. With this patch, it is determined if an allocation failed due to external fragmentation instead of low memory and if so, the calling process will compact until a suitable page is freed. Compaction by moving pages in memory is considerably cheaper than paging out to disk and works where there are locked pages or no swap. If compaction fails to free a page of a suitable size, then reclaim will still occur. Direct compaction returns as soon as possible. As each block is compacted, it is checked if a suitable page has been freed and if so, it returns. [akpm@linux-foundation.org: Fix build errors] [aarcange@redhat.com: fix count_vm_event preempt in memory compaction direct reclaim] Signed-off-by: Mel Gorman Acked-by: Rik van Riel Reviewed-by: Minchan Kim Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 24 ++++++++++++++++++++---- include/linux/vmstat.h | 1 + 2 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index ba98cfe0ae15..eed40ec4280b 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -1,15 +1,31 @@ #ifndef _LINUX_COMPACTION_H #define _LINUX_COMPACTION_H -/* Return values for compact_zone() */ -#define COMPACT_CONTINUE 0 -#define COMPACT_PARTIAL 1 -#define COMPACT_COMPLETE 2 +/* Return values for compact_zone() and try_to_compact_pages() */ +/* compaction didn't start as it was not possible or direct reclaim was more suitable */ +#define COMPACT_SKIPPED 0 +/* compaction should continue to another pageblock */ +#define COMPACT_CONTINUE 1 +/* direct compaction partially compacted a zone and there are suitable pages */ +#define COMPACT_PARTIAL 2 +/* The full zone was compacted */ +#define COMPACT_COMPLETE 3 #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); + +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); +#else +static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, + int order, gfp_t gfp_mask, nodemask_t *nodemask) +{ + return COMPACT_CONTINUE; +} + #endif /* CONFIG_COMPACTION */ #if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index b421d1b22b62..7f43ccdc1d38 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -45,6 +45,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PAGEOUTRUN, ALLOCSTALL, PGROTATED, #ifdef CONFIG_COMPACTION COMPACTBLOCKS, COMPACTPAGES, COMPACTPAGEFAILED, + COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS, #endif #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, -- cgit v1.2.3 From 5e7719058079a1423ccce56148b0aaa56b2df821 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:31 -0700 Subject: mm: compaction: add a tunable that decides when memory should be compacted and when it should be reclaimed The kernel applies some heuristics when deciding if memory should be compacted or reclaimed to satisfy a high-order allocation. One of these is based on the fragmentation. If the index is below 500, memory will not be compacted. This choice is arbitrary and not based on data. To help optimise the system and set a sensible default for this value, this patch adds a sysctl extfrag_threshold. The kernel will only compact memory if the fragmentation index is above the extfrag_threshold. [randy.dunlap@oracle.com: Fix build errors when proc fs is not configured] Signed-off-by: Mel Gorman Signed-off-by: Randy Dunlap Cc: Rik van Riel Cc: Minchan Kim Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index eed40ec4280b..3719325c6091 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -15,6 +15,9 @@ extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); +extern int sysctl_extfrag_threshold; +extern int sysctl_extfrag_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos); extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, -- cgit v1.2.3 From 4f92e2586b43a2402e116055d4edda704f911b5b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:32 -0700 Subject: mm: compaction: defer compaction using an exponential backoff when compaction fails The fragmentation index may indicate that a failure is due to external fragmentation but after a compaction run completes, it is still possible for an allocation to fail. There are two obvious reasons as to why o Page migration cannot move all pages so fragmentation remains o A suitable page may exist but watermarks are not met In the event of compaction followed by an allocation failure, this patch defers further compaction in the zone (1 << compact_defer_shift) times. If the next compaction attempt also fails, compact_defer_shift is increased up to a maximum of 6. If compaction succeeds, the defer counters are reset again. The zone that is deferred is the first zone in the zonelist - i.e. the preferred zone. To defer compaction in the other zones, the information would need to be stored in the zonelist or implemented similar to the zonelist_cache. This would impact the fast-paths and is not justified at this time. Signed-off-by: Mel Gorman Cc: Rik van Riel Cc: Minchan Kim Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 39 +++++++++++++++++++++++++++++++++++++++ include/linux/mmzone.h | 9 +++++++++ 2 files changed, 48 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 3719325c6091..5ac51552d908 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -22,6 +22,36 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, 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); + +/* Do not skip compaction more than 64 times */ +#define COMPACT_MAX_DEFER_SHIFT 6 + +/* + * Compaction is deferred when compaction fails to result in a page + * allocation success. 1 << compact_defer_limit compactions are skipped up + * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT + */ +static inline void defer_compaction(struct zone *zone) +{ + zone->compact_considered = 0; + zone->compact_defer_shift++; + + if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT) + zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT; +} + +/* Returns true if compaction should be skipped this time */ +static inline bool compaction_deferred(struct zone *zone) +{ + unsigned long defer_limit = 1UL << zone->compact_defer_shift; + + /* Avoid possible overflow */ + if (++zone->compact_considered > defer_limit) + zone->compact_considered = defer_limit; + + return zone->compact_considered < (1UL << zone->compact_defer_shift); +} + #else static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) @@ -29,6 +59,15 @@ static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, return COMPACT_CONTINUE; } +static inline void defer_compaction(struct zone *zone) +{ +} + +static inline bool compaction_deferred(struct zone *zone) +{ + return 1; +} + #endif /* CONFIG_COMPACTION */ #if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index cf9e458e96b0..fd55f725a09e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -321,6 +321,15 @@ struct zone { unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ +#ifdef CONFIG_COMPACTION + /* + * On compaction failure, 1< Date: Mon, 24 May 2010 14:32:40 -0700 Subject: vmscan: remove isolate_pages callback scan control For now, we have global isolation vs. memory control group isolation, do not allow the reclaim entry function to set an arbitrary page isolation callback, we do not need that flexibility. And since we already pass around the group descriptor for the memory control group isolation case, just use it to decide which one of the two isolator functions to use. The decisions can be merged into nearby branches, so no extra cost there. In fact, we save the indirect calls. Signed-off-by: Johannes Weiner Cc: KOSAKI Motohiro Cc: Mel Gorman Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 44301c6affa8..05894795fdc1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -25,6 +25,13 @@ struct page_cgroup; struct page; struct mm_struct; +extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, + struct list_head *dst, + unsigned long *scanned, int order, + int mode, struct zone *z, + struct mem_cgroup *mem_cont, + int active, int file); + #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* * All "charge" functions with gfp_mask should use GFP_KERNEL or @@ -64,12 +71,6 @@ extern void mem_cgroup_uncharge_cache_page(struct page *page); extern int mem_cgroup_shmem_charge_fallback(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); -extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, - struct list_head *dst, - unsigned long *scanned, int order, - int mode, struct zone *z, - struct mem_cgroup *mem_cont, - int active, int file); extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask); int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem); -- cgit v1.2.3 From cf23422b9d76215316855253da491d4c9f294372 Mon Sep 17 00:00:00 2001 From: minskey guo Date: Mon, 24 May 2010 14:32:41 -0700 Subject: cpu/mem hotplug: enable CPUs online before local memory online Enable users to online CPUs even if the CPUs belongs to a numa node which doesn't have onlined local memory. The zonlists(pg_data_t.node_zonelists[]) of a numa node are created either in system boot/init period, or at the time of local memory online. For a numa node without onlined local memory, its zonelists are not initialized at present. As a result, any memory allocation operations executed by CPUs within this node will fail. In fact, an out-of-memory error is triggered when attempt to online CPUs before memory comes to online. This patch tries to create zonelists for such numa nodes, so that the memory allocation for this node can be fallback'ed to other nodes. [akpm@linux-foundation.org: remove unneeded export] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: minskey guo Cc: Minchan Kim Cc: Yasunori Goto Cc: Andi Kleen Cc: Christoph Lameter Cc: Tejun Heo 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 35b07b773e6c..864035fb8f8a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -202,6 +202,7 @@ static inline int is_mem_section_removable(unsigned long pfn, } #endif /* CONFIG_MEMORY_HOTREMOVE */ +extern int mem_online_node(int nid); extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int remove_memory(u64 start, u64 size); -- cgit v1.2.3 From 263ff5d8e82e577202d2b8393585b0e2436b7ffc Mon Sep 17 00:00:00 2001 From: matt mooney Date: Mon, 24 May 2010 14:32:44 -0700 Subject: include/linux/gfp.h: spelling fixes Fix minor spelling errors in a few comments; no code changes. Signed-off-by: matt mooney Cc: Dan Carpenter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 4c6d41333f98..474887eac51f 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -15,7 +15,7 @@ struct vm_area_struct; * Zone modifiers (see linux/mmzone.h - low three bits) * * Do not put any conditional on these. If necessary modify the definitions - * without the underscores and use the consistently. The definitions here may + * without the underscores and use them consistently. The definitions here may * be used in bit comparisons. */ #define __GFP_DMA ((__force gfp_t)0x01u) @@ -152,12 +152,12 @@ static inline int allocflags_to_migratetype(gfp_t gfp_flags) * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the * zone to use given the lowest 4 bits of gfp_t. Entries are ZONE_SHIFT long * and there are 16 of them to cover all possible combinations of - * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM + * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM. * * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA. * But GFP_MOVABLE is not only a zone specifier but also an allocation * policy. Therefore __GFP_MOVABLE plus another zone selector is valid. - * Only 1bit of the lowest 3 bit (DMA,DMA32,HIGHMEM) can be set to "1". + * Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1". * * bit result * ================= @@ -197,7 +197,7 @@ static inline int allocflags_to_migratetype(gfp_t gfp_flags) ) /* - * GFP_ZONE_BAD is a bitmap for all combination of __GFP_DMA, __GFP_DMA32 + * GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32 * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per * entry starting with bit 0. Bit is set if the combination is not * allowed. -- cgit v1.2.3 From fd23855e38d2a7275a786238459c070b4e9f7975 Mon Sep 17 00:00:00 2001 From: matt mooney Date: Mon, 24 May 2010 14:32:45 -0700 Subject: include/linux/gfp.h: fix coding style Add parenthesis in a define. This doesn't change functionality. checkpatch errors: 1) white space fixes 2) add spaces after comas Signed-off-by: matt mooney Cc: Dan Carpenter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 474887eac51f..975609cb8548 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -101,7 +101,7 @@ struct vm_area_struct; __GFP_NORETRY|__GFP_NOMEMALLOC) /* Control slab gfp mask during early boot */ -#define GFP_BOOT_MASK __GFP_BITS_MASK & ~(__GFP_WAIT|__GFP_IO|__GFP_FS) +#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_WAIT|__GFP_IO|__GFP_FS)) /* Control allocation constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) @@ -187,7 +187,7 @@ static inline int allocflags_to_migratetype(gfp_t gfp_flags) #define GFP_ZONE_TABLE ( \ (ZONE_NORMAL << 0 * ZONES_SHIFT) \ - | (OPT_ZONE_DMA << __GFP_DMA * ZONES_SHIFT) \ + | (OPT_ZONE_DMA << __GFP_DMA * ZONES_SHIFT) \ | (OPT_ZONE_HIGHMEM << __GFP_HIGHMEM * ZONES_SHIFT) \ | (OPT_ZONE_DMA32 << __GFP_DMA32 * ZONES_SHIFT) \ | (ZONE_NORMAL << __GFP_MOVABLE * ZONES_SHIFT) \ @@ -320,17 +320,17 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask); void free_pages_exact(void *virt, size_t size); #define __get_free_page(gfp_mask) \ - __get_free_pages((gfp_mask),0) + __get_free_pages((gfp_mask), 0) #define __get_dma_pages(gfp_mask, order) \ - __get_free_pages((gfp_mask) | GFP_DMA,(order)) + __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); extern void free_hot_cold_page(struct page *page, int cold); #define __free_page(page) __free_pages((page), 0) -#define free_page(addr) free_pages((addr),0) +#define free_page(addr) free_pages((addr), 0) void page_alloc_init(void); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); -- cgit v1.2.3 From ff3d58c22b6827039983911d3460cf0c1657f8cc Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Mon, 24 May 2010 14:32:46 -0700 Subject: highmem: remove unneeded #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT for debug_kmap_atomic() In f4112de6b679d84bd9b9681c7504be7bdfb7c7d5 ("mm: introduce debug_kmap_atomic") I said that debug_kmap_atomic() needs CONFIG_TRACE_IRQFLAGS_SUPPORT. It was wrong. (I thought irqs_disabled() is only available when the architecture has CONFIG_TRACE_IRQFLAGS_SUPPORT) Remove the #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT check to enable kmap_atomic() debugging for the architectures which do not have CONFIG_TRACE_IRQFLAGS_SUPPORT. Reported-by: Andrew Morton Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 74152c08ad07..caafd0561aa1 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -27,7 +27,7 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #include -#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT) +#ifdef CONFIG_DEBUG_HIGHMEM void debug_kmap_atomic(enum km_type type); -- cgit v1.2.3 From 0faa56389c793cda7f967117415717bbab24fe4e Mon Sep 17 00:00:00 2001 From: Marcelo Roberto Jimenez Date: Mon, 24 May 2010 14:32:47 -0700 Subject: mm: fix NR_SECTION_ROOTS == 0 when using using sparsemem extreme. Got this while compiling for ARM/SA1100: mm/sparse.c: In function '__section_nr': mm/sparse.c:135: warning: 'root' is used uninitialized in this function This patch follows Russell King's suggestion for a new calculation for NR_SECTION_ROOTS. Thanks also to Sergei Shtylyov for pointing out the existence of the macro DIV_ROUND_UP. Atsushi Nemoto observed: : This fix doesn't just silence the warning - it fixes a real problem. : : Without this fix, mem_section[] might have 0 size so mem_section[0] : will share other variable area. For example, I got: : : c030c700 b __warned.16478 : c030c700 B mem_section : c030c701 b __warned.16483 : : This might cause very strange behavior. Your patch actually fixes it. Signed-off-by: Marcelo Roberto Jimenez Cc: Atsushi Nemoto Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: Mel Gorman Cc: Minchan Kim Cc: Yinghai Lu Cc: Sergei Shtylyov Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fd55f725a09e..f6f2c505fa7e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -981,7 +981,7 @@ struct mem_section { #endif #define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) -#define NR_SECTION_ROOTS (NR_MEM_SECTIONS / SECTIONS_PER_ROOT) +#define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT) #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME -- cgit v1.2.3 From 1f522509c77a5dea8dc384b735314f03908a6415 Mon Sep 17 00:00:00 2001 From: Haicheng Li Date: Mon, 24 May 2010 14:32:51 -0700 Subject: mem-hotplug: avoid multiple zones sharing same boot strapping boot_pageset For each new populated zone of hotadded node, need to update its pagesets with dynamically allocated per_cpu_pageset struct for all possible CPUs: 1) Detach zone->pageset from the shared boot_pageset at end of __build_all_zonelists(). 2) Use mutex to protect zone->pageset when it's still shared in onlined_pages() Otherwises, multiple zones of different nodes would share same boot strapping boot_pageset for same CPU, which will finally cause below kernel panic: ------------[ cut here ]------------ kernel BUG at mm/page_alloc.c:1239! invalid opcode: 0000 [#1] SMP ... Call Trace: [] __alloc_pages_nodemask+0x131/0x7b0 [] alloc_pages_current+0x87/0xd0 [] __page_cache_alloc+0x67/0x70 [] __do_page_cache_readahead+0x120/0x260 [] ra_submit+0x21/0x30 [] ondemand_readahead+0x166/0x2c0 [] page_cache_async_readahead+0x80/0xa0 [] generic_file_aio_read+0x364/0x670 [] nfs_file_read+0xca/0x130 [] do_sync_read+0xfa/0x140 [] vfs_read+0xb5/0x1a0 [] sys_read+0x51/0x80 [] system_call_fastpath+0x16/0x1b RIP [] get_page_from_freelist+0x883/0x900 RSP ---[ end trace 4bda28328b9990db ] [akpm@linux-foundation.org: merge fix] Signed-off-by: Haicheng Li Signed-off-by: Wu Fengguang Reviewed-by: Andi Kleen Reviewed-by: Christoph Lameter Cc: Mel Gorman Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f6f2c505fa7e..a367ed5bb3fe 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -652,7 +652,7 @@ typedef struct pglist_data { void get_zone_counts(unsigned long *active, unsigned long *inactive, unsigned long *free); -void build_all_zonelists(void); +void build_all_zonelists(void *data); void wakeup_kswapd(struct zone *zone, int order); int zone_watermark_ok(struct zone *z, int order, unsigned long mark, int classzone_idx, int alloc_flags); -- cgit v1.2.3 From 4eaf3f64397c3db3c5785eee508270d62a9fabd9 Mon Sep 17 00:00:00 2001 From: Haicheng Li Date: Mon, 24 May 2010 14:32:52 -0700 Subject: mem-hotplug: fix potential race while building zonelist for new populated zone Add global mutex zonelists_mutex to fix the possible race: CPU0 CPU1 CPU2 (1) zone->present_pages += online_pages; (2) build_all_zonelists(); (3) alloc_page(); (4) free_page(); (5) build_all_zonelists(); (6) __build_all_zonelists(); (7) zone->pageset = alloc_percpu(); In step (3,4), zone->pageset still points to boot_pageset, so bad things may happen if 2+ nodes are in this state. Even if only 1 node is accessing the boot_pageset, (3) may still consume too much memory to fail the memory allocations in step (7). Besides, atomic operation ensures alloc_percpu() in step (7) will never fail since there is a new fresh memory block added in step(6). [haicheng.li@linux.intel.com: hold zonelists_mutex when build_all_zonelists] Signed-off-by: Haicheng Li Signed-off-by: Wu Fengguang Reviewed-by: Andi Kleen Cc: Christoph Lameter Cc: Mel Gorman Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index a367ed5bb3fe..0fa491326c4a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -650,6 +650,7 @@ typedef struct pglist_data { #include +extern struct mutex zonelists_mutex; void get_zone_counts(unsigned long *active, unsigned long *inactive, unsigned long *free); void build_all_zonelists(void *data); -- cgit v1.2.3 From c6f6b596a5a73e63e5e930c414375c0c389199ab Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Mon, 24 May 2010 14:32:53 -0700 Subject: mm: make lowmem_page_address() use PFN_PHYS() for improved portability This ensures that platforms with lowmem PAs above 32 bits work correctly by avoiding truncating the PA during a left shift. Signed-off-by: Chris Metcalf Cc: Barry Song <21cnbao@gmail.com> Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 963f908af9d0..b969efb03787 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -13,6 +13,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -595,7 +596,7 @@ static inline void set_page_links(struct page *page, enum zone_type zone, static __always_inline void *lowmem_page_address(struct page *page) { - return __va(page_to_pfn(page) << PAGE_SHIFT); + return __va(PFN_PHYS(page_to_pfn(page))); } #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) -- cgit v1.2.3 From e47103b1af5df52fa69e18b14d3012472f78817d Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Mon, 24 May 2010 14:33:00 -0700 Subject: err.h: add __must_check to error pointer handlers Add __must_check to error pointer handlers to have the compiler warn about mistakes like: if (err) ERR_PTR(err); It found two bugs: Mar 12 Nikula Jani [PATCH] enclosure: fix error path - actually return ERR_PTR() on error Mar 12 Nikula Jani [PATCH] sunrpc: fix error path - actually return ERR_PTR() on error Signed-off-by: Jani Nikula Cc: Phil Carmody Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/err.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/err.h b/include/linux/err.h index 1b12642636c7..448afc12c78a 100644 --- a/include/linux/err.h +++ b/include/linux/err.h @@ -19,22 +19,22 @@ #define IS_ERR_VALUE(x) unlikely((x) >= (unsigned long)-MAX_ERRNO) -static inline void *ERR_PTR(long error) +static inline void * __must_check ERR_PTR(long error) { return (void *) error; } -static inline long PTR_ERR(const void *ptr) +static inline long __must_check PTR_ERR(const void *ptr) { return (long) ptr; } -static inline long IS_ERR(const void *ptr) +static inline long __must_check IS_ERR(const void *ptr) { return IS_ERR_VALUE((unsigned long)ptr); } -static inline long IS_ERR_OR_NULL(const void *ptr) +static inline long __must_check IS_ERR_OR_NULL(const void *ptr) { return !ptr || IS_ERR_VALUE((unsigned long)ptr); } @@ -46,7 +46,7 @@ static inline long IS_ERR_OR_NULL(const void *ptr) * Explicitly cast an error-valued pointer to another pointer type in such a * way as to make it clear that's what's going on. */ -static inline void *ERR_CAST(const void *ptr) +static inline void * __must_check ERR_CAST(const void *ptr) { /* cast away the const */ return (void *) ptr; -- cgit v1.2.3 From b3b77c8caef1750ebeea1054e39e358550ea9f55 Mon Sep 17 00:00:00 2001 From: Joakim Tjernlund Date: Mon, 24 May 2010 14:33:01 -0700 Subject: endian: #define __BYTE_ORDER Linux does not define __BYTE_ORDER in its endian header files which makes some header files bend backwards to get at the current endian. Lets #define __BYTE_ORDER in big_endian.h/litte_endian.h to make it easier for header files that are used in user space too. In userspace the convention is that 1. _both_ __LITTLE_ENDIAN and __BIG_ENDIAN are defined, 2. you have to test for e.g. __BYTE_ORDER == __BIG_ENDIAN. Signed-off-by: Joakim Tjernlund Cc: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/byteorder/big_endian.h | 3 +++ include/linux/byteorder/little_endian.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/byteorder/big_endian.h b/include/linux/byteorder/big_endian.h index 3c80fd7e8b56..d53a67dff018 100644 --- a/include/linux/byteorder/big_endian.h +++ b/include/linux/byteorder/big_endian.h @@ -7,6 +7,9 @@ #ifndef __BIG_ENDIAN_BITFIELD #define __BIG_ENDIAN_BITFIELD #endif +#ifndef __BYTE_ORDER +#define __BYTE_ORDER __BIG_ENDIAN +#endif #include #include diff --git a/include/linux/byteorder/little_endian.h b/include/linux/byteorder/little_endian.h index 83195fb82962..f7f8ad13adb6 100644 --- a/include/linux/byteorder/little_endian.h +++ b/include/linux/byteorder/little_endian.h @@ -7,6 +7,9 @@ #ifndef __LITTLE_ENDIAN_BITFIELD #define __LITTLE_ENDIAN_BITFIELD #endif +#ifndef __BYTE_ORDER +#define __BYTE_ORDER __LITTLE_ENDIAN +#endif #include #include -- cgit v1.2.3 From 4be929be34f9bdeffa40d815d32d7d60d2c7f03b Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 24 May 2010 14:33:03 -0700 Subject: kernel-wide: replace USHORT_MAX, SHORT_MAX and SHORT_MIN with USHRT_MAX, SHRT_MAX and SHRT_MIN - C99 knows about USHRT_MAX/SHRT_MAX/SHRT_MIN, not USHORT_MAX/SHORT_MAX/SHORT_MIN. - Make SHRT_MIN of type s16, not int, for consistency. [akpm@linux-foundation.org: fix drivers/dma/timb_dma.c] [akpm@linux-foundation.org: fix security/keys/keyring.c] Signed-off-by: Alexey Dobriyan Acked-by: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 6 +++--- include/linux/sched.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index cc5e3ffe9fce..a2e7c32e17e7 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -24,9 +24,9 @@ extern const char linux_banner[]; extern const char linux_proc_banner[]; -#define USHORT_MAX ((u16)(~0U)) -#define SHORT_MAX ((s16)(USHORT_MAX>>1)) -#define SHORT_MIN (-SHORT_MAX - 1) +#define USHRT_MAX ((u16)(~0U)) +#define SHRT_MAX ((s16)(USHRT_MAX>>1)) +#define SHRT_MIN ((s16)(-SHRT_MAX - 1)) #define INT_MAX ((int)(~0U>>1)) #define INT_MIN (-INT_MAX - 1) #define UINT_MAX (~0U) diff --git a/include/linux/sched.h b/include/linux/sched.h index 415b8f8a3f45..c0151ffd3541 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -384,7 +384,7 @@ struct user_namespace; * 1-3 now and depends on arch. We use "5" as safe margin, here. */ #define MAPCOUNT_ELF_CORE_MARGIN (5) -#define DEFAULT_MAX_MAP_COUNT (USHORT_MAX - MAPCOUNT_ELF_CORE_MARGIN) +#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) extern int sysctl_max_map_count; -- cgit v1.2.3 From fc62f2f19edf46c9bdbd1a54725b56b18c43e94f Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 24 May 2010 14:33:08 -0700 Subject: kernel.h: add pr_warn for symmetry to dev_warn, netdev_warn The current logging macros are pr_, dev_, netdev_, and netif_. pr_ uses warning, the other use warn. Standardize these logging macros a bit more by adding pr_warn and pr_warn_ratelimited. Right now, there are: $ for level in emerg alert crit err warn warning notice info ; do \ for prefix in pr dev netdev netif ; do \ echo -n "${prefix}_${level}: `git grep -w "${prefix}_${level}" | wc -l` " ; \ done ; \ echo ; \ done pr_emerg: 45 dev_emerg: 4 netdev_emerg: 1 netif_emerg: 4 pr_alert: 24 dev_alert: 36 netdev_alert: 1 netif_alert: 6 pr_crit: 24 dev_crit: 22 netdev_crit: 1 netif_crit: 4 pr_err: 2013 dev_err: 8467 netdev_err: 267 netif_err: 240 pr_warn: 0 dev_warn: 1818 netdev_warn: 126 netif_warn: 23 pr_warning: 773 dev_warning: 0 netdev_warning: 0 netif_warning: 0 pr_notice: 148 dev_notice: 111 netdev_notice: 9 netif_notice: 3 pr_info: 1717 dev_info: 3007 netdev_info: 101 netif_info: 85 Signed-off-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index a2e7c32e17e7..ea8490d7020e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -389,6 +389,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warning(fmt, ...) \ printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warn pr_warning #define pr_notice(fmt, ...) \ printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info(fmt, ...) \ @@ -447,6 +448,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) printk_ratelimited(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warning_ratelimited(fmt, ...) \ printk_ratelimited(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warn_ratelimited pr_warning_ratelimited #define pr_notice_ratelimited(fmt, ...) \ printk_ratelimited(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info_ratelimited(fmt, ...) \ -- cgit v1.2.3 From d8521fcc5e0ad3e79bbc4231bb20a6cdc2b50164 Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Mon, 24 May 2010 14:33:11 -0700 Subject: printk_ratelimited(): fix uninitialized spinlock ratelimit_state initialization of printk_ratelimited() seems broken. This fixes it by using DEFINE_RATELIMIT_STATE() to initialize spinlock properly. Signed-off-by: OGAWA Hirofumi Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index ea8490d7020e..05f332afc9e0 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -424,14 +424,13 @@ static inline char *pack_hex_byte(char *buf, u8 byte) * no local ratelimit_state used in the !PRINTK case */ #ifdef CONFIG_PRINTK -#define printk_ratelimited(fmt, ...) ({ \ - static struct ratelimit_state _rs = { \ - .interval = DEFAULT_RATELIMIT_INTERVAL, \ - .burst = DEFAULT_RATELIMIT_BURST, \ - }; \ - \ - if (__ratelimit(&_rs)) \ - printk(fmt, ##__VA_ARGS__); \ +#define printk_ratelimited(fmt, ...) ({ \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + \ + if (__ratelimit(&_rs)) \ + printk(fmt, ##__VA_ARGS__); \ }) #else /* No effect, but we still get type checking even in the !PRINTK case: */ -- cgit v1.2.3 From f40c396a9ab04eae526990e2b2cef875b424ed4e Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Mon, 24 May 2010 14:33:11 -0700 Subject: ratelimit: add ratelimit_state_init() For now, all users of ratelimit_state allocates it statically, so DEFINE_RATELIMIT_STATE() is enough. But, I want to use ratelimit_state for fs, i.e. per super_block to suppress too many error reports. So, this adds ratelimit_state_init() to initialize ratelimite_state which is dynamically allocated, instead of opencoding. Signed-off-by: OGAWA Hirofumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ratelimit.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h index 668cf1bef030..8f69d09a41a5 100644 --- a/include/linux/ratelimit.h +++ b/include/linux/ratelimit.h @@ -2,7 +2,7 @@ #define _LINUX_RATELIMIT_H #include -#include +#include #define DEFAULT_RATELIMIT_INTERVAL (5 * HZ) #define DEFAULT_RATELIMIT_BURST 10 @@ -25,6 +25,17 @@ struct ratelimit_state { .burst = burst_init, \ } +static inline void ratelimit_state_init(struct ratelimit_state *rs, + int interval, int burst) +{ + spin_lock_init(&rs->lock); + rs->interval = interval; + rs->burst = burst; + rs->printed = 0; + rs->missed = 0; + rs->begin = 0; +} + extern int ___ratelimit(struct ratelimit_state *rs, const char *func); #define __ratelimit(state) ___ratelimit(state, __func__) -- cgit v1.2.3 From 2b2f68b5383ea107295d7f1483256866e2daa1e3 Mon Sep 17 00:00:00 2001 From: Florian Ragwitz Date: Mon, 24 May 2010 14:33:21 -0700 Subject: DYNAMIC_DEBUG: fix documentation errors [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Florian Ragwitz Cc: Jason Baron Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dynamic_debug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index f8c2e1767500..b3cd4de9432b 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -28,7 +28,7 @@ struct _ddebug { /* * The flags field controls the behaviour at the callsite. * The bits here are changed dynamically when the user - * writes commands to /dynamic_debug/ddebug + * writes commands to /dynamic_debug/control */ #define _DPRINTK_FLAGS_PRINT (1<<0) /* printk() a message using the format */ #define _DPRINTK_FLAGS_DEFAULT 0 -- cgit v1.2.3 From 903788892ea0fc7fcaf7e8e5fac9a77379fc215b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 24 May 2010 14:33:23 -0700 Subject: lib: introduce common method to convert hex digits hex_to_bin() is a little method which converts hex digit to its actual value. There are plenty of places where such functionality is needed. [akpm@linux-foundation.org: use tolower(), saving 3 bytes, test the more common case first - it's quicker] [akpm@linux-foundation.org: relocate tolower to make it even faster! (Joe)] Signed-off-by: Andy Shevchenko Cc: Tilman Schmidt Cc: Duncan Sands Cc: Eric W. Biederman Cc: Greg Kroah-Hartman Cc: "Richard Russon (FlatCap)" Cc: John W. Linville Cc: Len Brown Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 05f332afc9e0..8317ec4b9f3b 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -375,6 +375,8 @@ static inline char *pack_hex_byte(char *buf, u8 byte) return buf; } +extern int hex_to_bin(char ch); + #ifndef pr_fmt #define pr_fmt(fmt) fmt #endif -- cgit v1.2.3 From 342c5f128140d54961c435d1702eadcaba97a37a Mon Sep 17 00:00:00 2001 From: Samu Onkalo Date: Mon, 24 May 2010 14:33:35 -0700 Subject: lis3: introduce platform data for second ff / wu unit 8 bit device has two wakeup / free fall units. It was not possible to configure the second unit. This patch introduces configuration entry to the platform data and also corresponding changes to the 8 bit setup function. High pass filters were enabled by default. Patch introduces configuration option for high pass filter cut off frequency and also possibility to disable or enable the filter via platform data. Since the control is a new one and default state was filter enabled, new option is used to disable the filter. This way old platform data is still compatible with the change. Signed-off-by: Samu Onkalo Acked-by: Eric Piel Tested-by: Daniel Mack Cc: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lis3lv02d.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lis3lv02d.h b/include/linux/lis3lv02d.h index f1ca0dcc1628..d6251995c042 100644 --- a/include/linux/lis3lv02d.h +++ b/include/linux/lis3lv02d.h @@ -43,6 +43,15 @@ struct lis3lv02d_platform_data { #define LIS3_WAKEUP_Z_HI (1 << 5) unsigned char wakeup_flags; unsigned char wakeup_thresh; + unsigned char wakeup_flags2; + unsigned char wakeup_thresh2; +#define LIS3_HIPASS_CUTFF_8HZ 0 +#define LIS3_HIPASS_CUTFF_4HZ 1 +#define LIS3_HIPASS_CUTFF_2HZ 2 +#define LIS3_HIPASS_CUTFF_1HZ 3 +#define LIS3_HIPASS1_DISABLE (1 << 2) +#define LIS3_HIPASS2_DISABLE (1 << 3) + unsigned char hipass_ctrl; #define LIS3_NO_MAP 0 #define LIS3_DEV_X 1 #define LIS3_DEV_Y 2 -- cgit v1.2.3 From 92ba4fe4b53b4fa5ac71ec4d80572348fca85796 Mon Sep 17 00:00:00 2001 From: Samu Onkalo Date: Mon, 24 May 2010 14:33:36 -0700 Subject: lis3: add skeletons for interrupt handlers Original lis3 driver didn't provide interrupt handler(s) for click or threshold event handling. This patch adds threaded handlers for one or two interrupt lines for 8 bit device. Actual content for interrupt handling is provided in the separate patch. Signed-off-by: Samu Onkalo Tested-by: Daniel Mack Acked-by: Eric Piel Cc: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lis3lv02d.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lis3lv02d.h b/include/linux/lis3lv02d.h index d6251995c042..fd289b1e1ec1 100644 --- a/include/linux/lis3lv02d.h +++ b/include/linux/lis3lv02d.h @@ -67,6 +67,7 @@ struct lis3lv02d_platform_data { /* Limits for selftest are specified in chip data sheet */ s16 st_min_limits[3]; /* min pass limit x, y, z */ s16 st_max_limits[3]; /* max pass limit x, y, z */ + int irq2; }; #endif /* __LIS3LV02D_H_ */ -- cgit v1.2.3 From 6d94d4081048756df78444a07201156f4930fe48 Mon Sep 17 00:00:00 2001 From: Samu Onkalo Date: Mon, 24 May 2010 14:33:37 -0700 Subject: lis3: interrupt handlers for 8bit wakeup and click events Content for the 8bit device threaded interrupt handlers. Depending on the interrupt line and chip configuration, either click or wakeup / freefall handler is called. In case of click, BTN_ event is sent via input device. In case of wakeup or freefall, input device ABS_ events are updated immediatelly. It is still possible to configure interrupt line 1 for fast freefall detection and use the second line either for click or threshold based interrupts. Or both lines can be used for click / threshold interrupts. Polled input device can be set to stopped state and still get coordinate updates via input device using interrupt based method. Polled mode and interrupt mode can also be used parallel. BTN_ events are remapped based on existing axis remapping information. Signed-off-by: Samu Onkalo Acked-by: Eric Piel Cc: Daniel Mack Cc: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lis3lv02d.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lis3lv02d.h b/include/linux/lis3lv02d.h index fd289b1e1ec1..0e8a346424bb 100644 --- a/include/linux/lis3lv02d.h +++ b/include/linux/lis3lv02d.h @@ -25,12 +25,14 @@ struct lis3lv02d_platform_data { #define LIS3_IRQ1_FF_WU_12 (3 << 0) #define LIS3_IRQ1_DATA_READY (4 << 0) #define LIS3_IRQ1_CLICK (7 << 0) +#define LIS3_IRQ1_MASK (7 << 0) #define LIS3_IRQ2_DISABLE (0 << 3) #define LIS3_IRQ2_FF_WU_1 (1 << 3) #define LIS3_IRQ2_FF_WU_2 (2 << 3) #define LIS3_IRQ2_FF_WU_12 (3 << 3) #define LIS3_IRQ2_DATA_READY (4 << 3) #define LIS3_IRQ2_CLICK (7 << 3) +#define LIS3_IRQ2_MASK (7 << 3) #define LIS3_IRQ_OPEN_DRAIN (1 << 6) #define LIS3_IRQ_ACTIVE_LOW (1 << 7) unsigned char irq_cfg; -- cgit v1.2.3 From 49c39b4953e545ce3b5957cce22e1ade01c6e642 Mon Sep 17 00:00:00 2001 From: Grazvydas Ignotas Date: Mon, 24 May 2010 14:34:02 -0700 Subject: fbdev: move FBIO_WAITFORVSYNC to linux/fb.h FBIO_WAITFORVSYNC is currently implemented by matroxfb, atyfb, intelfb and more. All of them keep redefining the same FBIO_WAITFORVSYNC macro over and over again, so move it to linux/fb.h and clean up those duplicate defines. Signed-off-by: Grazvydas Ignotas Cc: Ville Syrjala Cc: Grant Likely Cc: Maik Broemme Cc: Petr Vandrovec Cc: Benjamin Herrenschmidt Cc: Krzysztof Helt Cc: "Hiremath, Vaibhav" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 2 +- include/linux/ivtvfb.h | 1 - include/linux/matroxfb.h | 3 +-- 3 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 1296af45169d..f3793ebc241c 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -37,7 +37,7 @@ struct dentry; #define FBIOGET_HWCINFO 0x4616 #define FBIOPUT_MODEINFO 0x4617 #define FBIOGET_DISPINFO 0x4618 - +#define FBIO_WAITFORVSYNC _IOW('F', 0x20, __u32) #define FB_TYPE_PACKED_PIXELS 0 /* Packed Pixels */ #define FB_TYPE_PLANES 1 /* Non interleaved planes */ diff --git a/include/linux/ivtvfb.h b/include/linux/ivtvfb.h index 9d88b29ddf55..e8b92f67f10d 100644 --- a/include/linux/ivtvfb.h +++ b/include/linux/ivtvfb.h @@ -33,6 +33,5 @@ struct ivtvfb_dma_frame { }; #define IVTVFB_IOC_DMA_FRAME _IOW('V', BASE_VIDIOC_PRIVATE+0, struct ivtvfb_dma_frame) -#define FBIO_WAITFORVSYNC _IOW('F', 0x20, __u32) #endif diff --git a/include/linux/matroxfb.h b/include/linux/matroxfb.h index 2203121a43e9..8c22a8938642 100644 --- a/include/linux/matroxfb.h +++ b/include/linux/matroxfb.h @@ -4,6 +4,7 @@ #include #include #include +#include struct matroxioc_output_mode { __u32 output; /* which output */ @@ -37,7 +38,5 @@ enum matroxfb_ctrl_id { MATROXFB_CID_LAST }; -#define FBIO_WAITFORVSYNC _IOW('F', 0x20, __u32) - #endif -- cgit v1.2.3 From 5487ab4a5a71e955fef7094a0624df0542da91ef Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Tue, 25 May 2010 16:40:47 +0800 Subject: SFI: add support for v0.81 spec There are 2 major changes from v0.81 to v0.7: 1. Consolidating the SPIB/I2CB tables into a new DEVS table, which is more expandable and can support other bus types than spi/i2c. 2. Creating a new GPIO table, which list all the GPIO pins used in the platform. However, to avoid breaking current platforms who use SFI v0.7 version firmware, the definitions for SPIB/I2CB will still be kept for a while Signed-off-by: Feng Tang Signed-off-by: Len Brown --- include/linux/sfi.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sfi.h b/include/linux/sfi.h index 9a6f7607174e..0299b4ce63db 100644 --- a/include/linux/sfi.h +++ b/include/linux/sfi.h @@ -73,6 +73,8 @@ #define SFI_SIG_SPIB "SPIB" #define SFI_SIG_I2CB "I2CB" #define SFI_SIG_GPEM "GPEM" +#define SFI_SIG_DEVS "DEVS" +#define SFI_SIG_GPIO "GPIO" #define SFI_SIGNATURE_SIZE 4 #define SFI_OEM_ID_SIZE 6 @@ -145,6 +147,27 @@ struct sfi_rtc_table_entry { u32 irq; } __packed; +struct sfi_device_table_entry { + u8 type; /* bus type, I2C, SPI or ...*/ +#define SFI_DEV_TYPE_SPI 0 +#define SFI_DEV_TYPE_I2C 1 +#define SFI_DEV_TYPE_UART 2 +#define SFI_DEV_TYPE_HSI 3 +#define SFI_DEV_TYPE_IPC 4 + + u8 host_num; /* attached to host 0, 1...*/ + u16 addr; + u8 irq; + u32 max_freq; + char name[16]; +} __packed; + +struct sfi_gpio_table_entry { + char controller_name[16]; + u16 pin_no; + char pin_name[16]; +} __packed; + struct sfi_spi_table_entry { u16 host_num; /* attached to host 0, 1...*/ u16 cs; /* chip select */ @@ -166,7 +189,6 @@ struct sfi_gpe_table_entry { u16 phys_id; /* physical GPE id */ } __packed; - typedef int (*sfi_table_handler) (struct sfi_table_header *table); #ifdef CONFIG_SFI -- cgit v1.2.3 From 578454ff7eab61d13a26b568f99a89a2c9edc881 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Thu, 20 May 2010 18:07:20 +0200 Subject: driver core: add devname module aliases to allow module on-demand auto-loading This adds: alias: devname: to some common kernel modules, which will allow the on-demand loading of the kernel module when the device node is accessed. Ideally all these modules would be compiled-in, but distros seems too much in love with their modularization that we need to cover the common cases with this new facility. It will allow us to remove a bunch of pretty useless init scripts and modprobes from init scripts. The static device node aliases will be carried in the module itself. The program depmod will extract this information to a file in the module directory: $ cat /lib/modules/2.6.34-00650-g537b60d-dirty/modules.devname # Device nodes to trigger on-demand module loading. microcode cpu/microcode c10:184 fuse fuse c10:229 ppp_generic ppp c108:0 tun net/tun c10:200 dm_mod mapper/control c10:235 Udev will pick up the depmod created file on startup and create all the static device nodes which the kernel modules specify, so that these modules get automatically loaded when the device node is accessed: $ /sbin/udevd --debug ... static_dev_create_from_modules: mknod '/dev/cpu/microcode' c10:184 static_dev_create_from_modules: mknod '/dev/fuse' c10:229 static_dev_create_from_modules: mknod '/dev/ppp' c108:0 static_dev_create_from_modules: mknod '/dev/net/tun' c10:200 static_dev_create_from_modules: mknod '/dev/mapper/control' c10:235 udev_rules_apply_static_dev_perms: chmod '/dev/net/tun' 0666 udev_rules_apply_static_dev_perms: chmod '/dev/fuse' 0666 A few device nodes are switched to statically allocated numbers, to allow the static nodes to work. This might also useful for systems which still run a plain static /dev, which is completely unsafe to use with any dynamic minor numbers. Note: The devname aliases must be limited to the *common* and *single*instance* device nodes, like the misc devices, and never be used for conceptually limited systems like the loop devices, which should rather get fixed properly and get a control node for losetup to talk to, instead of creating a random number of device nodes in advance, regardless if they are ever used. This facility is to hide the mess distros are creating with too modualized kernels, and just to hide that these modules are not compiled-in, and not to paper-over broken concepts. Thanks! :) Cc: Greg Kroah-Hartman Cc: David S. Miller Cc: Miklos Szeredi Cc: Chris Mason Cc: Alasdair G Kergon Cc: Tigran Aivazian Cc: Ian Kent Signed-Off-By: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/miscdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 8b5f7cc0fba6..b631c46cffd9 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -31,6 +31,8 @@ #define FUSE_MINOR 229 #define KVM_MINOR 232 #define VHOST_NET_MINOR 233 +#define BTRFS_MINOR 234 +#define AUTOFS_MINOR 235 #define MISC_DYNAMIC_MINOR 255 struct device; -- cgit v1.2.3 From 37f65b8bc262a5ae4c8e58be92fe3032f0aaaf04 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 19 May 2010 22:10:20 +0200 Subject: libata-sff: ata_sff_irq_clear() is BMDMA specific ata_sff_irq_clear() is BMDMA specific. Rename it to ata_bmdma_irq_clear(), move it to ata_bmdma_port_ops and make ->sff_irq_clear() optional. Note: ata_bmdma_irq_clear() is actually only needed by ata_piix and possibly by sata_sil. This should be moved to respective low level drivers later. Signed-off-by: Tejun Heo 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 ee84e7e12039..8fd1ca8c7ef3 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1630,6 +1630,7 @@ extern unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc); extern void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); extern void ata_bmdma_error_handler(struct ata_port *ap); extern void ata_bmdma_post_internal_cmd(struct ata_queued_cmd *qc); +extern void ata_bmdma_irq_clear(struct ata_port *ap); extern void ata_bmdma_setup(struct ata_queued_cmd *qc); extern void ata_bmdma_start(struct ata_queued_cmd *qc); extern void ata_bmdma_stop(struct ata_queued_cmd *qc); -- cgit v1.2.3 From c3b2889424c26f3b42962b6f39aabb4f1fd1b576 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 19 May 2010 22:10:21 +0200 Subject: libata-sff: separate out BMDMA irq handler Separate out BMDMA irq handler from SFF irq handler. The misnamed host_intr() functions are renamed to ata_sff_port_intr() and ata_bmdma_port_intr(). Common parts are factored into __ata_sff_port_intr() and __ata_sff_interrupt() and used by sff and bmdma interrupt routines. All BMDMA drivers now use ata_bmdma_interrupt() or ata_bmdma_port_intr() while all non-BMDMA SFF ones use ata_sff_interrupt() or ata_sff_port_intr(). For now, ata_pci_sff_init_one() uses ata_bmdma_interrupt() as it's used by both SFF and BMDMA drivers. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 8fd1ca8c7ef3..b76d767e0240 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1593,7 +1593,7 @@ extern int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, extern void ata_sff_queue_pio_task(struct ata_port *ap, unsigned long delay); extern unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc); extern bool ata_sff_qc_fill_rtf(struct ata_queued_cmd *qc); -extern unsigned int ata_sff_host_intr(struct ata_port *ap, +extern unsigned int ata_sff_port_intr(struct ata_port *ap, struct ata_queued_cmd *qc); extern irqreturn_t ata_sff_interrupt(int irq, void *dev_instance); extern void ata_sff_lost_interrupt(struct ata_port *ap); @@ -1628,6 +1628,9 @@ extern int ata_pci_sff_init_one(struct pci_dev *pdev, extern void ata_bmdma_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc); extern void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); +extern unsigned int ata_bmdma_port_intr(struct ata_port *ap, + struct ata_queued_cmd *qc); +extern irqreturn_t ata_bmdma_interrupt(int irq, void *dev_instance); extern void ata_bmdma_error_handler(struct ata_port *ap); extern void ata_bmdma_post_internal_cmd(struct ata_queued_cmd *qc); extern void ata_bmdma_irq_clear(struct ata_port *ap); -- cgit v1.2.3 From 1c5afdf7a629d2e77de8dd043b97a33dcd7e6dfa Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 19 May 2010 22:10:22 +0200 Subject: libata-sff: separate out BMDMA init Separate out ata_pci_bmdma_prepare_host() and ata_pci_bmdma_init_one() from their SFF counterparts. SFF ones no longer try to initialize BMDMA or set PCI master. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index b76d767e0240..fe2be88bc266 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1644,6 +1644,13 @@ extern int ata_bmdma_port_start32(struct ata_port *ap); #ifdef CONFIG_PCI extern int ata_pci_bmdma_clear_simplex(struct pci_dev *pdev); extern void ata_pci_bmdma_init(struct ata_host *host); +extern int ata_pci_bmdma_prepare_host(struct pci_dev *pdev, + const struct ata_port_info * const * ppi, + struct ata_host **r_host); +extern int ata_pci_bmdma_init_one(struct pci_dev *pdev, + const struct ata_port_info * const * ppi, + struct scsi_host_template *sht, + void *host_priv, int hflags); #endif /* CONFIG_PCI */ /** -- cgit v1.2.3 From 9a7780c9acb821fe1c2b6fc53f74cc2556ff5364 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 19 May 2010 22:10:24 +0200 Subject: libata-sff: make BMDMA optional Make BMDMA optional depending on new config variable CONFIG_ATA_BMDMA. In Kconfig, drivers are grouped into five groups - non-SFF native, SFF w/ custom DMA interface, SFF w/ BMDMA, PIO-only SFF, and generic fallback / legacy ones. Kconfig and Makefile are reorganized according to the groups and ordered alphabetically inside each group. ata_ioports.bmdma_addr and ata_port.bmdma_prd[_dma] are put into CONFIG_ATA_BMDMA, as are all bmdma related ops, variables and functions. This increase the binary size slightly when BMDMA is enabled but on both native-only and PIO-only configurations the size is slightly reduced. Either way, the size difference is insignificant. This change is more meaningful to signify the separation between SFF and BMDMA and as a tool to verify the separation. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index fe2be88bc266..4c5eca4e663b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -513,7 +513,9 @@ struct ata_ioports { void __iomem *command_addr; void __iomem *altstatus_addr; void __iomem *ctl_addr; +#ifdef CONFIG_ATA_BMDMA void __iomem *bmdma_addr; +#endif /* CONFIG_ATA_BMDMA */ void __iomem *scr_addr; }; #endif /* CONFIG_ATA_SFF */ @@ -721,8 +723,10 @@ struct ata_port { u8 ctl; /* cache of ATA control register */ u8 last_ctl; /* Cache last written value */ struct delayed_work sff_pio_task; +#ifdef CONFIG_ATA_BMDMA struct ata_bmdma_prd *bmdma_prd; /* BMDMA SG list */ dma_addr_t bmdma_prd_dma; /* and its DMA mapping */ +#endif /* CONFIG_ATA_BMDMA */ #endif /* CONFIG_ATA_SFF */ unsigned int pio_mask; @@ -856,10 +860,12 @@ struct ata_port_operations { void (*sff_irq_clear)(struct ata_port *); void (*sff_drain_fifo)(struct ata_queued_cmd *qc); +#ifdef CONFIG_ATA_BMDMA void (*bmdma_setup)(struct ata_queued_cmd *qc); void (*bmdma_start)(struct ata_queued_cmd *qc); void (*bmdma_stop)(struct ata_queued_cmd *qc); u8 (*bmdma_status)(struct ata_port *ap); +#endif /* CONFIG_ATA_BMDMA */ #endif /* CONFIG_ATA_SFF */ ssize_t (*em_show)(struct ata_port *ap, char *buf); @@ -1555,7 +1561,6 @@ extern void sata_pmp_error_handler(struct ata_port *ap); #ifdef CONFIG_ATA_SFF extern const struct ata_port_operations ata_sff_port_ops; -extern const struct ata_port_operations ata_bmdma_port_ops; extern const struct ata_port_operations ata_bmdma32_port_ops; /* PIO only, sg_tablesize and dma_boundary limits can be removed */ @@ -1564,11 +1569,6 @@ extern const struct ata_port_operations ata_bmdma32_port_ops; .sg_tablesize = LIBATA_MAX_PRD, \ .dma_boundary = ATA_DMA_BOUNDARY -#define ATA_BMDMA_SHT(drv_name) \ - ATA_BASE_SHT(drv_name), \ - .sg_tablesize = LIBATA_MAX_PRD, \ - .dma_boundary = ATA_DMA_BOUNDARY - extern void ata_sff_dev_select(struct ata_port *ap, unsigned int device); extern u8 ata_sff_check_status(struct ata_port *ap); extern void ata_sff_pause(struct ata_port *ap); @@ -1625,6 +1625,15 @@ extern int ata_pci_sff_init_one(struct pci_dev *pdev, struct scsi_host_template *sht, void *host_priv, int hflags); #endif /* CONFIG_PCI */ +#ifdef CONFIG_ATA_BMDMA + +extern const struct ata_port_operations ata_bmdma_port_ops; + +#define ATA_BMDMA_SHT(drv_name) \ + ATA_BASE_SHT(drv_name), \ + .sg_tablesize = LIBATA_MAX_PRD, \ + .dma_boundary = ATA_DMA_BOUNDARY + extern void ata_bmdma_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc); extern void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); @@ -1652,6 +1661,7 @@ extern int ata_pci_bmdma_init_one(struct pci_dev *pdev, struct scsi_host_template *sht, void *host_priv, int hflags); #endif /* CONFIG_PCI */ +#endif /* CONFIG_ATA_BMDMA */ /** * ata_sff_busy_wait - Wait for a port status register -- cgit v1.2.3 From 43c9c59185eec7caaff6e9dd8d4c93a4d9836a86 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 23 May 2010 12:59:11 +0200 Subject: libata: implement dump_id force param Add dump_id libata.force parameter. If specified, libata dumps full IDENTIFY data during device configuration. This is to aid debugging. Signed-off-by: Tejun Heo Cc: Larry Baker 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 4c5eca4e663b..3bad2701bfa6 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -386,6 +386,7 @@ enum { ATA_HORKAGE_1_5_GBPS = (1 << 13), /* force 1.5 Gbps */ ATA_HORKAGE_NOSETXFER = (1 << 14), /* skip SETXFER, SATA only */ ATA_HORKAGE_BROKEN_FPDMA_AA = (1 << 15), /* skip AA */ + ATA_HORKAGE_DUMP_ID = (1 << 16), /* dump IDENTIFY data */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From 2146325df2c2640059a9e064890c30c6e259b458 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sat, 22 May 2010 20:54:55 +1000 Subject: leds: leds-gpio: Change blink_set callback to be able to turn off blinking The leds-gpio blink_set() callback follows the same prototype as the main leds subsystem blink_set() one. The problem is that to stop blink, normally, a leds driver does it in the brightness_set() callback when asked to set a new fixed value. However, with leds-gpio, the platform has no hook to do so, as this later callback results in a standard GPIO manipulation. This changes the leds-gpio specific callback to take a new argument that indicates whether the LED should be blinking or not and in what state it should be set if not. We also update the dns323 platform which seems to be the only user of this so far. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Richard Purdie --- include/linux/leds.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index d8bf9665e70c..ba6986a11663 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -149,14 +149,18 @@ struct gpio_led { unsigned default_state : 2; /* default_state should be one of LEDS_GPIO_DEFSTATE_(ON|OFF|KEEP) */ }; -#define LEDS_GPIO_DEFSTATE_OFF 0 -#define LEDS_GPIO_DEFSTATE_ON 1 -#define LEDS_GPIO_DEFSTATE_KEEP 2 +#define LEDS_GPIO_DEFSTATE_OFF 0 +#define LEDS_GPIO_DEFSTATE_ON 1 +#define LEDS_GPIO_DEFSTATE_KEEP 2 struct gpio_led_platform_data { int num_leds; struct gpio_led *leds; - int (*gpio_blink_set)(unsigned gpio, + +#define GPIO_LED_NO_BLINK_LOW 0 /* No blink GPIO state low */ +#define GPIO_LED_NO_BLINK_HIGH 1 /* No blink GPIO state high */ +#define GPIO_LED_BLINK 2 /* Plase, blink */ + int (*gpio_blink_set)(unsigned gpio, int state, unsigned long *delay_on, unsigned long *delay_off); }; -- cgit v1.2.3 From 7fdcef8a414eaeb367b3696005b25283d62d195d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Philippe=20R=C3=A9tornaz?= Date: Wed, 19 May 2010 09:24:31 +0200 Subject: leds: Add mc13783 LED support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This add basic led support for Freescale MC13783 PMIC. Signed-off-by: Philippe Rétornaz Signed-off-by: Richard Purdie --- include/linux/mfd/mc13783.h | 66 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 66 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mc13783.h b/include/linux/mfd/mc13783.h index 8895d9d8879c..4a894f688549 100644 --- a/include/linux/mfd/mc13783.h +++ b/include/linux/mfd/mc13783.h @@ -64,6 +64,70 @@ static inline int mc13783_ackirq(struct mc13783 *mc13783, int irq) MC13783_ADC0_TSMOD1 | \ MC13783_ADC0_TSMOD2) +struct mc13783_led_platform_data { +#define MC13783_LED_MD 0 +#define MC13783_LED_AD 1 +#define MC13783_LED_KP 2 +#define MC13783_LED_R1 3 +#define MC13783_LED_G1 4 +#define MC13783_LED_B1 5 +#define MC13783_LED_R2 6 +#define MC13783_LED_G2 7 +#define MC13783_LED_B2 8 +#define MC13783_LED_R3 9 +#define MC13783_LED_G3 10 +#define MC13783_LED_B3 11 +#define MC13783_LED_MAX MC13783_LED_B3 + int id; + const char *name; + const char *default_trigger; + +/* Three or two bits current selection depending on the led */ + char max_current; +}; + +struct mc13783_leds_platform_data { + int num_leds; + struct mc13783_led_platform_data *led; + +#define MC13783_LED_TRIODE_MD (1 << 0) +#define MC13783_LED_TRIODE_AD (1 << 1) +#define MC13783_LED_TRIODE_KP (1 << 2) +#define MC13783_LED_BOOST_EN (1 << 3) +#define MC13783_LED_TC1HALF (1 << 4) +#define MC13783_LED_SLEWLIMTC (1 << 5) +#define MC13783_LED_SLEWLIMBL (1 << 6) +#define MC13783_LED_TRIODE_TC1 (1 << 7) +#define MC13783_LED_TRIODE_TC2 (1 << 8) +#define MC13783_LED_TRIODE_TC3 (1 << 9) + int flags; + +#define MC13783_LED_AB_DISABLED 0 +#define MC13783_LED_AB_MD1 1 +#define MC13783_LED_AB_MD12 2 +#define MC13783_LED_AB_MD123 3 +#define MC13783_LED_AB_MD1234 4 +#define MC13783_LED_AB_MD1234_AD1 5 +#define MC13783_LED_AB_MD1234_AD12 6 +#define MC13783_LED_AB_MD1_AD 7 + char abmode; + +#define MC13783_LED_ABREF_200MV 0 +#define MC13783_LED_ABREF_400MV 1 +#define MC13783_LED_ABREF_600MV 2 +#define MC13783_LED_ABREF_800MV 3 + char abref; + +#define MC13783_LED_PERIOD_10MS 0 +#define MC13783_LED_PERIOD_100MS 1 +#define MC13783_LED_PERIOD_500MS 2 +#define MC13783_LED_PERIOD_2S 3 + char bl_period; + char tc1_period; + char tc2_period; + char tc3_period; +}; + /* to be cleaned up */ struct regulator_init_data; @@ -80,12 +144,14 @@ struct mc13783_regulator_platform_data { struct mc13783_platform_data { int num_regulators; struct mc13783_regulator_init_data *regulators; + struct mc13783_leds_platform_data *leds; #define MC13783_USE_TOUCHSCREEN (1 << 0) #define MC13783_USE_CODEC (1 << 1) #define MC13783_USE_ADC (1 << 2) #define MC13783_USE_RTC (1 << 3) #define MC13783_USE_REGULATOR (1 << 4) +#define MC13783_USE_LED (1 << 5) unsigned int flags; }; -- cgit v1.2.3 From 82fd53b7f70af9855eda613450a7e4701ffdae20 Mon Sep 17 00:00:00 2001 From: Michael Hennerich Date: Fri, 30 Apr 2010 14:09:51 -0700 Subject: backlight: new driver for the ADP8860 backlight parts The ADP8860 combines a programmable backlight LED charge pump driver with automatic phototransistor control. Signed-off-by: Michael Hennerich Signed-off-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Richard Purdie --- include/linux/i2c/adp8860.h | 137 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 137 insertions(+) create mode 100644 include/linux/i2c/adp8860.h (limited to 'include/linux') diff --git a/include/linux/i2c/adp8860.h b/include/linux/i2c/adp8860.h new file mode 100644 index 000000000000..115514b7176e --- /dev/null +++ b/include/linux/i2c/adp8860.h @@ -0,0 +1,137 @@ +/* + * Definitions and platform data for Analog Devices + * Backlight drivers ADP8860 + * + * Copyright 2009-2010 Analog Devices Inc. + * + * Licensed under the GPL-2 or later. + */ + +#ifndef __LINUX_I2C_ADP8860_H +#define __LINUX_I2C_ADP8860_H + +#include +#include + +#define ID_ADP8860 8860 + +#define ADP8860_MAX_BRIGHTNESS 0x7F +#define FLAG_OFFT_SHIFT 8 + +/* + * LEDs subdevice platform data + */ + +#define ADP8860_LED_DIS_BLINK (0 << FLAG_OFFT_SHIFT) +#define ADP8860_LED_OFFT_600ms (1 << FLAG_OFFT_SHIFT) +#define ADP8860_LED_OFFT_1200ms (2 << FLAG_OFFT_SHIFT) +#define ADP8860_LED_OFFT_1800ms (3 << FLAG_OFFT_SHIFT) + +#define ADP8860_LED_ONT_200ms 0 +#define ADP8860_LED_ONT_600ms 1 +#define ADP8860_LED_ONT_800ms 2 +#define ADP8860_LED_ONT_1200ms 3 + +#define ADP8860_LED_D7 (7) +#define ADP8860_LED_D6 (6) +#define ADP8860_LED_D5 (5) +#define ADP8860_LED_D4 (4) +#define ADP8860_LED_D3 (3) +#define ADP8860_LED_D2 (2) +#define ADP8860_LED_D1 (1) + +/* + * Backlight subdevice platform data + */ + +#define ADP8860_BL_D7 (1 << 6) +#define ADP8860_BL_D6 (1 << 5) +#define ADP8860_BL_D5 (1 << 4) +#define ADP8860_BL_D4 (1 << 3) +#define ADP8860_BL_D3 (1 << 2) +#define ADP8860_BL_D2 (1 << 1) +#define ADP8860_BL_D1 (1 << 0) + +#define ADP8860_FADE_T_DIS 0 /* Fade Timer Disabled */ +#define ADP8860_FADE_T_300ms 1 /* 0.3 Sec */ +#define ADP8860_FADE_T_600ms 2 +#define ADP8860_FADE_T_900ms 3 +#define ADP8860_FADE_T_1200ms 4 +#define ADP8860_FADE_T_1500ms 5 +#define ADP8860_FADE_T_1800ms 6 +#define ADP8860_FADE_T_2100ms 7 +#define ADP8860_FADE_T_2400ms 8 +#define ADP8860_FADE_T_2700ms 9 +#define ADP8860_FADE_T_3000ms 10 +#define ADP8860_FADE_T_3500ms 11 +#define ADP8860_FADE_T_4000ms 12 +#define ADP8860_FADE_T_4500ms 13 +#define ADP8860_FADE_T_5000ms 14 +#define ADP8860_FADE_T_5500ms 15 /* 5.5 Sec */ + +#define ADP8860_FADE_LAW_LINEAR 0 +#define ADP8860_FADE_LAW_SQUARE 1 +#define ADP8860_FADE_LAW_CUBIC1 2 +#define ADP8860_FADE_LAW_CUBIC2 3 + +#define ADP8860_BL_AMBL_FILT_80ms 0 /* Light sensor filter time */ +#define ADP8860_BL_AMBL_FILT_160ms 1 +#define ADP8860_BL_AMBL_FILT_320ms 2 +#define ADP8860_BL_AMBL_FILT_640ms 3 +#define ADP8860_BL_AMBL_FILT_1280ms 4 +#define ADP8860_BL_AMBL_FILT_2560ms 5 +#define ADP8860_BL_AMBL_FILT_5120ms 6 +#define ADP8860_BL_AMBL_FILT_10240ms 7 /* 10.24 sec */ + +/* + * Blacklight current 0..30mA + */ +#define ADP8860_BL_CUR_mA(I) ((I * 127) / 30) + +/* + * L2 comparator current 0..1106uA + */ +#define ADP8860_L2_COMP_CURR_uA(I) ((I * 255) / 1106) + +/* + * L3 comparator current 0..138uA + */ +#define ADP8860_L3_COMP_CURR_uA(I) ((I * 255) / 138) + +struct adp8860_backlight_platform_data { + u8 bl_led_assign; /* 1 = Backlight 0 = Individual LED */ + + u8 bl_fade_in; /* Backlight Fade-In Timer */ + u8 bl_fade_out; /* Backlight Fade-Out Timer */ + u8 bl_fade_law; /* fade-on/fade-off transfer characteristic */ + + u8 en_ambl_sens; /* 1 = enable ambient light sensor */ + u8 abml_filt; /* Light sensor filter time */ + + u8 l1_daylight_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l1_daylight_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l2_office_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l2_office_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l3_dark_max; /* use BL_CUR_mA(I) 0 <= I <= 30 mA */ + u8 l3_dark_dim; /* typ = 0, use BL_CUR_mA(I) 0 <= I <= 30 mA */ + + u8 l2_trip; /* use L2_COMP_CURR_uA(I) 0 <= I <= 1106 uA */ + u8 l2_hyst; /* use L2_COMP_CURR_uA(I) 0 <= I <= 1106 uA */ + u8 l3_trip; /* use L3_COMP_CURR_uA(I) 0 <= I <= 551 uA */ + u8 l3_hyst; /* use L3_COMP_CURR_uA(I) 0 <= I <= 551 uA */ + + /** + * Independent Current Sinks / LEDS + * Sinks not assigned to the Backlight can be exposed to + * user space using the LEDS CLASS interface + */ + + int num_leds; + struct led_info *leds; + u8 led_fade_in; /* LED Fade-In Timer */ + u8 led_fade_out; /* LED Fade-Out Timer */ + u8 led_fade_law; /* fade-on/fade-off transfer characteristic */ + u8 led_on_time; +}; + +#endif /* __LINUX_I2C_ADP8860_H */ -- cgit v1.2.3 From c7c06d8a95fd6b83d9f71a0cfecd3f91945d17e5 Mon Sep 17 00:00:00 2001 From: Michael Hennerich Date: Wed, 26 May 2010 03:00:59 -0400 Subject: backlight: adp8860: add support for ADP8861 & ADP8863 Signed-off-by: Michael Hennerich Signed-off-by: Mike Frysinger Signed-off-by: Richard Purdie --- include/linux/i2c/adp8860.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c/adp8860.h b/include/linux/i2c/adp8860.h index 115514b7176e..0b4d39855c91 100644 --- a/include/linux/i2c/adp8860.h +++ b/include/linux/i2c/adp8860.h @@ -132,6 +132,23 @@ struct adp8860_backlight_platform_data { u8 led_fade_out; /* LED Fade-Out Timer */ u8 led_fade_law; /* fade-on/fade-off transfer characteristic */ u8 led_on_time; + + /** + * Gain down disable. Setting this option does not allow the + * charge pump to switch to lower gains. NOT AVAILABLE on ADP8860 + * 1 = the charge pump doesn't switch down in gain until all LEDs are 0. + * The charge pump switches up in gain as needed. This feature is + * useful if the ADP8863 charge pump is used to drive an external load. + * This feature must be used when utilizing small fly capacitors + * (0402 or smaller). + * 0 = the charge pump automatically switches up and down in gain. + * This provides optimal efficiency, but is not suitable for driving + * loads that are not connected through the ADP8863 diode drivers. + * Additionally, the charge pump fly capacitors should be low ESR + * and sized 0603 or greater. + */ + + u8 gdwn_dis; }; #endif /* __LINUX_I2C_ADP8860_H */ -- cgit v1.2.3 From 13da9e200fe4740b02cd51e07ab454627e228920 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 26 May 2010 08:30:15 -0700 Subject: Revert "endian: #define __BYTE_ORDER" This reverts commit b3b77c8caef1750ebeea1054e39e358550ea9f55, which was also totally broken (see commit 0d2daf5cc858 that reverted the crc32 version of it). As reported by Stephen Rothwell, it causes problems on big-endian machines: > In file included from fs/jfs/jfs_types.h:33, > from fs/jfs/jfs_incore.h:26, > from fs/jfs/file.c:22: > fs/jfs/endian24.h:36:101: warning: "__LITTLE_ENDIAN" is not defined The kernel has never had that crazy "__BYTE_ORDER == __LITTLE_ENDIAN" model. It's not how we do things, and it isn't how we _should_ do things. So don't go there. Requested-by: Stephen Rothwell Signed-off-by: Linus Torvalds --- include/linux/byteorder/big_endian.h | 3 --- include/linux/byteorder/little_endian.h | 3 --- 2 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/byteorder/big_endian.h b/include/linux/byteorder/big_endian.h index d53a67dff018..3c80fd7e8b56 100644 --- a/include/linux/byteorder/big_endian.h +++ b/include/linux/byteorder/big_endian.h @@ -7,9 +7,6 @@ #ifndef __BIG_ENDIAN_BITFIELD #define __BIG_ENDIAN_BITFIELD #endif -#ifndef __BYTE_ORDER -#define __BYTE_ORDER __BIG_ENDIAN -#endif #include #include diff --git a/include/linux/byteorder/little_endian.h b/include/linux/byteorder/little_endian.h index f7f8ad13adb6..83195fb82962 100644 --- a/include/linux/byteorder/little_endian.h +++ b/include/linux/byteorder/little_endian.h @@ -7,9 +7,6 @@ #ifndef __LITTLE_ENDIAN_BITFIELD #define __LITTLE_ENDIAN_BITFIELD #endif -#ifndef __BYTE_ORDER -#define __BYTE_ORDER __LITTLE_ENDIAN -#endif #include #include -- cgit v1.2.3 From ee378a5c6550dcbfe6fa9c71b84ca2eb19cb288e Mon Sep 17 00:00:00 2001 From: InKi Dae Date: Mon, 24 May 2010 12:21:36 -0700 Subject: backlight: add S6E63M0 AMOLED LCD Panel driver This is S6E63M0 AMOLED LCD Panel(480x800) driver using 3-wired SPI interface also almost features for lcd panel driver has been implemented in here. and I added new structure common for all the lcd panel drivers to include/linux/lcd.h file. LCD Panel driver needs interfaces for controlling device power such as power on/off and reset. these interfaces are device specific so it should be implemented to machine code at this time, we should create new structure for registering these functions as callbacks and also a header file for that structure and finally registered callback functions would be called by lcd panel driver. such header file(including new structure for lcd panel) would be added for all the lcd panel drivers. If anyone provides common structure for registering such callback functions then we could reduce unnecessary header files for lcd panel. I thought that suitable anyone could be include/linux/lcd.h so a new lcd_platform_data structure was added there. [akpm@linux-foundation.org: coding-style fixes] [randy.dunlap@oracle.com: fix s6e63m0 kconfig] [randy.dunlap@oracle.com: fix device attribute functions return types] Signed-off-by: InKi Dae Reviewed-by: KyungMin Park Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Richard Purdie --- include/linux/lcd.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lcd.h b/include/linux/lcd.h index c67fecafff90..8877123f2d6e 100644 --- a/include/linux/lcd.h +++ b/include/linux/lcd.h @@ -69,6 +69,29 @@ struct lcd_device { struct device dev; }; +struct lcd_platform_data { + /* reset lcd panel device. */ + int (*reset)(struct lcd_device *ld); + /* on or off to lcd panel. if 'enable' is 0 then + lcd power off and 1, lcd power on. */ + int (*power_on)(struct lcd_device *ld, int enable); + + /* it indicates whether lcd panel was enabled + from bootloader or not. */ + int lcd_enabled; + /* it means delay for stable time when it becomes low to high + or high to low that is dependent on whether reset gpio is + low active or high active. */ + unsigned int reset_delay; + /* stable time needing to become lcd power on. */ + unsigned int power_on_delay; + /* stable time needing to become lcd power off. */ + unsigned int power_off_delay; + + /* it could be used for any purpose. */ + void *pdata; +}; + static inline void lcd_set_power(struct lcd_device *ld, int power) { mutex_lock(&ld->update_lock); -- cgit v1.2.3 From 2ddfd12f3584840f5190897214423061d8a0602f Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 12 May 2010 02:44:32 +0200 Subject: backlight: Add pcf50633 backlight driver This patch adds a backlight driver for controlling the pcf50633 LED module. Signed-off-by: Lars-Peter Clausen Acked-by: Samuel Ortiz Signed-off-by: Richard Purdie --- include/linux/mfd/pcf50633/backlight.h | 51 ++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 include/linux/mfd/pcf50633/backlight.h (limited to 'include/linux') diff --git a/include/linux/mfd/pcf50633/backlight.h b/include/linux/mfd/pcf50633/backlight.h new file mode 100644 index 000000000000..83747e217b27 --- /dev/null +++ b/include/linux/mfd/pcf50633/backlight.h @@ -0,0 +1,51 @@ +/* + * Copyright (C) 2009-2010, Lars-Peter Clausen + * PCF50633 backlight device driver + * + * 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. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 675 Mass Ave, Cambridge, MA 02139, USA. + * + */ + +#ifndef __LINUX_MFD_PCF50633_BACKLIGHT +#define __LINUX_MFD_PCF50633_BACKLIGHT + +/* +* @default_brightness: Backlight brightness is initialized to this value +* +* Brightness to be used after the driver has been probed. +* Valid range 0-63. +* +* @default_brightness_limit: The actual brightness is limited by this value +* +* Brightness limit to be used after the driver has been probed. This is useful +* when it is not known how much power is available for the backlight during +* probe. +* Valid range 0-63. Can be changed later with pcf50633_bl_set_brightness_limit. +* +* @ramp_time: Display ramp time when changing brightness +* +* When changing the backlights brightness the change is not instant, instead +* it fades smooth from one state to another. This value specifies how long +* the fade should take. The lower the value the higher the fade time. +* Valid range 0-255 +*/ +struct pcf50633_bl_platform_data { + unsigned int default_brightness; + unsigned int default_brightness_limit; + uint8_t ramp_time; +}; + + +struct pcf50633; + +int pcf50633_bl_set_brightness_limit(struct pcf50633 *pcf, unsigned int limit); + +#endif + -- cgit v1.2.3 From f5bf403a9dc944bf560f49dd029195e54fcbc41c Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 12 May 2010 02:44:33 +0200 Subject: backlight: pcf50633: Register a pcf50633-backlight device in pcf50633 core driver. Register a device newly added pcf50633-backlight driver as a child device in the pcf50633 core driver. Signed-off-by: Lars-Peter Clausen Acked-by: Samuel Ortiz Signed-off-by: Richard Purdie --- include/linux/mfd/pcf50633/core.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/pcf50633/core.h b/include/linux/mfd/pcf50633/core.h index 3398bd9aab11..ad411a78870c 100644 --- a/include/linux/mfd/pcf50633/core.h +++ b/include/linux/mfd/pcf50633/core.h @@ -18,6 +18,7 @@ #include #include #include +#include struct pcf50633; @@ -43,6 +44,8 @@ struct pcf50633_platform_data { void (*force_shutdown)(struct pcf50633 *); u8 resumers[5]; + + struct pcf50633_bl_platform_data *backlight_data; }; struct pcf50633_irq { @@ -152,6 +155,7 @@ struct pcf50633 { struct platform_device *mbc_pdev; struct platform_device *adc_pdev; struct platform_device *input_pdev; + struct platform_device *bl_pdev; struct platform_device *regulator_pdev[PCF50633_NUM_REGULATORS]; }; -- cgit v1.2.3 From 6b2c676bf32be91f43215d5874c07c1becaba013 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Tue, 11 May 2010 16:50:52 -0400 Subject: cpuidle: fail to register if !CONFIG_CPU_IDLE Signed-off-by: Len Brown --- include/linux/cpuidle.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index dcf77fa826b5..f5e6480dc16f 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -137,16 +137,16 @@ extern void cpuidle_disable_device(struct cpuidle_device *dev); #else static inline int cpuidle_register_driver(struct cpuidle_driver *drv) -{return 0;} +{return -ENODEV; } static inline void cpuidle_unregister_driver(struct cpuidle_driver *drv) { } static inline int cpuidle_register_device(struct cpuidle_device *dev) -{return 0;} +{return -ENODEV; } static inline void cpuidle_unregister_device(struct cpuidle_device *dev) { } static inline void cpuidle_pause_and_lock(void) { } static inline void cpuidle_resume_and_unlock(void) { } static inline int cpuidle_enable_device(struct cpuidle_device *dev) -{return 0;} +{return -ENODEV; } static inline void cpuidle_disable_device(struct cpuidle_device *dev) { } #endif -- cgit v1.2.3 From 43b8e3bc4af0b435fddaa59e827ca1010b024492 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 26 May 2010 18:11:38 +0200 Subject: ALSA: usb-audio: parse UAC2 endpoint descriptors correctly UAC2 devices have their information about pitch control stored in a different field. Parse it, and emulate the bits for a v1 device. A new struct uac2_iso_endpoint_descriptor is added. Signed-off-by: Daniel Mack Acked-by: Greg Kroah-Hartman Signed-off-by: Takashi Iwai --- include/linux/usb/audio-v2.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h index 2389f93a28b5..92f1d99f0f17 100644 --- a/include/linux/usb/audio-v2.h +++ b/include/linux/usb/audio-v2.h @@ -105,6 +105,22 @@ struct uac_as_header_descriptor_v2 { __u8 iChannelNames; } __attribute__((packed)); +/* 4.10.1.2 Class-Specific AS Isochronous Audio Data Endpoint Descriptor */ + +struct uac2_iso_endpoint_descriptor { + __u8 bLength; /* in bytes: 8 */ + __u8 bDescriptorType; /* USB_DT_CS_ENDPOINT */ + __u8 bDescriptorSubtype; /* EP_GENERAL */ + __u8 bmAttributes; + __u8 bmControls; + __u8 bLockDelayUnits; + __le16 wLockDelay; +} __attribute__((packed)); + +#define UAC2_CONTROL_PITCH (3 << 0) +#define UAC2_CONTROL_DATA_OVERRUN (3 << 2) +#define UAC2_CONTROL_DATA_UNDERRUN (3 << 4) + /* 6.1 Interrupt Data Message */ #define UAC2_INTERRUPT_DATA_MSG_VENDOR (1 << 0) -- cgit v1.2.3 From a7626b7a5de37bbd506b23633be95428ee81c2e4 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Wed, 26 May 2010 14:41:55 -0700 Subject: sdhci-pltfm: implement platform data passing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This includes platform ops, quirks and (de)initialization callbacks. Signed-off-by: Anton Vorontsov Cc: Richard Röjfors Cc: David Vrabel Cc: Pierre Ossman Cc: Ben Dooks Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sdhci-pltfm.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/linux/sdhci-pltfm.h (limited to 'include/linux') diff --git a/include/linux/sdhci-pltfm.h b/include/linux/sdhci-pltfm.h new file mode 100644 index 000000000000..0239bd70241e --- /dev/null +++ b/include/linux/sdhci-pltfm.h @@ -0,0 +1,35 @@ +/* + * Platform data declarations for the sdhci-pltfm driver. + * + * Copyright (c) 2010 MontaVista Software, LLC. + * + * Author: Anton Vorontsov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. + */ + +#ifndef _SDHCI_PLTFM_H +#define _SDHCI_PLTFM_H + +struct sdhci_ops; +struct sdhci_host; + +/** + * struct sdhci_pltfm_data - SDHCI platform-specific information & hooks + * @ops: optional pointer to the platform-provided SDHCI ops + * @quirks: optional SDHCI quirks + * @init: optional hook that is called during device probe, before the + * driver tries to access any SDHCI registers + * @exit: optional hook that is called during device removal + */ +struct sdhci_pltfm_data { + struct sdhci_ops *ops; + unsigned int quirks; + int (*init)(struct sdhci_host *host); + void (*exit)(struct sdhci_host *host); +}; + +#endif /* _SDHCI_PLTFM_H */ -- cgit v1.2.3 From fdc50a9444b9781f4dd5aa5f7453300d2688cc5f Mon Sep 17 00:00:00 2001 From: Yusuke Goda Date: Wed, 26 May 2010 14:41:59 -0700 Subject: mmc: add support MMCIF for SuperH MMCIF is the MMC Host Interface in SuperH. Signed-off-by: Yusuke Goda Cc: Ben Hutchings Cc: Paul Mundt Cc: Magnus Damm Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/sh_mmcif.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) create mode 100644 include/linux/mmc/sh_mmcif.h (limited to 'include/linux') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h new file mode 100644 index 000000000000..aafe832f18aa --- /dev/null +++ b/include/linux/mmc/sh_mmcif.h @@ -0,0 +1,39 @@ +/* + * include/linux/mmc/sh_mmcif.h + * + * platform data for eMMC driver + * + * Copyright (C) 2010 Renesas Solutions Corp. + * + * 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. + * + */ + +#ifndef __SH_MMCIF_H__ +#define __SH_MMCIF_H__ + +/* + * MMCIF : CE_CLK_CTRL [19:16] + * 1000 : Peripheral clock / 512 + * 0111 : Peripheral clock / 256 + * 0110 : Peripheral clock / 128 + * 0101 : Peripheral clock / 64 + * 0100 : Peripheral clock / 32 + * 0011 : Peripheral clock / 16 + * 0010 : Peripheral clock / 8 + * 0001 : Peripheral clock / 4 + * 0000 : Peripheral clock / 2 + * 1111 : Peripheral clock (sup_pclk set '1') + */ + +struct sh_mmcif_plat_data { + void (*set_pwr)(struct platform_device *pdev, int state); + void (*down_pwr)(struct platform_device *pdev); + u8 sup_pclk; /* 1 :SH7757, 0: SH7724/SH7372 */ + unsigned long caps; + u32 ocr; +}; + +#endif /* __SH_MMCIF_H__ */ -- cgit v1.2.3 From 1a13f8fa76c880be41d6b1e6a2b44404bcbfdf9e Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Wed, 26 May 2010 14:42:08 -0700 Subject: mmc: remove the "state" argument to mmc_suspend_host() Even though many mmc host drivers pass a pm_message_t argument to mmc_suspend_host() that argument isn't used the by MMC core. As host drivers are converted to dev_pm_ops they'll have to construct pm_message_t's (as they won't be passed by the PM subsystem any more) just to appease the mmc suspend interface. We might as well just delete the unused paramter. Signed-off-by: Matt Fleming Acked-by: Anton Vorontsov Acked-by: Michal Miroslaw ZZ Acked-by: Sascha Sommer Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 3196c84cc630..f65913c9f5a4 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -230,7 +230,7 @@ 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 *, pm_message_t); +extern int mmc_suspend_host(struct mmc_host *); extern int mmc_resume_host(struct mmc_host *); extern void mmc_power_save_host(struct mmc_host *host); -- cgit v1.2.3 From 6c1f716e8154ee9315534782b9b1eedea0559a24 Mon Sep 17 00:00:00 2001 From: Grazvydas Ignotas Date: Wed, 26 May 2010 14:42:09 -0700 Subject: sdio: add new function for RAW (Read after Write) operation SDIO specification allows RAW (Read after Write) operation using IO_RW_DIRECT command (CMD52) by setting the RAW bit. This operation is similar to ordinary read/write commands, except that both write and read are performed using single command/response pair. The Linux SDIO layer already supports this internaly, only external function is missing for drivers to make use, which is added by this patch. This type of command is required to implement proper power save mode support in wl1251 wifi driver. Android has similar patch for G1 in it's tree for the same reason: http://android.git.kernel.org/?p=kernel/common.git;a=commitdiff;h=74a47786f6ecbe6c1cf9fb15efe6a968451deb52 Signed-off-by: Grazvydas Ignotas Acked-by: Kalle Valo Cc: Dmitry Shmidt Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/sdio_func.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index c6c0cceba5fe..31baaf82f458 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -145,6 +145,9 @@ extern void sdio_writew(struct sdio_func *func, u16 b, extern void sdio_writel(struct sdio_func *func, u32 b, unsigned int addr, int *err_ret); +extern u8 sdio_writeb_readb(struct sdio_func *func, u8 write_byte, + unsigned int addr, int *err_ret); + extern int sdio_memcpy_toio(struct sdio_func *func, unsigned int addr, void *src, int count); extern int sdio_writesb(struct sdio_func *func, unsigned int addr, -- cgit v1.2.3 From c63b3cba4f47ef9f4b3f952b4f923cf341d250ac Mon Sep 17 00:00:00 2001 From: Viresh KUMAR Date: Wed, 26 May 2010 14:42:10 -0700 Subject: sdhci-spear: ST SPEAr based SDHCI controller glue Add a glue layer to support the sdhci driver on the ST SPEAr platform. Signed-off-by: Viresh Kumar Cc: Cc: Linus Walleij Cc: Russell King Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/sdhci-spear.h | 42 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) create mode 100644 include/linux/mmc/sdhci-spear.h (limited to 'include/linux') diff --git a/include/linux/mmc/sdhci-spear.h b/include/linux/mmc/sdhci-spear.h new file mode 100644 index 000000000000..9188c973f3e1 --- /dev/null +++ b/include/linux/mmc/sdhci-spear.h @@ -0,0 +1,42 @@ +/* + * include/linux/mmc/sdhci-spear.h + * + * SDHCI declarations specific to ST SPEAr platform + * + * Copyright (C) 2010 ST Microelectronics + * Viresh Kumar + * + * 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 MMC_SDHCI_SPEAR_H +#define MMC_SDHCI_SPEAR_H + +#include +/* + * struct sdhci_plat_data: spear sdhci platform data structure + * + * @card_power_gpio: gpio pin for enabling/disabling power to sdhci socket + * @power_active_high: if set, enable power to sdhci socket by setting + * card_power_gpio + * @power_always_enb: If set, then enable power on probe, otherwise enable only + * on card insertion and disable on card removal. + * card_int_gpio: gpio pin used for card detection + */ +struct sdhci_plat_data { + int card_power_gpio; + int power_active_high; + int power_always_enb; + int card_int_gpio; +}; + +/* This function is used to set platform_data field of pdev->dev */ +static inline void +sdhci_set_plat_data(struct platform_device *pdev, struct sdhci_plat_data *data) +{ + pdev->dev.platform_data = data; +} + +#endif /* MMC_SDHCI_SPEAR_H */ -- cgit v1.2.3 From a80a0bbee49872c296c9ed9d6af0f510fcd825a7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 26 May 2010 14:42:16 -0700 Subject: gpio: add interrupt handling capability to max732x Most of the GPIO expanders supported by the max732x driver have interrupt generation capability by reporting changes on input pins through an INT# pin. This patch implements the irq_chip functionnality (edge detection only). Signed-off-by: Marc Zyngier Cc: Eric Miao Cc: Jebediah Huang Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/i2c/max732x.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c/max732x.h b/include/linux/i2c/max732x.h index e10336631c62..c04bac8bf2fe 100644 --- a/include/linux/i2c/max732x.h +++ b/include/linux/i2c/max732x.h @@ -7,6 +7,9 @@ struct max732x_platform_data { /* number of the first GPIO */ unsigned gpio_base; + /* interrupt base */ + int irq_base; + void *context; /* param to setup/teardown */ int (*setup)(struct i2c_client *client, -- cgit v1.2.3 From 62154991a8b2b932112d39bf4aeaab37fa7b9a31 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 26 May 2010 14:42:17 -0700 Subject: gpiolib: make names array and its values const MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gpiolib doesn't need to modify the names and I assume most initializers use string constants that shouldn't be modified anyhow. [akpm@linux-foundation.org: fix drivers/gpio/cs5535-gpio.c] Signed-off-by: Uwe Kleine-König Cc: Kevin Wells Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/i2c/pca953x.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c/pca953x.h b/include/linux/i2c/pca953x.h index d5c5a60c8a0b..139ba52667c8 100644 --- a/include/linux/i2c/pca953x.h +++ b/include/linux/i2c/pca953x.h @@ -24,7 +24,7 @@ struct pca953x_platform_data { int (*teardown)(struct i2c_client *client, unsigned gpio, unsigned ngpio, void *context); - char **names; + const char *const *names; }; #endif /* _LINUX_PCA953X_H */ -- cgit v1.2.3 From c4b5be98fe78508e7199d6919eb712feba9a4f01 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Wed, 26 May 2010 14:42:23 -0700 Subject: gpiolib: introduce set_debounce method A few architectures, like OMAP, allow you to set a debouncing time for the gpio before generating the IRQ. Teach gpiolib about that. Mark said: : This would be generally useful for embedded systems, especially where : the interrupt concerned is a wake source. It allows drivers to avoid : spurious interrupts from noisy sources so if the hardware supports it : the driver can avoid having to explicitly wait for the signal to become : stable and software has to cope with fewer events. We've lived without : it for quite some time, though. David said: : I looked at adding debounce support to the generic GPIO calls (and thus : gpiolib) some time back, but decided against it. I forget why at this : time (check list archives) but it wasn't because of lack of utility in : certain contexts. : : One thing to watch out for is just how variable the hardware capabilities : are. Atmel GPIOs have something like a fixed number of 32K clock cycles : for debounce, twl4030 had something odd, OMAPs were more like the Atmel : chips but with a different clock. In some cases debouncing had to be : ganged, not per-GPIO. And so forth. Signed-off-by: Felipe Balbi Cc: Tony Lindgren Cc: David Brownell Reviewed-by: Mark Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gpio.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 4e949a5b5b85..03f616b78cfa 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -51,6 +51,11 @@ static inline int gpio_direction_output(unsigned gpio, int value) return -ENOSYS; } +static inline int gpio_set_debounce(unsigned gpio, unsigned debounce) +{ + return -ENOSYS; +} + static inline int gpio_get_value(unsigned gpio) { /* GPIO can never have been requested or set as {in,out}put */ -- cgit v1.2.3 From 87946a72283be3de936adc754b7007df7d3e6aeb Mon Sep 17 00:00:00 2001 From: Daisuke Nishimura Date: Wed, 26 May 2010 14:42:39 -0700 Subject: memcg: move charge of file pages This patch adds support for moving charge of file pages, which include normal file, tmpfs file and swaps of tmpfs file. It's enabled by setting bit 1 of /memory.move_charge_at_immigrate. Unlike the case of anonymous pages, file pages(and swaps) in the range mmapped by the task will be moved even if the task hasn't done page fault, i.e. they might not be the task's "RSS", but other task's "RSS" that maps the same file. And mapcount of the page is ignored(the page can be moved even if page_mapcount(page) > 1). So, conditions that the page/swap should be met to be moved is that it must be in the range mmapped by the target task and it must be charged to the old cgroup. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix warning] Signed-off-by: Daisuke Nishimura Acked-by: KAMEZAWA Hiroyuki Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index b6b614364dd8..ff4acea9bbdb 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -282,6 +282,11 @@ extern void kswapd_stop(int nid); extern int shmem_unuse(swp_entry_t entry, struct page *page); #endif /* CONFIG_MMU */ +#ifdef CONFIG_CGROUP_MEM_RES_CTLR +extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, + struct page **pagep, swp_entry_t *ent); +#endif + extern void swap_unplug_io_fn(struct backing_dev_info *, struct page *); #ifdef CONFIG_SWAP -- cgit v1.2.3 From ac39cf8cb86c45eeac6a592ce0d58f9021a97235 Mon Sep 17 00:00:00 2001 From: "akpm@linux-foundation.org" Date: Wed, 26 May 2010 14:42:46 -0700 Subject: memcg: fix mis-accounting of file mapped racy with migration FILE_MAPPED per memcg of migrated file cache is not properly updated, because our hook in page_add_file_rmap() can't know to which memcg FILE_MAPPED should be counted. Basically, this patch is for fixing the bug but includes some big changes to fix up other messes. Now, at migrating mapped file, events happen in following sequence. 1. allocate a new page. 2. get memcg of an old page. 3. charge ageinst a new page before migration. But at this point, no changes to new page's page_cgroup, no commit for the charge. (IOW, PCG_USED bit is not set.) 4. page migration replaces radix-tree, old-page and new-page. 5. page migration remaps the new page if the old page was mapped. 6. Here, the new page is unlocked. 7. memcg commits the charge for newpage, Mark the new page's page_cgroup as PCG_USED. Because "commit" happens after page-remap, we can count FILE_MAPPED at "5", because we should avoid to trust page_cgroup->mem_cgroup. if PCG_USED bit is unset. (Note: memcg's LRU removal code does that but LRU-isolation logic is used for helping it. When we overwrite page_cgroup->mem_cgroup, page_cgroup is not on LRU or page_cgroup->mem_cgroup is NULL.) We can lose file_mapped accounting information at 5 because FILE_MAPPED is updated only when mapcount changes 0->1. So we should catch it. BTW, historically, above implemntation comes from migration-failure of anonymous page. Because we charge both of old page and new page with mapcount=0, we can't catch - the page is really freed before remap. - migration fails but it's freed before remap or .....corner cases. New migration sequence with memcg is: 1. allocate a new page. 2. mark PageCgroupMigration to the old page. 3. charge against a new page onto the old page's memcg. (here, new page's pc is marked as PageCgroupUsed.) 4. page migration replaces radix-tree, page table, etc... 5. At remapping, new page's page_cgroup is now makrked as "USED" We can catch 0->1 event and FILE_MAPPED will be properly updated. And we can catch SWAPOUT event after unlock this and freeing this page by unmap() can be caught. 7. Clear PageCgroupMigration of the old page. So, FILE_MAPPED will be correctly updated. Then, for what MIGRATION flag is ? Without it, at migration failure, we may have to charge old page again because it may be fully unmapped. "charge" means that we have to dive into memory reclaim or something complated. So, it's better to avoid charge it again. Before this patch, __commit_charge() was working for both of the old/new page and fixed up all. But this technique has some racy condtion around FILE_MAPPED and SWAPOUT etc... Now, the kernel use MIGRATION flag and don't uncharge old page until the end of migration. I hope this change will make memcg's page migration much simpler. This page migration has caused several troubles. Worth to add a flag for simplification. Reviewed-by: Daisuke Nishimura Tested-by: Daisuke Nishimura Reported-by: Daisuke Nishimura Signed-off-by: KAMEZAWA Hiroyuki Cc: Balbir Singh Cc: Christoph Lameter Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++++-- include/linux/page_cgroup.h | 5 +++++ 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 05894795fdc1..9411d32840b0 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -90,7 +90,8 @@ int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup) extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem); extern int -mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr); +mem_cgroup_prepare_migration(struct page *page, + struct page *newpage, struct mem_cgroup **ptr); extern void mem_cgroup_end_migration(struct mem_cgroup *mem, struct page *oldpage, struct page *newpage); @@ -227,7 +228,8 @@ static inline struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem) } static inline int -mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr) +mem_cgroup_prepare_migration(struct page *page, struct page *newpage, + struct mem_cgroup **ptr) { return 0; } diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index aef22ae2af47..5bb13b3db84d 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -40,6 +40,7 @@ enum { PCG_USED, /* this object is in use. */ PCG_ACCT_LRU, /* page has been accounted for */ PCG_FILE_MAPPED, /* page is accounted as "mapped" */ + PCG_MIGRATION, /* under page migration */ }; #define TESTPCGFLAG(uname, lname) \ @@ -79,6 +80,10 @@ SETPCGFLAG(FileMapped, FILE_MAPPED) CLEARPCGFLAG(FileMapped, FILE_MAPPED) TESTPCGFLAG(FileMapped, FILE_MAPPED) +SETPCGFLAG(Migration, MIGRATION) +CLEARPCGFLAG(Migration, MIGRATION) +TESTPCGFLAG(Migration, MIGRATION) + static inline int page_cgroup_nid(struct page_cgroup *pc) { return page_to_nid(pc->page); -- cgit v1.2.3 From 907860ed381a31b0102f362df67c1c5cae6ef050 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 26 May 2010 14:42:46 -0700 Subject: cgroups: make cftype.unregister_event() void-returning Since we are unable to handle an error returned by cftype.unregister_event() properly, let's make the callback void-returning. mem_cgroup_unregister_event() has been rewritten to be a "never fail" function. On mem_cgroup_usage_register_event() we save old buffer for thresholds array and reuse it in mem_cgroup_usage_unregister_event() to avoid allocation. Signed-off-by: Kirill A. Shutemov Acked-by: KAMEZAWA Hiroyuki Cc: Phil Carmody Cc: Balbir Singh Cc: Daisuke Nishimura Cc: Paul Menage Cc: Li Zefan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 8f78073d7caa..0c621604baa1 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -397,7 +397,7 @@ struct cftype { * This callback must be implemented, if you want provide * notification functionality. */ - int (*unregister_event)(struct cgroup *cgrp, struct cftype *cft, + void (*unregister_event)(struct cgroup *cgrp, struct cftype *cft, struct eventfd_ctx *eventfd); }; -- cgit v1.2.3 From 6adef3ebe570bcde67fd6c16101451ddde5712b5 Mon Sep 17 00:00:00 2001 From: Jack Steiner Date: Wed, 26 May 2010 14:42:49 -0700 Subject: cpusets: new round-robin rotor for SLAB allocations We have observed several workloads running on multi-node systems where memory is assigned unevenly across the nodes in the system. There are numerous reasons for this but one is the round-robin rotor in cpuset_mem_spread_node(). For example, a simple test that writes a multi-page file will allocate pages on nodes 0 2 4 6 ... Odd nodes are skipped. (Sometimes it allocates on odd nodes & skips even nodes). An example is shown below. The program "lfile" writes a file consisting of 10 pages. The program then mmaps the file & uses get_mempolicy(..., MPOL_F_NODE) to determine the nodes where the file pages were allocated. The output is shown below: # ./lfile allocated on nodes: 2 4 6 0 1 2 6 0 2 There is a single rotor that is used for allocating both file pages & slab pages. Writing the file allocates both a data page & a slab page (buffer_head). This advances the RR rotor 2 nodes for each page allocated. A quick confirmation seems to confirm this is the cause of the uneven allocation: # echo 0 >/dev/cpuset/memory_spread_slab # ./lfile allocated on nodes: 6 7 8 9 0 1 2 3 4 5 This patch introduces a second rotor that is used for slab allocations. Signed-off-by: Jack Steiner Acked-by: Christoph Lameter Cc: Pekka Enberg Cc: Paul Menage Cc: Jack Steiner Cc: Robin Holt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 6 ++++++ include/linux/sched.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 20b51cab6593..457ed765a116 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -69,6 +69,7 @@ extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); extern int cpuset_mem_spread_node(void); +extern int cpuset_slab_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { @@ -194,6 +195,11 @@ static inline int cpuset_mem_spread_node(void) return 0; } +static inline int cpuset_slab_spread_node(void) +{ + return 0; +} + static inline int cpuset_do_page_mem_spread(void) { return 0; diff --git a/include/linux/sched.h b/include/linux/sched.h index c0151ffd3541..4f31a166b1a1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1423,6 +1423,7 @@ struct task_struct { nodemask_t mems_allowed; /* Protected by alloc_lock */ int mems_allowed_change_disable; int cpuset_mem_spread_rotor; + int cpuset_slab_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock */ -- cgit v1.2.3 From 0ac0c0d0f837c499afd02a802f9cf52d3027fa3b Mon Sep 17 00:00:00 2001 From: Jack Steiner Date: Wed, 26 May 2010 14:42:51 -0700 Subject: cpusets: randomize node rotor used in cpuset_mem_spread_node() Some workloads that create a large number of small files tend to assign too many pages to node 0 (multi-node systems). Part of the reason is that the rotor (in cpuset_mem_spread_node()) used to assign nodes starts at node 0 for newly created tasks. This patch changes the rotor to be initialized to a random node number of the cpuset. [akpm@linux-foundation.org: fix layout] [Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration] Signed-off-by: Jack Steiner Signed-off-by: Lee Schermerhorn Cc: Christoph Lameter Cc: Pekka Enberg Cc: Paul Menage Cc: Jack Steiner Cc: Robin Holt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 1 + include/linux/nodemask.h | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index daf8c480c786..6fb2720882fc 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -141,6 +141,7 @@ extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order); extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits); +extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits); #define BITMAP_LAST_WORD_MASK(nbits) \ ( \ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index dba35e413371..8a8f1d09c133 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -66,6 +66,8 @@ * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * + * int node_random(mask) Random node with set bit in mask + * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * @@ -430,6 +432,10 @@ static inline void node_set_offline(int nid) node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } + +#define node_random(mask) __node_random(&(mask)) +extern int __node_random(const nodemask_t *maskp); + #else static inline int node_state(int node, enum node_states state) @@ -460,6 +466,8 @@ static inline int num_node_state(enum node_states state) #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) + +static inline int node_random(const nodemask_t mask) { return 0; } #endif #define node_online_map node_states[N_ONLINE] -- cgit v1.2.3 From a06a4dc3a08201ff6a8a958f935b3cbf7744115f Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Wed, 26 May 2010 14:42:58 -0700 Subject: kmod: add init function to usermodehelper About 6 months ago, I made a set of changes to how the core-dump-to-a-pipe feature in the kernel works. We had reports of several races, including some reports of apps bypassing our recursion check so that a process that was forked as part of a core_pattern setup could infinitely crash and refork until the system crashed. We fixed those by improving our recursion checks. The new check basically refuses to fork a process if its core limit is zero, which works well. Unfortunately, I've been getting grief from maintainer of user space programs that are inserted as the forked process of core_pattern. They contend that in order for their programs (such as abrt and apport) to work, all the running processes in a system must have their core limits set to a non-zero value, to which I say 'yes'. I did this by design, and think thats the right way to do things. But I've been asked to ease this burden on user space enough times that I thought I would take a look at it. The first suggestion was to make the recursion check fail on a non-zero 'special' number, like one. That way the core collector process could set its core size ulimit to 1, and enable the kernel's recursion detection. This isn't a bad idea on the surface, but I don't like it since its opt-in, in that if a program like abrt or apport has a bug and fails to set such a core limit, we're left with a recursively crashing system again. So I've come up with this. What I've done is modify the call_usermodehelper api such that an extra parameter is added, a function pointer which will be called by the user helper task, after it forks, but before it exec's the required process. This will give the caller the opportunity to get a call back in the processes context, allowing it to do whatever it needs to to the process in the kernel prior to exec-ing the user space code. In the case of do_coredump, this callback is ues to set the core ulimit of the helper process to 1. This elimnates the opt-in problem that I had above, as it allows the ulimit for core sizes to be set to the value of 1, which is what the recursion check looks for in do_coredump. This patch: Create new function call_usermodehelper_fns() and allow it to assign both an init and cleanup function, as we'll as arbitrary data. The init function is called from the context of the forked process and allows for customization of the helper process prior to calling exec. Its return code gates the continuation of the process, or causes its exit. Also add an arbitrary data pointer to the subprocess_info struct allowing for data to be passed from the caller to the new process, and the subsequent cleanup process Also, use this patch to cleanup the cleanup function. It currently takes an argp and envp pointer for freeing, which is ugly. Lets instead just make the subprocess_info structure public, and pass that to the cleanup and init routines Signed-off-by: Neil Horman Reviewed-by: Oleg Nesterov Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmod.h | 51 +++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 41 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index facb27fe7de0..f9edf63e90ea 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -23,6 +23,7 @@ #include #include #include +#include #define KMOD_PATH_LEN 256 @@ -45,7 +46,27 @@ static inline int request_module_nowait(const char *name, ...) { return -ENOSYS; struct key; struct file; -struct subprocess_info; + +enum umh_wait { + UMH_NO_WAIT = -1, /* don't wait at all */ + UMH_WAIT_EXEC = 0, /* wait for the exec, but not the process */ + UMH_WAIT_PROC = 1, /* wait for the process to complete */ +}; + +struct subprocess_info { + struct work_struct work; + struct completion *complete; + struct cred *cred; + char *path; + char **argv; + char **envp; + enum umh_wait wait; + int retval; + struct file *stdin; + int (*init)(struct subprocess_info *info); + void (*cleanup)(struct subprocess_info *info); + void *data; +}; /* Allocate a subprocess_info structure */ struct subprocess_info *call_usermodehelper_setup(char *path, char **argv, @@ -56,14 +77,10 @@ void call_usermodehelper_setkeys(struct subprocess_info *info, struct key *session_keyring); int call_usermodehelper_stdinpipe(struct subprocess_info *sub_info, struct file **filp); -void call_usermodehelper_setcleanup(struct subprocess_info *info, - void (*cleanup)(char **argv, char **envp)); - -enum umh_wait { - UMH_NO_WAIT = -1, /* don't wait at all */ - UMH_WAIT_EXEC = 0, /* wait for the exec, but not the process */ - UMH_WAIT_PROC = 1, /* wait for the process to complete */ -}; +void call_usermodehelper_setfns(struct subprocess_info *info, + int (*init)(struct subprocess_info *info), + void (*cleanup)(struct subprocess_info *info), + void *data); /* Actually execute the sub-process */ int call_usermodehelper_exec(struct subprocess_info *info, enum umh_wait wait); @@ -73,17 +90,31 @@ int call_usermodehelper_exec(struct subprocess_info *info, enum umh_wait wait); void call_usermodehelper_freeinfo(struct subprocess_info *info); static inline int -call_usermodehelper(char *path, char **argv, char **envp, enum umh_wait wait) +call_usermodehelper_fns(char *path, char **argv, char **envp, + enum umh_wait wait, + int (*init)(struct subprocess_info *info), + void (*cleanup)(struct subprocess_info *), void *data) { struct subprocess_info *info; gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL; info = call_usermodehelper_setup(path, argv, envp, gfp_mask); + if (info == NULL) return -ENOMEM; + + call_usermodehelper_setfns(info, init, cleanup, data); + return call_usermodehelper_exec(info, wait); } +static inline int +call_usermodehelper(char *path, char **argv, char **envp, enum umh_wait wait) +{ + return call_usermodehelper_fns(path, argv, envp, wait, + NULL, NULL, NULL); +} + static inline int call_usermodehelper_keys(char *path, char **argv, char **envp, struct key *session_keyring, enum umh_wait wait) -- cgit v1.2.3 From 898b374af6f71041bd3bceebe257e564f3f1d458 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Wed, 26 May 2010 14:42:59 -0700 Subject: exec: replace call_usermodehelper_pipe with use of umh init function and resolve limit The first patch in this series introduced an init function to the call_usermodehelper api so that processes could be customized by caller. This patch takes advantage of that fact, by customizing the helper in do_coredump to create the pipe and set its core limit to one (for our recusrsion check). This lets us clean up the previous uglyness in the usermodehelper internals and factor call_usermodehelper out entirely. While I'm at it, we can also modify the helper setup to look for a core limit value of 1 rather than zero for our recursion check Signed-off-by: Neil Horman Reviewed-by: Oleg Nesterov Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmod.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index f9edf63e90ea..5c058778ad35 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -62,7 +62,6 @@ struct subprocess_info { char **envp; enum umh_wait wait; int retval; - struct file *stdin; int (*init)(struct subprocess_info *info); void (*cleanup)(struct subprocess_info *info); void *data; @@ -75,8 +74,6 @@ struct subprocess_info *call_usermodehelper_setup(char *path, char **argv, /* Set various pieces of state into the subprocess_info structure */ void call_usermodehelper_setkeys(struct subprocess_info *info, struct key *session_keyring); -int call_usermodehelper_stdinpipe(struct subprocess_info *sub_info, - struct file **filp); void call_usermodehelper_setfns(struct subprocess_info *info, int (*init)(struct subprocess_info *info), void (*cleanup)(struct subprocess_info *info), @@ -132,10 +129,6 @@ call_usermodehelper_keys(char *path, char **argv, char **envp, extern void usermodehelper_init(void); -struct file; -extern int call_usermodehelper_pipe(char *path, char *argv[], char *envp[], - struct file **filp); - extern int usermodehelper_disable(void); extern void usermodehelper_enable(void); -- cgit v1.2.3 From 685bfd2c48bb3284d31e73ff3151c957d76deda9 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 26 May 2010 14:43:00 -0700 Subject: umh: creds: convert call_usermodehelper_keys() to use subprocess_info->init() call_usermodehelper_keys() uses call_usermodehelper_setkeys() to change subprocess_info->cred in advance. Now that we have info->init() we can change this code to set tgcred->session_keyring in context of execing kernel thread. Note: since currently call_usermodehelper_keys() is never called with UMH_NO_WAIT, call_usermodehelper_keys()->key_get() and umh_keys_cleanup() are not really needed, we could rely on install_session_keyring_to_cred() which does key_get() on success. Signed-off-by: Oleg Nesterov Acked-by: Neil Horman Acked-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmod.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 5c058778ad35..d876dce217f0 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -72,8 +72,6 @@ struct subprocess_info *call_usermodehelper_setup(char *path, char **argv, char **envp, gfp_t gfp_mask); /* Set various pieces of state into the subprocess_info structure */ -void call_usermodehelper_setkeys(struct subprocess_info *info, - struct key *session_keyring); void call_usermodehelper_setfns(struct subprocess_info *info, int (*init)(struct subprocess_info *info), void (*cleanup)(struct subprocess_info *info), @@ -112,21 +110,6 @@ call_usermodehelper(char *path, char **argv, char **envp, enum umh_wait wait) NULL, NULL, NULL); } -static inline int -call_usermodehelper_keys(char *path, char **argv, char **envp, - struct key *session_keyring, enum umh_wait wait) -{ - struct subprocess_info *info; - gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL; - - info = call_usermodehelper_setup(path, argv, envp, gfp_mask); - if (info == NULL) - return -ENOMEM; - - call_usermodehelper_setkeys(info, session_keyring); - return call_usermodehelper_exec(info, wait); -} - extern void usermodehelper_init(void); extern int usermodehelper_disable(void); -- cgit v1.2.3 From c70a626d3eba373514c72287c93588b6974a0059 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 26 May 2010 14:43:01 -0700 Subject: umh: creds: kill subprocess_info->cred logic Now that nobody ever changes subprocess_info->cred we can kill this member and related code. ____call_usermodehelper() always runs in the context of freshly forked kernel thread, it has the proper ->cred copied from its parent kthread, keventd. Signed-off-by: Oleg Nesterov Acked-by: Neil Horman Acked-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cred.h | 1 - include/linux/kmod.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cred.h b/include/linux/cred.h index 52507c3e1387..75c0fa881308 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -156,7 +156,6 @@ extern int copy_creds(struct task_struct *, unsigned long); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); -extern struct cred *prepare_usermodehelper_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern const struct cred *override_creds(const struct cred *); diff --git a/include/linux/kmod.h b/include/linux/kmod.h index d876dce217f0..6efd7a78de6a 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -56,7 +56,6 @@ enum umh_wait { struct subprocess_info { struct work_struct work; struct completion *complete; - struct cred *cred; char *path; char **argv; char **envp; -- cgit v1.2.3 From 09faef11df8c559a23e2405d123cb2683733a79a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 26 May 2010 14:43:11 -0700 Subject: exit: change zap_other_threads() to count sub-threads Change zap_other_threads() to return the number of other sub-threads found on ->thread_group list. Other changes are cosmetic: - change the code to use while_each_thread() helper - remove the obsolete comment about SIGKILL/SIGSTOP Signed-off-by: Oleg Nesterov Acked-by: Roland McGrath Cc: Veaceslav Falico Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4f31a166b1a1..a95a2455cebe 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2036,7 +2036,7 @@ extern int do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int, struct task_struct *); extern int send_sig(int, struct task_struct *, int); -extern void zap_other_threads(struct task_struct *p); +extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group); -- cgit v1.2.3 From ea6d290ca34c4fd91b7348338c0cc7bdeff94a35 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 26 May 2010 14:43:16 -0700 Subject: signals: make task_struct->signal immutable/refcountable We have a lot of problems with accessing task_struct->signal, it can "disappear" at any moment. Even current can't use its ->signal safely after exit_notify(). ->siglock helps, but it is not convenient, not always possible, and sometimes it makes sense to use task->signal even after this task has already dead. This patch adds the reference counter, sigcnt, into signal_struct. This reference is owned by task_struct and it is dropped in __put_task_struct(). Perhaps it makes sense to export get/put_signal_struct() later, but currently I don't see the immediate reason. Rename __cleanup_signal() to free_signal_struct() and unexport it. With the previous changes it does nothing except kmem_cache_free(). Change __exit_signal() to not clear/free ->signal, it will be freed when the last reference to any thread in the thread group goes away. Note: - when the last thead exits signal->tty can point to nowhere, see the next patch. - with or without this patch signal_struct->count should go away, or at least it should be "int nr_threads" for fs/proc. This will be addressed later. Signed-off-by: Oleg Nesterov Cc: Alan Cox Cc: Ingo Molnar Cc: Peter Zijlstra Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a95a2455cebe..32e309df408c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -527,6 +527,7 @@ struct thread_group_cputimer { * the locking of signal_struct. */ struct signal_struct { + atomic_t sigcnt; atomic_t count; atomic_t live; @@ -2101,7 +2102,6 @@ extern void flush_thread(void); extern void exit_thread(void); extern void exit_files(struct task_struct *); -extern void __cleanup_signal(struct signal_struct *); extern void __cleanup_sighand(struct sighand_struct *); extern void exit_itimers(struct signal_struct *); -- cgit v1.2.3 From b7b8ff6373d4b910af081f76888395e6df53249d Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 26 May 2010 14:43:18 -0700 Subject: signals: kill the awful task_rq_unlock_wait() hack Now that task->signal can't go away we can revert the horrible hack added by ad474caca3e2a0550b7ce0706527ad5ab389a4d4 ("fix for account_group_exec_runtime(), make sure ->signal can't be freed under rq->lock"). And we can do more cleanups sched_stats.h/posix-cpu-timers.c later. Signed-off-by: Oleg Nesterov Cc: Alan Cox Cc: Ingo Molnar Cc: Peter Zijlstra Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 32e309df408c..2d1e1a1228ef 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -268,7 +268,6 @@ extern void init_idle(struct task_struct *idle, int cpu); extern void init_idle_bootup_task(struct task_struct *idle); extern int runqueue_is_locked(int cpu); -extern void task_rq_unlock_wait(struct task_struct *p); extern cpumask_var_t nohz_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) -- cgit v1.2.3 From a705be6b5e8b05f2ae51536ec709de921960326c Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 26 May 2010 14:43:19 -0700 Subject: kill the obsolete thread_group_cputime_free() helper Kill the empty thread_group_cputime_free() helper. It was needed to free the per-cpu data which we no longer have. Signed-off-by: Oleg Nesterov Cc: Balbir Singh Cc: Roland McGrath Cc: Veaceslav Falico Cc: Stanislaw Gruszka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2d1e1a1228ef..dd597d8013a8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2393,10 +2393,6 @@ static inline void thread_group_cputime_init(struct signal_struct *sig) spin_lock_init(&sig->cputimer.lock); } -static inline void thread_group_cputime_free(struct signal_struct *sig) -{ -} - /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. -- cgit v1.2.3 From 7e49827cc937a742ae02078b483e3eb78f791a2a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 26 May 2010 14:43:22 -0700 Subject: proc: get_nr_threads() doesn't need ->siglock any longer Now that task->signal can't go away get_nr_threads() doesn't need ->siglock to read signal->count. Also, make it inline, move into sched.h, and convert 2 other proc users of signal->count to use this (now trivial) helper. Henceforth get_nr_threads() is the only valid user of signal->count, we are ready to turn it into "int nr_threads" or, perhaps, kill it. Signed-off-by: Oleg Nesterov Cc: Alexey Dobriyan Cc: David Howells Cc: "Eric W. Biederman" Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index dd597d8013a8..ccd2d1500720 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2147,6 +2147,11 @@ extern bool current_is_single_threaded(void); #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) +static inline int get_nr_threads(struct task_struct *tsk) +{ + return atomic_read(&tsk->signal->count); +} + /* de_thread depends on thread_group_leader not being a pid based check */ #define thread_group_leader(p) (p == p->group_leader) -- cgit v1.2.3 From b3ac022cb9dc5883505a88b159d1b240ad1ef405 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 26 May 2010 14:43:24 -0700 Subject: proc: turn signal_struct->count into "int nr_threads" No functional changes, just s/atomic_t count/int nr_threads/. With the recent changes this counter has a single user, get_nr_threads() And, none of its callers need the really accurate number of threads, not to mention each caller obviously races with fork/exit. It is only used to report this value to the user-space, except first_tid() uses it to avoid the unnecessary while_each_thread() loop in the unlikely case. It is a bit sad we need a word in struct signal_struct for this, perhaps we can change get_nr_threads() to approximate the number of threads using signal->live and kill ->nr_threads later. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Oleg Nesterov Cc: Alexey Dobriyan Cc: "Eric W. Biederman" Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 2 +- include/linux/sched.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 7996fc2c9ba9..0551e0dcb71b 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -16,7 +16,7 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; #define INIT_SIGNALS(sig) { \ - .count = ATOMIC_INIT(1), \ + .nr_threads = 1, \ .wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\ .shared_pending = { \ .list = LIST_HEAD_INIT(sig.shared_pending.list), \ diff --git a/include/linux/sched.h b/include/linux/sched.h index ccd2d1500720..f118809c953f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -527,8 +527,8 @@ struct thread_group_cputimer { */ struct signal_struct { atomic_t sigcnt; - atomic_t count; atomic_t live; + int nr_threads; wait_queue_head_t wait_chldexit; /* for wait4() */ @@ -2149,7 +2149,7 @@ extern bool current_is_single_threaded(void); static inline int get_nr_threads(struct task_struct *tsk) { - return atomic_read(&tsk->signal->count); + return tsk->signal->nr_threads; } /* de_thread depends on thread_group_leader not being a pid based check */ -- cgit v1.2.3 From b957e043ee557ca9b6bc451755ecd849b28852a4 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Wed, 26 May 2010 14:43:29 -0700 Subject: notifier: change notifier_from_errno(0) to return NOTIFY_OK This changes notifier_from_errno(0) to be NOTIFY_OK instead of NOTIFY_STOP_MASK | NOTIFY_OK. Currently, the notifiers which return encapsulated errno value have to do something like this: err = do_something(); // returns -errno if (err) return notifier_from_errno(err); else return NOTIFY_OK; This change makes the above code simple: err = do_something(); // returns -errno return return notifier_from_errno(err); Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/notifier.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 7c3609622334..540703b555cb 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -164,7 +164,10 @@ extern int __srcu_notifier_call_chain(struct srcu_notifier_head *nh, /* Encapsulate (negative) errno value (in particular, NOTIFY_BAD <=> EPERM). */ static inline int notifier_from_errno(int err) { - return NOTIFY_STOP_MASK | (NOTIFY_OK - err); + if (err) + return NOTIFY_STOP_MASK | (NOTIFY_OK - err); + + return NOTIFY_OK; } /* Restore (negative) errno value from notify return value. */ -- cgit v1.2.3 From 31a7c4746e9925512afab30557dd445d677cc802 Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Wed, 26 May 2010 14:43:42 -0700 Subject: ipc/sem.c: cacheline align the ipc spinlock for semaphores Cacheline align the spinlock for sysv semaphores. Without the patch, the spinlock and sem_otime [written by every semop that modified the array] and sem_base [read in the hot path of try_atomic_semop()] can be in the same cacheline. Signed-off-by: Manfred Spraul Cc: Chris Mason Cc: Zach Brown Cc: Jens Axboe Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sem.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sem.h b/include/linux/sem.h index 8a4adbef8a0f..f2961afa2f66 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -79,6 +79,7 @@ struct seminfo { #ifdef __KERNEL__ #include #include +#include struct task_struct; @@ -91,7 +92,8 @@ struct sem { /* One sem_array data structure for each set of semaphores in the system. */ struct sem_array { - struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ + struct kern_ipc_perm ____cacheline_aligned_in_smp + sem_perm; /* permissions .. see ipc.h */ time_t sem_otime; /* last semop time */ time_t sem_ctime; /* last change time */ struct sem *sem_base; /* ptr to first semaphore in array */ -- cgit v1.2.3 From 07590ff03935a2efbc03bc7861f20c059576a479 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Wed, 26 May 2010 14:43:57 -0700 Subject: rapidio: add IDT CPS/TSI switches Extentions to RapidIO switch support: 1. modify switch route operation declarations to allow using single switch-specific file for family of switches that share the same route table operations. 2. add standard route table operations for switches that that support route table manipulation registers as defined in the Rev.1.3 of RapidIO specification. 3. add clear-route-table operation for switches 4. add CPSxx and TSIxxx families of RapidIO switches Signed-off-by: Alexandre Bounine Tested-by: Thomas Moll Cc: Matt Porter Cc: Li Yang Cc: Kumar Gala Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 6 ++++++ include/linux/rio_ids.h | 14 ++++++++++++++ include/linux/rio_regs.h | 14 ++++++++++++-- 3 files changed, 32 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index dc0c75556c63..29d98997c6c8 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -213,6 +213,7 @@ struct rio_net { * @route_table: Copy of switch routing table * @add_entry: Callback for switch-specific route add function * @get_entry: Callback for switch-specific route get function + * @clr_table: Callback for switch-specific clear route table function */ struct rio_switch { struct list_head node; @@ -224,6 +225,8 @@ struct rio_switch { u16 table, u16 route_destid, u8 route_port); int (*get_entry) (struct rio_mport * mport, u16 destid, u8 hopcount, u16 table, u16 route_destid, u8 * route_port); + int (*clr_table) (struct rio_mport *mport, u16 destid, u8 hopcount, + u16 table); }; /* Low-level architecture-dependent routines */ @@ -307,6 +310,7 @@ struct rio_device_id { * @did: RIO device ID * @add_hook: Callback that adds a route entry * @get_hook: Callback that gets a route entry + * @clr_hook: Callback that clears a switch route table (may be NULL) * * Defines the operations that are necessary to manipulate the route * tables for a particular RIO switch device. @@ -317,6 +321,8 @@ struct rio_route_ops { u16 table, u16 route_destid, u8 route_port); int (*get_hook) (struct rio_mport * mport, u16 destid, u8 hopcount, u16 table, u16 route_destid, u8 * route_port); + int (*clr_hook) (struct rio_mport *mport, u16 destid, u8 hopcount, + u16 table); }; /* Architecture and hardware-specific functions */ diff --git a/include/linux/rio_ids.h b/include/linux/rio_ids.h index 919d4e07d54e..db50e1c288b7 100644 --- a/include/linux/rio_ids.h +++ b/include/linux/rio_ids.h @@ -20,5 +20,19 @@ #define RIO_VID_TUNDRA 0x000d #define RIO_DID_TSI500 0x0500 +#define RIO_DID_TSI568 0x0568 +#define RIO_DID_TSI572 0x0572 +#define RIO_DID_TSI574 0x0574 +#define RIO_DID_TSI576 0x0578 /* Same ID as Tsi578 */ +#define RIO_DID_TSI577 0x0577 +#define RIO_DID_TSI578 0x0578 + +#define RIO_VID_IDT 0x0038 +#define RIO_DID_IDT70K200 0x0310 +#define RIO_DID_IDTCPS8 0x035c +#define RIO_DID_IDTCPS12 0x035d +#define RIO_DID_IDTCPS16 0x035b +#define RIO_DID_IDTCPS6Q 0x035f +#define RIO_DID_IDTCPS10Q 0x035e #endif /* LINUX_RIO_IDS_H */ diff --git a/include/linux/rio_regs.h b/include/linux/rio_regs.h index 326540f9b54e..4bfb0dcfac7c 100644 --- a/include/linux/rio_regs.h +++ b/include/linux/rio_regs.h @@ -39,6 +39,8 @@ #define RIO_PEF_INB_MBOX2 0x00200000 /* [II] Mailbox 2 */ #define RIO_PEF_INB_MBOX3 0x00100000 /* [II] Mailbox 3 */ #define RIO_PEF_INB_DOORBELL 0x00080000 /* [II] Doorbells */ +#define RIO_PEF_EXT_RT 0x00000200 /* [III, 1.3] Extended route table support */ +#define RIO_PEF_STD_RT 0x00000100 /* [III, 1.3] Standard route table support */ #define RIO_PEF_CTLS 0x00000010 /* [III] CTLS */ #define RIO_PEF_EXT_FEATURES 0x00000008 /* [I] EFT_PTR valid */ #define RIO_PEF_ADDR_66 0x00000004 /* [I] 66 bits */ @@ -91,7 +93,10 @@ #define RIO_OPS_ATOMIC_CLR 0x00000010 /* [I] Atomic clr op */ #define RIO_OPS_PORT_WRITE 0x00000004 /* [I] Port-write op */ - /* 0x20-0x3c *//* Reserved */ + /* 0x20-0x30 *//* Reserved */ + +#define RIO_SWITCH_RT_LIMIT 0x34 /* [III, 1.3] Switch Route Table Destination ID Limit CAR */ +#define RIO_RT_MAX_DESTID 0x0000ffff #define RIO_MBOX_CSR 0x40 /* [II] Mailbox CSR */ #define RIO_MBOX0_AVAIL 0x80000000 /* [II] Mbox 0 avail */ @@ -153,7 +158,11 @@ #define RIO_HOST_DID_LOCK_CSR 0x68 /* [III] Host Base Device ID Lock CSR */ #define RIO_COMPONENT_TAG_CSR 0x6c /* [III] Component Tag CSR */ - /* 0x70-0xf8 *//* Reserved */ +#define RIO_STD_RTE_CONF_DESTID_SEL_CSR 0x70 +#define RIO_STD_RTE_CONF_PORT_SEL_CSR 0x74 +#define RIO_STD_RTE_DEFAULT_PORT 0x78 + + /* 0x7c-0xf8 *//* Reserved */ /* 0x100-0xfff8 *//* [I] Extended Features Space */ /* 0x10000-0xfffff8 *//* [I] Implementation-defined Space */ @@ -186,6 +195,7 @@ #define RIO_EFB_SER_EP_ID 0x0004 /* [VI] LP/Serial EP Devices */ #define RIO_EFB_SER_EP_REC_ID 0x0005 /* [VI] LP/Serial EP Recovery Devices */ #define RIO_EFB_SER_EP_FREE_ID 0x0006 /* [VI] LP/Serial EP Free Devices */ +#define RIO_EFB_SER_EP_FREC_ID 0x0009 /* [VI] LP/Serial EP Free Recovery Devices */ /* * Physical 8/16 LP-LVDS -- cgit v1.2.3 From e5cabeb3d60f9cd3e3950aff071319ae0e2d08d8 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Wed, 26 May 2010 14:43:59 -0700 Subject: rapidio: add Port-Write handling for EM Add RapidIO Port-Write message handling in the context of Error Management Extensions Specification Rev.1.3. Signed-off-by: Alexandre Bounine Tested-by: Thomas Moll Cc: Matt Porter Cc: Li Yang Cc: Kumar Gala Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 42 +++++++++++++++++++++++++++++++++ include/linux/rio_drv.h | 6 +++++ include/linux/rio_regs.h | 61 +++++++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 106 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index 29d98997c6c8..4ec31f44f406 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -64,10 +64,13 @@ #define RIO_INB_MBOX_RESOURCE 1 #define RIO_OUTB_MBOX_RESOURCE 2 +#define RIO_PW_MSG_SIZE 64 + extern struct bus_type rio_bus_type; extern struct list_head rio_devices; /* list of all devices */ struct rio_mport; +union rio_pw_msg; /** * struct rio_dev - RIO device info @@ -107,11 +110,15 @@ struct rio_dev { u32 swpinfo; /* Only used for switches */ u32 src_ops; u32 dst_ops; + u32 comp_tag; + u32 phys_efptr; + u32 em_efptr; u64 dma_mask; struct rio_switch *rswitch; /* RIO switch info */ struct rio_driver *driver; /* RIO driver claiming this device */ struct device dev; /* LDM device structure */ struct resource riores[RIO_MAX_DEV_RESOURCES]; + int (*pwcback) (struct rio_dev *rdev, union rio_pw_msg *msg, int step); u16 destid; }; @@ -211,9 +218,12 @@ struct rio_net { * @hopcount: Hopcount to this switch * @destid: Associated destid in the path * @route_table: Copy of switch routing table + * @port_ok: Status of each port (one bit per port) - OK=1 or UNINIT=0 * @add_entry: Callback for switch-specific route add function * @get_entry: Callback for switch-specific route get function * @clr_table: Callback for switch-specific clear route table function + * @em_init: Callback for switch-specific error management initialization function + * @em_handle: Callback for switch-specific error management handler function */ struct rio_switch { struct list_head node; @@ -221,12 +231,15 @@ struct rio_switch { u16 hopcount; u16 destid; u8 *route_table; + u32 port_ok; int (*add_entry) (struct rio_mport * mport, u16 destid, u8 hopcount, u16 table, u16 route_destid, u8 route_port); int (*get_entry) (struct rio_mport * mport, u16 destid, u8 hopcount, u16 table, u16 route_destid, u8 * route_port); int (*clr_table) (struct rio_mport *mport, u16 destid, u8 hopcount, u16 table); + int (*em_init) (struct rio_dev *dev); + int (*em_handle) (struct rio_dev *dev, u8 swport); }; /* Low-level architecture-dependent routines */ @@ -238,6 +251,7 @@ struct rio_switch { * @cread: Callback to perform network read of config space. * @cwrite: Callback to perform network write of config space. * @dsend: Callback to send a doorbell message. + * @pwenable: Callback to enable/disable port-write message handling. */ struct rio_ops { int (*lcread) (struct rio_mport *mport, int index, u32 offset, int len, @@ -249,6 +263,7 @@ struct rio_ops { int (*cwrite) (struct rio_mport *mport, int index, u16 destid, u8 hopcount, u32 offset, int len, u32 data); int (*dsend) (struct rio_mport *mport, int index, u16 destid, u16 data); + int (*pwenable) (struct rio_mport *mport, int enable); }; #define RIO_RESOURCE_MEM 0x00000100 @@ -325,6 +340,33 @@ struct rio_route_ops { u16 table); }; +/** + * struct rio_em_ops - Per-switch error management operations + * @vid: RIO vendor ID + * @did: RIO device ID + * @init_hook: Switch specific error management initialization (may be NULL) + * @handler_hook: Switch specific error management handler (may be NULL) + * + * Defines the operations that are necessary to initialize and handle + * error management events for a particular RIO switch device. + */ +struct rio_em_ops { + u16 vid, did; + int (*init_hook) (struct rio_dev *dev); + int (*handler_hook) (struct rio_dev *dev, u8 swport); +}; + +union rio_pw_msg { + struct { + u32 comptag; /* Component Tag CSR */ + u32 errdetect; /* Port N Error Detect CSR */ + u32 is_port; /* Implementation specific + PortID */ + u32 ltlerrdet; /* LTL Error Detect CSR */ + u32 padding[12]; + } em; + u32 raw[RIO_PW_MSG_SIZE/sizeof(u32)]; +}; + /* Architecture and hardware-specific functions */ extern int rio_init_mports(void); extern void rio_register_mport(struct rio_mport *); diff --git a/include/linux/rio_drv.h b/include/linux/rio_drv.h index c93a58a40033..edc55da717b3 100644 --- a/include/linux/rio_drv.h +++ b/include/linux/rio_drv.h @@ -413,6 +413,12 @@ void rio_release_regions(struct rio_dev *); int rio_request_region(struct rio_dev *, int, char *); void rio_release_region(struct rio_dev *, int); +/* Port-Write management */ +extern int rio_request_inb_pwrite(struct rio_dev *, + int (*)(struct rio_dev *, union rio_pw_msg*, int)); +extern int rio_release_inb_pwrite(struct rio_dev *); +extern int rio_inb_pwrite_handler(union rio_pw_msg *pw_msg); + /* LDM support */ int rio_register_driver(struct rio_driver *); void rio_unregister_driver(struct rio_driver *); diff --git a/include/linux/rio_regs.h b/include/linux/rio_regs.h index 4bfb0dcfac7c..96ba2159d9fe 100644 --- a/include/linux/rio_regs.h +++ b/include/linux/rio_regs.h @@ -192,10 +192,14 @@ #define RIO_EFB_PAR_EP_ID 0x0001 /* [IV] LP/LVDS EP Devices */ #define RIO_EFB_PAR_EP_REC_ID 0x0002 /* [IV] LP/LVDS EP Recovery Devices */ #define RIO_EFB_PAR_EP_FREE_ID 0x0003 /* [IV] LP/LVDS EP Free Devices */ +#define RIO_EFB_SER_EP_ID_V13P 0x0001 /* [VI] LP/Serial EP Devices, RapidIO Spec ver 1.3 and above */ +#define RIO_EFB_SER_EP_REC_ID_V13P 0x0002 /* [VI] LP/Serial EP Recovery Devices, RapidIO Spec ver 1.3 and above */ +#define RIO_EFB_SER_EP_FREE_ID_V13P 0x0003 /* [VI] LP/Serial EP Free Devices, RapidIO Spec ver 1.3 and above */ #define RIO_EFB_SER_EP_ID 0x0004 /* [VI] LP/Serial EP Devices */ #define RIO_EFB_SER_EP_REC_ID 0x0005 /* [VI] LP/Serial EP Recovery Devices */ #define RIO_EFB_SER_EP_FREE_ID 0x0006 /* [VI] LP/Serial EP Free Devices */ #define RIO_EFB_SER_EP_FREC_ID 0x0009 /* [VI] LP/Serial EP Free Recovery Devices */ +#define RIO_EFB_ERR_MGMNT 0x0007 /* [VIII] Error Management Extensions */ /* * Physical 8/16 LP-LVDS @@ -211,15 +215,66 @@ #define RIO_PORT_MNT_HEADER 0x0000 #define RIO_PORT_REQ_CTL_CSR 0x0020 #define RIO_PORT_RSP_CTL_CSR 0x0024 /* 0x0001/0x0002 */ +#define RIO_PORT_LINKTO_CTL_CSR 0x0020 /* Serial */ +#define RIO_PORT_RSPTO_CTL_CSR 0x0024 /* Serial */ #define RIO_PORT_GEN_CTL_CSR 0x003c #define RIO_PORT_GEN_HOST 0x80000000 #define RIO_PORT_GEN_MASTER 0x40000000 #define RIO_PORT_GEN_DISCOVERED 0x20000000 #define RIO_PORT_N_MNT_REQ_CSR(x) (0x0040 + x*0x20) /* 0x0002 */ #define RIO_PORT_N_MNT_RSP_CSR(x) (0x0044 + x*0x20) /* 0x0002 */ +#define RIO_PORT_N_MNT_RSP_RVAL 0x80000000 /* Response Valid */ +#define RIO_PORT_N_MNT_RSP_ASTAT 0x000003e0 /* ackID Status */ +#define RIO_PORT_N_MNT_RSP_LSTAT 0x0000001f /* Link Status */ #define RIO_PORT_N_ACK_STS_CSR(x) (0x0048 + x*0x20) /* 0x0002 */ -#define RIO_PORT_N_ERR_STS_CSR(x) (0x58 + x*0x20) -#define PORT_N_ERR_STS_PORT_OK 0x00000002 -#define RIO_PORT_N_CTL_CSR(x) (0x5c + x*0x20) +#define RIO_PORT_N_ACK_CLEAR 0x80000000 +#define RIO_PORT_N_ACK_INBOUND 0x1f000000 +#define RIO_PORT_N_ACK_OUTSTAND 0x00001f00 +#define RIO_PORT_N_ACK_OUTBOUND 0x0000001f +#define RIO_PORT_N_ERR_STS_CSR(x) (0x0058 + x*0x20) +#define RIO_PORT_N_ERR_STS_PW_OUT_ES 0x00010000 /* Output Error-stopped */ +#define RIO_PORT_N_ERR_STS_PW_INP_ES 0x00000100 /* Input Error-stopped */ +#define RIO_PORT_N_ERR_STS_PW_PEND 0x00000010 /* Port-Write Pending */ +#define RIO_PORT_N_ERR_STS_PORT_ERR 0x00000004 +#define RIO_PORT_N_ERR_STS_PORT_OK 0x00000002 +#define RIO_PORT_N_ERR_STS_PORT_UNINIT 0x00000001 +#define RIO_PORT_N_ERR_STS_CLR_MASK 0x07120204 +#define RIO_PORT_N_CTL_CSR(x) (0x005c + x*0x20) +#define RIO_PORT_N_CTL_PWIDTH 0xc0000000 +#define RIO_PORT_N_CTL_PWIDTH_1 0x00000000 +#define RIO_PORT_N_CTL_PWIDTH_4 0x40000000 +#define RIO_PORT_N_CTL_LOCKOUT 0x00000002 + +/* + * Error Management Extensions (RapidIO 1.3+, Part 8) + * + * Extended Features Block ID=0x0007 + */ + +/* General EM Registers (Common for all Ports) */ + +#define RIO_EM_EFB_HEADER 0x000 /* Error Management Extensions Block Header */ +#define RIO_EM_LTL_ERR_DETECT 0x008 /* Logical/Transport Layer Error Detect CSR */ +#define RIO_EM_LTL_ERR_EN 0x00c /* Logical/Transport Layer Error Enable CSR */ +#define RIO_EM_LTL_HIADDR_CAP 0x010 /* Logical/Transport Layer High Address Capture CSR */ +#define RIO_EM_LTL_ADDR_CAP 0x014 /* Logical/Transport Layer Address Capture CSR */ +#define RIO_EM_LTL_DEVID_CAP 0x018 /* Logical/Transport Layer Device ID Capture CSR */ +#define RIO_EM_LTL_CTRL_CAP 0x01c /* Logical/Transport Layer Control Capture CSR */ +#define RIO_EM_PW_TGT_DEVID 0x028 /* Port-write Target deviceID CSR */ +#define RIO_EM_PKT_TTL 0x02c /* Packet Time-to-live CSR */ + +/* Per-Port EM Registers */ + +#define RIO_EM_PN_ERR_DETECT(x) (0x040 + x*0x40) /* Port N Error Detect CSR */ +#define REM_PED_IMPL_SPEC 0x80000000 +#define REM_PED_LINK_TO 0x00000001 +#define RIO_EM_PN_ERRRATE_EN(x) (0x044 + x*0x40) /* Port N Error Rate Enable CSR */ +#define RIO_EM_PN_ATTRIB_CAP(x) (0x048 + x*0x40) /* Port N Attributes Capture CSR */ +#define RIO_EM_PN_PKT_CAP_0(x) (0x04c + x*0x40) /* Port N Packet/Control Symbol Capture 0 CSR */ +#define RIO_EM_PN_PKT_CAP_1(x) (0x050 + x*0x40) /* Port N Packet Capture 1 CSR */ +#define RIO_EM_PN_PKT_CAP_2(x) (0x054 + x*0x40) /* Port N Packet Capture 2 CSR */ +#define RIO_EM_PN_PKT_CAP_3(x) (0x058 + x*0x40) /* Port N Packet Capture 3 CSR */ +#define RIO_EM_PN_ERRRATE(x) (0x068 + x*0x40) /* Port N Error Rate CSR */ +#define RIO_EM_PN_ERRRATE_TR(x) (0x06c + x*0x40) /* Port N Error Rate Threshold CSR */ #endif /* LINUX_RIO_REGS_H */ -- cgit v1.2.3 From 933af4a6c4913ab4c0691c8fb27fc305063889cd Mon Sep 17 00:00:00 2001 From: Thomas Moll Date: Wed, 26 May 2010 14:44:01 -0700 Subject: rapidio: add enabling SRIO port RX and TX Add the functionality to enable Input receiver and Output transmitter of every port, to allow non-maintenance traffic. Signed-off-by: Thomas Moll Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Li Yang Cc: Kumar Gala Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio_regs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rio_regs.h b/include/linux/rio_regs.h index 96ba2159d9fe..aedee0489fb4 100644 --- a/include/linux/rio_regs.h +++ b/include/linux/rio_regs.h @@ -243,7 +243,12 @@ #define RIO_PORT_N_CTL_PWIDTH 0xc0000000 #define RIO_PORT_N_CTL_PWIDTH_1 0x00000000 #define RIO_PORT_N_CTL_PWIDTH_4 0x40000000 +#define RIO_PORT_N_CTL_P_TYP_SER 0x00000001 #define RIO_PORT_N_CTL_LOCKOUT 0x00000002 +#define RIO_PORT_N_CTL_EN_RX_SER 0x00200000 +#define RIO_PORT_N_CTL_EN_TX_SER 0x00400000 +#define RIO_PORT_N_CTL_EN_RX_PAR 0x08000000 +#define RIO_PORT_N_CTL_EN_TX_PAR 0x40000000 /* * Error Management Extensions (RapidIO 1.3+, Part 8) -- cgit v1.2.3 From 058f88d672b3161fe511ebe2996c3faef63c1c8e Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Wed, 26 May 2010 14:44:03 -0700 Subject: rapidio: modify initialization of switch operations Modify the way how RapidIO switch operations are declared. Multiple assignments through the linker script replaced by single initialization call. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Li Yang Cc: Kumar Gala Cc: Thomas Moll Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 35 ++++++----------------------------- 1 file changed, 6 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index 4ec31f44f406..3d0ac930cbea 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -320,40 +320,17 @@ struct rio_device_id { }; /** - * struct rio_route_ops - Per-switch route operations + * struct rio_switch_ops - Per-switch operations * @vid: RIO vendor ID * @did: RIO device ID - * @add_hook: Callback that adds a route entry - * @get_hook: Callback that gets a route entry - * @clr_hook: Callback that clears a switch route table (may be NULL) + * @init_hook: Callback that performs switch device initialization * - * Defines the operations that are necessary to manipulate the route - * tables for a particular RIO switch device. + * Defines the operations that are necessary to initialize/control + * a particular RIO switch device. */ -struct rio_route_ops { +struct rio_switch_ops { u16 vid, did; - int (*add_hook) (struct rio_mport * mport, u16 destid, u8 hopcount, - u16 table, u16 route_destid, u8 route_port); - int (*get_hook) (struct rio_mport * mport, u16 destid, u8 hopcount, - u16 table, u16 route_destid, u8 * route_port); - int (*clr_hook) (struct rio_mport *mport, u16 destid, u8 hopcount, - u16 table); -}; - -/** - * struct rio_em_ops - Per-switch error management operations - * @vid: RIO vendor ID - * @did: RIO device ID - * @init_hook: Switch specific error management initialization (may be NULL) - * @handler_hook: Switch specific error management handler (may be NULL) - * - * Defines the operations that are necessary to initialize and handle - * error management events for a particular RIO switch device. - */ -struct rio_em_ops { - u16 vid, did; - int (*init_hook) (struct rio_dev *dev); - int (*handler_hook) (struct rio_dev *dev, u8 swport); + int (*init_hook) (struct rio_dev *rdev, int do_enum); }; union rio_pw_msg { -- cgit v1.2.3 From 7a88d6286240f1e8a0cf9c07252e1576169020f5 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Wed, 26 May 2010 14:44:04 -0700 Subject: rapidio: add switch domain routines Add switch specific domain routines required for 16-bit routing support in switches with hierarchical implementation of routing tables. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Li Yang Cc: Kumar Gala Cc: Thomas Moll Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index 3d0ac930cbea..19b5f227096e 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -238,6 +238,10 @@ struct rio_switch { u16 table, u16 route_destid, u8 * route_port); int (*clr_table) (struct rio_mport *mport, u16 destid, u8 hopcount, u16 table); + int (*set_domain) (struct rio_mport *mport, u16 destid, u8 hopcount, + u8 sw_domain); + int (*get_domain) (struct rio_mport *mport, u16 destid, u8 hopcount, + u8 *sw_domain); int (*em_init) (struct rio_dev *dev); int (*em_handle) (struct rio_dev *dev, u8 swport); }; -- cgit v1.2.3 From 72680a191b934377430032f93af15ef50aafb3a8 Mon Sep 17 00:00:00 2001 From: Hedi Berriche Date: Wed, 26 May 2010 14:44:06 -0700 Subject: pids: increase pid_max based on num_possible_cpus On a system with a substantial number of processors, the early default pid_max of 32k will not be enough. A system with 1664 CPU's, there are 25163 processes started before the login prompt. It's estimated that with 2048 CPU's we will pass the 32k limit. With 4096, we'll reach that limit very early during the boot cycle, and processes would stall waiting for an available pid. This patch increases the early maximum number of pids available, and increases the minimum number of pids that can be set during runtime. [akpm@linux-foundation.org: fix warnings] Signed-off-by: Hedi Berriche Signed-off-by: Mike Travis Signed-off-by: Robin Holt Acked-by: Linus Torvalds Cc: Ingo Molnar Cc: Pavel Machek Cc: Alan Cox Cc: Greg KH Cc: Rik van Riel Cc: John Stoffel Cc: Jack Steiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/threads.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/threads.h b/include/linux/threads.h index 052b12bec8bd..383ab9592bec 100644 --- a/include/linux/threads.h +++ b/include/linux/threads.h @@ -33,4 +33,13 @@ #define PID_MAX_LIMIT (CONFIG_BASE_SMALL ? PAGE_SIZE * 8 : \ (sizeof(long) > 4 ? 4 * 1024 * 1024 : PID_MAX_DEFAULT)) +/* + * Define a minimum number of pids per cpu. Heuristically based + * on original pid max of 32k for 32 cpus. Also, increase the + * minimum settable value for pid_max on the running system based + * on similar defaults. See kernel/pid.c:pidmap_init() for details. + */ +#define PIDS_PER_CPU_DEFAULT 1024 +#define PIDS_PER_CPU_MIN 8 + #endif -- cgit v1.2.3 From fa2755e20ab0c7215d99c2dc7c262e98a09b01df Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 26 May 2010 14:44:08 -0700 Subject: INIT_TASK() should initialize ->thread_group list The trivial /sbin/init doing int main(void) { kill(0, SIGKILL) } crashes the kernel. This happens because __kill_pgrp_info(init_struct_pid) also sends SIGKILL to the swapper process which runs with the uninitialized ->thread_group. Change INIT_TASK() to initialize ->thread_group properly. Note: the real problem is that the swapper process must not be visible to signals, see the next patch. But this change is right anyway and fixes the crash. Reported-and-tested-by: Mathias Krause Signed-off-by: Oleg Nesterov Cc: Cedric Le Goater Cc: Dave Hansen Cc: Eric Biederman Cc: Herbert Poetzl Cc: Mathias Krause Acked-by: Roland McGrath Acked-by: Serge Hallyn Acked-by: Sukadev Bhattiprolu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 0551e0dcb71b..6deb1ba52fdb 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -163,6 +163,7 @@ extern struct cred init_cred; [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \ [PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \ }, \ + .thread_group = LIST_HEAD_INIT(tsk.thread_group), \ .dirties = INIT_PROP_LOCAL_SINGLE(dirties), \ INIT_IDS \ INIT_PERF_EVENTS(tsk) \ -- cgit v1.2.3 From f20011457f41c11edb5ea5038ad0c8ea9f392023 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 26 May 2010 14:44:10 -0700 Subject: pids: init_struct_pid.tasks should never see the swapper process "statically initialize struct pid for swapper" commit 820e45db says: Statically initialize a struct pid for the swapper process (pid_t == 0) and attach it to init_task. This is needed so task_pid(), task_pgrp() and task_session() interfaces work on the swapper process also. OK, but: - it doesn't make sense to add init_task.pids[].node into init_struct_pid.tasks[], and in fact this just wrong. idle threads are special, they shouldn't be visible on any global list. In particular do_each_pid_task(init_struct_pid) shouldn't see swapper. This is the actual reason why kill(0, SIGKILL) from /sbin/init (which starts with 0,0 special pids) crashes the kernel. The signal sent to pgid/sid == 0 must never see idle threads, even if the previous patch fixed the crash itself. - we have other idle threads running on the non-boot CPUs, see the next patch. Change INIT_STRUCT_PID/INIT_PID_LINK to create the empty/unhashed hlist_head/hlist_node. Like any other idle thread swapper can never exit, so detach_pid()->__hlist_del() is not possible, but we could change INIT_PID_LINK() to set pprev = &next if needed. All we need is the valid swapper->pids[].pid == &init_struct_pid. Reported-by: Mathias Krause Signed-off-by: Oleg Nesterov Cc: Cedric Le Goater Cc: Dave Hansen Cc: Eric Biederman Cc: Herbert Poetzl Cc: Mathias Krause Acked-by: Roland McGrath Acked-by: Serge Hallyn Cc: Sukadev Bhattiprolu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 6deb1ba52fdb..94fecb748a28 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -45,9 +45,9 @@ extern struct group_info init_groups; #define INIT_STRUCT_PID { \ .count = ATOMIC_INIT(1), \ .tasks = { \ - { .first = &init_task.pids[PIDTYPE_PID].node }, \ - { .first = &init_task.pids[PIDTYPE_PGID].node }, \ - { .first = &init_task.pids[PIDTYPE_SID].node }, \ + { .first = NULL }, \ + { .first = NULL }, \ + { .first = NULL }, \ }, \ .level = 0, \ .numbers = { { \ @@ -61,7 +61,7 @@ extern struct group_info init_groups; { \ .node = { \ .next = NULL, \ - .pprev = &init_struct_pid.tasks[type].first, \ + .pprev = NULL, \ }, \ .pid = &init_struct_pid, \ } -- cgit v1.2.3 From 0a14a130cac9c6826bc81a089b12ab5cbb2b97fc Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 26 May 2010 14:44:12 -0700 Subject: INIT_SIGHAND: use SIG_DFL instead of NULL Cosmetic, no changes in the compiled code. Just s/NULL/SIG_DFL/ to make it more readable and grep-friendly. Note: probably SIG_IGN makes more sense, we could kill ignore_signals(). But then kernel_init() should do flush_signal_handlers() before exec(). Signed-off-by: Oleg Nesterov Cc: Cedric Le Goater Cc: Dave Hansen Cc: Eric Biederman Cc: Herbert Poetzl Cc: Mathias Krause Acked-by: Roland McGrath Acked-by: Serge Hallyn Cc: Sukadev Bhattiprolu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 94fecb748a28..2beaa13492be 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -35,7 +35,7 @@ extern struct nsproxy init_nsproxy; #define INIT_SIGHAND(sighand) { \ .count = ATOMIC_INIT(1), \ - .action = { { { .sa_handler = NULL, } }, }, \ + .action = { { { .sa_handler = SIG_DFL, } }, }, \ .siglock = __SPIN_LOCK_UNLOCKED(sighand.siglock), \ .signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(sighand.signalfd_wqh), \ } -- cgit v1.2.3 From 5960164fde9bc2f2a99e751d3393faea316e7e36 Mon Sep 17 00:00:00 2001 From: Joe Eykholt Date: Wed, 26 May 2010 14:44:13 -0700 Subject: lib/random32: export pseudo-random number generator for modules This patch moves the definition of struct rnd_state and the inline __seed() function to linux/random.h. It renames the static __random32() function to prandom32() and exports it for use in modules. prandom32() is useful as a privately-seeded pseudo random number generator that can give the same result every time it is initialized. For FCoE FC-BB-6 VN2VN mode self-selected unique FC address generation, we need an pseudo-random number generator seeded with the 64-bit world-wide port name. A truly random generator or one seeded with randomness won't do because the same sequence of numbers should be generated each time we boot or the link comes up. A prandom32_seed() inline function is added to the header file. It is inlined not for speed, but so the function won't be expanded in the base kernel, but only in the module that uses it. Signed-off-by: Joe Eykholt Acked-by: Matt Mackall Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/random.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index 25d02fe5c9b5..fb7ab9de5f36 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -40,6 +40,10 @@ struct rand_pool_info { __u32 buf[0]; }; +struct rnd_state { + __u32 s1, s2, s3; +}; + /* Exported functions */ #ifdef __KERNEL__ @@ -74,6 +78,30 @@ unsigned long randomize_range(unsigned long start, unsigned long end, unsigned l u32 random32(void); void srandom32(u32 seed); +u32 prandom32(struct rnd_state *); + +/* + * Handle minimum values for seeds + */ +static inline u32 __seed(u32 x, u32 m) +{ + return (x < m) ? x + m : x; +} + +/** + * prandom32_seed - set seed for prandom32(). + * @state: pointer to state structure to receive the seed. + * @seed: arbitrary 64-bit value to use as a seed. + */ +static inline void prandom32_seed(struct rnd_state *state, u64 seed) +{ + u32 i = (seed >> 32) ^ (seed << 10) ^ seed; + + state->s1 = __seed(i, 1); + state->s2 = __seed(i, 7); + state->s3 = __seed(i, 15); +} + #endif /* __KERNEL___ */ #endif /* _LINUX_RANDOM_H */ -- cgit v1.2.3 From 38388301b7b9d2921b58cfa1cd9b14c02d508c63 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Wed, 26 May 2010 14:44:18 -0700 Subject: swiotlb: remove unnecessary swiotlb_sync_single_range_* swiotlb_sync_single_range_for_cpu and swiotlb_sync_single_range_for_device are unnecessary because swiotlb_sync_single_for_cpu and swiotlb_sync_single_for_device can be used instead. Signed-off-by: FUJITA Tomonori Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swiotlb.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index febedcf67c7e..81a4e213c6cf 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -73,16 +73,6 @@ extern void swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, int nelems, enum dma_data_direction dir); -extern void -swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - unsigned long offset, size_t size, - enum dma_data_direction dir); - -extern void -swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr, - unsigned long offset, size_t size, - enum dma_data_direction dir); - extern int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr); -- cgit v1.2.3 From 5fd75a7850b5156aa93c9fb6404adb8f563b6e02 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Wed, 26 May 2010 14:44:18 -0700 Subject: dma-mapping: remove unnecessary sync_single_range_* in dma_map_ops sync_single_range_for_cpu and sync_single_range_for_device hooks are unnecessary because sync_single_for_cpu and sync_single_for_device can be used instead. Signed-off-by: FUJITA Tomonori Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dma-mapping.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index ca32ed78b057..2ea149435c44 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -40,16 +40,6 @@ struct dma_map_ops { void (*sync_single_for_device)(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir); - void (*sync_single_range_for_cpu)(struct device *dev, - dma_addr_t dma_handle, - unsigned long offset, - size_t size, - enum dma_data_direction dir); - void (*sync_single_range_for_device)(struct device *dev, - dma_addr_t dma_handle, - unsigned long offset, - size_t size, - enum dma_data_direction dir); void (*sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir); -- cgit v1.2.3 From 99d1bd2c131b2da10cf451c69e5b8c51761a901b Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Wed, 26 May 2010 14:44:20 -0700 Subject: dma-mapping: remove deprecated dma_sync_single and dma_sync_sg API Since 2.6.5, it had been commented, 'for backwards compatibility, removed in 2.7.x'. Since 2.6.31, it have been marked as __deprecated. I think that we can remove the API safely now. Signed-off-by: FUJITA Tomonori Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dma-mapping.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 2ea149435c44..89b7e1a605b8 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -95,21 +95,6 @@ static inline int is_device_dma_capable(struct device *dev) #include #endif -/* for backwards compatibility, removed soon */ -static inline void __deprecated dma_sync_single(struct device *dev, - dma_addr_t addr, size_t size, - enum dma_data_direction dir) -{ - dma_sync_single_for_cpu(dev, addr, size, dir); -} - -static inline void __deprecated dma_sync_sg(struct device *dev, - struct scatterlist *sg, int nelems, - enum dma_data_direction dir) -{ - dma_sync_sg_for_cpu(dev, sg, nelems, dir); -} - static inline u64 dma_get_mask(struct device *dev) { if (dev && dev->dma_mask && *dev->dma_mask) -- cgit v1.2.3 From b83733639a494d5f42fa00a2506563fbd2d3015d Mon Sep 17 00:00:00 2001 From: Jeff Moyer Date: Wed, 26 May 2010 14:44:25 -0700 Subject: compat: factor out compat_rw_copy_check_uvector from compat_do_readv_writev It was reported in http://lkml.org/lkml/2010/3/8/309 that 32 bit readv and writev AIO operations were not functioning properly. It turns out that the code to convert the 32bit io vectors to 64 bits was never written. The results of that can be pretty bad, but in my testing, it mostly ended up in generating EFAULT as we walked off the list of I/O vectors provided. This patch set fixes the problem in my environment. are greatly appreciated. This patch: Factor out code that will be used by both compat_do_readv_writev and the compat aio submission code paths. Signed-off-by: Jeff Moyer Reported-by: Michael Tokarev Cc: Zach Brown Cc: [2.6.35.1] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 717c691ecd8e..168f7daa7bde 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -356,5 +356,9 @@ asmlinkage long compat_sys_newfstatat(unsigned int dfd, char __user * filename, asmlinkage long compat_sys_openat(unsigned int dfd, const char __user *filename, int flags, int mode); +extern ssize_t compat_rw_copy_check_uvector(int type, + const struct compat_iovec __user *uvector, unsigned long nr_segs, + unsigned long fast_segs, struct iovec *fast_pointer, + struct iovec **ret_pointer); #endif /* CONFIG_COMPAT */ #endif /* _LINUX_COMPAT_H */ -- cgit v1.2.3 From 9d85cba718efeef9ca00ce3f7f34f5880737aa9b Mon Sep 17 00:00:00 2001 From: Jeff Moyer Date: Wed, 26 May 2010 14:44:26 -0700 Subject: aio: fix the compat vectored operations The aio compat code was not converting the struct iovecs from 32bit to 64bit pointers, causing either EINVAL to be returned from io_getevents, or EFAULT as the result of the I/O. This patch passes a compat flag to io_submit to signal that pointer conversion is necessary for a given iocb array. A variant of this was tested by Michael Tokarev. I have also updated the libaio test harness to exercise this code path with good success. Further, I grabbed a copy of ltp and ran the testcases/kernel/syscall/readv and writev tests there (compiled with -m32 on my 64bit system). All seems happy, but extra eyes on this would be welcome. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix CONFIG_COMPAT=n build] Signed-off-by: Jeff Moyer Reported-by: Michael Tokarev Cc: Zach Brown Cc: [2.6.35.1] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 811dbb369379..7a8db4155281 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -212,6 +212,8 @@ extern void kick_iocb(struct kiocb *iocb); extern int aio_complete(struct kiocb *iocb, long res, long res2); struct mm_struct; extern void exit_aio(struct mm_struct *mm); +extern long do_io_submit(aio_context_t ctx_id, long nr, + struct iocb __user *__user *iocbpp, bool compat); #else static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } static inline int aio_put_req(struct kiocb *iocb) { return 0; } @@ -219,6 +221,9 @@ static inline void kick_iocb(struct kiocb *iocb) { } static inline int aio_complete(struct kiocb *iocb, long res, long res2) { return 0; } struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } +static inline long do_io_submit(aio_context_t ctx_id, long nr, + struct iocb __user * __user *iocbpp, + bool compat) { return 0; } #endif /* CONFIG_AIO */ static inline struct kiocb *list_kiocb(struct list_head *h) -- cgit v1.2.3 From ae6afc3f5cf53fb97bac2d0a209bb465952742e7 Mon Sep 17 00:00:00 2001 From: jan Blunck Date: Wed, 26 May 2010 14:44:48 -0700 Subject: vfs: introduce noop_llseek() This is an implementation of ->llseek useable for the rare special case when userspace expects the seek to succeed but the (device) file is actually not able to perform the seek. In this case you use noop_llseek() instead of falling back to the default implementation of ->llseek. Signed-off-by: Jan Blunck Cc: Frederic Weisbecker Cc: Christoph Hellwig Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 b336cb9ca9a0..9682d52d1507 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2228,6 +2228,7 @@ extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); +extern loff_t noop_llseek(struct file *file, loff_t offset, int origin); extern loff_t no_llseek(struct file *file, loff_t offset, int origin); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin); extern loff_t generic_file_llseek_unlocked(struct file *file, loff_t offset, -- cgit v1.2.3 From 7281201922a0063fa60804ce39c277fc98142a47 Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Wed, 26 May 2010 14:44:56 -0700 Subject: numa: add generic percpu var numa_node_id() implementation Rework the generic version of the numa_node_id() function to use the new generic percpu variable infrastructure. Guard the new implementation with a new config option: CONFIG_USE_PERCPU_NUMA_NODE_ID. Archs which support this new implemention will default this option to 'y' when NUMA is configured. This config option could be removed if/when all archs switch over to the generic percpu implementation of numa_node_id(). Arch support involves: 1) converting any existing per cpu variable implementations to use this implementation. x86_64 is an instance of such an arch. 2) archs that don't use a per cpu variable for numa_node_id() will need to initialize the new per cpu variable "numa_node" as cpus are brought on-line. ia64 is an example. 3) Defining USE_PERCPU_NUMA_NODE_ID in arch dependent Kconfig--e.g., when NUMA is configured. This is required because I have retained the old implementation by default to allow archs to be modified incrementally, as desired. Subsequent patches will convert x86_64 and ia64 to use this implemenation. Signed-off-by: Lee Schermerhorn Cc: Tejun Heo Cc: Mel Gorman Reviewed-by: Christoph Lameter Cc: Nick Piggin Cc: David Rientjes Cc: Eric Whitney Cc: KAMEZAWA Hiroyuki Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: "Luck, Tony" Cc: Pekka Enberg Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/topology.h | 51 +++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 46 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index 5b81156780b1..2e5518f46571 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -31,6 +31,7 @@ #include #include #include +#include #include #ifndef node_has_online_mem @@ -203,8 +204,53 @@ int arch_update_cpu_topology(void); #ifndef SD_NODE_INIT #error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!! #endif + #endif /* CONFIG_NUMA */ +#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID +DECLARE_PER_CPU(int, numa_node); + +#ifndef numa_node_id +/* Returns the number of the current Node. */ +static inline int numa_node_id(void) +{ + return __this_cpu_read(numa_node); +} +#endif + +#ifndef cpu_to_node +static inline int cpu_to_node(int cpu) +{ + return per_cpu(numa_node, cpu); +} +#endif + +#ifndef set_numa_node +static inline void set_numa_node(int node) +{ + percpu_write(numa_node, node); +} +#endif + +#ifndef set_cpu_numa_node +static inline void set_cpu_numa_node(int cpu, int node) +{ + per_cpu(numa_node, cpu) = node; +} +#endif + +#else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */ + +/* Returns the number of the current Node. */ +#ifndef numa_node_id +static inline int numa_node_id(void) +{ + return cpu_to_node(raw_smp_processor_id()); +} +#endif + +#endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */ + #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif @@ -218,9 +264,4 @@ int arch_update_cpu_topology(void); #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif -/* Returns the number of the current Node. */ -#ifndef numa_node_id -#define numa_node_id() (cpu_to_node(raw_smp_processor_id())) -#endif - #endif /* _LINUX_TOPOLOGY_H */ -- cgit v1.2.3 From 7aac789885512388a66d47280d7e7777ffba1e59 Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Wed, 26 May 2010 14:45:00 -0700 Subject: numa: introduce numa_mem_id()- effective local memory node id Introduce numa_mem_id(), based on generic percpu variable infrastructure to track "nearest node with memory" for archs that support memoryless nodes. Define API in when CONFIG_HAVE_MEMORYLESS_NODES defined, else stubs. Architectures will define HAVE_MEMORYLESS_NODES if/when they support them. Archs can override definitions of: numa_mem_id() - returns node number of "local memory" node set_numa_mem() - initialize [this cpus'] per cpu variable 'numa_mem' cpu_to_mem() - return numa_mem for specified cpu; may be used as lvalue Generic initialization of 'numa_mem' occurs in __build_all_zonelists(). This will initialize the boot cpu at boot time, and all cpus on change of numa_zonelist_order, or when node or memory hot-plug requires zonelist rebuild. Archs that support memoryless nodes will need to initialize 'numa_mem' for secondary cpus as they're brought on-line. [akpm@linux-foundation.org: fix build] Signed-off-by: Lee Schermerhorn Signed-off-by: Christoph Lameter Cc: Tejun Heo Cc: Mel Gorman Cc: Christoph Lameter Cc: Nick Piggin Cc: David Rientjes Cc: Eric Whitney Cc: KAMEZAWA Hiroyuki Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: "Luck, Tony" Cc: Pekka Enberg Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 +++++ include/linux/topology.h | 61 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 67 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0fa491326c4a..b4d109e389b8 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -671,6 +671,12 @@ void memory_present(int nid, unsigned long start, unsigned long end); static inline void memory_present(int nid, unsigned long start, unsigned long end) {} #endif +#ifdef CONFIG_HAVE_MEMORYLESS_NODES +int local_memory_node(int node_id); +#else +static inline int local_memory_node(int node_id) { return node_id; }; +#endif + #ifdef CONFIG_NEED_NODE_MEMMAP_SIZE unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); #endif diff --git a/include/linux/topology.h b/include/linux/topology.h index 2e5518f46571..c44df50a05ab 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -251,6 +251,67 @@ static inline int numa_node_id(void) #endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */ +#ifdef CONFIG_HAVE_MEMORYLESS_NODES + +/* + * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. + * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. + * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem(). + */ +DECLARE_PER_CPU(int, _numa_mem_); + +#ifndef set_numa_mem +static inline void set_numa_mem(int node) +{ + percpu_write(_numa_mem_, node); +} +#endif + +#ifndef numa_mem_id +/* Returns the number of the nearest Node with memory */ +static inline int numa_mem_id(void) +{ + return __this_cpu_read(_numa_mem_); +} +#endif + +#ifndef cpu_to_mem +static inline int cpu_to_mem(int cpu) +{ + return per_cpu(_numa_mem_, cpu); +} +#endif + +#ifndef set_cpu_numa_mem +static inline void set_cpu_numa_mem(int cpu, int node) +{ + per_cpu(_numa_mem_, cpu) = node; +} +#endif + +#else /* !CONFIG_HAVE_MEMORYLESS_NODES */ + +static inline void set_numa_mem(int node) {} + +static inline void set_cpu_numa_mem(int cpu, int node) {} + +#ifndef numa_mem_id +/* Returns the number of the nearest Node with memory */ +static inline int numa_mem_id(void) +{ + return numa_node_id(); +} +#endif + +#ifndef cpu_to_mem +static inline int cpu_to_mem(int cpu) +{ + return cpu_to_node(cpu); +} +#endif + +#endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */ + #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif -- cgit v1.2.3 From f32764bd2bbb6ea003c158b1d276b4dc9f900348 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Wed, 26 May 2010 23:21:58 +0200 Subject: quota: Convert quota statistics to generic percpu_counter Generic per-cpu counter has some memory overhead but it is negligible for modern systems and embedded systems compile without quota support. And code reuse is a good thing. This patch should fix complain from preemptive kernels which was introduced by dde9588853b1bde. [Jan Kara: Fixed patch to work on 32-bit archs as well] Reported-by: Rafael J. Wysocki Signed-off-by: Dmitry Monakhov Signed-off-by: Jan Kara --- include/linux/quota.h | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 2789d07c37be..94c1f03b50eb 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -174,8 +174,7 @@ enum { #include #include #include -#include -#include +#include #include #include @@ -254,6 +253,7 @@ enum { struct dqstats { int stat[_DQST_DQSTAT_LAST]; + struct percpu_counter counter[_DQST_DQSTAT_LAST]; }; extern struct dqstats *dqstats_pcpu; @@ -261,20 +261,12 @@ extern struct dqstats dqstats; static inline void dqstats_inc(unsigned int type) { -#ifdef CONFIG_SMP - per_cpu_ptr(dqstats_pcpu, smp_processor_id())->stat[type]++; -#else - dqstats.stat[type]++; -#endif + percpu_counter_inc(&dqstats.counter[type]); } static inline void dqstats_dec(unsigned int type) { -#ifdef CONFIG_SMP - per_cpu_ptr(dqstats_pcpu, smp_processor_id())->stat[type]--; -#else - dqstats.stat[type]--; -#endif + percpu_counter_dec(&dqstats.counter[type]); } #define DQ_MOD_B 0 /* dquot modified since read */ -- cgit v1.2.3 From 70dd6beac02f43a5099fcf5fddf68cfee0cbf479 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 27 May 2010 19:58:37 +0200 Subject: hwmon: (asus_atk0110) Don't load if ACPI resources aren't enforced When the user passes the kernel parameter acpi_enforce_resources=lax, the ACPI resources are no longer protected, so a native driver can make use of them. In that case, we do not want the asus_atk0110 to be loaded. Unfortunately, this driver loads automatically due to its MODULE_DEVICE_TABLE, so the user ends up with two drivers loaded for the same device - this is bad. So I suggest that we prevent the asus_atk0110 driver from loading if acpi_enforce_resources=lax. Signed-off-by: Jean Delvare Acked-by: Luca Tettamanti Cc: Len Brown --- include/linux/acpi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 3da73f5f0ae9..2c60f1f70b38 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -248,6 +248,8 @@ int acpi_check_region(resource_size_t start, resource_size_t n, int acpi_check_mem_region(resource_size_t start, resource_size_t n, const char *name); +int acpi_resources_are_enforced(void); + #ifdef CONFIG_PM_SLEEP void __init acpi_no_s4_hw_signature(void); void __init acpi_old_suspend_ordering(void); -- cgit v1.2.3 From e090d506c3f1b314059fb77b177cd4193bb81d6e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sun, 21 Mar 2010 01:06:05 +0100 Subject: mfd: Add support for the RDC321x southbridge This patch adds a new MFD driver for the RDC321x southbridge. This southbridge is always present in the RDC321x System-on-a-Chip and provides access to some GPIOs as well as a watchdog. Access to these two functions is done using the southbridge PCI device configuration space. Signed-off-by: Florian Fainelli Signed-off-by: Samuel Ortiz --- include/linux/mfd/rdc321x.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 include/linux/mfd/rdc321x.h (limited to 'include/linux') diff --git a/include/linux/mfd/rdc321x.h b/include/linux/mfd/rdc321x.h new file mode 100644 index 000000000000..4bdf19c8eedf --- /dev/null +++ b/include/linux/mfd/rdc321x.h @@ -0,0 +1,26 @@ +#ifndef __RDC321X_MFD_H +#define __RDC321X_MFD_H + +#include +#include + +/* Offsets to be accessed in the southbridge PCI + * device configuration register */ +#define RDC321X_WDT_CTRL 0x44 +#define RDC321X_GPIO_CTRL_REG1 0x48 +#define RDC321X_GPIO_DATA_REG1 0x4c +#define RDC321X_GPIO_CTRL_REG2 0x84 +#define RDC321X_GPIO_DATA_REG2 0x88 + +#define RDC321X_MAX_GPIO 58 + +struct rdc321x_gpio_pdata { + struct pci_dev *sb_pdev; + unsigned max_gpios; +}; + +struct rdc321x_wdt_pdata { + struct pci_dev *sb_pdev; +}; + +#endif /* __RDC321X_MFD_H */ -- cgit v1.2.3 From 872c1b14e78661086ade8b501888850da2636eee Mon Sep 17 00:00:00 2001 From: Henrik Kretzschmar Date: Fri, 26 Mar 2010 02:40:13 +0100 Subject: mfd: Section cleanup of 88pm860x driver This patch fixes three section mismatches. WARNING: drivers/mfd/88pm860x.o(.text+0x12): Section mismatch in reference from the function pm860x_device_exit() to the function .devexit.text:device_irq_exit() The function pm860x_device_exit() references a function in an exit section. Often the function device_irq_exit() has valid usage outside the exit section and the fix is to remove the __devexit annotation of device_irq_exit. WARNING: drivers/mfd/88pm860x.o(.text+0xb0): Section mismatch in reference from the function pm860x_device_init() to the function .devinit.text:device_8606_init() The function pm860x_device_init() references the function __devinit device_8606_init(). This is often because pm860x_device_init lacks a __devinit annotation or the annotation of device_8606_init is wrong. WARNING: drivers/mfd/88pm860x.o(.text+0xbe): Section mismatch in reference from the function pm860x_device_init() to the function .devinit.text:device_8607_init() The function pm860x_device_init() references the function __devinit device_8607_init(). This is often because pm860x_device_init lacks a __devinit annotation or the annotation of device_8607_init is wrong. Signed-off-by: Henrik Kretzschmar Signed-off-by: Samuel Ortiz --- include/linux/mfd/88pm860x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/88pm860x.h b/include/linux/mfd/88pm860x.h index e3c4ff8c3e38..bfd23bef7363 100644 --- a/include/linux/mfd/88pm860x.h +++ b/include/linux/mfd/88pm860x.h @@ -370,7 +370,7 @@ extern int pm860x_set_bits(struct i2c_client *, int, unsigned char, unsigned char); extern int pm860x_device_init(struct pm860x_chip *chip, - struct pm860x_platform_data *pdata); -extern void pm860x_device_exit(struct pm860x_chip *chip); + struct pm860x_platform_data *pdata) __devinit ; +extern void pm860x_device_exit(struct pm860x_chip *chip) __devexit ; #endif /* __LINUX_MFD_88PM860X_H */ -- cgit v1.2.3 From bd3581323cc02aefc79a21780a4ca8c578642892 Mon Sep 17 00:00:00 2001 From: "Ira W. Snyder" Date: Wed, 7 Apr 2010 09:43:00 +0200 Subject: mfd: Janz CMOD-IO PCI MODULbus Carrier Board support The Janz CMOD-IO PCI MODULbus carrier board is a PCI to MODULbus bridge, which may host many different types of MODULbus daughterboards, including CAN and GPIO controllers. Signed-off-by: Ira W. Snyder Reviewed-by: Wolfgang Grandegger Signed-off-by: Samuel Ortiz --- include/linux/mfd/janz.h | 54 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) create mode 100644 include/linux/mfd/janz.h (limited to 'include/linux') diff --git a/include/linux/mfd/janz.h b/include/linux/mfd/janz.h new file mode 100644 index 000000000000..e9994c469803 --- /dev/null +++ b/include/linux/mfd/janz.h @@ -0,0 +1,54 @@ +/* + * Common Definitions for Janz MODULbus devices + * + * Copyright (c) 2010 Ira W. Snyder + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef JANZ_H +#define JANZ_H + +struct janz_platform_data { + /* MODULbus Module Number */ + unsigned int modno; +}; + +/* PLX bridge chip onboard registers */ +struct janz_cmodio_onboard_regs { + u8 unused1; + + /* + * Read access: interrupt status + * Write access: interrupt disable + */ + u8 int_disable; + u8 unused2; + + /* + * Read access: MODULbus number (hex switch) + * Write access: interrupt enable + */ + u8 int_enable; + u8 unused3; + + /* write-only */ + u8 reset_assert; + u8 unused4; + + /* write-only */ + u8 reset_deassert; + u8 unused5; + + /* read-write access to serial EEPROM */ + u8 eep; + u8 unused6; + + /* write-only access to EEPROM chip select */ + u8 enid; +}; + +#endif /* JANZ_H */ -- cgit v1.2.3 From d183fcc975cbbc9c427deb2d7948ab03673995c9 Mon Sep 17 00:00:00 2001 From: Todd Fischer Date: Mon, 5 Apr 2010 20:23:56 -0600 Subject: mfd: Move TPS6507x register definition to header file. Other sub-drivers for the TPS6507x chip will need to use register definition so move it out of the source file and into a header file. Signed-off-by: Todd Fischer Acked-by: Mark Brown Signed-off-by: Liam Girdwood Signed-off-by: Samuel Ortiz --- include/linux/mfd/tps6507x.h | 134 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 134 insertions(+) create mode 100644 include/linux/mfd/tps6507x.h (limited to 'include/linux') diff --git a/include/linux/mfd/tps6507x.h b/include/linux/mfd/tps6507x.h new file mode 100644 index 000000000000..155bee1f7823 --- /dev/null +++ b/include/linux/mfd/tps6507x.h @@ -0,0 +1,134 @@ +/* linux/mfd/tps6507x.h + * + * Functions to access TPS65070 power management chip. + * + * Copyright (c) 2009 RidgeRun (todd.fischer@ridgerun.com) + * + * + * For licencing details see kernel-base/COPYING + */ + +#ifndef __LINUX_MFD_TPS6507X_H +#define __LINUX_MFD_TPS6507X_H + +/* + * ---------------------------------------------------------------------------- + * Registers, all 8 bits + * ---------------------------------------------------------------------------- + */ + + +/* Register definitions */ +#define TPS6507X_REG_PPATH1 0X01 +#define TPS6507X_CHG_USB BIT(7) +#define TPS6507X_CHG_AC BIT(6) +#define TPS6507X_CHG_USB_PW_ENABLE BIT(5) +#define TPS6507X_CHG_AC_PW_ENABLE BIT(4) +#define TPS6507X_CHG_AC_CURRENT BIT(2) +#define TPS6507X_CHG_USB_CURRENT BIT(0) + +#define TPS6507X_REG_INT 0X02 +#define TPS6507X_REG_MASK_AC_USB BIT(7) +#define TPS6507X_REG_MASK_TSC BIT(6) +#define TPS6507X_REG_MASK_PB_IN BIT(5) +#define TPS6507X_REG_TSC_INT BIT(3) +#define TPS6507X_REG_PB_IN_INT BIT(2) +#define TPS6507X_REG_AC_USB_APPLIED BIT(1) +#define TPS6507X_REG_AC_USB_REMOVED BIT(0) + +#define TPS6507X_REG_CHGCONFIG0 0X03 + +#define TPS6507X_REG_CHGCONFIG1 0X04 +#define TPS6507X_CON_CTRL1_DCDC1_ENABLE BIT(4) +#define TPS6507X_CON_CTRL1_DCDC2_ENABLE BIT(3) +#define TPS6507X_CON_CTRL1_DCDC3_ENABLE BIT(2) +#define TPS6507X_CON_CTRL1_LDO1_ENABLE BIT(1) +#define TPS6507X_CON_CTRL1_LDO2_ENABLE BIT(0) + +#define TPS6507X_REG_CHGCONFIG2 0X05 + +#define TPS6507X_REG_CHGCONFIG3 0X06 + +#define TPS6507X_REG_ADCONFIG 0X07 +#define TPS6507X_ADCONFIG_AD_ENABLE BIT(7) +#define TPS6507X_ADCONFIG_START_CONVERSION BIT(6) +#define TPS6507X_ADCONFIG_CONVERSION_DONE BIT(5) +#define TPS6507X_ADCONFIG_VREF_ENABLE BIT(4) +#define TPS6507X_ADCONFIG_INPUT_AD_IN1 0 +#define TPS6507X_ADCONFIG_INPUT_AD_IN2 1 +#define TPS6507X_ADCONFIG_INPUT_AD_IN3 2 +#define TPS6507X_ADCONFIG_INPUT_AD_IN4 3 +#define TPS6507X_ADCONFIG_INPUT_TS_PIN 4 +#define TPS6507X_ADCONFIG_INPUT_BAT_CURRENT 5 +#define TPS6507X_ADCONFIG_INPUT_AC_VOLTAGE 6 +#define TPS6507X_ADCONFIG_INPUT_SYS_VOLTAGE 7 +#define TPS6507X_ADCONFIG_INPUT_CHARGER_VOLTAGE 8 +#define TPS6507X_ADCONFIG_INPUT_BAT_VOLTAGE 9 +#define TPS6507X_ADCONFIG_INPUT_THRESHOLD_VOLTAGE 10 +#define TPS6507X_ADCONFIG_INPUT_ISET1_VOLTAGE 11 +#define TPS6507X_ADCONFIG_INPUT_ISET2_VOLTAGE 12 +#define TPS6507X_ADCONFIG_INPUT_REAL_TSC 14 +#define TPS6507X_ADCONFIG_INPUT_TSC 15 + +#define TPS6507X_REG_TSCMODE 0X08 +#define TPS6507X_TSCMODE_X_POSITION 0 +#define TPS6507X_TSCMODE_Y_POSITION 1 +#define TPS6507X_TSCMODE_PRESSURE 2 +#define TPS6507X_TSCMODE_X_PLATE 3 +#define TPS6507X_TSCMODE_Y_PLATE 4 +#define TPS6507X_TSCMODE_STANDBY 5 +#define TPS6507X_TSCMODE_ADC_INPUT 6 +#define TPS6507X_TSCMODE_DISABLE 7 + +#define TPS6507X_REG_ADRESULT_1 0X09 + +#define TPS6507X_REG_ADRESULT_2 0X0A +#define TPS6507X_REG_ADRESULT_2_MASK (BIT(1) | BIT(0)) + +#define TPS6507X_REG_PGOOD 0X0B + +#define TPS6507X_REG_PGOODMASK 0X0C + +#define TPS6507X_REG_CON_CTRL1 0X0D +#define TPS6507X_CON_CTRL1_DCDC1_ENABLE BIT(4) +#define TPS6507X_CON_CTRL1_DCDC2_ENABLE BIT(3) +#define TPS6507X_CON_CTRL1_DCDC3_ENABLE BIT(2) +#define TPS6507X_CON_CTRL1_LDO1_ENABLE BIT(1) +#define TPS6507X_CON_CTRL1_LDO2_ENABLE BIT(0) + +#define TPS6507X_REG_CON_CTRL2 0X0E + +#define TPS6507X_REG_CON_CTRL3 0X0F + +#define TPS6507X_REG_DEFDCDC1 0X10 +#define TPS6507X_DEFDCDC1_DCDC1_EXT_ADJ_EN BIT(7) +#define TPS6507X_DEFDCDC1_DCDC1_MASK 0X3F + +#define TPS6507X_REG_DEFDCDC2_LOW 0X11 +#define TPS6507X_DEFDCDC2_LOW_DCDC2_MASK 0X3F + +#define TPS6507X_REG_DEFDCDC2_HIGH 0X12 +#define TPS6507X_DEFDCDC2_HIGH_DCDC2_MASK 0X3F + +#define TPS6507X_REG_DEFDCDC3_LOW 0X13 +#define TPS6507X_DEFDCDC3_LOW_DCDC3_MASK 0X3F + +#define TPS6507X_REG_DEFDCDC3_HIGH 0X14 +#define TPS6507X_DEFDCDC3_HIGH_DCDC3_MASK 0X3F + +#define TPS6507X_REG_DEFSLEW 0X15 + +#define TPS6507X_REG_LDO_CTRL1 0X16 +#define TPS6507X_REG_LDO_CTRL1_LDO1_MASK 0X0F + +#define TPS6507X_REG_DEFLDO2 0X17 +#define TPS6507X_REG_DEFLDO2_LDO2_MASK 0X3F + +#define TPS6507X_REG_WLED_CTRL1 0X18 + +#define TPS6507X_REG_WLED_CTRL2 0X19 + +/* VDCDC MASK */ +#define TPS6507X_DEFDCDCX_DCDC_MASK 0X3F + +#endif /* __LINUX_MFD_TPS6507X_H */ -- cgit v1.2.3 From 0bc20bba357f18a0e52f45afc452d0b69cf06f76 Mon Sep 17 00:00:00 2001 From: Todd Fischer Date: Mon, 5 Apr 2010 20:23:57 -0600 Subject: mfd: Add tps6507x board data structure Add mfd structure which refrences sub-driver initialization data. For example, for a giving hardware implementation, the voltage regulator sub-driver initialization data provides the mapping betten a voltage regulator and what the output voltage is being used for. Signed-off-by: Todd Fischer Acked-by: Mark Brown Signed-off-by: Liam Girdwood Signed-off-by: Samuel Ortiz --- include/linux/mfd/tps6507x.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps6507x.h b/include/linux/mfd/tps6507x.h index 155bee1f7823..fd73af5fb95a 100644 --- a/include/linux/mfd/tps6507x.h +++ b/include/linux/mfd/tps6507x.h @@ -131,4 +131,15 @@ /* VDCDC MASK */ #define TPS6507X_DEFDCDCX_DCDC_MASK 0X3F +/** + * struct tps6507x_board - packages regulator and touchscreen init data + * @tps6507x_regulator_data: regulator initialization values + * + * Board data may be used to initialize regulator and touchscreen. + */ + +struct tps6507x_board { + struct regulator_init_data *tps6507x_pmic_init_data; +}; + #endif /* __LINUX_MFD_TPS6507X_H */ -- cgit v1.2.3 From 31dd6a2672e337f5de188df3e5169ee732798236 Mon Sep 17 00:00:00 2001 From: Todd Fischer Date: Thu, 8 Apr 2010 09:04:55 +0200 Subject: mfd: Add TPS6507x support TPS6507x are multi function (PM, touchscreen) chipsets from TI. This commit also changes the corresponding regulator driver from being standalone to an MFD subdevice. Signed-off-by: Todd Fischer Acked-by: Mark Brown Signed-off-by: Liam Girdwood Signed-off-by: Samuel Ortiz --- include/linux/mfd/tps6507x.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps6507x.h b/include/linux/mfd/tps6507x.h index fd73af5fb95a..9543cb716428 100644 --- a/include/linux/mfd/tps6507x.h +++ b/include/linux/mfd/tps6507x.h @@ -131,6 +131,8 @@ /* VDCDC MASK */ #define TPS6507X_DEFDCDCX_DCDC_MASK 0X3F +#define TPS6507X_MAX_REGISTER 0X19 + /** * struct tps6507x_board - packages regulator and touchscreen init data * @tps6507x_regulator_data: regulator initialization values @@ -142,4 +144,24 @@ struct tps6507x_board { struct regulator_init_data *tps6507x_pmic_init_data; }; +/** + * struct tps6507x_dev - tps6507x sub-driver chip access routines + * @read_dev() - I2C register read function + * @write_dev() - I2C register write function + * + * Device data may be used to access the TPS6507x chip + */ + +struct tps6507x_dev { + struct device *dev; + struct i2c_client *i2c_client; + int (*read_dev)(struct tps6507x_dev *tps6507x, char reg, int size, + void *dest); + int (*write_dev)(struct tps6507x_dev *tps6507x, char reg, int size, + void *src); + + /* Client devices */ + struct tps6507x_pmic *pmic; +}; + #endif /* __LINUX_MFD_TPS6507X_H */ -- cgit v1.2.3 From 752599667048898b6969e06e4637f906b04ec752 Mon Sep 17 00:00:00 2001 From: Todd Fischer Date: Mon, 5 Apr 2010 17:53:12 -0600 Subject: input: Touchscreen driver for TPS6507x Add touch screen input driver for TPS6507x family of multi-function chips. Uses the TPS6507x MFD driver. No interrupt support due to testing limitations of current hardware. Signed-off-by: Todd Fischer Signed-off-by: Samuel Ortiz --- include/linux/input/tps6507x-ts.h | 24 ++++++++++++++++++++++++ include/linux/mfd/tps6507x.h | 2 ++ 2 files changed, 26 insertions(+) create mode 100644 include/linux/input/tps6507x-ts.h (limited to 'include/linux') diff --git a/include/linux/input/tps6507x-ts.h b/include/linux/input/tps6507x-ts.h new file mode 100644 index 000000000000..ab1440313924 --- /dev/null +++ b/include/linux/input/tps6507x-ts.h @@ -0,0 +1,24 @@ +/* linux/i2c/tps6507x-ts.h + * + * Functions to access TPS65070 touch screen chip. + * + * Copyright (c) 2009 RidgeRun (todd.fischer@ridgerun.com) + * + * + * For licencing details see kernel-base/COPYING + */ + +#ifndef __LINUX_I2C_TPS6507X_TS_H +#define __LINUX_I2C_TPS6507X_TS_H + +/* Board specific touch screen initial values */ +struct touchscreen_init_data { + int poll_period; /* ms */ + int vref; /* non-zero to leave vref on */ + __u16 min_pressure; /* min reading to be treated as a touch */ + __u16 vendor; + __u16 product; + __u16 version; +}; + +#endif /* __LINUX_I2C_TPS6507X_TS_H */ diff --git a/include/linux/mfd/tps6507x.h b/include/linux/mfd/tps6507x.h index 9543cb716428..c923e4864f55 100644 --- a/include/linux/mfd/tps6507x.h +++ b/include/linux/mfd/tps6507x.h @@ -142,6 +142,7 @@ struct tps6507x_board { struct regulator_init_data *tps6507x_pmic_init_data; + struct touchscreen_init_data *tps6507x_ts_init_data; }; /** @@ -162,6 +163,7 @@ struct tps6507x_dev { /* Client devices */ struct tps6507x_pmic *pmic; + struct tps6507x_ts *ts; }; #endif /* __LINUX_MFD_TPS6507X_H */ -- cgit v1.2.3 From b03b4d7cdd8f18395494478634707c6f132080d6 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 8 Apr 2010 10:02:39 +0200 Subject: mfd: Ensure WM831x charger interrupts are acknowledged when suspending The charger interrupts on the WM831x are unconditionally a wake source for the system. If the power driver is not able to monitor them (for example, due to the IRQ line not having been wired up on the system) then any charger interrupt will prevent the system suspending for any meaningful amount of time since nothing will ack them. Avoid this issue by manually acknowledging these interrupts when we suspend the WM831x core device if they are masked. If software is actually using the interrupts then they will be unmasked and this change will have no effect. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm831x/core.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 5915f6e3d9ab..eb5bd4e0e03c 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -256,8 +256,9 @@ struct wm831x { int irq_masks_cache[WM831X_NUM_IRQ_REGS]; /* Cached hardware value */ /* Chip revision based flags */ - unsigned has_gpio_ena:1; /* Has GPIO enable bit */ - unsigned has_cs_sts:1; /* Has current sink status bit */ + unsigned has_gpio_ena:1; /* Has GPIO enable bit */ + unsigned has_cs_sts:1; /* Has current sink status bit */ + unsigned charger_irq_wake:1; /* Are charger IRQs a wake source? */ int num_gpio; -- cgit v1.2.3 From b4ecd326b789f1029c5d4a5239d9bd12ecac353d Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Mon, 10 May 2010 23:39:47 +0200 Subject: mfd: Add Toshiba's TC35892 MFD core The TC35892 I/O Expander provides 24 GPIOs, a keypad controller, timers, and a rotator wheel interface. This patch adds the MFD core. Acked-by: Linus Walleij Signed-off-by: Rabin Vincent Signed-off-by: Samuel Ortiz --- include/linux/mfd/tc35892.h | 132 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 132 insertions(+) create mode 100644 include/linux/mfd/tc35892.h (limited to 'include/linux') diff --git a/include/linux/mfd/tc35892.h b/include/linux/mfd/tc35892.h new file mode 100644 index 000000000000..e47f770d3068 --- /dev/null +++ b/include/linux/mfd/tc35892.h @@ -0,0 +1,132 @@ +/* + * Copyright (C) ST-Ericsson SA 2010 + * + * License Terms: GNU General Public License, version 2 + */ + +#ifndef __LINUX_MFD_TC35892_H +#define __LINUX_MFD_TC35892_H + +#include + +#define TC35892_RSTCTRL_IRQRST (1 << 4) +#define TC35892_RSTCTRL_TIMRST (1 << 3) +#define TC35892_RSTCTRL_ROTRST (1 << 2) +#define TC35892_RSTCTRL_KBDRST (1 << 1) +#define TC35892_RSTCTRL_GPIRST (1 << 0) + +#define TC35892_IRQST 0x91 + +#define TC35892_MANFCODE_MAGIC 0x03 +#define TC35892_MANFCODE 0x80 +#define TC35892_VERSION 0x81 +#define TC35892_IOCFG 0xA7 + +#define TC35892_CLKMODE 0x88 +#define TC35892_CLKCFG 0x89 +#define TC35892_CLKEN 0x8A + +#define TC35892_RSTCTRL 0x82 +#define TC35892_EXTRSTN 0x83 +#define TC35892_RSTINTCLR 0x84 + +#define TC35892_GPIOIS0 0xC9 +#define TC35892_GPIOIS1 0xCA +#define TC35892_GPIOIS2 0xCB +#define TC35892_GPIOIBE0 0xCC +#define TC35892_GPIOIBE1 0xCD +#define TC35892_GPIOIBE2 0xCE +#define TC35892_GPIOIEV0 0xCF +#define TC35892_GPIOIEV1 0xD0 +#define TC35892_GPIOIEV2 0xD1 +#define TC35892_GPIOIE0 0xD2 +#define TC35892_GPIOIE1 0xD3 +#define TC35892_GPIOIE2 0xD4 +#define TC35892_GPIORIS0 0xD6 +#define TC35892_GPIORIS1 0xD7 +#define TC35892_GPIORIS2 0xD8 +#define TC35892_GPIOMIS0 0xD9 +#define TC35892_GPIOMIS1 0xDA +#define TC35892_GPIOMIS2 0xDB +#define TC35892_GPIOIC0 0xDC +#define TC35892_GPIOIC1 0xDD +#define TC35892_GPIOIC2 0xDE + +#define TC35892_GPIODATA0 0xC0 +#define TC35892_GPIOMASK0 0xc1 +#define TC35892_GPIODATA1 0xC2 +#define TC35892_GPIOMASK1 0xc3 +#define TC35892_GPIODATA2 0xC4 +#define TC35892_GPIOMASK2 0xC5 + +#define TC35892_GPIODIR0 0xC6 +#define TC35892_GPIODIR1 0xC7 +#define TC35892_GPIODIR2 0xC8 + +#define TC35892_GPIOSYNC0 0xE6 +#define TC35892_GPIOSYNC1 0xE7 +#define TC35892_GPIOSYNC2 0xE8 + +#define TC35892_GPIOWAKE0 0xE9 +#define TC35892_GPIOWAKE1 0xEA +#define TC35892_GPIOWAKE2 0xEB + +#define TC35892_GPIOODM0 0xE0 +#define TC35892_GPIOODE0 0xE1 +#define TC35892_GPIOODM1 0xE2 +#define TC35892_GPIOODE1 0xE3 +#define TC35892_GPIOODM2 0xE4 +#define TC35892_GPIOODE2 0xE5 + +#define TC35892_INT_GPIIRQ 0 +#define TC35892_INT_TI0IRQ 1 +#define TC35892_INT_TI1IRQ 2 +#define TC35892_INT_TI2IRQ 3 +#define TC35892_INT_ROTIRQ 5 +#define TC35892_INT_KBDIRQ 6 +#define TC35892_INT_PORIRQ 7 + +#define TC35892_NR_INTERNAL_IRQS 8 +#define TC35892_INT_GPIO(x) (TC35892_NR_INTERNAL_IRQS + (x)) + +struct tc35892 { + struct mutex lock; + struct device *dev; + struct i2c_client *i2c; + + int irq_base; + int num_gpio; + struct tc35892_platform_data *pdata; +}; + +extern int tc35892_reg_write(struct tc35892 *tc35892, u8 reg, u8 data); +extern int tc35892_reg_read(struct tc35892 *tc35892, u8 reg); +extern int tc35892_block_read(struct tc35892 *tc35892, u8 reg, u8 length, + u8 *values); +extern int tc35892_block_write(struct tc35892 *tc35892, u8 reg, u8 length, + const u8 *values); +extern int tc35892_set_bits(struct tc35892 *tc35892, u8 reg, u8 mask, u8 val); + +/** + * struct tc35892_gpio_platform_data - TC35892 GPIO platform data + * @gpio_base: first gpio number assigned to TC35892. A maximum of + * %TC35892_NR_GPIOS GPIOs will be allocated. + */ +struct tc35892_gpio_platform_data { + int gpio_base; +}; + +/** + * struct tc35892_platform_data - TC35892 platform data + * @irq_base: base IRQ number. %TC35892_NR_IRQS irqs will be used. + * @gpio: GPIO-specific platform data + */ +struct tc35892_platform_data { + int irq_base; + struct tc35892_gpio_platform_data *gpio; +}; + +#define TC35892_NR_GPIOS 24 +#define TC35892_NR_IRQS TC35892_INT_GPIO(TC35892_NR_GPIOS) + +#endif -- cgit v1.2.3 From 812f9e9d424dde9ccb35975c0281edb6f8543735 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 1 May 2010 18:26:07 +0200 Subject: mfd: Renamed ab3100.h to abx500.h The goal here is to make way for a more general interface for the analog baseband chips ab3100 ab3550 ab550 and future chips. This patch have been divided into two parts since both changing name and content of a file is not recommended in git. Signed-off-by: Mattias Wallin Signed-off-by: Linus Walleij Signed-off-by: Samuel Ortiz --- include/linux/mfd/ab3100.h | 129 --------------------------------------------- include/linux/mfd/abx500.h | 129 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 129 insertions(+), 129 deletions(-) delete mode 100644 include/linux/mfd/ab3100.h create mode 100644 include/linux/mfd/abx500.h (limited to 'include/linux') diff --git a/include/linux/mfd/ab3100.h b/include/linux/mfd/ab3100.h deleted file mode 100644 index 9a881c305a50..000000000000 --- a/include/linux/mfd/ab3100.h +++ /dev/null @@ -1,129 +0,0 @@ -/* - * Copyright (C) 2007-2009 ST-Ericsson AB - * License terms: GNU General Public License (GPL) version 2 - * AB3100 core access functions - * Author: Linus Walleij - */ - -#include -#include - -#ifndef MFD_AB3100_H -#define MFD_AB3100_H - -#define ABUNKNOWN 0 -#define AB3000 1 -#define AB3100 2 - -/* - * AB3100, EVENTA1, A2 and A3 event register flags - * these are catenated into a single 32-bit flag in the code - * for event notification broadcasts. - */ -#define AB3100_EVENTA1_ONSWA (0x01<<16) -#define AB3100_EVENTA1_ONSWB (0x02<<16) -#define AB3100_EVENTA1_ONSWC (0x04<<16) -#define AB3100_EVENTA1_DCIO (0x08<<16) -#define AB3100_EVENTA1_OVER_TEMP (0x10<<16) -#define AB3100_EVENTA1_SIM_OFF (0x20<<16) -#define AB3100_EVENTA1_VBUS (0x40<<16) -#define AB3100_EVENTA1_VSET_USB (0x80<<16) - -#define AB3100_EVENTA2_READY_TX (0x01<<8) -#define AB3100_EVENTA2_READY_RX (0x02<<8) -#define AB3100_EVENTA2_OVERRUN_ERROR (0x04<<8) -#define AB3100_EVENTA2_FRAMING_ERROR (0x08<<8) -#define AB3100_EVENTA2_CHARG_OVERCURRENT (0x10<<8) -#define AB3100_EVENTA2_MIDR (0x20<<8) -#define AB3100_EVENTA2_BATTERY_REM (0x40<<8) -#define AB3100_EVENTA2_ALARM (0x80<<8) - -#define AB3100_EVENTA3_ADC_TRIG5 (0x01) -#define AB3100_EVENTA3_ADC_TRIG4 (0x02) -#define AB3100_EVENTA3_ADC_TRIG3 (0x04) -#define AB3100_EVENTA3_ADC_TRIG2 (0x08) -#define AB3100_EVENTA3_ADC_TRIGVBAT (0x10) -#define AB3100_EVENTA3_ADC_TRIGVTX (0x20) -#define AB3100_EVENTA3_ADC_TRIG1 (0x40) -#define AB3100_EVENTA3_ADC_TRIG0 (0x80) - -/* AB3100, STR register flags */ -#define AB3100_STR_ONSWA (0x01) -#define AB3100_STR_ONSWB (0x02) -#define AB3100_STR_ONSWC (0x04) -#define AB3100_STR_DCIO (0x08) -#define AB3100_STR_BOOT_MODE (0x10) -#define AB3100_STR_SIM_OFF (0x20) -#define AB3100_STR_BATT_REMOVAL (0x40) -#define AB3100_STR_VBUS (0x80) - -/* - * AB3100 contains 8 regulators, one external regulator controller - * and a buck converter, further the LDO E and buck converter can - * have separate settings if they are in sleep mode, this is - * modeled as a separate regulator. - */ -#define AB3100_NUM_REGULATORS 10 - -/** - * struct ab3100 - * @access_mutex: lock out concurrent accesses to the AB3100 registers - * @dev: pointer to the containing device - * @i2c_client: I2C client for this chip - * @testreg_client: secondary client for test registers - * @chip_name: name of this chip variant - * @chip_id: 8 bit chip ID for this chip variant - * @event_subscribers: event subscribers are listed here - * @startup_events: a copy of the first reading of the event registers - * @startup_events_read: whether the first events have been read - * - * This struct is PRIVATE and devices using it should NOT - * access ANY fields. It is used as a token for calling the - * AB3100 functions. - */ -struct ab3100 { - struct mutex access_mutex; - struct device *dev; - struct i2c_client *i2c_client; - struct i2c_client *testreg_client; - char chip_name[32]; - u8 chip_id; - struct blocking_notifier_head event_subscribers; - u32 startup_events; - bool startup_events_read; -}; - -/** - * struct ab3100_platform_data - * Data supplied to initialize board connections to the AB3100 - * @reg_constraints: regulator constraints for target board - * the order of these constraints are: LDO A, C, D, E, - * F, G, H, K, EXT and BUCK. - * @reg_initvals: initial values for the regulator registers - * plus two sleep settings for LDO E and the BUCK converter. - * exactly AB3100_NUM_REGULATORS+2 values must be sent in. - * Order: LDO A, C, E, E sleep, F, G, H, K, EXT, BUCK, - * BUCK sleep, LDO D. (LDO D need to be initialized last.) - * @external_voltage: voltage level of the external regulator. - */ -struct ab3100_platform_data { - struct regulator_init_data reg_constraints[AB3100_NUM_REGULATORS]; - u8 reg_initvals[AB3100_NUM_REGULATORS+2]; - int external_voltage; -}; - -int ab3100_set_register_interruptible(struct ab3100 *ab3100, u8 reg, u8 regval); -int ab3100_get_register_interruptible(struct ab3100 *ab3100, u8 reg, u8 *regval); -int ab3100_get_register_page_interruptible(struct ab3100 *ab3100, - u8 first_reg, u8 *regvals, u8 numregs); -int ab3100_mask_and_set_register_interruptible(struct ab3100 *ab3100, - u8 reg, u8 andmask, u8 ormask); -u8 ab3100_get_chip_type(struct ab3100 *ab3100); -int ab3100_event_register(struct ab3100 *ab3100, - struct notifier_block *nb); -int ab3100_event_unregister(struct ab3100 *ab3100, - struct notifier_block *nb); -int ab3100_event_registers_startup_state_get(struct ab3100 *ab3100, - u32 *fatevent); - -#endif diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h new file mode 100644 index 000000000000..9a881c305a50 --- /dev/null +++ b/include/linux/mfd/abx500.h @@ -0,0 +1,129 @@ +/* + * Copyright (C) 2007-2009 ST-Ericsson AB + * License terms: GNU General Public License (GPL) version 2 + * AB3100 core access functions + * Author: Linus Walleij + */ + +#include +#include + +#ifndef MFD_AB3100_H +#define MFD_AB3100_H + +#define ABUNKNOWN 0 +#define AB3000 1 +#define AB3100 2 + +/* + * AB3100, EVENTA1, A2 and A3 event register flags + * these are catenated into a single 32-bit flag in the code + * for event notification broadcasts. + */ +#define AB3100_EVENTA1_ONSWA (0x01<<16) +#define AB3100_EVENTA1_ONSWB (0x02<<16) +#define AB3100_EVENTA1_ONSWC (0x04<<16) +#define AB3100_EVENTA1_DCIO (0x08<<16) +#define AB3100_EVENTA1_OVER_TEMP (0x10<<16) +#define AB3100_EVENTA1_SIM_OFF (0x20<<16) +#define AB3100_EVENTA1_VBUS (0x40<<16) +#define AB3100_EVENTA1_VSET_USB (0x80<<16) + +#define AB3100_EVENTA2_READY_TX (0x01<<8) +#define AB3100_EVENTA2_READY_RX (0x02<<8) +#define AB3100_EVENTA2_OVERRUN_ERROR (0x04<<8) +#define AB3100_EVENTA2_FRAMING_ERROR (0x08<<8) +#define AB3100_EVENTA2_CHARG_OVERCURRENT (0x10<<8) +#define AB3100_EVENTA2_MIDR (0x20<<8) +#define AB3100_EVENTA2_BATTERY_REM (0x40<<8) +#define AB3100_EVENTA2_ALARM (0x80<<8) + +#define AB3100_EVENTA3_ADC_TRIG5 (0x01) +#define AB3100_EVENTA3_ADC_TRIG4 (0x02) +#define AB3100_EVENTA3_ADC_TRIG3 (0x04) +#define AB3100_EVENTA3_ADC_TRIG2 (0x08) +#define AB3100_EVENTA3_ADC_TRIGVBAT (0x10) +#define AB3100_EVENTA3_ADC_TRIGVTX (0x20) +#define AB3100_EVENTA3_ADC_TRIG1 (0x40) +#define AB3100_EVENTA3_ADC_TRIG0 (0x80) + +/* AB3100, STR register flags */ +#define AB3100_STR_ONSWA (0x01) +#define AB3100_STR_ONSWB (0x02) +#define AB3100_STR_ONSWC (0x04) +#define AB3100_STR_DCIO (0x08) +#define AB3100_STR_BOOT_MODE (0x10) +#define AB3100_STR_SIM_OFF (0x20) +#define AB3100_STR_BATT_REMOVAL (0x40) +#define AB3100_STR_VBUS (0x80) + +/* + * AB3100 contains 8 regulators, one external regulator controller + * and a buck converter, further the LDO E and buck converter can + * have separate settings if they are in sleep mode, this is + * modeled as a separate regulator. + */ +#define AB3100_NUM_REGULATORS 10 + +/** + * struct ab3100 + * @access_mutex: lock out concurrent accesses to the AB3100 registers + * @dev: pointer to the containing device + * @i2c_client: I2C client for this chip + * @testreg_client: secondary client for test registers + * @chip_name: name of this chip variant + * @chip_id: 8 bit chip ID for this chip variant + * @event_subscribers: event subscribers are listed here + * @startup_events: a copy of the first reading of the event registers + * @startup_events_read: whether the first events have been read + * + * This struct is PRIVATE and devices using it should NOT + * access ANY fields. It is used as a token for calling the + * AB3100 functions. + */ +struct ab3100 { + struct mutex access_mutex; + struct device *dev; + struct i2c_client *i2c_client; + struct i2c_client *testreg_client; + char chip_name[32]; + u8 chip_id; + struct blocking_notifier_head event_subscribers; + u32 startup_events; + bool startup_events_read; +}; + +/** + * struct ab3100_platform_data + * Data supplied to initialize board connections to the AB3100 + * @reg_constraints: regulator constraints for target board + * the order of these constraints are: LDO A, C, D, E, + * F, G, H, K, EXT and BUCK. + * @reg_initvals: initial values for the regulator registers + * plus two sleep settings for LDO E and the BUCK converter. + * exactly AB3100_NUM_REGULATORS+2 values must be sent in. + * Order: LDO A, C, E, E sleep, F, G, H, K, EXT, BUCK, + * BUCK sleep, LDO D. (LDO D need to be initialized last.) + * @external_voltage: voltage level of the external regulator. + */ +struct ab3100_platform_data { + struct regulator_init_data reg_constraints[AB3100_NUM_REGULATORS]; + u8 reg_initvals[AB3100_NUM_REGULATORS+2]; + int external_voltage; +}; + +int ab3100_set_register_interruptible(struct ab3100 *ab3100, u8 reg, u8 regval); +int ab3100_get_register_interruptible(struct ab3100 *ab3100, u8 reg, u8 *regval); +int ab3100_get_register_page_interruptible(struct ab3100 *ab3100, + u8 first_reg, u8 *regvals, u8 numregs); +int ab3100_mask_and_set_register_interruptible(struct ab3100 *ab3100, + u8 reg, u8 andmask, u8 ormask); +u8 ab3100_get_chip_type(struct ab3100 *ab3100); +int ab3100_event_register(struct ab3100 *ab3100, + struct notifier_block *nb); +int ab3100_event_unregister(struct ab3100 *ab3100, + struct notifier_block *nb); +int ab3100_event_registers_startup_state_get(struct ab3100 *ab3100, + u32 *fatevent); + +#endif -- cgit v1.2.3 From fa661258a27aa74aaf741882053d195291cefb75 Mon Sep 17 00:00:00 2001 From: Mattias Wallin Date: Sat, 1 May 2010 18:26:20 +0200 Subject: mfd: AB3100 register access change to abx500 API The interface for the AB3100 is changed to make way for the ABX500 family of chips: AB3550, AB5500 and future ST-Ericsson Analog Baseband chips. The register access functions are moved out to a separate struct abx500_ops. In this way the interface is moved from the implementation and the sub functionality drivers can keep their interface intact when chip infrastructure and communication mechanisms changes. We also define the AB3550 device IDs and the AB3550 platform data struct and convert the catenated 32bit event to an array of 3 x 8bits. Signed-off-by: Mattias Wallin Signed-off-by: Linus Walleij Signed-off-by: Samuel Ortiz --- include/linux/mfd/abx500.h | 134 ++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 119 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h index 9a881c305a50..390726fcbcb1 100644 --- a/include/linux/mfd/abx500.h +++ b/include/linux/mfd/abx500.h @@ -3,17 +3,37 @@ * License terms: GNU General Public License (GPL) version 2 * AB3100 core access functions * Author: Linus Walleij + * + * ABX500 core access functions. + * The abx500 interface is used for the Analog Baseband chip + * ab3100, ab3550, ab5500 and possibly comming. It is not used for + * ab4500 and ab8500 since they are another family of chip. + * + * Author: Mattias Wallin + * Author: Mattias Nilsson + * Author: Bengt Jonsson + * Author: Rickard Andersson */ #include #include -#ifndef MFD_AB3100_H -#define MFD_AB3100_H +#ifndef MFD_ABX500_H +#define MFD_ABX500_H -#define ABUNKNOWN 0 -#define AB3000 1 -#define AB3100 2 +#define AB3100_P1A 0xc0 +#define AB3100_P1B 0xc1 +#define AB3100_P1C 0xc2 +#define AB3100_P1D 0xc3 +#define AB3100_P1E 0xc4 +#define AB3100_P1F 0xc5 +#define AB3100_P1G 0xc6 +#define AB3100_R2A 0xc7 +#define AB3100_R2B 0xc8 +#define AB3550_P1A 0x10 +#define AB5500_1_0 0x20 +#define AB5500_2_0 0x21 +#define AB5500_2_1 0x22 /* * AB3100, EVENTA1, A2 and A3 event register flags @@ -89,7 +109,7 @@ struct ab3100 { char chip_name[32]; u8 chip_id; struct blocking_notifier_head event_subscribers; - u32 startup_events; + u8 startup_events[3]; bool startup_events_read; }; @@ -112,18 +132,102 @@ struct ab3100_platform_data { int external_voltage; }; -int ab3100_set_register_interruptible(struct ab3100 *ab3100, u8 reg, u8 regval); -int ab3100_get_register_interruptible(struct ab3100 *ab3100, u8 reg, u8 *regval); -int ab3100_get_register_page_interruptible(struct ab3100 *ab3100, - u8 first_reg, u8 *regvals, u8 numregs); -int ab3100_mask_and_set_register_interruptible(struct ab3100 *ab3100, - u8 reg, u8 andmask, u8 ormask); -u8 ab3100_get_chip_type(struct ab3100 *ab3100); int ab3100_event_register(struct ab3100 *ab3100, struct notifier_block *nb); int ab3100_event_unregister(struct ab3100 *ab3100, struct notifier_block *nb); -int ab3100_event_registers_startup_state_get(struct ab3100 *ab3100, - u32 *fatevent); +/* AB3550, STR register flags */ +#define AB3550_STR_ONSWA (0x01) +#define AB3550_STR_ONSWB (0x02) +#define AB3550_STR_ONSWC (0x04) +#define AB3550_STR_DCIO (0x08) +#define AB3550_STR_BOOT_MODE (0x10) +#define AB3550_STR_SIM_OFF (0x20) +#define AB3550_STR_BATT_REMOVAL (0x40) +#define AB3550_STR_VBUS (0x80) + +/* Interrupt mask registers */ +#define AB3550_IMR1 0x29 +#define AB3550_IMR2 0x2a +#define AB3550_IMR3 0x2b +#define AB3550_IMR4 0x2c +#define AB3550_IMR5 0x2d + +enum ab3550_devid { + AB3550_DEVID_ADC, + AB3550_DEVID_DAC, + AB3550_DEVID_LEDS, + AB3550_DEVID_POWER, + AB3550_DEVID_REGULATORS, + AB3550_DEVID_SIM, + AB3550_DEVID_UART, + AB3550_DEVID_RTC, + AB3550_DEVID_CHARGER, + AB3550_DEVID_FUELGAUGE, + AB3550_DEVID_VIBRATOR, + AB3550_DEVID_CODEC, + AB3550_NUM_DEVICES, +}; + +/** + * struct abx500_init_setting + * Initial value of the registers for driver to use during setup. + */ +struct abx500_init_settings { + u8 bank; + u8 reg; + u8 setting; +}; + +/** + * struct ab3550_platform_data + * Data supplied to initialize board connections to the AB3550 + */ +struct ab3550_platform_data { + struct {unsigned int base; unsigned int count; } irq; + void *dev_data[AB3550_NUM_DEVICES]; + size_t dev_data_sz[AB3550_NUM_DEVICES]; + struct abx500_init_settings *init_settings; + unsigned int init_settings_sz; +}; + +int abx500_set_register_interruptible(struct device *dev, u8 bank, u8 reg, + u8 value); +int abx500_get_register_interruptible(struct device *dev, u8 bank, u8 reg, + u8 *value); +int abx500_get_register_page_interruptible(struct device *dev, u8 bank, + u8 first_reg, u8 *regvals, u8 numregs); +int abx500_set_register_page_interruptible(struct device *dev, u8 bank, + u8 first_reg, u8 *regvals, u8 numregs); +/** + * abx500_mask_and_set_register_inerruptible() - Modifies selected bits of a + * target register + * + * @dev: The AB sub device. + * @bank: The i2c bank number. + * @bitmask: The bit mask to use. + * @bitvalues: The new bit values. + * + * Updates the value of an AB register: + * value -> ((value & ~bitmask) | (bitvalues & bitmask)) + */ +int abx500_mask_and_set_register_interruptible(struct device *dev, u8 bank, + u8 reg, u8 bitmask, u8 bitvalues); +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); + +struct abx500_ops { + int (*get_chip_id) (struct device *); + int (*get_register) (struct device *, u8, u8, u8 *); + int (*set_register) (struct device *, u8, u8, u8); + int (*get_register_page) (struct device *, u8, u8, u8 *, u8); + int (*set_register_page) (struct device *, u8, u8, u8 *, u8); + 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); +}; + +int abx500_register_ops(struct device *core_dev, struct abx500_ops *ops); #endif -- cgit v1.2.3 From 62579266cf9caca5b999560be2b5ceee42fc4d4d Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Wed, 19 May 2010 11:39:02 +0200 Subject: mfd: New AB8500 driver Add a new driver to support the AB8500 Power Management chip, replacing the current AB4500. The new driver replaces the old one, instead of an incremental modification, because this is a substantial overhaul including: - Split of the driver into -core and -spi portions, to allow another interface layer to be added - Addition of interrupt support - Switch to MFD core API for handling subdevices - Simplification of the APIs to remove a redundant block parameter - Rename of the APIs and macros from ab4500_* to ab8500_* - Rename of the files from ab4500* to ab8500* - Change of the driver name from ab4500 to ab8500 Acked-by: Linus Walleij Acked-by: Srinidhi Kasagar Signed-off-by: Rabin Vincent Signed-off-by: Samuel Ortiz --- include/linux/mfd/ab4500.h | 262 --------------------------------------------- include/linux/mfd/ab8500.h | 128 ++++++++++++++++++++++ 2 files changed, 128 insertions(+), 262 deletions(-) delete mode 100644 include/linux/mfd/ab4500.h create mode 100644 include/linux/mfd/ab8500.h (limited to 'include/linux') diff --git a/include/linux/mfd/ab4500.h b/include/linux/mfd/ab4500.h deleted file mode 100644 index a42a7033ae53..000000000000 --- a/include/linux/mfd/ab4500.h +++ /dev/null @@ -1,262 +0,0 @@ -/* - * Copyright (C) 2009 ST-Ericsson - * - * Author: Srinidhi KASAGAR - * - * 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. - * - * AB4500 device core funtions, for client access - */ -#ifndef MFD_AB4500_H -#define MFD_AB4500_H - -#include - -/* - * AB4500 bank addresses - */ -#define AB4500_SYS_CTRL1_BLOCK 0x1 -#define AB4500_SYS_CTRL2_BLOCK 0x2 -#define AB4500_REGU_CTRL1 0x3 -#define AB4500_REGU_CTRL2 0x4 -#define AB4500_USB 0x5 -#define AB4500_TVOUT 0x6 -#define AB4500_DBI 0x7 -#define AB4500_ECI_AV_ACC 0x8 -#define AB4500_RESERVED 0x9 -#define AB4500_GPADC 0xA -#define AB4500_CHARGER 0xB -#define AB4500_GAS_GAUGE 0xC -#define AB4500_AUDIO 0xD -#define AB4500_INTERRUPT 0xE -#define AB4500_RTC 0xF -#define AB4500_MISC 0x10 -#define AB4500_DEBUG 0x12 -#define AB4500_PROD_TEST 0x13 -#define AB4500_OTP_EMUL 0x15 - -/* - * System control 1 register offsets. - * Bank = 0x01 - */ -#define AB4500_TURNON_STAT_REG 0x0100 -#define AB4500_RESET_STAT_REG 0x0101 -#define AB4500_PONKEY1_PRESS_STAT_REG 0x0102 - -#define AB4500_FSM_STAT1_REG 0x0140 -#define AB4500_FSM_STAT2_REG 0x0141 -#define AB4500_SYSCLK_REQ_STAT_REG 0x0142 -#define AB4500_USB_STAT1_REG 0x0143 -#define AB4500_USB_STAT2_REG 0x0144 -#define AB4500_STATUS_SPARE1_REG 0x0145 -#define AB4500_STATUS_SPARE2_REG 0x0146 - -#define AB4500_CTRL1_REG 0x0180 -#define AB4500_CTRL2_REG 0x0181 - -/* - * System control 2 register offsets. - * bank = 0x02 - */ -#define AB4500_CTRL3_REG 0x0200 -#define AB4500_MAIN_WDOG_CTRL_REG 0x0201 -#define AB4500_MAIN_WDOG_TIMER_REG 0x0202 -#define AB4500_LOW_BAT_REG 0x0203 -#define AB4500_BATT_OK_REG 0x0204 -#define AB4500_SYSCLK_TIMER_REG 0x0205 -#define AB4500_SMPSCLK_CTRL_REG 0x0206 -#define AB4500_SMPSCLK_SEL1_REG 0x0207 -#define AB4500_SMPSCLK_SEL2_REG 0x0208 -#define AB4500_SMPSCLK_SEL3_REG 0x0209 -#define AB4500_SYSULPCLK_CONF_REG 0x020A -#define AB4500_SYSULPCLK_CTRL1_REG 0x020B -#define AB4500_SYSCLK_CTRL_REG 0x020C -#define AB4500_SYSCLK_REQ1_VALID_REG 0x020D -#define AB4500_SYSCLK_REQ_VALID_REG 0x020E -#define AB4500_SYSCTRL_SPARE_REG 0x020F -#define AB4500_PAD_CONF_REG 0x0210 - -/* - * Regu control1 register offsets - * Bank = 0x03 - */ -#define AB4500_REGU_SERIAL_CTRL1_REG 0x0300 -#define AB4500_REGU_SERIAL_CTRL2_REG 0x0301 -#define AB4500_REGU_SERIAL_CTRL3_REG 0x0302 -#define AB4500_REGU_REQ_CTRL1_REG 0x0303 -#define AB4500_REGU_REQ_CTRL2_REG 0x0304 -#define AB4500_REGU_REQ_CTRL3_REG 0x0305 -#define AB4500_REGU_REQ_CTRL4_REG 0x0306 -#define AB4500_REGU_MISC1_REG 0x0380 -#define AB4500_REGU_OTGSUPPLY_CTRL_REG 0x0381 -#define AB4500_REGU_VUSB_CTRL_REG 0x0382 -#define AB4500_REGU_VAUDIO_SUPPLY_REG 0x0383 -#define AB4500_REGU_CTRL1_SPARE_REG 0x0384 - -/* - * Regu control2 Vmod register offsets - */ -#define AB4500_REGU_VMOD_REGU_REG 0x0440 -#define AB4500_REGU_VMOD_SEL1_REG 0x0441 -#define AB4500_REGU_VMOD_SEL2_REG 0x0442 -#define AB4500_REGU_CTRL_DISCH_REG 0x0443 -#define AB4500_REGU_CTRL_DISCH2_REG 0x0444 - -/* - * USB/ULPI register offsets - * Bank : 0x5 - */ -#define AB4500_USB_LINE_STAT_REG 0x0580 -#define AB4500_USB_LINE_CTRL1_REG 0x0581 -#define AB4500_USB_LINE_CTRL2_REG 0x0582 -#define AB4500_USB_LINE_CTRL3_REG 0x0583 -#define AB4500_USB_LINE_CTRL4_REG 0x0584 -#define AB4500_USB_LINE_CTRL5_REG 0x0585 -#define AB4500_USB_OTG_CTRL_REG 0x0587 -#define AB4500_USB_OTG_STAT_REG 0x0588 -#define AB4500_USB_OTG_STAT_REG 0x0588 -#define AB4500_USB_CTRL_SPARE_REG 0x0589 -#define AB4500_USB_PHY_CTRL_REG 0x058A - -/* - * TVOUT / CTRL register offsets - * Bank : 0x06 - */ -#define AB4500_TVOUT_CTRL_REG 0x0680 - -/* - * DBI register offsets - * Bank : 0x07 - */ -#define AB4500_DBI_REG1_REG 0x0700 -#define AB4500_DBI_REG2_REG 0x0701 - -/* - * ECI regsiter offsets - * Bank : 0x08 - */ -#define AB4500_ECI_CTRL_REG 0x0800 -#define AB4500_ECI_HOOKLEVEL_REG 0x0801 -#define AB4500_ECI_DATAOUT_REG 0x0802 -#define AB4500_ECI_DATAIN_REG 0x0803 - -/* - * AV Connector register offsets - * Bank : 0x08 - */ -#define AB4500_AV_CONN_REG 0x0840 - -/* - * Accessory detection register offsets - * Bank : 0x08 - */ -#define AB4500_ACC_DET_DB1_REG 0x0880 -#define AB4500_ACC_DET_DB2_REG 0x0881 - -/* - * GPADC register offsets - * Bank : 0x0A - */ -#define AB4500_GPADC_CTRL1_REG 0x0A00 -#define AB4500_GPADC_CTRL2_REG 0x0A01 -#define AB4500_GPADC_CTRL3_REG 0x0A02 -#define AB4500_GPADC_AUTO_TIMER_REG 0x0A03 -#define AB4500_GPADC_STAT_REG 0x0A04 -#define AB4500_GPADC_MANDATAL_REG 0x0A05 -#define AB4500_GPADC_MANDATAH_REG 0x0A06 -#define AB4500_GPADC_AUTODATAL_REG 0x0A07 -#define AB4500_GPADC_AUTODATAH_REG 0x0A08 -#define AB4500_GPADC_MUX_CTRL_REG 0x0A09 - -/* - * Charger / status register offfsets - * Bank : 0x0B - */ -#define AB4500_CH_STATUS1_REG 0x0B00 -#define AB4500_CH_STATUS2_REG 0x0B01 -#define AB4500_CH_USBCH_STAT1_REG 0x0B02 -#define AB4500_CH_USBCH_STAT2_REG 0x0B03 -#define AB4500_CH_FSM_STAT_REG 0x0B04 -#define AB4500_CH_STAT_REG 0x0B05 - -/* - * Charger / control register offfsets - * Bank : 0x0B - */ -#define AB4500_CH_VOLT_LVL_REG 0x0B40 - -/* - * Charger / main control register offfsets - * Bank : 0x0B - */ -#define AB4500_MCH_CTRL1 0x0B80 -#define AB4500_MCH_CTRL2 0x0B81 -#define AB4500_MCH_IPT_CURLVL_REG 0x0B82 -#define AB4500_CH_WD_REG 0x0B83 - -/* - * Charger / USB control register offsets - * Bank : 0x0B - */ -#define AB4500_USBCH_CTRL1_REG 0x0BC0 -#define AB4500_USBCH_CTRL2_REG 0x0BC1 -#define AB4500_USBCH_IPT_CRNTLVL_REG 0x0BC2 - -/* - * RTC bank register offsets - * Bank : 0xF - */ -#define AB4500_RTC_SOFF_STAT_REG 0x0F00 -#define AB4500_RTC_CC_CONF_REG 0x0F01 -#define AB4500_RTC_READ_REQ_REG 0x0F02 -#define AB4500_RTC_WATCH_TSECMID_REG 0x0F03 -#define AB4500_RTC_WATCH_TSECHI_REG 0x0F04 -#define AB4500_RTC_WATCH_TMIN_LOW_REG 0x0F05 -#define AB4500_RTC_WATCH_TMIN_MID_REG 0x0F06 -#define AB4500_RTC_WATCH_TMIN_HI_REG 0x0F07 -#define AB4500_RTC_ALRM_MIN_LOW_REG 0x0F08 -#define AB4500_RTC_ALRM_MIN_MID_REG 0x0F09 -#define AB4500_RTC_ALRM_MIN_HI_REG 0x0F0A -#define AB4500_RTC_STAT_REG 0x0F0B -#define AB4500_RTC_BKUP_CHG_REG 0x0F0C -#define AB4500_RTC_FORCE_BKUP_REG 0x0F0D -#define AB4500_RTC_CALIB_REG 0x0F0E -#define AB4500_RTC_SWITCH_STAT_REG 0x0F0F - -/* - * PWM Out generators - * Bank: 0x10 - */ -#define AB4500_PWM_OUT_CTRL1_REG 0x1060 -#define AB4500_PWM_OUT_CTRL2_REG 0x1061 -#define AB4500_PWM_OUT_CTRL3_REG 0x1062 -#define AB4500_PWM_OUT_CTRL4_REG 0x1063 -#define AB4500_PWM_OUT_CTRL5_REG 0x1064 -#define AB4500_PWM_OUT_CTRL6_REG 0x1065 -#define AB4500_PWM_OUT_CTRL7_REG 0x1066 - -#define AB4500_I2C_PAD_CTRL_REG 0x1067 -#define AB4500_REV_REG 0x1080 - -/** - * struct ab4500 - * @spi: spi device structure - * @tx_buf: transmit buffer - * @rx_buf: receive buffer - * @lock: sync primitive - */ -struct ab4500 { - struct spi_device *spi; - unsigned long tx_buf[4]; - unsigned long rx_buf[4]; - struct mutex lock; -}; - -int ab4500_write(struct ab4500 *ab4500, unsigned char block, - unsigned long addr, unsigned char data); -int ab4500_read(struct ab4500 *ab4500, unsigned char block, - unsigned long addr); - -#endif /* MFD_AB4500_H */ diff --git a/include/linux/mfd/ab8500.h b/include/linux/mfd/ab8500.h new file mode 100644 index 000000000000..b63ff3ba3351 --- /dev/null +++ b/include/linux/mfd/ab8500.h @@ -0,0 +1,128 @@ +/* + * Copyright (C) ST-Ericsson SA 2010 + * + * License Terms: GNU General Public License v2 + * Author: Srinidhi Kasagar + */ +#ifndef MFD_AB8500_H +#define MFD_AB8500_H + +#include + +/* + * Interrupts + */ + +#define AB8500_INT_MAIN_EXT_CH_NOT_OK 0 +#define AB8500_INT_UN_PLUG_TV_DET 1 +#define AB8500_INT_PLUG_TV_DET 2 +#define AB8500_INT_TEMP_WARM 3 +#define AB8500_INT_PON_KEY2DB_F 4 +#define AB8500_INT_PON_KEY2DB_R 5 +#define AB8500_INT_PON_KEY1DB_F 6 +#define AB8500_INT_PON_KEY1DB_R 7 +#define AB8500_INT_BATT_OVV 8 +#define AB8500_INT_MAIN_CH_UNPLUG_DET 10 +#define AB8500_INT_MAIN_CH_PLUG_DET 11 +#define AB8500_INT_USB_ID_DET_F 12 +#define AB8500_INT_USB_ID_DET_R 13 +#define AB8500_INT_VBUS_DET_F 14 +#define AB8500_INT_VBUS_DET_R 15 +#define AB8500_INT_VBUS_CH_DROP_END 16 +#define AB8500_INT_RTC_60S 17 +#define AB8500_INT_RTC_ALARM 18 +#define AB8500_INT_BAT_CTRL_INDB 20 +#define AB8500_INT_CH_WD_EXP 21 +#define AB8500_INT_VBUS_OVV 22 +#define AB8500_INT_MAIN_CH_DROP_END 23 +#define AB8500_INT_CCN_CONV_ACC 24 +#define AB8500_INT_INT_AUD 25 +#define AB8500_INT_CCEOC 26 +#define AB8500_INT_CC_INT_CALIB 27 +#define AB8500_INT_LOW_BAT_F 28 +#define AB8500_INT_LOW_BAT_R 29 +#define AB8500_INT_BUP_CHG_NOT_OK 30 +#define AB8500_INT_BUP_CHG_OK 31 +#define AB8500_INT_GP_HW_ADC_CONV_END 32 +#define AB8500_INT_ACC_DETECT_1DB_F 33 +#define AB8500_INT_ACC_DETECT_1DB_R 34 +#define AB8500_INT_ACC_DETECT_22DB_F 35 +#define AB8500_INT_ACC_DETECT_22DB_R 36 +#define AB8500_INT_ACC_DETECT_21DB_F 37 +#define AB8500_INT_ACC_DETECT_21DB_R 38 +#define AB8500_INT_GP_SW_ADC_CONV_END 39 +#define AB8500_INT_BTEMP_LOW 72 +#define AB8500_INT_BTEMP_LOW_MEDIUM 73 +#define AB8500_INT_BTEMP_MEDIUM_HIGH 74 +#define AB8500_INT_BTEMP_HIGH 75 +#define AB8500_INT_USB_CHARGER_NOT_OK 81 +#define AB8500_INT_ID_WAKEUP_R 82 +#define AB8500_INT_ID_DET_R1R 84 +#define AB8500_INT_ID_DET_R2R 85 +#define AB8500_INT_ID_DET_R3R 86 +#define AB8500_INT_ID_DET_R4R 87 +#define AB8500_INT_ID_WAKEUP_F 88 +#define AB8500_INT_ID_DET_R1F 90 +#define AB8500_INT_ID_DET_R2F 91 +#define AB8500_INT_ID_DET_R3F 92 +#define AB8500_INT_ID_DET_R4F 93 +#define AB8500_INT_USB_CHG_DET_DONE 94 +#define AB8500_INT_USB_CH_TH_PROT_F 96 +#define AB8500_INT_USB_CH_TH_PROP_R 97 +#define AB8500_INT_MAIN_CH_TH_PROP_F 98 +#define AB8500_INT_MAIN_CH_TH_PROT_R 99 +#define AB8500_INT_USB_CHARGER_NOT_OKF 103 + +#define AB8500_NR_IRQS 104 +#define AB8500_NUM_IRQ_REGS 13 + +/** + * struct ab8500 - ab8500 internal structure + * @dev: parent device + * @lock: read/write operations lock + * @irq_lock: genirq bus lock + * @revision: chip revision + * @irq: irq line + * @write: register write + * @read: register read + * @rx_buf: rx buf for SPI + * @tx_buf: tx buf for SPI + * @mask: cache of IRQ regs for bus lock + * @oldmask: cache of previous IRQ regs for bus lock + */ +struct ab8500 { + struct device *dev; + struct mutex lock; + struct mutex irq_lock; + int revision; + int irq_base; + int irq; + + int (*write) (struct ab8500 *a8500, u16 addr, u8 data); + int (*read) (struct ab8500 *a8500, u16 addr); + + unsigned long tx_buf[4]; + unsigned long rx_buf[4]; + + u8 mask[AB8500_NUM_IRQ_REGS]; + u8 oldmask[AB8500_NUM_IRQ_REGS]; +}; + +/** + * struct ab8500_platform_data - AB8500 platform data + * @irq_base: start of AB8500 IRQs, AB8500_NR_IRQS will be used + * @init: board-specific initialization after detection of ab8500 + */ +struct ab8500_platform_data { + int irq_base; + void (*init) (struct ab8500 *); +}; + +extern int ab8500_write(struct ab8500 *a8500, u16 addr, u8 data); +extern int ab8500_read(struct ab8500 *a8500, u16 addr); +extern int ab8500_set_bits(struct ab8500 *a8500, u16 addr, u8 mask, u8 data); + +extern int __devinit ab8500_init(struct ab8500 *ab8500); +extern int __devexit ab8500_exit(struct ab8500 *ab8500); + +#endif /* MFD_AB8500_H */ -- cgit v1.2.3 From 752138df0dc2daaae09379c754caeb08c97905dc Mon Sep 17 00:00:00 2001 From: Len Brown Date: Sat, 22 May 2010 16:57:26 -0400 Subject: cpuidle: make cpuidle_curr_driver static cpuidle_register_driver() sets cpuidle_curr_driver cpuidle_unregister_driver() clears cpuidle_curr_driver We should't expose cpuidle_curr_driver to potential modification except via these interfaces. So make it static and create cpuidle_get_driver() to observe it. Signed-off-by: Len Brown --- include/linux/cpuidle.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index f5e6480dc16f..55215cce5005 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -125,6 +125,7 @@ struct cpuidle_driver { #ifdef CONFIG_CPU_IDLE extern int cpuidle_register_driver(struct cpuidle_driver *drv); +struct cpuidle_driver *cpuidle_get_driver(void); extern void cpuidle_unregister_driver(struct cpuidle_driver *drv); extern int cpuidle_register_device(struct cpuidle_device *dev); extern void cpuidle_unregister_device(struct cpuidle_device *dev); @@ -138,6 +139,7 @@ extern void cpuidle_disable_device(struct cpuidle_device *dev); static inline int cpuidle_register_driver(struct cpuidle_driver *drv) {return -ENODEV; } +static inline struct cpuidle_driver *cpuidle_get_driver(void) {return NULL; } static inline void cpuidle_unregister_driver(struct cpuidle_driver *drv) { } static inline int cpuidle_register_device(struct cpuidle_device *dev) {return -ENODEV; } -- cgit v1.2.3 From d7065da038227a4d09a244e6014e0186a6bd21d0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 26 May 2010 15:13:55 -0400 Subject: get rid of the magic around f_count in aio __aio_put_req() plays sick games with file refcount. What it wants is fput() from atomic context; it's almost always done with f_count > 1, so they only have to deal with delayed work in rare cases when their reference happens to be the last one. Current code decrements f_count and if it hasn't hit 0, everything is fine. Otherwise it keeps a pointer to struct file (with zero f_count!) around and has delayed work do __fput() on it. Better way to do it: use atomic_long_add_unless( , -1, 1) instead of !atomic_long_dec_and_test(). IOW, decrement it only if it's not the last reference, leave refcount alone if it was. And use normal fput() in delayed work. I've made that atomic_long_add_unless call a new helper - fput_atomic(). Drops a reference to file if it's safe to do in atomic (i.e. if that's not the last one), tells if it had been able to do that. aio.c converted to it, __fput() use is gone. req->ki_file *always* contributes to refcount now. And __fput() became static. Signed-off-by: Al Viro --- include/linux/file.h | 1 - include/linux/fs.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 5555508fd517..b1e12970f617 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -11,7 +11,6 @@ struct file; -extern void __fput(struct file *); extern void fput(struct file *); extern void drop_file_write_access(struct file *file); diff --git a/include/linux/fs.h b/include/linux/fs.h index 85e823adcd4a..3d9ed8302402 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -954,6 +954,7 @@ extern spinlock_t files_lock; #define file_list_unlock() spin_unlock(&files_lock); #define get_file(x) atomic_long_inc(&(x)->f_count) +#define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1) #define file_count(x) atomic_long_read(&(x)->f_count) #ifdef CONFIG_DEBUG_WRITECOUNT -- cgit v1.2.3 From 7ea8085910ef3dd4f3cad6845aaa2b580d39b115 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 May 2010 17:53:25 +0200 Subject: drop unused dentry argument to ->fsync Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/buffer_head.h | 2 +- include/linux/ext3_fs.h | 2 +- include/linux/fb.h | 5 +---- include/linux/fs.h | 8 ++++---- 4 files changed, 7 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 16ed0284d780..05e5f5996216 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -224,7 +224,7 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, void block_sync_page(struct page *); sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); -int file_fsync(struct file *, struct dentry *, int); +int file_fsync(struct file *, int); int nobh_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 5f494b465097..7fc62d4550b2 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -868,7 +868,7 @@ extern int ext3_htree_store_dirent(struct file *dir_file, __u32 hash, extern void ext3_htree_free_dir_info(struct dir_private_info *p); /* fsync.c */ -extern int ext3_sync_file (struct file *, struct dentry *, int); +extern int ext3_sync_file(struct file *, int); /* hash.c */ extern int ext3fs_dirhash(const char *name, int len, struct diff --git a/include/linux/fb.h b/include/linux/fb.h index f3793ebc241c..907ace3a64c8 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -4,8 +4,6 @@ #include #include -struct dentry; - /* Definitions of frame buffers */ #define FB_MAX 32 /* sufficient for now */ @@ -1017,8 +1015,7 @@ extern void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file); extern void fb_deferred_io_cleanup(struct fb_info *info); -extern int fb_deferred_io_fsync(struct file *file, struct dentry *dentry, - int datasync); +extern int fb_deferred_io_fsync(struct file *file, int datasync); static inline bool fb_be_math(struct fb_info *info) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 3d9ed8302402..eb39e5eb77f5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1498,7 +1498,7 @@ struct file_operations { int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); - int (*fsync) (struct file *, struct dentry *, int datasync); + int (*fsync) (struct file *, int datasync); int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); @@ -2213,7 +2213,7 @@ extern int generic_segment_checks(const struct iovec *iov, /* fs/block_dev.c */ extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos); -extern int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync); +extern int blkdev_fsync(struct file *filp, int datasync); /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, @@ -2348,7 +2348,7 @@ extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); -extern int simple_sync_file(struct file *, struct dentry *, int); +extern int simple_sync_file(struct file *, int); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); extern int simple_write_begin(struct file *file, struct address_space *mapping, @@ -2373,7 +2373,7 @@ extern ssize_t simple_read_from_buffer(void __user *to, size_t count, extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); -extern int simple_fsync(struct file *, struct dentry *, int); +extern int simple_fsync(struct file *, int); #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, -- cgit v1.2.3 From 1b061d9247f71cd15edc4c4c4600191a903642c0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 May 2010 17:53:41 +0200 Subject: rename the generic fsync implementations We don't name our generic fsync implementations very well currently. The no-op implementation for in-memory filesystems currently is called simple_sync_file which doesn't make too much sense to start with, the the generic one for simple filesystems is called simple_fsync which can lead to some confusion. This patch renames the generic file fsync method to generic_file_fsync to match the other generic_file_* routines it is supposed to be used with, and the no-op implementation to noop_fsync to make it obvious what to expect. In addition add some documentation for both methods. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index eb39e5eb77f5..acf6c52a50dd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2348,7 +2348,7 @@ extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); -extern int simple_sync_file(struct file *, int); +extern int noop_fsync(struct file *, int); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); extern int simple_write_begin(struct file *file, struct address_space *mapping, @@ -2373,7 +2373,7 @@ extern ssize_t simple_read_from_buffer(void __user *to, size_t count, extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); -extern int simple_fsync(struct file *, int); +extern int generic_file_fsync(struct file *, int); #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, -- cgit v1.2.3 From 7bb46a6734a7e1ad4beaecc11cae7ed3ff81d30f Mon Sep 17 00:00:00 2001 From: "npiggin@suse.de" Date: Thu, 27 May 2010 01:05:33 +1000 Subject: fs: introduce new truncate sequence Introduce a new truncate calling sequence into fs/mm subsystems. Rather than setattr > vmtruncate > truncate, have filesystems call their truncate sequence from ->setattr if filesystem specific operations are required. vmtruncate is deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced previously should be used. simple_setattr is introduced for simple in-ram filesystems to implement the new truncate sequence. Eventually all filesystems should be converted to implement a setattr, and the default code in notify_change should go away. simple_setsize is also introduced to perform just the ATTR_SIZE portion of simple_setattr (ie. changing i_size and trimming pagecache). To implement the new truncate sequence: - filesystem specific manipulations (eg freeing blocks) must be done in the setattr method rather than ->truncate. - vmtruncate can not be used by core code to trim blocks past i_size in the event of write failure after allocation, so this must be performed in the fs code. - convert usage of helpers block_write_begin, nobh_write_begin, cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed variants. These avoid calling vmtruncate to trim blocks (see previous). - inode_setattr should not be used. generic_setattr is a new function to be used to copy simple attributes into the generic inode. - make use of the better opportunity to handle errors with the new sequence. Big problem with the previous calling sequence: the filesystem is not called until i_size has already changed. This means it is not allowed to fail the call, and also it does not know what the previous i_size was. Also, generic code calling vmtruncate to truncate allocated blocks in case of error had no good way to return a meaningful error (or, for example, atomically handle block deallocation). Cc: Christoph Hellwig Acked-by: Jan Kara Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- include/linux/buffer_head.h | 9 +++++++++ include/linux/fs.h | 27 ++++++++++++++++++++++++++- 2 files changed, 35 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 05e5f5996216..1b9ba193b789 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -203,6 +203,9 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block, int block_read_full_page(struct page*, get_block_t*); int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, unsigned long from); +int block_write_begin_newtrunc(struct file *, struct address_space *, + loff_t, unsigned, unsigned, + struct page **, void **, get_block_t*); int block_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); @@ -214,6 +217,9 @@ int generic_write_end(struct file *, struct address_space *, struct page *, void *); void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); int block_prepare_write(struct page*, unsigned, unsigned, get_block_t*); +int cont_write_begin_newtrunc(struct file *, struct address_space *, loff_t, + unsigned, unsigned, struct page **, void **, + get_block_t *, loff_t *); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t *, loff_t *); @@ -225,6 +231,9 @@ void block_sync_page(struct page *); sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); int file_fsync(struct file *, int); +int nobh_write_begin_newtrunc(struct file *, struct address_space *, + loff_t, unsigned, unsigned, + struct page **, void **, get_block_t*); int nobh_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); diff --git a/include/linux/fs.h b/include/linux/fs.h index acf6c52a50dd..3428393942a6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2257,6 +2257,10 @@ typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, loff_t file_offset); void dio_end_io(struct bio *bio, int error); +ssize_t __blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, const struct iovec *iov, loff_t offset, + unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, + dio_submit_t submit_io, int lock_type); ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, loff_t offset, unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, @@ -2270,6 +2274,24 @@ enum { DIO_SKIP_HOLES = 0x02, }; +static inline ssize_t blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb, + struct inode *inode, struct block_device *bdev, const struct iovec *iov, + loff_t offset, unsigned long nr_segs, get_block_t get_block, + dio_iodone_t end_io) +{ + return __blockdev_direct_IO_newtrunc(rw, iocb, inode, bdev, iov, offset, + nr_segs, get_block, end_io, NULL, + DIO_LOCKING | DIO_SKIP_HOLES); +} + +static inline ssize_t blockdev_direct_IO_no_locking_newtrunc(int rw, struct kiocb *iocb, + struct inode *inode, struct block_device *bdev, const struct iovec *iov, + loff_t offset, unsigned long nr_segs, get_block_t get_block, + dio_iodone_t end_io) +{ + return __blockdev_direct_IO_newtrunc(rw, iocb, inode, bdev, iov, offset, + nr_segs, get_block, end_io, NULL, 0); +} static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, loff_t offset, unsigned long nr_segs, get_block_t get_block, @@ -2342,12 +2364,14 @@ extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, void *, filldir_t); +extern int simple_setattr(struct dentry *, struct iattr *); extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); +extern int simple_setsize(struct inode *, loff_t); extern int noop_fsync(struct file *, int); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); @@ -2384,7 +2408,8 @@ extern int buffer_migrate_page(struct address_space *, extern int inode_change_ok(const struct inode *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); -extern int __must_check inode_setattr(struct inode *, struct iattr *); +extern int __must_check inode_setattr(struct inode *, const struct iattr *); +extern void generic_setattr(struct inode *inode, const struct iattr *attr); extern void file_update_time(struct file *file); -- cgit v1.2.3 From 0aa12fb439838a85802ab8b7fbb9bcfc3e6e05cb Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Sat, 29 May 2010 09:12:30 -0700 Subject: sched: add wait_for_completion_killable_timeout Add missing _killable_timeout variant for wait_for_completion that will return when a timeout expires or the task is killed. CC: Ingo Molnar CC: Andreas Herrmann CC: Thomas Gleixner CC: Mike Galbraith Acked-by: Peter Zijlstra Signed-off-by: Sage Weil --- include/linux/completion.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/completion.h b/include/linux/completion.h index 4a6b604ef7e4..51e3145196f6 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -83,6 +83,8 @@ extern unsigned long wait_for_completion_timeout(struct completion *x, unsigned long timeout); extern unsigned long wait_for_completion_interruptible_timeout( struct completion *x, unsigned long timeout); +extern unsigned long wait_for_completion_killable_timeout( + struct completion *x, unsigned long timeout); extern bool try_wait_for_completion(struct completion *x); extern bool completion_done(struct completion *x); -- cgit v1.2.3 From 0f1f694260e0d35b5ce7d471f6e679c3dd4d7d94 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 27 May 2010 09:17:17 -0500 Subject: SLUB: Allow full duplication of kmalloc array for 390 Commit 756dee75872a2a764b478e18076360b8a4ec9045 ("SLUB: Get rid of dynamic DMA kmalloc cache allocation") makes S390 run out of kmalloc caches. Increase the number of kmalloc caches to a safe size. Cc: [ .33 and .34 ] Reported-by: Heiko Carstens Tested-by: Heiko Carstens Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 6ac37664e8fe..4ba59cfc1f75 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -137,7 +137,7 @@ struct kmem_cache { #ifdef CONFIG_ZONE_DMA #define SLUB_DMA __GFP_DMA /* Reserve extra caches for potential DMA use */ -#define KMALLOC_CACHES (2 * SLUB_PAGE_SHIFT - 6) +#define KMALLOC_CACHES (2 * SLUB_PAGE_SHIFT) #else /* Disable DMA functionality */ #define SLUB_DMA (__force gfp_t)0 -- cgit v1.2.3 From 35926ff5fba8245bd1c6ac04155048f6f89232b1 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 May 2010 09:00:03 -0700 Subject: Revert "cpusets: randomize node rotor used in cpuset_mem_spread_node()" This reverts commit 0ac0c0d0f837c499afd02a802f9cf52d3027fa3b, which caused cross-architecture build problems for all the wrong reasons. IA64 already added its own version of __node_random(), but the fact is, there is nothing architectural about the function, and the original commit was just badly done. Revert it, since no fix is forthcoming. Requested-by: Stephen Rothwell Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 1 - include/linux/nodemask.h | 8 -------- 2 files changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 6fb2720882fc..daf8c480c786 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -141,7 +141,6 @@ extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order); extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits); -extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits); #define BITMAP_LAST_WORD_MASK(nbits) \ ( \ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 8a8f1d09c133..dba35e413371 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -66,8 +66,6 @@ * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * - * int node_random(mask) Random node with set bit in mask - * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * @@ -432,10 +430,6 @@ static inline void node_set_offline(int nid) node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } - -#define node_random(mask) __node_random(&(mask)) -extern int __node_random(const nodemask_t *maskp); - #else static inline int node_state(int node, enum node_states state) @@ -466,8 +460,6 @@ static inline int num_node_state(enum node_states state) #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) - -static inline int node_random(const nodemask_t mask) { return 0; } #endif #define node_online_map node_states[N_ONLINE] -- cgit v1.2.3 From 97ef6f7449da6ceddf9a90fa8851f607b67283dd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 28 May 2010 15:08:08 -0700 Subject: rapidio: fix new kernel-doc warnings Fix a bunch of new rapidio kernel-doc warnings: Warning(include/linux/rio.h:123): No description found for parameter 'comp_tag' Warning(include/linux/rio.h:123): No description found for parameter 'phys_efptr' Warning(include/linux/rio.h:123): No description found for parameter 'em_efptr' Warning(include/linux/rio.h:123): No description found for parameter 'pwcback' Warning(include/linux/rio.h:247): No description found for parameter 'set_domain' Warning(include/linux/rio.h:247): No description found for parameter 'get_domain' Warning(drivers/rapidio/rio-scan.c:1133): No description found for parameter 'rdev' Warning(drivers/rapidio/rio-scan.c:1133): Excess function parameter 'port' description in 'rio_init_em' Warning(drivers/rapidio/rio.c:349): No description found for parameter 'rdev' Warning(drivers/rapidio/rio.c:349): Excess function parameter 'mport' description in 'rio_request_inb_pwrite' Warning(drivers/rapidio/rio.c:393): No description found for parameter 'port' Warning(drivers/rapidio/rio.c:393): No description found for parameter 'local' Warning(drivers/rapidio/rio.c:393): No description found for parameter 'destid' Warning(drivers/rapidio/rio.c:393): No description found for parameter 'hopcount' Warning(drivers/rapidio/rio.c:393): Excess function parameter 'rdev' description in 'rio_mport_get_physefb' Warning(drivers/rapidio/rio.c:845): Excess function parameter 'local' description in 'rio_std_route_clr_table' Signed-off-by: Randy Dunlap Cc: Alexandre Bounine Signed-off-by: Linus Torvalds --- include/linux/rio.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index 19b5f227096e..bd6eb0ed34a7 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -88,11 +88,15 @@ union rio_pw_msg; * @swpinfo: Switch port info * @src_ops: Source operation capabilities * @dst_ops: Destination operation capabilities + * @comp_tag: RIO component tag + * @phys_efptr: RIO device extended features pointer + * @em_efptr: RIO Error Management features pointer * @dma_mask: Mask of bits of RIO address this device implements * @rswitch: Pointer to &struct rio_switch if valid for this device * @driver: Driver claiming this device * @dev: Device model device * @riores: RIO resources this device owns + * @pwcback: port-write callback function for this device * @destid: Network destination ID */ struct rio_dev { @@ -222,6 +226,8 @@ struct rio_net { * @add_entry: Callback for switch-specific route add function * @get_entry: Callback for switch-specific route get function * @clr_table: Callback for switch-specific clear route table function + * @set_domain: Callback for switch-specific domain setting function + * @get_domain: Callback for switch-specific domain get function * @em_init: Callback for switch-specific error management initialization function * @em_handle: Callback for switch-specific error management handler function */ -- cgit v1.2.3