From 8e552c36d90c03d2cabf5373788998966751b609 Mon Sep 17 00:00:00 2001 From: Andres Salomon Date: Mon, 12 May 2008 21:46:29 -0400 Subject: power_supply: add CHARGE_COUNTER property and olpc_battery support for it This adds PROP_CHARGE_COUNTER to the power supply class (documenting it as well). The OLPC battery driver uses this for spitting out its ACR values (in uAh). We have some rounding errors (the data sheet claims 416.7, the math actually works out to 416.666667, so we're forced to choose between overflows or precision loss. I chose precision loss, and stuck w/ data sheet values), but I don't think anyone will care that much. Signed-off-by: Andres Salomon Signed-off-by: Anton Vorontsov --- 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 68ed19ccf1f7..ea96ead1d39d 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -78,6 +78,7 @@ enum power_supply_property { POWER_SUPPLY_PROP_CHARGE_EMPTY, POWER_SUPPLY_PROP_CHARGE_NOW, POWER_SUPPLY_PROP_CHARGE_AVG, + POWER_SUPPLY_PROP_CHARGE_COUNTER, POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN, POWER_SUPPLY_PROP_ENERGY_EMPTY_DESIGN, POWER_SUPPLY_PROP_ENERGY_FULL, -- cgit v1.2.2 From 59018b6d2acabb114ab58637e6ab95ba424a89d0 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 20 May 2008 01:03:52 +0300 Subject: MTD/JFFS2: remove CVS keywords Once upon a time, the MTD repository was using CVS. This patch therefore removes all usages of the no longer updated CVS keywords from the MTD code. This also includes code that printed them to the user. Signed-off-by: Adrian Bunk Signed-off-by: David Woodhouse --- include/linux/jffs2.h | 3 --- include/linux/mtd/blktrans.h | 2 -- include/linux/mtd/cfi.h | 1 - include/linux/mtd/cfi_endian.h | 5 ----- include/linux/mtd/concat.h | 2 -- include/linux/mtd/doc2000.h | 2 -- include/linux/mtd/flashchip.h | 3 --- include/linux/mtd/ftl.h | 2 -- include/linux/mtd/gen_probe.h | 1 - include/linux/mtd/inftl.h | 4 ---- include/linux/mtd/map.h | 1 - include/linux/mtd/mtd.h | 2 -- include/linux/mtd/nand.h | 2 -- include/linux/mtd/nand_ecc.h | 2 -- include/linux/mtd/nftl.h | 2 -- include/linux/mtd/partitions.h | 2 -- include/linux/mtd/physmap.h | 2 -- include/linux/mtd/plat-ram.h | 2 -- include/linux/mtd/pmc551.h | 4 +--- include/linux/mtd/xip.h | 2 -- 20 files changed, 1 insertion(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jffs2.h b/include/linux/jffs2.h index 6b563cae23df..da720bc3eb15 100644 --- a/include/linux/jffs2.h +++ b/include/linux/jffs2.h @@ -7,9 +7,6 @@ * * For licensing information, see the file 'LICENCE' in the * jffs2 directory. - * - * $Id: jffs2.h,v 1.38 2005/09/26 11:37:23 havasi Exp $ - * */ #ifndef __LINUX_JFFS2_H__ diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index 9a6e2f953cba..310e61606415 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -1,6 +1,4 @@ /* - * $Id: blktrans.h,v 1.6 2005/11/07 11:14:54 gleixner Exp $ - * * (C) 2003 David Woodhouse * * Interface to Linux block layer for MTD 'translation layers'. diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index b0ddf4b25862..d6fb115f5a07 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -1,7 +1,6 @@ /* Common Flash Interface structures * See http://support.intel.com/design/flash/technote/index.htm - * $Id: cfi.h,v 1.57 2005/11/15 23:28:17 tpoynor Exp $ */ #ifndef __MTD_CFI_H__ diff --git a/include/linux/mtd/cfi_endian.h b/include/linux/mtd/cfi_endian.h index 25724f7d3867..d802f7736be3 100644 --- a/include/linux/mtd/cfi_endian.h +++ b/include/linux/mtd/cfi_endian.h @@ -1,8 +1,3 @@ -/* - * $Id: cfi_endian.h,v 1.11 2002/01/30 23:20:48 awozniak Exp $ - * - */ - #include #ifndef CONFIG_MTD_CFI_ADV_OPTIONS diff --git a/include/linux/mtd/concat.h b/include/linux/mtd/concat.h index ed8dc6755219..c02f3d264ecf 100644 --- a/include/linux/mtd/concat.h +++ b/include/linux/mtd/concat.h @@ -4,8 +4,6 @@ * (C) 2002 Robert Kaiser * * This code is GPL - * - * $Id: concat.h,v 1.1 2002/03/08 16:34:36 rkaiser Exp $ */ #ifndef MTD_CONCAT_H diff --git a/include/linux/mtd/doc2000.h b/include/linux/mtd/doc2000.h index 9addd073bf15..0a6d516ab71d 100644 --- a/include/linux/mtd/doc2000.h +++ b/include/linux/mtd/doc2000.h @@ -6,8 +6,6 @@ * Copyright (C) 2002-2003 Greg Ungerer * Copyright (C) 2002-2003 SnapGear Inc * - * $Id: doc2000.h,v 1.25 2005/11/07 11:14:54 gleixner Exp $ - * * Released under GPL */ diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h index 39e7d2a1be9a..08dd131301c1 100644 --- a/include/linux/mtd/flashchip.h +++ b/include/linux/mtd/flashchip.h @@ -5,9 +5,6 @@ * Contains information about the location and state of a given flash device * * (C) 2000 Red Hat. GPLd. - * - * $Id: flashchip.h,v 1.18 2005/11/07 11:14:54 gleixner Exp $ - * */ #ifndef __MTD_FLASHCHIP_H__ diff --git a/include/linux/mtd/ftl.h b/include/linux/mtd/ftl.h index d99609113307..0be442f881dd 100644 --- a/include/linux/mtd/ftl.h +++ b/include/linux/mtd/ftl.h @@ -1,6 +1,4 @@ /* - * $Id: ftl.h,v 1.7 2005/11/07 11:14:54 gleixner Exp $ - * * Derived from (and probably identical to): * ftl.h 1.7 1999/10/25 20:23:17 * diff --git a/include/linux/mtd/gen_probe.h b/include/linux/mtd/gen_probe.h index 256e7342ed1e..df362ddf2949 100644 --- a/include/linux/mtd/gen_probe.h +++ b/include/linux/mtd/gen_probe.h @@ -1,7 +1,6 @@ /* * (C) 2001, 2001 Red Hat, Inc. * GPL'd - * $Id: gen_probe.h,v 1.4 2005/11/07 11:14:54 gleixner Exp $ */ #ifndef __LINUX_MTD_GEN_PROBE_H__ diff --git a/include/linux/mtd/inftl.h b/include/linux/mtd/inftl.h index 85fd041d44ad..64ee53ce95a9 100644 --- a/include/linux/mtd/inftl.h +++ b/include/linux/mtd/inftl.h @@ -2,8 +2,6 @@ * inftl.h -- defines to support the Inverse NAND Flash Translation Layer * * (C) Copyright 2002, Greg Ungerer (gerg@snapgear.com) - * - * $Id: inftl.h,v 1.7 2005/06/13 13:08:45 sean Exp $ */ #ifndef __MTD_INFTL_H__ @@ -52,8 +50,6 @@ struct INFTLrecord { int INFTL_mount(struct INFTLrecord *s); int INFTL_formatblock(struct INFTLrecord *s, int block); -extern char inftlmountrev[]; - void INFTL_dumptables(struct INFTLrecord *s); void INFTL_dumpVUchains(struct INFTLrecord *s); diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index a9fae032ba81..85e3939cf487 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -1,6 +1,5 @@ /* Overhauled routines for dealing with different mmap regions of flash */ -/* $Id: map.h,v 1.54 2005/11/07 11:14:54 gleixner Exp $ */ #ifndef __LINUX_MTD_MAP_H__ #define __LINUX_MTD_MAP_H__ diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 245f9098e171..31ed234b2a74 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -1,6 +1,4 @@ /* - * $Id: mtd.h,v 1.61 2005/11/07 11:14:54 gleixner Exp $ - * * Copyright (C) 1999-2003 David Woodhouse et al. * * Released under GPL diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index c42bc7f533a5..1288be7b7740 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -5,8 +5,6 @@ * Steven J. Hill * Thomas Gleixner * - * $Id: nand.h,v 1.74 2005/09/15 13:58:50 vwool Exp $ - * * 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. diff --git a/include/linux/mtd/nand_ecc.h b/include/linux/mtd/nand_ecc.h index 12c5bc342ead..090da505425d 100644 --- a/include/linux/mtd/nand_ecc.h +++ b/include/linux/mtd/nand_ecc.h @@ -3,8 +3,6 @@ * * Copyright (C) 2000 Steven J. Hill (sjhill@realitydiluted.com) * - * $Id: nand_ecc.h,v 1.4 2004/06/17 02:35:02 dbrown Exp $ - * * 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. diff --git a/include/linux/mtd/nftl.h b/include/linux/mtd/nftl.h index 001eec50cac6..dcaf611ed748 100644 --- a/include/linux/mtd/nftl.h +++ b/include/linux/mtd/nftl.h @@ -1,6 +1,4 @@ /* - * $Id: nftl.h,v 1.16 2004/06/30 14:49:00 dbrown Exp $ - * * (C) 1999-2003 David Woodhouse */ diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 7c37d7e55abc..5014f7a9f5df 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -4,8 +4,6 @@ * (C) 2000 Nicolas Pitre * * This code is GPL - * - * $Id: partitions.h,v 1.17 2005/11/07 11:14:55 gleixner Exp $ */ #ifndef MTD_PARTITIONS_H diff --git a/include/linux/mtd/physmap.h b/include/linux/mtd/physmap.h index 0dc07d5f3354..c8e63a5ee72e 100644 --- a/include/linux/mtd/physmap.h +++ b/include/linux/mtd/physmap.h @@ -2,8 +2,6 @@ * For boards with physically mapped flash and using * drivers/mtd/maps/physmap.c mapping driver. * - * $Id: physmap.h,v 1.4 2005/11/07 11:14:55 gleixner Exp $ - * * Copyright (C) 2003 MontaVista Software Inc. * Author: Jun Sun, jsun@mvista.com or jsun@junsun.net * diff --git a/include/linux/mtd/plat-ram.h b/include/linux/mtd/plat-ram.h index 0e37ad07bce2..e07890aff1cf 100644 --- a/include/linux/mtd/plat-ram.h +++ b/include/linux/mtd/plat-ram.h @@ -6,8 +6,6 @@ * * Generic platform device based RAM map * - * $Id: plat-ram.h,v 1.2 2005/01/24 00:37:40 bjd Exp $ - * * 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. diff --git a/include/linux/mtd/pmc551.h b/include/linux/mtd/pmc551.h index 5cc070c24d88..27ad40aed19f 100644 --- a/include/linux/mtd/pmc551.h +++ b/include/linux/mtd/pmc551.h @@ -1,6 +1,4 @@ /* - * $Id: pmc551.h,v 1.6 2005/11/07 11:14:55 gleixner Exp $ - * * PMC551 PCI Mezzanine Ram Device * * Author: @@ -17,7 +15,7 @@ #include -#define PMC551_VERSION "$Id: pmc551.h,v 1.6 2005/11/07 11:14:55 gleixner Exp $\n"\ +#define PMC551_VERSION \ "Ramix PMC551 PCI Mezzanine Ram Driver. (C) 1999,2000 Nortel Networks.\n" /* diff --git a/include/linux/mtd/xip.h b/include/linux/mtd/xip.h index e9d40bdde48c..36efcba15ecd 100644 --- a/include/linux/mtd/xip.h +++ b/include/linux/mtd/xip.h @@ -11,8 +11,6 @@ * 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. - * - * $Id: xip.h,v 1.5 2005/11/07 11:14:55 gleixner Exp $ */ #ifndef __LINUX_MTD_XIP_H__ -- cgit v1.2.2 From a822bea7962b500b0bcab41bf3500f7c40ae56b5 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 6 Jun 2008 01:34:00 -0400 Subject: Input: serio - mark serio_register_driver() __must_check Also remove extra declaration of serio_register_driver(). Signed-off-by: Dmitry Torokhov --- include/linux/serio.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serio.h b/include/linux/serio.h index e72716cca577..25641d9e0ea8 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -87,11 +87,10 @@ void serio_unregister_port(struct serio *serio); void serio_unregister_child_port(struct serio *serio); int __serio_register_driver(struct serio_driver *drv, struct module *owner, const char *mod_name); -static inline int serio_register_driver(struct serio_driver *drv) +static inline int __must_check serio_register_driver(struct serio_driver *drv) { return __serio_register_driver(drv, THIS_MODULE, KBUILD_MODNAME); } -int serio_register_driver(struct serio_driver *drv); void serio_unregister_driver(struct serio_driver *drv); static inline int serio_write(struct serio *serio, unsigned char data) -- cgit v1.2.2 From d8e64406a037a64444175730294e449c9e21f5ec Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 23 Jul 2008 13:09:48 -0700 Subject: md: delay notification of 'active_idle' to the recovery thread sysfs_notify might sleep, so do not call it from md_safemode_timeout. Signed-off-by: Dan Williams --- include/linux/raid/md_k.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 9f2549ac0e2d..c200b9a34aff 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -128,6 +128,7 @@ struct mddev_s #define MD_CHANGE_DEVS 0 /* Some device status has changed */ #define MD_CHANGE_CLEAN 1 /* transition to or from 'clean' */ #define MD_CHANGE_PENDING 2 /* superblock update in progress */ +#define MD_NOTIFY_ARRAY_STATE 3 /* atomic context wants to notify userspace */ int ro; -- cgit v1.2.2 From 95984f62c9b0bf6d89ef4f514b1afe73623481de Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Tue, 22 Jul 2008 18:41:10 +0200 Subject: firewire: fw-ohci: TSB43AB22/A dualbuffer workaround Isochronous reception in dualbuffer mode is reportedly broken with TI TSB43AB22A on x86-64. Descriptor addresses above 2G have been determined as the trigger: https://bugzilla.redhat.com/show_bug.cgi?id=435550 Two fixes are possible: - pci_set_consistent_dma_mask(pdev, DMA_31BIT_MASK); at least when IR descriptors are allocated, or - simply don't use dualbuffer. This fix implements the latter workaround. But we keep using dualbuffer on x86-32 which won't give us highmen (and thus physical addresses outside the 31bit range) in coherent DMA memory allocations. Right now we could for example also whitelist PPC32, but DMA mapping implementation details are expected to change there. Signed-off-by: Stefan Richter Signed-off-by: Jarod Wilson --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 65953822c9cb..720d67554106 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -748,6 +748,7 @@ #define PCI_VENDOR_ID_TI 0x104c #define PCI_DEVICE_ID_TI_TVP4020 0x3d07 #define PCI_DEVICE_ID_TI_4450 0x8011 +#define PCI_DEVICE_ID_TI_TSB43AB22 0x8023 #define PCI_DEVICE_ID_TI_XX21_XX11 0x8031 #define PCI_DEVICE_ID_TI_XX21_XX11_FM 0x8033 #define PCI_DEVICE_ID_TI_XX21_XX11_SD 0x8034 -- cgit v1.2.2 From 3d45955962496879dead8d4dd70bb9a23b07154b Mon Sep 17 00:00:00 2001 From: Alexey Korolev Date: Thu, 15 May 2008 17:23:18 +0100 Subject: [MTD] [NAND] subpage read feature as a way to increase performance. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch enables NAND subpage read functionality. If upper layer drivers are requesting to read non page aligned data NAND subpage-read functionality reads the only whose ECC regions which include requested data when original code reads whole page. This significantly improves performance in many cases. Here are some digits : UBI volume mount time No subpage reads: 5.75 seconds Subpage read patch: 2.42 seconds Open/stat time for files on JFFS2 volume: No subpage read 0m 5.36s Subpage read 0m 2.88s Signed-off-by Alexey Korolev Acked-by: Artem Bityutskiy Acked-by: Jörn Engel Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 863e22a0ddb5..83f678702dff 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -177,6 +177,7 @@ typedef enum { #define NAND_MUST_PAD(chip) (!(chip->options & NAND_NO_PADDING)) #define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) #define NAND_HAS_COPYBACK(chip) ((chip->options & NAND_COPYBACK)) +#define NAND_SUBPAGE_READ(chip) ((chip->ecc.mode == NAND_ECC_SOFT)) /* Mask to zero out the chip options, which come from the id table */ #define NAND_CHIPOPTIONS_MSK (0x0000ffff & ~NAND_NO_AUTOINCR) @@ -274,6 +275,10 @@ struct nand_ecc_ctrl { int (*read_page)(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf); + int (*read_subpage)(struct mtd_info *mtd, + struct nand_chip *chip, + uint32_t offs, uint32_t len, + uint8_t *buf); void (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, const uint8_t *buf); -- cgit v1.2.2 From 25c94d010a8ae8605dc4d5453e0c82fa97da5d12 Mon Sep 17 00:00:00 2001 From: Yevgeny Petrilin Date: Fri, 25 Jul 2008 10:30:06 -0700 Subject: mlx4_core: Add VLAN tag field to WQE control segment struct Add fields for VLAN tag and insert VLAN tag flag to the control section struct. These fields will be used for sending ethernet packets. Signed-off-by: Yevgeny Petrilin Signed-off-by: Roland Dreier --- include/linux/mlx4/qp.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index e27082cd650e..bf8f11982dae 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -164,11 +164,13 @@ enum { MLX4_WQE_CTRL_SOLICITED = 1 << 1, MLX4_WQE_CTRL_IP_CSUM = 1 << 4, MLX4_WQE_CTRL_TCP_UDP_CSUM = 1 << 5, + MLX4_WQE_CTRL_INS_VLAN = 1 << 6, }; struct mlx4_wqe_ctrl_seg { __be32 owner_opcode; - u8 reserved2[3]; + __be16 vlan_tag; + u8 ins_vlan; u8 fence_size; /* * High 24 bits are SRC remote buffer; low 8 bits are flags: -- cgit v1.2.2 From 3f07af494dfa6de43137dae430431c9fbf929c0c Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Fri, 25 Jul 2008 22:25:13 -0400 Subject: of: adapt of_find_i2c_driver() to be usable by SPI also SPI has a similar problem as I2C in that it needs to determine an appropriate modalias value for each device node. This patch adapts the of_i2c of_find_i2c_driver() function to be usable by of_spi also. Signed-off-by: Grant Likely --- include/linux/of.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 59a61bdc98b6..79886ade070f 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -70,5 +70,6 @@ extern int of_n_addr_cells(struct device_node *np); extern int of_n_size_cells(struct device_node *np); extern const struct of_device_id *of_match_node( const struct of_device_id *matches, const struct device_node *node); +extern int of_modalias_node(struct device_node *node, char *modalias, int len); #endif /* _LINUX_OF_H */ -- cgit v1.2.2 From dc87c98e8f635a718f1abb2c3e15fc77c0001651 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 15 May 2008 16:50:22 -0600 Subject: spi: split up spi_new_device() to allow two stage registration. spi_new_device() allocates and registers an spi device all in one swoop. If the driver needs to add extra data to the spi_device before it is registered, then this causes problems. This is needed for OF device tree support so that the SPI device tree helper can add a pointer to the device node after the device is allocated, but before the device is registered. OF aware SPI devices can then retrieve data out of the device node to populate a platform data structure. This patch splits the allocation and registration portions of code out of spi_new_device() and creates two new functions; spi_alloc_device() and spi_register_device(). spi_new_device() is modified to use the new functions for allocation and registration. None of the existing users of spi_new_device() should be affected by this change. Drivers using the new API can forego the use of spi_board_info structure to describe the device layout and populate data into the spi_device structure directly. This change is in preparation for adding an OF device tree parser to generate spi_devices based on data in the device tree. Signed-off-by: Grant Likely Acked-by: David Brownell --- include/linux/spi/spi.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a9cc29d46653..4be01bb44377 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -778,7 +778,19 @@ spi_register_board_info(struct spi_board_info const *info, unsigned n) * use spi_new_device() to describe each device. You can also call * spi_unregister_device() to start making that device vanish, but * normally that would be handled by spi_unregister_master(). + * + * You can also use spi_alloc_device() and spi_add_device() to use a two + * stage registration sequence for each spi_device. This gives the caller + * some more control over the spi_device structure before it is registered, + * but requires that caller to initialize fields that would otherwise + * be defined using the board info. */ +extern struct spi_device * +spi_alloc_device(struct spi_master *master); + +extern int +spi_add_device(struct spi_device *spi); + extern struct spi_device * spi_new_device(struct spi_master *, struct spi_board_info *); -- cgit v1.2.2 From 284b01897340974000bcc84de87a4e1becc8a83d Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Fri, 16 May 2008 11:37:09 -0600 Subject: spi: Add OF binding support for SPI busses This patch adds support for populating an SPI bus based on data in the OF device tree. This is useful for powerpc platforms which use the device tree instead of discrete code for describing platform layout. Signed-off-by: Grant Likely --- include/linux/of_spi.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/of_spi.h (limited to 'include/linux') diff --git a/include/linux/of_spi.h b/include/linux/of_spi.h new file mode 100644 index 000000000000..5f71ee8c0868 --- /dev/null +++ b/include/linux/of_spi.h @@ -0,0 +1,18 @@ +/* + * OpenFirmware SPI support routines + * Copyright (C) 2008 Secret Lab Technologies Ltd. + * + * Support routines for deriving SPI device attachments from the device + * tree. + */ + +#ifndef __LINUX_OF_SPI_H +#define __LINUX_OF_SPI_H + +#include +#include + +extern void of_register_spi_devices(struct spi_master *master, + struct device_node *np); + +#endif /* __LINUX_OF_SPI */ -- cgit v1.2.2 From ec34c702ca8b7d6f0aa54379c3b0d0ec10b8ff23 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Fri, 25 Jul 2008 21:45:49 -0700 Subject: net: drop unused BUG_TRAP() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index f4d386c191f5..ca643b13b026 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -755,13 +755,6 @@ extern void __rtnl_unlock(void); } \ } while(0) -#define BUG_TRAP(x) do { \ - if (unlikely(!(x))) { \ - printk(KERN_ERR "KERNEL: assertion (%s) failed at %s (%d)\n", \ - #x, __FILE__ , __LINE__); \ - } \ -} while(0) - static inline u32 rtm_get_table(struct rtattr **rta, u8 table) { return RTA_GET_U32(rta[RTA_TABLE-1]); -- cgit v1.2.2 From 36ac26171afa8dbf29226199699fe955d4a0b6f6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 26 Jul 2008 11:22:33 +0200 Subject: crashdump: fix undefined reference to `elfcorehdr_addr' fix build bug introduced by 95b68dec0d5 "calgary iommu: use the first kernels TCE tables in kdump": arch/x86/kernel/built-in.o: In function `calgary_iommu_init': (.init.text+0x8399): undefined reference to `elfcorehdr_addr' arch/x86/kernel/built-in.o: In function `calgary_iommu_init': (.init.text+0x856c): undefined reference to `elfcorehdr_addr' arch/x86/kernel/built-in.o: In function `detect_calgary': (.init.text+0x8c68): undefined reference to `elfcorehdr_addr' arch/x86/kernel/built-in.o: In function `detect_calgary': (.init.text+0x8d0c): undefined reference to `elfcorehdr_addr' make elfcorehdr_addr a generally available symbol. Signed-off-by: Ingo Molnar --- include/linux/crash_dump.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 6cd39a927e1f..025e4f575103 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -8,7 +8,13 @@ #include #define ELFCORE_ADDR_MAX (-1ULL) + +#ifdef CONFIG_PROC_VMCORE extern unsigned long long elfcorehdr_addr; +#else +static const unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; +#endif + extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); extern const struct file_operations proc_vmcore_operations; -- cgit v1.2.2 From 3bc9f79ee1ddc913be0a6d3592036683ef8a3148 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 25 Jul 2008 14:57:58 +0200 Subject: iommu: add iommu_num_pages helper function Calculating the number of pages from given address and length numbers is a task required in multiple IOMMU implementations. So implement this as a generic function into the IOMMU helper code. Signed-off-by: Joerg Roedel Cc: iommu@lists.linux-foundation.org Cc: bhavna.sarathy@amd.com Cc: robert.richter@amd.com Cc: FUJITA Tomonori Signed-off-by: Ingo Molnar --- include/linux/iommu-helper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu-helper.h b/include/linux/iommu-helper.h index c975caf75385..f8598f583944 100644 --- a/include/linux/iommu-helper.h +++ b/include/linux/iommu-helper.h @@ -8,3 +8,4 @@ extern unsigned long iommu_area_alloc(unsigned long *map, unsigned long size, unsigned long align_mask); extern void iommu_area_free(unsigned long *map, unsigned long start, unsigned int nr); +extern unsigned long iommu_num_pages(unsigned long addr, unsigned long len); -- cgit v1.2.2 From b8d317d10cca76cabe6b03ebfeb23cc99118b731 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Thu, 24 Jul 2008 18:21:29 -0700 Subject: cpumask: make cpumask_of_cpu_map generic If an arch doesn't define cpumask_of_cpu_map, create a generic statically-initialized one for them. This allows removal of the buggy cpumask_of_cpu() macro (&cpumask_of_cpu() gives address of out-of-scope var). An arch with NR_CPUS of 4096 probably wants to allocate this itself based on the actual number of CPUs, since otherwise they're using 2MB of rodata (1024 cpus means 128k). That's what CONFIG_HAVE_CPUMASK_OF_CPU_MAP is for (only x86/64 does so at the moment). In future as we support more CPUs, we'll need to resort to a get_cpu_map()/put_cpu_map() allocation scheme. Signed-off-by: Mike Travis Signed-off-by: Rusty Russell Cc: Andrew Morton Cc: Jack Steiner Signed-off-by: Ingo Molnar --- include/linux/cpumask.h | 41 +++-------------------------------------- 1 file changed, 3 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1b5c98e7fef7..8fa3b6d4a320 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -62,15 +62,7 @@ * int next_cpu_nr(cpu, mask) Next cpu past 'cpu', or nr_cpu_ids * * cpumask_t cpumask_of_cpu(cpu) Return cpumask with bit 'cpu' set - *ifdef CONFIG_HAS_CPUMASK_OF_CPU - * cpumask_of_cpu_ptr_declare(v) Declares cpumask_t *v - * cpumask_of_cpu_ptr_next(v, cpu) Sets v = &cpumask_of_cpu_map[cpu] - * cpumask_of_cpu_ptr(v, cpu) Combines above two operations - *else - * cpumask_of_cpu_ptr_declare(v) Declares cpumask_t _v and *v = &_v - * cpumask_of_cpu_ptr_next(v, cpu) Sets _v = cpumask_of_cpu(cpu) - * cpumask_of_cpu_ptr(v, cpu) Combines above two operations - *endif + * (can be used as an lvalue) * CPU_MASK_ALL Initializer - all bits set * CPU_MASK_NONE Initializer - no bits set * unsigned long *cpus_addr(mask) Array of unsigned long's in mask @@ -274,36 +266,9 @@ static inline void __cpus_shift_left(cpumask_t *dstp, } -#ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP -extern cpumask_t *cpumask_of_cpu_map; +/* cpumask_of_cpu_map[] is in kernel/cpu.c */ +extern const cpumask_t *cpumask_of_cpu_map; #define cpumask_of_cpu(cpu) (cpumask_of_cpu_map[cpu]) -#define cpumask_of_cpu_ptr(v, cpu) \ - const cpumask_t *v = &cpumask_of_cpu(cpu) -#define cpumask_of_cpu_ptr_declare(v) \ - const cpumask_t *v -#define cpumask_of_cpu_ptr_next(v, cpu) \ - v = &cpumask_of_cpu(cpu) -#else -#define cpumask_of_cpu(cpu) \ -({ \ - typeof(_unused_cpumask_arg_) m; \ - if (sizeof(m) == sizeof(unsigned long)) { \ - m.bits[0] = 1UL<<(cpu); \ - } else { \ - cpus_clear(m); \ - cpu_set((cpu), m); \ - } \ - m; \ -}) -#define cpumask_of_cpu_ptr(v, cpu) \ - cpumask_t _##v = cpumask_of_cpu(cpu); \ - const cpumask_t *v = &_##v -#define cpumask_of_cpu_ptr_declare(v) \ - cpumask_t _##v; \ - const cpumask_t *v = &_##v -#define cpumask_of_cpu_ptr_next(v, cpu) \ - _##v = cpumask_of_cpu(cpu) -#endif #define CPU_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(NR_CPUS) -- cgit v1.2.2 From fdd2a7e2dac56a3384068802be46b822f2aed703 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 26 Jul 2008 13:25:25 -0300 Subject: V4L/DVB (8500a): videotext.h: whitespace cleanup Signed-off-by: Mauro Carvalho Chehab --- include/linux/videotext.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/videotext.h b/include/linux/videotext.h index 018f92047ff8..3e68c8d1c7f7 100644 --- a/include/linux/videotext.h +++ b/include/linux/videotext.h @@ -45,10 +45,10 @@ #define VTXIOCCLRCACHE_OLD 0x710b /* clear cache on VTX-interface (if avail.) */ #define VTXIOCSETVIRT_OLD 0x710c /* turn on virtual mode (this disables TV-display) */ -/* +/* * Definitions for VTXIOCGETINFO */ - + #define SAA5243 0 #define SAA5246 1 #define SAA5249 2 @@ -57,10 +57,10 @@ typedef struct { int version_major, version_minor; /* version of driver; if version_major changes, driver */ - /* is not backward compatible!!! CHECK THIS!!! */ + /* is not backward compatible!!! CHECK THIS!!! */ int numpages; /* number of page-buffers of vtx-chipset */ int cct_type; /* type of vtx-chipset (SAA5243, SAA5246, SAA5248 or - * SAA5249) */ + * SAA5249) */ } vtx_info_t; @@ -81,7 +81,7 @@ vtx_info_t; #define PGMASK_HOUR (HR_TEN | HR_UNIT) #define PGMASK_MINUTE (MIN_TEN | MIN_UNIT) -typedef struct +typedef struct { int page; /* number of requested page (hexadecimal) */ int hour; /* requested hour (hexadecimal) */ @@ -98,11 +98,11 @@ vtx_pagereq_t; /* * Definitions for VTXIOC{GETSTAT,PUTSTAT} */ - + #define VTX_PAGESIZE (40 * 24) #define VTX_VIRTUALSIZE (40 * 49) -typedef struct +typedef struct { int pagenum; /* number of page (hexadecimal) */ int hour; /* hour (hexadecimal) */ @@ -121,5 +121,5 @@ typedef struct unsigned hamming : 1; /* hamming-error occurred */ } vtx_pageinfo_t; - + #endif /* _VTX_H */ -- cgit v1.2.2 From 16d69265b930f7e2fa9eea381715696f780718f4 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 25 Jul 2008 19:44:36 -0700 Subject: uninline arch_pick_mmap_layout() Fix this, on avr32: include/linux/utsname.h:35, from init/main.c:20: include/linux/sched.h: In function 'arch_pick_mmap_layout': include/linux/sched.h:2149: error: implicit declaration of function 'PAGE_ALIGN' Reported-by: Adrian Bunk Cc: Haavard Skinnemoen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 42036ffe6b00..3260a5c42b91 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2139,16 +2139,7 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ -#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT extern void arch_pick_mmap_layout(struct mm_struct *mm); -#else -static inline void arch_pick_mmap_layout(struct mm_struct *mm) -{ - mm->mmap_base = TASK_UNMAPPED_BASE; - mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; -} -#endif #ifdef CONFIG_TRACING extern void -- cgit v1.2.2 From 8d8bb39b9eba32dd70e87fd5ad5c5dd4ba118e06 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Fri, 25 Jul 2008 19:44:49 -0700 Subject: dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori Cc: Muli Ben-Yehuda Cc: Andi Kleen Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Avi Kivity Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/i2o.h | 2 +- include/linux/ssb/ssb.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2o.h b/include/linux/i2o.h index 7d51cbca49ab..75ae6d8aba4f 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -758,7 +758,7 @@ static inline dma_addr_t i2o_dma_map_single(struct i2o_controller *c, void *ptr, } dma_addr = dma_map_single(&c->pdev->dev, ptr, size, direction); - if (!dma_mapping_error(dma_addr)) { + if (!dma_mapping_error(&c->pdev->dev, dma_addr)) { #ifdef CONFIG_I2O_EXT_ADAPTEC_DMA64 if ((sizeof(dma_addr_t) > 4) && c->pae_support) { *mptr++ = cpu_to_le32(0x7C020002); diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 4bf8cade9dbc..e530026eedf7 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -427,9 +427,9 @@ static inline int ssb_dma_mapping_error(struct ssb_device *dev, dma_addr_t addr) { switch (dev->bus->bustype) { case SSB_BUSTYPE_PCI: - return pci_dma_mapping_error(addr); + return pci_dma_mapping_error(dev->bus->host_pci, addr); case SSB_BUSTYPE_SSB: - return dma_mapping_error(addr); + return dma_mapping_error(dev->dev, addr); default: __ssb_dma_not_implemented(dev); } -- cgit v1.2.2 From 929dfb24fbcd60e2544b2de7bfb4a68da4dfc747 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 19:44:54 -0700 Subject: parport/share.c: proper externs This patch adds proper externs for parport_default_timeslice and parport_default_spintime in include/linux/parport.h Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/parport.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/parport.h b/include/linux/parport.h index dcb9e01a69ca..6a0d7cdb5774 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -560,5 +560,8 @@ extern int parport_device_proc_unregister(struct pardevice *device); #endif /* !CONFIG_PARPORT_NOT_PC */ +extern unsigned long parport_default_timeslice; +extern int parport_default_spintime; + #endif /* __KERNEL__ */ #endif /* _PARPORT_H_ */ -- cgit v1.2.2 From b77899985bdfd85a8e5a6e485033a9b4713d2471 Mon Sep 17 00:00:00 2001 From: Alex Dubov Date: Fri, 25 Jul 2008 19:45:00 -0700 Subject: memstick: allow "set_param" method to return an error code Some controllers (Jmicron, for instance) can report temporal failure condition during power-on. It is desirable to account for this using a return value of "set_param" device method. The return value can also be handy to distinguish between supported and unsupported device parameters in run time. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alex Dubov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memstick.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memstick.h b/include/linux/memstick.h index 37a5cdb03918..2fe599c66d52 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -284,7 +284,7 @@ struct memstick_host { /* Notify the host that some requests are pending. */ void (*request)(struct memstick_host *host); /* Set host IO parameters (power, clock, etc). */ - void (*set_param)(struct memstick_host *host, + int (*set_param)(struct memstick_host *host, enum memstick_param param, int value); unsigned long private[0] ____cacheline_aligned; -- cgit v1.2.2 From 17017d8d2c005734d7088d8281ce2daab8fcb097 Mon Sep 17 00:00:00 2001 From: Alex Dubov Date: Fri, 25 Jul 2008 19:45:01 -0700 Subject: memstick: add "start" and "stop" methods to memstick device In some cases it may be desirable to ensure that associated driver is not going to access the media in some period of time. "start" and "stop" methods are provided therefore to allow it. Signed-off-by: Alex Dubov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memstick.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memstick.h b/include/linux/memstick.h index 2fe599c66d52..a9f998a3f48b 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -263,6 +263,10 @@ struct memstick_dev { /* Get next request from the media driver. */ int (*next_request)(struct memstick_dev *card, struct memstick_request **mrq); + /* Tell the media driver to stop doing things */ + void (*stop)(struct memstick_dev *card); + /* Allow the media driver to continue */ + void (*start)(struct memstick_dev *card); struct device dev; }; -- cgit v1.2.2 From 3ab83521378268044a448113c6aa9a9e245f4d2f Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 25 Jul 2008 19:45:07 -0700 Subject: kexec jump This patch provides an enhancement to kexec/kdump. It implements the following features: - Backup/restore memory used by the original kernel before/after kexec. - Save/restore CPU state before/after kexec. The features of this patch can be used as a general method to call program in physical mode (paging turning off). This can be used to call BIOS code under Linux. kexec-tools needs to be patched to support kexec jump. The patches and the precompiled kexec can be download from the following URL: source: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-src_git_kh10.tar.bz2 patches: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-patches_git_kh10.tar.bz2 binary: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec_git_kh10 Usage example of calling some physical mode code and return: 1. Compile and install patched kernel with following options selected: CONFIG_X86_32=y CONFIG_KEXEC=y CONFIG_PM=y CONFIG_KEXEC_JUMP=y 2. Build patched kexec-tool or download the pre-built one. 3. Build some physical mode executable named such as "phy_mode" 4. Boot kernel compiled in step 1. 5. Load physical mode executable with /sbin/kexec. The shell command line can be as follow: /sbin/kexec --load-preserve-context --args-none phy_mode 6. Call physical mode executable with following shell command line: /sbin/kexec -e Implementation point: To support jumping without reserving memory. One shadow backup page (source page) is allocated for each page used by kexeced code image (destination page). When do kexec_load, the image of kexeced code is loaded into source pages, and before executing, the destination pages and the source pages are swapped, so the contents of destination pages are backupped. Before jumping to the kexeced code image and after jumping back to the original kernel, the destination pages and the source pages are swapped too. C ABI (calling convention) is used as communication protocol between kernel and called code. A flag named KEXEC_PRESERVE_CONTEXT for sys_kexec_load is added to indicate that the loaded kernel image is used for jumping back. Now, only the i386 architecture is supported. Signed-off-by: Huang Ying Acked-by: Vivek Goyal Cc: "Eric W. Biederman" Cc: Pavel Machek Cc: Nigel Cunningham Cc: "Rafael J. Wysocki" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 3265968cd2cd..82f88a8a827b 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -83,6 +83,7 @@ struct kimage { unsigned long start; struct page *control_code_page; + struct page *swap_page; unsigned long nr_segments; struct kexec_segment segment[KEXEC_SEGMENT_MAX]; @@ -98,18 +99,20 @@ struct kimage { unsigned int type : 1; #define KEXEC_TYPE_DEFAULT 0 #define KEXEC_TYPE_CRASH 1 + unsigned int preserve_context : 1; }; /* kexec interface functions */ -extern NORET_TYPE void machine_kexec(struct kimage *image) ATTRIB_NORET; +extern void machine_kexec(struct kimage *image); extern int machine_kexec_prepare(struct kimage *image); extern void machine_kexec_cleanup(struct kimage *image); extern asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, struct kexec_segment __user *segments, unsigned long flags); +extern int kernel_kexec(void); #ifdef CONFIG_COMPAT extern asmlinkage long compat_sys_kexec_load(unsigned long entry, unsigned long nr_segments, @@ -156,8 +159,9 @@ extern struct kimage *kexec_crash_image; #define kexec_flush_icache_page(page) #endif -#define KEXEC_ON_CRASH 0x00000001 -#define KEXEC_ARCH_MASK 0xffff0000 +#define KEXEC_ON_CRASH 0x00000001 +#define KEXEC_PRESERVE_CONTEXT 0x00000002 +#define KEXEC_ARCH_MASK 0xffff0000 /* These values match the ELF architecture values. * Unless there is a good reason that should continue to be the case. @@ -174,7 +178,12 @@ extern struct kimage *kexec_crash_image; #define KEXEC_ARCH_MIPS_LE (10 << 16) #define KEXEC_ARCH_MIPS ( 8 << 16) -#define KEXEC_FLAGS (KEXEC_ON_CRASH) /* List of defined/legal kexec flags */ +/* List of defined/legal kexec flags */ +#ifndef CONFIG_KEXEC_JUMP +#define KEXEC_FLAGS KEXEC_ON_CRASH +#else +#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT) +#endif #define VMCOREINFO_BYTES (4096) #define VMCOREINFO_NOTE_NAME "VMCOREINFO" -- cgit v1.2.2 From 89081d17f7bb81d89fa1aa9b70f821c5cf4d39e9 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 25 Jul 2008 19:45:10 -0700 Subject: kexec jump: save/restore device state This patch implements devices state save/restore before after kexec. This patch together with features in kexec_jump patch can be used for following: - A simple hibernation implementation without ACPI support. You can kexec a hibernating kernel, save the memory image of original system and shutdown the system. When resuming, you restore the memory image of original system via ordinary kexec load then jump back. - Kernel/system debug through making system snapshot. You can make system snapshot, jump back, do some thing and make another system snapshot. - Cooperative multi-kernel/system. With kexec jump, you can switch between several kernels/systems quickly without boot process except the first time. This appears like swap a whole kernel/system out/in. - A general method to call program in physical mode (paging turning off). This can be used to invoke BIOS code under Linux. The following user-space tools can be used with kexec jump: - kexec-tools needs to be patched to support kexec jump. The patches and the precompiled kexec can be download from the following URL: source: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-src_git_kh10.tar.bz2 patches: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-patches_git_kh10.tar.bz2 binary: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec_git_kh10 - makedumpfile with patches are used as memory image saving tool, it can exclude free pages from original kernel memory image file. The patches and the precompiled makedumpfile can be download from the following URL: source: http://khibernation.sourceforge.net/download/release_v10/makedumpfile/makedumpfile-src_cvs_kh10.tar.bz2 patches: http://khibernation.sourceforge.net/download/release_v10/makedumpfile/makedumpfile-patches_cvs_kh10.tar.bz2 binary: http://khibernation.sourceforge.net/download/release_v10/makedumpfile/makedumpfile_cvs_kh10 - An initramfs image can be used as the root file system of kexeced kernel. An initramfs image built with "BuildRoot" can be downloaded from the following URL: initramfs image: http://khibernation.sourceforge.net/download/release_v10/initramfs/rootfs_cvs_kh10.gz All user space tools above are included in the initramfs image. Usage example of simple hibernation: 1. Compile and install patched kernel with following options selected: CONFIG_X86_32=y CONFIG_RELOCATABLE=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y CONFIG_PM=y CONFIG_HIBERNATION=y CONFIG_KEXEC_JUMP=y 2. Build an initramfs image contains kexec-tool and makedumpfile, or download the pre-built initramfs image, called rootfs.gz in following text. 3. Prepare a partition to save memory image of original kernel, called hibernating partition in following text. 4. Boot kernel compiled in step 1 (kernel A). 5. In the kernel A, load kernel compiled in step 1 (kernel B) with /sbin/kexec. The shell command line can be as follow: /sbin/kexec --load-preserve-context /boot/bzImage --mem-min=0x100000 --mem-max=0xffffff --initrd=rootfs.gz 6. Boot the kernel B with following shell command line: /sbin/kexec -e 7. The kernel B will boot as normal kexec. In kernel B the memory image of kernel A can be saved into hibernating partition as follow: jump_back_entry=`cat /proc/cmdline | tr ' ' '\n' | grep kexec_jump_back_entry | cut -d '='` echo $jump_back_entry > kexec_jump_back_entry cp /proc/vmcore dump.elf Then you can shutdown the machine as normal. 8. Boot kernel compiled in step 1 (kernel C). Use the rootfs.gz as root file system. 9. In kernel C, load the memory image of kernel A as follow: /sbin/kexec -l --args-none --entry=`cat kexec_jump_back_entry` dump.elf 10. Jump back to the kernel A as follow: /sbin/kexec -e Then, kernel A is resumed. Implementation point: To support jumping between two kernels, before jumping to (executing) the new kernel and jumping back to the original kernel, the devices are put into quiescent state, and the state of devices and CPU is saved. After jumping back from kexeced kernel and jumping to the new kernel, the state of devices and CPU are restored accordingly. The devices/CPU state save/restore code of software suspend is called to implement corresponding function. Known issues: - Because the segment number supported by sys_kexec_load is limited, hibernation image with many segments may not be load. This is planned to be eliminated by adding a new flag to sys_kexec_load to make a image can be loaded with multiple sys_kexec_load invoking. Now, only the i386 architecture is supported. Signed-off-by: Huang Ying Acked-by: Vivek Goyal Cc: "Eric W. Biederman" Cc: Pavel Machek Cc: Nigel Cunningham Cc: "Rafael J. Wysocki" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/suspend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index e8e69159af71..c63435095970 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -278,4 +278,6 @@ static inline void register_nosave_region_late(unsigned long b, unsigned long e) } #endif +extern struct mutex pm_mutex; + #endif /* _LINUX_SUSPEND_H */ -- cgit v1.2.2 From c2147a5092cfe13dbf3210e54e8a622015edeecc Mon Sep 17 00:00:00 2001 From: Eduard - Gabriel Munteanu Date: Fri, 25 Jul 2008 19:45:11 -0700 Subject: Better interface for hooking early initcalls Added early initcall (pre-SMP) support, using an identical interface to that of regular initcalls. Functions called from do_pre_smp_initcalls() could be converted to use this cleaner interface. This is required by CPU hotplug, because early users have to register notifiers before going SMP. One such CPU hotplug user is the relay interface with buffer-only channels, which needs to register such a notifier, to be usable in early code. This in turn is used by kmemtrace. Signed-off-by: Eduard - Gabriel Munteanu Cc: Tom Zanussi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 42ae95411a93..11b84e106053 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -169,6 +169,13 @@ extern void (*late_time_init)(void); static initcall_t __initcall_##fn##id __used \ __attribute__((__section__(".initcall" level ".init"))) = fn +/* + * Early initcalls run before initializing SMP. + * + * Only for built-in code, not modules. + */ +#define early_initcall(fn) __define_initcall("early",fn,early) + /* * A "pure" initcall has no dependencies on anything else, and purely * initializes variables that couldn't be statically initialized. -- cgit v1.2.2 From 7babe8db99d305340cf4828ce1f5a1481d5622ef Mon Sep 17 00:00:00 2001 From: Eduard - Gabriel Munteanu Date: Fri, 25 Jul 2008 19:45:11 -0700 Subject: Full conversion to early_initcall() interface, remove old interface A previous patch added the early_initcall(), to allow a cleaner hooking of pre-SMP initcalls. Now we remove the older interface, converting all existing users to the new one. [akpm@linux-foundation.org: cleanups] [akpm@linux-foundation.org: build fix] [kosaki.motohiro@jp.fujitsu.com: warning fix] [kosaki.motohiro@jp.fujitsu.com: warning fix] Signed-off-by: Eduard - Gabriel Munteanu Cc: Tom Zanussi Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 9 --------- include/linux/smp.h | 5 ----- 2 files changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3260a5c42b91..adb8077dc463 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -292,7 +292,6 @@ extern void sched_show_task(struct task_struct *p); #ifdef CONFIG_DETECT_SOFTLOCKUP extern void softlockup_tick(void); -extern void spawn_softlockup_task(void); extern void touch_softlockup_watchdog(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; @@ -2222,14 +2221,6 @@ static inline void inc_syscw(struct task_struct *tsk) } #endif -#ifdef CONFIG_SMP -void migration_init(void); -#else -static inline void migration_init(void) -{ -} -#endif - #ifndef TASK_SIZE_OF #define TASK_SIZE_OF(tsk) TASK_SIZE #endif diff --git a/include/linux/smp.h b/include/linux/smp.h index 48262f86c969..66484d4a8459 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -74,15 +74,10 @@ void __smp_call_function_single(int cpuid, struct call_single_data *data); #ifdef CONFIG_USE_GENERIC_SMP_HELPERS void generic_smp_call_function_single_interrupt(void); void generic_smp_call_function_interrupt(void); -void init_call_single_data(void); void ipi_call_lock(void); void ipi_call_unlock(void); void ipi_call_lock_irq(void); void ipi_call_unlock_irq(void); -#else -static inline void init_call_single_data(void) -{ -} #endif /* -- cgit v1.2.2 From 20d8b67c06fa5e74f44e80b0a0fd68c8327f7c6a Mon Sep 17 00:00:00 2001 From: Eduard - Gabriel Munteanu Date: Fri, 25 Jul 2008 19:45:12 -0700 Subject: relay: add buffer-only channels; useful for early logging Allows one to create and use a channel with no associated files. Files can be initialized later. This is useful in scenarios such as logging in early code, before VFS is up. Therefore, such channels can be created and used as soon as kmem_cache_init() completed. This is needed by kmemtrace to do tracing in early kernel code. [kosaki.motohiro@jp.fujitsu.com: build fix] Signed-off-by: Eduard - Gabriel Munteanu Cc: Tom Zanussi Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/relay.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/relay.h b/include/linux/relay.h index 6cd8c4425fc7..953fc055e875 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -48,6 +48,7 @@ struct rchan_buf size_t *padding; /* padding counts per sub-buffer */ size_t prev_padding; /* temporary variable */ size_t bytes_consumed; /* bytes consumed in cur read subbuf */ + size_t early_bytes; /* bytes consumed before VFS inited */ unsigned int cpu; /* this buf's cpu */ } ____cacheline_aligned; @@ -68,6 +69,7 @@ struct rchan int is_global; /* One global buffer ? */ struct list_head list; /* for channel list */ struct dentry *parent; /* parent dentry passed to open */ + int has_base_filename; /* has a filename associated? */ char base_filename[NAME_MAX]; /* saved base filename */ }; @@ -169,6 +171,9 @@ struct rchan *relay_open(const char *base_filename, size_t n_subbufs, struct rchan_callbacks *cb, void *private_data); +extern int relay_late_setup_files(struct rchan *chan, + const char *base_filename, + struct dentry *parent); extern void relay_close(struct rchan *chan); extern void relay_flush(struct rchan *chan); extern void relay_subbufs_consumed(struct rchan *chan, -- cgit v1.2.2 From 080ccd4573607a930367c2128fc709814b2ade5d Mon Sep 17 00:00:00 2001 From: Huang Weiyi Date: Fri, 25 Jul 2008 19:45:13 -0700 Subject: include/linux/aio.h: removed duplicated include Removed duplicated include in include/linux/aio.h Signed-off-by: Huang Weiyi Signed-off-by: Benjamin LaHaise Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index b51ddd28444e..09b276c35227 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -7,7 +7,6 @@ #include #include -#include #define AIO_MAXSEGS 4 #define AIO_KIOGRP_NR_ATOMIC 8 -- cgit v1.2.2 From 21cc199baa815d7b3f1ace4be20b9558cbddc00f Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:22 -0700 Subject: mm: introduce get_user_pages_fast Introduce a new get_user_pages_fast mm API, which is basically a get_user_pages with a less general API (but still tends to be suited to the common case): - task and mm are always current and current->mm - force is always 0 - pages is always non-NULL - don't pass back vmas This restricted API can be implemented in a much more scalable way on many architectures when the ptes are present, by walking the page tables locklessly (no mmap_sem or page table locks). When the ptes are not populated, get_user_pages_fast() could be slower. This is implemented locklessly on x86, and used in some key direct IO call sites, in later patches, which provides nearly 10% performance improvement on a threaded database workload. Lots of other code could use this too, depending on use cases (eg. grep drivers/). And it might inspire some new and clever ways to use it. [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Nick Piggin Cc: Dave Kleikamp Cc: Andy Whitcroft Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Andi Kleen Cc: Dave Kleikamp Cc: Badari Pulavarty Cc: Zach Brown Cc: Jens Axboe Reviewed-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d87a5a5fe87d..f3fd70d6029f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -833,6 +833,39 @@ extern int mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); +#ifdef CONFIG_HAVE_GET_USER_PAGES_FAST +/* + * get_user_pages_fast provides equivalent functionality to get_user_pages, + * operating on current and current->mm (force=0 and doesn't return any vmas). + * + * get_user_pages_fast may take mmap_sem and page tables, so no assumptions + * can be made about locking. get_user_pages_fast is to be implemented in a + * way that is advantageous (vs get_user_pages()) when the user memory area is + * already faulted in and present in ptes. However if the pages have to be + * faulted in, it may turn out to be slightly slower). + */ +int get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages); + +#else +/* + * Should probably be moved to asm-generic, and architectures can include it if + * they don't implement their own get_user_pages_fast. + */ +#define get_user_pages_fast(start, nr_pages, write, pages) \ +({ \ + struct mm_struct *mm = current->mm; \ + int ret; \ + \ + down_read(&mm->mmap_sem); \ + ret = get_user_pages(current, mm, start, nr_pages, \ + write, 0, pages, NULL); \ + up_read(&mm->mmap_sem); \ + \ + ret; \ +}) +#endif + /* * A callback you can register to apply pressure to ageable caches. * -- cgit v1.2.2 From 47feff2c8eefe85099f87c43d3096855f0085ca0 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:29 -0700 Subject: radix-tree: add gang_lookup_slot, gang_lookup_slot_tag Introduce gang_lookup_slot() and gang_lookup_slot_tag() functions, which are used by lockless pagecache. Signed-off-by: Nick Piggin Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Hugh Dickins Cc: "Paul E. McKenney" Reviewed-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index b8ce2b444bb5..a916c6660dfa 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -99,12 +99,15 @@ do { \ * * The notable exceptions to this rule are the following functions: * radix_tree_lookup + * radix_tree_lookup_slot * radix_tree_tag_get * radix_tree_gang_lookup + * radix_tree_gang_lookup_slot * radix_tree_gang_lookup_tag + * radix_tree_gang_lookup_tag_slot * radix_tree_tagged * - * The first 4 functions are able to be called locklessly, using RCU. The + * The first 7 functions are able to be called locklessly, using RCU. The * caller must ensure calls to these functions are made within rcu_read_lock() * regions. Other readers (lock-free or otherwise) and modifications may be * running concurrently. @@ -159,6 +162,9 @@ void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items); +unsigned int +radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, + unsigned long first_index, unsigned int max_items); unsigned long radix_tree_next_hole(struct radix_tree_root *root, unsigned long index, unsigned long max_scan); int radix_tree_preload(gfp_t gfp_mask); @@ -173,6 +179,10 @@ unsigned int radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag); +unsigned int +radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results, + unsigned long first_index, unsigned int max_items, + unsigned int tag); int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag); static inline void radix_tree_preload_end(void) -- cgit v1.2.2 From e286781d5f2e9c846e012a39653a166e9d31777d Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:30 -0700 Subject: mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin Cc: Jeff Garzik Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Hugh Dickins Cc: "Paul E. McKenney" Reviewed-by: Peter Zijlstra Signed-off-by: Daisuke Nishimura Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: KOSAKI Motohiro Signed-off-by: Hugh Dickins Acked-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 111 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 110 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ee1ec2c7723c..a81d81890422 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -12,6 +12,7 @@ #include #include #include +#include /* for in_interrupt() */ /* * Bits in mapping->flags. The lower __GFP_BITS_SHIFT bits are the page @@ -62,6 +63,98 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define page_cache_release(page) put_page(page) void release_pages(struct page **pages, int nr, int cold); +/* + * speculatively take a reference to a page. + * If the page is free (_count == 0), then _count is untouched, and 0 + * is returned. Otherwise, _count is incremented by 1 and 1 is returned. + * + * This function must be called inside the same rcu_read_lock() section as has + * been used to lookup the page in the pagecache radix-tree (or page table): + * this allows allocators to use a synchronize_rcu() to stabilize _count. + * + * Unless an RCU grace period has passed, the count of all pages coming out + * of the allocator must be considered unstable. page_count may return higher + * than expected, and put_page must be able to do the right thing when the + * page has been finished with, no matter what it is subsequently allocated + * for (because put_page is what is used here to drop an invalid speculative + * reference). + * + * This is the interesting part of the lockless pagecache (and lockless + * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page) + * has the following pattern: + * 1. find page in radix tree + * 2. conditionally increment refcount + * 3. check the page is still in pagecache (if no, goto 1) + * + * Remove-side that cares about stability of _count (eg. reclaim) has the + * following (with tree_lock held for write): + * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg) + * B. remove page from pagecache + * C. free the page + * + * There are 2 critical interleavings that matter: + * - 2 runs before A: in this case, A sees elevated refcount and bails out + * - A runs before 2: in this case, 2 sees zero refcount and retries; + * subsequently, B will complete and 1 will find no page, causing the + * lookup to return NULL. + * + * It is possible that between 1 and 2, the page is removed then the exact same + * page is inserted into the same position in pagecache. That's OK: the + * old find_get_page using tree_lock could equally have run before or after + * such a re-insertion, depending on order that locks are granted. + * + * Lookups racing against pagecache insertion isn't a big problem: either 1 + * will find the page or it will not. Likewise, the old find_get_page could run + * either before the insertion or afterwards, depending on timing. + */ +static inline int page_cache_get_speculative(struct page *page) +{ + VM_BUG_ON(in_interrupt()); + +#if !defined(CONFIG_SMP) && defined(CONFIG_CLASSIC_RCU) +# ifdef CONFIG_PREEMPT + VM_BUG_ON(!in_atomic()); +# endif + /* + * Preempt must be disabled here - we rely on rcu_read_lock doing + * this for us. + * + * Pagecache won't be truncated from interrupt context, so if we have + * found a page in the radix tree here, we have pinned its refcount by + * disabling preempt, and hence no need for the "speculative get" that + * SMP requires. + */ + VM_BUG_ON(page_count(page) == 0); + atomic_inc(&page->_count); + +#else + if (unlikely(!get_page_unless_zero(page))) { + /* + * Either the page has been freed, or will be freed. + * In either case, retry here and the caller should + * do the right thing (see comments above). + */ + return 0; + } +#endif + VM_BUG_ON(PageTail(page)); + + return 1; +} + +static inline int page_freeze_refs(struct page *page, int count) +{ + return likely(atomic_cmpxchg(&page->_count, count, 0) == count); +} + +static inline void page_unfreeze_refs(struct page *page, int count) +{ + VM_BUG_ON(page_count(page) != 0); + VM_BUG_ON(count == 0); + + atomic_set(&page->_count, count); +} + #ifdef CONFIG_NUMA extern struct page *__page_cache_alloc(gfp_t gfp); #else @@ -133,13 +226,29 @@ static inline struct page *read_mapping_page(struct address_space *mapping, return read_cache_page(mapping, index, filler, data); } -int add_to_page_cache(struct page *page, struct address_space *mapping, +int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void remove_from_page_cache(struct page *page); extern void __remove_from_page_cache(struct page *page); +/* + * Like add_to_page_cache_locked, but used to add newly allocated pages: + * the page is new, so we can just run SetPageLocked() against it. + */ +static inline int add_to_page_cache(struct page *page, + struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) +{ + int error; + + SetPageLocked(page); + error = add_to_page_cache_locked(page, mapping, offset, gfp_mask); + if (unlikely(error)) + ClearPageLocked(page); + return error; +} + /* * Return byte-offset into filesystem object for page. */ -- cgit v1.2.2 From 19fd6231279be3c3bdd02ed99f9b0eb195978064 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:32 -0700 Subject: mm: spinlock tree_lock mapping->tree_lock has no read lockers. convert the lock from an rwlock to a spinlock. Signed-off-by: Nick Piggin Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Hugh Dickins Cc: "Paul E. McKenney" Reviewed-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 49d8eb7a71be..53d2edb709b3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -499,7 +499,7 @@ struct backing_dev_info; struct address_space { struct inode *host; /* owner: inode, block_device */ struct radix_tree_root page_tree; /* radix tree of all pages */ - rwlock_t tree_lock; /* and rwlock protecting it */ + spinlock_t tree_lock; /* and lock protecting it */ unsigned int i_mmap_writable;/* count VM_SHARED mappings */ struct prio_tree_root i_mmap; /* tree of private and shared mappings */ struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ -- cgit v1.2.2 From 51cc50685a4275c6a02653670af9f108a64e01cf Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 25 Jul 2008 19:45:34 -0700 Subject: SL*B: drop kmem cache argument from constructor Kmem cache passed to constructor is only needed for constructors that are themselves multiplexeres. Nobody uses this "feature", nor does anybody uses passed kmem cache in non-trivial way, so pass only pointer to object. Non-trivial places are: arch/powerpc/mm/init_64.c arch/powerpc/mm/hugetlbpage.c This is flag day, yes. Signed-off-by: Alexey Dobriyan Acked-by: Pekka Enberg Acked-by: Christoph Lameter Cc: Jon Tollefson Cc: Nick Piggin Cc: Matt Mackall [akpm@linux-foundation.org: fix arch/powerpc/mm/hugetlbpage.c] [akpm@linux-foundation.org: fix mm/slab.c] [akpm@linux-foundation.org: fix ubifs] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 +- include/linux/slub_def.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 41103910f8a2..9ff8e8499403 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -58,7 +58,7 @@ int slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, - void (*)(struct kmem_cache *, void *)); + void (*)(void *)); void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); void kmem_cache_free(struct kmem_cache *, void *); diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index d117ea2825a9..5bad61a93f65 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -85,7 +85,7 @@ struct kmem_cache { struct kmem_cache_order_objects min; gfp_t allocflags; /* gfp flags to use on each alloc */ int refcount; /* Refcount for slab cache destroy */ - void (*ctor)(struct kmem_cache *, void *); + void (*ctor)(void *); int inuse; /* Offset to metadata */ int align; /* Alignment */ const char *name; /* Name (only for display!) */ -- cgit v1.2.2 From 88ac2921a71f788ed693bcd44731dd6bc1994640 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:43 -0700 Subject: tracehook: add linux/tracehook.h This patch series introduces the "tracehook" interface layer of inlines in . There are more details in the log entry for patch 01/23 and in the header file comments inside that patch. Most of these changes move code around with little or no change, and they should not break anything or change any behavior. This sets a new standard for uniform arch support to enable clean arch-independent implementations of new debugging and tracing stuff, denoted by CONFIG_HAVE_ARCH_TRACEHOOK. Patch 20/23 adds that symbol to arch/Kconfig, with comments listing everything an arch has to do before setting "select HAVE_ARCH_TRACEHOOK". These are elaborted a bit at: http://sourceware.org/systemtap/wiki/utrace/arch/HowTo The new inlines that arch code must define or call have detailed kerneldoc comments in the generic header files that say what is required. No arch is obligated to do any work, and no arch's build should be broken by these changes. There are several steps that each arch should take so it can set HAVE_ARCH_TRACEHOOK. Most of these are simple. Providing this support will let new things people add for doing debugging and tracing of user-level threads "just work" for your arch in the future. For an arch that does not provide HAVE_ARCH_TRACEHOOK, some new options for such features will not be available for config. I have done some arch work and will submit this to the arch maintainers after the generic tracehook series settles in. For now, that work is available in my GIT repositories, and in patch and mbox-of-patches form at http://people.redhat.com/roland/utrace/2.6-current/ This paves the way for my "utrace" work, to be submitted later. But it is not innately tied to that. I hope that the tracehook series can go in soon regardless of what eventually does or doesn't go on top of it. For anyone implementing any kind of new tracing/debugging plan, or just understanding all the context of the existing ptrace implementation, having tracehook.h makes things much easier to find and understand. This patch: This adds the new kernel-internal header file . This is not yet used at all. The comments in the header introduce what the following series of patches is about. The aim is to formalize and consolidate all the places that the core kernel code and the arch code now ties into the ptrace implementation. These patches mostly don't cause any functional change. They just move the details of ptrace logic out of core code into tracehook.h inlines, where they are mostly compiled away to the same as before. All that changes is that everything is thoroughly documented and any future reworking of ptrace, or addition of something new, would not have to touch core code all over, just change the tracehook.h inlines. The new linux/ptrace.h inlines are used by the following patches in the new tracehook_*() inlines. Using these helpers for the ptrace event stops makes it simple to change or disable the old ptrace implementation of these stops conditionally later. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 33 ++++++++++++++++++++++++++++++ include/linux/tracehook.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 85 insertions(+) create mode 100644 include/linux/tracehook.h (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index c6f5f9dd0cee..c74abfc4c7e8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -121,6 +121,39 @@ static inline void ptrace_unlink(struct task_struct *child) int generic_ptrace_peekdata(struct task_struct *tsk, long addr, long data); int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data); +/** + * task_ptrace - return %PT_* flags that apply to a task + * @task: pointer to &task_struct in question + * + * Returns the %PT_* flags that apply to @task. + */ +static inline int task_ptrace(struct task_struct *task) +{ + return task->ptrace; +} + +/** + * ptrace_event - possibly stop for a ptrace event notification + * @mask: %PT_* bit to check in @current->ptrace + * @event: %PTRACE_EVENT_* value to report if @mask is set + * @message: value for %PTRACE_GETEVENTMSG to return + * + * This checks the @mask bit to see if ptrace wants stops for this event. + * If so we stop, reporting @event and @message to the ptrace parent. + * + * Returns nonzero if we did a ptrace notification, zero if not. + * + * Called without locks. + */ +static inline int ptrace_event(int mask, int event, unsigned long message) +{ + if (mask && likely(!(current->ptrace & mask))) + return 0; + current->ptrace_message = message; + ptrace_notify((event << 8) | SIGTRAP); + return 1; +} + #ifndef force_successful_syscall_return /* * System call handlers that, upon successful completion, need to return a diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h new file mode 100644 index 000000000000..bea0f3eeff54 --- /dev/null +++ b/include/linux/tracehook.h @@ -0,0 +1,52 @@ +/* + * Tracing hooks + * + * Copyright (C) 2008 Red Hat, Inc. All rights reserved. + * + * This copyrighted material is made available to anyone wishing to use, + * modify, copy, or redistribute it subject to the terms and conditions + * of the GNU General Public License v.2. + * + * This file defines hook entry points called by core code where + * user tracing/debugging support might need to do something. These + * entry points are called tracehook_*(). Each hook declared below + * has a detailed kerneldoc comment giving the context (locking et + * al) from which it is called, and the meaning of its return value. + * + * Each function here typically has only one call site, so it is ok + * to have some nontrivial tracehook_*() inlines. In all cases, the + * fast path when no tracing is enabled should be very short. + * + * The purpose of this file and the tracehook_* layer is to consolidate + * the interface that the kernel core and arch code uses to enable any + * user debugging or tracing facility (such as ptrace). The interfaces + * here are carefully documented so that maintainers of core and arch + * code do not need to think about the implementation details of the + * tracing facilities. Likewise, maintainers of the tracing code do not + * need to understand all the calling core or arch code in detail, just + * documented circumstances of each call, such as locking conditions. + * + * If the calling core code changes so that locking is different, then + * it is ok to change the interface documented here. The maintainer of + * core code changing should notify the maintainers of the tracing code + * that they need to work out the change. + * + * Some tracehook_*() inlines take arguments that the current tracing + * implementations might not necessarily use. These function signatures + * are chosen to pass in all the information that is on hand in the + * caller and might conceivably be relevant to a tracer, so that the + * core code won't have to be updated when tracing adds more features. + * If a call site changes so that some of those parameters are no longer + * already on hand without extra work, then the tracehook_* interface + * can change so there is no make-work burden on the core code. The + * maintainer of core code changing should notify the maintainers of the + * tracing code that they need to work out the change. + */ + +#ifndef _LINUX_TRACEHOOK_H +#define _LINUX_TRACEHOOK_H 1 + +#include +#include + +#endif /* */ -- cgit v1.2.2 From 6341c393fcc37d58727865f1ee2f65e632e9d4f0 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:44 -0700 Subject: tracehook: exec This moves all the ptrace hooks related to exec into tracehook.h inlines. This also lifts the calls for tracing out of the binfmt load_binary hooks into search_binary_handler() after it calls into the binfmt module. This change has no effect, since all the binfmt modules' load_binary functions did the call at the end on success, and now search_binary_handler() does it immediately after return if successful. We consolidate the repeated code, and binfmt modules no longer need to import ptrace_notify(). Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index bea0f3eeff54..6276353709c1 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -48,5 +48,51 @@ #include #include +#include +struct linux_binprm; + +/** + * tracehook_unsafe_exec - check for exec declared unsafe due to tracing + * @task: current task doing exec + * + * Return %LSM_UNSAFE_* bits applied to an exec because of tracing. + * + * Called with task_lock() held on @task. + */ +static inline int tracehook_unsafe_exec(struct task_struct *task) +{ + int unsafe = 0; + int ptrace = task_ptrace(task); + if (ptrace & PT_PTRACED) { + if (ptrace & PT_PTRACE_CAP) + unsafe |= LSM_UNSAFE_PTRACE_CAP; + else + unsafe |= LSM_UNSAFE_PTRACE; + } + return unsafe; +} + +/** + * tracehook_report_exec - a successful exec was completed + * @fmt: &struct linux_binfmt that performed the exec + * @bprm: &struct linux_binprm containing exec details + * @regs: user-mode register state + * + * An exec just completed, we are shortly going to return to user mode. + * The freshly initialized register state can be seen and changed in @regs. + * The name, file and other pointers in @bprm are still on hand to be + * inspected, but will be freed as soon as this returns. + * + * Called with no locks, but with some kernel resources held live + * and a reference on @fmt->module. + */ +static inline void tracehook_report_exec(struct linux_binfmt *fmt, + struct linux_binprm *bprm, + struct pt_regs *regs) +{ + if (!ptrace_event(PT_TRACE_EXEC, PTRACE_EVENT_EXEC, 0) && + unlikely(task_ptrace(current) & PT_PTRACED)) + send_sig(SIGTRAP, current, 0); +} #endif /* */ -- cgit v1.2.2 From 30199f5a46aee204bf437a4f5b0740f3efe448b7 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:46 -0700 Subject: tracehook: exit This moves the PTRACE_EVENT_EXIT tracing into a tracehook.h inline, tracehook_report_exec(). The change has no effect, just clean-up. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 6276353709c1..967ab473afbc 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -95,4 +95,19 @@ static inline void tracehook_report_exec(struct linux_binfmt *fmt, send_sig(SIGTRAP, current, 0); } +/** + * tracehook_report_exit - task has begun to exit + * @exit_code: pointer to value destined for @current->exit_code + * + * @exit_code points to the value passed to do_exit(), which tracing + * might change here. This is almost the first thing in do_exit(), + * before freeing any resources or setting the %PF_EXITING flag. + * + * Called with no locks held. + */ +static inline void tracehook_report_exit(long *exit_code) +{ + ptrace_event(PT_TRACE_EXIT, PTRACE_EVENT_EXIT, *exit_code); +} + #endif /* */ -- cgit v1.2.2 From 09a05394fe2448a4139b014936330af23fa7ec83 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:47 -0700 Subject: tracehook: clone This moves all the ptrace initialization and tracing logic for task creation into tracehook.h and ptrace.h inlines. It reorganizes the code slightly, but should not change any behavior. There are four tracehook entry points, at each important stage of task creation. This keeps the interface from the core fork.c code fairly clean, while supporting the complex setup required for ptrace or something like it. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 22 ++++++++++ include/linux/tracehook.h | 100 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 122 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index c74abfc4c7e8..dae6d85520fb 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -154,6 +154,28 @@ static inline int ptrace_event(int mask, int event, unsigned long message) return 1; } +/** + * ptrace_init_task - initialize ptrace state for a new child + * @child: new child task + * @ptrace: true if child should be ptrace'd by parent's tracer + * + * This is called immediately after adding @child to its parent's children + * list. @ptrace is false in the normal case, and true to ptrace @child. + * + * Called with current's siglock and write_lock_irq(&tasklist_lock) held. + */ +static inline void ptrace_init_task(struct task_struct *child, bool ptrace) +{ + INIT_LIST_HEAD(&child->ptrace_entry); + INIT_LIST_HEAD(&child->ptraced); + child->parent = child->real_parent; + child->ptrace = 0; + if (unlikely(ptrace)) { + child->ptrace = current->ptrace; + __ptrace_link(child, current->parent); + } +} + #ifndef force_successful_syscall_return /* * System call handlers that, upon successful completion, need to return a diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 967ab473afbc..3ebc58b59766 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -110,4 +110,104 @@ static inline void tracehook_report_exit(long *exit_code) ptrace_event(PT_TRACE_EXIT, PTRACE_EVENT_EXIT, *exit_code); } +/** + * tracehook_prepare_clone - prepare for new child to be cloned + * @clone_flags: %CLONE_* flags from clone/fork/vfork system call + * + * This is called before a new user task is to be cloned. + * Its return value will be passed to tracehook_finish_clone(). + * + * Called with no locks held. + */ +static inline int tracehook_prepare_clone(unsigned clone_flags) +{ + if (clone_flags & CLONE_UNTRACED) + return 0; + + if (clone_flags & CLONE_VFORK) { + if (current->ptrace & PT_TRACE_VFORK) + return PTRACE_EVENT_VFORK; + } else if ((clone_flags & CSIGNAL) != SIGCHLD) { + if (current->ptrace & PT_TRACE_CLONE) + return PTRACE_EVENT_CLONE; + } else if (current->ptrace & PT_TRACE_FORK) + return PTRACE_EVENT_FORK; + + return 0; +} + +/** + * tracehook_finish_clone - new child created and being attached + * @child: new child task + * @clone_flags: %CLONE_* flags from clone/fork/vfork system call + * @trace: return value from tracehook_clone_prepare() + * + * This is called immediately after adding @child to its parent's children list. + * The @trace value is that returned by tracehook_prepare_clone(). + * + * Called with current's siglock and write_lock_irq(&tasklist_lock) held. + */ +static inline void tracehook_finish_clone(struct task_struct *child, + unsigned long clone_flags, int trace) +{ + ptrace_init_task(child, (clone_flags & CLONE_PTRACE) || trace); +} + +/** + * tracehook_report_clone - in parent, new child is about to start running + * @trace: return value from tracehook_clone_prepare() + * @regs: parent's user register state + * @clone_flags: flags from parent's system call + * @pid: new child's PID in the parent's namespace + * @child: new child task + * + * Called after a child is set up, but before it has been started running. + * The @trace value is that returned by tracehook_clone_prepare(). + * This is not a good place to block, because the child has not started yet. + * Suspend the child here if desired, and block in tracehook_clone_complete(). + * This must prevent the child from self-reaping if tracehook_clone_complete() + * uses the @child pointer; otherwise it might have died and been released by + * the time tracehook_report_clone_complete() is called. + * + * Called with no locks held, but the child cannot run until this returns. + */ +static inline void tracehook_report_clone(int trace, struct pt_regs *regs, + unsigned long clone_flags, + pid_t pid, struct task_struct *child) +{ + if (unlikely(trace)) { + /* + * The child starts up with an immediate SIGSTOP. + */ + sigaddset(&child->pending.signal, SIGSTOP); + set_tsk_thread_flag(child, TIF_SIGPENDING); + } +} + +/** + * tracehook_report_clone_complete - new child is running + * @trace: return value from tracehook_clone_prepare() + * @regs: parent's user register state + * @clone_flags: flags from parent's system call + * @pid: new child's PID in the parent's namespace + * @child: child task, already running + * + * This is called just after the child has started running. This is + * just before the clone/fork syscall returns, or blocks for vfork + * child completion if @clone_flags has the %CLONE_VFORK bit set. + * The @child pointer may be invalid if a self-reaping child died and + * tracehook_report_clone() took no action to prevent it from self-reaping. + * + * Called with no locks held. + */ +static inline void tracehook_report_clone_complete(int trace, + struct pt_regs *regs, + unsigned long clone_flags, + pid_t pid, + struct task_struct *child) +{ + if (unlikely(trace)) + ptrace_event(0, trace, pid); +} + #endif /* */ -- cgit v1.2.2 From daded34be96b1975ff8539ff62ad8b158ce7d842 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:47 -0700 Subject: tracehook: vfork-done This moves the PTRACE_EVENT_VFORK_DONE tracing into a tracehook.h inline, tracehook_report_vfork_done(). The change has no effect, just clean-up. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 3ebc58b59766..830e6e16097d 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -210,4 +210,22 @@ static inline void tracehook_report_clone_complete(int trace, ptrace_event(0, trace, pid); } +/** + * tracehook_report_vfork_done - vfork parent's child has exited or exec'd + * @child: child task, already running + * @pid: new child's PID in the parent's namespace + * + * Called after a %CLONE_VFORK parent has waited for the child to complete. + * The clone/vfork system call will return immediately after this. + * The @child pointer may be invalid if a self-reaping child died and + * tracehook_report_clone() took no action to prevent it from self-reaping. + * + * Called with no locks held. + */ +static inline void tracehook_report_vfork_done(struct task_struct *child, + pid_t pid) +{ + ptrace_event(PT_TRACE_VFORK_DONE, PTRACE_EVENT_VFORK_DONE, pid); +} + #endif /* */ -- cgit v1.2.2 From dae33574dcf5211e1f43c7e45fa29f73ba3e00cb Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:48 -0700 Subject: tracehook: release_task This moves the ptrace-related logic from release_task into tracehook.h and ptrace.h inlines. It provides clean hooks both before and after locking tasklist_lock, for future tracing logic to do more cleanup without the lock. This also changes release_task() itself in the rare "zap_leader" case to set the leader to EXIT_DEAD before iterating. This maintains the invariant that release_task() only ever handles a task in EXIT_DEAD. This is a common-sense invariant that is already always true except in this one arcane case of zombie leader whose parent ignores SIGCHLD. This change is harmless and only costs one store in this one rare case. It keeps the expected state more consisently sane, which is nicer when debugging weirdness in release_task(). It also lets some future code in the tracehook entry points rely on this invariant for bookkeeping. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 13 +++++++++++++ include/linux/tracehook.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index dae6d85520fb..ed69c03692d9 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -176,6 +176,19 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) } } +/** + * ptrace_release_task - final ptrace-related cleanup of a zombie being reaped + * @task: task in %EXIT_DEAD state + * + * Called with write_lock(&tasklist_lock) held. + */ +static inline void ptrace_release_task(struct task_struct *task) +{ + BUG_ON(!list_empty(&task->ptraced)); + ptrace_unlink(task); + BUG_ON(!list_empty(&task->ptrace_entry)); +} + #ifndef force_successful_syscall_return /* * System call handlers that, upon successful completion, need to return a diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 830e6e16097d..9a5b3be2503a 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -228,4 +228,32 @@ static inline void tracehook_report_vfork_done(struct task_struct *child, ptrace_event(PT_TRACE_VFORK_DONE, PTRACE_EVENT_VFORK_DONE, pid); } +/** + * tracehook_prepare_release_task - task is being reaped, clean up tracing + * @task: task in %EXIT_DEAD state + * + * This is called in release_task() just before @task gets finally reaped + * and freed. This would be the ideal place to remove and clean up any + * tracing-related state for @task. + * + * Called with no locks held. + */ +static inline void tracehook_prepare_release_task(struct task_struct *task) +{ +} + +/** + * tracehook_finish_release_task - task is being reaped, clean up tracing + * @task: task in %EXIT_DEAD state + * + * This is called in release_task() when @task is being in the middle of + * being reaped. After this, there must be no tracing entanglements. + * + * Called with write_lock_irq(&tasklist_lock) held. + */ +static inline void tracehook_finish_release_task(struct task_struct *task) +{ + ptrace_release_task(task); +} + #endif /* */ -- cgit v1.2.2 From 0d094efeb1e98010c6b99923f1eb7e17bf1e3a74 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:49 -0700 Subject: tracehook: tracehook_tracer_task This adds the tracehook_tracer_task() hook to consolidate all forms of "Who is using ptrace on me?" logic. This is used for "TracerPid:" in /proc and for permission checks. We also clean up the selinux code the called an identical accessor. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 9a5b3be2503a..6468ca0fe69b 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -72,6 +72,24 @@ static inline int tracehook_unsafe_exec(struct task_struct *task) return unsafe; } +/** + * tracehook_tracer_task - return the task that is tracing the given task + * @tsk: task to consider + * + * Returns NULL if noone is tracing @task, or the &struct task_struct + * pointer to its tracer. + * + * Must called under rcu_read_lock(). The pointer returned might be kept + * live only by RCU. During exec, this may be called with task_lock() + * held on @task, still held from when tracehook_unsafe_exec() was called. + */ +static inline struct task_struct *tracehook_tracer_task(struct task_struct *tsk) +{ + if (task_ptrace(tsk) & PT_PTRACED) + return rcu_dereference(tsk->parent); + return NULL; +} + /** * tracehook_report_exec - a successful exec was completed * @fmt: &struct linux_binfmt that performed the exec -- cgit v1.2.2 From fa8e26ccd485216fc45c8c2dd1ec3b7ef1a0a2f8 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:50 -0700 Subject: tracehook: tracehook_expect_breakpoints This adds tracehook_expect_breakpoints() as a formal hook for the nommu code to use for its, "Is text-poking likely?" check at mmap time. This names the actual semantics the code means to test, and documents it. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 6468ca0fe69b..e113e09b0341 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -51,6 +51,21 @@ #include struct linux_binprm; +/** + * tracehook_expect_breakpoints - guess if task memory might be touched + * @task: current task, making a new mapping + * + * Return nonzero if @task is expected to want breakpoint insertion in + * its memory at some point. A zero return is no guarantee it won't + * be done, but this is a hint that it's known to be likely. + * + * May be called with @task->mm->mmap_sem held for writing. + */ +static inline int tracehook_expect_breakpoints(struct task_struct *task) +{ + return (task_ptrace(task) & PT_PTRACED) != 0; +} + /** * tracehook_unsafe_exec - check for exec declared unsafe due to tracing * @task: current task doing exec -- cgit v1.2.2 From c45aea27617d6a1e0aacddc3b0233f704222fcbd Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:50 -0700 Subject: tracehook: tracehook_signal_handler This defines tracehook_signal_handler() as a hook for the arch signal handling code to call. It gives ptrace the opportunity to stop for a pseudo-single-step trap immediately after signal handler setup is done. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index e113e09b0341..2d1426f8e33b 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -289,4 +289,27 @@ static inline void tracehook_finish_release_task(struct task_struct *task) ptrace_release_task(task); } +/** + * tracehook_signal_handler - signal handler setup is complete + * @sig: number of signal being delivered + * @info: siginfo_t of signal being delivered + * @ka: sigaction setting that chose the handler + * @regs: user register state + * @stepping: nonzero if debugger single-step or block-step in use + * + * Called by the arch code after a signal handler has been set up. + * Register and stack state reflects the user handler about to run. + * Signal mask changes have already been made. + * + * Called without locks, shortly before returning to user mode + * (or handling more signals). + */ +static inline void tracehook_signal_handler(int sig, siginfo_t *info, + const struct k_sigaction *ka, + struct pt_regs *regs, int stepping) +{ + if (stepping) + ptrace_notify(SIGTRAP); +} + #endif /* */ -- cgit v1.2.2 From 35de254dc60f91004b3b5ebb1fc7b2c3093d6032 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:51 -0700 Subject: tracehook: tracehook_consider_ignored_signal This defines tracehook_consider_ignored_signal() has a fine-grained hook for deciding to prevent the normal short-circuit of sending an ignored signal, as ptrace does. There is no change, only cleanup. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 2d1426f8e33b..8cffd34f88d5 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -312,4 +312,23 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info, ptrace_notify(SIGTRAP); } +/** + * tracehook_consider_ignored_signal - suppress short-circuit of ignored signal + * @task: task receiving the signal + * @sig: signal number being sent + * @handler: %SIG_IGN or %SIG_DFL + * + * Return zero iff tracing doesn't care to examine this ignored signal, + * so it can short-circuit normal delivery and never even get queued. + * Either @handler is %SIG_DFL and @sig's default is ignore, or it's %SIG_IGN. + * + * Called with @task->sighand->siglock held. + */ +static inline int tracehook_consider_ignored_signal(struct task_struct *task, + int sig, + void __user *handler) +{ + return (task_ptrace(task) & PT_PTRACED) != 0; +} + #endif /* */ -- cgit v1.2.2 From 445a91d2fe3667fb8fc251433645f686933cf56a Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:52 -0700 Subject: tracehook: tracehook_consider_fatal_signal This defines tracehook_consider_fatal_signal() has a fine-grained hook for deciding to skip the special cases for a fatal signal, as ptrace does. There is no change, only cleanup. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 8cffd34f88d5..8b4c15e208fe 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -331,4 +331,25 @@ static inline int tracehook_consider_ignored_signal(struct task_struct *task, return (task_ptrace(task) & PT_PTRACED) != 0; } +/** + * tracehook_consider_fatal_signal - suppress special handling of fatal signal + * @task: task receiving the signal + * @sig: signal number being sent + * @handler: %SIG_DFL or %SIG_IGN + * + * Return nonzero to prevent special handling of this termination signal. + * Normally @handler is %SIG_DFL. It can be %SIG_IGN if @sig is ignored, + * in which case force_sig() is about to reset it to %SIG_DFL. + * When this returns zero, this signal might cause a quick termination + * that does not give the debugger a chance to intercept the signal. + * + * Called with or without @task->sighand->siglock held. + */ +static inline int tracehook_consider_fatal_signal(struct task_struct *task, + int sig, + void __user *handler) +{ + return (task_ptrace(task) & PT_PTRACED) != 0; +} + #endif /* */ -- cgit v1.2.2 From 283d7559e7712f95a05331eb0a85394c6368101b Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:52 -0700 Subject: tracehook: syscall This adds standard tracehook.h inlines for arch code to call when TIF_SYSCALL_TRACE has been set. This replaces having each arch implement the ptrace guts for its syscall tracing support. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 70 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 8b4c15e208fe..3548694a24db 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -66,6 +66,76 @@ static inline int tracehook_expect_breakpoints(struct task_struct *task) return (task_ptrace(task) & PT_PTRACED) != 0; } +/* + * ptrace report for syscall entry and exit looks identical. + */ +static inline void ptrace_report_syscall(struct pt_regs *regs) +{ + int ptrace = task_ptrace(current); + + if (!(ptrace & PT_PTRACED)) + return; + + ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); + + /* + * this isn't the same as continuing with a signal, but it will do + * for normal use. strace only continues with a signal if the + * stopping signal is not SIGTRAP. -brl + */ + if (current->exit_code) { + send_sig(current->exit_code, current, 1); + current->exit_code = 0; + } +} + +/** + * tracehook_report_syscall_entry - task is about to attempt a system call + * @regs: user register state of current task + * + * This will be called if %TIF_SYSCALL_TRACE has been set, when the + * current task has just entered the kernel for a system call. + * Full user register state is available here. Changing the values + * in @regs can affect the system call number and arguments to be tried. + * It is safe to block here, preventing the system call from beginning. + * + * Returns zero normally, or nonzero if the calling arch code should abort + * the system call. That must prevent normal entry so no system call is + * made. If @task ever returns to user mode after this, its register state + * is unspecified, but should be something harmless like an %ENOSYS error + * return. + * + * Called without locks, just after entering kernel mode. + */ +static inline __must_check int tracehook_report_syscall_entry( + struct pt_regs *regs) +{ + ptrace_report_syscall(regs); + return 0; +} + +/** + * tracehook_report_syscall_exit - task has just finished a system call + * @regs: user register state of current task + * @step: nonzero if simulating single-step or block-step + * + * This will be called if %TIF_SYSCALL_TRACE has been set, when the + * current task has just finished an attempted system call. Full + * user register state is available here. It is safe to block here, + * preventing signals from being processed. + * + * If @step is nonzero, this report is also in lieu of the normal + * trap that would follow the system call instruction because + * user_enable_block_step() or user_enable_single_step() was used. + * In this case, %TIF_SYSCALL_TRACE might not be set. + * + * Called without locks, just before checking for pending signals. + */ +static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) +{ + ptrace_report_syscall(regs); +} + /** * tracehook_unsafe_exec - check for exec declared unsafe due to tracing * @task: current task doing exec -- cgit v1.2.2 From 7bcf6a2ca5f639b038c48711ebe6c4eca2036641 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:53 -0700 Subject: tracehook: get_signal_to_deliver This defines the tracehook_get_signal() hook to allow tracing code to slip in before normal signal dequeuing. This lays the groundwork for new tracing features that can inject synthetic signals outside the normal queue or control the disposition of delivered signals. The calling convention lets tracehook_get_signal() decide both exactly what will happen and what signal number to report in the handler/exit. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 3548694a24db..42a0d7b11959 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -422,4 +422,33 @@ static inline int tracehook_consider_fatal_signal(struct task_struct *task, return (task_ptrace(task) & PT_PTRACED) != 0; } +/** + * tracehook_get_signal - deliver synthetic signal to traced task + * @task: @current + * @regs: task_pt_regs(@current) + * @info: details of synthetic signal + * @return_ka: sigaction for synthetic signal + * + * Return zero to check for a real pending signal normally. + * Return -1 after releasing the siglock to repeat the check. + * Return a signal number to induce an artifical signal delivery, + * setting *@info and *@return_ka to specify its details and behavior. + * + * The @return_ka->sa_handler value controls the disposition of the + * signal, no matter the signal number. For %SIG_DFL, the return value + * is a representative signal to indicate the behavior (e.g. %SIGTERM + * for death, %SIGQUIT for core dump, %SIGSTOP for job control stop, + * %SIGTSTP for stop unless in an orphaned pgrp), but the signal number + * reported will be @info->si_signo instead. + * + * Called with @task->sighand->siglock held, before dequeuing pending signals. + */ +static inline int tracehook_get_signal(struct task_struct *task, + struct pt_regs *regs, + siginfo_t *info, + struct k_sigaction *return_ka) +{ + return 0; +} + #endif /* */ -- cgit v1.2.2 From fa00b80b3c41a845b3d56f866fb40a2e98754c51 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:54 -0700 Subject: tracehook: job control This defines the tracehook_notify_jctl() hook to formalize the ptrace effects on the job control notifications. There is no change, only cleanup. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 42a0d7b11959..6dc428dd2f38 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -451,4 +451,24 @@ static inline int tracehook_get_signal(struct task_struct *task, return 0; } +/** + * tracehook_notify_jctl - report about job control stop/continue + * @notify: nonzero if this is the last thread in the group to stop + * @why: %CLD_STOPPED or %CLD_CONTINUED + * + * This is called when we might call do_notify_parent_cldstop(). + * It's called when about to stop for job control; we are already in + * %TASK_STOPPED state, about to call schedule(). It's also called when + * a delayed %CLD_STOPPED or %CLD_CONTINUED report is ready to be made. + * + * Return nonzero to generate a %SIGCHLD with @why, which is + * normal if @notify is nonzero. + * + * Called with no locks held. + */ +static inline int tracehook_notify_jctl(int notify, int why) +{ + return notify || (current->ptrace & PT_PTRACED); +} + #endif /* */ -- cgit v1.2.2 From 2b2a1ff64afbadac842bbc58c5166962cf4f7664 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:54 -0700 Subject: tracehook: death This moves the ptrace logic in task death (exit_notify) into tracehook.h inlines. Some code is rearranged slightly to make things nicer. There is no change, only cleanup. There is one hook called with the tasklist_lock write-locked, as ptrace needs. There is also a new hook called after exit_state changes and without locks. This is a better place for tracing work to be in the future, since it doesn't delay the whole system with locking. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- include/linux/tracehook.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index adb8077dc463..a95d84d0da95 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1796,7 +1796,7 @@ extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_ extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern int kill_proc_info(int, struct siginfo *, pid_t); -extern void do_notify_parent(struct task_struct *, int); +extern int do_notify_parent(struct task_struct *, int); extern void force_sig(int, struct task_struct *); extern void force_sig_specific(int, struct task_struct *); extern int send_sig(int, struct task_struct *, int); diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 6dc428dd2f38..4c50e1b57349 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -471,4 +471,56 @@ static inline int tracehook_notify_jctl(int notify, int why) return notify || (current->ptrace & PT_PTRACED); } +/** + * tracehook_notify_death - task is dead, ready to notify parent + * @task: @current task now exiting + * @death_cookie: value to pass to tracehook_report_death() + * @group_dead: nonzero if this was the last thread in the group to die + * + * Return the signal number to send our parent with do_notify_parent(), or + * zero to send no signal and leave a zombie, or -1 to self-reap right now. + * + * Called with write_lock_irq(&tasklist_lock) held. + */ +static inline int tracehook_notify_death(struct task_struct *task, + void **death_cookie, int group_dead) +{ + if (task->exit_signal == -1) + return task->ptrace ? SIGCHLD : -1; + + /* + * If something other than our normal parent is ptracing us, then + * send it a SIGCHLD instead of honoring exit_signal. exit_signal + * only has special meaning to our real parent. + */ + if (thread_group_empty(task) && !ptrace_reparented(task)) + return task->exit_signal; + + return task->ptrace ? SIGCHLD : 0; +} + +/** + * tracehook_report_death - task is dead and ready to be reaped + * @task: @current task now exiting + * @signal: signal number sent to parent, or 0 or -1 + * @death_cookie: value passed back from tracehook_notify_death() + * @group_dead: nonzero if this was the last thread in the group to die + * + * Thread has just become a zombie or is about to self-reap. If positive, + * @signal is the signal number just sent to the parent (usually %SIGCHLD). + * If @signal is -1, this thread will self-reap. If @signal is 0, this is + * a delayed_group_leader() zombie. The @death_cookie was passed back by + * tracehook_notify_death(). + * + * If normal reaping is not inhibited, @task->exit_state might be changing + * in parallel. + * + * Called without locks. + */ +static inline void tracehook_report_death(struct task_struct *task, + int signal, void *death_cookie, + int group_dead) +{ +} + #endif /* */ -- cgit v1.2.2 From b787f7ba677840da16a2228c16571ce8a1fcb799 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:55 -0700 Subject: tracehook: force signal_pending() This defines a new hook tracehook_force_sigpending() that lets tracing code decide to force TIF_SIGPENDING on in recalc_sigpending(). This is not used yet, so it compiles away to nothing for now. It lays the groundwork for new tracing code that can interrupt a task synthetically without actually sending a signal. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 4c50e1b57349..43bc51b6bd33 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -422,6 +422,20 @@ static inline int tracehook_consider_fatal_signal(struct task_struct *task, return (task_ptrace(task) & PT_PTRACED) != 0; } +/** + * tracehook_force_sigpending - let tracing force signal_pending(current) on + * + * Called when recomputing our signal_pending() flag. Return nonzero + * to force the signal_pending() flag on, so that tracehook_get_signal() + * will be called before the next return to user mode. + * + * Called with @current->sighand->siglock held. + */ +static inline int tracehook_force_sigpending(void) +{ + return 0; +} + /** * tracehook_get_signal - deliver synthetic signal to traced task * @task: @current -- cgit v1.2.2 From 64b1208d5b0ef8859fd52ea7ae286a3eb994669b Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:56 -0700 Subject: tracehook: TIF_NOTIFY_RESUME This adds tracehook.h inlines to enable a new arch feature in support of user debugging/tracing. This is not used yet, but it lays the groundwork for a debugger to be able to wrangle a task that's possibly running, without interrupting its syscalls in progress. Each arch should define TIF_NOTIFY_RESUME, and in their entry.S code treat it much like TIF_SIGPENDING. That is, it causes you to take the slow path when returning to user mode, where you get the full user-mode state accessible as for signal handling or ptrace. The arch code should check TIF_NOTIFY_RESUME after handling TIF_SIGPENDING. When it's set, clear it and then call tracehook_notify_resume(). In future, tracing code will call set_notify_resume() when it wants to get a callback in tracehook_notify_resume(). Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 43bc51b6bd33..32867ab86c70 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -537,4 +537,38 @@ static inline void tracehook_report_death(struct task_struct *task, { } +#ifdef TIF_NOTIFY_RESUME +/** + * set_notify_resume - cause tracehook_notify_resume() to be called + * @task: task that will call tracehook_notify_resume() + * + * Calling this arranges that @task will call tracehook_notify_resume() + * before returning to user mode. If it's already running in user mode, + * it will enter the kernel and call tracehook_notify_resume() soon. + * If it's blocked, it will not be woken. + */ +static inline void set_notify_resume(struct task_struct *task) +{ + if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) + kick_process(task); +} + +/** + * tracehook_notify_resume - report when about to return to user mode + * @regs: user-mode registers of @current task + * + * This is called when %TIF_NOTIFY_RESUME has been set. Now we are + * about to return to user mode, and the user state in @regs can be + * inspected or adjusted. The caller in arch code has cleared + * %TIF_NOTIFY_RESUME before the call. If the flag gets set again + * asynchronously, this will be called again before we return to + * user mode. + * + * Called without locks. + */ +static inline void tracehook_notify_resume(struct pt_regs *regs) +{ +} +#endif /* TIF_NOTIFY_RESUME */ + #endif /* */ -- cgit v1.2.2 From 828c365cc8b8d38c346fccb19fa80d28f2240831 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:57 -0700 Subject: tracehook: asm/syscall.h This adds asm-generic/syscall.h, which documents what a real asm-ARCH/syscall.h file should define. This is not used yet, but will provide all the machine-dependent details of examining a user system call about to begin, in progress, or just ended. Each arch should add an asm-ARCH/syscall.h that defines all the entry points documented in asm-generic/syscall.h, as short inlines if possible. This lets us write new tracing code that understands user system call registers, without any new arch-specific work. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 32867ab86c70..589f429619c9 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -103,7 +103,8 @@ static inline void ptrace_report_syscall(struct pt_regs *regs) * the system call. That must prevent normal entry so no system call is * made. If @task ever returns to user mode after this, its register state * is unspecified, but should be something harmless like an %ENOSYS error - * return. + * return. It should preserve enough information so that syscall_rollback() + * can work (see asm-generic/syscall.h). * * Called without locks, just after entering kernel mode. */ -- cgit v1.2.2 From 85ba2d862e521375a8ee01526c5c46b1f24bb4af Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:58 -0700 Subject: tracehook: wait_task_inactive This extends wait_task_inactive() with a new argument so it can be used in a "soft" mode where it will check for the task changing state unexpectedly and back off. There is no change to existing callers. This lays the groundwork to allow robust, noninvasive tracing that can try to sample a blocked thread but back off safely if it wakes up. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a95d84d0da95..f59318a0099b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1882,9 +1882,13 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP -extern void wait_task_inactive(struct task_struct * p); +extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else -#define wait_task_inactive(p) do { } while (0) +static inline unsigned long wait_task_inactive(struct task_struct *p, + long match_state) +{ + return 1; +} #endif #define next_task(p) list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks) -- cgit v1.2.2 From bbc698636ed48b6fcd323964e0f847a6a796325d Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:59 -0700 Subject: task_current_syscall This adds the new function task_current_syscall() on machines where the asm/syscall.h interface is supported (CONFIG_HAVE_ARCH_TRACEHOOK). It's exported for modules to use in the future. This function safely samples the state of a blocked thread to collect what system call it is blocked in, and the six system call argument registers. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index ed69c03692d9..fd31756e1a00 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -314,6 +314,10 @@ static inline void user_enable_block_step(struct task_struct *task) #define arch_ptrace_stop(code, info) do { } while (0) #endif +extern int task_current_syscall(struct task_struct *target, long *callno, + unsigned long args[6], unsigned int maxargs, + unsigned long *sp, unsigned long *pc); + #endif #endif -- cgit v1.2.2 From 9d8fddfb17aaee4ffc5e3d0560620d0fa8b50a42 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 19:46:23 -0700 Subject: mm/allocpercpu.c: make 4 functions static This patch makes the following needlessly global functions static: - percpu_depopulate() - __percpu_depopulate_mask() - percpu_populate() - __percpu_populate_mask() Signed-off-by: Adrian Bunk Acked-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu.h | 29 ----------------------------- 1 file changed, 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 4cdd393e71e1..fac3337547eb 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -74,11 +74,6 @@ struct percpu_data { (__typeof__(ptr))__p->ptrs[(cpu)]; \ }) -extern void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu); -extern void percpu_depopulate(void *__pdata, int cpu); -extern int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp, - cpumask_t *mask); -extern void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask); extern void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask); extern void percpu_free(void *__pdata); @@ -86,26 +81,6 @@ extern void percpu_free(void *__pdata); #define percpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) -static inline void percpu_depopulate(void *__pdata, int cpu) -{ -} - -static inline void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask) -{ -} - -static inline void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, - int cpu) -{ - return percpu_ptr(__pdata, cpu); -} - -static inline int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp, - cpumask_t *mask) -{ - return 0; -} - static __always_inline void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask) { return kzalloc(size, gfp); @@ -118,10 +93,6 @@ static inline void percpu_free(void *__pdata) #endif /* CONFIG_SMP */ -#define percpu_populate_mask(__pdata, size, gfp, mask) \ - __percpu_populate_mask((__pdata), (size), (gfp), &(mask)) -#define percpu_depopulate_mask(__pdata, mask) \ - __percpu_depopulate_mask((__pdata), &(mask)) #define percpu_alloc_mask(size, gfp, mask) \ __percpu_alloc_mask((size), (gfp), &(mask)) -- cgit v1.2.2 From 15f59adae001766a2c7f7fe4f196387bb04bcff5 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 19:46:23 -0700 Subject: make mm/memory.c:print_bad_pte() static This patch makes the needlessly global print_bad_pte() static. Signed-off-by: Adrian Bunk Reviewed-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f3fd70d6029f..6e695eaab4ce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -810,7 +810,6 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void * int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, int write, int force, struct page **pages, struct vm_area_struct **vmas); -void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned long offset); -- cgit v1.2.2 From 7c363b8c6536f26934172d3c46f0bbec01a97c61 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 19:46:24 -0700 Subject: mm/swapfile.c: make code static This patch makes the following needlessly global code static: - swap_lock - nr_swapfiles - struct swap_list Signed-off-by: Adrian Bunk Reviewed-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 0b3377650c85..de40f169a4e4 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -237,7 +237,6 @@ extern struct page *swapin_readahead(swp_entry_t, gfp_t, /* linux/mm/swapfile.c */ extern long total_swap_pages; -extern unsigned int nr_swapfiles; extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(void); extern swp_entry_t get_swap_page_of_type(int); @@ -254,8 +253,6 @@ extern int can_share_swap_page(struct page *); extern int remove_exclusive_swap_page(struct page *); struct backing_dev_info; -extern spinlock_t swap_lock; - /* linux/mm/thrash.c */ extern struct mm_struct * swap_token_mm; extern void grab_swap_token(void); -- cgit v1.2.2 From 9580d85f9cdb076c4bfb467bc6c0d3c5e499957a Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 19:46:25 -0700 Subject: drivers/char/rtc.c: make 2 functions static The following functions can now become static: - rtc_interrupt() - rtc_get_rtc_time() Signed-off-by: Adrian Bunk Acked-by: Bernhard Walle Acked-by: Paul Gortmaker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index b01fe004cb5e..91f597ad6acc 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -225,8 +225,6 @@ typedef struct rtc_task { int rtc_register(rtc_task_t *task); int rtc_unregister(rtc_task_t *task); int rtc_control(rtc_task_t *t, unsigned int cmd, unsigned long arg); -void rtc_get_rtc_time(struct rtc_time *rtc_tm); -irqreturn_t rtc_interrupt(int irq, void *dev_id); #endif /* __KERNEL__ */ -- cgit v1.2.2 From a9906a19193db69ad0158f289f839edf8aaf103f Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Sat, 26 Jul 2008 14:41:26 -0700 Subject: tracehook: comment fixes This fixes some typos and errors in comments. No code changes. Signed-off-by: Roland McGrath --- include/linux/tracehook.h | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 589f429619c9..b1875582c1a1 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -244,7 +244,7 @@ static inline int tracehook_prepare_clone(unsigned clone_flags) * tracehook_finish_clone - new child created and being attached * @child: new child task * @clone_flags: %CLONE_* flags from clone/fork/vfork system call - * @trace: return value from tracehook_clone_prepare() + * @trace: return value from tracehook_prepare_clone() * * This is called immediately after adding @child to its parent's children list. * The @trace value is that returned by tracehook_prepare_clone(). @@ -259,19 +259,20 @@ static inline void tracehook_finish_clone(struct task_struct *child, /** * tracehook_report_clone - in parent, new child is about to start running - * @trace: return value from tracehook_clone_prepare() + * @trace: return value from tracehook_prepare_clone() * @regs: parent's user register state * @clone_flags: flags from parent's system call * @pid: new child's PID in the parent's namespace * @child: new child task * - * Called after a child is set up, but before it has been started running. - * The @trace value is that returned by tracehook_clone_prepare(). - * This is not a good place to block, because the child has not started yet. - * Suspend the child here if desired, and block in tracehook_clone_complete(). - * This must prevent the child from self-reaping if tracehook_clone_complete() - * uses the @child pointer; otherwise it might have died and been released by - * the time tracehook_report_clone_complete() is called. + * Called after a child is set up, but before it has been started + * running. @trace is the value returned by tracehook_prepare_clone(). + * This is not a good place to block, because the child has not started + * yet. Suspend the child here if desired, and then block in + * tracehook_report_clone_complete(). This must prevent the child from + * self-reaping if tracehook_report_clone_complete() uses the @child + * pointer; otherwise it might have died and been released by the time + * tracehook_report_report_clone_complete() is called. * * Called with no locks held, but the child cannot run until this returns. */ @@ -290,7 +291,7 @@ static inline void tracehook_report_clone(int trace, struct pt_regs *regs, /** * tracehook_report_clone_complete - new child is running - * @trace: return value from tracehook_clone_prepare() + * @trace: return value from tracehook_prepare_clone() * @regs: parent's user register state * @clone_flags: flags from parent's system call * @pid: new child's PID in the parent's namespace @@ -347,7 +348,7 @@ static inline void tracehook_prepare_release_task(struct task_struct *task) } /** - * tracehook_finish_release_task - task is being reaped, clean up tracing + * tracehook_finish_release_task - final tracing clean-up * @task: task in %EXIT_DEAD state * * This is called in release_task() when @task is being in the middle of -- cgit v1.2.2 From 6edd8ee60ac9b974bd6ec3b1bcb2aab02762fa8c Mon Sep 17 00:00:00 2001 From: Haavard Skinnemoen Date: Thu, 24 Jul 2008 14:18:57 +0200 Subject: mmc: Export internal host state through debugfs When CONFIG_DEBUG_FS is set, create a few files under /sys/kernel/debug containing information about an mmc host's internal state. Currently, just a single file is created, "ios", which contains information about the current operating parameters for the bus (clock speed, bus width, etc.) Host drivers can add additional files and directories under the host's root directory by passing the debugfs_root field in struct mmc_host as the 'parent' parameter to debugfs_create_*. Signed-off-by: Haavard Skinnemoen Signed-off-by: Pierre Ossman --- include/linux/mmc/host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 10a2080086ca..9c288c909878 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -157,6 +157,8 @@ struct mmc_host { struct led_trigger *led; /* activity led */ #endif + struct dentry *debugfs_root; + unsigned long private[0] ____cacheline_aligned; }; -- cgit v1.2.2 From f4b7f927b531ca350cfc4ca1bdc3377dac7f9a32 Mon Sep 17 00:00:00 2001 From: Haavard Skinnemoen Date: Thu, 24 Jul 2008 14:18:58 +0200 Subject: mmc: Add per-card debugfs support For each card successfully added to the bus, create a subdirectory under the host's debugfs root with information about the card. At the moment, only a single file is added to the card directory for all cards: "state". It reflects the "state" field in struct mmc_card, indicating whether the card is present, readonly, etc. For MMC and SD cards (not SDIO), another file is added: "status". Reading this file will ask the card about its current status and return it. This can be useful if the card just refuses to respond to any commands, which might indicate that the card state is not what the MMC core thinks it is (due to a missing stop command, for example.) Signed-off-by: Haavard Skinnemoen Signed-off-by: Pierre Ossman --- include/linux/mmc/card.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 0d508ac17d64..ee6e822d5994 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -111,6 +111,8 @@ struct mmc_card { unsigned num_info; /* number of info strings */ const char **info; /* info strings */ struct sdio_func_tuple *tuples; /* unknown common tuples */ + + struct dentry *debugfs_root; }; #define mmc_card_mmc(c) ((c)->type == MMC_TYPE_MMC) -- cgit v1.2.2 From 04578dd330f1ec6bc9c4233833bee0d0ca73ff09 Mon Sep 17 00:00:00 2001 From: Karsten Keil Date: Sat, 26 Jul 2008 18:52:34 +0200 Subject: Define AF_ISDN and PF_ISDN Define the address and protocol family value for mISDN. Signed-off-by: Karsten Keil --- include/linux/socket.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 950af631e7fb..dc5086fe7736 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -189,7 +189,8 @@ struct ucred { #define AF_BLUETOOTH 31 /* Bluetooth sockets */ #define AF_IUCV 32 /* IUCV sockets */ #define AF_RXRPC 33 /* RxRPC sockets */ -#define AF_MAX 34 /* For now.. */ +#define AF_ISDN 34 /* mISDN sockets */ +#define AF_MAX 35 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -225,6 +226,7 @@ struct ucred { #define PF_BLUETOOTH AF_BLUETOOTH #define PF_IUCV AF_IUCV #define PF_RXRPC AF_RXRPC +#define PF_ISDN AF_ISDN #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ -- cgit v1.2.2 From 1b2b03f8e514e4f68e293846ba511a948b80243c Mon Sep 17 00:00:00 2001 From: Karsten Keil Date: Sun, 27 Jul 2008 01:54:58 +0200 Subject: Add mISDN core files Add mISDN core files Signed-off-by: Karsten Keil --- include/linux/mISDNhw.h | 193 +++++++++++++++++++ include/linux/mISDNif.h | 487 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 680 insertions(+) create mode 100644 include/linux/mISDNhw.h create mode 100644 include/linux/mISDNif.h (limited to 'include/linux') diff --git a/include/linux/mISDNhw.h b/include/linux/mISDNhw.h new file mode 100644 index 000000000000..e794dfb87504 --- /dev/null +++ b/include/linux/mISDNhw.h @@ -0,0 +1,193 @@ +/* + * + * Author Karsten Keil + * + * Basic declarations for the mISDN HW channels + * + * Copyright 2008 by Karsten Keil + * + * 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. + * + */ + +#ifndef MISDNHW_H +#define MISDNHW_H +#include +#include + +/* + * HW DEBUG 0xHHHHGGGG + * H - hardware driver specific bits + * G - for all drivers + */ + +#define DEBUG_HW 0x00000001 +#define DEBUG_HW_OPEN 0x00000002 +#define DEBUG_HW_DCHANNEL 0x00000100 +#define DEBUG_HW_DFIFO 0x00000200 +#define DEBUG_HW_BCHANNEL 0x00001000 +#define DEBUG_HW_BFIFO 0x00002000 + +#define MAX_DFRAME_LEN_L1 300 +#define MAX_MON_FRAME 32 +#define MAX_LOG_SPACE 2048 +#define MISDN_COPY_SIZE 32 + +/* channel->Flags bit field */ +#define FLG_TX_BUSY 0 /* tx_buf in use */ +#define FLG_TX_NEXT 1 /* next_skb in use */ +#define FLG_L1_BUSY 2 /* L1 is permanent busy */ +#define FLG_L2_ACTIVATED 3 /* activated from L2 */ +#define FLG_OPEN 5 /* channel is in use */ +#define FLG_ACTIVE 6 /* channel is activated */ +#define FLG_BUSY_TIMER 7 +/* channel type */ +#define FLG_DCHANNEL 8 /* channel is D-channel */ +#define FLG_BCHANNEL 9 /* channel is B-channel */ +#define FLG_ECHANNEL 10 /* channel is E-channel */ +#define FLG_TRANSPARENT 12 /* channel use transparent data */ +#define FLG_HDLC 13 /* channel use hdlc data */ +#define FLG_L2DATA 14 /* channel use L2 DATA primitivs */ +#define FLG_ORIGIN 15 /* channel is on origin site */ +/* channel specific stuff */ +/* arcofi specific */ +#define FLG_ARCOFI_TIMER 16 +#define FLG_ARCOFI_ERROR 17 +/* isar specific */ +#define FLG_INITIALIZED 16 +#define FLG_DLEETX 17 +#define FLG_LASTDLE 18 +#define FLG_FIRST 19 +#define FLG_LASTDATA 20 +#define FLG_NMD_DATA 21 +#define FLG_FTI_RUN 22 +#define FLG_LL_OK 23 +#define FLG_LL_CONN 24 +#define FLG_DTMFSEND 25 + +/* workq events */ +#define FLG_RECVQUEUE 30 +#define FLG_PHCHANGE 31 + +#define schedule_event(s, ev) do { \ + test_and_set_bit(ev, &((s)->Flags)); \ + schedule_work(&((s)->workq)); \ + } while (0) + +struct dchannel { + struct mISDNdevice dev; + u_long Flags; + struct work_struct workq; + void (*phfunc) (struct dchannel *); + u_int state; + void *l1; + /* HW access */ + u_char (*read_reg) (void *, u_char); + void (*write_reg) (void *, u_char, u_char); + void (*read_fifo) (void *, u_char *, int); + void (*write_fifo) (void *, u_char *, int); + void *hw; + int slot; /* multiport card channel slot */ + struct timer_list timer; + /* receive data */ + struct sk_buff *rx_skb; + int maxlen; + /* send data */ + struct sk_buff_head squeue; + struct sk_buff_head rqueue; + struct sk_buff *tx_skb; + int tx_idx; + int debug; + /* statistics */ + int err_crc; + int err_tx; + int err_rx; +}; + +typedef int (dchannel_l1callback)(struct dchannel *, u_int); +extern int create_l1(struct dchannel *, dchannel_l1callback *); + +/* private L1 commands */ +#define INFO0 0x8002 +#define INFO1 0x8102 +#define INFO2 0x8202 +#define INFO3_P8 0x8302 +#define INFO3_P10 0x8402 +#define INFO4_P8 0x8502 +#define INFO4_P10 0x8602 +#define LOSTFRAMING 0x8702 +#define ANYSIGNAL 0x8802 +#define HW_POWERDOWN 0x8902 +#define HW_RESET_REQ 0x8a02 +#define HW_POWERUP_REQ 0x8b02 +#define HW_DEACT_REQ 0x8c02 +#define HW_ACTIVATE_REQ 0x8e02 +#define HW_D_NOBLOCKED 0x8f02 +#define HW_RESET_IND 0x9002 +#define HW_POWERUP_IND 0x9102 +#define HW_DEACT_IND 0x9202 +#define HW_ACTIVATE_IND 0x9302 +#define HW_DEACT_CNF 0x9402 +#define HW_TESTLOOP 0x9502 +#define HW_TESTRX_RAW 0x9602 +#define HW_TESTRX_HDLC 0x9702 +#define HW_TESTRX_OFF 0x9802 + +struct layer1; +extern int l1_event(struct layer1 *, u_int); + + +struct bchannel { + struct mISDNchannel ch; + int nr; + u_long Flags; + struct work_struct workq; + u_int state; + /* HW access */ + u_char (*read_reg) (void *, u_char); + void (*write_reg) (void *, u_char, u_char); + void (*read_fifo) (void *, u_char *, int); + void (*write_fifo) (void *, u_char *, int); + void *hw; + int slot; /* multiport card channel slot */ + struct timer_list timer; + /* receive data */ + struct sk_buff *rx_skb; + int maxlen; + /* send data */ + struct sk_buff *next_skb; + struct sk_buff *tx_skb; + struct sk_buff_head rqueue; + int rcount; + int tx_idx; + int debug; + /* statistics */ + int err_crc; + int err_tx; + int err_rx; +}; + +extern int mISDN_initdchannel(struct dchannel *, int, void *); +extern int mISDN_initbchannel(struct bchannel *, int); +extern int mISDN_freedchannel(struct dchannel *); +extern int mISDN_freebchannel(struct bchannel *); +extern void queue_ch_frame(struct mISDNchannel *, u_int, + int, struct sk_buff *); +extern int dchannel_senddata(struct dchannel *, struct sk_buff *); +extern int bchannel_senddata(struct bchannel *, struct sk_buff *); +extern void recv_Dchannel(struct dchannel *); +extern void recv_Bchannel(struct bchannel *); +extern void recv_Dchannel_skb(struct dchannel *, struct sk_buff *); +extern void recv_Bchannel_skb(struct bchannel *, struct sk_buff *); +extern void confirm_Bsend(struct bchannel *bch); +extern int get_next_bframe(struct bchannel *); +extern int get_next_dframe(struct dchannel *); + +#endif diff --git a/include/linux/mISDNif.h b/include/linux/mISDNif.h new file mode 100644 index 000000000000..5c948f337817 --- /dev/null +++ b/include/linux/mISDNif.h @@ -0,0 +1,487 @@ +/* + * + * Author Karsten Keil + * + * Copyright 2008 by Karsten Keil + * + * This code is free software; you can redistribute it and/or modify + * it under the terms of the GNU LESSER GENERAL PUBLIC LICENSE + * version 2.1 as published by the Free Software Foundation. + * + * This code 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 LESSER GENERAL PUBLIC LICENSE for more details. + * + */ + +#ifndef mISDNIF_H +#define mISDNIF_H + +#include +#include +#include +#include + +/* + * ABI Version 32 bit + * + * <8 bit> Major version + * - changed if any interface become backwards incompatible + * + * <8 bit> Minor version + * - changed if any interface is extended but backwards compatible + * + * <16 bit> Release number + * - should be incremented on every checkin + */ +#define MISDN_MAJOR_VERSION 1 +#define MISDN_MINOR_VERSION 0 +#define MISDN_RELEASE 18 + +/* primitives for information exchange + * generell format + * <16 bit 0 > + * <8 bit command> + * BIT 8 = 1 LAYER private + * BIT 7 = 1 answer + * BIT 6 = 1 DATA + * <8 bit target layer mask> + * + * Layer = 00 is reserved for general commands + Layer = 01 L2 -> HW + Layer = 02 HW -> L2 + Layer = 04 L3 -> L2 + Layer = 08 L2 -> L3 + * Layer = FF is reserved for broadcast commands + */ + +#define MISDN_CMDMASK 0xff00 +#define MISDN_LAYERMASK 0x00ff + +/* generell commands */ +#define OPEN_CHANNEL 0x0100 +#define CLOSE_CHANNEL 0x0200 +#define CONTROL_CHANNEL 0x0300 +#define CHECK_DATA 0x0400 + +/* layer 2 -> layer 1 */ +#define PH_ACTIVATE_REQ 0x0101 +#define PH_DEACTIVATE_REQ 0x0201 +#define PH_DATA_REQ 0x2001 +#define MPH_ACTIVATE_REQ 0x0501 +#define MPH_DEACTIVATE_REQ 0x0601 +#define MPH_INFORMATION_REQ 0x0701 +#define PH_CONTROL_REQ 0x0801 + +/* layer 1 -> layer 2 */ +#define PH_ACTIVATE_IND 0x0102 +#define PH_ACTIVATE_CNF 0x4102 +#define PH_DEACTIVATE_IND 0x0202 +#define PH_DEACTIVATE_CNF 0x4202 +#define PH_DATA_IND 0x2002 +#define MPH_ACTIVATE_IND 0x0502 +#define MPH_DEACTIVATE_IND 0x0602 +#define MPH_INFORMATION_IND 0x0702 +#define PH_DATA_CNF 0x6002 +#define PH_CONTROL_IND 0x0802 +#define PH_CONTROL_CNF 0x4802 + +/* layer 3 -> layer 2 */ +#define DL_ESTABLISH_REQ 0x1004 +#define DL_RELEASE_REQ 0x1104 +#define DL_DATA_REQ 0x3004 +#define DL_UNITDATA_REQ 0x3104 +#define DL_INFORMATION_REQ 0x0004 + +/* layer 2 -> layer 3 */ +#define DL_ESTABLISH_IND 0x1008 +#define DL_ESTABLISH_CNF 0x5008 +#define DL_RELEASE_IND 0x1108 +#define DL_RELEASE_CNF 0x5108 +#define DL_DATA_IND 0x3008 +#define DL_UNITDATA_IND 0x3108 +#define DL_INFORMATION_IND 0x0008 + +/* intern layer 2 managment */ +#define MDL_ASSIGN_REQ 0x1804 +#define MDL_ASSIGN_IND 0x1904 +#define MDL_REMOVE_REQ 0x1A04 +#define MDL_REMOVE_IND 0x1B04 +#define MDL_STATUS_UP_IND 0x1C04 +#define MDL_STATUS_DOWN_IND 0x1D04 +#define MDL_STATUS_UI_IND 0x1E04 +#define MDL_ERROR_IND 0x1F04 +#define MDL_ERROR_RSP 0x5F04 + +/* DL_INFORMATION_IND types */ +#define DL_INFO_L2_CONNECT 0x0001 +#define DL_INFO_L2_REMOVED 0x0002 + +/* PH_CONTROL types */ +/* TOUCH TONE IS 0x20XX XX "0"..."9", "A","B","C","D","*","#" */ +#define DTMF_TONE_VAL 0x2000 +#define DTMF_TONE_MASK 0x007F +#define DTMF_TONE_START 0x2100 +#define DTMF_TONE_STOP 0x2200 +#define DTMF_HFC_COEF 0x4000 +#define DSP_CONF_JOIN 0x2403 +#define DSP_CONF_SPLIT 0x2404 +#define DSP_RECEIVE_OFF 0x2405 +#define DSP_RECEIVE_ON 0x2406 +#define DSP_ECHO_ON 0x2407 +#define DSP_ECHO_OFF 0x2408 +#define DSP_MIX_ON 0x2409 +#define DSP_MIX_OFF 0x240a +#define DSP_DELAY 0x240b +#define DSP_JITTER 0x240c +#define DSP_TXDATA_ON 0x240d +#define DSP_TXDATA_OFF 0x240e +#define DSP_TX_DEJITTER 0x240f +#define DSP_TX_DEJ_OFF 0x2410 +#define DSP_TONE_PATT_ON 0x2411 +#define DSP_TONE_PATT_OFF 0x2412 +#define DSP_VOL_CHANGE_TX 0x2413 +#define DSP_VOL_CHANGE_RX 0x2414 +#define DSP_BF_ENABLE_KEY 0x2415 +#define DSP_BF_DISABLE 0x2416 +#define DSP_BF_ACCEPT 0x2416 +#define DSP_BF_REJECT 0x2417 +#define DSP_PIPELINE_CFG 0x2418 +#define HFC_VOL_CHANGE_TX 0x2601 +#define HFC_VOL_CHANGE_RX 0x2602 +#define HFC_SPL_LOOP_ON 0x2603 +#define HFC_SPL_LOOP_OFF 0x2604 + +/* DSP_TONE_PATT_ON parameter */ +#define TONE_OFF 0x0000 +#define TONE_GERMAN_DIALTONE 0x0001 +#define TONE_GERMAN_OLDDIALTONE 0x0002 +#define TONE_AMERICAN_DIALTONE 0x0003 +#define TONE_GERMAN_DIALPBX 0x0004 +#define TONE_GERMAN_OLDDIALPBX 0x0005 +#define TONE_AMERICAN_DIALPBX 0x0006 +#define TONE_GERMAN_RINGING 0x0007 +#define TONE_GERMAN_OLDRINGING 0x0008 +#define TONE_AMERICAN_RINGPBX 0x000b +#define TONE_GERMAN_RINGPBX 0x000c +#define TONE_GERMAN_OLDRINGPBX 0x000d +#define TONE_AMERICAN_RINGING 0x000e +#define TONE_GERMAN_BUSY 0x000f +#define TONE_GERMAN_OLDBUSY 0x0010 +#define TONE_AMERICAN_BUSY 0x0011 +#define TONE_GERMAN_HANGUP 0x0012 +#define TONE_GERMAN_OLDHANGUP 0x0013 +#define TONE_AMERICAN_HANGUP 0x0014 +#define TONE_SPECIAL_INFO 0x0015 +#define TONE_GERMAN_GASSENBESETZT 0x0016 +#define TONE_GERMAN_AUFSCHALTTON 0x0016 + +/* MPH_INFORMATION_IND */ +#define L1_SIGNAL_LOS_OFF 0x0010 +#define L1_SIGNAL_LOS_ON 0x0011 +#define L1_SIGNAL_AIS_OFF 0x0012 +#define L1_SIGNAL_AIS_ON 0x0013 +#define L1_SIGNAL_RDI_OFF 0x0014 +#define L1_SIGNAL_RDI_ON 0x0015 +#define L1_SIGNAL_SLIP_RX 0x0020 +#define L1_SIGNAL_SLIP_TX 0x0021 + +/* + * protocol ids + * D channel 1-31 + * B channel 33 - 63 + */ + +#define ISDN_P_NONE 0 +#define ISDN_P_BASE 0 +#define ISDN_P_TE_S0 0x01 +#define ISDN_P_NT_S0 0x02 +#define ISDN_P_TE_E1 0x03 +#define ISDN_P_NT_E1 0x04 +#define ISDN_P_LAPD_TE 0x10 +#define ISDN_P_LAPD_NT 0x11 + +#define ISDN_P_B_MASK 0x1f +#define ISDN_P_B_START 0x20 + +#define ISDN_P_B_RAW 0x21 +#define ISDN_P_B_HDLC 0x22 +#define ISDN_P_B_X75SLP 0x23 +#define ISDN_P_B_L2DTMF 0x24 +#define ISDN_P_B_L2DSP 0x25 +#define ISDN_P_B_L2DSPHDLC 0x26 + +#define OPTION_L2_PMX 1 +#define OPTION_L2_PTP 2 +#define OPTION_L2_FIXEDTEI 3 +#define OPTION_L2_CLEANUP 4 + +/* should be in sync with linux/kobject.h:KOBJ_NAME_LEN */ +#define MISDN_MAX_IDLEN 20 + +struct mISDNhead { + unsigned int prim; + unsigned int id; +} __attribute__((packed)); + +#define MISDN_HEADER_LEN sizeof(struct mISDNhead) +#define MAX_DATA_SIZE 2048 +#define MAX_DATA_MEM (MAX_DATA_SIZE + MISDN_HEADER_LEN) +#define MAX_DFRAME_LEN 260 + +#define MISDN_ID_ADDR_MASK 0xFFFF +#define MISDN_ID_TEI_MASK 0xFF00 +#define MISDN_ID_SAPI_MASK 0x00FF +#define MISDN_ID_TEI_ANY 0x7F00 + +#define MISDN_ID_ANY 0xFFFF +#define MISDN_ID_NONE 0xFFFE + +#define GROUP_TEI 127 +#define TEI_SAPI 63 +#define CTRL_SAPI 0 + +#define MISDN_CHMAP_SIZE 4 + +#define SOL_MISDN 0 + +struct sockaddr_mISDN { + sa_family_t family; + unsigned char dev; + unsigned char channel; + unsigned char sapi; + unsigned char tei; +}; + +/* timer device ioctl */ +#define IMADDTIMER _IOR('I', 64, int) +#define IMDELTIMER _IOR('I', 65, int) +/* socket ioctls */ +#define IMGETVERSION _IOR('I', 66, int) +#define IMGETCOUNT _IOR('I', 67, int) +#define IMGETDEVINFO _IOR('I', 68, int) +#define IMCTRLREQ _IOR('I', 69, int) +#define IMCLEAR_L2 _IOR('I', 70, int) + +struct mISDNversion { + unsigned char major; + unsigned char minor; + unsigned short release; +}; + +struct mISDN_devinfo { + u_int id; + u_int Dprotocols; + u_int Bprotocols; + u_int protocol; + u_long channelmap[MISDN_CHMAP_SIZE]; + u_int nrbchan; + char name[MISDN_MAX_IDLEN]; +}; + +/* CONTROL_CHANNEL parameters */ +#define MISDN_CTRL_GETOP 0x0000 +#define MISDN_CTRL_LOOP 0x0001 +#define MISDN_CTRL_CONNECT 0x0002 +#define MISDN_CTRL_DISCONNECT 0x0004 +#define MISDN_CTRL_PCMCONNECT 0x0010 +#define MISDN_CTRL_PCMDISCONNECT 0x0020 +#define MISDN_CTRL_SETPEER 0x0040 +#define MISDN_CTRL_UNSETPEER 0x0080 +#define MISDN_CTRL_RX_OFF 0x0100 +#define MISDN_CTRL_HW_FEATURES_OP 0x2000 +#define MISDN_CTRL_HW_FEATURES 0x2001 +#define MISDN_CTRL_HFC_OP 0x4000 +#define MISDN_CTRL_HFC_PCM_CONN 0x4001 +#define MISDN_CTRL_HFC_PCM_DISC 0x4002 +#define MISDN_CTRL_HFC_CONF_JOIN 0x4003 +#define MISDN_CTRL_HFC_CONF_SPLIT 0x4004 +#define MISDN_CTRL_HFC_RECEIVE_OFF 0x4005 +#define MISDN_CTRL_HFC_RECEIVE_ON 0x4006 +#define MISDN_CTRL_HFC_ECHOCAN_ON 0x4007 +#define MISDN_CTRL_HFC_ECHOCAN_OFF 0x4008 + + +/* socket options */ +#define MISDN_TIME_STAMP 0x0001 + +struct mISDN_ctrl_req { + int op; + int channel; + int p1; + int p2; +}; + +/* muxer options */ +#define MISDN_OPT_ALL 1 +#define MISDN_OPT_TEIMGR 2 + +#ifdef __KERNEL__ +#include +#include +#include +#include +#include + +#define DEBUG_CORE 0x000000ff +#define DEBUG_CORE_FUNC 0x00000002 +#define DEBUG_SOCKET 0x00000004 +#define DEBUG_MANAGER 0x00000008 +#define DEBUG_SEND_ERR 0x00000010 +#define DEBUG_MSG_THREAD 0x00000020 +#define DEBUG_QUEUE_FUNC 0x00000040 +#define DEBUG_L1 0x0000ff00 +#define DEBUG_L1_FSM 0x00000200 +#define DEBUG_L2 0x00ff0000 +#define DEBUG_L2_FSM 0x00020000 +#define DEBUG_L2_CTRL 0x00040000 +#define DEBUG_L2_RECV 0x00080000 +#define DEBUG_L2_TEI 0x00100000 +#define DEBUG_L2_TEIFSM 0x00200000 +#define DEBUG_TIMER 0x01000000 + +#define mISDN_HEAD_P(s) ((struct mISDNhead *)&s->cb[0]) +#define mISDN_HEAD_PRIM(s) (((struct mISDNhead *)&s->cb[0])->prim) +#define mISDN_HEAD_ID(s) (((struct mISDNhead *)&s->cb[0])->id) + +/* socket states */ +#define MISDN_OPEN 1 +#define MISDN_BOUND 2 +#define MISDN_CLOSED 3 + +struct mISDNchannel; +struct mISDNdevice; +struct mISDNstack; + +struct channel_req { + u_int protocol; + struct sockaddr_mISDN adr; + struct mISDNchannel *ch; +}; + +typedef int (ctrl_func_t)(struct mISDNchannel *, u_int, void *); +typedef int (send_func_t)(struct mISDNchannel *, struct sk_buff *); +typedef int (create_func_t)(struct channel_req *); + +struct Bprotocol { + struct list_head list; + char *name; + u_int Bprotocols; + create_func_t *create; +}; + +struct mISDNchannel { + struct list_head list; + u_int protocol; + u_int nr; + u_long opt; + u_int addr; + struct mISDNstack *st; + struct mISDNchannel *peer; + send_func_t *send; + send_func_t *recv; + ctrl_func_t *ctrl; +}; + +struct mISDN_sock_list { + struct hlist_head head; + rwlock_t lock; +}; + +struct mISDN_sock { + struct sock sk; + struct mISDNchannel ch; + u_int cmask; + struct mISDNdevice *dev; +}; + + + +struct mISDNdevice { + struct mISDNchannel D; + u_int id; + char name[MISDN_MAX_IDLEN]; + u_int Dprotocols; + u_int Bprotocols; + u_int nrbchan; + u_long channelmap[MISDN_CHMAP_SIZE]; + struct list_head bchannels; + struct mISDNchannel *teimgr; + struct device dev; +}; + +struct mISDNstack { + u_long status; + struct mISDNdevice *dev; + struct task_struct *thread; + struct completion *notify; + wait_queue_head_t workq; + struct sk_buff_head msgq; + struct list_head layer2; + struct mISDNchannel *layer1; + struct mISDNchannel own; + struct mutex lmutex; /* protect lists */ + struct mISDN_sock_list l1sock; +#ifdef MISDN_MSG_STATS + u_int msg_cnt; + u_int sleep_cnt; + u_int stopped_cnt; +#endif +}; + +/* global alloc/queue dunctions */ + +static inline struct sk_buff * +mI_alloc_skb(unsigned int len, gfp_t gfp_mask) +{ + struct sk_buff *skb; + + skb = alloc_skb(len + MISDN_HEADER_LEN, gfp_mask); + if (likely(skb)) + skb_reserve(skb, MISDN_HEADER_LEN); + return skb; +} + +static inline struct sk_buff * +_alloc_mISDN_skb(u_int prim, u_int id, u_int len, void *dp, gfp_t gfp_mask) +{ + struct sk_buff *skb = mI_alloc_skb(len, gfp_mask); + struct mISDNhead *hh; + + if (!skb) + return NULL; + if (len) + memcpy(skb_put(skb, len), dp, len); + hh = mISDN_HEAD_P(skb); + hh->prim = prim; + hh->id = id; + return skb; +} + +static inline void +_queue_data(struct mISDNchannel *ch, u_int prim, + u_int id, u_int len, void *dp, gfp_t gfp_mask) +{ + struct sk_buff *skb; + + if (!ch->peer) + return; + skb = _alloc_mISDN_skb(prim, id, len, dp, gfp_mask); + if (!skb) + return; + if (ch->recv(ch->peer, skb)) + dev_kfree_skb(skb); +} + +/* global register/unregister functions */ + +extern int mISDN_register_device(struct mISDNdevice *, char *name); +extern void mISDN_unregister_device(struct mISDNdevice *); +extern int mISDN_register_Bprotocol(struct Bprotocol *); +extern void mISDN_unregister_Bprotocol(struct Bprotocol *); + +extern void set_channel_address(struct mISDNchannel *, u_int, u_int); + +#endif /* __KERNEL__ */ +#endif /* mISDNIF_H */ -- cgit v1.2.2 From 960366cf8dbb3359afaca30cf7fdbf69a6d6dda7 Mon Sep 17 00:00:00 2001 From: Karsten Keil Date: Sun, 27 Jul 2008 01:56:38 +0200 Subject: Add mISDN DSP Enable support for digital audio processing capability. This module may be used for special applications that require cross connecting of bchannels, conferencing, dtmf decoding echo cancelation, tone generation, and Blowfish encryption and decryption. It may use hardware features if available. Signed-off-by: Karsten Keil --- include/linux/mISDNdsp.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 include/linux/mISDNdsp.h (limited to 'include/linux') diff --git a/include/linux/mISDNdsp.h b/include/linux/mISDNdsp.h new file mode 100644 index 000000000000..6b71d2dce508 --- /dev/null +++ b/include/linux/mISDNdsp.h @@ -0,0 +1,37 @@ +#ifndef __mISDNdsp_H__ +#define __mISDNdsp_H__ + +struct mISDN_dsp_element_arg { + char *name; + char *def; + char *desc; +}; + +struct mISDN_dsp_element { + char *name; + void *(*new)(const char *arg); + void (*free)(void *p); + void (*process_tx)(void *p, unsigned char *data, int len); + void (*process_rx)(void *p, unsigned char *data, int len); + int num_args; + struct mISDN_dsp_element_arg + *args; +}; + +extern int mISDN_dsp_element_register(struct mISDN_dsp_element *elem); +extern void mISDN_dsp_element_unregister(struct mISDN_dsp_element *elem); + +struct dsp_features { + int hfc_id; /* unique id to identify the chip (or -1) */ + int hfc_dtmf; /* set if HFCmulti card supports dtmf */ + int hfc_loops; /* set if card supports tone loops */ + int hfc_echocanhw; /* set if card supports echocancelation*/ + int pcm_id; /* unique id to identify the pcm bus (or -1) */ + int pcm_slots; /* number of slots on the pcm bus */ + int pcm_banks; /* number of IO banks of pcm bus */ + int unclocked; /* data is not clocked (has jitter/loss) */ + int unordered; /* data is unordered (packets have index) */ +}; + +#endif + -- cgit v1.2.2 From af69fb3a8ffa37e986db00ed93099dc44babeef4 Mon Sep 17 00:00:00 2001 From: Karsten Keil Date: Sun, 27 Jul 2008 02:00:43 +0200 Subject: Add mISDN HFC multiport driver Enable support for cards with Cologne Chip AG's HFC multiport chip. Signed-off-by: Karsten Keil --- include/linux/pci_ids.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index c3b1761aba26..ffe479ba0779 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1832,7 +1832,13 @@ #define PCI_DEVICE_ID_MOXA_C320 0x3200 #define PCI_VENDOR_ID_CCD 0x1397 +#define PCI_DEVICE_ID_CCD_HFC4S 0x08B4 +#define PCI_SUBDEVICE_ID_CCD_PMX2S 0x1234 +#define PCI_DEVICE_ID_CCD_HFC8S 0x16B8 #define PCI_DEVICE_ID_CCD_2BD0 0x2bd0 +#define PCI_DEVICE_ID_CCD_HFCE1 0x30B1 +#define PCI_SUBDEVICE_ID_CCD_SPD4S 0x3136 +#define PCI_SUBDEVICE_ID_CCD_SPDE1 0x3137 #define PCI_DEVICE_ID_CCD_B000 0xb000 #define PCI_DEVICE_ID_CCD_B006 0xb006 #define PCI_DEVICE_ID_CCD_B007 0xb007 @@ -1842,8 +1848,32 @@ #define PCI_DEVICE_ID_CCD_B00B 0xb00b #define PCI_DEVICE_ID_CCD_B00C 0xb00c #define PCI_DEVICE_ID_CCD_B100 0xb100 +#define PCI_SUBDEVICE_ID_CCD_IOB4ST 0xB520 +#define PCI_SUBDEVICE_ID_CCD_IOB8STR 0xB521 +#define PCI_SUBDEVICE_ID_CCD_IOB8ST 0xB522 +#define PCI_SUBDEVICE_ID_CCD_IOB1E1 0xB523 +#define PCI_SUBDEVICE_ID_CCD_SWYX4S 0xB540 +#define PCI_SUBDEVICE_ID_CCD_JH4S20 0xB550 +#define PCI_SUBDEVICE_ID_CCD_IOB8ST_1 0xB552 +#define PCI_SUBDEVICE_ID_CCD_BN4S 0xB560 +#define PCI_SUBDEVICE_ID_CCD_BN8S 0xB562 +#define PCI_SUBDEVICE_ID_CCD_BNE1 0xB563 +#define PCI_SUBDEVICE_ID_CCD_BNE1D 0xB564 +#define PCI_SUBDEVICE_ID_CCD_BNE1DP 0xB565 +#define PCI_SUBDEVICE_ID_CCD_BN2S 0xB566 +#define PCI_SUBDEVICE_ID_CCD_BN1SM 0xB567 +#define PCI_SUBDEVICE_ID_CCD_BN4SM 0xB568 +#define PCI_SUBDEVICE_ID_CCD_BN2SM 0xB569 +#define PCI_SUBDEVICE_ID_CCD_BNE1M 0xB56A +#define PCI_SUBDEVICE_ID_CCD_BN8SP 0xB56B +#define PCI_SUBDEVICE_ID_CCD_HFC4S 0xB620 +#define PCI_SUBDEVICE_ID_CCD_HFC8S 0xB622 #define PCI_DEVICE_ID_CCD_B700 0xb700 #define PCI_DEVICE_ID_CCD_B701 0xb701 +#define PCI_SUBDEVICE_ID_CCD_HFCE1 0xC523 +#define PCI_SUBDEVICE_ID_CCD_OV2S 0xE884 +#define PCI_SUBDEVICE_ID_CCD_OV4S 0xE888 +#define PCI_SUBDEVICE_ID_CCD_OV8S 0xE998 #define PCI_VENDOR_ID_EXAR 0x13a8 #define PCI_DEVICE_ID_EXAR_XR17C152 0x0152 @@ -2523,6 +2553,9 @@ #define PCI_VENDOR_ID_3COM_2 0xa727 +#define PCI_VENDOR_ID_DIGIUM 0xd161 +#define PCI_DEVICE_ID_DIGIUM_HFC4S 0xb410 + #define PCI_SUBVENDOR_ID_EXSYS 0xd84d #define PCI_SUBDEVICE_ID_EXSYS_4014 0x4014 #define PCI_SUBDEVICE_ID_EXSYS_4055 0x4055 -- cgit v1.2.2 From 93bc4e89c260d91576840c4881d1066d84ccd422 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Sat, 26 Jul 2008 17:49:33 -0700 Subject: netfilter: fix double-free and use-after free As suggested by Patrick McHardy, introduce a __krealloc() that doesn't free the original buffer to fix a double-free and use-after-free bug introduced by me in netfilter that uses RCU. Reported-by: Patrick McHardy Signed-off-by: Pekka Enberg Tested-by: Dieter Ries Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/slab.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 9aa90a6f20e0..be6f1d40b66a 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -96,6 +96,7 @@ int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr); /* * Common kmalloc functions provided by all allocators */ +void * __must_check __krealloc(const void *, size_t, gfp_t); void * __must_check krealloc(const void *, size_t, gfp_t); void kfree(const void *); size_t ksize(const void *); -- cgit v1.2.2 From d2d9648ec6858e19d16a0b16da62534e85888653 Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Tue, 1 Jul 2008 14:16:09 +0200 Subject: [PATCH] reuse xxx_fifo_fops for xxx_pipe_fops Merge fifo and pipe file_operations. Signed-off-by: Denys Vlasenko 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 53d2edb709b3..7721a2ac9c0e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1696,9 +1696,9 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern int is_bad_inode(struct inode *); -extern const struct file_operations read_fifo_fops; -extern const struct file_operations write_fifo_fops; -extern const struct file_operations rdwr_fifo_fops; +extern const struct file_operations read_pipefifo_fops; +extern const struct file_operations write_pipefifo_fops; +extern const struct file_operations rdwr_pipefifo_fops; extern int fs_may_remount_ro(struct super_block *); -- cgit v1.2.2 From 734550921e9b7ab924a43aa3d0bd4239dac4fbf1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 14 Jul 2008 21:22:20 -0400 Subject: [PATCH] beginning of sysctl cleanup - ctl_table_set New object: set of sysctls [currently - root and per-net-ns]. Contains: pointer to parent set, list of tables and "should I see this set?" method (->is_seen(set)). Current lists of tables are subsumed by that; net-ns contains such a beast. ->lookup() for ctl_table_root returns pointer to ctl_table_set instead of that to ->list of that ctl_table_set. [folded compile fixes by rdd for configs without sysctl] Signed-off-by: Al Viro --- include/linux/sysctl.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 24141b4d1a11..c1e0cf408af9 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -947,6 +947,16 @@ struct ctl_table; struct nsproxy; struct ctl_table_root; +struct ctl_table_set { + struct list_head list; + struct ctl_table_set *parent; + int (*is_seen)(struct ctl_table_set *); +}; + +extern void setup_sysctl_set(struct ctl_table_set *p, + struct ctl_table_set *parent, + int (*is_seen)(struct ctl_table_set *)); + extern struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev); extern struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces, struct ctl_table_header *prev); @@ -1049,8 +1059,8 @@ struct ctl_table struct ctl_table_root { struct list_head root_list; - struct list_head header_list; - struct list_head *(*lookup)(struct ctl_table_root *root, + struct ctl_table_set default_set; + struct ctl_table_set *(*lookup)(struct ctl_table_root *root, struct nsproxy *namespaces); int (*permissions)(struct ctl_table_root *root, struct nsproxy *namespaces, struct ctl_table *table); @@ -1066,6 +1076,7 @@ struct ctl_table_header struct completion *unregistering; struct ctl_table *ctl_table_arg; struct ctl_table_root *root; + struct ctl_table_set *set; }; /* struct ctl_path describes where in the hierarchy a table is added */ -- cgit v1.2.2 From f7e6ced4061da509f737541ca4dbd44d83a6e82f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 15 Jul 2008 01:44:23 -0400 Subject: [PATCH] allow delayed freeing of ctl_table_header Refcount the sucker; instead of freeing it by the end of unregistration just drop the refcount and free only when it hits zero. Make sure that we _always_ make ->unregistering non-NULL in start_unregistering(). That allows anybody to get a reference to such puppy, preventing its freeing and reuse. It does *not* block unregistration. Anybody who holds such a reference can * try to grab a "use" reference (ctl_head_grab()); that will succeeds if and only if it hadn't entered unregistration yet. If it succeeds, we can use it in all normal ways until we release the "use" reference (with ctl_head_finish()). Note that this relies on having ->unregistering become non-NULL in all cases when one starts to unregister the sucker. * keep pointers to ctl_table entries; they *can* be freed if the entire thing is unregistered. However, if ctl_head_grab() succeeds, we know that unregistration had not happened (and will not happen until ctl_head_finish()) and such pointers can be used safely. IOW, now we can have inodes under /proc/sys keep references to ctl_table entries, protecting them with references to ctl_table_header and grabbing the latter for the duration of operations that require access to ctl_table. That won't cause deadlocks, since unregistration will not be stopped by mere keeping a reference to ctl_table_header. Signed-off-by: Al Viro --- include/linux/sysctl.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index c1e0cf408af9..956264d09ba0 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -957,6 +957,11 @@ extern void setup_sysctl_set(struct ctl_table_set *p, struct ctl_table_set *parent, int (*is_seen)(struct ctl_table_set *)); +struct ctl_table_header; + +extern void sysctl_head_get(struct ctl_table_header *); +extern void sysctl_head_put(struct ctl_table_header *); +extern struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *); extern struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev); extern struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces, struct ctl_table_header *prev); @@ -1073,6 +1078,7 @@ struct ctl_table_header struct ctl_table *ctl_table; struct list_head ctl_entry; int used; + int count; struct completion *unregistering; struct ctl_table *ctl_table_arg; struct ctl_table_root *root; -- cgit v1.2.2 From ae7edecc9b8810770a8e5cb9a466ea4bdcfa8401 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 15 Jul 2008 06:33:31 -0400 Subject: [PATCH] sysctl: keep track of tree relationships In a sense, that's the heart of the series. It's based on the following property of the trees we are actually asked to add: they can be split into stem that is already covered by registered trees and crown that is entirely new. IOW, if a/b and a/c/d are introduced by our tree, then a/c is also introduced by it. That allows to associate tree and table entry with each node in the union; while directory nodes might be covered by many trees, only one will cover the node by its crown. And that will allow much saner logics for /proc/sys in the next patches. This patch introduces the data structures needed to keep track of that. When adding a sysctl table, we find a "parent" one. Which is to say, find the deepest node on its stem that already is present in one of the tables from our table set or its ancestor sets. That table will be our parent and that node in it - attachment point. Add our table to list anchored in parent, have it refer the parent and contents of attachment point. Also remember where its crown lives. Signed-off-by: Al Viro --- include/linux/sysctl.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 956264d09ba0..3f6599aeb0db 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -1083,6 +1083,9 @@ struct ctl_table_header struct ctl_table *ctl_table_arg; struct ctl_table_root *root; struct ctl_table_set *set; + struct ctl_table *attached_by; + struct ctl_table *attached_to; + struct ctl_table_header *parent; }; /* struct ctl_path describes where in the hierarchy a table is added */ -- cgit v1.2.2 From 9043476f726802f4b00c96d0c4f418dde48d1304 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 15 Jul 2008 08:54:06 -0400 Subject: [PATCH] sanitize proc_sysctl * keep references to ctl_table_head and ctl_table in /proc/sys inodes * grab the former during operations, use the latter for access to entry if that succeeds * have ->d_compare() check if table should be seen for one who does lookup; that allows us to avoid flipping inodes - if we have the same name resolve to different things, we'll just keep several dentries and ->d_compare() will reject the wrong ones. * have ->lookup() and ->readdir() scan the table of our inode first, then walk all ctl_table_header and scan ->attached_by for those that are attached to our directory. * implement ->getattr(). * get rid of insane amounts of tree-walking * get rid of the need to know dentry in ->permission() and of the contortions induced by that. Signed-off-by: Al Viro --- include/linux/proc_fs.h | 5 +++++ include/linux/sysctl.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index f560d1705afe..fb61850d1cfc 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -282,11 +282,16 @@ union proc_op { struct task_struct *task); }; +struct ctl_table_header; +struct ctl_table; + struct proc_inode { struct pid *pid; int fd; union proc_op op; struct proc_dir_entry *pde; + struct ctl_table_header *sysctl; + struct ctl_table *sysctl_entry; struct inode vfs_inode; }; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 3f6599aeb0db..d0437f36921f 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -961,6 +961,7 @@ struct ctl_table_header; extern void sysctl_head_get(struct ctl_table_header *); extern void sysctl_head_put(struct ctl_table_header *); +extern int sysctl_is_seen(struct ctl_table_header *); extern struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *); extern struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev); extern struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces, -- cgit v1.2.2 From e6305c43eda10ebfd2ad9e35d6e172ccc7bb3695 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 15 Jul 2008 21:03:57 -0400 Subject: [PATCH] sanitize ->permission() prototype * kill nameidata * argument; map the 3 bits in ->flags anybody cares about to new MAY_... ones and pass with the mask. * kill redundant gfs2_iop_permission() * sanitize ecryptfs_permission() * fix remaining places where ->permission() instances might barf on new MAY_... found in mask. The obvious next target in that direction is permission(9) folded fix for nfs_permission() breakage from Miklos Szeredi Signed-off-by: Al Viro --- include/linux/coda_linux.h | 2 +- include/linux/fs.h | 5 ++++- include/linux/nfs_fs.h | 2 +- include/linux/reiserfs_xattr.h | 2 +- include/linux/shmem_fs.h | 2 +- 5 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coda_linux.h b/include/linux/coda_linux.h index 31b75311e2ca..dcc228aa335a 100644 --- a/include/linux/coda_linux.h +++ b/include/linux/coda_linux.h @@ -37,7 +37,7 @@ extern const struct file_operations coda_ioctl_operations; /* operations shared over more than one file */ int coda_open(struct inode *i, struct file *f); int coda_release(struct inode *i, struct file *f); -int coda_permission(struct inode *inode, int mask, struct nameidata *nd); +int coda_permission(struct inode *inode, int mask); int coda_revalidate_inode(struct dentry *); int coda_getattr(struct vfsmount *, struct dentry *, struct kstat *); int coda_setattr(struct dentry *, struct iattr *); diff --git a/include/linux/fs.h b/include/linux/fs.h index 7721a2ac9c0e..6c923c9b79bc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -60,6 +60,9 @@ extern int dir_notify_enable; #define MAY_WRITE 2 #define MAY_READ 4 #define MAY_APPEND 8 +#define MAY_ACCESS 16 +#define MAY_CHDIR 32 +#define MAY_OPEN 64 #define FMODE_READ 1 #define FMODE_WRITE 2 @@ -1272,7 +1275,7 @@ struct inode_operations { void * (*follow_link) (struct dentry *, struct nameidata *); void (*put_link) (struct dentry *, struct nameidata *, void *); void (*truncate) (struct inode *); - int (*permission) (struct inode *, int, struct nameidata *); + int (*permission) (struct inode *, int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 29d261918734..f08f9ca602af 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -332,7 +332,7 @@ extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *); -extern int nfs_permission(struct inode *, int, struct nameidata *); +extern int nfs_permission(struct inode *, int); extern int nfs_open(struct inode *, struct file *); extern int nfs_release(struct inode *, struct file *); extern int nfs_attribute_timeout(struct inode *inode); diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 66a96814d614..af135ae895db 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -55,7 +55,7 @@ int reiserfs_removexattr(struct dentry *dentry, const char *name); int reiserfs_delete_xattrs(struct inode *inode); int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs); int reiserfs_xattr_init(struct super_block *sb, int mount_flags); -int reiserfs_permission(struct inode *inode, int mask, struct nameidata *nd); +int reiserfs_permission(struct inode *inode, int mask); int reiserfs_xattr_del(struct inode *, const char *); int reiserfs_xattr_get(const struct inode *, const char *, void *, size_t); diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index f2d12d5a21b8..fd83f2584b15 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -43,7 +43,7 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) } #ifdef CONFIG_TMPFS_POSIX_ACL -int shmem_permission(struct inode *, int, struct nameidata *); +int shmem_permission(struct inode *, int); int shmem_acl_init(struct inode *, struct inode *); void shmem_acl_destroy_inode(struct inode *); -- cgit v1.2.2 From 2f1936b87783a3a56c9441b27b9ba7a747f11e8e Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 24 Jun 2008 16:50:14 +0200 Subject: [patch 3/5] vfs: change remove_suid() to file_remove_suid() All calls to remove_suid() are made with a file pointer, because (similarly to file_update_time) it is called when the file is written. Clean up callers by passing in a file instead of a dentry. Signed-off-by: Miklos Szeredi --- 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 6c923c9b79bc..1a3546e69f9e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1834,7 +1834,7 @@ extern void clear_inode(struct inode *); extern void destroy_inode(struct inode *); extern struct inode *new_inode(struct super_block *); extern int should_remove_suid(struct dentry *); -extern int remove_suid(struct dentry *); +extern int file_remove_suid(struct file *); extern void __insert_inode_hash(struct inode *, unsigned long hashval); extern void remove_inode_hash(struct inode *); -- cgit v1.2.2 From db2e747b14991a4c6a5c98b0e5f552a193237c03 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 24 Jun 2008 16:50:16 +0200 Subject: [patch 5/5] vfs: remove mode parameter from vfs_symlink() Remove the unused mode parameter from vfs_symlink and callers. Thanks to Tetsuo Handa for noticing. CC: Tetsuo Handa Signed-off-by: Miklos Szeredi --- 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 1a3546e69f9e..25998e803fc2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1139,7 +1139,7 @@ extern int vfs_permission(struct nameidata *, int); extern int vfs_create(struct inode *, struct dentry *, int, struct nameidata *); extern int vfs_mkdir(struct inode *, struct dentry *, int); extern int vfs_mknod(struct inode *, struct dentry *, int, dev_t); -extern int vfs_symlink(struct inode *, struct dentry *, const char *, int); +extern int vfs_symlink(struct inode *, struct dentry *, const char *); extern int vfs_link(struct dentry *, struct inode *, struct dentry *); extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *); -- cgit v1.2.2 From 8bb79224b87aab92071e94d46e70bd160d89bf34 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 16 Jul 2008 09:51:03 -0400 Subject: [PATCH] permission checks for chdir need special treatment only on the last step ... so we ought to pass MAY_CHDIR to vfs_permission() instead of having it triggered on every step of preceding pathname resolution. LOOKUP_CHDIR is killed by that. Signed-off-by: Al Viro --- include/linux/namei.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 24d88e98a626..3cf62d26d493 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -55,7 +55,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_OPEN (0x0100) #define LOOKUP_CREATE (0x0200) #define LOOKUP_ACCESS (0x0400) -#define LOOKUP_CHDIR (0x0800) extern int __user_walk(const char __user *, unsigned, struct nameidata *); extern int __user_walk_fd(int dfd, const char __user *, unsigned, struct nameidata *); -- cgit v1.2.2 From 7f2da1e7d0330395e5e9e350b879b98a1ea495df Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 10 May 2008 20:44:54 -0400 Subject: [PATCH] kill altroot long overdue... Signed-off-by: Al Viro --- include/linux/fs_struct.h | 3 +-- include/linux/namei.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 282f54219129..9e5a06e78d02 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -7,7 +7,7 @@ struct fs_struct { atomic_t count; rwlock_t lock; int umask; - struct path root, pwd, altroot; + struct path root, pwd; }; #define INIT_FS { \ @@ -19,7 +19,6 @@ struct fs_struct { extern struct kmem_cache *fs_cachep; extern void exit_fs(struct task_struct *); -extern void set_fs_altroot(void); extern void set_fs_root(struct fs_struct *, struct path *); extern void set_fs_pwd(struct fs_struct *, struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); diff --git a/include/linux/namei.h b/include/linux/namei.h index 3cf62d26d493..768773d57857 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -47,7 +47,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_DIRECTORY 2 #define LOOKUP_CONTINUE 4 #define LOOKUP_PARENT 16 -#define LOOKUP_NOALT 32 #define LOOKUP_REVAL 64 /* * Intent data -- cgit v1.2.2 From a110343f0d6d41f68b7cf8c00b57a3172c67f816 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Jul 2008 09:19:08 -0400 Subject: [PATCH] fix MAY_CHDIR/MAY_ACCESS/LOOKUP_ACCESS mess * MAY_CHDIR is redundant - it's an equivalent of MAY_ACCESS * MAY_ACCESS on fuse should affect only the last step of pathname resolution * fchdir() and chroot() should pass MAY_ACCESS, for the same reason why chdir() needs that. * now that we pass MAY_ACCESS explicitly in all cases, LOOKUP_ACCESS can be removed; it has no business being in nameidata. Signed-off-by: Al Viro --- include/linux/fs.h | 3 +-- include/linux/namei.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 25998e803fc2..d8721e818b45 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -61,8 +61,7 @@ extern int dir_notify_enable; #define MAY_READ 4 #define MAY_APPEND 8 #define MAY_ACCESS 16 -#define MAY_CHDIR 32 -#define MAY_OPEN 64 +#define MAY_OPEN 32 #define FMODE_READ 1 #define FMODE_WRITE 2 diff --git a/include/linux/namei.h b/include/linux/namei.h index 768773d57857..60e35a02f6cb 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -53,7 +53,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; */ #define LOOKUP_OPEN (0x0100) #define LOOKUP_CREATE (0x0200) -#define LOOKUP_ACCESS (0x0400) extern int __user_walk(const char __user *, unsigned, struct nameidata *); extern int __user_walk_fd(int dfd, const char __user *, unsigned, struct nameidata *); -- cgit v1.2.2 From b77b0646ef4efe31a7449bb3d9360fd00f95433d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Jul 2008 09:37:02 -0400 Subject: [PATCH] pass MAY_OPEN to vfs_permission() explicitly ... and get rid of the last "let's deduce mask from nameidata->flags" bit. Signed-off-by: Al Viro --- include/linux/security.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index f0e9adb22ac2..fd96e7f8a6f9 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1362,7 +1362,7 @@ struct security_operations { struct inode *new_dir, struct dentry *new_dentry); int (*inode_readlink) (struct dentry *dentry); int (*inode_follow_link) (struct dentry *dentry, struct nameidata *nd); - int (*inode_permission) (struct inode *inode, int mask, struct nameidata *nd); + int (*inode_permission) (struct inode *inode, int mask); int (*inode_setattr) (struct dentry *dentry, struct iattr *attr); int (*inode_getattr) (struct vfsmount *mnt, struct dentry *dentry); void (*inode_delete) (struct inode *inode); @@ -1628,7 +1628,7 @@ int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); int security_inode_readlink(struct dentry *dentry); int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd); -int security_inode_permission(struct inode *inode, int mask, struct nameidata *nd); +int security_inode_permission(struct inode *inode, int mask); int security_inode_setattr(struct dentry *dentry, struct iattr *attr); int security_inode_getattr(struct vfsmount *mnt, struct dentry *dentry); void security_inode_delete(struct inode *inode); @@ -2021,8 +2021,7 @@ static inline int security_inode_follow_link(struct dentry *dentry, return 0; } -static inline int security_inode_permission(struct inode *inode, int mask, - struct nameidata *nd) +static inline int security_inode_permission(struct inode *inode, int mask) { return 0; } -- cgit v1.2.2 From 88b387824fdaecb6ba0f471acf0aadf7d24739fd Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 21 Jul 2008 18:06:36 +0800 Subject: [PATCH] vfs: use kstrdup() and check failing allocation - use kstrdup() instead of kmalloc() + memcpy() - return NULL if allocating ->mnt_devname failed - mnt_devname should be const Signed-off-by: Li Zefan Acked-by: Cyrill Gorcunov Signed-off-by: Al Viro --- include/linux/mount.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index 4374d1adeb4b..b5efaa2132ab 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -47,7 +47,7 @@ struct vfsmount { struct list_head mnt_child; /* and going through their mnt_child */ int mnt_flags; /* 4 bytes hole on 64bits arches */ - char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ + const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ -- cgit v1.2.2 From 9767d74957450da6365c363d69e3d02d605d7375 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 1 Jul 2008 15:01:26 +0200 Subject: [patch 1/4] vfs: utimes: move owner check into inode_change_ok() Add a new ia_valid flag: ATTR_TIMES_SET, to handle the UTIMES_OMIT/UTIMES_NOW and UTIMES_NOW/UTIMES_OMIT cases. In these cases neither ATTR_MTIME_SET nor ATTR_ATIME_SET is in the flags, yet the POSIX draft specifies that permission checking is performed the same way as if one or both of the times was explicitly set to a timestamp. See the path "vfs: utimensat(): fix error checking for {UTIME_NOW,UTIME_OMIT} case" by Michael Kerrisk for the patch introducing this behavior. This is a cleanup, as well as allowing filesystems (NFS/fuse/...) to perform their own permission checking instead of the default. CC: Ulrich Drepper CC: Michael Kerrisk Signed-off-by: Miklos Szeredi Signed-off-by: Al Viro --- include/linux/fs.h | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d8721e818b45..527b9e482f99 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -320,22 +320,23 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * Attribute flags. These should be or-ed together to figure out what * has been changed! */ -#define ATTR_MODE 1 -#define ATTR_UID 2 -#define ATTR_GID 4 -#define ATTR_SIZE 8 -#define ATTR_ATIME 16 -#define ATTR_MTIME 32 -#define ATTR_CTIME 64 -#define ATTR_ATIME_SET 128 -#define ATTR_MTIME_SET 256 -#define ATTR_FORCE 512 /* Not a change, but a change it */ -#define ATTR_ATTR_FLAG 1024 -#define ATTR_KILL_SUID 2048 -#define ATTR_KILL_SGID 4096 -#define ATTR_FILE 8192 -#define ATTR_KILL_PRIV 16384 -#define ATTR_OPEN 32768 /* Truncating from open(O_TRUNC) */ +#define ATTR_MODE (1 << 0) +#define ATTR_UID (1 << 1) +#define ATTR_GID (1 << 2) +#define ATTR_SIZE (1 << 3) +#define ATTR_ATIME (1 << 4) +#define ATTR_MTIME (1 << 5) +#define ATTR_CTIME (1 << 6) +#define ATTR_ATIME_SET (1 << 7) +#define ATTR_MTIME_SET (1 << 8) +#define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ +#define ATTR_ATTR_FLAG (1 << 10) +#define ATTR_KILL_SUID (1 << 11) +#define ATTR_KILL_SGID (1 << 12) +#define ATTR_FILE (1 << 13) +#define ATTR_KILL_PRIV (1 << 14) +#define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ +#define ATTR_TIMES_SET (1 << 16) /* * This is the Inode Attributes structure, used for notify_change(). It -- cgit v1.2.2 From f419a2e3b64def707e1384ee38abb77f99af5f6d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 22 Jul 2008 00:07:17 -0400 Subject: [PATCH] kill nameidata passing to permission(), rename to inode_permission() Incidentally, the name that gives hundreds of false positives on grep is not a good idea... 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 527b9e482f99..9d2de4cadabd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1770,7 +1770,7 @@ extern int do_remount_sb(struct super_block *sb, int flags, extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *); -extern int permission(struct inode *, int, struct nameidata *); +extern int inode_permission(struct inode *, int); extern int generic_permission(struct inode *, int, int (*check_acl)(struct inode *, int)); -- cgit v1.2.2 From 2d8f30380ab8c706f4e0a8f1aaa22b5886e9ac8a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 22 Jul 2008 09:59:21 -0400 Subject: [PATCH] sanitize __user_walk_fd() et.al. * do not pass nameidata; struct path is all the callers want. * switch to new helpers: user_path_at(dfd, pathname, flags, &path) user_path(pathname, &path) user_lpath(pathname, &path) user_path_dir(pathname, &path) (fail if not a directory) The last 3 are trivial macro wrappers for the first one. * remove nameidata in callers. Signed-off-by: Al Viro --- include/linux/namei.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 60e35a02f6cb..00888ff69504 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -54,12 +54,13 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_OPEN (0x0100) #define LOOKUP_CREATE (0x0200) -extern int __user_walk(const char __user *, unsigned, struct nameidata *); -extern int __user_walk_fd(int dfd, const char __user *, unsigned, struct nameidata *); -#define user_path_walk(name,nd) \ - __user_walk_fd(AT_FDCWD, name, LOOKUP_FOLLOW, nd) -#define user_path_walk_link(name,nd) \ - __user_walk_fd(AT_FDCWD, name, 0, nd) +extern int user_path_at(int, const char __user *, unsigned, struct path *); + +#define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path) +#define user_lpath(name, path) user_path_at(AT_FDCWD, name, 0, path) +#define user_path_dir(name, path) \ + user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, path) + extern int path_lookup(const char *, unsigned, struct nameidata *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct nameidata *); -- cgit v1.2.2 From 516e0cc5646f377ab80fcc2ee639892eccb99853 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 26 Jul 2008 00:39:17 -0400 Subject: [PATCH] f_count may wrap around make it atomic_long_t; while we are at it, get rid of useless checks in affs, hfs and hpfs - ->open() always has it equal to 1, ->release() - to 0. 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 9d2de4cadabd..7676fa1c20ae 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -795,7 +795,7 @@ struct file { #define f_dentry f_path.dentry #define f_vfsmnt f_path.mnt const struct file_operations *f_op; - atomic_t f_count; + atomic_long_t f_count; unsigned int f_flags; mode_t f_mode; loff_t f_pos; @@ -824,8 +824,8 @@ extern spinlock_t files_lock; #define file_list_lock() spin_lock(&files_lock); #define file_list_unlock() spin_unlock(&files_lock); -#define get_file(x) atomic_inc(&(x)->f_count) -#define file_count(x) atomic_read(&(x)->f_count) +#define get_file(x) atomic_long_inc(&(x)->f_count) +#define file_count(x) atomic_long_read(&(x)->f_count) #ifdef CONFIG_DEBUG_WRITECOUNT static inline void file_take_write(struct file *f) -- cgit v1.2.2 From 964bd183624c03680796b63b4ab97ee3905a806a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 26 Jul 2008 03:33:14 -0400 Subject: [PATCH] get rid of __user_path_lookup_open Signed-off-by: Al Viro --- include/linux/namei.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 00888ff69504..68f8c3203c89 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -65,7 +65,6 @@ extern int path_lookup(const char *, unsigned, struct nameidata *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct nameidata *); -extern int __user_path_lookup_open(const char __user *, unsigned lookup_flags, struct nameidata *nd, int open_flags); extern int path_lookup_open(int dfd, const char *name, unsigned lookup_flags, struct nameidata *, int open_flags); extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, int (*open)(struct inode *, struct file *)); -- cgit v1.2.2 From 3f8206d496e9e9495afb1d4e70d29712b4d403c9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 26 Jul 2008 03:46:43 -0400 Subject: [PATCH] get rid of indirect users of namei.h fs.h needs path.h, not namei.h; nfs_fs.h doesn't need it at all. Several places in the tree needed direct include. Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- include/linux/nfs_fs.h | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7676fa1c20ae..8252b045e624 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -279,7 +279,7 @@ extern int dir_notify_enable; #include #include #include -#include +#include #include #include #include diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f08f9ca602af..78a5922a2f11 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -42,7 +42,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.2 From 510a35d4a47802f4a0028aa6bd2ca2170da5e32f Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Sat, 26 Jul 2008 15:22:27 -0700 Subject: hugetlb: remove unused variable warning Remove the following warning when CONFIG_HUGETLB_PAGE is not set: ipc/shm.c: In function `shm_get_stat': ipc/shm.c:565: warning: unused variable `h' [akpm@linux-foundation.org: use tabs, not spaces] Signed-off-by: Andrea Righi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 9a71d4cc88c8..32e0ef0f6e1f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -273,7 +273,10 @@ struct hstate {}; #define huge_page_mask(h) PAGE_MASK #define huge_page_order(h) 0 #define huge_page_shift(h) PAGE_SHIFT -#define pages_per_huge_page(h) 1 +static inline unsigned int pages_per_huge_page(struct hstate *h) +{ + return 1; +} #endif #endif /* _LINUX_HUGETLB_H */ -- cgit v1.2.2 From 9993e51c0c47ec69dce1f26c2321af6bb9165e9e Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 26 Jul 2008 13:53:46 -0300 Subject: V4L/DVB (8502): videodev2.h: CodingStyle cleanups Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 378 ++++++++++++++++++++-------------------------- 1 file changed, 166 insertions(+), 212 deletions(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 2e66a95e8d32..cc0c8952323b 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -91,8 +91,8 @@ */ /* Four-character-code (FOURCC) */ -#define v4l2_fourcc(a,b,c,d)\ - (((__u32)(a)<<0)|((__u32)(b)<<8)|((__u32)(c)<<16)|((__u32)(d)<<24)) +#define v4l2_fourcc(a, b, c, d)\ + ((__u32)(a) | ((__u32)(b) << 8) | ((__u32)(c) << 16) | ((__u32)(d) << 24)) /* * E N U M S @@ -226,8 +226,7 @@ struct v4l2_fract { /* * D R I V E R C A P A B I L I T I E S */ -struct v4l2_capability -{ +struct v4l2_capability { __u8 driver[16]; /* i.e. "bttv" */ __u8 card[32]; /* i.e. "Hauppauge WinTV" */ __u8 bus_info[32]; /* "PCI:" + pci_name(pci_dev) */ @@ -259,8 +258,7 @@ struct v4l2_capability /* * V I D E O I M A G E F O R M A T */ -struct v4l2_pix_format -{ +struct v4l2_pix_format { __u32 width; __u32 height; __u32 pixelformat; @@ -272,68 +270,67 @@ struct v4l2_pix_format }; /* Pixel format FOURCC depth Description */ -#define V4L2_PIX_FMT_RGB332 v4l2_fourcc('R','G','B','1') /* 8 RGB-3-3-2 */ -#define V4L2_PIX_FMT_RGB444 v4l2_fourcc('R','4','4','4') /* 16 xxxxrrrr ggggbbbb */ -#define V4L2_PIX_FMT_RGB555 v4l2_fourcc('R','G','B','O') /* 16 RGB-5-5-5 */ -#define V4L2_PIX_FMT_RGB565 v4l2_fourcc('R','G','B','P') /* 16 RGB-5-6-5 */ -#define V4L2_PIX_FMT_RGB555X v4l2_fourcc('R','G','B','Q') /* 16 RGB-5-5-5 BE */ -#define V4L2_PIX_FMT_RGB565X v4l2_fourcc('R','G','B','R') /* 16 RGB-5-6-5 BE */ -#define V4L2_PIX_FMT_BGR24 v4l2_fourcc('B','G','R','3') /* 24 BGR-8-8-8 */ -#define V4L2_PIX_FMT_RGB24 v4l2_fourcc('R','G','B','3') /* 24 RGB-8-8-8 */ -#define V4L2_PIX_FMT_BGR32 v4l2_fourcc('B','G','R','4') /* 32 BGR-8-8-8-8 */ -#define V4L2_PIX_FMT_RGB32 v4l2_fourcc('R','G','B','4') /* 32 RGB-8-8-8-8 */ -#define V4L2_PIX_FMT_GREY v4l2_fourcc('G','R','E','Y') /* 8 Greyscale */ -#define V4L2_PIX_FMT_Y16 v4l2_fourcc('Y','1','6',' ') /* 16 Greyscale */ -#define V4L2_PIX_FMT_PAL8 v4l2_fourcc('P','A','L','8') /* 8 8-bit palette */ -#define V4L2_PIX_FMT_YVU410 v4l2_fourcc('Y','V','U','9') /* 9 YVU 4:1:0 */ -#define V4L2_PIX_FMT_YVU420 v4l2_fourcc('Y','V','1','2') /* 12 YVU 4:2:0 */ -#define V4L2_PIX_FMT_YUYV v4l2_fourcc('Y','U','Y','V') /* 16 YUV 4:2:2 */ -#define V4L2_PIX_FMT_UYVY v4l2_fourcc('U','Y','V','Y') /* 16 YUV 4:2:2 */ -#define V4L2_PIX_FMT_YUV422P v4l2_fourcc('4','2','2','P') /* 16 YVU422 planar */ -#define V4L2_PIX_FMT_YUV411P v4l2_fourcc('4','1','1','P') /* 16 YVU411 planar */ -#define V4L2_PIX_FMT_Y41P v4l2_fourcc('Y','4','1','P') /* 12 YUV 4:1:1 */ -#define V4L2_PIX_FMT_YUV444 v4l2_fourcc('Y','4','4','4') /* 16 xxxxyyyy uuuuvvvv */ -#define V4L2_PIX_FMT_YUV555 v4l2_fourcc('Y','U','V','O') /* 16 YUV-5-5-5 */ -#define V4L2_PIX_FMT_YUV565 v4l2_fourcc('Y','U','V','P') /* 16 YUV-5-6-5 */ -#define V4L2_PIX_FMT_YUV32 v4l2_fourcc('Y','U','V','4') /* 32 YUV-8-8-8-8 */ +#define V4L2_PIX_FMT_RGB332 v4l2_fourcc('R', 'G', 'B', '1') /* 8 RGB-3-3-2 */ +#define V4L2_PIX_FMT_RGB444 v4l2_fourcc('R', '4', '4', '4') /* 16 xxxxrrrr ggggbbbb */ +#define V4L2_PIX_FMT_RGB555 v4l2_fourcc('R', 'G', 'B', 'O') /* 16 RGB-5-5-5 */ +#define V4L2_PIX_FMT_RGB565 v4l2_fourcc('R', 'G', 'B', 'P') /* 16 RGB-5-6-5 */ +#define V4L2_PIX_FMT_RGB555X v4l2_fourcc('R', 'G', 'B', 'Q') /* 16 RGB-5-5-5 BE */ +#define V4L2_PIX_FMT_RGB565X v4l2_fourcc('R', 'G', 'B', 'R') /* 16 RGB-5-6-5 BE */ +#define V4L2_PIX_FMT_BGR24 v4l2_fourcc('B', 'G', 'R', '3') /* 24 BGR-8-8-8 */ +#define V4L2_PIX_FMT_RGB24 v4l2_fourcc('R', 'G', 'B', '3') /* 24 RGB-8-8-8 */ +#define V4L2_PIX_FMT_BGR32 v4l2_fourcc('B', 'G', 'R', '4') /* 32 BGR-8-8-8-8 */ +#define V4L2_PIX_FMT_RGB32 v4l2_fourcc('R', 'G', 'B', '4') /* 32 RGB-8-8-8-8 */ +#define V4L2_PIX_FMT_GREY v4l2_fourcc('G', 'R', 'E', 'Y') /* 8 Greyscale */ +#define V4L2_PIX_FMT_Y16 v4l2_fourcc('Y', '1', '6', ' ') /* 16 Greyscale */ +#define V4L2_PIX_FMT_PAL8 v4l2_fourcc('P', 'A', 'L', '8') /* 8 8-bit palette */ +#define V4L2_PIX_FMT_YVU410 v4l2_fourcc('Y', 'V', 'U', '9') /* 9 YVU 4:1:0 */ +#define V4L2_PIX_FMT_YVU420 v4l2_fourcc('Y', 'V', '1', '2') /* 12 YVU 4:2:0 */ +#define V4L2_PIX_FMT_YUYV v4l2_fourcc('Y', 'U', 'Y', 'V') /* 16 YUV 4:2:2 */ +#define V4L2_PIX_FMT_UYVY v4l2_fourcc('U', 'Y', 'V', 'Y') /* 16 YUV 4:2:2 */ +#define V4L2_PIX_FMT_YUV422P v4l2_fourcc('4', '2', '2', 'P') /* 16 YVU422 planar */ +#define V4L2_PIX_FMT_YUV411P v4l2_fourcc('4', '1', '1', 'P') /* 16 YVU411 planar */ +#define V4L2_PIX_FMT_Y41P v4l2_fourcc('Y', '4', '1', 'P') /* 12 YUV 4:1:1 */ +#define V4L2_PIX_FMT_YUV444 v4l2_fourcc('Y', '4', '4', '4') /* 16 xxxxyyyy uuuuvvvv */ +#define V4L2_PIX_FMT_YUV555 v4l2_fourcc('Y', 'U', 'V', 'O') /* 16 YUV-5-5-5 */ +#define V4L2_PIX_FMT_YUV565 v4l2_fourcc('Y', 'U', 'V', 'P') /* 16 YUV-5-6-5 */ +#define V4L2_PIX_FMT_YUV32 v4l2_fourcc('Y', 'U', 'V', '4') /* 32 YUV-8-8-8-8 */ /* two planes -- one Y, one Cr + Cb interleaved */ -#define V4L2_PIX_FMT_NV12 v4l2_fourcc('N','V','1','2') /* 12 Y/CbCr 4:2:0 */ -#define V4L2_PIX_FMT_NV21 v4l2_fourcc('N','V','2','1') /* 12 Y/CrCb 4:2:0 */ +#define V4L2_PIX_FMT_NV12 v4l2_fourcc('N', 'V', '1', '2') /* 12 Y/CbCr 4:2:0 */ +#define V4L2_PIX_FMT_NV21 v4l2_fourcc('N', 'V', '2', '1') /* 12 Y/CrCb 4:2:0 */ /* The following formats are not defined in the V4L2 specification */ -#define V4L2_PIX_FMT_YUV410 v4l2_fourcc('Y','U','V','9') /* 9 YUV 4:1:0 */ -#define V4L2_PIX_FMT_YUV420 v4l2_fourcc('Y','U','1','2') /* 12 YUV 4:2:0 */ -#define V4L2_PIX_FMT_YYUV v4l2_fourcc('Y','Y','U','V') /* 16 YUV 4:2:2 */ -#define V4L2_PIX_FMT_HI240 v4l2_fourcc('H','I','2','4') /* 8 8-bit color */ -#define V4L2_PIX_FMT_HM12 v4l2_fourcc('H','M','1','2') /* 8 YUV 4:2:0 16x16 macroblocks */ +#define V4L2_PIX_FMT_YUV410 v4l2_fourcc('Y', 'U', 'V', '9') /* 9 YUV 4:1:0 */ +#define V4L2_PIX_FMT_YUV420 v4l2_fourcc('Y', 'U', '1', '2') /* 12 YUV 4:2:0 */ +#define V4L2_PIX_FMT_YYUV v4l2_fourcc('Y', 'Y', 'U', 'V') /* 16 YUV 4:2:2 */ +#define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* 8 8-bit color */ +#define V4L2_PIX_FMT_HM12 v4l2_fourcc('H', 'M', '1', '2') /* 8 YUV 4:2:0 16x16 macroblocks */ /* see http://www.siliconimaging.com/RGB%20Bayer.htm */ -#define V4L2_PIX_FMT_SBGGR8 v4l2_fourcc('B','A','8','1') /* 8 BGBG.. GRGR.. */ -#define V4L2_PIX_FMT_SGBRG8 v4l2_fourcc('G','B','R','G') /* 8 GBGB.. RGRG.. */ -#define V4L2_PIX_FMT_SBGGR16 v4l2_fourcc('B','Y','R','2') /* 16 BGBG.. GRGR.. */ +#define V4L2_PIX_FMT_SBGGR8 v4l2_fourcc('B', 'A', '8', '1') /* 8 BGBG.. GRGR.. */ +#define V4L2_PIX_FMT_SGBRG8 v4l2_fourcc('G', 'B', 'R', 'G') /* 8 GBGB.. RGRG.. */ +#define V4L2_PIX_FMT_SBGGR16 v4l2_fourcc('B', 'Y', 'R', '2') /* 16 BGBG.. GRGR.. */ /* compressed formats */ -#define V4L2_PIX_FMT_MJPEG v4l2_fourcc('M','J','P','G') /* Motion-JPEG */ -#define V4L2_PIX_FMT_JPEG v4l2_fourcc('J','P','E','G') /* JFIF JPEG */ -#define V4L2_PIX_FMT_DV v4l2_fourcc('d','v','s','d') /* 1394 */ -#define V4L2_PIX_FMT_MPEG v4l2_fourcc('M','P','E','G') /* MPEG-1/2/4 */ +#define V4L2_PIX_FMT_MJPEG v4l2_fourcc('M', 'J', 'P', 'G') /* Motion-JPEG */ +#define V4L2_PIX_FMT_JPEG v4l2_fourcc('J', 'P', 'E', 'G') /* JFIF JPEG */ +#define V4L2_PIX_FMT_DV v4l2_fourcc('d', 'v', 's', 'd') /* 1394 */ +#define V4L2_PIX_FMT_MPEG v4l2_fourcc('M', 'P', 'E', 'G') /* MPEG-1/2/4 */ /* Vendor-specific formats */ -#define V4L2_PIX_FMT_WNVA v4l2_fourcc('W','N','V','A') /* Winnov hw compress */ -#define V4L2_PIX_FMT_SN9C10X v4l2_fourcc('S','9','1','0') /* SN9C10x compression */ -#define V4L2_PIX_FMT_PWC1 v4l2_fourcc('P','W','C','1') /* pwc older webcam */ -#define V4L2_PIX_FMT_PWC2 v4l2_fourcc('P','W','C','2') /* pwc newer webcam */ -#define V4L2_PIX_FMT_ET61X251 v4l2_fourcc('E','6','2','5') /* ET61X251 compression */ -#define V4L2_PIX_FMT_SPCA501 v4l2_fourcc('S','5','0','1') /* YUYV per line */ -#define V4L2_PIX_FMT_SPCA561 v4l2_fourcc('S','5','6','1') /* compressed GBRG bayer */ -#define V4L2_PIX_FMT_PAC207 v4l2_fourcc('P','2','0','7') /* compressed BGGR bayer */ +#define V4L2_PIX_FMT_WNVA v4l2_fourcc('W', 'N', 'V', 'A') /* Winnov hw compress */ +#define V4L2_PIX_FMT_SN9C10X v4l2_fourcc('S', '9', '1', '0') /* SN9C10x compression */ +#define V4L2_PIX_FMT_PWC1 v4l2_fourcc('P', 'W', 'C', '1') /* pwc older webcam */ +#define V4L2_PIX_FMT_PWC2 v4l2_fourcc('P', 'W', 'C', '2') /* pwc newer webcam */ +#define V4L2_PIX_FMT_ET61X251 v4l2_fourcc('E', '6', '2', '5') /* ET61X251 compression */ +#define V4L2_PIX_FMT_SPCA501 v4l2_fourcc('S', '5', '0', '1') /* YUYV per line */ +#define V4L2_PIX_FMT_SPCA561 v4l2_fourcc('S', '5', '6', '1') /* compressed GBRG bayer */ +#define V4L2_PIX_FMT_PAC207 v4l2_fourcc('P', '2', '0', '7') /* compressed BGGR bayer */ /* * F O R M A T E N U M E R A T I O N */ -struct v4l2_fmtdesc -{ +struct v4l2_fmtdesc { __u32 index; /* Format number */ enum v4l2_buf_type type; /* buffer type */ __u32 flags; @@ -349,21 +346,18 @@ struct v4l2_fmtdesc /* * F R A M E S I Z E E N U M E R A T I O N */ -enum v4l2_frmsizetypes -{ +enum v4l2_frmsizetypes { V4L2_FRMSIZE_TYPE_DISCRETE = 1, V4L2_FRMSIZE_TYPE_CONTINUOUS = 2, V4L2_FRMSIZE_TYPE_STEPWISE = 3, }; -struct v4l2_frmsize_discrete -{ +struct v4l2_frmsize_discrete { __u32 width; /* Frame width [pixel] */ __u32 height; /* Frame height [pixel] */ }; -struct v4l2_frmsize_stepwise -{ +struct v4l2_frmsize_stepwise { __u32 min_width; /* Minimum frame width [pixel] */ __u32 max_width; /* Maximum frame width [pixel] */ __u32 step_width; /* Frame width step size [pixel] */ @@ -372,8 +366,7 @@ struct v4l2_frmsize_stepwise __u32 step_height; /* Frame height step size [pixel] */ }; -struct v4l2_frmsizeenum -{ +struct v4l2_frmsizeenum { __u32 index; /* Frame size number */ __u32 pixel_format; /* Pixel format */ __u32 type; /* Frame size type the device supports. */ @@ -389,22 +382,19 @@ struct v4l2_frmsizeenum /* * F R A M E R A T E E N U M E R A T I O N */ -enum v4l2_frmivaltypes -{ +enum v4l2_frmivaltypes { V4L2_FRMIVAL_TYPE_DISCRETE = 1, V4L2_FRMIVAL_TYPE_CONTINUOUS = 2, V4L2_FRMIVAL_TYPE_STEPWISE = 3, }; -struct v4l2_frmival_stepwise -{ +struct v4l2_frmival_stepwise { struct v4l2_fract min; /* Minimum frame interval [s] */ struct v4l2_fract max; /* Maximum frame interval [s] */ struct v4l2_fract step; /* Frame interval step size [s] */ }; -struct v4l2_frmivalenum -{ +struct v4l2_frmivalenum { __u32 index; /* Frame format index */ __u32 pixel_format; /* Pixel format */ __u32 width; /* Frame width */ @@ -423,8 +413,7 @@ struct v4l2_frmivalenum /* * T I M E C O D E */ -struct v4l2_timecode -{ +struct v4l2_timecode { __u32 type; __u32 flags; __u8 frames; @@ -449,8 +438,7 @@ struct v4l2_timecode #define V4L2_TC_USERBITS_8BITCHARS 0x0008 /* The above is based on SMPTE timecodes */ -struct v4l2_jpegcompression -{ +struct v4l2_jpegcompression { int quality; int APPn; /* Number of APP segment to be written, @@ -482,16 +470,14 @@ struct v4l2_jpegcompression /* * M E M O R Y - M A P P I N G B U F F E R S */ -struct v4l2_requestbuffers -{ +struct v4l2_requestbuffers { __u32 count; enum v4l2_buf_type type; enum v4l2_memory memory; __u32 reserved[2]; }; -struct v4l2_buffer -{ +struct v4l2_buffer { __u32 index; enum v4l2_buf_type type; __u32 bytesused; @@ -525,13 +511,12 @@ struct v4l2_buffer /* * O V E R L A Y P R E V I E W */ -struct v4l2_framebuffer -{ +struct v4l2_framebuffer { __u32 capability; __u32 flags; /* FIXME: in theory we should pass something like PCI device + memory * region + offset instead of some physical address */ - void* base; + void *base; struct v4l2_pix_format fmt; }; /* Flags for the 'capability' field. Read only */ @@ -550,14 +535,12 @@ struct v4l2_framebuffer #define V4L2_FBUF_FLAG_GLOBAL_ALPHA 0x0010 #define V4L2_FBUF_FLAG_LOCAL_INV_ALPHA 0x0020 -struct v4l2_clip -{ +struct v4l2_clip { struct v4l2_rect c; struct v4l2_clip __user *next; }; -struct v4l2_window -{ +struct v4l2_window { struct v4l2_rect w; enum v4l2_field field; __u32 chromakey; @@ -570,8 +553,7 @@ struct v4l2_window /* * C A P T U R E P A R A M E T E R S */ -struct v4l2_captureparm -{ +struct v4l2_captureparm { __u32 capability; /* Supported modes */ __u32 capturemode; /* Current mode */ struct v4l2_fract timeperframe; /* Time per frame in .1us units */ @@ -584,8 +566,7 @@ struct v4l2_captureparm #define V4L2_MODE_HIGHQUALITY 0x0001 /* High quality imaging mode */ #define V4L2_CAP_TIMEPERFRAME 0x1000 /* timeperframe field is supported */ -struct v4l2_outputparm -{ +struct v4l2_outputparm { __u32 capability; /* Supported modes */ __u32 outputmode; /* Current mode */ struct v4l2_fract timeperframe; /* Time per frame in seconds */ @@ -702,8 +683,7 @@ typedef __u64 v4l2_std_id; #define V4L2_STD_ALL (V4L2_STD_525_60 |\ V4L2_STD_625_50) -struct v4l2_standard -{ +struct v4l2_standard { __u32 index; v4l2_std_id id; __u8 name[24]; @@ -715,8 +695,7 @@ struct v4l2_standard /* * V I D E O I N P U T S */ -struct v4l2_input -{ +struct v4l2_input { __u32 index; /* Which input */ __u8 name[32]; /* Label */ __u32 type; /* Type of input */ @@ -753,8 +732,7 @@ struct v4l2_input /* * V I D E O O U T P U T S */ -struct v4l2_output -{ +struct v4l2_output { __u32 index; /* Which output */ __u8 name[32]; /* Label */ __u32 type; /* Type of output */ @@ -771,14 +749,12 @@ struct v4l2_output /* * C O N T R O L S */ -struct v4l2_control -{ +struct v4l2_control { __u32 id; __s32 value; }; -struct v4l2_ext_control -{ +struct v4l2_ext_control { __u32 id; __u32 reserved2[2]; union { @@ -788,8 +764,7 @@ struct v4l2_ext_control }; } __attribute__ ((packed)); -struct v4l2_ext_controls -{ +struct v4l2_ext_controls { __u32 ctrl_class; __u32 count; __u32 error_idx; @@ -807,8 +782,7 @@ struct v4l2_ext_controls #define V4L2_CTRL_DRIVER_PRIV(id) (((id) & 0xffff) >= 0x1000) /* Used in the VIDIOC_QUERYCTRL ioctl for querying controls */ -struct v4l2_queryctrl -{ +struct v4l2_queryctrl { __u32 id; enum v4l2_ctrl_type type; __u8 name[32]; /* Whatever */ @@ -821,8 +795,7 @@ struct v4l2_queryctrl }; /* Used in the VIDIOC_QUERYMENU ioctl for querying menu items */ -struct v4l2_querymenu -{ +struct v4l2_querymenu { __u32 id; __u32 index; __u8 name[32]; /* Whatever */ @@ -1104,8 +1077,7 @@ enum v4l2_exposure_auto_type { /* * T U N I N G */ -struct v4l2_tuner -{ +struct v4l2_tuner { __u32 index; __u8 name[32]; enum v4l2_tuner_type type; @@ -1119,8 +1091,7 @@ struct v4l2_tuner __u32 reserved[4]; }; -struct v4l2_modulator -{ +struct v4l2_modulator { __u32 index; __u8 name[32]; __u32 capability; @@ -1153,8 +1124,7 @@ struct v4l2_modulator #define V4L2_TUNER_MODE_LANG1 0x0003 #define V4L2_TUNER_MODE_LANG1_LANG2 0x0004 -struct v4l2_frequency -{ +struct v4l2_frequency { __u32 tuner; enum v4l2_tuner_type type; __u32 frequency; @@ -1172,8 +1142,7 @@ struct v4l2_hw_freq_seek { /* * A U D I O */ -struct v4l2_audio -{ +struct v4l2_audio { __u32 index; __u8 name[32]; __u32 capability; @@ -1188,8 +1157,7 @@ struct v4l2_audio /* Flags for the 'mode' field */ #define V4L2_AUDMODE_AVL 0x00001 -struct v4l2_audioout -{ +struct v4l2_audioout { __u32 index; __u8 name[32]; __u32 capability; @@ -1253,8 +1221,7 @@ struct v4l2_encoder_cmd { */ /* Raw VBI */ -struct v4l2_vbi_format -{ +struct v4l2_vbi_format { __u32 sampling_rate; /* in 1 Hz */ __u32 offset; __u32 samples_per_line; @@ -1266,8 +1233,8 @@ struct v4l2_vbi_format }; /* VBI flags */ -#define V4L2_VBI_UNSYNC (1<< 0) -#define V4L2_VBI_INTERLACED (1<< 1) +#define V4L2_VBI_UNSYNC (1 << 0) +#define V4L2_VBI_INTERLACED (1 << 1) /* Sliced VBI * @@ -1276,8 +1243,7 @@ struct v4l2_vbi_format * notice in the definitive implementation. */ -struct v4l2_sliced_vbi_format -{ +struct v4l2_sliced_vbi_format { __u16 service_set; /* service_lines[0][...] specifies lines 0-23 (1-23 used) of the first field service_lines[1][...] specifies lines 0-23 (1-23 used) of the second field @@ -1301,8 +1267,7 @@ struct v4l2_sliced_vbi_format #define V4L2_SLICED_VBI_525 (V4L2_SLICED_CAPTION_525) #define V4L2_SLICED_VBI_625 (V4L2_SLICED_TELETEXT_B | V4L2_SLICED_VPS | V4L2_SLICED_WSS_625) -struct v4l2_sliced_vbi_cap -{ +struct v4l2_sliced_vbi_cap { __u16 service_set; /* service_lines[0][...] specifies lines 0-23 (1-23 used) of the first field service_lines[1][...] specifies lines 0-23 (1-23 used) of the second field @@ -1313,8 +1278,7 @@ struct v4l2_sliced_vbi_cap __u32 reserved[3]; /* must be 0 */ }; -struct v4l2_sliced_vbi_data -{ +struct v4l2_sliced_vbi_data { __u32 id; __u32 field; /* 0: first field, 1: second field */ __u32 line; /* 1-23 */ @@ -1328,27 +1292,23 @@ struct v4l2_sliced_vbi_data /* Stream data format */ -struct v4l2_format -{ +struct v4l2_format { enum v4l2_buf_type type; - union - { - struct v4l2_pix_format pix; // V4L2_BUF_TYPE_VIDEO_CAPTURE - struct v4l2_window win; // V4L2_BUF_TYPE_VIDEO_OVERLAY - struct v4l2_vbi_format vbi; // V4L2_BUF_TYPE_VBI_CAPTURE - struct v4l2_sliced_vbi_format sliced; // V4L2_BUF_TYPE_SLICED_VBI_CAPTURE - __u8 raw_data[200]; // user-defined + union { + struct v4l2_pix_format pix; /* V4L2_BUF_TYPE_VIDEO_CAPTURE */ + struct v4l2_window win; /* V4L2_BUF_TYPE_VIDEO_OVERLAY */ + struct v4l2_vbi_format vbi; /* V4L2_BUF_TYPE_VBI_CAPTURE */ + struct v4l2_sliced_vbi_format sliced; /* V4L2_BUF_TYPE_SLICED_VBI_CAPTURE */ + __u8 raw_data[200]; /* user-defined */ } fmt; }; /* Stream type-dependent parameters */ -struct v4l2_streamparm -{ +struct v4l2_streamparm { enum v4l2_buf_type type; - union - { + union { struct v4l2_captureparm capture; struct v4l2_outputparm output; __u8 raw_data[200]; /* user-defined */ @@ -1386,92 +1346,86 @@ struct v4l2_chip_ident { * I O C T L C O D E S F O R V I D E O D E V I C E S * */ -#define VIDIOC_QUERYCAP _IOR ('V', 0, struct v4l2_capability) -#define VIDIOC_RESERVED _IO ('V', 1) -#define VIDIOC_ENUM_FMT _IOWR ('V', 2, struct v4l2_fmtdesc) -#define VIDIOC_G_FMT _IOWR ('V', 4, struct v4l2_format) -#define VIDIOC_S_FMT _IOWR ('V', 5, struct v4l2_format) -#define VIDIOC_REQBUFS _IOWR ('V', 8, struct v4l2_requestbuffers) -#define VIDIOC_QUERYBUF _IOWR ('V', 9, struct v4l2_buffer) -#define VIDIOC_G_FBUF _IOR ('V', 10, struct v4l2_framebuffer) -#define VIDIOC_S_FBUF _IOW ('V', 11, struct v4l2_framebuffer) -#define VIDIOC_OVERLAY _IOW ('V', 14, int) -#define VIDIOC_QBUF _IOWR ('V', 15, struct v4l2_buffer) -#define VIDIOC_DQBUF _IOWR ('V', 17, struct v4l2_buffer) -#define VIDIOC_STREAMON _IOW ('V', 18, int) -#define VIDIOC_STREAMOFF _IOW ('V', 19, int) -#define VIDIOC_G_PARM _IOWR ('V', 21, struct v4l2_streamparm) -#define VIDIOC_S_PARM _IOWR ('V', 22, struct v4l2_streamparm) -#define VIDIOC_G_STD _IOR ('V', 23, v4l2_std_id) -#define VIDIOC_S_STD _IOW ('V', 24, v4l2_std_id) -#define VIDIOC_ENUMSTD _IOWR ('V', 25, struct v4l2_standard) -#define VIDIOC_ENUMINPUT _IOWR ('V', 26, struct v4l2_input) -#define VIDIOC_G_CTRL _IOWR ('V', 27, struct v4l2_control) -#define VIDIOC_S_CTRL _IOWR ('V', 28, struct v4l2_control) -#define VIDIOC_G_TUNER _IOWR ('V', 29, struct v4l2_tuner) -#define VIDIOC_S_TUNER _IOW ('V', 30, struct v4l2_tuner) -#define VIDIOC_G_AUDIO _IOR ('V', 33, struct v4l2_audio) -#define VIDIOC_S_AUDIO _IOW ('V', 34, struct v4l2_audio) -#define VIDIOC_QUERYCTRL _IOWR ('V', 36, struct v4l2_queryctrl) -#define VIDIOC_QUERYMENU _IOWR ('V', 37, struct v4l2_querymenu) -#define VIDIOC_G_INPUT _IOR ('V', 38, int) -#define VIDIOC_S_INPUT _IOWR ('V', 39, int) -#define VIDIOC_G_OUTPUT _IOR ('V', 46, int) -#define VIDIOC_S_OUTPUT _IOWR ('V', 47, int) -#define VIDIOC_ENUMOUTPUT _IOWR ('V', 48, struct v4l2_output) -#define VIDIOC_G_AUDOUT _IOR ('V', 49, struct v4l2_audioout) -#define VIDIOC_S_AUDOUT _IOW ('V', 50, struct v4l2_audioout) -#define VIDIOC_G_MODULATOR _IOWR ('V', 54, struct v4l2_modulator) -#define VIDIOC_S_MODULATOR _IOW ('V', 55, struct v4l2_modulator) -#define VIDIOC_G_FREQUENCY _IOWR ('V', 56, struct v4l2_frequency) -#define VIDIOC_S_FREQUENCY _IOW ('V', 57, struct v4l2_frequency) -#define VIDIOC_CROPCAP _IOWR ('V', 58, struct v4l2_cropcap) -#define VIDIOC_G_CROP _IOWR ('V', 59, struct v4l2_crop) -#define VIDIOC_S_CROP _IOW ('V', 60, struct v4l2_crop) -#define VIDIOC_G_JPEGCOMP _IOR ('V', 61, struct v4l2_jpegcompression) -#define VIDIOC_S_JPEGCOMP _IOW ('V', 62, struct v4l2_jpegcompression) -#define VIDIOC_QUERYSTD _IOR ('V', 63, v4l2_std_id) -#define VIDIOC_TRY_FMT _IOWR ('V', 64, struct v4l2_format) -#define VIDIOC_ENUMAUDIO _IOWR ('V', 65, struct v4l2_audio) -#define VIDIOC_ENUMAUDOUT _IOWR ('V', 66, struct v4l2_audioout) -#define VIDIOC_G_PRIORITY _IOR ('V', 67, enum v4l2_priority) -#define VIDIOC_S_PRIORITY _IOW ('V', 68, enum v4l2_priority) -#define VIDIOC_G_SLICED_VBI_CAP _IOWR ('V', 69, struct v4l2_sliced_vbi_cap) -#define VIDIOC_LOG_STATUS _IO ('V', 70) -#define VIDIOC_G_EXT_CTRLS _IOWR ('V', 71, struct v4l2_ext_controls) -#define VIDIOC_S_EXT_CTRLS _IOWR ('V', 72, struct v4l2_ext_controls) -#define VIDIOC_TRY_EXT_CTRLS _IOWR ('V', 73, struct v4l2_ext_controls) +#define VIDIOC_QUERYCAP _IOR('V', 0, struct v4l2_capability) +#define VIDIOC_RESERVED _IO('V', 1) +#define VIDIOC_ENUM_FMT _IOWR('V', 2, struct v4l2_fmtdesc) +#define VIDIOC_G_FMT _IOWR('V', 4, struct v4l2_format) +#define VIDIOC_S_FMT _IOWR('V', 5, struct v4l2_format) +#define VIDIOC_REQBUFS _IOWR('V', 8, struct v4l2_requestbuffers) +#define VIDIOC_QUERYBUF _IOWR('V', 9, struct v4l2_buffer) +#define VIDIOC_G_FBUF _IOR('V', 10, struct v4l2_framebuffer) +#define VIDIOC_S_FBUF _IOW('V', 11, struct v4l2_framebuffer) +#define VIDIOC_OVERLAY _IOW('V', 14, int) +#define VIDIOC_QBUF _IOWR('V', 15, struct v4l2_buffer) +#define VIDIOC_DQBUF _IOWR('V', 17, struct v4l2_buffer) +#define VIDIOC_STREAMON _IOW('V', 18, int) +#define VIDIOC_STREAMOFF _IOW('V', 19, int) +#define VIDIOC_G_PARM _IOWR('V', 21, struct v4l2_streamparm) +#define VIDIOC_S_PARM _IOWR('V', 22, struct v4l2_streamparm) +#define VIDIOC_G_STD _IOR('V', 23, v4l2_std_id) +#define VIDIOC_S_STD _IOW('V', 24, v4l2_std_id) +#define VIDIOC_ENUMSTD _IOWR('V', 25, struct v4l2_standard) +#define VIDIOC_ENUMINPUT _IOWR('V', 26, struct v4l2_input) +#define VIDIOC_G_CTRL _IOWR('V', 27, struct v4l2_control) +#define VIDIOC_S_CTRL _IOWR('V', 28, struct v4l2_control) +#define VIDIOC_G_TUNER _IOWR('V', 29, struct v4l2_tuner) +#define VIDIOC_S_TUNER _IOW('V', 30, struct v4l2_tuner) +#define VIDIOC_G_AUDIO _IOR('V', 33, struct v4l2_audio) +#define VIDIOC_S_AUDIO _IOW('V', 34, struct v4l2_audio) +#define VIDIOC_QUERYCTRL _IOWR('V', 36, struct v4l2_queryctrl) +#define VIDIOC_QUERYMENU _IOWR('V', 37, struct v4l2_querymenu) +#define VIDIOC_G_INPUT _IOR('V', 38, int) +#define VIDIOC_S_INPUT _IOWR('V', 39, int) +#define VIDIOC_G_OUTPUT _IOR('V', 46, int) +#define VIDIOC_S_OUTPUT _IOWR('V', 47, int) +#define VIDIOC_ENUMOUTPUT _IOWR('V', 48, struct v4l2_output) +#define VIDIOC_G_AUDOUT _IOR('V', 49, struct v4l2_audioout) +#define VIDIOC_S_AUDOUT _IOW('V', 50, struct v4l2_audioout) +#define VIDIOC_G_MODULATOR _IOWR('V', 54, struct v4l2_modulator) +#define VIDIOC_S_MODULATOR _IOW('V', 55, struct v4l2_modulator) +#define VIDIOC_G_FREQUENCY _IOWR('V', 56, struct v4l2_frequency) +#define VIDIOC_S_FREQUENCY _IOW('V', 57, struct v4l2_frequency) +#define VIDIOC_CROPCAP _IOWR('V', 58, struct v4l2_cropcap) +#define VIDIOC_G_CROP _IOWR('V', 59, struct v4l2_crop) +#define VIDIOC_S_CROP _IOW('V', 60, struct v4l2_crop) +#define VIDIOC_G_JPEGCOMP _IOR('V', 61, struct v4l2_jpegcompression) +#define VIDIOC_S_JPEGCOMP _IOW('V', 62, struct v4l2_jpegcompression) +#define VIDIOC_QUERYSTD _IOR('V', 63, v4l2_std_id) +#define VIDIOC_TRY_FMT _IOWR('V', 64, struct v4l2_format) +#define VIDIOC_ENUMAUDIO _IOWR('V', 65, struct v4l2_audio) +#define VIDIOC_ENUMAUDOUT _IOWR('V', 66, struct v4l2_audioout) +#define VIDIOC_G_PRIORITY _IOR('V', 67, enum v4l2_priority) +#define VIDIOC_S_PRIORITY _IOW('V', 68, enum v4l2_priority) +#define VIDIOC_G_SLICED_VBI_CAP _IOWR('V', 69, struct v4l2_sliced_vbi_cap) +#define VIDIOC_LOG_STATUS _IO('V', 70) +#define VIDIOC_G_EXT_CTRLS _IOWR('V', 71, struct v4l2_ext_controls) +#define VIDIOC_S_EXT_CTRLS _IOWR('V', 72, struct v4l2_ext_controls) +#define VIDIOC_TRY_EXT_CTRLS _IOWR('V', 73, struct v4l2_ext_controls) #if 1 -#define VIDIOC_ENUM_FRAMESIZES _IOWR ('V', 74, struct v4l2_frmsizeenum) -#define VIDIOC_ENUM_FRAMEINTERVALS _IOWR ('V', 75, struct v4l2_frmivalenum) -#define VIDIOC_G_ENC_INDEX _IOR ('V', 76, struct v4l2_enc_idx) -#define VIDIOC_ENCODER_CMD _IOWR ('V', 77, struct v4l2_encoder_cmd) -#define VIDIOC_TRY_ENCODER_CMD _IOWR ('V', 78, struct v4l2_encoder_cmd) +#define VIDIOC_ENUM_FRAMESIZES _IOWR('V', 74, struct v4l2_frmsizeenum) +#define VIDIOC_ENUM_FRAMEINTERVALS _IOWR('V', 75, struct v4l2_frmivalenum) +#define VIDIOC_G_ENC_INDEX _IOR('V', 76, struct v4l2_enc_idx) +#define VIDIOC_ENCODER_CMD _IOWR('V', 77, struct v4l2_encoder_cmd) +#define VIDIOC_TRY_ENCODER_CMD _IOWR('V', 78, struct v4l2_encoder_cmd) /* Experimental, only implemented if CONFIG_VIDEO_ADV_DEBUG is defined */ -#define VIDIOC_DBG_S_REGISTER _IOW ('V', 79, struct v4l2_register) -#define VIDIOC_DBG_G_REGISTER _IOWR ('V', 80, struct v4l2_register) +#define VIDIOC_DBG_S_REGISTER _IOW('V', 79, struct v4l2_register) +#define VIDIOC_DBG_G_REGISTER _IOWR('V', 80, struct v4l2_register) -#define VIDIOC_G_CHIP_IDENT _IOWR ('V', 81, struct v4l2_chip_ident) +#define VIDIOC_G_CHIP_IDENT _IOWR('V', 81, struct v4l2_chip_ident) #endif -#define VIDIOC_S_HW_FREQ_SEEK _IOW ('V', 82, struct v4l2_hw_freq_seek) +#define VIDIOC_S_HW_FREQ_SEEK _IOW('V', 82, struct v4l2_hw_freq_seek) #ifdef __OLD_VIDIOC_ /* for compatibility, will go away some day */ -#define VIDIOC_OVERLAY_OLD _IOWR ('V', 14, int) -#define VIDIOC_S_PARM_OLD _IOW ('V', 22, struct v4l2_streamparm) -#define VIDIOC_S_CTRL_OLD _IOW ('V', 28, struct v4l2_control) -#define VIDIOC_G_AUDIO_OLD _IOWR ('V', 33, struct v4l2_audio) -#define VIDIOC_G_AUDOUT_OLD _IOWR ('V', 49, struct v4l2_audioout) -#define VIDIOC_CROPCAP_OLD _IOR ('V', 58, struct v4l2_cropcap) +#define VIDIOC_OVERLAY_OLD _IOWR('V', 14, int) +#define VIDIOC_S_PARM_OLD _IOW('V', 22, struct v4l2_streamparm) +#define VIDIOC_S_CTRL_OLD _IOW('V', 28, struct v4l2_control) +#define VIDIOC_G_AUDIO_OLD _IOWR('V', 33, struct v4l2_audio) +#define VIDIOC_G_AUDOUT_OLD _IOWR('V', 49, struct v4l2_audioout) +#define VIDIOC_CROPCAP_OLD _IOR('V', 58, struct v4l2_cropcap) #endif #define BASE_VIDIOC_PRIVATE 192 /* 192-255 are private */ #endif /* __LINUX_VIDEODEV2_H */ - -/* - * Local variables: - * c-basic-offset: 8 - * End: - */ -- cgit v1.2.2 From 1250ac6d4ab716dafe0ac245fd31cd3a7cbc0a98 Mon Sep 17 00:00:00 2001 From: Jean-Francois Moine Date: Sat, 26 Jul 2008 08:02:47 -0300 Subject: V4L/DVB (8518): gspca: Remove the remaining frame decoding functions from the subdrivers. SPCA505 and SPCA508 added in the pixel formats. Decode functions and associated resources removed in spca505, 506 and 508. The decode routines are now found in the V4L library. Signed-off-by: Jean-Francois Moine Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index cc0c8952323b..7d9ac046389e 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -324,6 +324,8 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_PWC2 v4l2_fourcc('P', 'W', 'C', '2') /* pwc newer webcam */ #define V4L2_PIX_FMT_ET61X251 v4l2_fourcc('E', '6', '2', '5') /* ET61X251 compression */ #define V4L2_PIX_FMT_SPCA501 v4l2_fourcc('S', '5', '0', '1') /* YUYV per line */ +#define V4L2_PIX_FMT_SPCA505 v4l2_fourcc('S','5','0','5') /* YYUV per line */ +#define V4L2_PIX_FMT_SPCA508 v4l2_fourcc('S','5','0','8') /* YUVY per line */ #define V4L2_PIX_FMT_SPCA561 v4l2_fourcc('S', '5', '6', '1') /* compressed GBRG bayer */ #define V4L2_PIX_FMT_PAC207 v4l2_fourcc('P', '2', '0', '7') /* compressed BGGR bayer */ -- cgit v1.2.2 From c1d7f4f1648cb8efd87f1b9560c40af2297e7c05 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 26 Jul 2008 08:33:47 -0300 Subject: V4L/DVB (8524): videodev: copy the VID_TYPE defines to videodev.h The VID_TYPE defines are V4L1 specific, so copy them back to videodev.h. In videodev2.h ensure that they are not used in the kernel (you need to include videodev.h instead) and mark them are deprecated. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev.h | 15 +++++++++++++++ include/linux/videodev2.h | 6 ++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/videodev.h b/include/linux/videodev.h index 9385a566aed8..15a653d41132 100644 --- a/include/linux/videodev.h +++ b/include/linux/videodev.h @@ -17,6 +17,21 @@ #if defined(CONFIG_VIDEO_V4L1_COMPAT) || !defined (__KERNEL__) +#define VID_TYPE_CAPTURE 1 /* Can capture */ +#define VID_TYPE_TUNER 2 /* Can tune */ +#define VID_TYPE_TELETEXT 4 /* Does teletext */ +#define VID_TYPE_OVERLAY 8 /* Overlay onto frame buffer */ +#define VID_TYPE_CHROMAKEY 16 /* Overlay by chromakey */ +#define VID_TYPE_CLIPPING 32 /* Can clip */ +#define VID_TYPE_FRAMERAM 64 /* Uses the frame buffer memory */ +#define VID_TYPE_SCALES 128 /* Scalable */ +#define VID_TYPE_MONOCHROME 256 /* Monochrome only */ +#define VID_TYPE_SUBCAPTURE 512 /* Can capture subareas of the image */ +#define VID_TYPE_MPEG_DECODER 1024 /* Can decode MPEG streams */ +#define VID_TYPE_MPEG_ENCODER 2048 /* Can encode MPEG streams */ +#define VID_TYPE_MJPEG_DECODER 4096 /* Can decode MJPEG streams */ +#define VID_TYPE_MJPEG_ENCODER 8192 /* Can encode MJPEG streams */ + struct video_capability { char name[32]; diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 7d9ac046389e..f7195351a1e7 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -71,6 +71,11 @@ */ #define VIDEO_MAX_FRAME 32 +#ifndef __KERNEL__ + +/* These defines are V4L1 specific and should not be used with the V4L2 API! + They will be removed from this header in the future. */ + #define VID_TYPE_CAPTURE 1 /* Can capture */ #define VID_TYPE_TUNER 2 /* Can tune */ #define VID_TYPE_TELETEXT 4 /* Does teletext */ @@ -85,6 +90,7 @@ #define VID_TYPE_MPEG_ENCODER 2048 /* Can encode MPEG streams */ #define VID_TYPE_MJPEG_DECODER 4096 /* Can decode MJPEG streams */ #define VID_TYPE_MJPEG_ENCODER 8192 /* Can encode MJPEG streams */ +#endif /* * M I S C E L L A N E O U S -- cgit v1.2.2 From 9fa0f6db3a201bef49f28e69f80802559a38586b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 27 Jul 2008 08:55:17 -0300 Subject: V4L/DVB (8522): videodev2: Fix merge conflict Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index f7195351a1e7..e466bd54a50e 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -330,8 +330,8 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_PWC2 v4l2_fourcc('P', 'W', 'C', '2') /* pwc newer webcam */ #define V4L2_PIX_FMT_ET61X251 v4l2_fourcc('E', '6', '2', '5') /* ET61X251 compression */ #define V4L2_PIX_FMT_SPCA501 v4l2_fourcc('S', '5', '0', '1') /* YUYV per line */ -#define V4L2_PIX_FMT_SPCA505 v4l2_fourcc('S','5','0','5') /* YYUV per line */ -#define V4L2_PIX_FMT_SPCA508 v4l2_fourcc('S','5','0','8') /* YUVY per line */ +#define V4L2_PIX_FMT_SPCA505 v4l2_fourcc('S', '5', '0', '5') /* YYUV per line */ +#define V4L2_PIX_FMT_SPCA508 v4l2_fourcc('S', '5', '0', '8') /* YUVY per line */ #define V4L2_PIX_FMT_SPCA561 v4l2_fourcc('S', '5', '6', '1') /* compressed GBRG bayer */ #define V4L2_PIX_FMT_PAC207 v4l2_fourcc('P', '2', '0', '7') /* compressed BGGR bayer */ -- cgit v1.2.2 From 5995477ab7f3522c497c9c4a1c55373e9d655574 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Sun, 27 Jul 2008 17:29:15 +0200 Subject: task IO accounting: improve code readability Put all i/o statistics in struct proc_io_accounting and use inline functions to initialize and increment statistics, removing a lot of single variable assignments. This also reduces the kernel size as following (with CONFIG_TASK_XACCT=y and CONFIG_TASK_IO_ACCOUNTING=y). text data bss dec hex filename 11651 0 0 11651 2d83 kernel/exit.o.before 11619 0 0 11619 2d63 kernel/exit.o.after 10886 132 136 11154 2b92 kernel/fork.o.before 10758 132 136 11026 2b12 kernel/fork.o.after 3082029 807968 4818600 8708597 84e1f5 vmlinux.o.before 3081869 807968 4818600 8708437 84e155 vmlinux.o.after Signed-off-by: Andrea Righi Acked-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- include/linux/sched.h | 19 ++++-------- include/linux/task_io_accounting.h | 27 ++++++++++++++-- include/linux/task_io_accounting_ops.h | 56 ++++++++++++++++++++++++++++------ 3 files changed, 76 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f59318a0099b..034c1ca6b332 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -505,10 +505,7 @@ struct signal_struct { unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; -#ifdef CONFIG_TASK_XACCT - u64 rchar, wchar, syscr, syscw; -#endif - struct task_io_accounting ioac; + struct proc_io_accounting ioac; /* * Cumulative ns of scheduled CPU time for dead threads in the @@ -1256,11 +1253,7 @@ struct task_struct { unsigned long ptrace_message; siginfo_t *last_siginfo; /* For ptrace use. */ -#ifdef CONFIG_TASK_XACCT -/* i/o counters(bytes read/written, #syscalls */ - u64 rchar, wchar, syscr, syscw; -#endif - struct task_io_accounting ioac; + struct proc_io_accounting ioac; #if defined(CONFIG_TASK_XACCT) u64 acct_rss_mem1; /* accumulated rss usage */ u64 acct_vm_mem1; /* accumulated virtual memory usage */ @@ -2190,22 +2183,22 @@ extern long sched_group_rt_period(struct task_group *tg); #ifdef CONFIG_TASK_XACCT static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { - tsk->rchar += amt; + tsk->ioac.chr.rchar += amt; } static inline void add_wchar(struct task_struct *tsk, ssize_t amt) { - tsk->wchar += amt; + tsk->ioac.chr.wchar += amt; } static inline void inc_syscr(struct task_struct *tsk) { - tsk->syscr++; + tsk->ioac.chr.syscr++; } static inline void inc_syscw(struct task_struct *tsk) { - tsk->syscw++; + tsk->ioac.chr.syscw++; } #else static inline void add_rchar(struct task_struct *tsk, ssize_t amt) diff --git a/include/linux/task_io_accounting.h b/include/linux/task_io_accounting.h index 44d00e9cceea..165390f8b936 100644 --- a/include/linux/task_io_accounting.h +++ b/include/linux/task_io_accounting.h @@ -1,5 +1,5 @@ /* - * task_io_accounting: a structure which is used for recording a single task's + * proc_io_accounting: a structure which is used for recording a single task's * IO statistics. * * Don't include this header file directly - it is designed to be dragged in via @@ -8,6 +8,22 @@ * Blame akpm@osdl.org for all this. */ +#ifdef CONFIG_TASK_XACCT +struct task_chr_io_accounting { + /* bytes read */ + u64 rchar; + /* bytes written */ + u64 wchar; + /* # of read syscalls */ + u64 syscr; + /* # of write syscalls */ + u64 syscw; +}; +#else /* CONFIG_TASK_XACCT */ +struct task_chr_io_accounting { +}; +#endif /* CONFIG_TASK_XACCT */ + #ifdef CONFIG_TASK_IO_ACCOUNTING struct task_io_accounting { /* @@ -31,7 +47,12 @@ struct task_io_accounting { */ u64 cancelled_write_bytes; }; -#else +#else /* CONFIG_TASK_IO_ACCOUNTING */ struct task_io_accounting { }; -#endif +#endif /* CONFIG_TASK_IO_ACCOUNTING */ + +struct proc_io_accounting { + struct task_chr_io_accounting chr; + struct task_io_accounting blk; +}; diff --git a/include/linux/task_io_accounting_ops.h b/include/linux/task_io_accounting_ops.h index ff46c6fad79d..e6f958ebe97f 100644 --- a/include/linux/task_io_accounting_ops.h +++ b/include/linux/task_io_accounting_ops.h @@ -9,7 +9,7 @@ #ifdef CONFIG_TASK_IO_ACCOUNTING static inline void task_io_account_read(size_t bytes) { - current->ioac.read_bytes += bytes; + current->ioac.blk.read_bytes += bytes; } /* @@ -18,12 +18,12 @@ static inline void task_io_account_read(size_t bytes) */ static inline unsigned long task_io_get_inblock(const struct task_struct *p) { - return p->ioac.read_bytes >> 9; + return p->ioac.blk.read_bytes >> 9; } static inline void task_io_account_write(size_t bytes) { - current->ioac.write_bytes += bytes; + current->ioac.blk.write_bytes += bytes; } /* @@ -32,17 +32,25 @@ static inline void task_io_account_write(size_t bytes) */ static inline unsigned long task_io_get_oublock(const struct task_struct *p) { - return p->ioac.write_bytes >> 9; + return p->ioac.blk.write_bytes >> 9; } static inline void task_io_account_cancelled_write(size_t bytes) { - current->ioac.cancelled_write_bytes += bytes; + current->ioac.blk.cancelled_write_bytes += bytes; } -static inline void task_io_accounting_init(struct task_struct *tsk) +static inline void task_io_accounting_init(struct proc_io_accounting *ioac) { - memset(&tsk->ioac, 0, sizeof(tsk->ioac)); + memset(ioac, 0, sizeof(*ioac)); +} + +static inline void task_blk_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) +{ + dst->blk.read_bytes += src->blk.read_bytes; + dst->blk.write_bytes += src->blk.write_bytes; + dst->blk.cancelled_write_bytes += src->blk.cancelled_write_bytes; } #else @@ -69,9 +77,37 @@ static inline void task_io_account_cancelled_write(size_t bytes) { } -static inline void task_io_accounting_init(struct task_struct *tsk) +static inline void task_io_accounting_init(struct proc_io_accounting *ioac) +{ +} + +static inline void task_blk_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) { } -#endif /* CONFIG_TASK_IO_ACCOUNTING */ -#endif /* __TASK_IO_ACCOUNTING_OPS_INCLUDED */ +#endif /* CONFIG_TASK_IO_ACCOUNTING */ + +#ifdef CONFIG_TASK_XACCT +static inline void task_chr_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) +{ + dst->chr.rchar += src->chr.rchar; + dst->chr.wchar += src->chr.wchar; + dst->chr.syscr += src->chr.syscr; + dst->chr.syscw += src->chr.syscw; +} +#else +static inline void task_chr_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) +{ +} +#endif /* CONFIG_TASK_XACCT */ + +static inline void task_io_accounting_add(struct proc_io_accounting *dst, + struct proc_io_accounting *src) +{ + task_chr_io_accounting_add(dst, src); + task_blk_io_accounting_add(dst, src); +} +#endif /* __TASK_IO_ACCOUNTING_OPS_INCLUDED */ -- cgit v1.2.2 From 940389b8afad6495211614c13eb91ef7001773ec Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Mon, 28 Jul 2008 00:48:12 +0200 Subject: task IO accounting: move all IO statistics in struct task_io_accounting Simplify the code of include/linux/task_io_accounting.h. It is also more reasonable to have all the task i/o-related statistics in a single struct (task_io_accounting). Signed-off-by: Andrea Righi Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- include/linux/sched.h | 12 ++++----- include/linux/task_io_accounting.h | 17 ++---------- include/linux/task_io_accounting_ops.h | 48 +++++++++++++++++----------------- 3 files changed, 32 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 034c1ca6b332..5270d449ff9d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -505,7 +505,7 @@ struct signal_struct { unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; - struct proc_io_accounting ioac; + struct task_io_accounting ioac; /* * Cumulative ns of scheduled CPU time for dead threads in the @@ -1253,7 +1253,7 @@ struct task_struct { unsigned long ptrace_message; siginfo_t *last_siginfo; /* For ptrace use. */ - struct proc_io_accounting ioac; + struct task_io_accounting ioac; #if defined(CONFIG_TASK_XACCT) u64 acct_rss_mem1; /* accumulated rss usage */ u64 acct_vm_mem1; /* accumulated virtual memory usage */ @@ -2183,22 +2183,22 @@ extern long sched_group_rt_period(struct task_group *tg); #ifdef CONFIG_TASK_XACCT static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { - tsk->ioac.chr.rchar += amt; + tsk->ioac.rchar += amt; } static inline void add_wchar(struct task_struct *tsk, ssize_t amt) { - tsk->ioac.chr.wchar += amt; + tsk->ioac.wchar += amt; } static inline void inc_syscr(struct task_struct *tsk) { - tsk->ioac.chr.syscr++; + tsk->ioac.syscr++; } static inline void inc_syscw(struct task_struct *tsk) { - tsk->ioac.chr.syscw++; + tsk->ioac.syscw++; } #else static inline void add_rchar(struct task_struct *tsk, ssize_t amt) diff --git a/include/linux/task_io_accounting.h b/include/linux/task_io_accounting.h index 165390f8b936..5e88afc9a2fb 100644 --- a/include/linux/task_io_accounting.h +++ b/include/linux/task_io_accounting.h @@ -1,5 +1,5 @@ /* - * proc_io_accounting: a structure which is used for recording a single task's + * task_io_accounting: a structure which is used for recording a single task's * IO statistics. * * Don't include this header file directly - it is designed to be dragged in via @@ -8,8 +8,8 @@ * Blame akpm@osdl.org for all this. */ +struct task_io_accounting { #ifdef CONFIG_TASK_XACCT -struct task_chr_io_accounting { /* bytes read */ u64 rchar; /* bytes written */ @@ -18,14 +18,9 @@ struct task_chr_io_accounting { u64 syscr; /* # of write syscalls */ u64 syscw; -}; -#else /* CONFIG_TASK_XACCT */ -struct task_chr_io_accounting { -}; #endif /* CONFIG_TASK_XACCT */ #ifdef CONFIG_TASK_IO_ACCOUNTING -struct task_io_accounting { /* * The number of bytes which this task has caused to be read from * storage. @@ -46,13 +41,5 @@ struct task_io_accounting { * information loss in doing that. */ u64 cancelled_write_bytes; -}; -#else /* CONFIG_TASK_IO_ACCOUNTING */ -struct task_io_accounting { -}; #endif /* CONFIG_TASK_IO_ACCOUNTING */ - -struct proc_io_accounting { - struct task_chr_io_accounting chr; - struct task_io_accounting blk; }; diff --git a/include/linux/task_io_accounting_ops.h b/include/linux/task_io_accounting_ops.h index e6f958ebe97f..4d090f9ee608 100644 --- a/include/linux/task_io_accounting_ops.h +++ b/include/linux/task_io_accounting_ops.h @@ -9,7 +9,7 @@ #ifdef CONFIG_TASK_IO_ACCOUNTING static inline void task_io_account_read(size_t bytes) { - current->ioac.blk.read_bytes += bytes; + current->ioac.read_bytes += bytes; } /* @@ -18,12 +18,12 @@ static inline void task_io_account_read(size_t bytes) */ static inline unsigned long task_io_get_inblock(const struct task_struct *p) { - return p->ioac.blk.read_bytes >> 9; + return p->ioac.read_bytes >> 9; } static inline void task_io_account_write(size_t bytes) { - current->ioac.blk.write_bytes += bytes; + current->ioac.write_bytes += bytes; } /* @@ -32,25 +32,25 @@ static inline void task_io_account_write(size_t bytes) */ static inline unsigned long task_io_get_oublock(const struct task_struct *p) { - return p->ioac.blk.write_bytes >> 9; + return p->ioac.write_bytes >> 9; } static inline void task_io_account_cancelled_write(size_t bytes) { - current->ioac.blk.cancelled_write_bytes += bytes; + current->ioac.cancelled_write_bytes += bytes; } -static inline void task_io_accounting_init(struct proc_io_accounting *ioac) +static inline void task_io_accounting_init(struct task_io_accounting *ioac) { memset(ioac, 0, sizeof(*ioac)); } -static inline void task_blk_io_accounting_add(struct proc_io_accounting *dst, - struct proc_io_accounting *src) +static inline void task_blk_io_accounting_add(struct task_io_accounting *dst, + struct task_io_accounting *src) { - dst->blk.read_bytes += src->blk.read_bytes; - dst->blk.write_bytes += src->blk.write_bytes; - dst->blk.cancelled_write_bytes += src->blk.cancelled_write_bytes; + dst->read_bytes += src->read_bytes; + dst->write_bytes += src->write_bytes; + dst->cancelled_write_bytes += src->cancelled_write_bytes; } #else @@ -77,35 +77,35 @@ static inline void task_io_account_cancelled_write(size_t bytes) { } -static inline void task_io_accounting_init(struct proc_io_accounting *ioac) +static inline void task_io_accounting_init(struct task_io_accounting *ioac) { } -static inline void task_blk_io_accounting_add(struct proc_io_accounting *dst, - struct proc_io_accounting *src) +static inline void task_blk_io_accounting_add(struct task_io_accounting *dst, + struct task_io_accounting *src) { } #endif /* CONFIG_TASK_IO_ACCOUNTING */ #ifdef CONFIG_TASK_XACCT -static inline void task_chr_io_accounting_add(struct proc_io_accounting *dst, - struct proc_io_accounting *src) +static inline void task_chr_io_accounting_add(struct task_io_accounting *dst, + struct task_io_accounting *src) { - dst->chr.rchar += src->chr.rchar; - dst->chr.wchar += src->chr.wchar; - dst->chr.syscr += src->chr.syscr; - dst->chr.syscw += src->chr.syscw; + dst->rchar += src->rchar; + dst->wchar += src->wchar; + dst->syscr += src->syscr; + dst->syscw += src->syscw; } #else -static inline void task_chr_io_accounting_add(struct proc_io_accounting *dst, - struct proc_io_accounting *src) +static inline void task_chr_io_accounting_add(struct task_io_accounting *dst, + struct task_io_accounting *src) { } #endif /* CONFIG_TASK_XACCT */ -static inline void task_io_accounting_add(struct proc_io_accounting *dst, - struct proc_io_accounting *src) +static inline void task_io_accounting_add(struct task_io_accounting *dst, + struct task_io_accounting *src) { task_chr_io_accounting_add(dst, src); task_blk_io_accounting_add(dst, src); -- cgit v1.2.2 From 5c2aed622571ac7c3c6ec182d6d3c318e4b45c8b Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Thu, 28 Feb 2008 11:33:03 -0500 Subject: stop_machine: add ALL_CPUS option -allow stop_mahcine_run() to call a function on all cpus. Calling stop_machine_run() with a 'ALL_CPUS' invokes this new behavior. stop_machine_run() proceeds as normal until the calling cpu has invoked 'fn'. Then, we tell all the other cpus to call 'fn'. Signed-off-by: Jason Baron Signed-off-by: Mathieu Desnoyers Signed-off-by: Rusty Russell CC: Adrian Bunk CC: Andi Kleen CC: Alexey Dobriyan CC: Christoph Hellwig CC: mingo@elte.hu CC: akpm@osdl.org --- include/linux/stop_machine.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 5bfc553bdb21..18af011c13af 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -8,11 +8,17 @@ #include #if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP) + +#define ALL_CPUS ~0U + /** * stop_machine_run: freeze the machine on all CPUs and run this function * @fn: the function to run * @data: the data ptr for the @fn() - * @cpu: the cpu to run @fn() on (or any, if @cpu == NR_CPUS. + * @cpu: if @cpu == n, run @fn() on cpu n + * if @cpu == NR_CPUS, run @fn() on any cpu + * if @cpu == ALL_CPUS, run @fn() first on the calling cpu, and then + * concurrently on all the other cpus * * Description: This causes a thread to be scheduled on every other cpu, * each of which disables interrupts, and finally interrupts are disabled -- cgit v1.2.2 From ffdb5976c47609c862917d4c186ecbb5706d2dda Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 28 Jul 2008 12:16:28 -0500 Subject: Simplify stop_machine stop_machine creates a kthread which creates kernel threads. We can create those threads directly and simplify things a little. Some care must be taken with CPU hotunplug, which has special needs, but that code seems more robust than it was in the past. Signed-off-by: Rusty Russell Acked-by: Christian Borntraeger --- include/linux/stop_machine.h | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 18af011c13af..36c2c7284eb3 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -17,13 +17,12 @@ * @data: the data ptr for the @fn() * @cpu: if @cpu == n, run @fn() on cpu n * if @cpu == NR_CPUS, run @fn() on any cpu - * if @cpu == ALL_CPUS, run @fn() first on the calling cpu, and then - * concurrently on all the other cpus + * if @cpu == ALL_CPUS, run @fn() on every online CPU. * - * Description: This causes a thread to be scheduled on every other cpu, - * each of which disables interrupts, and finally interrupts are disabled - * on the current CPU. The result is that noone is holding a spinlock - * or inside any other preempt-disabled region when @fn() runs. + * Description: This causes a thread to be scheduled on every cpu, + * each of which disables interrupts. The result is that noone is + * holding a spinlock or inside any other preempt-disabled region when + * @fn() runs. * * This can be thought of as a very heavy write lock, equivalent to * grabbing every spinlock in the kernel. */ @@ -35,13 +34,10 @@ int stop_machine_run(int (*fn)(void *), void *data, unsigned int cpu); * @data: the data ptr for the @fn * @cpu: the cpu to run @fn on (or any, if @cpu == NR_CPUS. * - * Description: This is a special version of the above, which returns the - * thread which has run @fn(): kthread_stop will return the return value - * of @fn(). Used by hotplug cpu. + * Description: This is a special version of the above, which assumes cpus + * won't come or go while it's being called. Used by hotplug cpu. */ -struct task_struct *__stop_machine_run(int (*fn)(void *), void *data, - unsigned int cpu); - +int __stop_machine_run(int (*fn)(void *), void *data, unsigned int cpu); #else static inline int stop_machine_run(int (*fn)(void *), void *data, -- cgit v1.2.2 From eeec4fad963490821348a331cca6102ae1c4a7a3 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 28 Jul 2008 12:16:30 -0500 Subject: stop_machine(): stop_machine_run() changed to use cpu mask Instead of a "cpu" arg with magic values NR_CPUS (any cpu) and ~0 (all cpus), pass a cpumask_t. Allow NULL for the common case (where we don't care which CPU the function is run on): temporary cpumask_t's are usually considered bad for stack space. This deprecates stop_machine_run, to be removed soon when all the callers are dead. Signed-off-by: Rusty Russell --- include/linux/stop_machine.h | 34 ++++++++++++++++++++++++---------- 1 file changed, 24 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 36c2c7284eb3..f1cb0ba6d715 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -5,19 +5,19 @@ (and more). So the "read" side to such a lock is anything which diables preeempt. */ #include +#include #include #if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP) +/* Deprecated, but useful for transition. */ #define ALL_CPUS ~0U /** - * stop_machine_run: freeze the machine on all CPUs and run this function + * stop_machine: freeze the machine on all CPUs and run this function * @fn: the function to run * @data: the data ptr for the @fn() - * @cpu: if @cpu == n, run @fn() on cpu n - * if @cpu == NR_CPUS, run @fn() on any cpu - * if @cpu == ALL_CPUS, run @fn() on every online CPU. + * @cpus: the cpus to run the @fn() on (NULL = any online cpu) * * Description: This causes a thread to be scheduled on every cpu, * each of which disables interrupts. The result is that noone is @@ -26,22 +26,22 @@ * * This can be thought of as a very heavy write lock, equivalent to * grabbing every spinlock in the kernel. */ -int stop_machine_run(int (*fn)(void *), void *data, unsigned int cpu); +int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus); /** - * __stop_machine_run: freeze the machine on all CPUs and run this function + * __stop_machine: freeze the machine on all CPUs and run this function * @fn: the function to run * @data: the data ptr for the @fn - * @cpu: the cpu to run @fn on (or any, if @cpu == NR_CPUS. + * @cpus: the cpus to run the @fn() on (NULL = any online cpu) * * Description: This is a special version of the above, which assumes cpus * won't come or go while it's being called. Used by hotplug cpu. */ -int __stop_machine_run(int (*fn)(void *), void *data, unsigned int cpu); +int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus); #else -static inline int stop_machine_run(int (*fn)(void *), void *data, - unsigned int cpu) +static inline int stop_machine(int (*fn)(void *), void *data, + const cpumask_t *cpus) { int ret; local_irq_disable(); @@ -50,4 +50,18 @@ static inline int stop_machine_run(int (*fn)(void *), void *data, return ret; } #endif /* CONFIG_SMP */ + +static inline int __deprecated stop_machine_run(int (*fn)(void *), void *data, + unsigned int cpu) +{ + /* If they don't care which cpu fn runs on, just pick one. */ + if (cpu == NR_CPUS) + return stop_machine(fn, data, NULL); + else if (cpu == ~0U) + return stop_machine(fn, data, &cpu_possible_map); + else { + cpumask_t cpus = cpumask_of_cpu(cpu); + return stop_machine(fn, data, &cpus); + } +} #endif /* _LINUX_STOP_MACHINE */ -- cgit v1.2.2 From 9403540c0653122ca34884a180439ddbfcbcb524 Mon Sep 17 00:00:00 2001 From: Barry Naujok Date: Wed, 21 May 2008 16:50:46 +1000 Subject: dcache: Add case-insensitive support d_ci_add() routine This add a dcache entry to the dcache for lookup, but changing the name that is associated with the entry rather than the one passed in to the lookup routine. First, it sees if the case-exact match already exists in the dcache and uses it if one exists. Otherwise, it allocates a new node with the new name and splices it into the dcache. Original code from ntfs_lookup in fs/ntfs/namei.c by Anton Altaparmakov. Signed-off-by: Barry Naujok Signed-off-by: Anton Altaparmakov Acked-by: Christoph Hellwig --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 98202c672fde..07aa198f19ed 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -230,6 +230,7 @@ extern void d_delete(struct dentry *); extern struct dentry * d_alloc(struct dentry *, const struct qstr *); extern struct dentry * d_alloc_anon(struct inode *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); +extern struct dentry * d_add_ci(struct inode *, struct dentry *, struct qstr *); extern void shrink_dcache_sb(struct super_block *); extern void shrink_dcache_parent(struct dentry *); extern void shrink_dcache_for_umount(struct super_block *); -- cgit v1.2.2 From 306cfd630a4d121cf4e08b894d8b4c4cf106e57e Mon Sep 17 00:00:00 2001 From: Adrian McMenamin Date: Sun, 15 Jun 2008 20:48:09 +0100 Subject: maple: tidy maple_driver code by removing redundant connect/disconnect The connect and disconnect functions are unnecessary - everything they do can be accomplished in the initial probe - so remove them. Signed-off-by: Adrian McMenamin Signed-off-by: Paul Mundt --- include/linux/maple.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/maple.h b/include/linux/maple.h index d31e36ebb436..523a286bb477 100644 --- a/include/linux/maple.h +++ b/include/linux/maple.h @@ -61,8 +61,6 @@ struct maple_device { struct maple_driver { unsigned long function; - int (*connect) (struct maple_device * dev); - void (*disconnect) (struct maple_device * dev); struct device_driver drv; }; -- cgit v1.2.2 From 7f71ac9374fec066e428892a68db158946cee1fb Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Mon, 28 Jul 2008 18:29:09 +0200 Subject: mfd: Coding style fixes Fix some coding style fixes in the mfd core driver. Signed-off-by: Ben Dooks Signed-off-by: Samuel Ortiz --- include/linux/mfd/core.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index bb3dd0545928..b7cbb9968339 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -1,5 +1,3 @@ -#ifndef MFD_CORE_H -#define MFD_CORE_H /* * drivers/mfd/mfd-core.h * @@ -13,6 +11,9 @@ * */ +#ifndef MFD_CORE_H +#define MFD_CORE_H + #include /* @@ -38,17 +39,15 @@ struct mfd_cell { const struct resource *resources; }; -static inline struct mfd_cell * -mfd_get_cell(struct platform_device *pdev) +static inline struct mfd_cell *mfd_get_cell(struct platform_device *pdev) { return (struct mfd_cell *)pdev->dev.platform_data; } -extern int mfd_add_devices( - struct platform_device *parent, - const struct mfd_cell *cells, int n_devs, - struct resource *mem_base, - int irq_base); +extern int mfd_add_devices(struct platform_device *parent, + const struct mfd_cell *cells, int n_devs, + struct resource *mem_base, + int irq_base); extern void mfd_remove_devices(struct platform_device *parent); -- cgit v1.2.2 From e56b3bc7942982ac2589c942fb345e38bc7a341a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 28 Jul 2008 11:32:33 -0700 Subject: cpu masks: optimize and clean up cpumask_of_cpu() Clean up and optimize cpumask_of_cpu(), by sharing all the zero words. Instead of stupidly generating all possible i=0...NR_CPUS 2^i patterns creating a huge array of constant bitmasks, realize that the zero words can be shared. In other words, on a 64-bit architecture, we only ever need 64 of these arrays - with a different bit set in one single world (with enough zero words around it so that we can create any bitmask by just offsetting in that big array). And then we just put enough zeroes around it that we can point every single cpumask to be one of those things. So when we have 4k CPU's, instead of having 4k arrays (of 4k bits each, with one bit set in each array - 2MB memory total), we have exactly 64 arrays instead, each 8k bits in size (64kB total). And then we just point cpumask(n) to the right position (which we can calculate dynamically). Once we have the right arrays, getting "cpumask(n)" ends up being: static inline const cpumask_t *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; return (const cpumask_t *)p; } This brings other advantages and simplifications as well: - we are not wasting memory that is just filled with a single bit in various different places - we don't need all those games to re-create the arrays in some dense format, because they're already going to be dense enough. if we compile a kernel for up to 4k CPU's, "wasting" that 64kB of memory is a non-issue (especially since by doing this "overlapping" trick we probably get better cache behaviour anyway). [ mingo@elte.hu: Converted Linus's mails into a commit. See: http://lkml.org/lkml/2008/7/27/156 http://lkml.org/lkml/2008/7/28/320 Also applied a family filter - which also has the side-effect of leaving out the bits where Linus calls me an idio... Oh, never mind ;-) ] Signed-off-by: Ingo Molnar Cc: Rusty Russell Cc: Andrew Morton Cc: Al Viro Cc: Mike Travis Signed-off-by: Ingo Molnar --- include/linux/cpumask.h | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 8fa3b6d4a320..96d0509fb8d8 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -265,10 +265,30 @@ static inline void __cpus_shift_left(cpumask_t *dstp, bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); } +/* + * Special-case data structure for "single bit set only" constant CPU masks. + * + * We pre-generate all the 64 (or 32) possible bit positions, with enough + * padding to the left and the right, and return the constant pointer + * appropriately offset. + */ +extern const unsigned long + cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; + +static inline const cpumask_t *get_cpu_mask(unsigned int cpu) +{ + const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; + p -= cpu / BITS_PER_LONG; + return (const cpumask_t *)p; +} + +/* + * In cases where we take the address of the cpumask immediately, + * gcc optimizes it out (it's a constant) and there's no huge stack + * variable created: + */ +#define cpumask_of_cpu(cpu) ({ *get_cpu_mask(cpu); }) -/* cpumask_of_cpu_map[] is in kernel/cpu.c */ -extern const cpumask_t *cpumask_of_cpu_map; -#define cpumask_of_cpu(cpu) (cpumask_of_cpu_map[cpu]) #define CPU_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(NR_CPUS) -- cgit v1.2.2 From 5fde244d39b88625ac578d83e6625138714de031 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 23 Jul 2008 10:32:24 +0800 Subject: PCI: disable ASPM per ACPI FADT setting The ACPI FADT table includes an ASPM control bit. If the bit is set, do not enable ASPM since it may indicate that the platform doesn't actually support the feature. Tested-by: Jack Howarth Signed-off-by: Shaohua Li Signed-off-by: Jesse Barnes --- include/linux/pci-aspm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-aspm.h b/include/linux/pci-aspm.h index a1a1e618e996..91ba0b338b47 100644 --- a/include/linux/pci-aspm.h +++ b/include/linux/pci-aspm.h @@ -27,6 +27,7 @@ extern void pcie_aspm_init_link_state(struct pci_dev *pdev); extern void pcie_aspm_exit_link_state(struct pci_dev *pdev); extern void pcie_aspm_pm_state_change(struct pci_dev *pdev); extern void pci_disable_link_state(struct pci_dev *pdev, int state); +extern void pcie_no_aspm(void); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { @@ -40,6 +41,10 @@ static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) static inline void pci_disable_link_state(struct pci_dev *pdev, int state) { } + +static inline void pcie_no_aspm(void) +{ +} #endif #ifdef CONFIG_PCIEASPM_DEBUG /* this depends on CONFIG_PCIEASPM */ -- cgit v1.2.2 From 149e16372a2066c5474d8a8db9b252afd57eb427 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 23 Jul 2008 10:32:31 +0800 Subject: PCI: disable ASPM on pre-1.1 PCIe devices Disable ASPM on pre-1.1 PCIe devices, as many of them don't implement it correctly. Tested-by: Jack Howarth Signed-off-by: Shaohua Li Signed-off-by: Jesse Barnes --- include/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index 19958b929905..450684f7eaac 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -374,6 +374,7 @@ #define PCI_EXP_DEVCAP_ATN_BUT 0x1000 /* Attention Button Present */ #define PCI_EXP_DEVCAP_ATN_IND 0x2000 /* Attention Indicator Present */ #define PCI_EXP_DEVCAP_PWR_IND 0x4000 /* Power Indicator Present */ +#define PCI_EXP_DEVCAP_RBER 0x8000 /* Role-Based Error Reporting */ #define PCI_EXP_DEVCAP_PWR_VAL 0x3fc0000 /* Slot Power Limit Value */ #define PCI_EXP_DEVCAP_PWR_SCL 0xc000000 /* Slot Power Limit Scale */ #define PCI_EXP_DEVCTL 8 /* Device Control */ -- cgit v1.2.2 From 979b1791e5b8f8b556faeec4c48339e7ed63af9f Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Thu, 24 Jul 2008 17:18:38 +0100 Subject: PCI: add D3 power state avoidance quirk Libata has some hacks to deal with certain controllers going silly in D3 state. The right way to handle this is to keep a PCI device flag for such devices. That can then be generalised for no ATA devices with power problems. Signed-off-by: Alan Cox Signed-off-by: Jesse Barnes --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 1d296d31abe0..825be3878f68 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -124,6 +124,8 @@ enum pci_dev_flags { * generation too. */ PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG = (__force pci_dev_flags_t) 1, + /* Device configuration is irrevocably lost if disabled into D3 */ + PCI_DEV_FLAGS_NO_D3 = (__force pci_dev_flags_t) 2, }; typedef unsigned short __bitwise pci_bus_flags_t; -- cgit v1.2.2 From 56edb58be157a06dc147a988af3588059556d392 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 29 Jul 2008 01:23:32 +0200 Subject: mfd: add platform_data to mfd_cell Adding platform_data to mfd_cell allows passing of platform data directly to the platform_device created for each cell and thus reuse of existing drivers. On the other side it can be used as a hook to mfd_cell itself removing the need in mfd_get_cell method. Signed-off-by: Mike Rapoport Acked-by: Dmitry Baryshkov Signed-off-by: Samuel Ortiz --- include/linux/mfd/core.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index b7cbb9968339..ea45d4a5a2ac 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -29,7 +29,13 @@ struct mfd_cell { int (*suspend)(struct platform_device *dev); int (*resume)(struct platform_device *dev); - void *driver_data; /* driver-specific data */ + /* driver-specific data for MFD-aware "cell" drivers */ + void *driver_data; + + /* platform_data can be used to either pass data to "generic" + driver or as a hook to mfd_cell for the "cell" drivers */ + void *platform_data; + size_t data_size; /* * This resources can be specified relatievly to the parent device. @@ -39,11 +45,6 @@ struct mfd_cell { const struct resource *resources; }; -static inline struct mfd_cell *mfd_get_cell(struct platform_device *pdev) -{ - return (struct mfd_cell *)pdev->dev.platform_data; -} - extern int mfd_add_devices(struct platform_device *parent, const struct mfd_cell *cells, int n_devs, struct resource *mem_base, -- cgit v1.2.2 From 6beeac76f5f96590fb751af5e138fbc3f62e8460 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Mon, 28 Jul 2008 15:46:22 -0700 Subject: mmu-notifiers: add list_del_init_rcu() Introduce list_del_init_rcu() and document it. Signed-off-by: Andrea Arcangeli Acked-by: Linus Torvalds Cc: "Paul E. McKenney" Cc: Ingo Molnar Cc: Christoph Lameter Cc: Jack Steiner Cc: Robin Holt Cc: Nick Piggin Cc: Peter Zijlstra Cc: Kanoj Sarcar Cc: Roland Dreier Cc: Steve Wise Cc: Avi Kivity Cc: Hugh Dickins Cc: Rusty Russell Cc: Anthony Liguori Cc: Chris Wright Cc: Marcelo Tosatti Cc: Eric Dumazet Cc: "Paul E. McKenney" Cc: Izik Eidus Cc: Anthony Liguori Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rculist.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index b0f39be08b6c..eb4443c7e05b 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -97,6 +97,34 @@ static inline void list_del_rcu(struct list_head *entry) entry->prev = LIST_POISON2; } +/** + * hlist_del_init_rcu - deletes entry from hash list with re-initialization + * @n: the element to delete from the hash list. + * + * Note: list_unhashed() on the node return true after this. It is + * useful for RCU based read lockfree traversal if the writer side + * must know if the list entry is still hashed or already unhashed. + * + * In particular, it means that we can not poison the forward pointers + * that may still be used for walking the hash list and we can only + * zero the pprev pointer so list_unhashed() will return true after + * this. + * + * The caller must take whatever precautions are necessary (such as + * holding appropriate locks) to avoid racing with another + * list-mutation primitive, such as hlist_add_head_rcu() or + * hlist_del_rcu(), running on this same list. However, it is + * perfectly legal to run concurrently with the _rcu list-traversal + * primitives, such as hlist_for_each_entry_rcu(). + */ +static inline void hlist_del_init_rcu(struct hlist_node *n) +{ + if (!hlist_unhashed(n)) { + __hlist_del(n); + n->pprev = NULL; + } +} + /** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced -- cgit v1.2.2 From 7906d00cd1f687268f0a3599442d113767795ae6 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Mon, 28 Jul 2008 15:46:26 -0700 Subject: mmu-notifiers: add mm_take_all_locks() operation mm_take_all_locks holds off reclaim from an entire mm_struct. This allows mmu notifiers to register into the mm at any time with the guarantee that no mmu operation is in progress on the mm. This operation locks against the VM for all pte/vma/mm related operations that could ever happen on a certain mm. This includes vmtruncate, try_to_unmap, and all page faults. The caller must take the mmap_sem in write mode before calling mm_take_all_locks(). The caller isn't allowed to release the mmap_sem until mm_drop_all_locks() returns. mmap_sem in write mode is required in order to block all operations that could modify pagetables and free pages without need of altering the vma layout (for example populate_range() with nonlinear vmas). It's also needed in write mode to avoid new anon_vmas to be associated with existing vmas. A single task can't take more than one mm_take_all_locks() in a row or it would deadlock. mm_take_all_locks() and mm_drop_all_locks are expensive operations that may have to take thousand of locks. mm_take_all_locks() can fail if it's interrupted by signals. When mmu_notifier_register returns, we must be sure that the driver is notified if some task is in the middle of a vmtruncate for the 'mm' where the mmu notifier was registered (mmu_notifier_invalidate_range_start/end is run around the vmtruncation but mmu_notifier_register can run after mmu_notifier_invalidate_range_start and before mmu_notifier_invalidate_range_end). Same problem for rmap paths. And we've to remove page pinning to avoid replicating the tlb_gather logic inside KVM (and GRU doesn't work well with page pinning regardless of needing tlb_gather), so without mm_take_all_locks when vmtruncate frees the page, kvm would have no way to notice that it mapped into sptes a page that is going into the freelist without a chance of any further mmu_notifier notification. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Andrea Arcangeli Acked-by: Linus Torvalds Cc: Christoph Lameter Cc: Jack Steiner Cc: Robin Holt Cc: Nick Piggin Cc: Peter Zijlstra Cc: Kanoj Sarcar Cc: Roland Dreier Cc: Steve Wise Cc: Avi Kivity Cc: Hugh Dickins Cc: Rusty Russell Cc: Anthony Liguori Cc: Chris Wright Cc: Marcelo Tosatti Cc: Eric Dumazet Cc: "Paul E. McKenney" Cc: Izik Eidus Cc: Anthony Liguori Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ include/linux/pagemap.h | 1 + include/linux/rmap.h | 8 ++++++++ 3 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6e695eaab4ce..866a3dbe5c75 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1104,6 +1104,9 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff); extern void exit_mmap(struct mm_struct *); +extern int mm_take_all_locks(struct mm_struct *mm); +extern void mm_drop_all_locks(struct mm_struct *mm); + #ifdef CONFIG_PROC_FS /* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */ extern void added_exe_file_vma(struct mm_struct *mm); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a81d81890422..a39b38ccdc97 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -20,6 +20,7 @@ */ #define AS_EIO (__GFP_BITS_SHIFT + 0) /* IO error on async write */ #define AS_ENOSPC (__GFP_BITS_SHIFT + 1) /* ENOSPC on async write */ +#define AS_MM_ALL_LOCKS (__GFP_BITS_SHIFT + 2) /* under mm_take_all_locks() */ static inline void mapping_set_error(struct address_space *mapping, int error) { diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 1383692ac5bd..69407f85e10b 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -26,6 +26,14 @@ */ struct anon_vma { spinlock_t lock; /* Serialize access to vma list */ + /* + * NOTE: the LSB of the head.next is set by + * mm_take_all_locks() _after_ taking the above lock. So the + * head must only be read/written after taking the above lock + * to be sure to see a valid next pointer. The LSB bit itself + * is serialized by a system wide lock only visible to + * mm_take_all_locks() (mm_all_locks_mutex). + */ struct list_head head; /* List of private "related" vmas */ }; -- cgit v1.2.2 From cddb8a5c14aa89810b40495d94d3d2a0faee6619 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Mon, 28 Jul 2008 15:46:29 -0700 Subject: mmu-notifiers: core With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages. There are secondary MMUs (with secondary sptes and secondary tlbs) too. sptes in the kvm case are shadow pagetables, but when I say spte in mmu-notifier context, I mean "secondary pte". In GRU case there's no actual secondary pte and there's only a secondary tlb because the GRU secondary MMU has no knowledge about sptes and every secondary tlb miss event in the MMU always generates a page fault that has to be resolved by the CPU (this is not the case of KVM where the a secondary tlb miss will walk sptes in hardware and it will refill the secondary tlb transparently to software if the corresponding spte is present). The same way zap_page_range has to invalidate the pte before freeing the page, the spte (and secondary tlb) must also be invalidated before any page is freed and reused. Currently we take a page_count pin on every page mapped by sptes, but that means the pages can't be swapped whenever they're mapped by any spte because they're part of the guest working set. Furthermore a spte unmap event can immediately lead to a page to be freed when the pin is released (so requiring the same complex and relatively slow tlb_gather smp safe logic we have in zap_page_range and that can be avoided completely if the spte unmap event doesn't require an unpin of the page previously mapped in the secondary MMU). The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know when the VM is swapping or freeing or doing anything on the primary MMU so that the secondary MMU code can drop sptes before the pages are freed, avoiding all page pinning and allowing 100% reliable swapping of guest physical address space. Furthermore it avoids the code that teardown the mappings of the secondary MMU, to implement a logic like tlb_gather in zap_page_range that would require many IPI to flush other cpu tlbs, for each fixed number of spte unmapped. To make an example: if what happens on the primary MMU is a protection downgrade (from writeable to wrprotect) the secondary MMU mappings will be invalidated, and the next secondary-mmu-page-fault will call get_user_pages and trigger a do_wp_page through get_user_pages if it called get_user_pages with write=1, and it'll re-establishing an updated spte or secondary-tlb-mapping on the copied page. Or it will setup a readonly spte or readonly tlb mapping if it's a guest-read, if it calls get_user_pages with write=0. This is just an example. This allows to map any page pointed by any pte (and in turn visible in the primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an full MMU with both sptes and secondary-tlb like the shadow-pagetable layer with kvm), or a remote DMA in software like XPMEM (hence needing of schedule in XPMEM code to send the invalidate to the remote node, while no need to schedule in kvm/gru as it's an immediate event like invalidating primary-mmu pte). At least for KVM without this patch it's impossible to swap guests reliably. And having this feature and removing the page pin allows several other optimizations that simplify life considerably. Dependencies: 1) mm_take_all_locks() to register the mmu notifier when the whole VM isn't doing anything with "mm". This allows mmu notifier users to keep track if the VM is in the middle of the invalidate_range_begin/end critical section with an atomic counter incraese in range_begin and decreased in range_end. No secondary MMU page fault is allowed to map any spte or secondary tlb reference, while the VM is in the middle of range_begin/end as any page returned by get_user_pages in that critical section could later immediately be freed without any further ->invalidate_page notification (invalidate_range_begin/end works on ranges and ->invalidate_page isn't called immediately before freeing the page). To stop all page freeing and pagetable overwrites the mmap_sem must be taken in write mode and all other anon_vma/i_mmap locks must be taken too. 2) It'd be a waste to add branches in the VM if nobody could possibly run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if CONFIG_KVM=m/y. In the current kernel kvm won't yet take advantage of mmu notifiers, but this already allows to compile a KVM external module against a kernel with mmu notifiers enabled and from the next pull from kvm.git we'll start using them. And GRU/XPMEM will also be able to continue the development by enabling KVM=m in their config, until they submit all GRU/XPMEM GPLv2 code to the mainline kernel. Then they can also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n). This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM are all =n. The mmu_notifier_register call can fail because mm_take_all_locks may be interrupted by a signal and return -EINTR. Because mmu_notifier_reigster is used when a driver startup, a failure can be gracefully handled. Here an example of the change applied to kvm to register the mmu notifiers. Usually when a driver startups other allocations are required anyway and -ENOMEM failure paths exists already. struct kvm *kvm_arch_create_vm(void) { struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + int err; if (!kvm) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops; + err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm); + if (err) { + kfree(kvm); + return ERR_PTR(err); + } + return kvm; } mmu_notifier_unregister returns void and it's reliable. The patch also adds a few needed but missing includes that would prevent kernel to compile after these changes on non-x86 archs (x86 didn't need them by luck). [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix mm/filemap_xip.c build] [akpm@linux-foundation.org: fix mm/mmu_notifier.c build] Signed-off-by: Andrea Arcangeli Signed-off-by: Nick Piggin Signed-off-by: Christoph Lameter Cc: Jack Steiner Cc: Robin Holt Cc: Nick Piggin Cc: Peter Zijlstra Cc: Kanoj Sarcar Cc: Roland Dreier Cc: Steve Wise Cc: Avi Kivity Cc: Hugh Dickins Cc: Rusty Russell Cc: Anthony Liguori Cc: Chris Wright Cc: Marcelo Tosatti Cc: Eric Dumazet Cc: "Paul E. McKenney" Cc: Izik Eidus Cc: Anthony Liguori Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 4 + include/linux/mmu_notifier.h | 279 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 283 insertions(+) create mode 100644 include/linux/mmu_notifier.h (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 746f975b58ef..386edbe2cb4e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -253,6 +254,9 @@ struct mm_struct { struct file *exe_file; unsigned long num_exe_file_vmas; #endif +#ifdef CONFIG_MMU_NOTIFIER + struct mmu_notifier_mm *mmu_notifier_mm; +#endif }; #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h new file mode 100644 index 000000000000..b77486d152cd --- /dev/null +++ b/include/linux/mmu_notifier.h @@ -0,0 +1,279 @@ +#ifndef _LINUX_MMU_NOTIFIER_H +#define _LINUX_MMU_NOTIFIER_H + +#include +#include +#include + +struct mmu_notifier; +struct mmu_notifier_ops; + +#ifdef CONFIG_MMU_NOTIFIER + +/* + * The mmu notifier_mm structure is allocated and installed in + * mm->mmu_notifier_mm inside the mm_take_all_locks() protected + * critical section and it's released only when mm_count reaches zero + * in mmdrop(). + */ +struct mmu_notifier_mm { + /* all mmu notifiers registerd in this mm are queued in this list */ + struct hlist_head list; + /* to serialize the list modifications and hlist_unhashed */ + spinlock_t lock; +}; + +struct mmu_notifier_ops { + /* + * Called either by mmu_notifier_unregister or when the mm is + * being destroyed by exit_mmap, always before all pages are + * freed. This can run concurrently with other mmu notifier + * methods (the ones invoked outside the mm context) and it + * should tear down all secondary mmu mappings and freeze the + * secondary mmu. If this method isn't implemented you've to + * be sure that nothing could possibly write to the pages + * through the secondary mmu by the time the last thread with + * tsk->mm == mm exits. + * + * As side note: the pages freed after ->release returns could + * be immediately reallocated by the gart at an alias physical + * address with a different cache model, so if ->release isn't + * implemented because all _software_ driven memory accesses + * through the secondary mmu are terminated by the time the + * last thread of this mm quits, you've also to be sure that + * speculative _hardware_ operations can't allocate dirty + * cachelines in the cpu that could not be snooped and made + * coherent with the other read and write operations happening + * through the gart alias address, so leading to memory + * corruption. + */ + void (*release)(struct mmu_notifier *mn, + struct mm_struct *mm); + + /* + * clear_flush_young is called after the VM is + * test-and-clearing the young/accessed bitflag in the + * pte. This way the VM will provide proper aging to the + * accesses to the page through the secondary MMUs and not + * only to the ones through the Linux pte. + */ + int (*clear_flush_young)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long address); + + /* + * Before this is invoked any secondary MMU is still ok to + * read/write to the page previously pointed to by the Linux + * pte because the page hasn't been freed yet and it won't be + * freed until this returns. If required set_page_dirty has to + * be called internally to this method. + */ + void (*invalidate_page)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long address); + + /* + * invalidate_range_start() and invalidate_range_end() must be + * paired and are called only when the mmap_sem and/or the + * locks protecting the reverse maps are held. The subsystem + * must guarantee that no additional references are taken to + * the pages in the range established between the call to + * invalidate_range_start() and the matching call to + * invalidate_range_end(). + * + * Invalidation of multiple concurrent ranges may be + * optionally permitted by the driver. Either way the + * establishment of sptes is forbidden in the range passed to + * invalidate_range_begin/end for the whole duration of the + * invalidate_range_begin/end critical section. + * + * invalidate_range_start() is called when all pages in the + * range are still mapped and have at least a refcount of one. + * + * invalidate_range_end() is called when all pages in the + * range have been unmapped and the pages have been freed by + * the VM. + * + * The VM will remove the page table entries and potentially + * the page between invalidate_range_start() and + * invalidate_range_end(). If the page must not be freed + * because of pending I/O or other circumstances then the + * invalidate_range_start() callback (or the initial mapping + * by the driver) must make sure that the refcount is kept + * elevated. + * + * If the driver increases the refcount when the pages are + * initially mapped into an address space then either + * invalidate_range_start() or invalidate_range_end() may + * decrease the refcount. If the refcount is decreased on + * invalidate_range_start() then the VM can free pages as page + * table entries are removed. If the refcount is only + * droppped on invalidate_range_end() then the driver itself + * will drop the last refcount but it must take care to flush + * any secondary tlb before doing the final free on the + * page. Pages will no longer be referenced by the linux + * address space but may still be referenced by sptes until + * the last refcount is dropped. + */ + void (*invalidate_range_start)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, unsigned long end); + void (*invalidate_range_end)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, unsigned long end); +}; + +/* + * The notifier chains are protected by mmap_sem and/or the reverse map + * semaphores. Notifier chains are only changed when all reverse maps and + * the mmap_sem locks are taken. + * + * Therefore notifier chains can only be traversed when either + * + * 1. mmap_sem is held. + * 2. One of the reverse map locks is held (i_mmap_lock or anon_vma->lock). + * 3. No other concurrent thread can access the list (release) + */ +struct mmu_notifier { + struct hlist_node hlist; + const struct mmu_notifier_ops *ops; +}; + +static inline int mm_has_notifiers(struct mm_struct *mm) +{ + return unlikely(mm->mmu_notifier_mm); +} + +extern int mmu_notifier_register(struct mmu_notifier *mn, + struct mm_struct *mm); +extern int __mmu_notifier_register(struct mmu_notifier *mn, + struct mm_struct *mm); +extern void mmu_notifier_unregister(struct mmu_notifier *mn, + struct mm_struct *mm); +extern void __mmu_notifier_mm_destroy(struct mm_struct *mm); +extern void __mmu_notifier_release(struct mm_struct *mm); +extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address); +extern void __mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address); +extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end); +extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end); + +static inline void mmu_notifier_release(struct mm_struct *mm) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_release(mm); +} + +static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address) +{ + if (mm_has_notifiers(mm)) + return __mmu_notifier_clear_flush_young(mm, address); + return 0; +} + +static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_page(mm, address); +} + +static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_range_start(mm, start, end); +} + +static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_range_end(mm, start, end); +} + +static inline void mmu_notifier_mm_init(struct mm_struct *mm) +{ + mm->mmu_notifier_mm = NULL; +} + +static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_mm_destroy(mm); +} + +/* + * These two macros will sometime replace ptep_clear_flush. + * ptep_clear_flush is impleemnted as macro itself, so this also is + * implemented as a macro until ptep_clear_flush will converted to an + * inline function, to diminish the risk of compilation failure. The + * invalidate_page method over time can be moved outside the PT lock + * and these two macros can be later removed. + */ +#define ptep_clear_flush_notify(__vma, __address, __ptep) \ +({ \ + pte_t __pte; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __pte = ptep_clear_flush(___vma, ___address, __ptep); \ + mmu_notifier_invalidate_page(___vma->vm_mm, ___address); \ + __pte; \ +}) + +#define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ +({ \ + int __young; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __young = ptep_clear_flush_young(___vma, ___address, __ptep); \ + __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ + ___address); \ + __young; \ +}) + +#else /* CONFIG_MMU_NOTIFIER */ + +static inline void mmu_notifier_release(struct mm_struct *mm) +{ +} + +static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address) +{ + return 0; +} + +static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address) +{ +} + +static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ +} + +static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ +} + +static inline void mmu_notifier_mm_init(struct mm_struct *mm) +{ +} + +static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) +{ +} + +#define ptep_clear_flush_young_notify ptep_clear_flush_young +#define ptep_clear_flush_notify ptep_clear_flush + +#endif /* CONFIG_MMU_NOTIFIER */ + +#endif /* _LINUX_MMU_NOTIFIER_H */ -- cgit v1.2.2 From 8ab22b9abb5c55413802e4adc9aa6223324547c3 Mon Sep 17 00:00:00 2001 From: Hisashi Hifumi Date: Mon, 28 Jul 2008 15:46:36 -0700 Subject: vfs: pagecache usage optimization for pagesize!=blocksize When we read some part of a file through pagecache, if there is a pagecache of corresponding index but this page is not uptodate, read IO is issued and this page will be uptodate. I think this is good for pagesize == blocksize environment but there is room for improvement on pagesize != blocksize environment. Because in this case a page can have multiple buffers and even if a page is not uptodate, some buffers can be uptodate. So I suggest that when all buffers which correspond to a part of a file that we want to read are uptodate, use this pagecache and copy data from this pagecache to user buffer even if a page is not uptodate. This can reduce read IO and improve system throughput. I wrote a benchmark program and got result number with this program. This benchmark do: 1: mount and open a test file. 2: create a 512MB file. 3: close a file and umount. 4: mount and again open a test file. 5: pwrite randomly 300000 times on a test file. offset is aligned by IO size(1024bytes). 6: measure time of preading randomly 100000 times on a test file. The result was: 2.6.26 330 sec 2.6.26-patched 226 sec Arch:i386 Filesystem:ext3 Blocksize:1024 bytes Memory: 1GB On ext3/4, a file is written through buffer/block. So random read/write mixed workloads or random read after random write workloads are optimized with this patch under pagesize != blocksize environment. This test result showed this. The benchmark program is as follows: #include #include #include #include #include #include #include #include #include #define LEN 1024 #define LOOP 1024*512 /* 512MB */ main(void) { unsigned long i, offset, filesize; int fd; char buf[LEN]; time_t t1, t2; if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } memset(buf, 0, LEN); fd = open("/root/test1/testfile", O_CREAT|O_RDWR|O_TRUNC); if (fd < 0) { perror("cannot open file\n"); exit(1); } for (i = 0; i < LOOP; i++) write(fd, buf, LEN); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } fd = open("/root/test1/testfile", O_RDWR); if (fd < 0) { perror("cannot open file\n"); exit(1); } filesize = LEN * LOOP; for (i = 0; i < 300000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pwrite(fd, buf, LEN, offset); } printf("start test\n"); time(&t1); for (i = 0; i < 100000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pread(fd, buf, LEN, offset); } time(&t2); printf("%ld sec\n", t2-t1); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } } Signed-off-by: Hisashi Hifumi Cc: Nick Piggin Cc: Christoph Hellwig Cc: Jan Kara Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/buffer_head.h | 2 ++ include/linux/fs.h | 44 +++++++++++++++++++++++--------------------- 2 files changed, 25 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 82aa36c53ea7..50cfe8ceb478 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -205,6 +205,8 @@ void block_invalidatepage(struct page *page, unsigned long offset); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); 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(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 8252b045e624..580b513668fe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -443,6 +443,27 @@ static inline size_t iov_iter_count(struct iov_iter *i) return i->count; } +/* + * "descriptor" for what we're up to with a read. + * This allows us to use the same read code yet + * have multiple different users of the data that + * we read from a file. + * + * The simplest case just copies the data to user + * mode. + */ +typedef struct { + size_t written; + size_t count; + union { + char __user *buf; + void *data; + } arg; + int error; +} read_descriptor_t; + +typedef int (*read_actor_t)(read_descriptor_t *, struct page *, + unsigned long, unsigned long); struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); @@ -484,6 +505,8 @@ struct address_space_operations { int (*migratepage) (struct address_space *, struct page *, struct page *); int (*launder_page) (struct page *); + int (*is_partially_uptodate) (struct page *, read_descriptor_t *, + unsigned long); }; /* @@ -1198,27 +1221,6 @@ struct block_device_operations { struct module *owner; }; -/* - * "descriptor" for what we're up to with a read. - * This allows us to use the same read code yet - * have multiple different users of the data that - * we read from a file. - * - * The simplest case just copies the data to user - * mode. - */ -typedef struct { - size_t written; - size_t count; - union { - char __user * buf; - void *data; - } arg; - int error; -} read_descriptor_t; - -typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long); - /* These macros are for out of kernel modules to test that * the kernel supports the unlocked_ioctl and compat_ioctl * fields in struct file_operations. */ -- cgit v1.2.2 From 424f525a1241351da947fb48a938128ddd774511 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Tue, 29 Jul 2008 01:30:26 +0200 Subject: mfd: accept pure device as a parent, not only platform_device Signed-off-by: Dmitry Baryshkov Signed-off-by: Samuel Ortiz --- include/linux/mfd/core.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index ea45d4a5a2ac..49ef857cdb2d 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -45,11 +45,11 @@ struct mfd_cell { const struct resource *resources; }; -extern int mfd_add_devices(struct platform_device *parent, +extern int mfd_add_devices(struct device *parent, int id, const struct mfd_cell *cells, int n_devs, struct resource *mem_base, int irq_base); -extern void mfd_remove_devices(struct platform_device *parent); +extern void mfd_remove_devices(struct device *parent); #endif -- cgit v1.2.2 From e930bffe95e1e886a1ede80726ea38df5838d067 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 25 Jul 2008 16:24:52 +0200 Subject: KVM: Synchronize guest physical memory map to host virtual memory map Synchronize changes to host virtual addresses which are part of a KVM memory slot to the KVM shadow mmu. This allows pte operations like swapping, page migration, and madvise() to transparently work with KVM. Signed-off-by: Andrea Arcangeli Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 07d68a8ae8e9..8525afc53107 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -121,6 +121,12 @@ struct kvm { struct kvm_coalesced_mmio_dev *coalesced_mmio_dev; struct kvm_coalesced_mmio_ring *coalesced_mmio_ring; #endif + +#ifdef KVM_ARCH_WANT_MMU_NOTIFIER + struct mmu_notifier mmu_notifier; + unsigned long mmu_notifier_seq; + long mmu_notifier_count; +#endif }; /* The guest did something we don't support. */ @@ -332,4 +338,22 @@ int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg) #define kvm_trace_cleanup() ((void)0) #endif +#ifdef KVM_ARCH_WANT_MMU_NOTIFIER +static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_seq) +{ + if (unlikely(vcpu->kvm->mmu_notifier_count)) + return 1; + /* + * Both reads happen under the mmu_lock and both values are + * modified under mmu_lock, so there's no need of smb_rmb() + * here in between, otherwise mmu_notifier_count should be + * read before mmu_notifier_seq, see + * mmu_notifier_invalidate_range_end write side. + */ + if (vcpu->kvm->mmu_notifier_seq != mmu_seq) + return 1; + return 0; +} +#endif + #endif -- cgit v1.2.2 From ed8486243379ef3e6c61363df915882945c0eaec Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Tue, 29 Jul 2008 11:30:57 +0300 Subject: KVM: Advertise synchronized mmu support to userspace 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 0ea064cbfbc8..69511f74f912 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -371,6 +371,7 @@ struct kvm_trace_rec { #define KVM_CAP_PV_MMU 13 #define KVM_CAP_MP_STATE 14 #define KVM_CAP_COALESCED_MMIO 15 +#define KVM_CAP_SYNC_MMU 16 /* Changes to host mmap are reflected in guest */ /* * ioctls for VM fds -- cgit v1.2.2 From 8978b74253280d59e97cf49a3ec2c0cbccd5b801 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 29 Jul 2008 13:38:53 +0900 Subject: generic, x86: fix add iommu_num_pages helper function This IOMMU helper function doesn't work for some architectures: http://marc.info/?l=linux-kernel&m=121699304403202&w=2 It also breaks POWER and SPARC builds: http://marc.info/?l=linux-kernel&m=121730388001890&w=2 Currently, only x86 IOMMUs use this so let's move it to x86 for now. Reported-by: Stephen Rothwell Signed-off-by: FUJITA Tomonori Signed-off-by: Ingo Molnar --- include/linux/iommu-helper.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu-helper.h b/include/linux/iommu-helper.h index f8598f583944..c975caf75385 100644 --- a/include/linux/iommu-helper.h +++ b/include/linux/iommu-helper.h @@ -8,4 +8,3 @@ extern unsigned long iommu_area_alloc(unsigned long *map, unsigned long size, unsigned long align_mask); extern void iommu_area_free(unsigned long *map, unsigned long start, unsigned int nr); -extern unsigned long iommu_num_pages(unsigned long addr, unsigned long len); -- cgit v1.2.2 From 1795cf48b322b4d19230a40dbe7181acedd34a94 Mon Sep 17 00:00:00 2001 From: Adrian McMenamin Date: Tue, 29 Jul 2008 22:10:56 +0900 Subject: sh/maple: clean maple bus code This patch cleans up the handling of the maple bus queue to remove the risk of races when adding packets. It also removes references to the redundant connect and disconnect functions. Signed-off-by: Adrian McMenamin Signed-off-by: Paul Mundt --- include/linux/maple.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/maple.h b/include/linux/maple.h index 523a286bb477..c853b1066018 100644 --- a/include/linux/maple.h +++ b/include/linux/maple.h @@ -2,6 +2,7 @@ #define __LINUX_MAPLE_H #include +#include extern struct bus_type maple_bus_type; @@ -33,6 +34,7 @@ struct mapleq { void *sendbuf, *recvbuf, *recvbufdcsp; unsigned char length; enum maple_code command; + struct mutex mutex; }; struct maple_devinfo { @@ -69,7 +71,9 @@ void maple_getcond_callback(struct maple_device *dev, unsigned long interval, unsigned long function); int maple_driver_register(struct device_driver *drv); -void maple_add_packet(struct mapleq *mq); +int maple_add_packet_sleeps(struct maple_device *mdev, u32 function, + u32 command, u32 length, void *data); +void maple_clear_dev(struct maple_device *mdev); #define to_maple_dev(n) container_of(n, struct maple_device, dev) #define to_maple_driver(n) container_of(n, struct maple_driver, drv) -- cgit v1.2.2 From f1b23361a0f15497d4c6795a2935b2e98064ddfb Mon Sep 17 00:00:00 2001 From: Henrique de Moraes Holschuh Date: Mon, 21 Jul 2008 21:18:19 -0300 Subject: rfkill: document the rfkill struct locking (v2) Reorder fields in struct rfkill and add comments to make it clear which fields are protected by rfkill->mutex. Signed-off-by: Henrique de Moraes Holschuh Acked-by: Ivo van Doorn Signed-off-by: John W. Linville --- include/linux/rfkill.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index c5f6e54ec6ae..741d1a62cc3f 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -68,7 +68,8 @@ enum rfkill_state { * @user_claim_unsupported: Whether the hardware supports exclusive * RF-kill control by userspace. Set this before registering. * @user_claim: Set when the switch is controlled exlusively by userspace. - * @mutex: Guards switch state transitions + * @mutex: Guards switch state transitions. It serializes callbacks + * and also protects the state. * @data: Pointer to the RF button drivers private data which will be * passed along when toggling radio state. * @toggle_radio(): Mandatory handler to control state of the radio. @@ -89,12 +90,13 @@ struct rfkill { const char *name; enum rfkill_type type; - enum rfkill_state state; bool user_claim_unsupported; bool user_claim; + /* the mutex serializes callbacks and also protects + * the state */ struct mutex mutex; - + enum rfkill_state state; void *data; int (*toggle_radio)(void *data, enum rfkill_state state); int (*get_state)(void *data, enum rfkill_state *state); -- cgit v1.2.2 From d0f09804144fd9471a13cf4d80e66842c7fa114f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 29 Jul 2008 11:32:07 +0200 Subject: mac80211: partially fix skb->cb use This patch fixes mac80211 to not use the skb->cb over the queue step from virtual interfaces to the master. The patch also, for now, disables aggregation because that would still require requeuing, will fix that in a separate patch. There are two other places (software requeue and powersaving stations) where requeue can happen, but that is not currently used by any drivers/not possible to use respectively. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/skbuff.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7ea44f6621f2..a640385e0598 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -316,7 +316,10 @@ struct sk_buff { #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif - /* 14 bit hole */ +#if defined(CONFIG_MAC80211) || defined(CONFIG_MAC80211_MODULE) + __u8 do_not_encrypt:1; +#endif + /* 0/13/14 bit hole */ #ifdef CONFIG_NET_DMA dma_cookie_t dma_cookie; -- cgit v1.2.2 From ce0ad7f0952581ba75ab6aee55bb1ed9bb22cf4f Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 30 Jul 2008 15:23:13 +1000 Subject: powerpc/mm: Lockless get_user_pages_fast() for 64-bit (v3) Implement lockless get_user_pages_fast for 64-bit powerpc. Page table existence is guaranteed with RCU, and speculative page references are used to take a reference to the pages without having a prior existence guarantee on them. Signed-off-by: Nick Piggin Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Benjamin Herrenschmidt --- include/linux/pagemap.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a39b38ccdc97..69ed3cb1197a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -143,6 +143,29 @@ static inline int page_cache_get_speculative(struct page *page) return 1; } +/* + * Same as above, but add instead of inc (could just be merged) + */ +static inline int page_cache_add_speculative(struct page *page, int count) +{ + VM_BUG_ON(in_interrupt()); + +#if !defined(CONFIG_SMP) && defined(CONFIG_CLASSIC_RCU) +# ifdef CONFIG_PREEMPT + VM_BUG_ON(!in_atomic()); +# endif + VM_BUG_ON(page_count(page) == 0); + atomic_add(count, &page->_count); + +#else + if (unlikely(!atomic_add_unless(&page->_count, count, 0))) + return 0; +#endif + VM_BUG_ON(PageCompound(page) && page != compound_head(page)); + + return 1; +} + static inline int page_freeze_refs(struct page *page, int count) { return likely(atomic_cmpxchg(&page->_count, count, 0) == count); -- cgit v1.2.2 From e2ce4eaa76214f65a3f328ec5b45c30248115768 Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Wed, 30 Apr 2008 15:10:07 +0100 Subject: regulator: consumer device interface Add support to allow consumer device drivers to control their regulator power supply. This uses a similar API to the kernel clock interface in that consumer drivers can get and put a regulator (like they can with clocks atm) and get/set voltage, current limit, mode, enable and disable. This should allow consumers complete control over their supply voltage and current limit. This also compiles out if not in use so drivers can be reused in systems with no regulator based power control. Signed-off-by: Liam Girdwood Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 284 +++++++++++++++++++++++++++++++++++++ 1 file changed, 284 insertions(+) create mode 100644 include/linux/regulator/consumer.h (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h new file mode 100644 index 000000000000..afdc4558bb94 --- /dev/null +++ b/include/linux/regulator/consumer.h @@ -0,0 +1,284 @@ +/* + * consumer.h -- SoC Regulator consumer support. + * + * Copyright (C) 2007, 2008 Wolfson Microelectronics PLC. + * + * Author: Liam Girdwood + * + * 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. + * + * Regulator Consumer Interface. + * + * A Power Management Regulator framework for SoC based devices. + * Features:- + * o Voltage and current level control. + * o Operating mode control. + * o Regulator status. + * o sysfs entries for showing client devices and status + * + * EXPERIMENTAL FEATURES: + * Dynamic Regulator operating Mode Switching (DRMS) - allows regulators + * to use most efficient operating mode depending upon voltage and load and + * is transparent to client drivers. + * + * e.g. Devices x,y,z share regulator r. Device x and y draw 20mA each during + * IO and 1mA at idle. Device z draws 100mA when under load and 5mA when + * idling. Regulator r has > 90% efficiency in NORMAL mode at loads > 100mA + * but this drops rapidly to 60% when below 100mA. Regulator r has > 90% + * efficiency in IDLE mode at loads < 10mA. Thus regulator r will operate + * in normal mode for loads > 10mA and in IDLE mode for load <= 10mA. + * + */ + +#ifndef __LINUX_REGULATOR_CONSUMER_H_ +#define __LINUX_REGULATOR_CONSUMER_H_ + +/* + * Regulator operating modes. + * + * Regulators can run in a variety of different operating modes depending on + * output load. This allows further system power savings by selecting the + * best (and most efficient) regulator mode for a desired load. + * + * Most drivers will only care about NORMAL. The modes below are generic and + * will probably not match the naming convention of your regulator data sheet + * but should match the use cases in the datasheet. + * + * In order of power efficiency (least efficient at top). + * + * Mode Description + * FAST Regulator can handle fast changes in it's load. + * e.g. useful in CPU voltage & frequency scaling where + * load can quickly increase with CPU frequency increases. + * + * NORMAL Normal regulator power supply mode. Most drivers will + * use this mode. + * + * IDLE Regulator runs in a more efficient mode for light + * loads. Can be used for devices that have a low power + * requirement during periods of inactivity. This mode + * may be more noisy than NORMAL and may not be able + * to handle fast load switching. + * + * STANDBY Regulator runs in the most efficient mode for very + * light loads. Can be used by devices when they are + * in a sleep/standby state. This mode is likely to be + * the most noisy and may not be able to handle fast load + * switching. + * + * NOTE: Most regulators will only support a subset of these modes. Some + * will only just support NORMAL. + * + * These modes can be OR'ed together to make up a mask of valid register modes. + */ + +#define REGULATOR_MODE_FAST 0x1 +#define REGULATOR_MODE_NORMAL 0x2 +#define REGULATOR_MODE_IDLE 0x4 +#define REGULATOR_MODE_STANDBY 0x8 + +/* + * Regulator notifier events. + * + * UNDER_VOLTAGE Regulator output is under voltage. + * OVER_CURRENT Regulator output current is too high. + * REGULATION_OUT Regulator output is out of regulation. + * FAIL Regulator output has failed. + * OVER_TEMP Regulator over temp. + * FORCE_DISABLE Regulator shut down by software. + * + * NOTE: These events can be OR'ed together when passed into handler. + */ + +#define REGULATOR_EVENT_UNDER_VOLTAGE 0x01 +#define REGULATOR_EVENT_OVER_CURRENT 0x02 +#define REGULATOR_EVENT_REGULATION_OUT 0x04 +#define REGULATOR_EVENT_FAIL 0x08 +#define REGULATOR_EVENT_OVER_TEMP 0x10 +#define REGULATOR_EVENT_FORCE_DISABLE 0x20 + +struct regulator; + +/** + * struct regulator_bulk_data - Data used for bulk regulator operations. + * + * @supply The name of the supply. Initialised by the user before + * using the bulk regulator APIs. + * @consumer The regulator consumer for the supply. This will be managed + * by the bulk API. + * + * The regulator APIs provide a series of regulator_bulk_() API calls as + * a convenience to consumers which require multiple supplies. This + * structure is used to manage data for these calls. + */ +struct regulator_bulk_data { + const char *supply; + struct regulator *consumer; +}; + +#if defined(CONFIG_REGULATOR) + +/* regulator get and put */ +struct regulator *__must_check regulator_get(struct device *dev, + const char *id); +void regulator_put(struct regulator *regulator); + +/* regulator output control and status */ +int regulator_enable(struct regulator *regulator); +int regulator_disable(struct regulator *regulator); +int regulator_force_disable(struct regulator *regulator); +int regulator_is_enabled(struct regulator *regulator); + +int regulator_bulk_get(struct device *dev, int num_consumers, + struct regulator_bulk_data *consumers); +int regulator_bulk_enable(int num_consumers, + struct regulator_bulk_data *consumers); +int regulator_bulk_disable(int num_consumers, + struct regulator_bulk_data *consumers); +void regulator_bulk_free(int num_consumers, + struct regulator_bulk_data *consumers); + +int regulator_set_voltage(struct regulator *regulator, int min_uV, int max_uV); +int regulator_get_voltage(struct regulator *regulator); +int regulator_set_current_limit(struct regulator *regulator, + int min_uA, int max_uA); +int regulator_get_current_limit(struct regulator *regulator); + +int regulator_set_mode(struct regulator *regulator, unsigned int mode); +unsigned int regulator_get_mode(struct regulator *regulator); +int regulator_set_optimum_mode(struct regulator *regulator, int load_uA); + +/* regulator notifier block */ +int regulator_register_notifier(struct regulator *regulator, + struct notifier_block *nb); +int regulator_unregister_notifier(struct regulator *regulator, + struct notifier_block *nb); + +/* driver data - core doesn't touch */ +void *regulator_get_drvdata(struct regulator *regulator); +void regulator_set_drvdata(struct regulator *regulator, void *data); + +#else + +/* + * Make sure client drivers will still build on systems with no software + * controllable voltage or current regulators. + */ +static inline struct regulator *__must_check regulator_get(struct device *dev, + const char *id) +{ + /* Nothing except the stubbed out regulator API should be + * looking at the value except to check if it is an error + * value so the actual return value doesn't matter. + */ + return (struct regulator *)id; +} +static inline void regulator_put(struct regulator *regulator) +{ +} + +static inline int regulator_enable(struct regulator *regulator) +{ + return 0; +} + +static inline int regulator_disable(struct regulator *regulator) +{ + return 0; +} + +static inline int regulator_is_enabled(struct regulator *regulator) +{ + return 1; +} + +static inline int regulator_bulk_get(struct device *dev, + int num_consumers, + struct regulator_bulk_data *consumers) +{ + return 0; +} + +static inline int regulator_bulk_enable(int num_consumers, + struct regulator_bulk_data *consumers) +{ + return 0; +} + +static inline int regulator_bulk_disable(int num_consumers, + struct regulator_bulk_data *consumers) +{ + return 0; +} + +static inline void regulator_bulk_free(int num_consumers, + struct regulator_bulk_data *consumers) +{ +} + +static inline int regulator_set_voltage(struct regulator *regulator, + int min_uV, int max_uV) +{ + return 0; +} + +static inline int regulator_get_voltage(struct regulator *regulator) +{ + return 0; +} + +static inline int regulator_set_current_limit(struct regulator *regulator, + int min_uA, int max_uA) +{ + return 0; +} + +static inline int regulator_get_current_limit(struct regulator *regulator) +{ + return 0; +} + +static inline int regulator_set_mode(struct regulator *regulator, + unsigned int mode) +{ + return 0; +} + +static inline unsigned int regulator_get_mode(struct regulator *regulator) +{ + return REGULATOR_MODE_NORMAL; +} + +static inline int regulator_set_optimum_mode(struct regulator *regulator, + int load_uA) +{ + return REGULATOR_MODE_NORMAL; +} + +static inline int regulator_register_notifier(struct regulator *regulator, + struct notifier_block *nb) +{ + return 0; +} + +static inline int regulator_unregister_notifier(struct regulator *regulator, + struct notifier_block *nb) +{ + return 0; +} + +static inline void *regulator_get_drvdata(struct regulator *regulator) +{ + return NULL; +} + +static inline void regulator_set_drvdata(struct regulator *regulator, + void *data) +{ +} + +#endif + +#endif -- cgit v1.2.2 From 571a354b1542a274d88617e1f6703f3fe7a517f1 Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Wed, 30 Apr 2008 15:42:28 +0100 Subject: regulator: regulator driver interface This allows regulator drivers to register their regulators and provide operations to the core. It also has a notifier call chain for propagating regulator events to clients. Signed-off-by: Liam Girdwood Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 99 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) create mode 100644 include/linux/regulator/driver.h (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h new file mode 100644 index 000000000000..1d712c7172a2 --- /dev/null +++ b/include/linux/regulator/driver.h @@ -0,0 +1,99 @@ +/* + * driver.h -- SoC Regulator driver support. + * + * Copyright (C) 2007, 2008 Wolfson Microelectronics PLC. + * + * Author: Liam Girdwood + * + * 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. + * + * Regulator Driver Interface. + */ + +#ifndef __LINUX_REGULATOR_DRIVER_H_ +#define __LINUX_REGULATOR_DRIVER_H_ + +#include +#include + +struct regulator_constraints; +struct regulator_dev; + +/** + * struct regulator_ops - regulator operations. + * + * This struct describes regulator operations. + */ +struct regulator_ops { + + /* get/set regulator voltage */ + int (*set_voltage) (struct regulator_dev *, int min_uV, int max_uV); + int (*get_voltage) (struct regulator_dev *); + + /* get/set regulator current */ + int (*set_current_limit) (struct regulator_dev *, + int min_uA, int max_uA); + int (*get_current_limit) (struct regulator_dev *); + + /* enable/disable regulator */ + int (*enable) (struct regulator_dev *); + int (*disable) (struct regulator_dev *); + int (*is_enabled) (struct regulator_dev *); + + /* get/set regulator operating mode (defined in regulator.h) */ + int (*set_mode) (struct regulator_dev *, unsigned int mode); + unsigned int (*get_mode) (struct regulator_dev *); + + /* get most efficient regulator operating mode for load */ + unsigned int (*get_optimum_mode) (struct regulator_dev *, int input_uV, + int output_uV, int load_uA); + + /* the operations below are for configuration of regulator state when + * it's parent PMIC enters a global STANBY/HIBERNATE state */ + + /* set regulator suspend voltage */ + int (*set_suspend_voltage) (struct regulator_dev *, int uV); + + /* enable/disable regulator in suspend state */ + int (*set_suspend_enable) (struct regulator_dev *); + int (*set_suspend_disable) (struct regulator_dev *); + + /* set regulator suspend operating mode (defined in regulator.h) */ + int (*set_suspend_mode) (struct regulator_dev *, unsigned int mode); +}; + +/* + * Regulators can either control voltage or current. + */ +enum regulator_type { + REGULATOR_VOLTAGE, + REGULATOR_CURRENT, +}; + +/** + * struct regulator_desc - Regulator descriptor + * + */ +struct regulator_desc { + const char *name; + int id; + struct regulator_ops *ops; + int irq; + enum regulator_type type; + struct module *owner; +}; + + +struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc, + void *reg_data); +void regulator_unregister(struct regulator_dev *rdev); + +int regulator_notifier_call_chain(struct regulator_dev *rdev, + unsigned long event, void *data); + +void *rdev_get_drvdata(struct regulator_dev *rdev); +int rdev_get_id(struct regulator_dev *rdev); + +#endif -- cgit v1.2.2 From 4c1184e85cb381121a5273ea20ad31ca3faa0a4f Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Wed, 30 Apr 2008 15:46:09 +0100 Subject: regulator: machine driver interface This interface is for machine specific code and allows the creation of voltage/current domains (with constraints) for each regulator. It can provide regulator constraints that will prevent device damage through overvoltage or over current caused by buggy client drivers. It also allows the creation of a regulator tree whereby some regulators are supplied by others (similar to a clock tree). Signed-off-by: Liam Girdwood Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown --- include/linux/regulator/machine.h | 104 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 104 insertions(+) create mode 100644 include/linux/regulator/machine.h (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h new file mode 100644 index 000000000000..11e737dbfcf2 --- /dev/null +++ b/include/linux/regulator/machine.h @@ -0,0 +1,104 @@ +/* + * machine.h -- SoC Regulator support, machine/board driver API. + * + * Copyright (C) 2007, 2008 Wolfson Microelectronics PLC. + * + * Author: Liam Girdwood + * + * 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. + * + * Regulator Machine/Board Interface. + */ + +#ifndef __LINUX_REGULATOR_MACHINE_H_ +#define __LINUX_REGULATOR_MACHINE_H_ + +#include +#include + +struct regulator; + +/* + * Regulator operation constraint flags. These flags are used to enable + * certain regulator operations and can be OR'ed together. + * + * VOLTAGE: Regulator output voltage can be changed by software on this + * board/machine. + * CURRENT: Regulator output current can be changed by software on this + * board/machine. + * MODE: Regulator operating mode can be changed by software on this + * board/machine. + * STATUS: Regulator can be enabled and disabled. + * DRMS: Dynamic Regulator Mode Switching is enabled for this regulator. + */ + +#define REGULATOR_CHANGE_VOLTAGE 0x1 +#define REGULATOR_CHANGE_CURRENT 0x2 +#define REGULATOR_CHANGE_MODE 0x4 +#define REGULATOR_CHANGE_STATUS 0x8 +#define REGULATOR_CHANGE_DRMS 0x10 + +/** + * struct regulator_state - regulator state during low power syatem states + * + * This describes a regulators state during a system wide low power state. + */ +struct regulator_state { + int uV; /* suspend voltage */ + unsigned int mode; /* suspend regulator operating mode */ + int enabled; /* is regulator enabled in this suspend state */ +}; + +/** + * struct regulation_constraints - regulator operating constraints. + * + * This struct describes regulator and board/machine specific constraints. + */ +struct regulation_constraints { + + char *name; + + /* voltage output range (inclusive) - for voltage control */ + int min_uV; + int max_uV; + + /* current output range (inclusive) - for current control */ + int min_uA; + int max_uA; + + /* valid regulator operating modes for this machine */ + unsigned int valid_modes_mask; + + /* valid operations for regulator on this machine */ + unsigned int valid_ops_mask; + + /* regulator input voltage - only if supply is another regulator */ + int input_uV; + + /* regulator suspend states for global PMIC STANDBY/HIBERNATE */ + struct regulator_state state_disk; + struct regulator_state state_mem; + struct regulator_state state_standby; + suspend_state_t initial_state; /* suspend state to set at init */ + + /* constriant flags */ + unsigned always_on:1; /* regulator never off when system is on */ + unsigned boot_on:1; /* bootloader/firmware enabled regulator */ + unsigned apply_uV:1; /* apply uV constraint iff min == max */ +}; + +int regulator_set_supply(const char *regulator, const char *regulator_supply); + +const char *regulator_get_supply(const char *regulator); + +int regulator_set_machine_constraints(const char *regulator, + struct regulation_constraints *constraints); + +int regulator_set_device_supply(const char *regulator, struct device *dev, + const char *supply); + +int regulator_suspend_prepare(suspend_state_t state); + +#endif -- cgit v1.2.2 From 48d335ba3164ce99cb8847513d0e3b6ee604eb20 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 30 Apr 2008 15:50:21 +0100 Subject: regulator: fixed regulator interface This patch adds support for fixed regulators. This class of regulator is not software controllable but can coexist on machines with software controlable regulators. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/fixed.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 include/linux/regulator/fixed.h (limited to 'include/linux') diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h new file mode 100644 index 000000000000..1387a5d2190e --- /dev/null +++ b/include/linux/regulator/fixed.h @@ -0,0 +1,22 @@ +/* + * fixed.h + * + * Copyright 2008 Wolfson Microelectronics PLC. + * + * Author: Mark Brown + * + * 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 __REGULATOR_FIXED_H +#define __REGULATOR_FIXED_H + +struct fixed_voltage_config { + const char *supply_name; + int microvolts; +}; + +#endif -- cgit v1.2.2 From 0eb5d5ab3ec99bfd22ff16797d95835369ffb25b Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Fri, 11 Jul 2008 17:28:06 +0200 Subject: regulator: TI bq24022 Li-Ion Charger driver This adds a regulator driver for the TI bq24022 Single-Chip Li-Ion Charger with its nCE and ISET2 pins connected to GPIOs. Signed-off-by: Philipp Zabel Signed-off-by: Liam Girdwood --- include/linux/regulator/bq24022.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/regulator/bq24022.h (limited to 'include/linux') diff --git a/include/linux/regulator/bq24022.h b/include/linux/regulator/bq24022.h new file mode 100644 index 000000000000..e84b0a9feda5 --- /dev/null +++ b/include/linux/regulator/bq24022.h @@ -0,0 +1,21 @@ +/* + * Support for TI bq24022 (bqTINY-II) Dual Input (USB/AC Adpater) + * 1-Cell Li-Ion Charger connected via GPIOs. + * + * Copyright (c) 2008 Philipp Zabel + * + * 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. + * + */ + +/** + * bq24022_mach_info - platform data for bq24022 + * @gpio_nce: GPIO line connected to the nCE pin, used to enable / disable charging + * @gpio_iset2: GPIO line connected to the ISET2 pin, used to limit charging current to 100 mA / 500 mA + */ +struct bq24022_mach_info { + int gpio_nce; + int gpio_iset2; +}; -- cgit v1.2.2 From 785957d3e8c6fb37b18bf671923a76dbd8240025 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 30 Jul 2008 03:03:15 -0700 Subject: tcp: MD5: Use MIB counter instead of warning for MD5 mismatch. From a report by Matti Aarnio, and preliminary patch by Adam Langley. Signed-off-by: David S. Miller --- include/linux/snmp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 5df62ef1280c..7a6e6bba4a71 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -214,6 +214,8 @@ enum LINUX_MIB_TCPDSACKIGNOREDOLD, /* TCPSACKIgnoredOld */ LINUX_MIB_TCPDSACKIGNOREDNOUNDO, /* TCPSACKIgnoredNoUndo */ LINUX_MIB_TCPSPURIOUSRTOS, /* TCPSpuriousRTOs */ + LINUX_MIB_TCPMD5NOTFOUND, /* TCPMD5NotFound */ + LINUX_MIB_TCPMD5UNEXPECTED, /* TCPMD5Unexpected */ __LINUX_MIB_MAX }; -- cgit v1.2.2 From 96d8b647cfff90c8ff07863866aacdcd9d13cead Mon Sep 17 00:00:00 2001 From: Alexey Korolev Date: Tue, 29 Jul 2008 13:54:11 +0100 Subject: [MTD] [NAND] fix subpage read for small page NAND Current implementation of subpage read feature for NAND has issues with small page devices. Small page NAND do not support RNDOUT command. So subpage feature is not applicable for them. This patch disables support of subpage for small page NAND. The code is verified on nandsim(SP NAND simulation) and on LP NAND devices. Thanks a lot to Artem for finding this issue. Signed-off-by: Alexey Korolev Signed-off-by: Artem Bityutskiy 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 83f678702dff..81774e5facf4 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -177,7 +177,9 @@ typedef enum { #define NAND_MUST_PAD(chip) (!(chip->options & NAND_NO_PADDING)) #define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) #define NAND_HAS_COPYBACK(chip) ((chip->options & NAND_COPYBACK)) -#define NAND_SUBPAGE_READ(chip) ((chip->ecc.mode == NAND_ECC_SOFT)) +/* Large page NAND with SOFT_ECC should support subpage reads */ +#define NAND_SUBPAGE_READ(chip) ((chip->ecc.mode == NAND_ECC_SOFT) \ + && (chip->page_shift > 9)) /* Mask to zero out the chip options, which come from the id table */ #define NAND_CHIPOPTIONS_MSK (0x0000ffff & ~NAND_NO_AUTOINCR) -- cgit v1.2.2 From 95b1bc20532c18e3f19cd460c8350350c84ffbb2 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Tue, 29 Jul 2008 22:28:12 -0700 Subject: [MTD] MTD_DEBUG always does compile-time typechecks The current style for debug messages is to ensure they're always parsed by the compiler and then subjected to dead code removal. That way builds won't break only when debug options get enabled, which is common when they are stripped out early by CPP. This patch makes CONFIG_MTD_DEBUG adopt that convention. Signed-off-by: David Brownell Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 4ed40caff4e5..922636548558 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -272,7 +272,11 @@ static inline void mtd_erase_callback(struct erase_info *instr) printk(KERN_INFO args); \ } while(0) #else /* CONFIG_MTD_DEBUG */ -#define DEBUG(n, args...) do { } while(0) +#define DEBUG(n, args...) \ + do { \ + if (0) \ + printk(KERN_INFO args); \ + } while(0) #endif /* CONFIG_MTD_DEBUG */ -- cgit v1.2.2 From 1a4e564b7db999fbe5d88318c96ac8747699d417 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Tue, 29 Jul 2008 22:32:57 -0700 Subject: resource: add resource_size() Avoid one-off errors by introducing a resource_size() function. Signed-off-by: Magnus Damm Cc: Ben Dooks Cc: Jean Delvare Cc: Paul Mundt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ioport.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 2cd07cc29687..22d2115458c6 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -118,6 +118,10 @@ extern int allocate_resource(struct resource *root, struct resource *new, int adjust_resource(struct resource *res, resource_size_t start, resource_size_t size); resource_size_t resource_alignment(struct resource *res); +static inline resource_size_t resource_size(struct resource *res) +{ + return res->end - res->start + 1; +} /* Convenience shorthand with allocation */ #define request_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name)) -- cgit v1.2.2 From a1531acd43310a7e4571d52e8846640667f4c74b Mon Sep 17 00:00:00 2001 From: Thomas Renninger Date: Tue, 29 Jul 2008 22:32:58 -0700 Subject: cpufreq acpi: only call _PPC after cpufreq ACPI init funcs got called already Ingo Molnar provided a fix to not call _PPC at processor driver initialization time in "[PATCH] ACPI: fix cpufreq regression" (git commit e4233dec749a3519069d9390561b5636a75c7579) But it can still happen that _PPC is called at processor driver initialization time. This patch should make sure that this is not possible anymore. Signed-off-by: Thomas Renninger Cc: Andi Kleen Cc: Len Brown Cc: Dave Jones Cc: Ingo Molnar Cc: Venkatesh Pallipadi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpufreq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 2270ca5ec631..6fd5668aa572 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -106,6 +106,7 @@ struct cpufreq_policy { #define CPUFREQ_ADJUST (0) #define CPUFREQ_INCOMPATIBLE (1) #define CPUFREQ_NOTIFY (2) +#define CPUFREQ_START (3) #define CPUFREQ_SHARED_TYPE_NONE (0) /* None */ #define CPUFREQ_SHARED_TYPE_HW (1) /* HW does needed coordination */ -- cgit v1.2.2 From 1d1958f05095a7e9ecbba86235122784a3d1b561 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 29 Jul 2008 22:33:16 -0700 Subject: mm: remove find_max_pfn_with_active_regions It has no user now Also print out info about adding/removing active regions. Signed-off-by: Yinghai Lu Acked-by: Mel Gorman Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 866a3dbe5c75..5e2c8af49998 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1041,7 +1041,6 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn, extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); -extern unsigned long find_max_pfn_with_active_regions(void); extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); typedef int (*work_fn_t)(unsigned long, unsigned long, void *); -- cgit v1.2.2 From 3f1712bac586069d6c891a8201457283b27e8abe Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Tue, 29 Jul 2008 22:33:32 -0700 Subject: print_ip_sym(): use %pS Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kallsyms.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 57aefa160a92..b96144887444 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -108,8 +108,7 @@ static inline void print_fn_descriptor_symbol(const char *fmt, void *addr) static inline void print_ip_sym(unsigned long ip) { - printk("[<%p>]", (void *) ip); - print_symbol(" %s\n", ip); + printk("[<%p>] %pS\n", (void *) ip, (void *) ip); } #endif /*_LINUX_KALLSYMS_H*/ -- cgit v1.2.2 From 2c203003f64de5fe55ae35712942100d270667fa Mon Sep 17 00:00:00 2001 From: Jerome Arbez-Gindre Date: Tue, 29 Jul 2008 22:33:33 -0700 Subject: connector: add a BlackBoard user to connector Add a BlackBoard user to connector. BlackBoard is part of the TSP GPL sampling framework (http://savannah.nongnu.org/p/tsp) [akpm@linux-foundation.org: add comment] Signed-off-by: Jerome Arbez-Gindre Acked-by: Evgeniy Polyakov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/connector.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 96a89d3d6727..5c7f9468f753 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -38,8 +38,9 @@ #define CN_W1_VAL 0x1 #define CN_IDX_V86D 0x4 #define CN_VAL_V86D_UVESAFB 0x1 +#define CN_IDX_BB 0x5 /* BlackBoard, from the TSP GPL sampling framework */ -#define CN_NETLINK_USERS 5 +#define CN_NETLINK_USERS 6 /* * Maximum connector's message size. -- cgit v1.2.2 From 204b885e7322656284626949e51f292fe61313fa Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 29 Jul 2008 22:33:42 -0700 Subject: introduce lower_32_bits() macro The file kernel.h contains the upper_32_bits macro. This patch adds the other part, the lower_32_bits macro. Its first use will be in the driver for AMD IOMMU. Cc: H. Peter Anvin Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index fdbbf72ca2eb..aaa998f65c7a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -75,6 +75,12 @@ extern const char linux_proc_banner[]; */ #define upper_32_bits(n) ((u32)(((n) >> 16) >> 16)) +/** + * lower_32_bits - return bits 0-31 of a number + * @n: the number we're accessing + */ +#define lower_32_bits(n) ((u32)(n)) + #define KERN_EMERG "<0>" /* system is unusable */ #define KERN_ALERT "<1>" /* action must be taken immediately */ #define KERN_CRIT "<2>" /* critical conditions */ -- cgit v1.2.2 From c627f9cc046c7cd93b4525d89377fb409e170a18 Mon Sep 17 00:00:00 2001 From: Jack Steiner Date: Tue, 29 Jul 2008 22:33:53 -0700 Subject: mm: add zap_vma_ptes(): a library function to unmap driver ptes zap_vma_ptes() is intended to be used by drivers to unmap ptes assigned to the driver private vmas. This interface is similar to zap_page_range() but is less general & less likely to be abused. Needed by the GRU driver. Signed-off-by: Jack Steiner Cc: Nick Piggin Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5e2c8af49998..335288bff1b7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -744,6 +744,8 @@ struct zap_details { struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); +int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, + unsigned long size); unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *); unsigned long unmap_vmas(struct mmu_gather **tlb, -- cgit v1.2.2 From 3dd730f2b49f101b90d283c3efc4e6cd826dd8f6 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Tue, 29 Jul 2008 16:07:37 +1000 Subject: cpumask: statement expressions confuse some versions of gcc when you take the address of the result. Noticed on a sparc64 compile using a version 3.4.5 cross compiler. kernel/time/tick-common.c: In function `tick_check_new_device': kernel/time/tick-common.c:210: error: invalid lvalue in unary `&' ... Just make it a regular expression. Signed-off-by: Stephen Rothwell Acked-by: Ingo Molnar Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 96d0509fb8d8..d3219d73f8e6 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -287,7 +287,7 @@ static inline const cpumask_t *get_cpu_mask(unsigned int cpu) * gcc optimizes it out (it's a constant) and there's no huge stack * variable created: */ -#define cpumask_of_cpu(cpu) ({ *get_cpu_mask(cpu); }) +#define cpumask_of_cpu(cpu) (*get_cpu_mask(cpu)) #define CPU_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(NR_CPUS) -- cgit v1.2.2 From 1f938d060a7bc01b5f82d46db3e38cd501b445a6 Mon Sep 17 00:00:00 2001 From: Alexander Beregalov Date: Mon, 21 Jul 2008 00:06:19 +0400 Subject: libata.h: replace __FUNCTION__ with __func__ Signed-off-by: Alexander Beregalov Signed-off-by: Jeff Garzik --- include/linux/libata.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 5b247b8a6b3b..d4b8e5fa3e8b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -60,9 +60,9 @@ /* note: prints function name for you */ #ifdef ATA_DEBUG -#define DPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __FUNCTION__, ## args) +#define DPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) #ifdef ATA_VERBOSE_DEBUG -#define VPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __FUNCTION__, ## args) +#define VPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) #else #define VPRINTK(fmt, args...) #endif /* ATA_VERBOSE_DEBUG */ @@ -71,7 +71,7 @@ #define VPRINTK(fmt, args...) #endif /* ATA_DEBUG */ -#define BPRINTK(fmt, args...) if (ap->flags & ATA_FLAG_DEBUGMSG) printk(KERN_ERR "%s: " fmt, __FUNCTION__, ## args) +#define BPRINTK(fmt, args...) if (ap->flags & ATA_FLAG_DEBUGMSG) printk(KERN_ERR "%s: " fmt, __func__, ## args) /* NEW: debug levels */ #define HAVE_LIBATA_MSG 1 -- cgit v1.2.2 From 963e4975c6f93c148ca809d986d412201df9af89 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Thu, 24 Jul 2008 17:16:06 +0100 Subject: pata_it821x: Driver updates and reworking - Add support for the RDC 1010 variant - Rework the core library to have a read_id method. This allows the hacky bits of it821x to go and prepares us for pata_hd - Switch from WARN to BUG in ata_id_string as it will reboot if you get it wrong so WARN won't be seen - Allow the issue of command 0xFC on the 821x. This is needed to query rebuild status. - Tidy up printk formatting - Do more ident rewriting on RAID volumes to handle firmware provided ident data which is rather wonky - Report the firmware revision and device layout in RAID mode - Don't try and disable raid on the 8211 or RDC - they don't have the relevant bits Signed-off-by: Alan Cox Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index d4b8e5fa3e8b..06b80337303b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -750,6 +750,7 @@ struct ata_port_operations { void (*set_piomode)(struct ata_port *ap, struct ata_device *dev); void (*set_dmamode)(struct ata_port *ap, struct ata_device *dev); int (*set_mode)(struct ata_link *link, struct ata_device **r_failed_dev); + unsigned int (*read_id)(struct ata_device *dev, struct ata_taskfile *tf, u16 *id); void (*dev_config)(struct ata_device *dev); @@ -951,6 +952,8 @@ extern void ata_id_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern void ata_id_c_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); +extern unsigned int ata_do_dev_read_id(struct ata_device *dev, + struct ata_taskfile *tf, u16 *id); extern void ata_qc_complete(struct ata_queued_cmd *qc); extern int ata_qc_complete_multiple(struct ata_port *ap, u32 qc_active); extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd, -- cgit v1.2.2 From ae375044d31075a31de5a839e07ded7f67b660aa Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 31 Jul 2008 00:38:01 -0700 Subject: netfilter: nf_conntrack_tcp: decrease timeouts while data in unacknowledged In order to time out dead connections quicker, keep track of outstanding data and cap the timeout. Suggested by Herbert Xu. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_tcp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_tcp.h b/include/linux/netfilter/nf_conntrack_tcp.h index 22ce29995f13..a049df4f2236 100644 --- a/include/linux/netfilter/nf_conntrack_tcp.h +++ b/include/linux/netfilter/nf_conntrack_tcp.h @@ -30,6 +30,9 @@ enum tcp_conntrack { /* Be liberal in window checking */ #define IP_CT_TCP_FLAG_BE_LIBERAL 0x08 +/* Has unacknowledged data */ +#define IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED 0x10 + struct nf_ct_tcp_flags { u_int8_t flags; u_int8_t mask; -- cgit v1.2.2 From e4e4e534faa3c2be4e165ce414f44b76ada7208c Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 14 Apr 2008 08:50:02 +0200 Subject: sched clock: revert various sched_clock() changes Found an interactivity problem on a quad core test-system - simple CPU loops would occasionally delay the system un an unacceptable way. After much debugging with Peter Zijlstra it turned out that the problem is caused by the string of sched_clock() changes - they caused the CPU clock to jump backwards a bit - which confuses the scheduler arithmetics. (which is unsigned for performance reasons) So revert: # c300ba2: sched_clock: and multiplier for TSC to gtod drift # c0c8773: sched_clock: only update deltas with local reads. # af52a90: sched_clock: stop maximum check on NO HZ # f7cce27: sched_clock: widen the max and min time This solves the interactivity problems. Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Acked-by: Mike Galbraith --- include/linux/sched.h | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5270d449ff9d..ea436bc1a0e2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1572,28 +1572,13 @@ static inline void sched_clock_idle_sleep_event(void) static inline void sched_clock_idle_wakeup_event(u64 delta_ns) { } - -#ifdef CONFIG_NO_HZ -static inline void sched_clock_tick_stop(int cpu) -{ -} - -static inline void sched_clock_tick_start(int cpu) -{ -} -#endif - -#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ +#else extern void sched_clock_init(void); extern u64 sched_clock_cpu(int cpu); extern void sched_clock_tick(void); extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); -#ifdef CONFIG_NO_HZ -extern void sched_clock_tick_stop(int cpu); -extern void sched_clock_tick_start(int cpu); #endif -#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ /* * For kernel-internal use: high-speed (but slightly incorrect) per-cpu -- cgit v1.2.2 From 419ca3f13532793b81aff09f80c60af3eacbb43d Mon Sep 17 00:00:00 2001 From: David Miller Date: Tue, 29 Jul 2008 21:45:03 -0700 Subject: lockdep: fix combinatorial explosion in lock subgraph traversal When we traverse the graph, either forwards or backwards, we are interested in whether a certain property exists somewhere in a node reachable in the graph. Therefore it is never necessary to traverse through a node more than once to get a correct answer to the given query. Take advantage of this property using a global ID counter so that we need not clear all the markers in all the lock_class entries before doing a traversal. A new ID is choosen when we start to traverse, and we continue through a lock_class only if it's ID hasn't been marked with the new value yet. This short-circuiting is essential especially for high CPU count systems. The scheduler has a runqueue per cpu, and needs to take two runqueue locks at a time, which leads to long chains of backwards and forwards subgraphs from these runqueue lock nodes. Without the short-circuit implemented here, a graph traversal on a runqueue lock can take up to (1 << (N - 1)) checks on a system with N cpus. For anything more than 16 cpus or so, lockdep will eventually bring the machine to a complete standstill. Signed-off-by: David S. Miller Acked-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 2486eb4edbf1..1bfdc30bb0af 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -89,6 +89,7 @@ struct lock_class { struct lockdep_subclass_key *key; unsigned int subclass; + unsigned int dep_gen_id; /* * IRQ/softirq usage tracking bits: -- cgit v1.2.2 From dacdd0e04768da1fd2b24a6ee274c582b40d0c5b Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Thu, 17 Jul 2008 16:54:19 -0700 Subject: [PATCH] configfs: Include linux/err.h in linux/configfs.h We now use PTR_ERR() in the ->make_item() and ->make_group() operations. Folks including configfs.h need err.h. Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- include/linux/configfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/configfs.h b/include/linux/configfs.h index d62c19ff041c..0a5491baf0bc 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -40,6 +40,7 @@ #include #include #include +#include #include -- cgit v1.2.2 From ecb3d28c7edd58b54f16838c434b342ba9195bec Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Wed, 18 Jun 2008 19:29:05 -0700 Subject: [PATCH] configfs: Convenience macros for attribute definition. Sysfs has the _ATTR() and _ATTR_RO() macros to make defining extended form attributes easier. configfs should have something similiar. - _CONFIGFS_ATTR() and _CONFIGFS_ATTR_RO() are the counterparts to the sysfs macros. - CONFIGFS_ATTR_STRUCT() creates the extended form attribute structure. - CONFIGFS_ATTR_OPS() defines the show_attribute()/store_attribute() operations that call the show()/store() operations of the extended form configfs_attributes. Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- include/linux/configfs.h | 67 ++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 65 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 0a5491baf0bc..7f627775c947 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -130,8 +130,25 @@ struct configfs_attribute { /* * Users often need to create attribute structures for their configurable * attributes, containing a configfs_attribute member and function pointers - * for the show() and store() operations on that attribute. They can use - * this macro (similar to sysfs' __ATTR) to make defining attributes easier. + * for the show() and store() operations on that attribute. If they don't + * need anything else on the extended attribute structure, they can use + * this macro to define it The argument _item is the name of the + * config_item structure. + */ +#define CONFIGFS_ATTR_STRUCT(_item) \ +struct _item##_attribute { \ + struct configfs_attribute attr; \ + ssize_t (*show)(struct _item *, char *); \ + ssize_t (*store)(struct _item *, const char *, size_t); \ +} + +/* + * With the extended attribute structure, users can use this macro + * (similar to sysfs' __ATTR) to make defining attributes easier. + * An example: + * #define MYITEM_ATTR(_name, _mode, _show, _store) \ + * struct myitem_attribute childless_attr_##_name = \ + * __CONFIGFS_ATTR(_name, _mode, _show, _store) */ #define __CONFIGFS_ATTR(_name, _mode, _show, _store) \ { \ @@ -143,6 +160,52 @@ struct configfs_attribute { .show = _show, \ .store = _store, \ } +/* Here is a readonly version, only requiring a show() operation */ +#define __CONFIGFS_ATTR_RO(_name, _show) \ +{ \ + .attr = { \ + .ca_name = __stringify(_name), \ + .ca_mode = 0444, \ + .ca_owner = THIS_MODULE, \ + }, \ + .show = _show, \ +} + +/* + * With these extended attributes, the simple show_attribute() and + * store_attribute() operations need to call the show() and store() of the + * attributes. This is a common pattern, so we provide a macro to define + * them. The argument _item is the name of the config_item structure. + * This macro expects the attributes to be named "struct _attribute" + * and the function to_() to exist; + */ +#define CONFIGFS_ATTR_OPS(_item) \ +static ssize_t _item##_attr_show(struct config_item *item, \ + struct configfs_attribute *attr, \ + char *page) \ +{ \ + struct _item *_item = to_##_item(item); \ + struct _item##_attribute *_item##_attr = \ + container_of(attr, struct _item##_attribute, attr); \ + ssize_t ret = 0; \ + \ + if (_item##_attr->show) \ + ret = _item##_attr->show(_item, page); \ + return ret; \ +} \ +static ssize_t _item##_attr_store(struct config_item *item, \ + struct configfs_attribute *attr, \ + const char *page, size_t count) \ +{ \ + struct _item *_item = to_##_item(item); \ + struct _item##_attribute *_item##_attr = \ + container_of(attr, struct _item##_attribute, attr); \ + ssize_t ret = -EINVAL; \ + \ + if (_item##_attr->store) \ + ret = _item##_attr->store(_item, page, count); \ + return ret; \ +} /* * If allow_link() exists, the item can symlink(2) out to other -- cgit v1.2.2 From c3f26a269c2421f97f10cf8ed05d5099b573af4d Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 31 Jul 2008 16:58:50 -0700 Subject: netdev: Fix lockdep warnings in multiqueue configurations. When support for multiple TX queues were added, the netif_tx_lock() routines we converted to iterate over all TX queues and grab each queue's spinlock. This causes heartburn for lockdep and it's not a healthy thing to do with lots of TX queues anyways. So modify this to use a top-level lock and a "frozen" state for the individual TX queues. Signed-off-by: David S. Miller --- include/linux/netdevice.h | 86 ++++++++++++++++++++++++++++++----------------- 1 file changed, 55 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b4d056ceab96..ee583f642a9f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -440,6 +440,7 @@ static inline void napi_synchronize(const struct napi_struct *n) enum netdev_queue_state_t { __QUEUE_STATE_XOFF, + __QUEUE_STATE_FROZEN, }; struct netdev_queue { @@ -636,7 +637,7 @@ struct net_device unsigned int real_num_tx_queues; unsigned long tx_queue_len; /* Max frames per queue allowed */ - + spinlock_t tx_global_lock; /* * One part is mostly used on xmit path (device) */ @@ -1099,6 +1100,11 @@ static inline int netif_queue_stopped(const struct net_device *dev) return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0)); } +static inline int netif_tx_queue_frozen(const struct netdev_queue *dev_queue) +{ + return test_bit(__QUEUE_STATE_FROZEN, &dev_queue->state); +} + /** * netif_running - test if up * @dev: network device @@ -1475,6 +1481,26 @@ static inline void __netif_tx_lock_bh(struct netdev_queue *txq) txq->xmit_lock_owner = smp_processor_id(); } +static inline int __netif_tx_trylock(struct netdev_queue *txq) +{ + int ok = spin_trylock(&txq->_xmit_lock); + if (likely(ok)) + txq->xmit_lock_owner = smp_processor_id(); + return ok; +} + +static inline void __netif_tx_unlock(struct netdev_queue *txq) +{ + txq->xmit_lock_owner = -1; + spin_unlock(&txq->_xmit_lock); +} + +static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) +{ + txq->xmit_lock_owner = -1; + spin_unlock_bh(&txq->_xmit_lock); +} + /** * netif_tx_lock - grab network device transmit lock * @dev: network device @@ -1484,12 +1510,23 @@ static inline void __netif_tx_lock_bh(struct netdev_queue *txq) */ static inline void netif_tx_lock(struct net_device *dev) { - int cpu = smp_processor_id(); unsigned int i; + int cpu; + spin_lock(&dev->tx_global_lock); + cpu = smp_processor_id(); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + /* We are the only thread of execution doing a + * freeze, but we have to grab the _xmit_lock in + * order to synchronize with threads which are in + * the ->hard_start_xmit() handler and already + * checked the frozen bit. + */ __netif_tx_lock(txq, cpu); + set_bit(__QUEUE_STATE_FROZEN, &txq->state); + __netif_tx_unlock(txq); } } @@ -1499,40 +1536,22 @@ static inline void netif_tx_lock_bh(struct net_device *dev) netif_tx_lock(dev); } -static inline int __netif_tx_trylock(struct netdev_queue *txq) -{ - int ok = spin_trylock(&txq->_xmit_lock); - if (likely(ok)) - txq->xmit_lock_owner = smp_processor_id(); - return ok; -} - -static inline int netif_tx_trylock(struct net_device *dev) -{ - return __netif_tx_trylock(netdev_get_tx_queue(dev, 0)); -} - -static inline void __netif_tx_unlock(struct netdev_queue *txq) -{ - txq->xmit_lock_owner = -1; - spin_unlock(&txq->_xmit_lock); -} - -static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) -{ - txq->xmit_lock_owner = -1; - spin_unlock_bh(&txq->_xmit_lock); -} - static inline void netif_tx_unlock(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - __netif_tx_unlock(txq); - } + /* No need to grab the _xmit_lock here. If the + * queue is not stopped for another reason, we + * force a schedule. + */ + clear_bit(__QUEUE_STATE_FROZEN, &txq->state); + if (!test_bit(__QUEUE_STATE_XOFF, &txq->state)) + __netif_schedule(txq->qdisc); + } + spin_unlock(&dev->tx_global_lock); } static inline void netif_tx_unlock_bh(struct net_device *dev) @@ -1556,13 +1575,18 @@ static inline void netif_tx_unlock_bh(struct net_device *dev) static inline void netif_tx_disable(struct net_device *dev) { unsigned int i; + int cpu; - netif_tx_lock_bh(dev); + local_bh_disable(); + cpu = smp_processor_id(); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + __netif_tx_lock(txq, cpu); netif_tx_stop_queue(txq); + __netif_tx_unlock(txq); } - netif_tx_unlock_bh(dev); + local_bh_enable(); } static inline void netif_addr_lock(struct net_device *dev) -- cgit v1.2.2 From bc4768eb081a67642c0c44c34ea597c273bdedcb Mon Sep 17 00:00:00 2001 From: Julius Volz Date: Thu, 31 Jul 2008 20:45:24 -0700 Subject: ipvs: Move userspace definitions to include/linux/ip_vs.h Current versions of ipvsadm include "/usr/src/linux/include/net/ip_vs.h" directly. This file also contains kernel-only definitions. Normally, public definitions should live in include/linux, so this patch moves the definitions shared with userspace to a new file, "include/linux/ip_vs.h". This also removes the unused NFC_IPVS_PROPERTY bitmask, which was once used to point into skb->nfcache. To make old ipvsadms still compile with this, the old header file includes the new one. Thanks to Dave Miller and Horms for noting/adding the missing Kbuild entry for the new header file. Signed-off-by: Julius Volz Acked-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/Kbuild | 1 + include/linux/ip_vs.h | 245 ++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 246 insertions(+) create mode 100644 include/linux/ip_vs.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 4c4142c5aa6e..a26f565e8189 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -97,6 +97,7 @@ header-y += ioctl.h header-y += ip6_tunnel.h header-y += ipmi_msgdefs.h header-y += ipsec.h +header-y += ip_vs.h header-y += ipx.h header-y += irda.h header-y += iso_fs.h diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h new file mode 100644 index 000000000000..ec6eb49af2d8 --- /dev/null +++ b/include/linux/ip_vs.h @@ -0,0 +1,245 @@ +/* + * IP Virtual Server + * data structure and functionality definitions + */ + +#ifndef _IP_VS_H +#define _IP_VS_H + +#include /* For __beXX types in userland */ + +#define IP_VS_VERSION_CODE 0x010201 +#define NVERSION(version) \ + (version >> 16) & 0xFF, \ + (version >> 8) & 0xFF, \ + version & 0xFF + +/* + * Virtual Service Flags + */ +#define IP_VS_SVC_F_PERSISTENT 0x0001 /* persistent port */ +#define IP_VS_SVC_F_HASHED 0x0002 /* hashed entry */ + +/* + * Destination Server Flags + */ +#define IP_VS_DEST_F_AVAILABLE 0x0001 /* server is available */ +#define IP_VS_DEST_F_OVERLOAD 0x0002 /* server is overloaded */ + +/* + * IPVS sync daemon states + */ +#define IP_VS_STATE_NONE 0x0000 /* daemon is stopped */ +#define IP_VS_STATE_MASTER 0x0001 /* started as master */ +#define IP_VS_STATE_BACKUP 0x0002 /* started as backup */ + +/* + * IPVS socket options + */ +#define IP_VS_BASE_CTL (64+1024+64) /* base */ + +#define IP_VS_SO_SET_NONE IP_VS_BASE_CTL /* just peek */ +#define IP_VS_SO_SET_INSERT (IP_VS_BASE_CTL+1) +#define IP_VS_SO_SET_ADD (IP_VS_BASE_CTL+2) +#define IP_VS_SO_SET_EDIT (IP_VS_BASE_CTL+3) +#define IP_VS_SO_SET_DEL (IP_VS_BASE_CTL+4) +#define IP_VS_SO_SET_FLUSH (IP_VS_BASE_CTL+5) +#define IP_VS_SO_SET_LIST (IP_VS_BASE_CTL+6) +#define IP_VS_SO_SET_ADDDEST (IP_VS_BASE_CTL+7) +#define IP_VS_SO_SET_DELDEST (IP_VS_BASE_CTL+8) +#define IP_VS_SO_SET_EDITDEST (IP_VS_BASE_CTL+9) +#define IP_VS_SO_SET_TIMEOUT (IP_VS_BASE_CTL+10) +#define IP_VS_SO_SET_STARTDAEMON (IP_VS_BASE_CTL+11) +#define IP_VS_SO_SET_STOPDAEMON (IP_VS_BASE_CTL+12) +#define IP_VS_SO_SET_RESTORE (IP_VS_BASE_CTL+13) +#define IP_VS_SO_SET_SAVE (IP_VS_BASE_CTL+14) +#define IP_VS_SO_SET_ZERO (IP_VS_BASE_CTL+15) +#define IP_VS_SO_SET_MAX IP_VS_SO_SET_ZERO + +#define IP_VS_SO_GET_VERSION IP_VS_BASE_CTL +#define IP_VS_SO_GET_INFO (IP_VS_BASE_CTL+1) +#define IP_VS_SO_GET_SERVICES (IP_VS_BASE_CTL+2) +#define IP_VS_SO_GET_SERVICE (IP_VS_BASE_CTL+3) +#define IP_VS_SO_GET_DESTS (IP_VS_BASE_CTL+4) +#define IP_VS_SO_GET_DEST (IP_VS_BASE_CTL+5) /* not used now */ +#define IP_VS_SO_GET_TIMEOUT (IP_VS_BASE_CTL+6) +#define IP_VS_SO_GET_DAEMON (IP_VS_BASE_CTL+7) +#define IP_VS_SO_GET_MAX IP_VS_SO_GET_DAEMON + + +/* + * IPVS Connection Flags + */ +#define IP_VS_CONN_F_FWD_MASK 0x0007 /* mask for the fwd methods */ +#define IP_VS_CONN_F_MASQ 0x0000 /* masquerading/NAT */ +#define IP_VS_CONN_F_LOCALNODE 0x0001 /* local node */ +#define IP_VS_CONN_F_TUNNEL 0x0002 /* tunneling */ +#define IP_VS_CONN_F_DROUTE 0x0003 /* direct routing */ +#define IP_VS_CONN_F_BYPASS 0x0004 /* cache bypass */ +#define IP_VS_CONN_F_SYNC 0x0020 /* entry created by sync */ +#define IP_VS_CONN_F_HASHED 0x0040 /* hashed entry */ +#define IP_VS_CONN_F_NOOUTPUT 0x0080 /* no output packets */ +#define IP_VS_CONN_F_INACTIVE 0x0100 /* not established */ +#define IP_VS_CONN_F_OUT_SEQ 0x0200 /* must do output seq adjust */ +#define IP_VS_CONN_F_IN_SEQ 0x0400 /* must do input seq adjust */ +#define IP_VS_CONN_F_SEQ_MASK 0x0600 /* in/out sequence mask */ +#define IP_VS_CONN_F_NO_CPORT 0x0800 /* no client port set yet */ +#define IP_VS_CONN_F_TEMPLATE 0x1000 /* template, not connection */ + +#define IP_VS_SCHEDNAME_MAXLEN 16 +#define IP_VS_IFNAME_MAXLEN 16 + + +/* + * The struct ip_vs_service_user and struct ip_vs_dest_user are + * used to set IPVS rules through setsockopt. + */ +struct ip_vs_service_user { + /* virtual service addresses */ + u_int16_t protocol; + __be32 addr; /* virtual ip address */ + __be16 port; + u_int32_t fwmark; /* firwall mark of service */ + + /* virtual service options */ + char sched_name[IP_VS_SCHEDNAME_MAXLEN]; + unsigned flags; /* virtual service flags */ + unsigned timeout; /* persistent timeout in sec */ + __be32 netmask; /* persistent netmask */ +}; + + +struct ip_vs_dest_user { + /* destination server address */ + __be32 addr; + __be16 port; + + /* real server options */ + unsigned conn_flags; /* connection flags */ + int weight; /* destination weight */ + + /* thresholds for active connections */ + u_int32_t u_threshold; /* upper threshold */ + u_int32_t l_threshold; /* lower threshold */ +}; + + +/* + * IPVS statistics object (for user space) + */ +struct ip_vs_stats_user +{ + __u32 conns; /* connections scheduled */ + __u32 inpkts; /* incoming packets */ + __u32 outpkts; /* outgoing packets */ + __u64 inbytes; /* incoming bytes */ + __u64 outbytes; /* outgoing bytes */ + + __u32 cps; /* current connection rate */ + __u32 inpps; /* current in packet rate */ + __u32 outpps; /* current out packet rate */ + __u32 inbps; /* current in byte rate */ + __u32 outbps; /* current out byte rate */ +}; + + +/* The argument to IP_VS_SO_GET_INFO */ +struct ip_vs_getinfo { + /* version number */ + unsigned int version; + + /* size of connection hash table */ + unsigned int size; + + /* number of virtual services */ + unsigned int num_services; +}; + + +/* The argument to IP_VS_SO_GET_SERVICE */ +struct ip_vs_service_entry { + /* which service: user fills in these */ + u_int16_t protocol; + __be32 addr; /* virtual address */ + __be16 port; + u_int32_t fwmark; /* firwall mark of service */ + + /* service options */ + char sched_name[IP_VS_SCHEDNAME_MAXLEN]; + unsigned flags; /* virtual service flags */ + unsigned timeout; /* persistent timeout */ + __be32 netmask; /* persistent netmask */ + + /* number of real servers */ + unsigned int num_dests; + + /* statistics */ + struct ip_vs_stats_user stats; +}; + + +struct ip_vs_dest_entry { + __be32 addr; /* destination address */ + __be16 port; + unsigned conn_flags; /* connection flags */ + int weight; /* destination weight */ + + u_int32_t u_threshold; /* upper threshold */ + u_int32_t l_threshold; /* lower threshold */ + + u_int32_t activeconns; /* active connections */ + u_int32_t inactconns; /* inactive connections */ + u_int32_t persistconns; /* persistent connections */ + + /* statistics */ + struct ip_vs_stats_user stats; +}; + + +/* The argument to IP_VS_SO_GET_DESTS */ +struct ip_vs_get_dests { + /* which service: user fills in these */ + u_int16_t protocol; + __be32 addr; /* virtual address */ + __be16 port; + u_int32_t fwmark; /* firwall mark of service */ + + /* number of real servers */ + unsigned int num_dests; + + /* the real servers */ + struct ip_vs_dest_entry entrytable[0]; +}; + + +/* The argument to IP_VS_SO_GET_SERVICES */ +struct ip_vs_get_services { + /* number of virtual services */ + unsigned int num_services; + + /* service table */ + struct ip_vs_service_entry entrytable[0]; +}; + + +/* The argument to IP_VS_SO_GET_TIMEOUT */ +struct ip_vs_timeout_user { + int tcp_timeout; + int tcp_fin_timeout; + int udp_timeout; +}; + + +/* The argument to IP_VS_SO_GET_DAEMON */ +struct ip_vs_daemon_user { + /* sync daemon state (master/backup) */ + int state; + + /* multicast interface name */ + char mcast_ifn[IP_VS_IFNAME_MAXLEN]; + + /* SyncID we belong to */ + int syncid; +}; + +#endif /* _IP_VS_H */ -- cgit v1.2.2 From 4a7b61d23505854dff7d04cc11944566cffdd0ee Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 31 Jul 2008 20:52:08 -0700 Subject: skbuff: add missing kernel-doc for do_not_encrypt Add missing kernel-doc notation to sk_buff: Warning(linux-2.6.27-rc1-git2//include/linux/skbuff.h:345): No description found for parameter 'do_not_encrypt' Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a640385e0598..cfcc45b3bef0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -243,6 +243,7 @@ typedef unsigned char *sk_buff_data_t; * @tc_index: Traffic control index * @tc_verd: traffic control verdict * @ndisc_nodetype: router type (from link layer) + * @do_not_encrypt: set to prevent encryption of this frame * @dma_cookie: a cookie to one of several possible DMA operations * done by skb DMA functions * @secmark: security marking -- cgit v1.2.2 From a4b526b3ba6353cd89a38e41da48ed83b0ead16f Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 1 Aug 2008 16:39:12 +0200 Subject: [S390] Optimize storage key operations for anon pages For anonymous pages without a swap cache backing the check in page_remove_rmap for the physical dirty bit in page_remove_rmap is unnecessary. The instructions that are used to check and reset the dirty bit are expensive. Removing the check noticably speeds up process exit. In addition the clearing of the dirty bit in __SetPageUptodate is pointless as well. With these two changes there is no storage key operation for an anonymous page anymore if it does not hit the swap space. The micro benchmark which repeatedly executes an empty shell script gets about 5% faster. Signed-off-by: Martin Schwidefsky --- include/linux/page-flags.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 54590a9a103e..25aaccdb2f26 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -239,9 +239,6 @@ static inline void __SetPageUptodate(struct page *page) { smp_wmb(); __set_bit(PG_uptodate, &(page)->flags); -#ifdef CONFIG_S390 - page_clear_dirty(page); -#endif } static inline void SetPageUptodate(struct page *page) -- cgit v1.2.2 From 1027abe8827b47f7e9c4ed6514fde3d44f79963c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 30 Jul 2008 04:13:04 -0400 Subject: [PATCH] merge locate_fd() and get_unused_fd() New primitive: alloc_fd(start, flags). get_unused_fd() and get_unused_fd_flags() become wrappers on top of it. Signed-off-by: Al Viro --- include/linux/file.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 27c64bdc68c9..a20259e248a5 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -34,8 +34,9 @@ extern struct file *fget(unsigned int fd); extern struct file *fget_light(unsigned int fd, int *fput_needed); extern void set_close_on_exec(unsigned int fd, int flag); extern void put_filp(struct file *); +extern int alloc_fd(unsigned start, unsigned flags); extern int get_unused_fd(void); -extern int get_unused_fd_flags(int flags); +#define get_unused_fd_flags(flags) alloc_fd(0, (flags)) extern void put_unused_fd(unsigned int fd); extern void fd_install(unsigned int fd, struct file *file); -- cgit v1.2.2 From 77e69dac3cefacee939cb107ae9cd520a62338e0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 1 Aug 2008 04:29:18 -0400 Subject: [PATCH] fix races and leaks in vfs_quota_on() users * new helper: vfs_quota_on_path(); equivalent of vfs_quota_on() sans the pathname resolution. * callers of vfs_quota_on() that do their own pathname resolution and checks based on it are switched to vfs_quota_on_path(); that way we avoid the races. * reiserfs leaked dentry/vfsmount references on several failure exits. Signed-off-by: Al Viro --- include/linux/quotaops.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 742187f7a05c..ca6b9b5c8d52 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -43,6 +43,8 @@ int dquot_mark_dquot_dirty(struct dquot *dquot); int vfs_quota_on(struct super_block *sb, int type, int format_id, char *path, int remount); +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); -- cgit v1.2.2 From 8d66bf5481002b0960aa49aed0987c73f5d7816c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 1 Aug 2008 09:05:54 -0400 Subject: [PATCH] pass struct path * to do_add_mount() Signed-off-by: Al Viro --- include/linux/mount.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index b5efaa2132ab..30a1d63b6fb5 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -105,7 +105,8 @@ extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, struct nameidata; -extern int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd, +struct path; +extern int do_add_mount(struct vfsmount *newmnt, struct path *path, int mnt_flags, struct list_head *fslist); extern void mark_mounts_for_expiry(struct list_head *mounts); -- cgit v1.2.2 From 6c5e0c4d518a37e1d5d794c14433e80284415079 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 1 Aug 2008 20:31:32 +0200 Subject: block: add a blk_plug_device_unlocked() that grabs the queue lock blk_plug_device() must be called with the queue lock held, so callers often just grab and release the lock for that purpose. Add a helper that does just that. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 88d68081a0f1..e61f22be4d0e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -655,6 +655,7 @@ extern struct request *blk_get_request(struct request_queue *, int, gfp_t); extern void blk_insert_request(struct request_queue *, struct request *, int, void *); extern void blk_requeue_request(struct request_queue *, struct request *); extern void blk_plug_device(struct request_queue *); +extern void blk_plug_device_unlocked(struct request_queue *); extern int blk_remove_plug(struct request_queue *); extern void blk_recount_segments(struct request_queue *, struct bio *); extern int scsi_cmd_ioctl(struct file *, struct request_queue *, -- cgit v1.2.2 From 5c7edcd7ee6b77b88252fe4096dce1a46a60c829 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Thu, 31 Jul 2008 02:04:09 -0700 Subject: tracehook: fix exit_signal=0 case My commit 2b2a1ff64afbadac842bbc58c5166962cf4f7664 introduced a regression (sorry about that) for the odd case of exit_signal=0 (e.g. clone_flags=0). This is not a normal use, but it's used by a case in the glibc test suite. Dying with exit_signal=0 sends no signal, but it's supposed to wake up a parent's blocked wait*() calls (unlike the delayed_group_leader case). This fixes tracehook_notify_death() and its caller to distinguish a "signal 0" wakeup from the delayed_group_leader case (with no wakeup). Signed-off-by: Roland McGrath Tested-by: Serge Hallyn Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index b1875582c1a1..12532839f508 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -493,16 +493,21 @@ static inline int tracehook_notify_jctl(int notify, int why) * @death_cookie: value to pass to tracehook_report_death() * @group_dead: nonzero if this was the last thread in the group to die * - * Return the signal number to send our parent with do_notify_parent(), or - * zero to send no signal and leave a zombie, or -1 to self-reap right now. + * A return value >= 0 means call do_notify_parent() with that signal + * number. Negative return value can be %DEATH_REAP to self-reap right + * now, or %DEATH_DELAYED_GROUP_LEADER to a zombie without notifying our + * parent. Note that a return value of 0 means a do_notify_parent() call + * that sends no signal, but still wakes up a parent blocked in wait*(). * * Called with write_lock_irq(&tasklist_lock) held. */ +#define DEATH_REAP -1 +#define DEATH_DELAYED_GROUP_LEADER -2 static inline int tracehook_notify_death(struct task_struct *task, void **death_cookie, int group_dead) { if (task->exit_signal == -1) - return task->ptrace ? SIGCHLD : -1; + return task->ptrace ? SIGCHLD : DEATH_REAP; /* * If something other than our normal parent is ptracing us, then @@ -512,21 +517,21 @@ static inline int tracehook_notify_death(struct task_struct *task, if (thread_group_empty(task) && !ptrace_reparented(task)) return task->exit_signal; - return task->ptrace ? SIGCHLD : 0; + return task->ptrace ? SIGCHLD : DEATH_DELAYED_GROUP_LEADER; } /** * tracehook_report_death - task is dead and ready to be reaped * @task: @current task now exiting - * @signal: signal number sent to parent, or 0 or -1 + * @signal: return value from tracheook_notify_death() * @death_cookie: value passed back from tracehook_notify_death() * @group_dead: nonzero if this was the last thread in the group to die * * Thread has just become a zombie or is about to self-reap. If positive, * @signal is the signal number just sent to the parent (usually %SIGCHLD). - * If @signal is -1, this thread will self-reap. If @signal is 0, this is - * a delayed_group_leader() zombie. The @death_cookie was passed back by - * tracehook_notify_death(). + * If @signal is %DEATH_REAP, this thread will self-reap. If @signal is + * %DEATH_DELAYED_GROUP_LEADER, this is a delayed_group_leader() zombie. + * The @death_cookie was passed back by tracehook_notify_death(). * * If normal reaping is not inhibited, @task->exit_state might be changing * in parallel. -- cgit v1.2.2 From 4744b43431e8613f920c5cba88346756f53c5165 Mon Sep 17 00:00:00 2001 From: Tim Bird Date: Fri, 1 Aug 2008 14:05:50 -0700 Subject: embedded: fix vc_translate operator precedence This fixes a bug in operator precedence in the newly introduced vc_translate macro. Without this fix, the translation of some characters on the kernel console is garbled. This patch was copied to the e-mail list previously for testing. Now, all reports confirm that it works, so this is an official post for application. Signed-off-by: Tim Bird Signed-off-by: David Woodhouse --- include/linux/vt_kern.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 14c0e91be9b5..8c8119ffee12 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -74,7 +74,7 @@ void con_protect_unimap(struct vc_data *vc, int rdonly); int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc); #define vc_translate(vc, c) ((vc)->vc_translate[(c) | \ - (vc)->vc_toggle_meta ? 0x80 : 0]) + ((vc)->vc_toggle_meta ? 0x80 : 0)]) #else #define con_set_trans_old(arg) (0) #define con_get_trans_old(arg) (-EINVAL) -- cgit v1.2.2 From ff4cc1de2401ad44ae084c3f5a9e898af0879520 Mon Sep 17 00:00:00 2001 From: Karsten Keil Date: Wed, 30 Jul 2008 18:26:58 +0200 Subject: mISDN cleanup user interface The channelmap should have the same size on 32 and 64 bit systems and should not depend on endianess. Thanks to David Woodhouse for spotting this. Signed-off-by: Karsten Keil --- include/linux/mISDNif.h | 32 +++++++++++++++++++++++++++----- 1 file changed, 27 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mISDNif.h b/include/linux/mISDNif.h index 5c948f337817..8f2d60da04e7 100644 --- a/include/linux/mISDNif.h +++ b/include/linux/mISDNif.h @@ -37,7 +37,7 @@ */ #define MISDN_MAJOR_VERSION 1 #define MISDN_MINOR_VERSION 0 -#define MISDN_RELEASE 18 +#define MISDN_RELEASE 19 /* primitives for information exchange * generell format @@ -242,7 +242,8 @@ struct mISDNhead { #define TEI_SAPI 63 #define CTRL_SAPI 0 -#define MISDN_CHMAP_SIZE 4 +#define MISDN_MAX_CHANNEL 127 +#define MISDN_CHMAP_SIZE ((MISDN_MAX_CHANNEL + 1) >> 3) #define SOL_MISDN 0 @@ -275,11 +276,32 @@ struct mISDN_devinfo { u_int Dprotocols; u_int Bprotocols; u_int protocol; - u_long channelmap[MISDN_CHMAP_SIZE]; + u_char channelmap[MISDN_CHMAP_SIZE]; u_int nrbchan; char name[MISDN_MAX_IDLEN]; }; +static inline int +test_channelmap(u_int nr, u_char *map) +{ + if (nr <= MISDN_MAX_CHANNEL) + return map[nr >> 3] & (1 << (nr & 7)); + else + return 0; +} + +static inline void +set_channelmap(u_int nr, u_char *map) +{ + map[nr >> 3] |= (1 << (nr & 7)); +} + +static inline void +clear_channelmap(u_int nr, u_char *map) +{ + map[nr >> 3] &= ~(1 << (nr & 7)); +} + /* CONTROL_CHANNEL parameters */ #define MISDN_CTRL_GETOP 0x0000 #define MISDN_CTRL_LOOP 0x0001 @@ -405,7 +427,7 @@ struct mISDNdevice { u_int Dprotocols; u_int Bprotocols; u_int nrbchan; - u_long channelmap[MISDN_CHMAP_SIZE]; + u_char channelmap[MISDN_CHMAP_SIZE]; struct list_head bchannels; struct mISDNchannel *teimgr; struct device dev; @@ -430,7 +452,7 @@ struct mISDNstack { #endif }; -/* global alloc/queue dunctions */ +/* global alloc/queue functions */ static inline struct sk_buff * mI_alloc_skb(unsigned int len, gfp_t gfp_mask) -- cgit v1.2.2 From 85ebd00334099fd5d296bcae74a66c943d46686d Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 2 Aug 2008 19:12:23 +0200 Subject: Fix IHEX firmware generation/loading Fix both the IHEX firmware generation (len field always null, and EOF marker a byte too short) and loading (struct ihex_binrec needs to be packed to reflect the on-disk structure). Signed-off-by: Marc Zyngier Signed-off-by: David Woodhouse --- include/linux/ihex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ihex.h b/include/linux/ihex.h index 2baace2788a7..31d8629e75a1 100644 --- a/include/linux/ihex.h +++ b/include/linux/ihex.h @@ -18,7 +18,7 @@ struct ihex_binrec { __be32 addr; __be16 len; uint8_t data[0]; -} __attribute__((aligned(4))); +} __attribute__((packed)); /* Find the next record, taking into account the 4-byte alignment */ static inline const struct ihex_binrec * -- cgit v1.2.2 From cf368d2f9aced8adc8bd6b1f04294a71551d5fce Mon Sep 17 00:00:00 2001 From: Alexander Beregalov Date: Sun, 3 Aug 2008 03:03:57 +0400 Subject: drivers/video/console/promcon.c: fix build error drivers/video/console/promcon.c:158: error: implicit declaration of function 'con_protect_unimap' Introduced by commit a29ccf6f823a84d89e1c7aaaf221cf7282022024 ("embedded: fix vc_translate operator precedence"). Signed-off-by: Alexander Beregalov Cc: Tim Bird Signed-off-by: David Woodhouse --- include/linux/vt_kern.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 8c8119ffee12..1c78d56c57e5 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -86,6 +86,7 @@ int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc); #define con_copy_unimap(d, s) (0) #define con_get_unimap(vc, ct, uct, list) (-EINVAL) #define con_free_unimap(vc) do { ; } while (0) +#define con_protect_unimap(vc, rdonly) do { ; } while (0) #define vc_translate(vc, c) (c) #endif -- cgit v1.2.2 From 63870295de9adb365cd121dab94379b8cfdf986a Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 4 Aug 2008 10:39:46 +0900 Subject: maple: Clean up maple_driver_register/unregister routines. These were completely inconsistent. Clean these up to take a maple_driver pointer directly for consistency. Signed-off-by: Paul Mundt --- include/linux/maple.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/maple.h b/include/linux/maple.h index c853b1066018..b2b7ce0fb1f7 100644 --- a/include/linux/maple.h +++ b/include/linux/maple.h @@ -70,7 +70,9 @@ void maple_getcond_callback(struct maple_device *dev, void (*callback) (struct mapleq * mq), unsigned long interval, unsigned long function); -int maple_driver_register(struct device_driver *drv); +int maple_driver_register(struct maple_driver *); +void maple_driver_unregister(struct maple_driver *); + int maple_add_packet_sleeps(struct maple_device *mdev, u32 function, u32 command, u32 length, void *data); void maple_clear_dev(struct maple_device *mdev); -- cgit v1.2.2 From 617870632de6739fca0893f3e6648e9ae1bd0ddb Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 4 Aug 2008 10:58:24 +0900 Subject: maple: Kill useless private_data pointer. We can simply wrap in to the dev_set/get_drvdata(), there's no reason to track an extra level of private data on top of the struct device. Signed-off-by: Paul Mundt --- include/linux/maple.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/maple.h b/include/linux/maple.h index b2b7ce0fb1f7..c23d3f51ba40 100644 --- a/include/linux/maple.h +++ b/include/linux/maple.h @@ -51,7 +51,6 @@ struct maple_devinfo { struct maple_device { struct maple_driver *driver; struct mapleq *mq; - void *private_data; void (*callback) (struct mapleq * mq); unsigned long when, interval, function; struct maple_devinfo devinfo; @@ -80,4 +79,7 @@ void maple_clear_dev(struct maple_device *mdev); #define to_maple_dev(n) container_of(n, struct maple_device, dev) #define to_maple_driver(n) container_of(n, struct maple_driver, drv) +#define maple_get_drvdata(d) dev_get_drvdata(&(d)->dev) +#define maple_set_drvdata(d,p) dev_set_drvdata(&(d)->dev, (p)) + #endif /* __LINUX_MAPLE_H */ -- cgit v1.2.2 From 98f7dfd86cbbd377e2cbc293529681b914296f68 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Fri, 18 Jul 2008 13:52:59 +0800 Subject: mac80211: pass dtim_period to low level driver This patch adds the dtim_period in ieee80211_bss_conf, this allows the low level driver to know the dtim_period, and to plan power save accordingly. Signed-off-by: Emmanuel Grumbach Signed-off-by: Tomas Winkler Signed-off-by: Zhu Yi Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a1630ba0b87c..7f4df7c7659d 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -506,6 +506,19 @@ struct ieee80211_channel_sw_ie { u8 count; } __attribute__ ((packed)); +/** + * struct ieee80211_tim + * + * This structure refers to "Traffic Indication Map information element" + */ +struct ieee80211_tim_ie { + u8 dtim_count; + u8 dtim_period; + u8 bitmap_ctrl; + /* variable size: 1 - 251 bytes */ + u8 virtual_map[0]; +} __attribute__ ((packed)); + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; -- cgit v1.2.2 From 1a3f7d98e5f50f21ce6fb1406a35531d9596c5c6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 4 Aug 2008 16:50:38 -0700 Subject: Revert "UFS: add const to parser token table" This reverts commit f9247273cb69ba101877e946d2d83044409cc8c5 (and fb2e405fc1fc8b20d9c78eaa1c7fd5a297efde43 - "fix fs/nfs/nfsroot.c compilation" - that fixed a missed conversion). The changes cause problems for at least the sparc build. Let's re-do them when the exact issues are resolved. Requested-by: Andrew Morton Requested-by: Steven Whitehouse Cc: David Miller Signed-off-by: Linus Torvalds --- include/linux/parser.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/parser.h b/include/linux/parser.h index cc554ca8bc78..7dcd05075756 100644 --- a/include/linux/parser.h +++ b/include/linux/parser.h @@ -14,7 +14,7 @@ struct match_token { const char *pattern; }; -typedef const struct match_token match_table_t[]; +typedef struct match_token match_table_t[]; /* Maximum number of arguments that match_token will find in a pattern */ enum {MAX_OPT_ARGS = 3}; -- cgit v1.2.2 From 115a326c1e5cab457924356123bbfd7d783ecf9d Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Mon, 4 Aug 2008 13:56:01 -0700 Subject: tracehook: kerneldoc fix My last change to tracehook.h made it confuse the kerneldoc parser. Move the #define's before the comment so it's happy again. Signed-off-by: Roland McGrath Acked-by: Randy Dunlap Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 12532839f508..ab3ef7aefa95 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -487,6 +487,9 @@ static inline int tracehook_notify_jctl(int notify, int why) return notify || (current->ptrace & PT_PTRACED); } +#define DEATH_REAP -1 +#define DEATH_DELAYED_GROUP_LEADER -2 + /** * tracehook_notify_death - task is dead, ready to notify parent * @task: @current task now exiting @@ -501,8 +504,6 @@ static inline int tracehook_notify_jctl(int notify, int why) * * Called with write_lock_irq(&tasklist_lock) held. */ -#define DEATH_REAP -1 -#define DEATH_DELAYED_GROUP_LEADER -2 static inline int tracehook_notify_death(struct task_struct *task, void **death_cookie, int group_dead) { -- cgit v1.2.2 From 529ae9aaa08378cfe2a4350bded76f32cc8ff0ce Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sat, 2 Aug 2008 12:01:03 +0200 Subject: mm: rename page trylock Converting page lock to new locking bitops requires a change of page flag operation naming, so we might as well convert it to something nicer (!TestSetPageLocked_Lock => trylock_page, SetPageLocked => set_page_locked). This also facilitates lockdeping of page lock. Signed-off-by: Nick Piggin Acked-by: KOSAKI Motohiro Acked-by: Peter Zijlstra Acked-by: Andrew Morton Acked-by: Benjamin Herrenschmidt Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- include/linux/pagemap.h | 67 ++++++++++++++++++++++++++++------------------ 2 files changed, 42 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 25aaccdb2f26..c74d3e875314 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -163,7 +163,7 @@ static inline int Page##uname(struct page *page) \ struct page; /* forward declaration */ -PAGEFLAG(Locked, locked) TESTSCFLAG(Locked, locked) +TESTPAGEFLAG(Locked, locked) PAGEFLAG(Error, error) PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 69ed3cb1197a..5da31c12101c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -250,29 +250,6 @@ static inline struct page *read_mapping_page(struct address_space *mapping, return read_cache_page(mapping, index, filler, data); } -int add_to_page_cache_locked(struct page *page, struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask); -int add_to_page_cache_lru(struct page *page, struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask); -extern void remove_from_page_cache(struct page *page); -extern void __remove_from_page_cache(struct page *page); - -/* - * Like add_to_page_cache_locked, but used to add newly allocated pages: - * the page is new, so we can just run SetPageLocked() against it. - */ -static inline int add_to_page_cache(struct page *page, - struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) -{ - int error; - - SetPageLocked(page); - error = add_to_page_cache_locked(page, mapping, offset, gfp_mask); - if (unlikely(error)) - ClearPageLocked(page); - return error; -} - /* * Return byte-offset into filesystem object for page. */ @@ -294,13 +271,28 @@ extern int __lock_page_killable(struct page *page); extern void __lock_page_nosync(struct page *page); extern void unlock_page(struct page *page); +static inline void set_page_locked(struct page *page) +{ + set_bit(PG_locked, &page->flags); +} + +static inline void clear_page_locked(struct page *page) +{ + clear_bit(PG_locked, &page->flags); +} + +static inline int trylock_page(struct page *page) +{ + return !test_and_set_bit(PG_locked, &page->flags); +} + /* * lock_page may only be called if we have the page's inode pinned. */ static inline void lock_page(struct page *page) { might_sleep(); - if (TestSetPageLocked(page)) + if (!trylock_page(page)) __lock_page(page); } @@ -312,7 +304,7 @@ static inline void lock_page(struct page *page) static inline int lock_page_killable(struct page *page) { might_sleep(); - if (TestSetPageLocked(page)) + if (!trylock_page(page)) return __lock_page_killable(page); return 0; } @@ -324,7 +316,7 @@ static inline int lock_page_killable(struct page *page) static inline void lock_page_nosync(struct page *page) { might_sleep(); - if (TestSetPageLocked(page)) + if (!trylock_page(page)) __lock_page_nosync(page); } @@ -409,4 +401,27 @@ static inline int fault_in_pages_readable(const char __user *uaddr, int size) return ret; } +int add_to_page_cache_locked(struct page *page, struct address_space *mapping, + pgoff_t index, gfp_t gfp_mask); +int add_to_page_cache_lru(struct page *page, struct address_space *mapping, + pgoff_t index, gfp_t gfp_mask); +extern void remove_from_page_cache(struct page *page); +extern void __remove_from_page_cache(struct page *page); + +/* + * Like add_to_page_cache_locked, but used to add newly allocated pages: + * the page is new, so we can just run set_page_locked() against it. + */ +static inline int add_to_page_cache(struct page *page, + struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) +{ + int error; + + set_page_locked(page); + error = add_to_page_cache_locked(page, mapping, offset, gfp_mask); + if (unlikely(error)) + clear_page_locked(page); + return error; +} + #endif /* _LINUX_PAGEMAP_H */ -- cgit v1.2.2 From ca5de404ff036a29b25e9a83f6919c9f606c5841 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sat, 2 Aug 2008 12:02:13 +0200 Subject: fs: rename buffer trylock Like the page lock change, this also requires name change, so convert the raw test_and_set bitop to a trylock. Signed-off-by: Nick Piggin Signed-off-by: Linus Torvalds --- include/linux/buffer_head.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 50cfe8ceb478..eadaab44015f 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -115,7 +115,6 @@ BUFFER_FNS(Uptodate, uptodate) BUFFER_FNS(Dirty, dirty) TAS_BUFFER_FNS(Dirty, dirty) BUFFER_FNS(Lock, locked) -TAS_BUFFER_FNS(Lock, locked) BUFFER_FNS(Req, req) TAS_BUFFER_FNS(Req, req) BUFFER_FNS(Mapped, mapped) @@ -321,10 +320,15 @@ static inline void wait_on_buffer(struct buffer_head *bh) __wait_on_buffer(bh); } +static inline int trylock_buffer(struct buffer_head *bh) +{ + return likely(!test_and_set_bit(BH_Lock, &bh->b_state)); +} + static inline void lock_buffer(struct buffer_head *bh) { might_sleep(); - if (test_set_buffer_locked(bh)) + if (!trylock_buffer(bh)) __lock_buffer(bh); } -- cgit v1.2.2 From 378a2f090f7a478704a372a4869b8a9ac206234e Mon Sep 17 00:00:00 2001 From: Jarek Poplawski Date: Mon, 4 Aug 2008 22:31:03 -0700 Subject: net_sched: Add qdisc __NET_XMIT_STOLEN flag Patrick McHardy noticed: "The other problem that affects all qdiscs supporting actions is TC_ACT_QUEUED/TC_ACT_STOLEN getting mapped to NET_XMIT_SUCCESS even though the packet is not queued, corrupting upper qdiscs' qlen counters." and later explained: "The reason why it translates it at all seems to be to not increase the drops counter. Within a single qdisc this could be avoided by other means easily, upper qdiscs would still increase the counter when we return anything besides NET_XMIT_SUCCESS though. This means we need a new NET_XMIT return value to indicate this to the upper qdiscs. So I'd suggest to introduce NET_XMIT_STOLEN, return that to upper qdiscs and translate it to NET_XMIT_SUCCESS in dev_queue_xmit, similar to NET_XMIT_BYPASS." David Miller noticed: "Maybe these NET_XMIT_* values being passed around should be a set of bits. They could be composed of base meanings, combined with specific attributes. So you could say "NET_XMIT_DROP | __NET_XMIT_NO_DROP_COUNT" The attributes get masked out by the top-level ->enqueue() caller, such that the base meanings are the only thing that make their way up into the stack. If it's only about communication within the qdisc tree, let's simply code it that way." This patch is trying to realize these ideas. Signed-off-by: Jarek Poplawski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ee583f642a9f..abbf5d52ec86 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -64,6 +64,7 @@ struct wireless_dev; #define NET_XMIT_BYPASS 4 /* packet does not leave via dequeue; (TC use only - dev_queue_xmit returns this as NET_XMIT_SUCCESS) */ +#define NET_XMIT_MASK 0xFFFF /* qdisc flags in net/sch_generic.h */ /* Backlog congestion levels */ #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ -- cgit v1.2.2 From cc6533e98a7f3cb7fce9d740da49195c7aa523a4 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 4 Aug 2008 23:04:08 -0700 Subject: net: Kill plain NET_XMIT_BYPASS. dst_input() was doing something completely absurd, looping on skb->dst->input() if NET_XMIT_BYPASS was seen, but these functions never return such an error. And as a result plain ole' NET_XMIT_BYPASS has no more references and can be completely killed off. Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index abbf5d52ec86..488c56e649b5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -61,9 +61,6 @@ struct wireless_dev; #define NET_XMIT_DROP 1 /* skb dropped */ #define NET_XMIT_CN 2 /* congestion notification */ #define NET_XMIT_POLICED 3 /* skb is shot by police */ -#define NET_XMIT_BYPASS 4 /* packet does not leave via dequeue; - (TC use only - dev_queue_xmit - returns this as NET_XMIT_SUCCESS) */ #define NET_XMIT_MASK 0xFFFF /* qdisc flags in net/sch_generic.h */ /* Backlog congestion levels */ -- cgit v1.2.2 From 5595cffc8248e4672c5803547445e85e4053c8fc Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 5 Aug 2008 09:28:47 +0300 Subject: SLUB: dynamic per-cache MIN_PARTIAL This patch changes the static MIN_PARTIAL to a dynamic per-cache ->min_partial value that is calculated from object size. The bigger the object size, the more pages we keep on the partial list. I tested SLAB, SLUB, and SLUB with this patch on Jens Axboe's 'netio' example script of the fio benchmarking tool. The script stresses the networking subsystem which should also give a fairly good beating of kmalloc() et al. To run the test yourself, first clone the fio repository: git clone git://git.kernel.dk/fio.git and then run the following command n times on your machine: time ./fio examples/netio The results on my 2-way 64-bit x86 machine are as follows: [ the minimum, maximum, and average are captured from 50 individual runs ] real time (seconds) min max avg sd SLAB 22.76 23.38 22.98 0.17 SLUB 22.80 25.78 23.46 0.72 SLUB (dynamic) 22.74 23.54 23.00 0.20 sys time (seconds) min max avg sd SLAB 6.90 8.28 7.70 0.28 SLUB 7.42 16.95 8.89 2.28 SLUB (dynamic) 7.17 8.64 7.73 0.29 user time (seconds) min max avg sd SLAB 36.89 38.11 37.50 0.29 SLUB 30.85 37.99 37.06 1.67 SLUB (dynamic) 36.75 38.07 37.59 0.32 As you can see from the above numbers, this patch brings SLUB to the same level as SLAB for this particular workload fixing a ~2% regression. I'd expect this change to help similar workloads that allocate a lot of objects that are close to the size of a page. Cc: Matthew Wilcox Cc: Andrew Morton Acked-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 5bad61a93f65..2f5c16b1aacd 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -46,6 +46,7 @@ struct kmem_cache_cpu { struct kmem_cache_node { spinlock_t list_lock; /* Protect partial list and nr_partial */ unsigned long nr_partial; + unsigned long min_partial; struct list_head partial; #ifdef CONFIG_SLUB_DEBUG atomic_long_t nr_slabs; -- cgit v1.2.2 From 39b986a6c73434d122967dc86efb295ab9a28437 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 5 Aug 2008 18:16:57 +0200 Subject: ide: sanitize struct ide_port_ops documentation (take 2) v2: Add missing '@'-s. (Noticed by Randy Dunlap) Cc: Randy Dunlap Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index b846bc44a27e..b1fb15f10a00 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -509,24 +509,33 @@ struct ide_tp_ops { extern const struct ide_tp_ops default_tp_ops; +/** + * struct ide_port_ops - IDE port operations + * + * @init_dev: host specific initialization of a device + * @set_pio_mode: routine to program host for PIO mode + * @set_dma_mode: routine to program host for DMA mode + * @selectproc: tweaks hardware to select drive + * @reset_poll: chipset polling based on hba specifics + * @pre_reset: chipset specific changes to default for device-hba resets + * @resetproc: routine to reset controller after a disk reset + * @maskproc: special host masking for drive selection + * @quirkproc: check host's drive quirk list + * + * @mdma_filter: filter MDMA modes + * @udma_filter: filter UDMA modes + * + * @cable_detect: detect cable type + */ struct ide_port_ops { - /* host specific initialization of a device */ void (*init_dev)(ide_drive_t *); - /* routine to program host for PIO mode */ void (*set_pio_mode)(ide_drive_t *, const u8); - /* routine to program host for DMA mode */ void (*set_dma_mode)(ide_drive_t *, const u8); - /* tweaks hardware to select drive */ void (*selectproc)(ide_drive_t *); - /* chipset polling based on hba specifics */ int (*reset_poll)(ide_drive_t *); - /* chipset specific changes to default for device-hba resets */ void (*pre_reset)(ide_drive_t *); - /* routine to reset controller after a disk reset */ void (*resetproc)(ide_drive_t *); - /* special host masking for drive selection */ void (*maskproc)(ide_drive_t *, int); - /* check host's drive quirk list */ void (*quirkproc)(ide_drive_t *); u8 (*mdma_filter)(ide_drive_t *); -- cgit v1.2.2 From c5bfc3757f1d843a8e1261840c1f53c5062f8e92 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 5 Aug 2008 18:17:01 +0200 Subject: ide: remove CONFIG_IDE_MAX_HWIFS The benefits of a user settable CONFIG_IDE_MAX_HWIFS have become pretty tiny and are no longer considered worth the trouble of an own option. Simply always #define MAX_HWIFS to 10. Signed-off-by: Adrian Bunk Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index b1fb15f10a00..87c12ed96954 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -219,18 +219,7 @@ static inline int __ide_default_irq(unsigned long base) #include #endif -#ifndef MAX_HWIFS -#if defined(CONFIG_BLACKFIN) || defined(CONFIG_H8300) || defined(CONFIG_XTENSA) -# define MAX_HWIFS 1 -#else -# define MAX_HWIFS 10 -#endif -#endif - -#if !defined(MAX_HWIFS) || defined(CONFIG_EMBEDDED) -#undef MAX_HWIFS -#define MAX_HWIFS CONFIG_IDE_MAX_HWIFS -#endif +#define MAX_HWIFS 10 /* Currently only m68k, apus and m8xx need it */ #ifndef IDE_ARCH_ACK_INTR -- cgit v1.2.2 From c6e2bee26eee190b20cd87e71b288bca6a5357a4 Mon Sep 17 00:00:00 2001 From: Bernhard Walle Date: Tue, 5 Aug 2008 13:01:05 -0700 Subject: kdump: report actual value of VMCOREINFO_OSRELEASE in VMCOREINFO The current implementation reports the structure name as VMCOREINFO_OSRELEASE in VMCOREINFO, e.g. VMCOREINFO_OSRELEASE=init_uts_ns.name.release That doesn't make sense because it's always the same. Instead, use the value, e.g. VMCOREINFO_OSRELEASE=2.6.26-rc3 That's also what the 'makedumpfile -g' does. Signed-off-by: Bernhard Walle Cc: "Ken'ichi Ohmichi" Acked-by: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 82f88a8a827b..32110cede64f 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -130,8 +130,8 @@ void vmcoreinfo_append_str(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); unsigned long paddr_vmcoreinfo_note(void); -#define VMCOREINFO_OSRELEASE(name) \ - vmcoreinfo_append_str("OSRELEASE=%s\n", #name) +#define VMCOREINFO_OSRELEASE(value) \ + vmcoreinfo_append_str("OSRELEASE=%s\n", value) #define VMCOREINFO_PAGESIZE(value) \ vmcoreinfo_append_str("PAGESIZE=%ld\n", value) #define VMCOREINFO_SYMBOL(name) \ -- cgit v1.2.2 From 60cadec9da7b6c91aca51f408c828f7e74a68379 Mon Sep 17 00:00:00 2001 From: Shadi Ammouri Date: Tue, 5 Aug 2008 13:01:09 -0700 Subject: spi: new orion_spi driver This adds an SPI driver for the SPI controller found in various Marvell Orion ARM SoCs. It currently supports only one slave, which must use SPI mode 0. [dbrownell@users.sourceforge.net: cleanups, meet specs, pass "sparse"] Signed-off-by: Shadi Ammouri Signed-off-by: Saeed Bishara Signed-off-by: Lennert Buytenhek Signed-off-by: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spi/orion_spi.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/linux/spi/orion_spi.h (limited to 'include/linux') diff --git a/include/linux/spi/orion_spi.h b/include/linux/spi/orion_spi.h new file mode 100644 index 000000000000..b4d9fa6f797c --- /dev/null +++ b/include/linux/spi/orion_spi.h @@ -0,0 +1,17 @@ +/* + * orion_spi.h + * + * 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 __LINUX_SPI_ORION_SPI_H +#define __LINUX_SPI_ORION_SPI_H + +struct orion_spi_info { + u32 tclk; /* no support yet */ +}; + + +#endif -- cgit v1.2.2 From f6ac436dcc4c34709bcde355f3f2254ac0a183d4 Mon Sep 17 00:00:00 2001 From: Mark Asselstine Date: Tue, 5 Aug 2008 13:01:24 -0700 Subject: Remove the deprecated cli() sti() functions These functions have been deprecated for some time now but remained until all legacy callers could be removed. With a few commits in 2.6.26 this has happened so now we can remove these deprecated functions. Signed-off-by: Mark Asselstine Reviewed-by: Matthew Wilcox Cc: Alan Cox Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/interrupt.h | 29 ----------------------------- 1 file changed, 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 62aa4f895abe..58ff4e74b2f3 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -223,35 +223,6 @@ static inline int disable_irq_wake(unsigned int irq) #define or_softirq_pending(x) (local_softirq_pending() |= (x)) #endif -/* - * Temporary defines for UP kernels, until all code gets fixed. - */ -#ifndef CONFIG_SMP -static inline void __deprecated cli(void) -{ - local_irq_disable(); -} -static inline void __deprecated sti(void) -{ - local_irq_enable(); -} -static inline void __deprecated save_flags(unsigned long *x) -{ - local_save_flags(*x); -} -#define save_flags(x) save_flags(&x) -static inline void __deprecated restore_flags(unsigned long x) -{ - local_irq_restore(x); -} - -static inline void __deprecated save_and_cli(unsigned long *x) -{ - local_irq_save(*x); -} -#define save_and_cli(x) save_and_cli(&x) -#endif /* CONFIG_SMP */ - /* Some architectures might implement lazy enabling/disabling of * interrupts. In some cases, such as stop_machine, we might want * to ensure that after a local_irq_disable(), interrupts have -- cgit v1.2.2 From bf1db69fbf4ff511e88736ce2e6318846f34492b Mon Sep 17 00:00:00 2001 From: Richard Hughes Date: Tue, 5 Aug 2008 13:01:35 -0700 Subject: pm_qos: spelling fixes A documentation cleanup patch. With a minor tweak to clarify units for kbs. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: mark gross Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pm_qos_params.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_qos_params.h b/include/linux/pm_qos_params.h index 2e4e97bd19f7..d74f75ed1e47 100644 --- a/include/linux/pm_qos_params.h +++ b/include/linux/pm_qos_params.h @@ -1,6 +1,6 @@ /* interface for the pm_qos_power infrastructure of the linux kernel. * - * Mark Gross + * Mark Gross */ #include #include -- cgit v1.2.2 From f780a9f119caa48088b230836a7fa73d1096de7c Mon Sep 17 00:00:00 2001 From: Yevgeny Petrilin Date: Wed, 6 Aug 2008 20:14:06 -0700 Subject: mlx4_core: Add ethernet fields to CQE struct Add ethernet-related fields to struct mlx4_cqe so that the mlx4_en ethernet NIC driver can share the same definition. Signed-off-by: Yevgeny Petrilin Signed-off-by: Roland Dreier --- include/linux/mlx4/cq.h | 36 ++++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/cq.h b/include/linux/mlx4/cq.h index 071cf96cf01f..6f65b2c8bb89 100644 --- a/include/linux/mlx4/cq.h +++ b/include/linux/mlx4/cq.h @@ -39,17 +39,18 @@ #include struct mlx4_cqe { - __be32 my_qpn; + __be32 vlan_my_qpn; __be32 immed_rss_invalid; __be32 g_mlpath_rqpn; - u8 sl; - u8 reserved1; + __be16 sl_vid; __be16 rlid; - __be32 ipoib_status; + __be16 status; + u8 ipv6_ext_mask; + u8 badfcs_enc; __be32 byte_cnt; __be16 wqe_index; __be16 checksum; - u8 reserved2[3]; + u8 reserved[3]; u8 owner_sr_opcode; }; @@ -63,6 +64,11 @@ struct mlx4_err_cqe { u8 owner_sr_opcode; }; +enum { + MLX4_CQE_VLAN_PRESENT_MASK = 1 << 29, + MLX4_CQE_QPN_MASK = 0xffffff, +}; + enum { MLX4_CQE_OWNER_MASK = 0x80, MLX4_CQE_IS_SEND_MASK = 0x40, @@ -86,13 +92,19 @@ enum { }; enum { - MLX4_CQE_IPOIB_STATUS_IPV4 = 1 << 22, - MLX4_CQE_IPOIB_STATUS_IPV4F = 1 << 23, - MLX4_CQE_IPOIB_STATUS_IPV6 = 1 << 24, - MLX4_CQE_IPOIB_STATUS_IPV4OPT = 1 << 25, - MLX4_CQE_IPOIB_STATUS_TCP = 1 << 26, - MLX4_CQE_IPOIB_STATUS_UDP = 1 << 27, - MLX4_CQE_IPOIB_STATUS_IPOK = 1 << 28, + MLX4_CQE_STATUS_IPV4 = 1 << 6, + MLX4_CQE_STATUS_IPV4F = 1 << 7, + MLX4_CQE_STATUS_IPV6 = 1 << 8, + MLX4_CQE_STATUS_IPV4OPT = 1 << 9, + MLX4_CQE_STATUS_TCP = 1 << 10, + MLX4_CQE_STATUS_UDP = 1 << 11, + MLX4_CQE_STATUS_IPOK = 1 << 12, +}; + +enum { + MLX4_CQE_LLC = 1, + MLX4_CQE_SNAP = 1 << 1, + MLX4_CQE_BAD_FCS = 1 << 4, }; static inline void mlx4_cq_arm(struct mlx4_cq *cq, u32 cmd, -- cgit v1.2.2 From b11f8d8cc3bb2fa6fa55286babc1a5ebb2e932c4 Mon Sep 17 00:00:00 2001 From: Brandon Philips Date: Tue, 15 Jul 2008 02:18:41 -0700 Subject: ethtool: Expand ethtool_cmd.speed to 32 bits Introduce the speed_hi field to ethtool_cmd, using the reserved space, to expand the speed field to 2^32 Megabits/second. Making this field expansion now gives us plenty of time to fix up the user-space pieces that use SIOCETHTOOL before hardware faster than 64 Gb/s is available. Signed-off-by: Brandon Philips Signed-off-by: Jeff Garzik --- include/linux/ethtool.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 8bb5e87df365..b4b038b89ee6 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -27,9 +27,24 @@ struct ethtool_cmd { __u8 autoneg; /* Enable or disable autonegotiation */ __u32 maxtxpkt; /* Tx pkts before generating tx int */ __u32 maxrxpkt; /* Rx pkts before generating rx int */ - __u32 reserved[4]; + __u16 speed_hi; + __u16 reserved2; + __u32 reserved[3]; }; +static inline void ethtool_cmd_speed_set(struct ethtool_cmd *ep, + __u32 speed) +{ + + ep->speed = (__u16)speed; + ep->speed_hi = (__u16)(speed >> 16); +} + +static inline __u32 ethtool_cmd_speed(struct ethtool_cmd *ep) +{ + return (ep->speed_hi << 16) | ep->speed; +} + #define ETHTOOL_BUSINFO_LEN 32 /* these strings are set to whatever the driver author decides... */ struct ethtool_drvinfo { -- cgit v1.2.2 From fe414248551e2880fe8913577699003ff145ab9d Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 23 Jul 2008 17:41:52 +0200 Subject: dm9000: Support MAC address setting through platform data. The dm9000 driver reads the chip's MAC address from the attached EEPROM. When no EEPROM is present, or when the MAC address is invalid, it falls back to reading the address from the chip. This patch lets platform code set the desired MAC address through platform data. Signed-off-by: Laurent Pinchart Signed-off-by: Jeff Garzik --- include/linux/dm9000.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dm9000.h b/include/linux/dm9000.h index fc82446b6425..c30879cf93bc 100644 --- a/include/linux/dm9000.h +++ b/include/linux/dm9000.h @@ -27,6 +27,7 @@ struct dm9000_plat_data { unsigned int flags; + unsigned char dev_addr[6]; /* allow replacement IO routines */ -- cgit v1.2.2 From 7d283aee50351ec19eaf654a8690d77c4e1dff50 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 6 Aug 2008 15:21:26 -0700 Subject: list.h: Add list_splice_tail() and list_splice_tail_init() If you are using linked lists for queues list_splice() will not do what you would expect even if you use the elements passed reversed. We need to handle these differently. We add list_splice_tail() and list_splice_tail_init(). Signed-off-by: Peter Zijlstra Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/linux/list.h | 47 ++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 38 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 453916bc0412..a886f27a1181 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -215,21 +215,21 @@ static inline int list_is_singular(const struct list_head *head) } static inline void __list_splice(const struct list_head *list, - struct list_head *head) + struct list_head *prev, + struct list_head *next) { struct list_head *first = list->next; struct list_head *last = list->prev; - struct list_head *at = head->next; - first->prev = head; - head->next = first; + first->prev = prev; + prev->next = first; - last->next = at; - at->prev = last; + last->next = next; + next->prev = last; } /** - * list_splice - join two lists + * list_splice - join two lists, this is designed for stacks * @list: the new list to add. * @head: the place to add it in the first list. */ @@ -237,7 +237,19 @@ static inline void list_splice(const struct list_head *list, struct list_head *head) { if (!list_empty(list)) - __list_splice(list, head); + __list_splice(list, head, head->next); +} + +/** + * list_splice_tail - join two lists, each list being a queue + * @list: the new list to add. + * @head: the place to add it in the first list. + */ +static inline void list_splice_tail(struct list_head *list, + struct list_head *head) +{ + if (!list_empty(list)) + __list_splice(list, head->prev, head); } /** @@ -251,7 +263,24 @@ static inline void list_splice_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { - __list_splice(list, head); + __list_splice(list, head, head->next); + INIT_LIST_HEAD(list); + } +} + +/** + * list_splice_tail_init - join two lists, each list being a queue, and + * reinitialise the emptied list. + * @list: the new list to add. + * @head: the place to add it in the first list. + * + * The list at @list is reinitialised + */ +static inline void list_splice_tail_init(struct list_head *list, + struct list_head *head) +{ + if (!list_empty(list)) { + __list_splice(list, head->prev, head); INIT_LIST_HEAD(list); } } -- cgit v1.2.2 From 00e8a4da8cf0d7dba8cc4b0da28ea0f12dcf6b36 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 6 Aug 2008 13:28:54 -0700 Subject: list.h: add list_cut_position() This adds list_cut_position() which lets you cut a list into two lists given a pivot in the list. Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/linux/list.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index a886f27a1181..1d109e2ef0a9 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -214,6 +214,46 @@ static inline int list_is_singular(const struct list_head *head) return !list_empty(head) && (head->next == head->prev); } +static inline void __list_cut_position(struct list_head *list, + struct list_head *head, struct list_head *entry) +{ + struct list_head *new_first = entry->next; + list->next = head->next; + list->next->prev = list; + list->prev = entry; + entry->next = list; + head->next = new_first; + new_first->prev = head; +} + +/** + * list_cut_position - cut a list into two + * @list: a new list to add all removed entries + * @head: a list with entries + * @entry: an entry within head, could be the head itself + * and if so we won't cut the list + * + * This helper moves the initial part of @head, up to and + * including @entry, from @head to @list. You should + * pass on @entry an element you know is on @head. @list + * should be an empty list or a list you do not care about + * losing its data. + * + */ +static inline void list_cut_position(struct list_head *list, + struct list_head *head, struct list_head *entry) +{ + if (list_empty(head)) + return; + if (list_is_singular(head) && + (head->next != entry && head != entry)) + return; + if (entry == head) + INIT_LIST_HEAD(list); + else + __list_cut_position(list, head, entry); +} + static inline void __list_splice(const struct list_head *list, struct list_head *prev, struct list_head *next) -- cgit v1.2.2 From bba81165867313766534dd31603de51bdd36ef9b Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 30 Jul 2008 12:07:04 -0700 Subject: PCI: make pci_register_driver() a macro alpha: CC [M] drivers/usb/gadget/u_ether.o In file included from include/asm/dma-mapping.h:7, from include/linux/dma-mapping.h:52, from include/linux/dmaengine.h:29, from include/linux/skbuff.h:29, from include/linux/if_ether.h:114, from include/linux/etherdevice.h:27, from drivers/usb/gadget/u_ether.c:29: include/linux/pci.h: In function 'pci_register_driver': include/linux/pci.h:673: error: 'KBUILD_MODNAME' undeclared (first use in this function) include/linux/pci.h:673: error: (Each undeclared identifier is reported only once include/linux/pci.h:673: error: for each function it appears in.) Sam says: The problem is that u_ether.o is used by two modules so when we build it KBUILD_MODNAME is not defined because kbuild does not know what value to use. And in pci.h we have the following inline: static inline int __must_check pci_register_driver(struct pci_driver *driver) { return __pci_register_driver(driver, THIS_MODULE, KBUILD_MODNAME); } And alpha uses dma-mapping.h to nullify a number of functions that seem to require something from pci.h. Making it a macro fixes this particular problem. However, the underlying issue of a file using KBUILD_MODNAME and being shared between multiple modules is *not* addressed. I guess the answer there is "don't do that". Cc: Sam Ravnborg Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Jesse Barnes --- include/linux/pci.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 825be3878f68..b0269492c34e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -680,10 +680,12 @@ void pci_enable_bridges(struct pci_bus *bus); /* Proper probing supporting hot-pluggable devices */ int __must_check __pci_register_driver(struct pci_driver *, struct module *, const char *mod_name); -static inline int __must_check pci_register_driver(struct pci_driver *driver) -{ - return __pci_register_driver(driver, THIS_MODULE, KBUILD_MODNAME); -} + +/* + * pci_register_driver must be a macro so that KBUILD_MODNAME can be expanded + */ +#define pci_register_driver(driver) \ + __pci_register_driver(driver, THIS_MODULE, KBUILD_MODNAME) void pci_unregister_driver(struct pci_driver *dev); void pci_remove_behind_bridge(struct pci_dev *dev); -- cgit v1.2.2 From 7bed523a95425b70af7a59df61d5adb422ef2038 Mon Sep 17 00:00:00 2001 From: "akpm@linux-foundation.org" Date: Tue, 5 Aug 2008 14:07:53 -0700 Subject: PCI: remove duplicate symbol from pci_ids.h pci.ids.h: remove a duplicated symbol Cc: Doug Thompson Signed-off-by: Grant Coady Signed-off-by: Andrew Morton Signed-off-by: Jesse Barnes --- include/linux/pci_ids.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 35a78415accc..9ec2bcce8e83 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2177,8 +2177,6 @@ #define PCI_DEVICE_ID_HERC_WIN 0x5732 #define PCI_DEVICE_ID_HERC_UNI 0x5832 -#define PCI_VENDOR_ID_RDC 0x17f3 - #define PCI_VENDOR_ID_SITECOM 0x182d #define PCI_DEVICE_ID_SITECOM_DC105V2 0x3069 -- cgit v1.2.2 From 5a6c9b60b4cc15b22d3102b0033e5cb842125456 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 8 Aug 2008 00:14:24 +0200 Subject: PCI PM: Export pci_pme_active to drivers Export pci_pme_active() to drivers, so that they can clear the PME_status bit and disable PME# for their devices without involving ACPI. Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index b0269492c34e..c0e14008a3c2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -641,6 +641,7 @@ int pci_restore_state(struct pci_dev *dev); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); +void pci_pme_active(struct pci_dev *dev, bool enable); int pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable); pci_power_t pci_target_state(struct pci_dev *dev); int pci_prepare_to_sleep(struct pci_dev *dev); -- cgit v1.2.2 From 5861bbfcc10fc0358abf52c7d22850c8d180f0b0 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Thu, 7 Aug 2008 16:55:03 -0700 Subject: tracehook: fix CLONE_PTRACE In the change in commit 09a05394fe2448a4139b014936330af23fa7ec83, I overlooked two nits in the logic and this broke using CLONE_PTRACE when PTRACE_O_TRACE* are not being used. A parent that is itself traced at all but not using PTRACE_O_TRACE*, using CLONE_PTRACE would have its new child fail to be traced. A parent that is not itself traced at all that uses CLONE_PTRACE (which should be a no-op in this case) would confuse the bookkeeping and lead to a crash at exit time. This restores the missing checks and fixes both failure modes. Reported-by: Eduardo Habkost Signed-off-by: Roland McGrath --- include/linux/ptrace.h | 2 +- include/linux/tracehook.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index fd31756e1a00..ea7416c901d1 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -172,7 +172,7 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) child->ptrace = 0; if (unlikely(ptrace)) { child->ptrace = current->ptrace; - __ptrace_link(child, current->parent); + ptrace_link(child, current->parent); } } diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index ab3ef7aefa95..b48d81969574 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -280,7 +280,7 @@ static inline void tracehook_report_clone(int trace, struct pt_regs *regs, unsigned long clone_flags, pid_t pid, struct task_struct *child) { - if (unlikely(trace)) { + if (unlikely(trace) || unlikely(clone_flags & CLONE_PTRACE)) { /* * The child starts up with an immediate SIGSTOP. */ -- cgit v1.2.2 From 2727f226a65e034f93846def7fab314dee430df3 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 8 Aug 2008 15:13:27 +0100 Subject: [ARM] fix pnx4008 build errors include/linux/i2c-pnx.h was missed when moving the include files. Fix it now; it doesn't really need to include mach/i2c.h at all. Successfully build tested with pnx4008_defconfig, which had failed in linux-next. Signed-off-by: Russell King --- include/linux/i2c-pnx.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c-pnx.h b/include/linux/i2c-pnx.h index e6e9c814da61..f13255e06406 100644 --- a/include/linux/i2c-pnx.h +++ b/include/linux/i2c-pnx.h @@ -12,7 +12,9 @@ #ifndef __I2C_PNX_H__ #define __I2C_PNX_H__ -#include +#include + +struct platform_device; struct i2c_pnx_mif { int ret; /* Return value */ -- cgit v1.2.2 From 6724cce8fb4b408ae1a2fab455050f3407c80144 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 8 Aug 2008 13:56:20 -0700 Subject: list.h: fix fatal kernel-doc error Fix fatal multi-line kernel-doc error in list.h: function short description must be on one line. Error(linux-2.6.27-rc2-git3//include/linux/list.h:318): duplicate section name 'Description' Signed-off-by: Randy Dunlap Signed-off-by: Linus Torvalds --- include/linux/list.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 1d109e2ef0a9..db35ef02e745 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -309,11 +309,11 @@ static inline void list_splice_init(struct list_head *list, } /** - * list_splice_tail_init - join two lists, each list being a queue, and - * reinitialise the emptied list. + * list_splice_tail_init - join two lists and reinitialise the emptied list * @list: the new list to add. * @head: the place to add it in the first list. * + * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void list_splice_tail_init(struct list_head *list, -- cgit v1.2.2 From d3a2f71853ce543c5515d4982e202751e15b0b6d Mon Sep 17 00:00:00 2001 From: Ian Molton Date: Thu, 31 Jul 2008 20:44:28 +0200 Subject: mfd: TMIO MMC structures and accessors. Signed-off-by: Ian Molton Signed-off-by: Samuel Ortiz --- include/linux/mfd/tmio.h | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 9438d8c9ac1c..ec612e66391c 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -1,6 +1,21 @@ #ifndef MFD_TMIO_H #define MFD_TMIO_H +#define tmio_ioread8(addr) readb(addr) +#define tmio_ioread16(addr) readw(addr) +#define tmio_ioread16_rep(r, b, l) readsw(r, b, l) +#define tmio_ioread32(addr) \ + (((u32) readw((addr))) | (((u32) readw((addr) + 2)) << 16)) + +#define tmio_iowrite8(val, addr) writeb((val), (addr)) +#define tmio_iowrite16(val, addr) writew((val), (addr)) +#define tmio_iowrite16_rep(r, b, l) writesw(r, b, l) +#define tmio_iowrite32(val, addr) \ + do { \ + writew((val), (addr)); \ + writew((val) >> 16, (addr) + 2); \ + } while (0) + /* * data for the NAND controller */ @@ -10,8 +25,4 @@ struct tmio_nand_data { unsigned int num_partitions; }; -#define TMIO_NAND_CONFIG "tmio-nand-config" -#define TMIO_NAND_CONTROL "tmio-nand-control" -#define TMIO_NAND_IRQ "tmio-nand" - #endif -- cgit v1.2.2 From 1f192015ca5b2f4d0a79c191f03f64e72fd8fc29 Mon Sep 17 00:00:00 2001 From: Ian Molton Date: Tue, 15 Jul 2008 15:09:43 +0100 Subject: mfd: driver for the T7L66XB TMIO SoC This patchset provides support for the core functinality of the T7L66XB SoC from Toshiba. Supported in this patchset is the IRQ MUX, MMC controller and NAND flash controller. Signed-off-by: Ian Molton Signed-off-by: Samuel Ortiz --- include/linux/mfd/t7l66xb.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 include/linux/mfd/t7l66xb.h (limited to 'include/linux') diff --git a/include/linux/mfd/t7l66xb.h b/include/linux/mfd/t7l66xb.h new file mode 100644 index 000000000000..e83c7f2036f9 --- /dev/null +++ b/include/linux/mfd/t7l66xb.h @@ -0,0 +1,36 @@ +/* + * This file contains the definitions for the T7L66XB + * + * (C) Copyright 2005 Ian Molton + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#ifndef MFD_T7L66XB_H +#define MFD_T7L66XB_H + +#include +#include + +struct t7l66xb_platform_data { + int (*enable_clk32k)(struct platform_device *dev); + void (*disable_clk32k)(struct platform_device *dev); + int (*enable)(struct platform_device *dev); + int (*disable)(struct platform_device *dev); + int (*suspend)(struct platform_device *dev); + int (*resume)(struct platform_device *dev); + + int irq_base; /* The base for subdevice irqs */ + + struct tmio_nand_data *nand_data; +}; + + +#define IRQ_T7L66XB_MMC (1) +#define IRQ_T7L66XB_NAND (3) + +#define T7L66XB_NR_IRQS 8 + +#endif -- cgit v1.2.2 From cbdfb426392557d49b1a0e7cb59b16c20dc42955 Mon Sep 17 00:00:00 2001 From: Ian Molton Date: Tue, 15 Jul 2008 15:12:52 +0100 Subject: mfd: driver for the TC6387XB TMIO controller. This patch adds support for the TC6387XB. Unlike other TMIO devices this one has only one subdevice and no interrupt mux, however using the MFD framework allows it to share the TMIO MMC driver. Signed-off-by: Ian Molton Signed-off-by: Samuel Ortiz --- include/linux/mfd/tc6387xb.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 include/linux/mfd/tc6387xb.h (limited to 'include/linux') diff --git a/include/linux/mfd/tc6387xb.h b/include/linux/mfd/tc6387xb.h new file mode 100644 index 000000000000..fa06e0610b8e --- /dev/null +++ b/include/linux/mfd/tc6387xb.h @@ -0,0 +1,23 @@ +/* + * This file contains the definitions for the TC6387XB + * + * (C) Copyright 2005 Ian Molton + * + * May be copied or modified under the terms of the GNU General Public + * License. See linux/COPYING for more information. + * + */ +#ifndef MFD_TC6387XB_H +#define MFD_TC6387XB_H + +struct tc6387xb_platform_data { + int (*enable_clk32k)(struct platform_device *dev); + void (*disable_clk32k)(struct platform_device *dev); + + int (*enable)(struct platform_device *dev); + int (*disable)(struct platform_device *dev); + int (*suspend)(struct platform_device *dev); + int (*resume)(struct platform_device *dev); +}; + +#endif -- cgit v1.2.2 From 25d6cbd840d958aada29a342c9ee370590ff7b21 Mon Sep 17 00:00:00 2001 From: Ian Molton Date: Sun, 10 Aug 2008 23:32:07 +0200 Subject: mfd: tc6393 cleanup and update This patchset cleans up the TC6393XB support. * Add provision for the MMC subdevice * Disable / enable clocks on suspend / resume * Remove fragments of badly merged code (eg. linux/fb include etc.) * Use a device specific clock name to break dependancy on ARM/PXA2XX * Drop unnecessary resource names * Switch to tmio_io* accessors Signed-off-by: Ian Molton Signed-off-by: Samuel Ortiz --- include/linux/mfd/tc6393xb.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tc6393xb.h b/include/linux/mfd/tc6393xb.h index 7cc824a58f7c..fec7b3f7a81f 100644 --- a/include/linux/mfd/tc6393xb.h +++ b/include/linux/mfd/tc6393xb.h @@ -14,8 +14,8 @@ * published by the Free Software Foundation. */ -#ifndef TC6393XB_H -#define TC6393XB_H +#ifndef MFD_TC6393XB_H +#define MFD_TC6393XB_H /* Also one should provide the CK3P6MI clock */ struct tc6393xb_platform_data { @@ -29,7 +29,7 @@ struct tc6393xb_platform_data { int (*suspend)(struct platform_device *dev); int (*resume)(struct platform_device *dev); - int irq_base; /* a base for cascaded irq */ + int irq_base; /* base for subdevice irqs */ int gpio_base; struct tmio_nand_data *nand_data; @@ -40,9 +40,6 @@ struct tc6393xb_platform_data { */ #define IRQ_TC6393_NAND 0 #define IRQ_TC6393_MMC 1 -#define IRQ_TC6393_OHCI 2 -#define IRQ_TC6393_SERIAL 3 -#define IRQ_TC6393_FB 4 #define TC6393XB_NR_IRQS 8 -- cgit v1.2.2 From c1955a3d4762e7a9bf84035eb3c4886a900f0d15 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 11 Aug 2008 08:59:03 +0200 Subject: sched_clock: delay using sched_clock() Some arch's can't handle sched_clock() being called too early - delay this until sched_clock_init() has been called. Reported-by: Bill Gatliff Signed-off-by: Peter Zijlstra Tested-by: Nishanth Aravamudan CC: Russell King - ARM Linux Signed-off-by: Ingo Molnar --- include/linux/sched.h | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ea436bc1a0e2..5850bfb968a8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1551,16 +1551,10 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) extern unsigned long long sched_clock(void); -#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -static inline void sched_clock_init(void) -{ -} - -static inline u64 sched_clock_cpu(int cpu) -{ - return sched_clock(); -} +extern void sched_clock_init(void); +extern u64 sched_clock_cpu(int cpu); +#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK static inline void sched_clock_tick(void) { } @@ -1573,8 +1567,6 @@ static inline void sched_clock_idle_wakeup_event(u64 delta_ns) { } #else -extern void sched_clock_init(void); -extern u64 sched_clock_cpu(int cpu); extern void sched_clock_tick(void); extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); -- cgit v1.2.2 From 64aa348edc617dea17bbd01ddee4e47886d5ec8c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 11 Aug 2008 09:30:21 +0200 Subject: lockdep: lock_set_subclass - reset a held lock's subclass this can be used to reset a held lock's subclass, for arbitrary-depth iterated data structures such as trees or lists which have per-node locks. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 1bfdc30bb0af..f270ce1582ff 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -300,6 +300,9 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, extern void lock_release(struct lockdep_map *lock, int nested, unsigned long ip); +extern void lock_set_subclass(struct lockdep_map *lock, unsigned int subclass, + unsigned long ip); + # define INIT_LOCKDEP .lockdep_recursion = 0, #define lockdep_depth(tsk) (debug_locks ? (tsk)->lockdep_depth : 0) @@ -316,6 +319,7 @@ static inline void lockdep_on(void) # define lock_acquire(l, s, t, r, c, i) do { } while (0) # define lock_release(l, n, i) do { } while (0) +# define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) # define lockdep_info() do { } while (0) # define lockdep_init_map(lock, name, key, sub) do { (void)(key); } while (0) -- cgit v1.2.2 From f82b217e3513fe3af342c0f3ee1494e86250c21c Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Mon, 11 Aug 2008 09:30:23 +0200 Subject: lockdep: shrink held_lock structure struct held_lock { u64 prev_chain_key; /* 0 8 */ struct lock_class * class; /* 8 8 */ long unsigned int acquire_ip; /* 16 8 */ struct lockdep_map * instance; /* 24 8 */ int irq_context; /* 32 4 */ int trylock; /* 36 4 */ int read; /* 40 4 */ int check; /* 44 4 */ int hardirqs_off; /* 48 4 */ /* size: 56, cachelines: 1 */ /* padding: 4 */ /* last cacheline: 56 bytes */ }; struct held_lock { u64 prev_chain_key; /* 0 8 */ long unsigned int acquire_ip; /* 8 8 */ struct lockdep_map * instance; /* 16 8 */ unsigned int class_idx:11; /* 24:21 4 */ unsigned int irq_context:2; /* 24:19 4 */ unsigned int trylock:1; /* 24:18 4 */ unsigned int read:2; /* 24:16 4 */ unsigned int check:2; /* 24:14 4 */ unsigned int hardirqs_off:1; /* 24:13 4 */ /* size: 32, cachelines: 1 */ /* padding: 4 */ /* bit_padding: 13 bits */ /* last cacheline: 32 bytes */ }; [mingo@elte.hu: shrunk hlock->class too] [peterz@infradead.org: fixup bit sizes] Signed-off-by: Dave Jones Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra --- include/linux/lockdep.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index f270ce1582ff..b49bfa8e4a5c 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -190,6 +190,9 @@ struct lock_chain { u64 chain_key; }; +#define MAX_LOCKDEP_KEYS_BITS 11 +#define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS) + struct held_lock { /* * One-way hash of the dependency chain up to this point. We @@ -206,14 +209,13 @@ struct held_lock { * with zero), here we store the previous hash value: */ u64 prev_chain_key; - struct lock_class *class; unsigned long acquire_ip; struct lockdep_map *instance; - #ifdef CONFIG_LOCK_STAT u64 waittime_stamp; u64 holdtime_stamp; #endif + unsigned int class_idx:MAX_LOCKDEP_KEYS_BITS; /* * The lock-stack is unified in that the lock chains of interrupt * contexts nest ontop of process context chains, but we 'separate' @@ -227,11 +229,11 @@ struct held_lock { * The following field is used to detect when we cross into an * interrupt context: */ - int irq_context; - int trylock; - int read; - int check; - int hardirqs_off; + unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */ + unsigned int trylock:1; + unsigned int read:2; /* see lock_acquire() comment */ + unsigned int check:2; /* see lock_acquire() comment */ + unsigned int hardirqs_off:1; }; /* -- cgit v1.2.2 From 4f3e7524b2e703d9f8b02ac338153a53dd7ede66 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 11 Aug 2008 09:30:23 +0200 Subject: lockdep: map_acquire Most the free-standing lock_acquire() usages look remarkably similar, sweep them into a new helper. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index b49bfa8e4a5c..e431d1d6eaf3 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -459,4 +459,16 @@ static inline void print_irqtrace_events(struct task_struct *curr) # define rwsem_release(l, n, i) do { } while (0) #endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# ifdef CONFIG_PROVE_LOCKING +# define map_acquire(l) lock_acquire(l, 0, 0, 0, 2, _THIS_IP_) +# else +# define map_acquire(l) lock_acquire(l, 0, 0, 0, 1, _THIS_IP_) +# endif +# define map_release(l) lock_release(l, 1, _THIS_IP_) +#else +# define map_acquire(l) do { } while (0) +# define map_release(l) do { } while (0) +#endif + #endif /* __LINUX_LOCKDEP_H */ -- cgit v1.2.2 From 7531e2f34d1d551b096143f19111139f0dd84c8b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 11 Aug 2008 09:30:24 +0200 Subject: lockdep: lock protection locks On Fri, 2008-08-01 at 16:26 -0700, Linus Torvalds wrote: > On Fri, 1 Aug 2008, David Miller wrote: > > > > Taking more than a few locks of the same class at once is bad > > news and it's better to find an alternative method. > > It's not always wrong. > > If you can guarantee that anybody that takes more than one lock of a > particular class will always take a single top-level lock _first_, then > that's all good. You can obviously screw up and take the same lock _twice_ > (which will deadlock), but at least you cannot get into ABBA situations. > > So maybe the right thing to do is to just teach lockdep about "lock > protection locks". That would have solved the multi-queue issues for > networking too - all the actual network drivers would still have taken > just their single queue lock, but the one case that needs to take all of > them would have taken a separate top-level lock first. > > Never mind that the multi-queue locks were always taken in the same order: > it's never wrong to just have some top-level serialization, and anybody > who needs to take locks might as well do , because they sure as > hell aren't going to be on _any_ fastpaths. > > So the simplest solution really sounds like just teaching lockdep about > that one special case. It's not "nesting" exactly, although it's obviously > related to it. Do as Linus suggested. The lock protection lock is called nest_lock. Note that we still have the MAX_LOCK_DEPTH (48) limit to consider, so anything that spills that it still up shit creek. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 34 ++++++++++++++++++---------------- include/linux/rcuclassic.h | 2 +- 2 files changed, 19 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index e431d1d6eaf3..93a8cc02a033 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -211,6 +211,7 @@ struct held_lock { u64 prev_chain_key; unsigned long acquire_ip; struct lockdep_map *instance; + struct lockdep_map *nest_lock; #ifdef CONFIG_LOCK_STAT u64 waittime_stamp; u64 holdtime_stamp; @@ -297,7 +298,8 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name, * 2: full validation */ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, - int trylock, int read, int check, unsigned long ip); + int trylock, int read, int check, + struct lockdep_map *nest_lock, unsigned long ip); extern void lock_release(struct lockdep_map *lock, int nested, unsigned long ip); @@ -319,7 +321,7 @@ static inline void lockdep_on(void) { } -# define lock_acquire(l, s, t, r, c, i) do { } while (0) +# define lock_acquire(l, s, t, r, c, n, i) do { } while (0) # define lock_release(l, n, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) @@ -407,9 +409,9 @@ static inline void print_irqtrace_events(struct task_struct *curr) #ifdef CONFIG_DEBUG_LOCK_ALLOC # ifdef CONFIG_PROVE_LOCKING -# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, i) +# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) # else -# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, i) +# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) # endif # define spin_release(l, n, i) lock_release(l, n, i) #else @@ -419,11 +421,11 @@ static inline void print_irqtrace_events(struct task_struct *curr) #ifdef CONFIG_DEBUG_LOCK_ALLOC # ifdef CONFIG_PROVE_LOCKING -# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, i) -# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 2, i) +# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) +# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 2, NULL, i) # else -# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, i) -# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 1, i) +# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) +# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 1, NULL, i) # endif # define rwlock_release(l, n, i) lock_release(l, n, i) #else @@ -434,9 +436,9 @@ static inline void print_irqtrace_events(struct task_struct *curr) #ifdef CONFIG_DEBUG_LOCK_ALLOC # ifdef CONFIG_PROVE_LOCKING -# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, i) +# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) # else -# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, i) +# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) # endif # define mutex_release(l, n, i) lock_release(l, n, i) #else @@ -446,11 +448,11 @@ static inline void print_irqtrace_events(struct task_struct *curr) #ifdef CONFIG_DEBUG_LOCK_ALLOC # ifdef CONFIG_PROVE_LOCKING -# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, i) -# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 2, i) +# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) +# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 2, NULL, i) # else -# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, i) -# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 1, i) +# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) +# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 1, NULL, i) # endif # define rwsem_release(l, n, i) lock_release(l, n, i) #else @@ -461,9 +463,9 @@ static inline void print_irqtrace_events(struct task_struct *curr) #ifdef CONFIG_DEBUG_LOCK_ALLOC # ifdef CONFIG_PROVE_LOCKING -# define map_acquire(l) lock_acquire(l, 0, 0, 0, 2, _THIS_IP_) +# define map_acquire(l) lock_acquire(l, 0, 0, 0, 2, NULL, _THIS_IP_) # else -# define map_acquire(l) lock_acquire(l, 0, 0, 0, 1, _THIS_IP_) +# define map_acquire(l) lock_acquire(l, 0, 0, 0, 1, NULL, _THIS_IP_) # endif # define map_release(l) lock_release(l, 1, _THIS_IP_) #else diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h index 8c774905dcfe..4ab843622727 100644 --- a/include/linux/rcuclassic.h +++ b/include/linux/rcuclassic.h @@ -117,7 +117,7 @@ extern int rcu_needs_cpu(int cpu); #ifdef CONFIG_DEBUG_LOCK_ALLOC extern struct lockdep_map rcu_lock_map; # define rcu_read_acquire() \ - lock_acquire(&rcu_lock_map, 0, 0, 2, 1, _THIS_IP_) + lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) # define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_) #else # define rcu_read_acquire() do { } while (0) -- cgit v1.2.2 From b7d39aff91454f2534db2275f55908656ec0470c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 11 Aug 2008 09:30:24 +0200 Subject: lockdep: spin_lock_nest_lock() Expose the new lock protection lock. This can be used to annotate places where we take multiple locks of the same class and avoid deadlocks by always taking another (top-level) lock first. NOTE: we're still bound to the MAX_LOCK_DEPTH (48) limit. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 2 ++ include/linux/spinlock.h | 6 ++++++ include/linux/spinlock_api_smp.h | 2 ++ 3 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 93a8cc02a033..4452c04a7f6e 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -410,8 +410,10 @@ static inline void print_irqtrace_events(struct task_struct *curr) #ifdef CONFIG_DEBUG_LOCK_ALLOC # ifdef CONFIG_PROVE_LOCKING # define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) +# define spin_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) # else # define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) +# define spin_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, NULL, i) # endif # define spin_release(l, n, i) lock_release(l, n, i) #else diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 61e5610ad165..e0c0fccced46 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -183,8 +183,14 @@ do { \ #ifdef CONFIG_DEBUG_LOCK_ALLOC # define spin_lock_nested(lock, subclass) _spin_lock_nested(lock, subclass) +# define spin_lock_nest_lock(lock, nest_lock) \ + do { \ + typecheck(struct lockdep_map *, &(nest_lock)->dep_map);\ + _spin_lock_nest_lock(lock, &(nest_lock)->dep_map); \ + } while (0) #else # define spin_lock_nested(lock, subclass) _spin_lock(lock) +# define spin_lock_nest_lock(lock, nest_lock) _spin_lock(lock) #endif #define write_lock(lock) _write_lock(lock) diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 8a2307ce7296..d79845d034b5 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -22,6 +22,8 @@ int in_lock_functions(unsigned long addr); void __lockfunc _spin_lock(spinlock_t *lock) __acquires(lock); void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass) __acquires(lock); +void __lockfunc _spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *map) + __acquires(lock); void __lockfunc _read_lock(rwlock_t *lock) __acquires(lock); void __lockfunc _write_lock(rwlock_t *lock) __acquires(lock); void __lockfunc _spin_lock_bh(spinlock_t *lock) __acquires(lock); -- cgit v1.2.2 From 3295f0ef9ff048a4619ede597ad9ec9cab725654 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 11 Aug 2008 10:30:30 +0200 Subject: lockdep: rename map_[acquire|release]() => lock_map_[acquire|release]() the names were too generic: drivers/uio/uio.c:87: error: expected identifier or '(' before 'do' drivers/uio/uio.c:87: error: expected identifier or '(' before 'while' drivers/uio/uio.c:113: error: 'map_release' undeclared here (not in a function) Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 4452c04a7f6e..67f42b300c65 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -465,14 +465,14 @@ static inline void print_irqtrace_events(struct task_struct *curr) #ifdef CONFIG_DEBUG_LOCK_ALLOC # ifdef CONFIG_PROVE_LOCKING -# define map_acquire(l) lock_acquire(l, 0, 0, 0, 2, NULL, _THIS_IP_) +# define lock_map_acquire(l) lock_acquire(l, 0, 0, 0, 2, NULL, _THIS_IP_) # else -# define map_acquire(l) lock_acquire(l, 0, 0, 0, 1, NULL, _THIS_IP_) +# define lock_map_acquire(l) lock_acquire(l, 0, 0, 0, 1, NULL, _THIS_IP_) # endif -# define map_release(l) lock_release(l, 1, _THIS_IP_) +# define lock_map_release(l) lock_release(l, 1, _THIS_IP_) #else -# define map_acquire(l) do { } while (0) -# define map_release(l) do { } while (0) +# define lock_map_acquire(l) do { } while (0) +# define lock_map_release(l) do { } while (0) #endif #endif /* __LINUX_LOCKDEP_H */ -- cgit v1.2.2 From b42e737e576339c795d9ac77a1fce6057f6bc0cf Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 11 Aug 2008 12:34:42 +0200 Subject: lockdep: fix overflow in the hlock shrinkage code There is a overflow by 1 case in the new shrunken hlock code. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 67f42b300c65..c88aa3d8e87f 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -191,7 +191,12 @@ struct lock_chain { }; #define MAX_LOCKDEP_KEYS_BITS 11 -#define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS) +/* + * Subtract one because we offset hlock->class_idx by 1 in order + * to make 0 mean no class. This avoids overflowing the class_idx + * bitfield and hitting the BUG in hlock_class(). + */ +#define MAX_LOCKDEP_KEYS ((1UL << MAX_LOCKDEP_KEYS_BITS) - 1) struct held_lock { /* -- cgit v1.2.2 From 13fa00a8780885edcdf0bc53b81e5d0fec71119a Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 11 Aug 2008 20:59:59 +1000 Subject: powerpc: Remove include/linux/harrier_defs.h It was only used by code in arch/ppc, and arch/ppc is gone, so remove the unused harrier_defs.h as well. Signed-off-by: Paul Mackerras --- include/linux/harrier_defs.h | 212 ------------------------------------------- 1 file changed, 212 deletions(-) delete mode 100644 include/linux/harrier_defs.h (limited to 'include/linux') diff --git a/include/linux/harrier_defs.h b/include/linux/harrier_defs.h deleted file mode 100644 index efef11db790f..000000000000 --- a/include/linux/harrier_defs.h +++ /dev/null @@ -1,212 +0,0 @@ -/* - * include/linux/harrier_defs.h - * - * Definitions for Motorola MCG Harrier North Bridge & Memory controller - * - * Author: Dale Farnsworth - * dale.farnsworth@mvista.com - * - * Extracted from asm-ppc/harrier.h by: - * Randy Vinson - * rvinson@mvista.com - * - * Copyright 2001-2002 MontaVista Software Inc. - * - * 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 __ASMPPC_HARRIER_DEFS_H -#define __ASMPPC_HARRIER_DEFS_H - -#define HARRIER_DEFAULT_XCSR_BASE 0xfeff0000 - -#define HARRIER_VEND_DEV_ID 0x1057480b - -#define HARRIER_VENI_OFF 0x00 - -#define HARRIER_REVI_OFF 0x05 -#define HARRIER_UCTL_OFF 0xd0 -#define HARRIER_XTAL64_MASK 0x02 - -#define HARRIER_MISC_CSR_OFF 0x1c -#define HARRIER_RSTOUT 0x01000000 -#define HARRIER_SYSCON 0x08000000 -#define HARRIER_EREADY 0x10000000 -#define HARRIER_ERDYS 0x20000000 - -/* Function exception registers */ -#define HARRIER_FEEN_OFF 0x40 /* enable */ -#define HARRIER_FEST_OFF 0x44 /* status */ -#define HARRIER_FEMA_OFF 0x48 /* mask */ -#define HARRIER_FECL_OFF 0x4c /* clear */ - -#define HARRIER_FE_DMA 0x80 -#define HARRIER_FE_MIDB 0x40 -#define HARRIER_FE_MIM0 0x20 -#define HARRIER_FE_MIM1 0x10 -#define HARRIER_FE_MIP 0x08 -#define HARRIER_FE_UA0 0x04 -#define HARRIER_FE_UA1 0x02 -#define HARRIER_FE_ABT 0x01 - -#define HARRIER_SERIAL_0_OFF 0xc0 - -#define HARRIER_MBAR_OFF 0xe0 -#define HARRIER_MBAR_MSK 0xfffc0000 -#define HARRIER_MPIC_CSR_OFF 0xe4 -#define HARRIER_MPIC_OPI_ENABLE 0x40 -#define HARRIER_MPIC_IFEVP_OFF 0x10200 -#define HARRIER_MPIC_IFEVP_VECT_MSK 0xff -#define HARRIER_MPIC_IFEDE_OFF 0x10210 - -/* - * Define the Memory Controller register offsets. - */ -#define HARRIER_SDBA_OFF 0x110 -#define HARRIER_SDBB_OFF 0x114 -#define HARRIER_SDBC_OFF 0x118 -#define HARRIER_SDBD_OFF 0x11c -#define HARRIER_SDBE_OFF 0x120 -#define HARRIER_SDBF_OFF 0x124 -#define HARRIER_SDBG_OFF 0x128 -#define HARRIER_SDBH_OFF 0x12c - -#define HARRIER_SDB_ENABLE 0x00000100 -#define HARRIER_SDB_SIZE_MASK 0xf -#define HARRIER_SDB_SIZE_SHIFT 16 -#define HARRIER_SDB_BASE_MASK 0xff -#define HARRIER_SDB_BASE_SHIFT 24 - -/* - * Define outbound register offsets. - */ -#define HARRIER_OTAD0_OFF 0x220 -#define HARRIER_OTOF0_OFF 0x224 -#define HARRIER_OTAD1_OFF 0x228 -#define HARRIER_OTOF1_OFF 0x22c -#define HARRIER_OTAD2_OFF 0x230 -#define HARRIER_OTOF2_OFF 0x234 -#define HARRIER_OTAD3_OFF 0x238 -#define HARRIER_OTOF3_OFF 0x23c - -#define HARRIER_OTADX_START_MSK 0xffff0000UL -#define HARRIER_OTADX_END_MSK 0x0000ffffUL - -#define HARRIER_OTOFX_OFF_MSK 0xffff0000UL -#define HARRIER_OTOFX_ENA 0x80UL -#define HARRIER_OTOFX_WPE 0x10UL -#define HARRIER_OTOFX_SGE 0x08UL -#define HARRIER_OTOFX_RAE 0x04UL -#define HARRIER_OTOFX_MEM 0x02UL -#define HARRIER_OTOFX_IOM 0x01UL - -/* - * Define generic message passing register offsets - */ -/* Mirrored registers (visible from both PowerPC and PCI space) */ -#define HARRIER_XCSR_MP_BASE_OFF 0x290 /* base offset in XCSR space */ -#define HARRIER_PMEP_MP_BASE_OFF 0x100 /* base offset in PMEM space */ -#define HARRIER_MGOM0_OFF 0x00 /* outbound msg 0 */ -#define HARRIER_MGOM1_OFF 0x04 /* outbound msg 1 */ -#define HARRIER_MGOD_OFF 0x08 /* outbound doorbells */ - -#define HARRIER_MGIM0_OFF 0x10 /* inbound msg 0 */ -#define HARRIER_MGIM1_OFF 0x14 /* inbound msg 1 */ -#define HARRIER_MGID_OFF 0x18 /* inbound doorbells */ - -/* PowerPC-only registers */ -#define HARRIER_MGIDM_OFF 0x20 /* inbound doorbell mask */ - -/* PCI-only registers */ -#define HARRIER_PMEP_MGST_OFF 0x20 /* (outbound) interrupt status */ -#define HARRIER_PMEP_MGMS_OFF 0x24 /* (outbound) interrupt mask */ -#define HARRIER_MG_OMI0 (1<<4) -#define HARRIER_MG_OMI1 (1<<5) - -#define HARRIER_PMEP_MGODM_OFF 0x28 /* outbound doorbell mask */ - -/* - * Define PCI configuration space register offsets - */ -#define HARRIER_XCSR_TO_PCFS_OFF 0x300 - -/* - * Define message passing attribute register offset - */ -#define HARRIER_MPAT_OFF 0x44 - -/* - * Define inbound attribute register offsets. - */ -#define HARRIER_ITSZ0_OFF 0x48 -#define HARRIER_ITAT0_OFF 0x4c - -#define HARRIER_ITSZ1_OFF 0x50 -#define HARRIER_ITAT1_OFF 0x54 - -#define HARRIER_ITSZ2_OFF 0x58 -#define HARRIER_ITAT2_OFF 0x5c - -#define HARRIER_ITSZ3_OFF 0x60 -#define HARRIER_ITAT3_OFF 0x64 - -/* inbound translation size constants */ -#define HARRIER_ITSZ_MSK 0xff -#define HARRIER_ITSZ_4KB 0x00 -#define HARRIER_ITSZ_8KB 0x01 -#define HARRIER_ITSZ_16KB 0x02 -#define HARRIER_ITSZ_32KB 0x03 -#define HARRIER_ITSZ_64KB 0x04 -#define HARRIER_ITSZ_128KB 0x05 -#define HARRIER_ITSZ_256KB 0x06 -#define HARRIER_ITSZ_512KB 0x07 -#define HARRIER_ITSZ_1MB 0x08 -#define HARRIER_ITSZ_2MB 0x09 -#define HARRIER_ITSZ_4MB 0x0A -#define HARRIER_ITSZ_8MB 0x0B -#define HARRIER_ITSZ_16MB 0x0C -#define HARRIER_ITSZ_32MB 0x0D -#define HARRIER_ITSZ_64MB 0x0E -#define HARRIER_ITSZ_128MB 0x0F -#define HARRIER_ITSZ_256MB 0x10 -#define HARRIER_ITSZ_512MB 0x11 -#define HARRIER_ITSZ_1GB 0x12 -#define HARRIER_ITSZ_2GB 0x13 - -/* inbound translation offset */ -#define HARRIER_ITOF_SHIFT 0x10 -#define HARRIER_ITOF_MSK 0xffff - -/* inbound translation atttributes */ -#define HARRIER_ITAT_PRE (1<<3) -#define HARRIER_ITAT_RAE (1<<4) -#define HARRIER_ITAT_WPE (1<<5) -#define HARRIER_ITAT_MEM (1<<6) -#define HARRIER_ITAT_ENA (1<<7) -#define HARRIER_ITAT_GBL (1<<16) - -#define HARRIER_LBA_OFF 0x80 -#define HARRIER_LBA_MSK (1<<31) - -#define HARRIER_XCSR_SIZE 1024 - -/* macros to calculate message passing register offsets */ -#define HARRIER_MP_XCSR(x) ((u32)HARRIER_XCSR_MP_BASE_OFF + (u32)x) - -#define HARRIER_MP_PMEP(x) ((u32)HARRIER_PMEP_MP_BASE_OFF + (u32)x) - -/* - * Define PCI configuration space register offsets - */ -#define HARRIER_MPBAR_OFF PCI_BASE_ADDRESS_0 -#define HARRIER_ITBAR0_OFF PCI_BASE_ADDRESS_1 -#define HARRIER_ITBAR1_OFF PCI_BASE_ADDRESS_2 -#define HARRIER_ITBAR2_OFF PCI_BASE_ADDRESS_3 -#define HARRIER_ITBAR3_OFF PCI_BASE_ADDRESS_4 - -#define HARRIER_XCSR_CONFIG(x) ((u32)HARRIER_XCSR_TO_PCFS_OFF + (u32)x) - -#endif /* __ASMPPC_HARRIER_DEFS_H */ -- cgit v1.2.2 From e5f363e358cf16e4ad13a6826e15088c5495efe9 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 11 Aug 2008 12:37:27 +0200 Subject: lockdep: increase MAX_LOCKDEP_KEYS certain configs produce: [ 70.076229] BUG: MAX_LOCKDEP_KEYS too low! [ 70.080230] turning off the locking correctness validator. tune them up. Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index c88aa3d8e87f..331e5f1c2d8e 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -190,7 +190,7 @@ struct lock_chain { u64 chain_key; }; -#define MAX_LOCKDEP_KEYS_BITS 11 +#define MAX_LOCKDEP_KEYS_BITS 13 /* * Subtract one because we offset hlock->class_idx by 1 in order * to make 0 mean no class. This avoids overflowing the class_idx -- cgit v1.2.2 From a8c84df9f71e4a7b14bdd41687a70d366c087eef Mon Sep 17 00:00:00 2001 From: Keith Packard Date: Thu, 31 Jul 2008 15:48:07 +1000 Subject: intel/agp: rewrite GTT on resume On my Intel chipset (965GM), the GTT is entirely erased across suspend/resume. This patch simply re-plays the current mapping at resume time to restore the table.=20 I noticed this once I started relying on persistent GTT mappings across VT switch in our GEM work -- the old X server and DRM code carefully unbind all memory from the GTT on VT switch, but GEM does not bother. I placed the list management and rewrite code in the generic layer on the assumption that it will be needed on other hardware, but I did not add the rewrite call to anything other than the Intel resume function. Keep a list of current GATT mappings. At resume time, rewrite them into the GATT. This is needed on Intel (at least) as the entire GATT is cleared across suspend/resume. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Keith Packard Cc: Dave Jones Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Dave Airlie --- include/linux/agp_backend.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/agp_backend.h b/include/linux/agp_backend.h index 972b12bcfb36..2b8df8b420fd 100644 --- a/include/linux/agp_backend.h +++ b/include/linux/agp_backend.h @@ -30,6 +30,8 @@ #ifndef _AGP_BACKEND_H #define _AGP_BACKEND_H 1 +#include + enum chipset_type { NOT_SUPPORTED, SUPPORTED, @@ -78,6 +80,8 @@ struct agp_memory { bool is_bound; bool is_flushed; bool vmalloc_flag; + /* list of agp_memory mapped to the aperture */ + struct list_head mapped_list; }; #define AGP_NORMAL_MEMORY 0 @@ -96,6 +100,7 @@ extern struct agp_memory *agp_allocate_memory(struct agp_bridge_data *, size_t, extern int agp_copy_info(struct agp_bridge_data *, struct agp_kern_info *); extern int agp_bind_memory(struct agp_memory *, off_t); extern int agp_unbind_memory(struct agp_memory *); +extern int agp_rebind_memory(void); extern void agp_enable(struct agp_bridge_data *, u32); extern struct agp_bridge_data *agp_backend_acquire(struct pci_dev *); extern void agp_backend_release(struct agp_bridge_data *); -- cgit v1.2.2 From 987c402ac31988f7ecdb38b657bcfeea5831d479 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Mon, 11 Aug 2008 18:17:17 -0700 Subject: skbuff: Code readability NiT Inserting a space between the `-' improved the C readability (some languages allow hyphens within functions and variable names, which is confusing). Signed-off-by: Gerrit Renker Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cfcc45b3bef0..358661c9990e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -901,7 +901,7 @@ extern unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline unsigned char *__pskb_pull(struct sk_buff *skb, unsigned int len) { if (len > skb_headlen(skb) && - !__pskb_pull_tail(skb, len-skb_headlen(skb))) + !__pskb_pull_tail(skb, len - skb_headlen(skb))) return NULL; skb->len -= len; return skb->data += len; @@ -918,7 +918,7 @@ static inline int pskb_may_pull(struct sk_buff *skb, unsigned int len) return 1; if (unlikely(len > skb->len)) return 0; - return __pskb_pull_tail(skb, len-skb_headlen(skb)) != NULL; + return __pskb_pull_tail(skb, len - skb_headlen(skb)) != NULL; } /** @@ -1321,7 +1321,7 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len) unsigned int size = skb->len; if (likely(size >= len)) return 0; - return skb_pad(skb, len-size); + return skb_pad(skb, len - size); } static inline int skb_add_data(struct sk_buff *skb, -- cgit v1.2.2 From 912985dce45ef18fcdd9f5439fef054e0e22302a Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 12 Aug 2008 17:52:52 -0500 Subject: mm: Make generic weak get_user_pages_fast and EXPORT_GPL it Out of line get_user_pages_fast fallback implementation, make it a weak symbol, get rid of CONFIG_HAVE_GET_USER_PAGES_FAST. Export the symbol to modules so lguest can use it. Signed-off-by: Nick Piggin Signed-off-by: Rusty Russell --- include/linux/mm.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 335288bff1b7..fa651609b65d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -834,7 +834,6 @@ extern int mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); -#ifdef CONFIG_HAVE_GET_USER_PAGES_FAST /* * get_user_pages_fast provides equivalent functionality to get_user_pages, * operating on current and current->mm (force=0 and doesn't return any vmas). @@ -848,25 +847,6 @@ extern int mprotect_fixup(struct vm_area_struct *vma, int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); -#else -/* - * Should probably be moved to asm-generic, and architectures can include it if - * they don't implement their own get_user_pages_fast. - */ -#define get_user_pages_fast(start, nr_pages, write, pages) \ -({ \ - struct mm_struct *mm = current->mm; \ - int ret; \ - \ - down_read(&mm->mmap_sem); \ - ret = get_user_pages(current, mm, start, nr_pages, \ - write, 0, pages, NULL); \ - up_read(&mm->mmap_sem); \ - \ - ret; \ -}) -#endif - /* * A callback you can register to apply pressure to ageable caches. * -- cgit v1.2.2 From 4bceba417a795b78a5146e3f85291cb7bb2402ef Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 8 Aug 2008 11:15:07 +0200 Subject: export virtio_rng.h Hello Rusty, The entropy device was added after we exported all virtio headers. This patch adds virtio_rng.h to the exportable userspace headers. Signed-off-by: Christian Borntraeger Signed-off-by: Rusty Russell --- include/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index a26f565e8189..327f60658d94 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -356,6 +356,7 @@ unifdef-y += virtio_balloon.h unifdef-y += virtio_console.h unifdef-y += virtio_pci.h unifdef-y += virtio_ring.h +unifdef-y += virtio_rng.h unifdef-y += vt.h unifdef-y += wait.h unifdef-y += wanrouter.h -- cgit v1.2.2 From 59f9415ffb9759e950d775f4c400f747b332cc02 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Wed, 30 Jul 2008 12:49:02 -0700 Subject: modules: extend initcall_debug functionality to the module loader The kernel has this really nice facility where if you put "initcall_debug" on the kernel commandline, it'll print which function it's going to execute just before calling an initcall, and then after the call completes it will 1) print if it had an error code 2) checks for a few simple bugs (like leaving irqs off) and 3) print how long the init call took in milliseconds. While trying to optimize the boot speed of my laptop, I have been loving number 3 to figure out what to optimize... ... and then I wished that the same thing was done for module loading. This patch makes the module loader use this exact same functionality; it's a logical extension in my view (since modules are just sort of late binding initcalls anyway) and so far I've found it quite useful in finding where things are too slow in my boot. Signed-off-by: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Rusty Russell --- include/linux/init.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 11b84e106053..93538b696e3d 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -139,6 +139,7 @@ extern initcall_t __con_initcall_start[], __con_initcall_end[]; extern initcall_t __security_initcall_start[], __security_initcall_end[]; /* Defined in init/main.c */ +extern int do_one_initcall(initcall_t fn); extern char __initdata boot_command_line[]; extern char *saved_command_line; extern unsigned int reset_devices; -- cgit v1.2.2 From 74768ed833344bb0f82b97cee46320a3d7f09ecd Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 12 Aug 2008 15:08:39 -0700 Subject: page allocator: use no-panic variant of alloc_bootmem() in alloc_large_system_hash() .. since a failed allocation is being (initially) handled gracefully, and panic()-ed upon failure explicitly in the function if retries with smaller sizes failed. Signed-off-by: Jan Beulich Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 652470b687c9..95837bfb5256 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -97,10 +97,14 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE #define alloc_bootmem(x) \ __alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) +#define alloc_bootmem_nopanic(x) \ + __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_low(x) \ __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) #define alloc_bootmem_pages(x) \ __alloc_bootmem(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) +#define alloc_bootmem_pages_nopanic(x) \ + __alloc_bootmem_nopanic(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_low_pages(x) \ __alloc_bootmem_low(x, PAGE_SIZE, 0) #define alloc_bootmem_node(pgdat, x) \ -- cgit v1.2.2 From 10546355323e4826d13e62f85ac6198385a817a9 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 12 Aug 2008 15:08:55 -0700 Subject: matrox maven: convert to a new-style i2c driver The legacy i2c model is going away soon, so switch to the new model. Signed-off-by: Jean Delvare Acked-by: Krzysztof Helt Cc: Petr Vandrovec Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/i2c-id.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 4862398e05bf..bf34c5f4c051 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -39,7 +39,6 @@ #define I2C_DRIVERID_SAA7111A 8 /* video input processor */ #define I2C_DRIVERID_SAA7185B 13 /* video encoder */ #define I2C_DRIVERID_SAA7110 22 /* video decoder */ -#define I2C_DRIVERID_MGATVO 23 /* Matrox TVOut */ #define I2C_DRIVERID_SAA5249 24 /* SAA5249 and compatibles */ #define I2C_DRIVERID_PCF8583 25 /* real time clock */ #define I2C_DRIVERID_SAB3036 26 /* SAB3036 tuner */ @@ -95,7 +94,6 @@ #define I2C_HW_B_BT848 0x010005 /* BT848 video boards */ #define I2C_HW_B_VIA 0x010007 /* Via vt82c586b */ #define I2C_HW_B_HYDRA 0x010008 /* Apple Hydra Mac I/O */ -#define I2C_HW_B_G400 0x010009 /* Matrox G400 */ #define I2C_HW_B_I810 0x01000a /* Intel I810 */ #define I2C_HW_B_VOO 0x01000b /* 3dfx Voodoo 3 / Banshee */ #define I2C_HW_B_SCX200 0x01000e /* Nat'l Semi SCx200 I2C */ -- cgit v1.2.2 From 070cb06593006e7d565d4763380f3edd8dbdc134 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 12 Aug 2008 15:08:59 -0700 Subject: move kernel-doc comment for might_sleep directly before its defining block MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Uwe Kleine-König Cc: Ingo Molnar Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index aaa998f65c7a..2651f805ba6d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -108,6 +108,13 @@ struct completion; struct pt_regs; struct user; +#ifdef CONFIG_PREEMPT_VOLUNTARY +extern int _cond_resched(void); +# define might_resched() _cond_resched() +#else +# define might_resched() do { } while (0) +#endif + /** * might_sleep - annotation for functions that can sleep * @@ -118,13 +125,6 @@ struct user; * be bitten later when the calling function happens to sleep when it is not * supposed to. */ -#ifdef CONFIG_PREEMPT_VOLUNTARY -extern int _cond_resched(void); -# define might_resched() _cond_resched() -#else -# define might_resched() do { } while (0) -#endif - #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP void __might_sleep(char *file, int line); # define might_sleep() \ -- cgit v1.2.2 From 50ac2d694f2dd1658341cf97bcf2ffb836d772cb Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 12 Aug 2008 15:09:02 -0700 Subject: seq_file: add seq_cpumask(), seq_nodemask() Short enough reads from /proc/irq/*/smp_affinity return -EINVAL for no good reason. This became noticed with NR_CPUS=4096 patches, when length of printed representation of cpumask becase 1152, but cat(1) continued to read with 1024-byte chunks. bitmap_scnprintf() in good faith fills buffer, returns 1023, check returns -EINVAL. Fix it by switching to seq_file, so handler will just fill buffer and doesn't care about offsets, length, filling EOF and all this crap. For that add seq_bitmap(), and wrappers around it -- seq_cpumask() and seq_nodemask(). Signed-off-by: Alexey Dobriyan Reviewed-by: Paul Jackson Cc: Mike Travis Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 1 + include/linux/seq_file.h | 12 ++++++++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 1abfe664c444..89781fd48859 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -110,6 +110,7 @@ extern int __bitmap_weight(const unsigned long *bitmap, int bits); extern int bitmap_scnprintf(char *buf, unsigned int len, const unsigned long *src, int nbits); +extern int bitmap_scnprintf_len(unsigned int nr_bits); extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user, unsigned long *dst, int nbits); extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index a66304a09955..a1783b229ef4 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -4,6 +4,8 @@ #include #include #include +#include +#include struct seq_operations; struct file; @@ -47,6 +49,16 @@ int seq_path(struct seq_file *, struct path *, char *); int seq_dentry(struct seq_file *, struct dentry *, char *); int seq_path_root(struct seq_file *m, struct path *path, struct path *root, char *esc); +int seq_bitmap(struct seq_file *m, unsigned long *bits, unsigned int nr_bits); +static inline int seq_cpumask(struct seq_file *m, cpumask_t *mask) +{ + return seq_bitmap(m, mask->bits, NR_CPUS); +} + +static inline int seq_nodemask(struct seq_file *m, nodemask_t *mask) +{ + return seq_bitmap(m, mask->bits, MAX_NUMNODES); +} int single_open(struct file *, int (*)(struct seq_file *, void *), void *); int single_release(struct inode *, struct file *); -- cgit v1.2.2 From 40c9f22210f2d22f45d4fb430c94f472d19407d6 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Tue, 12 Aug 2008 15:09:04 -0700 Subject: byteorder: add a new include/linux/swab.h to define byteswapping functions Collect the implementations from include/linux/byteorder/swab.h, swabb.h in swab.h The functionality provided covers: u16 swab16(u16 val) - return a byteswapped 16 bit value u32 swab32(u32 val) - return a byteswapped 32 bit value u64 swab64(u64 val) - return a byteswapped 64 bit value u32 swahw32(u32 val) - return a wordswapped 32 bit value u32 swahb32(u32 val) - return a high/low byteswapped 32 bit value Similar to above, but return swapped value from a naturally-aligned pointer u16 swab16p(u16 *p) u32 swab32p(u32 *p) u64 swab64p(u64 *p) u32 swahw32p(u32 *p) u32 swahb32p(u32 *p) Similar to above, but swap the value in-place (in-situ) void swab16s(u16 *p) void swab32s(u32 *p) void swab64s(u64 *p) void swahw32s(u32 *p) void swahb32s(u32 *p) Arches can override any of these with an optimized version by defining an inline in their asm/byteorder.h (example given for swab16()): u16 __arch_swab16() {} #define __arch_swab16 __arch_swab16 Signed-off-by: Harvey Harrison Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swab.h | 309 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 309 insertions(+) create mode 100644 include/linux/swab.h (limited to 'include/linux') diff --git a/include/linux/swab.h b/include/linux/swab.h new file mode 100644 index 000000000000..270d5c208a89 --- /dev/null +++ b/include/linux/swab.h @@ -0,0 +1,309 @@ +#ifndef _LINUX_SWAB_H +#define _LINUX_SWAB_H + +#include +#include +#include + +/* + * casts are necessary for constants, because we never know how for sure + * how U/UL/ULL map to __u16, __u32, __u64. At least not in a portable way. + */ +#define __const_swab16(x) ((__u16)( \ + (((__u16)(x) & (__u16)0x00ffU) << 8) | \ + (((__u16)(x) & (__u16)0xff00U) >> 8))) + +#define __const_swab32(x) ((__u32)( \ + (((__u32)(x) & (__u32)0x000000ffUL) << 24) | \ + (((__u32)(x) & (__u32)0x0000ff00UL) << 8) | \ + (((__u32)(x) & (__u32)0x00ff0000UL) >> 8) | \ + (((__u32)(x) & (__u32)0xff000000UL) >> 24))) + +#define __const_swab64(x) ((__u64)( \ + (((__u64)(x) & (__u64)0x00000000000000ffULL) << 56) | \ + (((__u64)(x) & (__u64)0x000000000000ff00ULL) << 40) | \ + (((__u64)(x) & (__u64)0x0000000000ff0000ULL) << 24) | \ + (((__u64)(x) & (__u64)0x00000000ff000000ULL) << 8) | \ + (((__u64)(x) & (__u64)0x000000ff00000000ULL) >> 8) | \ + (((__u64)(x) & (__u64)0x0000ff0000000000ULL) >> 24) | \ + (((__u64)(x) & (__u64)0x00ff000000000000ULL) >> 40) | \ + (((__u64)(x) & (__u64)0xff00000000000000ULL) >> 56))) + +#define __const_swahw32(x) ((__u32)( \ + (((__u32)(x) & (__u32)0x0000ffffUL) << 16) | \ + (((__u32)(x) & (__u32)0xffff0000UL) >> 16))) + +#define __const_swahb32(x) ((__u32)( \ + (((__u32)(x) & (__u32)0x00ff00ffUL) << 8) | \ + (((__u32)(x) & (__u32)0xff00ff00UL) >> 8))) + +/* + * Implement the following as inlines, but define the interface using + * macros to allow constant folding when possible: + * ___swab16, ___swab32, ___swab64, ___swahw32, ___swahb32 + */ + +static inline __attribute_const__ __u16 ___swab16(__u16 val) +{ +#ifdef __arch_swab16 + return __arch_swab16(val); +#elif defined(__arch_swab16p) + return __arch_swab16p(&val); +#else + return __const_swab16(val); +#endif +} + +static inline __attribute_const__ __u32 ___swab32(__u32 val) +{ +#ifdef __arch_swab32 + return __arch_swab32(val); +#elif defined(__arch_swab32p) + return __arch_swab32p(&val); +#else + return __const_swab32(val); +#endif +} + +static inline __attribute_const__ __u64 ___swab64(__u64 val) +{ +#ifdef __arch_swab64 + return __arch_swab64(val); +#elif defined(__arch_swab64p) + return __arch_swab64p(&val); +#elif defined(__SWAB_64_THRU_32__) + __u32 h = val >> 32; + __u32 l = val & ((1ULL << 32) - 1); + return (((__u64)___swab32(l)) << 32) | ((__u64)(___swab32(h))); +#else + return __const_swab64(val); +#endif +} + +static inline __attribute_const__ __u32 ___swahw32(__u32 val) +{ +#ifdef __arch_swahw32 + return __arch_swahw32(val); +#elif defined(__arch_swahw32p) + return __arch_swahw32p(&val); +#else + return __const_swahw32(val); +#endif +} + +static inline __attribute_const__ __u32 ___swahb32(__u32 val) +{ +#ifdef __arch_swahb32 + return __arch_swahb32(val); +#elif defined(__arch_swahb32p) + return __arch_swahb32p(&val); +#else + return __const_swahb32(val); +#endif +} + +/** + * __swab16 - return a byteswapped 16-bit value + * @x: value to byteswap + */ +#define __swab16(x) \ + (__builtin_constant_p((__u16)(x)) ? \ + __const_swab16((x)) : \ + ___swab16((x))) + +/** + * __swab32 - return a byteswapped 32-bit value + * @x: value to byteswap + */ +#define __swab32(x) \ + (__builtin_constant_p((__u32)(x)) ? \ + __const_swab32((x)) : \ + ___swab32((x))) + +/** + * __swab64 - return a byteswapped 64-bit value + * @x: value to byteswap + */ +#define __swab64(x) \ + (__builtin_constant_p((__u64)(x)) ? \ + __const_swab64((x)) : \ + ___swab64((x))) + +/** + * __swahw32 - return a word-swapped 32-bit value + * @x: value to wordswap + * + * __swahw32(0x12340000) is 0x00001234 + */ +#define __swahw32(x) \ + (__builtin_constant_p((__u32)(x)) ? \ + __const_swahw32((x)) : \ + ___swahw32((x))) + +/** + * __swahb32 - return a high and low byte-swapped 32-bit value + * @x: value to byteswap + * + * __swahb32(0x12345678) is 0x34127856 + */ +#define __swahb32(x) \ + (__builtin_constant_p((__u32)(x)) ? \ + __const_swahb32((x)) : \ + ___swahb32((x))) + +/** + * __swab16p - return a byteswapped 16-bit value from a pointer + * @p: pointer to a naturally-aligned 16-bit value + */ +static inline __u16 __swab16p(const __u16 *p) +{ +#ifdef __arch_swab16p + return __arch_swab16p(p); +#else + return __swab16(*p); +#endif +} + +/** + * __swab32p - return a byteswapped 32-bit value from a pointer + * @p: pointer to a naturally-aligned 32-bit value + */ +static inline __u32 __swab32p(const __u32 *p) +{ +#ifdef __arch_swab32p + return __arch_swab32p(p); +#else + return __swab32(*p); +#endif +} + +/** + * __swab64p - return a byteswapped 64-bit value from a pointer + * @p: pointer to a naturally-aligned 64-bit value + */ +static inline __u64 __swab64p(const __u64 *p) +{ +#ifdef __arch_swab64p + return __arch_swab64p(p); +#else + return __swab64(*p); +#endif +} + +/** + * __swahw32p - return a wordswapped 32-bit value from a pointer + * @p: pointer to a naturally-aligned 32-bit value + * + * See __swahw32() for details of wordswapping. + */ +static inline __u32 __swahw32p(const __u32 *p) +{ +#ifdef __arch_swahw32p + return __arch_swahw32p(p); +#else + return __swahw32(*p); +#endif +} + +/** + * __swahb32p - return a high and low byteswapped 32-bit value from a pointer + * @p: pointer to a naturally-aligned 32-bit value + * + * See __swahb32() for details of high/low byteswapping. + */ +static inline __u32 __swahb32p(const __u32 *p) +{ +#ifdef __arch_swahb32p + return __arch_swahb32p(p); +#else + return __swahb32(*p); +#endif +} + +/** + * __swab16s - byteswap a 16-bit value in-place + * @p: pointer to a naturally-aligned 16-bit value + */ +static inline void __swab16s(__u16 *p) +{ +#ifdef __arch_swab16s + __arch_swab16s(p); +#else + *p = __swab16p(p); +#endif +} +/** + * __swab32s - byteswap a 32-bit value in-place + * @p: pointer to a naturally-aligned 32-bit value + */ +static inline void __swab32s(__u32 *p) +{ +#ifdef __arch_swab32s + __arch_swab32s(p); +#else + *p = __swab32p(p); +#endif +} + +/** + * __swab64s - byteswap a 64-bit value in-place + * @p: pointer to a naturally-aligned 64-bit value + */ +static inline void __swab64s(__u64 *p) +{ +#ifdef __arch_swab64s + __arch_swab64s(p); +#else + *p = __swab64p(p); +#endif +} + +/** + * __swahw32s - wordswap a 32-bit value in-place + * @p: pointer to a naturally-aligned 32-bit value + * + * See __swahw32() for details of wordswapping + */ +static inline void __swahw32s(__u32 *p) +{ +#ifdef __arch_swahw32s + __arch_swahw32s(p); +#else + *p = __swahw32p(p); +#endif +} + +/** + * __swahb32s - high and low byteswap a 32-bit value in-place + * @p: pointer to a naturally-aligned 32-bit value + * + * See __swahb32() for details of high and low byte swapping + */ +static inline void __swahb32s(__u32 *p) +{ +#ifdef __arch_swahb32s + __arch_swahb32s(p); +#else + *p = __swahb32p(p); +#endif +} + +#ifdef __KERNEL__ +# define swab16 __swab16 +# define swab32 __swab32 +# define swab64 __swab64 +# define swahw32 __swahw32 +# define swahb32 __swahb32 +# define swab16p __swab16p +# define swab32p __swab32p +# define swab64p __swab64p +# define swahw32p __swahw32p +# define swahb32p __swahb32p +# define swab16s __swab16s +# define swab32s __swab32s +# define swab64s __swab64s +# define swahw32s __swahw32s +# define swahb32s __swahb32s +#endif /* __KERNEL__ */ + +#endif /* _LINUX_SWAB_H */ -- cgit v1.2.2 From bc2aa80e18a1b43ea2b8066500006b729c4ba4a7 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Tue, 12 Aug 2008 15:09:05 -0700 Subject: byteorder: add include/linux/byteorder.h to define endian helpers Signed-off-by: Harvey Harrison Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/byteorder.h | 372 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 372 insertions(+) create mode 100644 include/linux/byteorder.h (limited to 'include/linux') diff --git a/include/linux/byteorder.h b/include/linux/byteorder.h new file mode 100644 index 000000000000..29f002d73d98 --- /dev/null +++ b/include/linux/byteorder.h @@ -0,0 +1,372 @@ +#ifndef _LINUX_BYTEORDER_H +#define _LINUX_BYTEORDER_H + +#include +#include + +#if defined(__LITTLE_ENDIAN) && defined(__BIG_ENDIAN) +# error Fix asm/byteorder.h to define one endianness +#endif + +#if !defined(__LITTLE_ENDIAN) && !defined(__BIG_ENDIAN) +# error Fix asm/byteorder.h to define arch endianness +#endif + +#ifdef __LITTLE_ENDIAN +# undef __LITTLE_ENDIAN +# define __LITTLE_ENDIAN 1234 +#endif + +#ifdef __BIG_ENDIAN +# undef __BIG_ENDIAN +# define __BIG_ENDIAN 4321 +#endif + +#if defined(__LITTLE_ENDIAN) && !defined(__LITTLE_ENDIAN_BITFIELD) +# define __LITTLE_ENDIAN_BITFIELD +#endif + +#if defined(__BIG_ENDIAN) && !defined(__BIG_ENDIAN_BITFIELD) +# define __BIG_ENDIAN_BITFIELD +#endif + +#ifdef __LITTLE_ENDIAN +# define __le16_to_cpu(x) ((__force __u16)(__le16)(x)) +# define __le32_to_cpu(x) ((__force __u32)(__le32)(x)) +# define __le64_to_cpu(x) ((__force __u64)(__le64)(x)) +# define __cpu_to_le16(x) ((__force __le16)(__u16)(x)) +# define __cpu_to_le32(x) ((__force __le32)(__u32)(x)) +# define __cpu_to_le64(x) ((__force __le64)(__u64)(x)) + +# define __be16_to_cpu(x) __swab16((__force __u16)(__be16)(x)) +# define __be32_to_cpu(x) __swab32((__force __u32)(__be32)(x)) +# define __be64_to_cpu(x) __swab64((__force __u64)(__be64)(x)) +# define __cpu_to_be16(x) ((__force __be16)__swab16(x)) +# define __cpu_to_be32(x) ((__force __be32)__swab32(x)) +# define __cpu_to_be64(x) ((__force __be64)__swab64(x)) +#endif + +#ifdef __BIG_ENDIAN +# define __be16_to_cpu(x) ((__force __u16)(__be16)(x)) +# define __be32_to_cpu(x) ((__force __u32)(__be32)(x)) +# define __be64_to_cpu(x) ((__force __u64)(__be64)(x)) +# define __cpu_to_be16(x) ((__force __be16)(__u16)(x)) +# define __cpu_to_be32(x) ((__force __be32)(__u32)(x)) +# define __cpu_to_be64(x) ((__force __be64)(__u64)(x)) + +# define __le16_to_cpu(x) __swab16((__force __u16)(__le16)(x)) +# define __le32_to_cpu(x) __swab32((__force __u32)(__le32)(x)) +# define __le64_to_cpu(x) __swab64((__force __u64)(__le64)(x)) +# define __cpu_to_le16(x) ((__force __le16)__swab16(x)) +# define __cpu_to_le32(x) ((__force __le32)__swab32(x)) +# define __cpu_to_le64(x) ((__force __le64)__swab64(x)) +#endif + +/* + * These helpers could be phased out over time as the base version + * handles constant folding. + */ +#define __constant_htonl(x) __cpu_to_be32(x) +#define __constant_ntohl(x) __be32_to_cpu(x) +#define __constant_htons(x) __cpu_to_be16(x) +#define __constant_ntohs(x) __be16_to_cpu(x) + +#define __constant_le16_to_cpu(x) __le16_to_cpu(x) +#define __constant_le32_to_cpu(x) __le32_to_cpu(x) +#define __constant_le64_to_cpu(x) __le64_to_cpu(x) +#define __constant_be16_to_cpu(x) __be16_to_cpu(x) +#define __constant_be32_to_cpu(x) __be32_to_cpu(x) +#define __constant_be64_to_cpu(x) __be64_to_cpu(x) + +#define __constant_cpu_to_le16(x) __cpu_to_le16(x) +#define __constant_cpu_to_le32(x) __cpu_to_le32(x) +#define __constant_cpu_to_le64(x) __cpu_to_le64(x) +#define __constant_cpu_to_be16(x) __cpu_to_be16(x) +#define __constant_cpu_to_be32(x) __cpu_to_be32(x) +#define __constant_cpu_to_be64(x) __cpu_to_be64(x) + +static inline void __le16_to_cpus(__u16 *p) +{ +#ifdef __BIG_ENDIAN + __swab16s(p); +#endif +} + +static inline void __cpu_to_le16s(__u16 *p) +{ +#ifdef __BIG_ENDIAN + __swab16s(p); +#endif +} + +static inline void __le32_to_cpus(__u32 *p) +{ +#ifdef __BIG_ENDIAN + __swab32s(p); +#endif +} + +static inline void __cpu_to_le32s(__u32 *p) +{ +#ifdef __BIG_ENDIAN + __swab32s(p); +#endif +} + +static inline void __le64_to_cpus(__u64 *p) +{ +#ifdef __BIG_ENDIAN + __swab64s(p); +#endif +} + +static inline void __cpu_to_le64s(__u64 *p) +{ +#ifdef __BIG_ENDIAN + __swab64s(p); +#endif +} + +static inline void __be16_to_cpus(__u16 *p) +{ +#ifdef __LITTLE_ENDIAN + __swab16s(p); +#endif +} + +static inline void __cpu_to_be16s(__u16 *p) +{ +#ifdef __LITTLE_ENDIAN + __swab16s(p); +#endif +} + +static inline void __be32_to_cpus(__u32 *p) +{ +#ifdef __LITTLE_ENDIAN + __swab32s(p); +#endif +} + +static inline void __cpu_to_be32s(__u32 *p) +{ +#ifdef __LITTLE_ENDIAN + __swab32s(p); +#endif +} + +static inline void __be64_to_cpus(__u64 *p) +{ +#ifdef __LITTLE_ENDIAN + __swab64s(p); +#endif +} + +static inline void __cpu_to_be64s(__u64 *p) +{ +#ifdef __LITTLE_ENDIAN + __swab64s(p); +#endif +} + +static inline __u16 __le16_to_cpup(const __le16 *p) +{ +#ifdef __LITTLE_ENDIAN + return (__force __u16)*p; +#else + return __swab16p((__force __u16 *)p); +#endif +} + +static inline __u32 __le32_to_cpup(const __le32 *p) +{ +#ifdef __LITTLE_ENDIAN + return (__force __u32)*p; +#else + return __swab32p((__force __u32 *)p); +#endif +} + +static inline __u64 __le64_to_cpup(const __le64 *p) +{ +#ifdef __LITTLE_ENDIAN + return (__force __u64)*p; +#else + return __swab64p((__force __u64 *)p); +#endif +} + +static inline __le16 __cpu_to_le16p(const __u16 *p) +{ +#ifdef __LITTLE_ENDIAN + return (__force __le16)*p; +#else + return (__force __le16)__swab16p(p); +#endif +} + +static inline __le32 __cpu_to_le32p(const __u32 *p) +{ +#ifdef __LITTLE_ENDIAN + return (__force __le32)*p; +#else + return (__force __le32)__swab32p(p); +#endif +} + +static inline __le64 __cpu_to_le64p(const __u64 *p) +{ +#ifdef __LITTLE_ENDIAN + return (__force __le64)*p; +#else + return (__force __le64)__swab64p(p); +#endif +} + +static inline __u16 __be16_to_cpup(const __be16 *p) +{ +#ifdef __BIG_ENDIAN + return (__force __u16)*p; +#else + return __swab16p((__force __u16 *)p); +#endif +} + +static inline __u32 __be32_to_cpup(const __be32 *p) +{ +#ifdef __BIG_ENDIAN + return (__force __u32)*p; +#else + return __swab32p((__force __u32 *)p); +#endif +} + +static inline __u64 __be64_to_cpup(const __be64 *p) +{ +#ifdef __BIG_ENDIAN + return (__force __u64)*p; +#else + return __swab64p((__force __u64 *)p); +#endif +} + +static inline __be16 __cpu_to_be16p(const __u16 *p) +{ +#ifdef __BIG_ENDIAN + return (__force __be16)*p; +#else + return (__force __be16)__swab16p(p); +#endif +} + +static inline __be32 __cpu_to_be32p(const __u32 *p) +{ +#ifdef __BIG_ENDIAN + return (__force __be32)*p; +#else + return (__force __be32)__swab32p(p); +#endif +} + +static inline __be64 __cpu_to_be64p(const __u64 *p) +{ +#ifdef __BIG_ENDIAN + return (__force __be64)*p; +#else + return (__force __be64)__swab64p(p); +#endif +} + +#ifdef __KERNEL__ + +# define le16_to_cpu __le16_to_cpu +# define le32_to_cpu __le32_to_cpu +# define le64_to_cpu __le64_to_cpu +# define be16_to_cpu __be16_to_cpu +# define be32_to_cpu __be32_to_cpu +# define be64_to_cpu __be64_to_cpu +# define cpu_to_le16 __cpu_to_le16 +# define cpu_to_le32 __cpu_to_le32 +# define cpu_to_le64 __cpu_to_le64 +# define cpu_to_be16 __cpu_to_be16 +# define cpu_to_be32 __cpu_to_be32 +# define cpu_to_be64 __cpu_to_be64 + +# define le16_to_cpup __le16_to_cpup +# define le32_to_cpup __le32_to_cpup +# define le64_to_cpup __le64_to_cpup +# define be16_to_cpup __be16_to_cpup +# define be32_to_cpup __be32_to_cpup +# define be64_to_cpup __be64_to_cpup +# define cpu_to_le16p __cpu_to_le16p +# define cpu_to_le32p __cpu_to_le32p +# define cpu_to_le64p __cpu_to_le64p +# define cpu_to_be16p __cpu_to_be16p +# define cpu_to_be32p __cpu_to_be32p +# define cpu_to_be64p __cpu_to_be64p + +# define le16_to_cpus __le16_to_cpus +# define le32_to_cpus __le32_to_cpus +# define le64_to_cpus __le64_to_cpus +# define be16_to_cpus __be16_to_cpus +# define be32_to_cpus __be32_to_cpus +# define be64_to_cpus __be64_to_cpus +# define cpu_to_le16s __cpu_to_le16s +# define cpu_to_le32s __cpu_to_le32s +# define cpu_to_le64s __cpu_to_le64s +# define cpu_to_be16s __cpu_to_be16s +# define cpu_to_be32s __cpu_to_be32s +# define cpu_to_be64s __cpu_to_be64s + +/* + * They have to be macros in order to do the constant folding + * correctly - if the argument passed into a inline function + * it is no longer constant according to gcc.. + */ +# undef ntohl +# undef ntohs +# undef htonl +# undef htons + +# define ___htonl(x) __cpu_to_be32(x) +# define ___htons(x) __cpu_to_be16(x) +# define ___ntohl(x) __be32_to_cpu(x) +# define ___ntohs(x) __be16_to_cpu(x) + +# define htonl(x) ___htonl(x) +# define ntohl(x) ___ntohl(x) +# define htons(x) ___htons(x) +# define ntohs(x) ___ntohs(x) + +static inline void le16_add_cpu(__le16 *var, u16 val) +{ + *var = cpu_to_le16(le16_to_cpup(var) + val); +} + +static inline void le32_add_cpu(__le32 *var, u32 val) +{ + *var = cpu_to_le32(le32_to_cpup(var) + val); +} + +static inline void le64_add_cpu(__le64 *var, u64 val) +{ + *var = cpu_to_le64(le64_to_cpup(var) + val); +} + +static inline void be16_add_cpu(__be16 *var, u16 val) +{ + *var = cpu_to_be16(be16_to_cpup(var) + val); +} + +static inline void be32_add_cpu(__be32 *var, u32 val) +{ + *var = cpu_to_be32(be32_to_cpup(var) + val); +} + +static inline void be64_add_cpu(__be64 *var, u64 val) +{ + *var = cpu_to_be64(be64_to_cpup(var) + val); +} + +#endif /* __KERNEL__ */ +#endif /* _LINUX_BYTEORDER_H */ -- cgit v1.2.2 From 31bad9246b5e17d547430697791acca5e9712333 Mon Sep 17 00:00:00 2001 From: Bernhard Walle Date: Tue, 12 Aug 2008 15:09:14 -0700 Subject: firmware/memmap: cleanup Various cleanup the drivers/firmware/memmap (after review by AKPM): - fix kdoc to conform to the standard - move kdoc from header to implementation files - remove superfluous WARN_ON() after kmalloc() - WARN_ON(x); if (!x) -> if(!WARN_ON(x)) - improve some comments Signed-off-by: Bernhard Walle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/firmware-map.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware-map.h b/include/linux/firmware-map.h index acbdbcc16051..6e199c8dfacc 100644 --- a/include/linux/firmware-map.h +++ b/include/linux/firmware-map.h @@ -24,34 +24,8 @@ */ #ifdef CONFIG_FIRMWARE_MEMMAP -/** - * Adds a firmware mapping entry. This function uses kmalloc() for memory - * allocation. Use firmware_map_add_early() if you want to use the bootmem - * allocator. - * - * That function must be called before late_initcall. - * - * @start: Start of the memory range. - * @end: End of the memory range (inclusive). - * @type: Type of the memory range. - * - * Returns 0 on success, or -ENOMEM if no memory could be allocated. - */ int firmware_map_add(resource_size_t start, resource_size_t end, const char *type); - -/** - * Adds a firmware mapping entry. This function uses the bootmem allocator - * for memory allocation. Use firmware_map_add() if you want to use kmalloc(). - * - * That function must be called before late_initcall. - * - * @start: Start of the memory range. - * @end: End of the memory range (inclusive). - * @type: Type of the memory range. - * - * Returns 0 on success, or -ENOMEM if no memory could be allocated. - */ int firmware_map_add_early(resource_size_t start, resource_size_t end, const char *type); -- cgit v1.2.2 From 39d2f1ab2a36ac527a6c41cfe689f50c239eaca3 Mon Sep 17 00:00:00 2001 From: David Chinner Date: Wed, 13 Aug 2008 16:40:43 +1000 Subject: [XFS] extend completions to provide XFS object flush requirements XFS object flushing doesn't quite match existing completion semantics. It mixed exclusive access with completion. That is, we need to mark an object as being flushed before flushing it to disk, and then block any other attempt to flush it until the completion occurs. We do this but adding an extra count to the completion before we start using them. However, we still need to determine if there is a completion in progress, and allow no-blocking attempts fo completions to decrement the count. To do this we introduce: int try_wait_for_completion(struct completion *x) returns a failure status if done == 0, otherwise decrements done to zero and returns a "started" status. This is provided to allow counted completions to begin safely while holding object locks in inverted order. int completion_done(struct completion *x) returns 1 if there is no waiter, 0 if there is a waiter (i.e. a completion in progress). This replaces the use of semaphores for providing this exclusion and completion mechanism. SGI-PV: 981498 SGI-Modid: xfs-linux-melb:xfs-kern:31816a Signed-off-by: David Chinner Signed-off-by: Lachlan McIlroy --- include/linux/completion.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/completion.h b/include/linux/completion.h index d2961b66d53d..57faa60de9bd 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -55,4 +55,49 @@ extern void complete_all(struct completion *); #define INIT_COMPLETION(x) ((x).done = 0) + +/** + * try_wait_for_completion - try to decrement a completion without blocking + * @x: completion structure + * + * Returns: 0 if a decrement cannot be done without blocking + * 1 if a decrement succeeded. + * + * If a completion is being used as a counting completion, + * attempt to decrement the counter without blocking. This + * enables us to avoid waiting if the resource the completion + * is protecting is not available. + */ +static inline bool try_wait_for_completion(struct completion *x) +{ + int ret = 1; + + spin_lock_irq(&x->wait.lock); + if (!x->done) + ret = 0; + else + x->done--; + spin_unlock_irq(&x->wait.lock); + return ret; +} + +/** + * completion_done - Test to see if a completion has any waiters + * @x: completion structure + * + * Returns: 0 if there are waiters (wait_for_completion() in progress) + * 1 if there are no waiters. + * + */ +static inline bool completion_done(struct completion *x) +{ + int ret = 1; + + spin_lock_irq(&x->wait.lock); + if (!x->done) + ret = 0; + spin_unlock_irq(&x->wait.lock); + return ret; +} + #endif -- cgit v1.2.2 From 9e2b2dc4133f65272a6d3c5dcb2ce63f8a87cae9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 13 Aug 2008 16:20:04 +0100 Subject: CRED: Introduce credential access wrappers The patches that are intended to introduce copy-on-write credentials for 2.6.28 require abstraction of access to some fields of the task structure, particularly for the case of one task accessing another's credentials where RCU will have to be observed. Introduced here are trivial no-op versions of the desired accessors for current and other tasks so that other subsystems can start to be converted over more easily. Wrappers are introduced into a new header (linux/cred.h) for UID/GID, EUID/EGID, SUID/SGID, FSUID/FSGID, cap_effective and current's subscribed user_struct. These wrappers are macros because the ordering between header files mitigates against making them inline functions. linux/cred.h is #included from linux/sched.h. Further, XFS is modified such that it no longer defines and uses parameterised versions of current_fs[ug]id(), thus getting rid of the namespace collision otherwise incurred. Signed-off-by: David Howells Signed-off-by: James Morris --- include/linux/cred.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 1 + 2 files changed, 51 insertions(+) create mode 100644 include/linux/cred.h (limited to 'include/linux') diff --git a/include/linux/cred.h b/include/linux/cred.h new file mode 100644 index 000000000000..b69222cc1fd2 --- /dev/null +++ b/include/linux/cred.h @@ -0,0 +1,50 @@ +/* Credentials management + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _LINUX_CRED_H +#define _LINUX_CRED_H + +#define get_current_user() (get_uid(current->user)) + +#define task_uid(task) ((task)->uid) +#define task_gid(task) ((task)->gid) +#define task_euid(task) ((task)->euid) +#define task_egid(task) ((task)->egid) + +#define current_uid() (current->uid) +#define current_gid() (current->gid) +#define current_euid() (current->euid) +#define current_egid() (current->egid) +#define current_suid() (current->suid) +#define current_sgid() (current->sgid) +#define current_fsuid() (current->fsuid) +#define current_fsgid() (current->fsgid) +#define current_cap() (current->cap_effective) + +#define current_uid_gid(_uid, _gid) \ +do { \ + *(_uid) = current->uid; \ + *(_gid) = current->gid; \ +} while(0) + +#define current_euid_egid(_uid, _gid) \ +do { \ + *(_uid) = current->euid; \ + *(_gid) = current->egid; \ +} while(0) + +#define current_fsuid_fsgid(_uid, _gid) \ +do { \ + *(_uid) = current->fsuid; \ + *(_gid) = current->fsgid; \ +} while(0) + +#endif /* _LINUX_CRED_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 5850bfb968a8..cfb0d87b99fc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -87,6 +87,7 @@ struct sched_param { #include #include #include +#include #include -- cgit v1.2.2 From f4f4d58734916e816d4b4a7cf61b3fc22ce02683 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 28 Jul 2008 10:39:28 -0400 Subject: USB: add missing kerneldoc line for "needs_binding" This patch (as1117) adds a kerneldoc line for the "needs_binding" field in struct usb_interface. It was accidentally omitted when the field was added. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 5811c5da69f9..0924cd9c30f6 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -110,6 +110,8 @@ enum usb_interface_condition { * @sysfs_files_created: sysfs attributes exist * @needs_remote_wakeup: flag set when the driver requires remote-wakeup * capability during autosuspend. + * @needs_binding: flag set when the driver should be re-probed or unbound + * following a reset or suspend operation it doesn't support. * @dev: driver model's view of this device * @usb_dev: if an interface is bound to the USB major, this will point * to the sysfs representation for that device. -- cgit v1.2.2 From 0282b7f2a874e72c18fcd5a112ccf67f71ba7f5c Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 29 Jul 2008 12:01:04 -0400 Subject: usb-serial: don't release unregistered minors This patch (as1121) fixes a bug in the USB serial core. When a device is unregistered, the core will give back its minors -- even if the device hasn't been assigned any! The patch reserves the highest minor value (255) to mean that no minor was assigned. It also removes some dead code and does a small style fixup. Signed-off-by: Alan Stern Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/serial.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 09a3e6a7518f..655341d0f534 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -17,7 +17,8 @@ #include #define SERIAL_TTY_MAJOR 188 /* Nice legal number now */ -#define SERIAL_TTY_MINORS 255 /* loads of devices :) */ +#define SERIAL_TTY_MINORS 254 /* loads of devices :) */ +#define SERIAL_TTY_NO_MINOR 255 /* No minor was assigned */ /* The maximum number of ports one device can grab at once */ #define MAX_NUM_PORTS 8 -- cgit v1.2.2 From 550a7375fe720924241f0eb76e4a5c1a3eb8c32f Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 24 Jul 2008 12:27:36 +0300 Subject: USB: Add MUSB and TUSB support This patch adds support for MUSB and TUSB controllers integrated into omap2430 and davinci. It also adds support for external tusb6010 controller. Cc: David Brownell Cc: Tony Lindgren Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/musb.h | 70 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) create mode 100644 include/linux/usb/musb.h (limited to 'include/linux') diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h new file mode 100644 index 000000000000..d325a0d5bf4f --- /dev/null +++ b/include/linux/usb/musb.h @@ -0,0 +1,70 @@ +/* + * This is used to for host and peripheral modes of the driver for + * Inventra (Multidrop) Highspeed Dual-Role Controllers: (M)HDRC. + * + * Board initialization should put one of these into dev->platform_data, + * probably on some platform_device named "musb_hdrc". It encapsulates + * key configuration differences between boards. + */ + +/* The USB role is defined by the connector used on the board, so long as + * standards are being followed. (Developer boards sometimes won't.) + */ +enum musb_mode { + MUSB_UNDEFINED = 0, + MUSB_HOST, /* A or Mini-A connector */ + MUSB_PERIPHERAL, /* B or Mini-B connector */ + MUSB_OTG /* Mini-AB connector */ +}; + +struct clk; + +struct musb_hdrc_platform_data { + /* MUSB_HOST, MUSB_PERIPHERAL, or MUSB_OTG */ + u8 mode; + + /* for clk_get() */ + const char *clock; + + /* (HOST or OTG) switch VBUS on/off */ + int (*set_vbus)(struct device *dev, int is_on); + + /* (HOST or OTG) mA/2 power supplied on (default = 8mA) */ + u8 power; + + /* (PERIPHERAL) mA/2 max power consumed (default = 100mA) */ + u8 min_power; + + /* (HOST or OTG) msec/2 after VBUS on till power good */ + u8 potpgt; + + /* TBD: chip defaults should probably go someplace else, + * e.g. number of tx/rx endpoints, etc + */ + unsigned multipoint:1; + + /* Power the device on or off */ + int (*set_power)(int state); + + /* Turn device clock on or off */ + int (*set_clock)(struct clk *clock, int is_on); +}; + + +/* TUSB 6010 support */ + +#define TUSB6010_OSCCLK_60 16667 /* psec/clk @ 60.0 MHz */ +#define TUSB6010_REFCLK_24 41667 /* psec/clk @ 24.0 MHz XI */ +#define TUSB6010_REFCLK_19 52083 /* psec/clk @ 19.2 MHz CLKIN */ + +#ifdef CONFIG_ARCH_OMAP2 + +extern int __init tusb6010_setup_interface( + struct musb_hdrc_platform_data *data, + unsigned ps_refclk, unsigned waitpin, + unsigned async_cs, unsigned sync_cs, + unsigned irq, unsigned dmachan); + +extern int tusb6010_platform_retime(unsigned is_refclk); + +#endif /* OMAP2 */ -- cgit v1.2.2 From ca6d1b1333bc2e61e37982de1f28d8604c232414 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Fri, 8 Aug 2008 12:40:54 +0300 Subject: usb: musb: pass configuration specifics via pdata Use platform_data to pass musb configuration-specific details to musb driver. This patch will prevent that other platforms selecting HAVE_CLK and enabling musb won't break tree building. The other parts of it will come when linux-omap merge up more omap2/3 board-files. Signed-off-by: Felipe Balbi Acked-by: Paul Mundt Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/musb.h | 38 +++++++++++++++++++++++++++++++++----- 1 file changed, 33 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h index d325a0d5bf4f..630962c04ca4 100644 --- a/include/linux/usb/musb.h +++ b/include/linux/usb/musb.h @@ -19,6 +19,36 @@ enum musb_mode { struct clk; +struct musb_hdrc_eps_bits { + const char name[16]; + u8 bits; +}; + +struct musb_hdrc_config { + /* MUSB configuration-specific details */ + unsigned multipoint:1; /* multipoint device */ + unsigned dyn_fifo:1; /* supports dynamic fifo sizing */ + unsigned soft_con:1; /* soft connect required */ + unsigned utm_16:1; /* utm data witdh is 16 bits */ + unsigned big_endian:1; /* true if CPU uses big-endian */ + unsigned mult_bulk_tx:1; /* Tx ep required for multbulk pkts */ + unsigned mult_bulk_rx:1; /* Rx ep required for multbulk pkts */ + unsigned high_iso_tx:1; /* Tx ep required for HB iso */ + unsigned high_iso_rx:1; /* Rx ep required for HD iso */ + unsigned dma:1; /* supports DMA */ + unsigned vendor_req:1; /* vendor registers required */ + + u8 num_eps; /* number of endpoints _with_ ep0 */ + u8 dma_channels; /* number of dma channels */ + u8 dyn_fifo_size; /* dynamic size in bytes */ + u8 vendor_ctrl; /* vendor control reg width */ + u8 vendor_stat; /* vendor status reg witdh */ + u8 dma_req_chan; /* bitmask for required dma channels */ + u8 ram_bits; /* ram address size */ + + struct musb_hdrc_eps_bits *eps_bits; +}; + struct musb_hdrc_platform_data { /* MUSB_HOST, MUSB_PERIPHERAL, or MUSB_OTG */ u8 mode; @@ -38,16 +68,14 @@ struct musb_hdrc_platform_data { /* (HOST or OTG) msec/2 after VBUS on till power good */ u8 potpgt; - /* TBD: chip defaults should probably go someplace else, - * e.g. number of tx/rx endpoints, etc - */ - unsigned multipoint:1; - /* Power the device on or off */ int (*set_power)(int state); /* Turn device clock on or off */ int (*set_clock)(struct clk *clock, int is_on); + + /* MUSB configuration-specific details */ + struct musb_hdrc_config *config; }; -- cgit v1.2.2 From 5cd9c58fbe9ec92b45b27e131719af4f2bd9eb40 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 14 Aug 2008 11:37:28 +0100 Subject: security: Fix setting of PF_SUPERPRIV by __capable() Fix the setting of PF_SUPERPRIV by __capable() as it could corrupt the flags the target process if that is not the current process and it is trying to change its own flags in a different way at the same time. __capable() is using neither atomic ops nor locking to protect t->flags. This patch removes __capable() and introduces has_capability() that doesn't set PF_SUPERPRIV on the process being queried. This patch further splits security_ptrace() in two: (1) security_ptrace_may_access(). This passes judgement on whether one process may access another only (PTRACE_MODE_ATTACH for ptrace() and PTRACE_MODE_READ for /proc), and takes a pointer to the child process. current is the parent. (2) security_ptrace_traceme(). This passes judgement on PTRACE_TRACEME only, and takes only a pointer to the parent process. current is the child. In Smack and commoncap, this uses has_capability() to determine whether the parent will be permitted to use PTRACE_ATTACH if normal checks fail. This does not set PF_SUPERPRIV. Two of the instances of __capable() actually only act on current, and so have been changed to calls to capable(). Of the places that were using __capable(): (1) The OOM killer calls __capable() thrice when weighing the killability of a process. All of these now use has_capability(). (2) cap_ptrace() and smack_ptrace() were using __capable() to check to see whether the parent was allowed to trace any process. As mentioned above, these have been split. For PTRACE_ATTACH and /proc, capable() is now used, and for PTRACE_TRACEME, has_capability() is used. (3) cap_safe_nice() only ever saw current, so now uses capable(). (4) smack_setprocattr() rejected accesses to tasks other than current just after calling __capable(), so the order of these two tests have been switched and capable() is used instead. (5) In smack_file_send_sigiotask(), we need to allow privileged processes to receive SIGIO on files they're manipulating. (6) In smack_task_wait(), we let a process wait for a privileged process, whether or not the process doing the waiting is privileged. I've tested this with the LTP SELinux and syscalls testscripts. Signed-off-by: David Howells Acked-by: Serge Hallyn Acked-by: Casey Schaufler Acked-by: Andrew G. Morgan Acked-by: Al Viro Signed-off-by: James Morris --- include/linux/capability.h | 15 +++++++++++++-- include/linux/security.h | 39 +++++++++++++++++++++++++-------------- 2 files changed, 38 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index 02673846d205..9d1fe30b6f6c 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -503,8 +503,19 @@ extern const kernel_cap_t __cap_init_eff_set; kernel_cap_t cap_set_effective(const kernel_cap_t pE_new); -int capable(int cap); -int __capable(struct task_struct *t, int cap); +/** + * has_capability - Determine if a task has a superior capability available + * @t: The task in question + * @cap: The capability to be tested for + * + * Return true if the specified task has the given superior capability + * currently in effect, false if not. + * + * Note that this does not set PF_SUPERPRIV on the task. + */ +#define has_capability(t, cap) (security_capable((t), (cap)) == 0) + +extern int capable(int cap); #endif /* __KERNEL__ */ diff --git a/include/linux/security.h b/include/linux/security.h index fd96e7f8a6f9..2ee5ecfb2393 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -46,8 +46,8 @@ struct audit_krule; */ extern int cap_capable(struct task_struct *tsk, int cap); extern int cap_settime(struct timespec *ts, struct timezone *tz); -extern int cap_ptrace(struct task_struct *parent, struct task_struct *child, - unsigned int mode); +extern int cap_ptrace_may_access(struct task_struct *child, unsigned int mode); +extern int cap_ptrace_traceme(struct task_struct *parent); extern int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted); extern int cap_capset_check(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted); extern void cap_capset_set(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted); @@ -1157,17 +1157,24 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @alter contains the flag indicating whether changes are to be made. * Return 0 if permission is granted. * - * @ptrace: - * Check permission before allowing the @parent process to trace the + * @ptrace_may_access: + * Check permission before allowing the current process to trace the * @child process. * Security modules may also want to perform a process tracing check * during an execve in the set_security or apply_creds hooks of * binprm_security_ops if the process is being traced and its security * attributes would be changed by the execve. - * @parent contains the task_struct structure for parent process. - * @child contains the task_struct structure for child process. + * @child contains the task_struct structure for the target process. * @mode contains the PTRACE_MODE flags indicating the form of access. * Return 0 if permission is granted. + * @ptrace_traceme: + * Check that the @parent process has sufficient permission to trace the + * current process before allowing the current process to present itself + * to the @parent process for tracing. + * The parent process will still have to undergo the ptrace_may_access + * checks before it is allowed to trace this one. + * @parent contains the task_struct structure for debugger process. + * Return 0 if permission is granted. * @capget: * Get the @effective, @inheritable, and @permitted capability sets for * the @target process. The hook may also perform permission checking to @@ -1287,8 +1294,8 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) struct security_operations { char name[SECURITY_NAME_MAX + 1]; - int (*ptrace) (struct task_struct *parent, struct task_struct *child, - unsigned int mode); + int (*ptrace_may_access) (struct task_struct *child, unsigned int mode); + int (*ptrace_traceme) (struct task_struct *parent); int (*capget) (struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted); @@ -1560,8 +1567,8 @@ extern struct dentry *securityfs_create_dir(const char *name, struct dentry *par extern void securityfs_remove(struct dentry *dentry); /* Security operations */ -int security_ptrace(struct task_struct *parent, struct task_struct *child, - unsigned int mode); +int security_ptrace_may_access(struct task_struct *child, unsigned int mode); +int security_ptrace_traceme(struct task_struct *parent); int security_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, @@ -1742,11 +1749,15 @@ static inline int security_init(void) return 0; } -static inline int security_ptrace(struct task_struct *parent, - struct task_struct *child, - unsigned int mode) +static inline int security_ptrace_may_access(struct task_struct *child, + unsigned int mode) +{ + return cap_ptrace_may_access(child, mode); +} + +static inline int security_ptrace_traceme(struct task_struct *child) { - return cap_ptrace(parent, child, mode); + return cap_ptrace_traceme(parent); } static inline int security_capget(struct task_struct *target, -- cgit v1.2.2 From ce289e89726948b50a58c9e8f4e81174a8c9c254 Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Fri, 15 Aug 2008 00:40:19 -0700 Subject: suspend: fix section mismatch warning - register_nosave_region WARNING: vmlinux.o(.text+0xe684): Section mismatch in reference from the function register_nosave_region() to the function .init.text:__register_nosave_region() The function register_nosave_region() references the function __init __register_nosave_region(). This is often because register_nosave_region lacks a __init annotation or the annotation of __register_nosave_region is wrong. register_nosave_region calls __init function and is called only from __init functions Signed-off-by: Marcin Slusarz Acked-by: Rafael J. Wysocki Cc: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/suspend.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index c63435095970..2ce8207686e2 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -217,11 +217,11 @@ struct platform_hibernation_ops { #ifdef CONFIG_HIBERNATION /* kernel/power/snapshot.c */ extern void __register_nosave_region(unsigned long b, unsigned long e, int km); -static inline void register_nosave_region(unsigned long b, unsigned long e) +static inline void __init register_nosave_region(unsigned long b, unsigned long e) { __register_nosave_region(b, e, 0); } -static inline void register_nosave_region_late(unsigned long b, unsigned long e) +static inline void __init register_nosave_region_late(unsigned long b, unsigned long e) { __register_nosave_region(b, e, 1); } -- cgit v1.2.2 From 163f6876f5c3ff8215e900b93779e960a56b3694 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 15 Aug 2008 00:40:22 -0700 Subject: kexec jump: rename KEXEC_CONTROL_CODE_SIZE to KEXEC_CONTROL_PAGE_SIZE Rename KEXEC_CONTROL_CODE_SIZE to KEXEC_CONTROL_PAGE_SIZE, because control page is used for not only code on some platform. For example in kexec jump, it is used for data and stack too. [akpm@linux-foundation.org: unbreak powerpc and arm, finish conversion] Signed-off-by: Huang Ying Cc: Pavel Machek Cc: "Rafael J. Wysocki" Cc: "Eric W. Biederman" Cc: Vivek Goyal Cc: Ingo Molnar Cc: Russell King Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 32110cede64f..17f76fc05173 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -25,8 +25,8 @@ #error KEXEC_CONTROL_MEMORY_LIMIT not defined #endif -#ifndef KEXEC_CONTROL_CODE_SIZE -#error KEXEC_CONTROL_CODE_SIZE not defined +#ifndef KEXEC_CONTROL_PAGE_SIZE +#error KEXEC_CONTROL_PAGE_SIZE not defined #endif #ifndef KEXEC_ARCH -- cgit v1.2.2 From ca195b7f6da3d5dde0bb85a7c322d7de73352653 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 15 Aug 2008 00:40:24 -0700 Subject: kexec jump: remove duplication of kexec_restart_prepare() Call kernel_restart_prepare() in kernel_kexec() instead of duplicating the code. Signed-off-by: Huang Ying Acked-by: Pavel Machek Acked-by: Vivek Goyal Cc: Pavel Machek Cc: "Rafael J. Wysocki" Cc: "Eric W. Biederman" Cc: Vivek Goyal Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reboot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index b93b541cf111..988e55fe649b 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -59,6 +59,7 @@ extern void machine_crash_shutdown(struct pt_regs *); * Architecture independent implemenations of sys_reboot commands. */ +extern void kernel_restart_prepare(char *cmd); extern void kernel_restart(char *cmd); extern void kernel_halt(void); extern void kernel_power_off(void); -- cgit v1.2.2 From 9bdeb7b5d34f197dea7859d24475943395ffea5e Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 15 Aug 2008 00:40:25 -0700 Subject: kexec jump: __ftrace_enabled_save/restore Add __ftrace_enabled_save/restore, used to disable ftrace for a while. Now, this is used by kexec jump, which need a version without lock, for general situation, a locked version should be used. Signed-off-by: Huang Ying Cc: Pavel Machek Cc: "Rafael J. Wysocki" Cc: "Eric W. Biederman" Cc: Vivek Goyal Cc: Ingo Molnar Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ftrace.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index f368d041e02d..bb384068272e 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -98,6 +98,27 @@ static inline void tracer_disable(void) #endif } +/* Ftrace disable/restore without lock. Some synchronization mechanism + * must be used to prevent ftrace_enabled to be changed between + * disable/restore. */ +static inline int __ftrace_enabled_save(void) +{ +#ifdef CONFIG_FTRACE + int saved_ftrace_enabled = ftrace_enabled; + ftrace_enabled = 0; + return saved_ftrace_enabled; +#else + return 0; +#endif +} + +static inline void __ftrace_enabled_restore(int enabled) +{ +#ifdef CONFIG_FTRACE + ftrace_enabled = enabled; +#endif +} + #ifdef CONFIG_FRAME_POINTER /* TODO: need to fix this for ARM */ # define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -- cgit v1.2.2 From be4de35263f59ca1f4740edfffbfb02cc3f2189e Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 15 Aug 2008 00:40:44 -0700 Subject: completions: uninline try_wait_for_completion and completion_done m68k fails to build with these functions inlined in completion.h. Move them out of line into sched.c and export them to avoid this problem. Signed-off-by: Dave Chinner Cc: Geert Uytterhoeven Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/completion.h | 46 ++-------------------------------------------- 1 file changed, 2 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/completion.h b/include/linux/completion.h index 57faa60de9bd..02ef8835999c 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -49,6 +49,8 @@ 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 bool try_wait_for_completion(struct completion *x); +extern bool completion_done(struct completion *x); extern void complete(struct completion *); extern void complete_all(struct completion *); @@ -56,48 +58,4 @@ extern void complete_all(struct completion *); #define INIT_COMPLETION(x) ((x).done = 0) -/** - * try_wait_for_completion - try to decrement a completion without blocking - * @x: completion structure - * - * Returns: 0 if a decrement cannot be done without blocking - * 1 if a decrement succeeded. - * - * If a completion is being used as a counting completion, - * attempt to decrement the counter without blocking. This - * enables us to avoid waiting if the resource the completion - * is protecting is not available. - */ -static inline bool try_wait_for_completion(struct completion *x) -{ - int ret = 1; - - spin_lock_irq(&x->wait.lock); - if (!x->done) - ret = 0; - else - x->done--; - spin_unlock_irq(&x->wait.lock); - return ret; -} - -/** - * completion_done - Test to see if a completion has any waiters - * @x: completion structure - * - * Returns: 0 if there are waiters (wait_for_completion() in progress) - * 1 if there are no waiters. - * - */ -static inline bool completion_done(struct completion *x) -{ - int ret = 1; - - spin_lock_irq(&x->wait.lock); - if (!x->done) - ret = 0; - spin_unlock_irq(&x->wait.lock); - return ret; -} - #endif -- cgit v1.2.2 From 8c9a9dd0fa3a269d380eaae2dc1bee39e865fae1 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Fri, 15 Aug 2008 10:39:38 +0100 Subject: tty: remove resize window special case This moves it to being a tty operation. That removes special cases and now also means that resize can be picked up by um and other non vt consoles which may have a resize operation. Signed-off-by: Alan Cox Signed-off-by: Linus Torvalds --- include/linux/tty.h | 2 ++ include/linux/tty_driver.h | 14 ++++++++++++++ include/linux/vt_kern.h | 1 - 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index e3579cb086e0..0cbec74ec086 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -331,6 +331,8 @@ extern int tty_write_room(struct tty_struct *tty); extern void tty_driver_flush_buffer(struct tty_struct *tty); extern void tty_throttle(struct tty_struct *tty); extern void tty_unthrottle(struct tty_struct *tty); +extern int tty_do_resize(struct tty_struct *tty, struct tty_struct *real_tty, + struct winsize *ws); extern int is_current_pgrp_orphaned(void); extern struct pid *tty_get_pgrp(struct tty_struct *tty); diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index e1065ac0d922..16d27944c321 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -168,6 +168,18 @@ * * Optional: If not provided then the write method is called under * the atomic write lock to keep it serialized with the ldisc. + * + * int (*resize)(struct tty_struct *tty, struct tty_struct *real_tty, + * unsigned int rows, unsigned int cols); + * + * Called when a termios request is issued which changes the + * requested terminal geometry. + * + * Optional: the default action is to update the termios structure + * without error. This is usually the correct behaviour. Drivers should + * not force errors here if they are not resizable objects (eg a serial + * line). See tty_do_resize() if you need to wrap the standard method + * in your own logic - the usual case. */ #include @@ -206,6 +218,8 @@ struct tty_operations { int (*tiocmget)(struct tty_struct *tty, struct file *file); int (*tiocmset)(struct tty_struct *tty, struct file *file, unsigned int set, unsigned int clear); + int (*resize)(struct tty_struct *tty, struct tty_struct *real_tty, + struct winsize *ws); #ifdef CONFIG_CONSOLE_POLL int (*poll_init)(struct tty_driver *driver, int line, char *options); int (*poll_get_char)(struct tty_driver *driver, int line); diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 1c78d56c57e5..1cbd0a7db4e6 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -35,7 +35,6 @@ extern int fg_console, last_console, want_console; int vc_allocate(unsigned int console); int vc_cons_allocated(unsigned int console); int vc_resize(struct vc_data *vc, unsigned int cols, unsigned int lines); -int vc_lock_resize(struct vc_data *vc, unsigned int cols, unsigned int lines); void vc_deallocate(unsigned int console); void reset_palette(struct vc_data *vc); void do_blank_screen(int entering_gfx); -- cgit v1.2.2 From 605d9288b3e8a3d15e6f36185c2fc737b6979572 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 16 Aug 2008 11:07:21 +0100 Subject: mm: VM_flags comment fixes Try to comment away a little of the confusion between mm's vm_area_struct vm_flags and vmalloc's vm_struct flags: based on an idea by Ulrich Drepper. Signed-off-by: Hugh Dickins Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- include/linux/mm_types.h | 2 +- include/linux/vmalloc.h | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index fa651609b65d..72a15dc26bbf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -73,7 +73,7 @@ extern unsigned int kobjsize(const void *objp); #endif /* - * vm_flags.. + * vm_flags in vm_area_struct, see mm_types.h. */ #define VM_READ 0x00000001 /* currently active flags */ #define VM_WRITE 0x00000002 diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 386edbe2cb4e..bf334138c7c1 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -113,7 +113,7 @@ struct vm_area_struct { struct vm_area_struct *vm_next; pgprot_t vm_page_prot; /* Access permissions of this VMA. */ - unsigned long vm_flags; /* Flags, listed below. */ + unsigned long vm_flags; /* Flags, see mm.h. */ struct rb_node vm_rb; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 364789aae9f3..328eb4022727 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -4,9 +4,9 @@ #include #include /* pgprot_t */ -struct vm_area_struct; +struct vm_area_struct; /* vma defining user mapping in mm_types.h */ -/* bits in vm_struct->flags */ +/* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ #define VM_ALLOC 0x00000002 /* vmalloc() */ #define VM_MAP 0x00000004 /* vmap()ed pages */ -- cgit v1.2.2 From 5e6b83ed8c00f2e2ae5b2413c5907bed735b600d Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 16 Aug 2008 11:55:04 +0100 Subject: Fix header export of videodev2.h, ivtv.h, ivtvfb.h The exported copy of videodev2.h contains this line: #define #include This is because for some reason it defines __user for itself -- despite the fact that we remove all instances of __user when exporting headers. _All_ pointers in userspace are user pointers. Fix it by removing the unnecessary '#define __user' from the file. The new headers ivtv.h and ivtvfb.h would have the same problem... if whoever put them there had actually remembered to add them to the Kbuild file while he was at it. Fix those too, and export them as was presumably intended. Note that includes of are also stripped by the header export process, so those don't need to be conditional. Signed-off-by: David Woodhouse Signed-off-by: Mauro Carvalho Chehab Acked-by: Hans Verkuil Signed-off-by: Linus Torvalds --- include/linux/Kbuild | 2 ++ include/linux/ivtv.h | 6 +----- include/linux/ivtvfb.h | 6 +----- include/linux/videodev2.h | 4 ++-- 4 files changed, 6 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 327f60658d94..7d970678f940 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -250,6 +250,8 @@ unifdef-y += isdn.h unifdef-y += isdnif.h unifdef-y += isdn_divertif.h unifdef-y += isdn_ppp.h +unifdef-y += ivtv.h +unifdef-y += ivtvfb.h unifdef-y += joystick.h unifdef-y += kdev_t.h unifdef-y += kd.h diff --git a/include/linux/ivtv.h b/include/linux/ivtv.h index 794b8daa9378..17ca64b5a66c 100644 --- a/include/linux/ivtv.h +++ b/include/linux/ivtv.h @@ -21,11 +21,7 @@ #ifndef __LINUX_IVTV_H__ #define __LINUX_IVTV_H__ -#ifdef __KERNEL__ -#include /* need __user */ -#else -#define __user -#endif +#include #include /* ivtv knows several distinct output modes: MPEG streaming, diff --git a/include/linux/ivtvfb.h b/include/linux/ivtvfb.h index e980ba62ddcc..e20af47b59ad 100644 --- a/include/linux/ivtvfb.h +++ b/include/linux/ivtvfb.h @@ -21,11 +21,7 @@ #ifndef __LINUX_IVTVFB_H__ #define __LINUX_IVTVFB_H__ -#ifdef __KERNEL__ -#include /* need __user */ -#else -#define __user -#endif +#include #include /* Framebuffer external API */ diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index e466bd54a50e..e65a6bed4e3e 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -55,13 +55,13 @@ */ #ifndef __LINUX_VIDEODEV2_H #define __LINUX_VIDEODEV2_H + #ifdef __KERNEL__ #include /* need struct timeval */ -#include /* need __user */ #else -#define __user #include #endif +#include #include #include -- cgit v1.2.2 From 5e186b57e7ede86aeb9db30e66315bde4e8b1815 Mon Sep 17 00:00:00 2001 From: Alexander Beregalov Date: Sun, 17 Aug 2008 05:34:20 +0400 Subject: security.h: fix build failure security.h: fix build failure include/linux/security.h: In function 'security_ptrace_traceme': include/linux/security.h:1760: error: 'parent' undeclared (first use in this function) Signed-off-by: Alexander Beregalov Tested-by: Ingo Molnar Signed-off-by: James Morris --- include/linux/security.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 2ee5ecfb2393..80c4d002864c 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1755,7 +1755,7 @@ static inline int security_ptrace_may_access(struct task_struct *child, return cap_ptrace_may_access(child, mode); } -static inline int security_ptrace_traceme(struct task_struct *child) +static inline int security_ptrace_traceme(struct task_struct *parent) { return cap_ptrace_traceme(parent); } -- cgit v1.2.2