From b652b438fcad4c9c079d0774e9d45ee58fae22e2 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 15 Jun 2005 12:38:14 +0100 Subject: [PATCH] I2C: Add PXA I2C driver Add support for the I2C PXA driver. Signed-off-by: Russell King --- include/linux/i2c-id.h | 1 + include/linux/i2c-pxa.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+) create mode 100644 include/linux/i2c-pxa.h (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 89270ce51470..74d6dc942715 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -203,6 +203,7 @@ #define I2C_ALGO_MV64XXX 0x190000 /* Marvell mv64xxx i2c ctlr */ #define I2C_ALGO_PCA 0x1a0000 /* PCA 9564 style adapters */ #define I2C_ALGO_AU1550 0x1b0000 /* Au1550 PSC algorithm */ +#define I2C_ALGO_PXA 0x1c0000 /* Intel PXA I2C algorithm */ #define I2C_ALGO_EXP 0x800000 /* experimental */ diff --git a/include/linux/i2c-pxa.h b/include/linux/i2c-pxa.h new file mode 100644 index 000000000000..5f3eaf802223 --- /dev/null +++ b/include/linux/i2c-pxa.h @@ -0,0 +1,48 @@ +#ifndef _LINUX_I2C_ALGO_PXA_H +#define _LINUX_I2C_ALGO_PXA_H + +struct i2c_eeprom_emu_watcher { + void (*write)(void *, unsigned int addr, unsigned char newval); +}; + +struct i2c_eeprom_emu_watch { + struct list_head node; + unsigned int start; + unsigned int end; + struct i2c_eeprom_emu_watcher *ops; + void *data; +}; + +#define I2C_EEPROM_EMU_SIZE (256) + +struct i2c_eeprom_emu { + unsigned int size; + unsigned int ptr; + unsigned int seen_start; + struct list_head watch; + + unsigned char bytes[I2C_EEPROM_EMU_SIZE]; +}; + +typedef enum i2c_slave_event_e { + I2C_SLAVE_EVENT_START_READ, + I2C_SLAVE_EVENT_START_WRITE, + I2C_SLAVE_EVENT_STOP +} i2c_slave_event_t; + +struct i2c_slave_client { + void *data; + void (*event)(void *ptr, i2c_slave_event_t event); + int (*read) (void *ptr); + void (*write)(void *ptr, unsigned int val); +}; + +extern int i2c_eeprom_emu_addwatcher(struct i2c_eeprom_emu *, void *data, + unsigned int addr, unsigned int size, + struct i2c_eeprom_emu_watcher *); + +extern void i2c_eeprom_emu_delwatcher(struct i2c_eeprom_emu *, void *data, struct i2c_eeprom_emu_watcher *watcher); + +extern struct i2c_eeprom_emu *i2c_pxa_get_eeprom(void); + +#endif /* _LINUX_I2C_ALGO_PXA_H */ -- cgit v1.2.3 From df46b9a44ceb5af2ea2351ce8e28ae7bd840b00f Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 20 Jun 2005 14:04:44 +0200 Subject: [PATCH] Add blk_rq_map_kern() Add blk_rq_map_kern which takes a kernel buffer and maps it into a request and bio. This can be used by the dm hw_handlers, old sg_scsi_ioctl, and one day scsi special requests so all requests comming into scsi will have bios. All requests having bios should allow scsi to use scatter lists for all IO and allow it to use block layer functions. Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 ++ include/linux/blkdev.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 038022763f09..1dd2bc2e84ae 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -282,6 +282,8 @@ extern int bio_get_nr_vecs(struct block_device *); extern struct bio *bio_map_user(struct request_queue *, struct block_device *, unsigned long, unsigned int, int); extern void bio_unmap_user(struct bio *); +extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int, + unsigned int); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); extern struct bio *bio_copy_user(struct request_queue *, unsigned long, unsigned int, int); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4a99b76c5a33..67339bc5f6bc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -560,6 +560,8 @@ extern void blk_run_queue(request_queue_t *); extern void blk_queue_activity_fn(request_queue_t *, activity_fn *, void *); extern struct request *blk_rq_map_user(request_queue_t *, int, void __user *, unsigned int); extern int blk_rq_unmap_user(struct request *, struct bio *, unsigned int); +extern struct request *blk_rq_map_kern(request_queue_t *, int, void *, + unsigned int, unsigned int); extern int blk_execute_rq(request_queue_t *, struct gendisk *, struct request *); static inline request_queue_t *bdev_get_queue(struct block_device *bdev) -- cgit v1.2.3 From dd1cab95f356f1395278633565f198463cf6bd24 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 20 Jun 2005 14:06:01 +0200 Subject: [PATCH] Cleanup blk_rq_map_* interfaces Change the blk_rq_map_user() and blk_rq_map_kern() interface to require a previously allocated request to be passed in. This is both more efficient for multiple iterations of mapping data to the same request, and it is also a much nicer API. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 67339bc5f6bc..fc0dce078616 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -558,10 +558,9 @@ extern void blk_sync_queue(struct request_queue *q); extern void __blk_stop_queue(request_queue_t *q); extern void blk_run_queue(request_queue_t *); extern void blk_queue_activity_fn(request_queue_t *, activity_fn *, void *); -extern struct request *blk_rq_map_user(request_queue_t *, int, void __user *, unsigned int); -extern int blk_rq_unmap_user(struct request *, struct bio *, unsigned int); -extern struct request *blk_rq_map_kern(request_queue_t *, int, void *, - unsigned int, unsigned int); +extern int blk_rq_map_user(request_queue_t *, struct request *, void __user *, unsigned int); +extern int blk_rq_unmap_user(struct bio *, unsigned int); +extern int blk_rq_map_kern(request_queue_t *, struct request *, void *, unsigned int, unsigned int); extern int blk_execute_rq(request_queue_t *, struct gendisk *, struct request *); static inline request_queue_t *bdev_get_queue(struct block_device *bdev) -- cgit v1.2.3 From f1970baf6d74e03bd32072ab453f2fc01bc1b8d3 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Mon, 20 Jun 2005 14:06:52 +0200 Subject: [PATCH] Add scatter-gather support for the block layer SG_IO Signed-off-by: Jens Axboe --- include/linux/bio.h | 4 ++++ include/linux/blkdev.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 1dd2bc2e84ae..ebcd03ba2e20 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -281,6 +281,10 @@ extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_get_nr_vecs(struct block_device *); extern struct bio *bio_map_user(struct request_queue *, struct block_device *, unsigned long, unsigned int, int); +struct sg_iovec; +extern struct bio *bio_map_user_iov(struct request_queue *, + struct block_device *, + struct sg_iovec *, int, int); extern void bio_unmap_user(struct bio *); extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int, unsigned int); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index fc0dce078616..0430ea3e5f2e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -561,6 +561,7 @@ extern void blk_queue_activity_fn(request_queue_t *, activity_fn *, void *); extern int blk_rq_map_user(request_queue_t *, struct request *, void __user *, unsigned int); extern int blk_rq_unmap_user(struct bio *, unsigned int); extern int blk_rq_map_kern(request_queue_t *, struct request *, void *, unsigned int, unsigned int); +extern int blk_rq_map_user_iov(request_queue_t *, struct request *, struct sg_iovec *, int); extern int blk_execute_rq(request_queue_t *, struct gendisk *, struct request *); static inline request_queue_t *bdev_get_queue(struct block_device *bdev) -- cgit v1.2.3 From 994ca9a19616f0d4161a9e825f0835925d522426 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Mon, 20 Jun 2005 14:11:09 +0200 Subject: [PATCH] update blk_execute_rq to take an at_head parameter Original From: Mike Christie Modified to split out block changes (this patch) and SCSI pieces. Signed-off-by: Jens Axboe Signed-off-by: James Bottomley --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0430ea3e5f2e..a48dc12c6699 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -562,8 +562,8 @@ extern int blk_rq_map_user(request_queue_t *, struct request *, void __user *, u extern int blk_rq_unmap_user(struct bio *, unsigned int); extern int blk_rq_map_kern(request_queue_t *, struct request *, void *, unsigned int, unsigned int); extern int blk_rq_map_user_iov(request_queue_t *, struct request *, struct sg_iovec *, int); -extern int blk_execute_rq(request_queue_t *, struct gendisk *, struct request *); - +extern int blk_execute_rq(request_queue_t *, struct gendisk *, + struct request *, int); static inline request_queue_t *bdev_get_queue(struct block_device *bdev) { return bdev->bd_disk->queue; -- cgit v1.2.3 From 559fb51ba7e66fe298b8355fabde1275b7def35f Mon Sep 17 00:00:00 2001 From: Scott Bardone Date: Thu, 23 Jun 2005 01:40:19 -0400 Subject: Update Chelsio gige net driver. - Use extern prefix for functions required. - Removed a lot of wrappers, including t1_read/write_reg_4. - Removed various macros, using native kernel calls now. - Enumerated various #defines. - Removed a lot of shared code which is not currently used in "NIC only" mode. - Removed dead code. Documentation/networking/cxgb.txt: - Updated release notes for version 2.1.1 drivers/net/chelsio/ch_ethtool.h - removed file, no longer using ETHTOOL namespace. drivers/net/chelsio/common.h - moved code from osdep.h to common.h - added comment to #endif indicating which symbol it closes. drivers/net/chelsio/cphy.h - removed dead code. - added comment to #endif indicating which symbol it closes. drivers/net/chelsio/cxgb2.c - use DMA_{32,64}BIT_MASK in include/linux/dma-mapping.h. - removed unused code. - use printk message for link info resembling drivers/net/mii.c. - no longer using the MODULE_xxx namespace. - no longer using "pci_" namespace. - no longer using ETHTOOL namespace. drivers/net/chelsio/cxgb2.h - removed file, merged into common.h drivers/net/chelsio/elmer0.h - removed dead code. - added various enums. - added comment to #endif indicating which symbol it closes. drivers/net/chelsio/espi.c - removed various macros, using native kernel calls now. - removed a lot of wrappers, including t1_read/write_reg_4. drivers/net/chelsio/espi.h - added comment to #endif indicating which symbol it closes. drivers/net/chelsio/gmac.h - added comment to #endif indicating which symbol it closes. drivers/net/chelsio/mv88x201x.c - changes to sync with Chelsio TOT. drivers/net/chelsio/osdep.h - removed file, consolidation. osdep was used to translate wrapper functions since our code supports multiple OSs. removed wrappers. drivers/net/chelsio/pm3393.c - removed various macros, using native kernel calls now. - removed a lot of wrappers, including t1_read/write_reg_4. - removed unused code. drivers/net/chelsio/regs.h - added a few register entries for future and current feature support. - added comment to #endif indicating which symbol it closes. drivers/net/chelsio/sge.c - rewrote large portion of scatter-gather engine to stabilize performance. - using u8/u16/u32 kernel types instead of __u8/__u16/__u32 compiler types. drivers/net/chelsio/sge.h - rewrote large portion of scatter-gather engine to stabilize performance. - added comment to #endif indicating which symbol it closes. drivers/net/chelsio/subr.c - merged tp.c into subr.c - removed various macros, using native kernel calls now. - removed a lot of wrappers, including t1_read/write_reg_4. - removed unused code. drivers/net/chelsio/suni1x10gexp_regs.h - modified copyright and authorship of file. - added comment to #endif indicating which symbol it closes. drivers/net/chelsio/tp.c - removed file, merged into subr.c. drivers/net/chelsio/tp.h - removed file. include/linux/pci_ids.h - patched to include PCI_VENDOR_ID_CHELSIO 0x1425, removed define from our code. --- 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 63e89e47b8e9..41e35a72b964 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2120,6 +2120,7 @@ #define PCI_DEVICE_ID_ENE_1225 0x1225 #define PCI_DEVICE_ID_ENE_1410 0x1410 #define PCI_DEVICE_ID_ENE_1420 0x1420 +#define PCI_VENDOR_ID_CHELSIO 0x1425 #define PCI_VENDOR_ID_SYBA 0x1592 #define PCI_DEVICE_ID_SYBA_2P_EPP 0x0782 -- cgit v1.2.3 From 9bd481f85940726bf66aae5cd03c5b912ad0ae4c Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Tue, 28 Jun 2005 01:46:35 -0400 Subject: wireless: fix ipw warning; add is_broadcast_ether_addr() to linux/etherdevice.h --- include/linux/etherdevice.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 8a2df4dfbc59..ae588aab21b6 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -68,6 +68,12 @@ static inline int is_multicast_ether_addr(const u8 *addr) return ((addr[0] != 0xff) && (0x01 & addr[0])); } +static inline int is_broadcast_ether_addr(const u8 *addr) +{ + return ((addr[0] == 0xff) && (addr[1] == 0xff) && (addr[2] == 0xff) && + (addr[3] == 0xff) && (addr[4] == 0xff) && (addr[5] == 0xff)); +} + /** * is_valid_ether_addr - Determine if the given Ethernet address is valid * @addr: Pointer to a six-byte array containing the Ethernet address -- cgit v1.2.3 From 241fc4367b3ca5d407b043599ed980304a70b91f Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 27 Jul 2005 11:35:54 +0100 Subject: [SERIAL] Expose 8250_pci setup/removal/suspend/resume functions Re-jig the setup/removal/suspend/resume of 8250 pci ports so that they know slightly less about how they're attached to a PCI device. Expose this as the new interface for registering PCI serial ports, as well as the pciserial_board structure and associated flag definitions. Signed-off-by: Russell King --- include/linux/8250_pci.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include/linux') diff --git a/include/linux/8250_pci.h b/include/linux/8250_pci.h index 5f3ab21b339b..192c0ff7a774 100644 --- a/include/linux/8250_pci.h +++ b/include/linux/8250_pci.h @@ -1,2 +1,40 @@ +/* + * Definitions for PCI support. + */ +#define FL_BASE_MASK 0x0007 +#define FL_BASE0 0x0000 +#define FL_BASE1 0x0001 +#define FL_BASE2 0x0002 +#define FL_BASE3 0x0003 +#define FL_BASE4 0x0004 +#define FL_GET_BASE(x) (x & FL_BASE_MASK) + +/* Use successive BARs (PCI base address registers), + else use offset into some specified BAR */ +#define FL_BASE_BARS 0x0008 + +/* do not assign an irq */ +#define FL_NOIRQ 0x0080 + +/* Use the Base address register size to cap number of ports */ +#define FL_REGION_SZ_CAP 0x0100 + +struct pciserial_board { + unsigned int flags; + unsigned int num_ports; + unsigned int base_baud; + unsigned int uart_offset; + unsigned int reg_shift; + unsigned int first_offset; +}; + +struct serial_private; + +struct serial_private * +pciserial_init_ports(struct pci_dev *dev, struct pciserial_board *board); +void pciserial_remove_ports(struct serial_private *priv); +void pciserial_suspend_ports(struct serial_private *priv); +void pciserial_resume_ports(struct serial_private *priv); + int pci_siig10x_fn(struct pci_dev *dev, int enable); int pci_siig20x_fn(struct pci_dev *dev, int enable); -- cgit v1.2.3 From 05caac585f8abd6c0113856bc8858e3ef214d8a6 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 27 Jul 2005 11:41:18 +0100 Subject: [SERIAL] Convert parport_serial to use new 8250_pci interfaces Convert parport_serial to use the new 8250_pci interface, converting the table to a pciserial_board table. This also unuses the SPCI_* definitions in serialP.h, which can now be removed. Signed-off-by: Russell King --- include/linux/8250_pci.h | 3 --- include/linux/serialP.h | 40 ---------------------------------------- 2 files changed, 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/8250_pci.h b/include/linux/8250_pci.h index 192c0ff7a774..3209dd46ea7d 100644 --- a/include/linux/8250_pci.h +++ b/include/linux/8250_pci.h @@ -35,6 +35,3 @@ pciserial_init_ports(struct pci_dev *dev, struct pciserial_board *board); void pciserial_remove_ports(struct serial_private *priv); void pciserial_suspend_ports(struct serial_private *priv); void pciserial_resume_ports(struct serial_private *priv); - -int pci_siig10x_fn(struct pci_dev *dev, int enable); -int pci_siig20x_fn(struct pci_dev *dev, int enable); diff --git a/include/linux/serialP.h b/include/linux/serialP.h index 2b2f35a64d75..2b9e6b9554d5 100644 --- a/include/linux/serialP.h +++ b/include/linux/serialP.h @@ -140,44 +140,4 @@ struct rs_multiport_struct { #define ALPHA_KLUDGE_MCR 0 #endif -/* - * Definitions for PCI support. - */ -#define SPCI_FL_BASE_MASK 0x0007 -#define SPCI_FL_BASE0 0x0000 -#define SPCI_FL_BASE1 0x0001 -#define SPCI_FL_BASE2 0x0002 -#define SPCI_FL_BASE3 0x0003 -#define SPCI_FL_BASE4 0x0004 -#define SPCI_FL_GET_BASE(x) (x & SPCI_FL_BASE_MASK) - -#define SPCI_FL_IRQ_MASK (0x0007 << 4) -#define SPCI_FL_IRQBASE0 (0x0000 << 4) -#define SPCI_FL_IRQBASE1 (0x0001 << 4) -#define SPCI_FL_IRQBASE2 (0x0002 << 4) -#define SPCI_FL_IRQBASE3 (0x0003 << 4) -#define SPCI_FL_IRQBASE4 (0x0004 << 4) -#define SPCI_FL_GET_IRQBASE(x) ((x & SPCI_FL_IRQ_MASK) >> 4) - -/* Use successive BARs (PCI base address registers), - else use offset into some specified BAR */ -#define SPCI_FL_BASE_TABLE 0x0100 - -/* Use successive entries in the irq resource table */ -#define SPCI_FL_IRQ_TABLE 0x0200 - -/* Use the irq resource table instead of dev->irq */ -#define SPCI_FL_IRQRESOURCE 0x0400 - -/* Use the Base address register size to cap number of ports */ -#define SPCI_FL_REGION_SZ_CAP 0x0800 - -/* Do not use irq sharing for this device */ -#define SPCI_FL_NO_SHIRQ 0x1000 - -/* This is a PNP device */ -#define SPCI_FL_ISPNP 0x2000 - -#define SPCI_FL_PNPDEFAULT (SPCI_FL_IRQRESOURCE|SPCI_FL_ISPNP) - #endif /* _LINUX_SERIAL_H */ -- cgit v1.2.3 From 00db8189d984d6c51226dafbbe4a667ce9b7d5da Mon Sep 17 00:00:00 2001 From: Andy Fleming Date: Sat, 30 Jul 2005 19:31:23 -0400 Subject: This patch adds a PHY Abstraction Layer to the Linux Kernel, enabling ethernet drivers to remain as ignorant as is reasonable of the connected PHY's design and operation details. Signed-off-by: Andy Fleming Signed-off-by: Jeff Garzik --- include/linux/ethtool.h | 4 + include/linux/mii.h | 9 +- include/linux/phy.h | 378 ++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 390 insertions(+), 1 deletion(-) create mode 100644 include/linux/phy.h (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index a0ab26aab450..d7021c391b2b 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -408,6 +408,8 @@ struct ethtool_ops { #define SUPPORTED_FIBRE (1 << 10) #define SUPPORTED_BNC (1 << 11) #define SUPPORTED_10000baseT_Full (1 << 12) +#define SUPPORTED_Pause (1 << 13) +#define SUPPORTED_Asym_Pause (1 << 14) /* Indicates what features are advertised by the interface. */ #define ADVERTISED_10baseT_Half (1 << 0) @@ -423,6 +425,8 @@ struct ethtool_ops { #define ADVERTISED_FIBRE (1 << 10) #define ADVERTISED_BNC (1 << 11) #define ADVERTISED_10000baseT_Full (1 << 12) +#define ADVERTISED_Pause (1 << 13) +#define ADVERTISED_Asym_Pause (1 << 14) /* The following are all involved in forcing a particular link * mode for the device for setting things. When getting the diff --git a/include/linux/mii.h b/include/linux/mii.h index 374b615ea9ea..9b8d0476988a 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -22,6 +22,7 @@ #define MII_EXPANSION 0x06 /* Expansion register */ #define MII_CTRL1000 0x09 /* 1000BASE-T control */ #define MII_STAT1000 0x0a /* 1000BASE-T status */ +#define MII_ESTATUS 0x0f /* Extended Status */ #define MII_DCOUNTER 0x12 /* Disconnect counter */ #define MII_FCSCOUNTER 0x13 /* False carrier counter */ #define MII_NWAYTEST 0x14 /* N-way auto-neg test reg */ @@ -54,7 +55,10 @@ #define BMSR_ANEGCAPABLE 0x0008 /* Able to do auto-negotiation */ #define BMSR_RFAULT 0x0010 /* Remote fault detected */ #define BMSR_ANEGCOMPLETE 0x0020 /* Auto-negotiation complete */ -#define BMSR_RESV 0x07c0 /* Unused... */ +#define BMSR_RESV 0x00c0 /* Unused... */ +#define BMSR_ESTATEN 0x0100 /* Extended Status in R15 */ +#define BMSR_100FULL2 0x0200 /* Can do 100BASE-T2 HDX */ +#define BMSR_100HALF2 0x0400 /* Can do 100BASE-T2 FDX */ #define BMSR_10HALF 0x0800 /* Can do 10mbps, half-duplex */ #define BMSR_10FULL 0x1000 /* Can do 10mbps, full-duplex */ #define BMSR_100HALF 0x2000 /* Can do 100mbps, half-duplex */ @@ -114,6 +118,9 @@ #define EXPANSION_MFAULTS 0x0010 /* Multiple faults detected */ #define EXPANSION_RESV 0xffe0 /* Unused... */ +#define ESTATUS_1000_TFULL 0x2000 /* Can do 1000BT Full */ +#define ESTATUS_1000_THALF 0x1000 /* Can do 1000BT Half */ + /* N-way test register. */ #define NWAYTEST_RESV1 0x00ff /* Unused... */ #define NWAYTEST_LOOPBACK 0x0100 /* Enable loopback for N-way */ diff --git a/include/linux/phy.h b/include/linux/phy.h new file mode 100644 index 000000000000..3404804dc22d --- /dev/null +++ b/include/linux/phy.h @@ -0,0 +1,378 @@ +/* + * include/linux/phy.h + * + * Framework and drivers for configuring and reading different PHYs + * Based on code in sungem_phy.c and gianfar_phy.c + * + * Author: Andy Fleming + * + * Copyright (c) 2004 Freescale Semiconductor, 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 __PHY_H +#define __PHY_H + +#include +#include + +#define PHY_BASIC_FEATURES (SUPPORTED_10baseT_Half | \ + SUPPORTED_10baseT_Full | \ + SUPPORTED_100baseT_Half | \ + SUPPORTED_100baseT_Full | \ + SUPPORTED_Autoneg | \ + SUPPORTED_TP | \ + SUPPORTED_MII) + +#define PHY_GBIT_FEATURES (PHY_BASIC_FEATURES | \ + SUPPORTED_1000baseT_Half | \ + SUPPORTED_1000baseT_Full) + +/* Set phydev->irq to PHY_POLL if interrupts are not supported, + * or not desired for this PHY. Set to PHY_IGNORE_INTERRUPT if + * the attached driver handles the interrupt + */ +#define PHY_POLL -1 +#define PHY_IGNORE_INTERRUPT -2 + +#define PHY_HAS_INTERRUPT 0x00000001 +#define PHY_HAS_MAGICANEG 0x00000002 + +#define MII_BUS_MAX 4 + + +#define PHY_INIT_TIMEOUT 100000 +#define PHY_STATE_TIME 1 +#define PHY_FORCE_TIMEOUT 10 +#define PHY_AN_TIMEOUT 10 + +#define PHY_MAX_ADDR 32 + +/* The Bus class for PHYs. Devices which provide access to + * PHYs should register using this structure */ +struct mii_bus { + const char *name; + int id; + void *priv; + int (*read)(struct mii_bus *bus, int phy_id, int regnum); + int (*write)(struct mii_bus *bus, int phy_id, int regnum, u16 val); + int (*reset)(struct mii_bus *bus); + + /* A lock to ensure that only one thing can read/write + * the MDIO bus at a time */ + spinlock_t mdio_lock; + + struct device *dev; + + /* list of all PHYs on bus */ + struct phy_device *phy_map[PHY_MAX_ADDR]; + + /* Pointer to an array of interrupts, each PHY's + * interrupt at the index matching its address */ + int *irq; +}; + +#define PHY_INTERRUPT_DISABLED 0x0 +#define PHY_INTERRUPT_ENABLED 0x80000000 + +/* PHY state machine states: + * + * DOWN: PHY device and driver are not ready for anything. probe + * should be called if and only if the PHY is in this state, + * given that the PHY device exists. + * - PHY driver probe function will, depending on the PHY, set + * the state to STARTING or READY + * + * STARTING: PHY device is coming up, and the ethernet driver is + * not ready. PHY drivers may set this in the probe function. + * If they do, they are responsible for making sure the state is + * eventually set to indicate whether the PHY is UP or READY, + * depending on the state when the PHY is done starting up. + * - PHY driver will set the state to READY + * - start will set the state to PENDING + * + * READY: PHY is ready to send and receive packets, but the + * controller is not. By default, PHYs which do not implement + * probe will be set to this state by phy_probe(). If the PHY + * driver knows the PHY is ready, and the PHY state is STARTING, + * then it sets this STATE. + * - start will set the state to UP + * + * PENDING: PHY device is coming up, but the ethernet driver is + * ready. phy_start will set this state if the PHY state is + * STARTING. + * - PHY driver will set the state to UP when the PHY is ready + * + * UP: The PHY and attached device are ready to do work. + * Interrupts should be started here. + * - timer moves to AN + * + * AN: The PHY is currently negotiating the link state. Link is + * therefore down for now. phy_timer will set this state when it + * detects the state is UP. config_aneg will set this state + * whenever called with phydev->autoneg set to AUTONEG_ENABLE. + * - If autonegotiation finishes, but there's no link, it sets + * the state to NOLINK. + * - If aneg finishes with link, it sets the state to RUNNING, + * and calls adjust_link + * - If autonegotiation did not finish after an arbitrary amount + * of time, autonegotiation should be tried again if the PHY + * supports "magic" autonegotiation (back to AN) + * - If it didn't finish, and no magic_aneg, move to FORCING. + * + * NOLINK: PHY is up, but not currently plugged in. + * - If the timer notes that the link comes back, we move to RUNNING + * - config_aneg moves to AN + * - phy_stop moves to HALTED + * + * FORCING: PHY is being configured with forced settings + * - if link is up, move to RUNNING + * - If link is down, we drop to the next highest setting, and + * retry (FORCING) after a timeout + * - phy_stop moves to HALTED + * + * RUNNING: PHY is currently up, running, and possibly sending + * and/or receiving packets + * - timer will set CHANGELINK if we're polling (this ensures the + * link state is polled every other cycle of this state machine, + * which makes it every other second) + * - irq will set CHANGELINK + * - config_aneg will set AN + * - phy_stop moves to HALTED + * + * CHANGELINK: PHY experienced a change in link state + * - timer moves to RUNNING if link + * - timer moves to NOLINK if the link is down + * - phy_stop moves to HALTED + * + * HALTED: PHY is up, but no polling or interrupts are done. Or + * PHY is in an error state. + * + * - phy_start moves to RESUMING + * + * RESUMING: PHY was halted, but now wants to run again. + * - If we are forcing, or aneg is done, timer moves to RUNNING + * - If aneg is not done, timer moves to AN + * - phy_stop moves to HALTED + */ +enum phy_state { + PHY_DOWN=0, + PHY_STARTING, + PHY_READY, + PHY_PENDING, + PHY_UP, + PHY_AN, + PHY_RUNNING, + PHY_NOLINK, + PHY_FORCING, + PHY_CHANGELINK, + PHY_HALTED, + PHY_RESUMING +}; + +/* phy_device: An instance of a PHY + * + * drv: Pointer to the driver for this PHY instance + * bus: Pointer to the bus this PHY is on + * dev: driver model device structure for this PHY + * phy_id: UID for this device found during discovery + * state: state of the PHY for management purposes + * dev_flags: Device-specific flags used by the PHY driver. + * addr: Bus address of PHY + * link_timeout: The number of timer firings to wait before the + * giving up on the current attempt at acquiring a link + * irq: IRQ number of the PHY's interrupt (-1 if none) + * phy_timer: The timer for handling the state machine + * phy_queue: A work_queue for the interrupt + * attached_dev: The attached enet driver's device instance ptr + * adjust_link: Callback for the enet controller to respond to + * changes in the link state. + * adjust_state: Callback for the enet driver to respond to + * changes in the state machine. + * + * speed, duplex, pause, supported, advertising, and + * autoneg are used like in mii_if_info + * + * interrupts currently only supports enabled or disabled, + * but could be changed in the future to support enabling + * and disabling specific interrupts + * + * Contains some infrastructure for polling and interrupt + * handling, as well as handling shifts in PHY hardware state + */ +struct phy_device { + /* Information about the PHY type */ + /* And management functions */ + struct phy_driver *drv; + + struct mii_bus *bus; + + struct device dev; + + u32 phy_id; + + enum phy_state state; + + u32 dev_flags; + + /* Bus address of the PHY (0-32) */ + int addr; + + /* forced speed & duplex (no autoneg) + * partner speed & duplex & pause (autoneg) + */ + int speed; + int duplex; + int pause; + int asym_pause; + + /* The most recently read link state */ + int link; + + /* Enabled Interrupts */ + u32 interrupts; + + /* Union of PHY and Attached devices' supported modes */ + /* See mii.h for more info */ + u32 supported; + u32 advertising; + + int autoneg; + + int link_timeout; + + /* Interrupt number for this PHY + * -1 means no interrupt */ + int irq; + + /* private data pointer */ + /* For use by PHYs to maintain extra state */ + void *priv; + + /* Interrupt and Polling infrastructure */ + struct work_struct phy_queue; + struct timer_list phy_timer; + + spinlock_t lock; + + struct net_device *attached_dev; + + void (*adjust_link)(struct net_device *dev); + + void (*adjust_state)(struct net_device *dev); +}; +#define to_phy_device(d) container_of(d, struct phy_device, dev) + +/* struct phy_driver: Driver structure for a particular PHY type + * + * phy_id: The result of reading the UID registers of this PHY + * type, and ANDing them with the phy_id_mask. This driver + * only works for PHYs with IDs which match this field + * name: The friendly name of this PHY type + * phy_id_mask: Defines the important bits of the phy_id + * features: A list of features (speed, duplex, etc) supported + * by this PHY + * flags: A bitfield defining certain other features this PHY + * supports (like interrupts) + * + * The drivers must implement config_aneg and read_status. All + * other functions are optional. Note that none of these + * functions should be called from interrupt time. The goal is + * for the bus read/write functions to be able to block when the + * bus transaction is happening, and be freed up by an interrupt + * (The MPC85xx has this ability, though it is not currently + * supported in the driver). + */ +struct phy_driver { + u32 phy_id; + char *name; + unsigned int phy_id_mask; + u32 features; + u32 flags; + + /* Called to initialize the PHY, + * including after a reset */ + int (*config_init)(struct phy_device *phydev); + + /* Called during discovery. Used to set + * up device-specific structures, if any */ + int (*probe)(struct phy_device *phydev); + + /* PHY Power Management */ + int (*suspend)(struct phy_device *phydev); + int (*resume)(struct phy_device *phydev); + + /* Configures the advertisement and resets + * autonegotiation if phydev->autoneg is on, + * forces the speed to the current settings in phydev + * if phydev->autoneg is off */ + int (*config_aneg)(struct phy_device *phydev); + + /* Determines the negotiated speed and duplex */ + int (*read_status)(struct phy_device *phydev); + + /* Clears any pending interrupts */ + int (*ack_interrupt)(struct phy_device *phydev); + + /* Enables or disables interrupts */ + int (*config_intr)(struct phy_device *phydev); + + /* Clears up any memory if needed */ + void (*remove)(struct phy_device *phydev); + + struct device_driver driver; +}; +#define to_phy_driver(d) container_of(d, struct phy_driver, driver) + +int phy_read(struct phy_device *phydev, u16 regnum); +int phy_write(struct phy_device *phydev, u16 regnum, u16 val); +struct phy_device* get_phy_device(struct mii_bus *bus, int addr); +int phy_clear_interrupt(struct phy_device *phydev); +int phy_config_interrupt(struct phy_device *phydev, u32 interrupts); +struct phy_device * phy_attach(struct net_device *dev, + const char *phy_id, u32 flags); +struct phy_device * phy_connect(struct net_device *dev, const char *phy_id, + void (*handler)(struct net_device *), u32 flags); +void phy_disconnect(struct phy_device *phydev); +void phy_detach(struct phy_device *phydev); +void phy_start(struct phy_device *phydev); +void phy_stop(struct phy_device *phydev); +int phy_start_aneg(struct phy_device *phydev); + +int mdiobus_register(struct mii_bus *bus); +void mdiobus_unregister(struct mii_bus *bus); +void phy_sanitize_settings(struct phy_device *phydev); +int phy_stop_interrupts(struct phy_device *phydev); + +static inline int phy_read_status(struct phy_device *phydev) { + return phydev->drv->read_status(phydev); +} + +int genphy_config_advert(struct phy_device *phydev); +int genphy_setup_forced(struct phy_device *phydev); +int genphy_restart_aneg(struct phy_device *phydev); +int genphy_config_aneg(struct phy_device *phydev); +int genphy_update_link(struct phy_device *phydev); +int genphy_read_status(struct phy_device *phydev); +void phy_driver_unregister(struct phy_driver *drv); +int phy_driver_register(struct phy_driver *new_driver); +void phy_prepare_link(struct phy_device *phydev, + void (*adjust_link)(struct net_device *)); +void phy_start_machine(struct phy_device *phydev, + void (*handler)(struct net_device *)); +void phy_stop_machine(struct phy_device *phydev); +int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); +int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd); +int phy_mii_ioctl(struct phy_device *phydev, + struct mii_ioctl_data *mii_data, int cmd); +int phy_start_interrupts(struct phy_device *phydev); +void phy_print_status(struct phy_device *phydev); + +extern struct bus_type mdio_bus_type; +extern struct phy_driver genphy_driver; +#endif /* __PHY_H */ -- cgit v1.2.3 From 541134cfe7af179f45458b68421ee1da7bab9cba Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Sun, 3 Jul 2005 13:44:39 +0100 Subject: [PATCH] sata_nv: Support MCP51/MCP55 device IDs This is a multi-part message in MIME format. Signed-off-by: Jeff Garzik --- 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 bc4cc10fabe9..639291fe8ac0 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1249,6 +1249,7 @@ #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_SATA 0x0266 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_SATA2 0x0267 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_IDE 0x036E +#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_SATA 0x036F #define PCI_DEVICE_ID_NVIDIA_NVENET_12 0x0268 #define PCI_DEVICE_ID_NVIDIA_NVENET_13 0x0269 #define PCI_DEVICE_ID_NVIDIA_MCP51_AUDIO 0x026B -- cgit v1.2.3 From 8a60a07129fad60bba779a2a4038c7518b167fc7 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Sun, 31 Jul 2005 13:13:24 -0400 Subject: libata: trim trailing whitespace. Also, fixup a tabs-to-spaces block of code in ata_piix. --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 6cd9ba63563b..85b0aaee0ef8 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -644,7 +644,7 @@ static inline void scr_write(struct ata_port *ap, unsigned int reg, u32 val) ap->ops->scr_write(ap, reg, val); } -static inline void scr_write_flush(struct ata_port *ap, unsigned int reg, +static inline void scr_write_flush(struct ata_port *ap, unsigned int reg, u32 val) { ap->ops->scr_write(ap, reg, val); -- cgit v1.2.3 From 1f3a6a15771ed70d3b2581663dcc6b9bc134baa5 Mon Sep 17 00:00:00 2001 From: Kenji Kaneshige Date: Thu, 28 Jul 2005 14:42:00 -0400 Subject: [ACPI] acpi_register_gsi() can return error Current acpi_register_gsi() function has no way to indicate errors to its callers even though acpi_register_gsi() can fail to register gsi because of some reasons (out of memory, lack of interrupt vectors, incorrect BIOS, and so on). As a result, caller of acpi_register_gsi() cannot handle the case that acpi_register_gsi() fails. I think failure of acpi_register_gsi() should be handled properly. This series of patches changes acpi_register_gsi() to return negative value on error, and also changes callers of acpi_register_gsi() to handle failure of acpi_register_gsi(). This patch changes the type of return value of acpi_register_gsi() from "unsigned int" to "int" to indicate an error. If acpi_register_gsi() fails to register gsi, it returns negative value. Signed-off-by: Kenji Kaneshige Signed-off-by: Andrew Morton Signed-off-by: Len Brown --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index ca0cd240cee0..9378bcde73a4 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -432,7 +432,7 @@ static inline int acpi_boot_table_init(void) #endif /*!CONFIG_ACPI_BOOT*/ -unsigned int acpi_register_gsi (u32 gsi, int edge_level, int active_high_low); +int acpi_register_gsi (u32 gsi, int edge_level, int active_high_low); int acpi_gsi_to_irq (u32 gsi, unsigned int *irq); /* -- cgit v1.2.3 From 53de49f52e305e96143375d1741f15acff7bf34b Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sat, 30 Jul 2005 04:18:00 -0400 Subject: [ACPI] CONFIG_ACPI=n build fix Signed-off-by: Andrew Morton Signed-off-by: Len Brown --- include/linux/acpi.h | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 9378bcde73a4..bf96ae9d93a3 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -420,16 +420,6 @@ extern int sbf_port ; #define acpi_mp_config 0 -static inline int acpi_boot_init(void) -{ - return 0; -} - -static inline int acpi_boot_table_init(void) -{ - return 0; -} - #endif /*!CONFIG_ACPI_BOOT*/ int acpi_register_gsi (u32 gsi, int edge_level, int active_high_low); @@ -536,5 +526,17 @@ static inline int acpi_get_pxm(acpi_handle handle) extern int pnpacpi_disabled; +#else /* CONFIG_ACPI */ + +static inline int acpi_boot_init(void) +{ + return 0; +} + +static inline int acpi_boot_table_init(void) +{ + return 0; +} + #endif /* CONFIG_ACPI */ #endif /*_LINUX_ACPI_H*/ -- cgit v1.2.3 From 67c4f3fa25502ce7ed82fb0307e09cf36f1f81da Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Thu, 11 Aug 2005 02:07:25 -0400 Subject: Fix numerous minor problems with new phy subsystem. Includes fixes for problems noted by Adrian Bunk, Andrew Morton, and one other person lost in the annals of history (and email folders). --- include/linux/phy.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 3404804dc22d..72cb67b66e0c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -374,5 +374,4 @@ int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); extern struct bus_type mdio_bus_type; -extern struct phy_driver genphy_driver; #endif /* __PHY_H */ -- cgit v1.2.3 From 2bf69b5fe90b3246ab50064c5a690a363e8c53e2 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Thu, 11 Aug 2005 02:47:54 -0400 Subject: phy subsystem: more cleanups - unexport symbols never used outside of home module - remove dead code - remove CONFIG_PHYCONTROL, make it unconditionally enabled --- include/linux/phy.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 72cb67b66e0c..4f2b5effc16b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -334,26 +334,11 @@ int phy_write(struct phy_device *phydev, u16 regnum, u16 val); struct phy_device* get_phy_device(struct mii_bus *bus, int addr); int phy_clear_interrupt(struct phy_device *phydev); int phy_config_interrupt(struct phy_device *phydev, u32 interrupts); -struct phy_device * phy_attach(struct net_device *dev, - const char *phy_id, u32 flags); -struct phy_device * phy_connect(struct net_device *dev, const char *phy_id, - void (*handler)(struct net_device *), u32 flags); -void phy_disconnect(struct phy_device *phydev); -void phy_detach(struct phy_device *phydev); -void phy_start(struct phy_device *phydev); -void phy_stop(struct phy_device *phydev); -int phy_start_aneg(struct phy_device *phydev); - -int mdiobus_register(struct mii_bus *bus); -void mdiobus_unregister(struct mii_bus *bus); -void phy_sanitize_settings(struct phy_device *phydev); -int phy_stop_interrupts(struct phy_device *phydev); static inline int phy_read_status(struct phy_device *phydev) { return phydev->drv->read_status(phydev); } -int genphy_config_advert(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_config_aneg(struct phy_device *phydev); @@ -370,8 +355,6 @@ int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct mii_ioctl_data *mii_data, int cmd); -int phy_start_interrupts(struct phy_device *phydev); -void phy_print_status(struct phy_device *phydev); extern struct bus_type mdio_bus_type; #endif /* __PHY_H */ -- cgit v1.2.3 From 972dcafb6d743a6c7611a2e4681ed814e30d6230 Mon Sep 17 00:00:00 2001 From: Douglas Gilbert Date: Thu, 11 Aug 2005 03:35:53 -0400 Subject: [libata scsi] add START STOP UNIT translation --- include/linux/ata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index ca5fcadf9981..9d25e9886d60 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -108,6 +108,8 @@ enum { /* ATA device commands */ ATA_CMD_CHK_POWER = 0xE5, /* check power mode */ + ATA_CMD_STANDBY = 0xE2, /* place in standby power mode */ + ATA_CMD_IDLE = 0xE3, /* place in idle power mode */ ATA_CMD_EDD = 0x90, /* execute device diagnostic */ ATA_CMD_FLUSH = 0xE7, ATA_CMD_FLUSH_EXT = 0xEA, -- cgit v1.2.3 From d0a7e574007fd547d72ec693bfa35778623d0738 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Sun, 14 Aug 2005 17:09:01 -0500 Subject: [SCSI] correct transport class abstraction to work outside SCSI I recently tried to construct a totally generic transport class and found there were certain features missing from the current abstract transport class. Most notable is that you have to hang the data on the class_device but most of the API is framed in terms of the generic device, not the class_device. These changes are two fold - Provide the class_device to all of the setup and configure APIs - Provide and extra API to take the device and the attribute class and return the corresponding class_device Signed-off-by: James Bottomley --- include/linux/attribute_container.h | 9 +++------ include/linux/transport_class.h | 11 ++++++++--- 2 files changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/attribute_container.h b/include/linux/attribute_container.h index af1010b6dab7..f54b05b052b3 100644 --- a/include/linux/attribute_container.h +++ b/include/linux/attribute_container.h @@ -11,10 +11,12 @@ #include #include +#include struct attribute_container { struct list_head node; struct list_head containers; + spinlock_t containers_lock; struct class *class; struct class_device_attribute **attrs; int (*match)(struct attribute_container *, struct device *); @@ -62,12 +64,7 @@ int attribute_container_add_class_device_adapter(struct attribute_container *con struct class_device *classdev); void attribute_container_remove_attrs(struct class_device *classdev); void attribute_container_class_device_del(struct class_device *classdev); - - - - - - +struct class_device *attribute_container_find_class_device(struct attribute_container *, struct device *); struct class_device_attribute **attribute_container_classdev_to_attrs(const struct class_device *classdev); #endif diff --git a/include/linux/transport_class.h b/include/linux/transport_class.h index 87d98d1faefb..1d6cc22e5f42 100644 --- a/include/linux/transport_class.h +++ b/include/linux/transport_class.h @@ -12,11 +12,16 @@ #include #include +struct transport_container; + struct transport_class { struct class class; - int (*setup)(struct device *); - int (*configure)(struct device *); - int (*remove)(struct device *); + int (*setup)(struct transport_container *, struct device *, + struct class_device *); + int (*configure)(struct transport_container *, struct device *, + struct class_device *); + int (*remove)(struct transport_container *, struct device *, + struct class_device *); }; #define DECLARE_TRANSPORT_CLASS(cls, nm, su, rm, cfg) \ -- cgit v1.2.3 From 89204c40a03346cd951e698d854105db4cfedc28 Mon Sep 17 00:00:00 2001 From: John McCutchan Date: Mon, 15 Aug 2005 12:13:28 -0400 Subject: [PATCH] inotify: add MOVE_SELF event This adds a MOVE_SELF event to inotify. It is sent whenever the inode you are watching is moved. We need this event so that we can catch something like this: - app1: watch /etc/mtab - app2: cp /etc/mtab /tmp/mtab-work mv /etc/mtab /etc/mtab~ mv /tmp/mtab-work /etc/mtab app1 still thinks it's watching /etc/mtab but it's actually watching /etc/mtab~. Signed-off-by: John McCutchan Signed-off-by: Robert Love Signed-off-by: Linus Torvalds --- include/linux/fsnotify.h | 6 +++++- include/linux/inotify.h | 4 +++- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 602c305c8585..03b8e7932b83 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -21,7 +21,7 @@ */ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, const char *old_name, const char *new_name, - int isdir, struct inode *target) + int isdir, struct inode *target, struct inode *source) { u32 cookie = inotify_get_cookie(); @@ -41,6 +41,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, inotify_inode_queue_event(target, IN_DELETE_SELF, 0, NULL); inotify_inode_is_dead(target); } + + if (source) { + inotify_inode_queue_event(source, IN_MOVE_SELF, 0, NULL); + } } /* diff --git a/include/linux/inotify.h b/include/linux/inotify.h index a40c2bf0408e..93bb3afe646b 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -35,6 +35,7 @@ struct inotify_event { #define IN_CREATE 0x00000100 /* Subfile was created */ #define IN_DELETE 0x00000200 /* Subfile was deleted */ #define IN_DELETE_SELF 0x00000400 /* Self was deleted */ +#define IN_MOVE_SELF 0x00000800 /* Self was moved */ /* the following are legal events. they are sent as needed to any watch */ #define IN_UNMOUNT 0x00002000 /* Backing fs was unmounted */ @@ -56,7 +57,8 @@ struct inotify_event { */ #define IN_ALL_EVENTS (IN_ACCESS | IN_MODIFY | IN_ATTRIB | IN_CLOSE_WRITE | \ IN_CLOSE_NOWRITE | IN_OPEN | IN_MOVED_FROM | \ - IN_MOVED_TO | IN_DELETE | IN_CREATE | IN_DELETE_SELF) + IN_MOVED_TO | IN_DELETE | IN_CREATE | IN_DELETE_SELF | \ + IN_MOVE_SELF) #ifdef __KERNEL__ -- cgit v1.2.3 From 58fcb8df0bf663bb6b8f46cd3010bfe8d13d97cf Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 10 Aug 2005 18:15:12 -0400 Subject: [PATCH] NFS: Ensure ACL xdr code doesn't overflow. Signed-off-by: Trond Myklebust Signed-off-by: Linus Torvalds --- include/linux/sunrpc/xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 34ec3e8d99b3..23448d0fb5bc 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -177,6 +177,7 @@ typedef int (*xdr_xcode_elem_t)(struct xdr_array2_desc *desc, void *elem); struct xdr_array2_desc { unsigned int elem_size; unsigned int array_len; + unsigned int array_maxlen; xdr_xcode_elem_t xcode; }; -- cgit v1.2.3 From 65e4308d2500e7daf60c3dccc202c61ffb066c63 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 16 Aug 2005 11:49:44 -0400 Subject: [PATCH] NFS: Ensure we always update inode->i_mode when doing O_EXCL creates When the client performs an exclusive create and opens the file for writing, a Netapp filer will first create the file using the mode 01777. It does this since an NFSv3/v4 exclusive create cannot immediately set the mode bits. The 01777 mode then gets put into the inode->i_mode. After the file creation is successful, we then do a setattr to change the mode to the correct value (as per the NFS spec). The problem is that nfs_refresh_inode() no longer updates inode->i_mode, so the latter retains the 01777 mode. A bit later, the VFS notices this, and calls remove_suid(). This of course now resets the file mode to inode->i_mode & 0777. Hey presto, the file mode on the server is now magically changed to 0777. Duh... Fixes http://bugzilla.linux-nfs.org/show_bug.cgi?id=32 Signed-off-by: Trond Myklebust Signed-off-by: Linus Torvalds --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8ea249110fb0..7d78a783c64a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -292,6 +292,7 @@ extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern void nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_setattr(struct dentry *, struct iattr *); +extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr); extern void nfs_begin_attr_update(struct inode *); extern void nfs_end_attr_update(struct inode *); extern void nfs_begin_data_update(struct inode *); -- cgit v1.2.3 From 4602b88d9743b5f20655de8078fb42e9fd25581f Mon Sep 17 00:00:00 2001 From: Kristen Accardi Date: Tue, 16 Aug 2005 15:15:58 -0700 Subject: [PATCH] PCI: 6700/6702PXH quirk On the 6700/6702 PXH part, a MSI may get corrupted if an ACPI hotplug driver and SHPC driver in MSI mode are used together. This patch will prevent MSI from being enabled for the SHPC as part of an early pci quirk, as well as on any pci device which sets the no_msi bit. Signed-off-by: Kristen Carlson Accardi Signed-off-by: Greg Kroah-Hartman Signed-off-by: Linus Torvalds --- include/linux/pci.h | 3 ++- include/linux/pci_ids.h | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 8621cf42b46f..bc4c40000c0d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -556,7 +556,8 @@ struct pci_dev { /* keep track of device state */ unsigned int is_enabled:1; /* pci_enable_device has been called */ unsigned int is_busmaster:1; /* device is busmaster */ - + unsigned int no_msi:1; /* device may not use msi */ + u32 saved_config_space[16]; /* config space saved at suspend time */ struct bin_attribute *rom_attr; /* attribute descriptor for sysfs ROM entry */ int rom_attr_enabled; /* has display of the rom attribute been enabled? */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index bc4cc10fabe9..51e61e96051c 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2281,6 +2281,11 @@ #define PCI_VENDOR_ID_INTEL 0x8086 #define PCI_DEVICE_ID_INTEL_EESSC 0x0008 #define PCI_DEVICE_ID_INTEL_21145 0x0039 +#define PCI_DEVICE_ID_INTEL_PXHD_0 0x0320 +#define PCI_DEVICE_ID_INTEL_PXHD_1 0x0321 +#define PCI_DEVICE_ID_INTEL_PXH_0 0x0329 +#define PCI_DEVICE_ID_INTEL_PXH_1 0x032A +#define PCI_DEVICE_ID_INTEL_PXHV 0x032C #define PCI_DEVICE_ID_INTEL_82375 0x0482 #define PCI_DEVICE_ID_INTEL_82424 0x0483 #define PCI_DEVICE_ID_INTEL_82378 0x0484 -- cgit v1.2.3 From 5529680981807b44abf3be30fb6d612ff04f68ff Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 18 Aug 2005 11:24:09 -0700 Subject: [PATCH] NFS: split nfsi->flags into two fields Certain bits in nfsi->flags can be manipulated with atomic bitops, and some are better manipulated via logical bitmask operations. This patch splits the flags field into two. The next patch introduces atomic bitops for one of the fields. Test plan: Millions of fsx ops on SMP clients. Signed-off-by: Chuck Lever Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfs_fs.h | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 7d78a783c64a..229a1755842a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -113,6 +113,7 @@ struct nfs_inode { * Various flags */ unsigned int flags; + unsigned long cache_validity; /* * read_cache_jiffies is when we started read-caching this inode, @@ -188,17 +189,21 @@ struct nfs_inode { }; /* - * Legal inode flag values + * Cache validity bit flags */ -#define NFS_INO_STALE 0x0001 /* possible stale inode */ -#define NFS_INO_ADVISE_RDPLUS 0x0002 /* advise readdirplus */ -#define NFS_INO_REVALIDATING 0x0004 /* revalidating attrs */ -#define NFS_INO_INVALID_ATTR 0x0008 /* cached attrs are invalid */ -#define NFS_INO_INVALID_DATA 0x0010 /* cached data is invalid */ -#define NFS_INO_INVALID_ATIME 0x0020 /* cached atime is invalid */ -#define NFS_INO_INVALID_ACCESS 0x0040 /* cached access cred invalid */ -#define NFS_INO_INVALID_ACL 0x0080 /* cached acls are invalid */ -#define NFS_INO_REVAL_PAGECACHE 0x1000 /* must revalidate pagecache */ +#define NFS_INO_INVALID_ATTR 0x0001 /* cached attrs are invalid */ +#define NFS_INO_INVALID_DATA 0x0002 /* cached data is invalid */ +#define NFS_INO_INVALID_ATIME 0x0004 /* cached atime is invalid */ +#define NFS_INO_INVALID_ACCESS 0x0008 /* cached access cred invalid */ +#define NFS_INO_INVALID_ACL 0x0010 /* cached acls are invalid */ +#define NFS_INO_REVAL_PAGECACHE 0x0020 /* must revalidate pagecache */ + +/* + * Legal values of flags field + */ +#define NFS_INO_REVALIDATING 0x0001 /* revalidating attrs */ +#define NFS_INO_ADVISE_RDPLUS 0x0002 /* advise readdirplus */ +#define NFS_INO_STALE 0x0004 /* possible stale inode */ static inline struct nfs_inode *NFS_I(struct inode *inode) { @@ -237,7 +242,7 @@ static inline int nfs_caches_unstable(struct inode *inode) static inline void NFS_CACHEINV(struct inode *inode) { if (!nfs_caches_unstable(inode)) - NFS_FLAGS(inode) |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS; + NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS; } static inline int nfs_server_capable(struct inode *inode, int cap) -- cgit v1.2.3 From 412d582ec1dd59aab2353f8cb7e74f2c79cd20b9 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 18 Aug 2005 11:24:11 -0700 Subject: [PATCH] NFS: use atomic bitops to manipulate flags in nfsi->flags Introduce atomic bitops to manipulate the bits in the nfs_inode structure's "flags" field. Using bitops means we can use a generic wait_on_bit call instead of an ad hoc locking scheme in fs/nfs/inode.c, so we can remove the "nfs_i_wait" field from nfs_inode at the same time. The other new flags field will continue to use bitmask and logic AND and OR. This permits several flags to be set at the same time efficiently. The following patch adds a spin lock to protect these flags, and this spin lock will later cover other fields in the nfs_inode structure, amortizing the cost of using this type of serialization. Test plan: Millions of fsx ops on SMP clients. Signed-off-by: Chuck Lever Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfs_fs.h | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 229a1755842a..deef9567788a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -112,8 +112,8 @@ struct nfs_inode { /* * Various flags */ - unsigned int flags; - unsigned long cache_validity; + unsigned long flags; /* atomic bit ops */ + unsigned long cache_validity; /* bit mask */ /* * read_cache_jiffies is when we started read-caching this inode, @@ -175,8 +175,6 @@ struct nfs_inode { /* Open contexts for shared mmap writes */ struct list_head open_files; - wait_queue_head_t nfs_i_wait; - #ifdef CONFIG_NFS_V4 struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ @@ -199,11 +197,11 @@ struct nfs_inode { #define NFS_INO_REVAL_PAGECACHE 0x0020 /* must revalidate pagecache */ /* - * Legal values of flags field + * Bit offsets in flags field */ -#define NFS_INO_REVALIDATING 0x0001 /* revalidating attrs */ -#define NFS_INO_ADVISE_RDPLUS 0x0002 /* advise readdirplus */ -#define NFS_INO_STALE 0x0004 /* possible stale inode */ +#define NFS_INO_REVALIDATING (0) /* revalidating attrs */ +#define NFS_INO_ADVISE_RDPLUS (1) /* advise readdirplus */ +#define NFS_INO_STALE (2) /* possible stale inode */ static inline struct nfs_inode *NFS_I(struct inode *inode) { @@ -229,8 +227,7 @@ static inline struct nfs_inode *NFS_I(struct inode *inode) #define NFS_ATTRTIMEO_UPDATE(inode) (NFS_I(inode)->attrtimeo_timestamp) #define NFS_FLAGS(inode) (NFS_I(inode)->flags) -#define NFS_REVALIDATING(inode) (NFS_FLAGS(inode) & NFS_INO_REVALIDATING) -#define NFS_STALE(inode) (NFS_FLAGS(inode) & NFS_INO_STALE) +#define NFS_STALE(inode) (test_bit(NFS_INO_STALE, &NFS_FLAGS(inode))) #define NFS_FILEID(inode) (NFS_I(inode)->fileid) @@ -252,7 +249,7 @@ static inline int nfs_server_capable(struct inode *inode, int cap) static inline int NFS_USE_READDIRPLUS(struct inode *inode) { - return NFS_FLAGS(inode) & NFS_INO_ADVISE_RDPLUS; + return test_bit(NFS_INO_ADVISE_RDPLUS, &NFS_FLAGS(inode)); } /** -- cgit v1.2.3 From dc59250c6ebed099a9bc0a11298e2281dd896657 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 18 Aug 2005 11:24:12 -0700 Subject: [PATCH] NFS: Introduce the use of inode->i_lock to protect fields in nfsi Down the road we want to eliminate the use of the global kernel lock entirely from the NFS client. To do this, we need to protect the fields in the nfs_inode structure adequately. Start by serializing updates to the "cache_validity" field. Note this change addresses an SMP hang found by njw@osdl.org, where processes deadlock because nfs_end_data_update and nfs_revalidate_mapping update the "cache_validity" field without proper serialization. Test plan: Millions of fsx ops on SMP clients. Run Nick Wilson's breaknfs program on large SMP clients. Signed-off-by: Chuck Lever Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfs_fs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index deef9567788a..9a6047ff1b25 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -238,8 +238,11 @@ static inline int nfs_caches_unstable(struct inode *inode) static inline void NFS_CACHEINV(struct inode *inode) { - if (!nfs_caches_unstable(inode)) + if (!nfs_caches_unstable(inode)) { + spin_lock(&inode->i_lock); NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS; + spin_unlock(&inode->i_lock); + } } static inline int nfs_server_capable(struct inode *inode, int cap) -- cgit v1.2.3 From b07e5eccaf512ae3209beae5cd2e3a27c92c300b Mon Sep 17 00:00:00 2001 From: Grant Coady Date: Thu, 18 Aug 2005 22:19:55 +0200 Subject: [PATCH] ide: fix PCI_DEVIEC_ID_APPLE_UNI_N_ATA spelling Signed-off-by: Grant Coady Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/pci_ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 51e61e96051c..953b4dc819ae 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -881,7 +881,7 @@ #define PCI_DEVICE_ID_APPLE_UNI_N_PCI15 0x002e #define PCI_DEVICE_ID_APPLE_UNI_N_FW2 0x0030 #define PCI_DEVICE_ID_APPLE_UNI_N_GMAC2 0x0032 -#define PCI_DEVIEC_ID_APPLE_UNI_N_ATA 0x0033 +#define PCI_DEVICE_ID_APPLE_UNI_N_ATA 0x0033 #define PCI_DEVICE_ID_APPLE_UNI_N_AGP2 0x0034 #define PCI_DEVICE_ID_APPLE_IPID_ATA100 0x003b #define PCI_DEVICE_ID_APPLE_KEYLARGO_I 0x003e -- cgit v1.2.3 From 2f09a7f4af131bf23c013ead89373deba1c7593c Mon Sep 17 00:00:00 2001 From: Matt Gillette Date: Thu, 18 Aug 2005 22:27:07 +0200 Subject: [PATCH] ide: add support for Netcell Revolution to pci-ide generic driver Adds support for Netcell Revolution to pci-ide generic driver by including it in the list of devices matched. Includes the Revolution in the list of simplex devices forced into DMA mode. Signed-off-by: Matt Gillette Cc: Bartlomiej Zolnierkiewicz Cc: Jeff Garzik Signed-off-by: Andrew Morton Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 953b4dc819ae..163036867ac7 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2184,6 +2184,9 @@ #define PCI_VENDOR_ID_SIBYTE 0x166d #define PCI_DEVICE_ID_BCM1250_HT 0x0002 +#define PCI_VENDOR_ID_NETCELL 0x169c +#define PCI_DEVICE_ID_REVOLUTION 0x0044 + #define PCI_VENDOR_ID_LINKSYS 0x1737 #define PCI_DEVICE_ID_LINKSYS_EG1032 0x1032 #define PCI_DEVICE_ID_LINKSYS_EG1064 0x1064 -- cgit v1.2.3 From 84f57fbc724e3b56dc87c37dddac89f82cf75ef6 Mon Sep 17 00:00:00 2001 From: Narendra Sankar Date: Thu, 18 Aug 2005 22:30:35 +0200 Subject: [PATCH] serverworks: add support for new southbridge IDE BCM5785 (HT1000) is a Opteron Southbridge from Serverworks/Broadcom that incorporates a single channel ATA100 IDE controller that is functionally identical to the Serverworks CSB6 IDE controller. This patch adds support for the new PCI device ID and also the support for this controller. Signed-off-by: Narendra Sankar Acked-by: Jeff Garzik Signed-off-by: Bartlomiej Zolnierkiewicz --- 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 163036867ac7..927ed487630d 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1580,6 +1580,7 @@ #define PCI_DEVICE_ID_SERVERWORKS_OSB4IDE 0x0211 #define PCI_DEVICE_ID_SERVERWORKS_CSB5IDE 0x0212 #define PCI_DEVICE_ID_SERVERWORKS_CSB6IDE 0x0213 +#define PCI_DEVICE_ID_SERVERWORKS_HT1000IDE 0x0214 #define PCI_DEVICE_ID_SERVERWORKS_CSB6IDE2 0x0217 #define PCI_DEVICE_ID_SERVERWORKS_OSB4USB 0x0220 #define PCI_DEVICE_ID_SERVERWORKS_CSB5USB PCI_DEVICE_ID_SERVERWORKS_OSB4USB -- cgit v1.2.3 From d366b6436386875b1310ce8f70e3f9dea4647bac Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 19 Aug 2005 09:40:08 +0100 Subject: [MMC] Add mmc_hostname() macro mmc_hostname() returns a pointer to the hostname for the mmc_host. Signed-off-by: Russell King --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index f90f674eb3b0..307862308596 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -97,6 +97,7 @@ extern void mmc_free_host(struct mmc_host *); #define mmc_priv(x) ((void *)((x) + 1)) #define mmc_dev(x) ((x)->dev) +#define mmc_hostname(x) ((x)->host_name) extern int mmc_suspend_host(struct mmc_host *, pm_message_t); extern int mmc_resume_host(struct mmc_host *); -- cgit v1.2.3 From 00b137cfda5276b3d2c87d44236fe4c5ee68b405 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 19 Aug 2005 09:41:24 +0100 Subject: [MMC] Add MMC class devices Create a mmc_host class to allow enumeration of MMC host controllers even though they have no card(s) inserted. Patch based on work by Pierre Ossman. Signed-off-by: Russell King --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 307862308596..a74a810a1302 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -63,6 +63,7 @@ struct device; struct mmc_host { struct device *dev; + struct class_device class_dev; struct mmc_host_ops *ops; unsigned int f_min; unsigned int f_max; -- cgit v1.2.3 From 1ad434d7cf5f490c71cfbbb2fb91076c01c8704e Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 19 Aug 2005 09:42:21 +0100 Subject: [MMC] Use class device name for mmc host name There's no point in having the host name duplicated between the mmc_host structure and the encapsulated class device structure. Signed-off-by: Russell King --- include/linux/mmc/host.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index a74a810a1302..113cc27865f0 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -68,7 +68,6 @@ struct mmc_host { unsigned int f_min; unsigned int f_max; u32 ocr_avail; - char host_name[8]; /* host specific block data */ unsigned int max_seg_size; /* see blk_queue_max_segment_size */ @@ -98,7 +97,7 @@ extern void mmc_free_host(struct mmc_host *); #define mmc_priv(x) ((void *)((x) + 1)) #define mmc_dev(x) ((x)->dev) -#define mmc_hostname(x) ((x)->host_name) +#define mmc_hostname(x) ((x)->class_dev.class_id) extern int mmc_suspend_host(struct mmc_host *, pm_message_t); extern int mmc_resume_host(struct mmc_host *); -- cgit v1.2.3 From dce773771834221817e2d359a7e07a618ba08807 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 19 Aug 2005 09:42:52 +0100 Subject: [MMC] Use an IDR for host name indicies Signed-off-by: Russell King --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 113cc27865f0..9a0893f3249e 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -64,6 +64,7 @@ struct device; struct mmc_host { struct device *dev; struct class_device class_dev; + int index; struct mmc_host_ops *ops; unsigned int f_min; unsigned int f_max; -- cgit v1.2.3 From cc314eef0128a807e50fa03baf2d0abc0647952c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 19 Aug 2005 18:02:56 -0700 Subject: Fix nasty ncpfs symlink handling bug. This bug could cause oopses and page state corruption, because ncpfs used the generic page-cache symlink handlign functions. But those functions only work if the page cache is guaranteed to be "stable", ie a page that was installed when the symlink walk was started has to still be installed in the page cache at the end of the walk. We could have fixed ncpfs to not use the generic helper routines, but it is in many ways much cleaner to instead improve on the symlink walking helper routines so that they don't require that absolute stability. We do this by allowing "follow_link()" to return a error-pointer as a cookie, which is fed back to the cleanup "put_link()" routine. This also simplifies NFS symlink handling. Signed-off-by: Linus Torvalds --- include/linux/fs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f9adf75fd9b4..67e6732d4fdc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -993,8 +993,8 @@ struct inode_operations { int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *); int (*readlink) (struct dentry *, char __user *,int); - int (*follow_link) (struct dentry *, struct nameidata *); - void (*put_link) (struct dentry *, struct nameidata *); + 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 (*setattr) (struct dentry *, struct iattr *); @@ -1602,8 +1602,8 @@ extern struct file_operations generic_ro_fops; extern int vfs_readlink(struct dentry *, char __user *, int, const char *); extern int vfs_follow_link(struct nameidata *, const char *); extern int page_readlink(struct dentry *, char __user *, int); -extern int page_follow_link_light(struct dentry *, struct nameidata *); -extern void page_put_link(struct dentry *, struct nameidata *); +extern void *page_follow_link_light(struct dentry *, struct nameidata *); +extern void page_put_link(struct dentry *, struct nameidata *, void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern struct inode_operations page_symlink_inode_operations; extern int generic_readlink(struct dentry *, char __user *, int); -- cgit v1.2.3 From c1389503710ef4b4e5d21bea284afde19e9619cf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Aug 2005 14:59:24 +0900 Subject: [PATCH] fix atapi_packet_task vs. intr race (take 2) Interrupts from devices sharing the same IRQ could cause ata_host_intr to finish commands being processed by atapi_packet_task if the commands are using ATA_PROT_ATAPI_NODATA or ATA_PROT_ATAPI_DMA protocol. This is because libata interrupt handler is unaware that interrupts are not expected during that period. This patch adds ATA_FLAG_NOINTR flag to tell the interrupt handler that we're not expecting interrupts. Note that once proper HSM is implemented for interrupt-driven PIO, this should be merged into it and this flag will be removed. ahci.c is a different kind of beast, so it's left alone. * The following drivers use ata_qc_issue_prot and ata_interrupt, so changes in libata core will do. ata_piix sata_sil sata_svw sata_via sata_sis sata_uli * The following drivers use ata_qc_issue_prot and custom intr handler. They need this change to work correctly. sata_nv sata_vsc * The following drivers use custom issue function and intr handler. Currently all custom issue functions don't support ATAPI, so this change is irrelevant, updated for consistency and to avoid later mistakes. sata_promise sata_qstor sata_sx4 Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 85b0aaee0ef8..724b7d1c18ea 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -113,6 +113,8 @@ enum { ATA_FLAG_MMIO = (1 << 6), /* use MMIO, not PIO */ ATA_FLAG_SATA_RESET = (1 << 7), /* use COMRESET */ ATA_FLAG_PIO_DMA = (1 << 8), /* PIO cmds via DMA */ + ATA_FLAG_NOINTR = (1 << 9), /* FIXME: Remove this once + * proper HSM is in place. */ ATA_QCFLAG_ACTIVE = (1 << 1), /* cmd not yet ack'd to scsi lyer */ ATA_QCFLAG_SG = (1 << 3), /* have s/g table? */ -- cgit v1.2.3 From 888ba6c62bc61a995d283977eb3a6cbafd6f4ac6 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 24 Aug 2005 12:07:20 -0400 Subject: [ACPI] delete CONFIG_ACPI_BOOT it has been a synonym for CONFIG_ACPI since 2.6.12 Signed-off-by: Len Brown --- include/linux/acpi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index fd48db320f5b..fa1ad1a60a09 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -41,7 +41,7 @@ #include -#ifdef CONFIG_ACPI_BOOT +#ifdef CONFIG_ACPI enum acpi_irq_model_id { ACPI_IRQ_MODEL_PIC = 0, @@ -429,11 +429,11 @@ extern int pci_mmcfg_config_num; extern int sbf_port ; -#else /*!CONFIG_ACPI_BOOT*/ +#else /* !CONFIG_ACPI */ #define acpi_mp_config 0 -#endif /*!CONFIG_ACPI_BOOT*/ +#endif /* !CONFIG_ACPI */ int acpi_register_gsi (u32 gsi, int edge_level, int active_high_low); int acpi_gsi_to_irq (u32 gsi, unsigned int *irq); -- cgit v1.2.3 From 8466361ad5233d4356a4601e16b66c25277920d1 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 24 Aug 2005 12:09:07 -0400 Subject: [ACPI] delete CONFIG_ACPI_INTERPRETER it is a synonym for CONFIG_ACPI Signed-off-by: Len Brown --- include/linux/acpi.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index fa1ad1a60a09..6882b32aa40f 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -488,20 +488,9 @@ extern int ec_write(u8 addr, u8 val); #endif /*CONFIG_ACPI_EC*/ -#ifdef CONFIG_ACPI_INTERPRETER - extern int acpi_blacklisted(void); extern void acpi_bios_year(char *s); -#else /*!CONFIG_ACPI_INTERPRETER*/ - -static inline int acpi_blacklisted(void) -{ - return 0; -} - -#endif /*!CONFIG_ACPI_INTERPRETER*/ - #define ACPI_CSTATE_LIMIT_DEFINED /* for driver builds */ #ifdef CONFIG_ACPI -- cgit v1.2.3 From 6153df7b2f4d27c8bde054db1b947369a6f64d83 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Thu, 25 Aug 2005 12:27:09 -0400 Subject: [ACPI] delete CONFIG_ACPI_PCI Delete the ability to build an ACPI kernel that does not include PCI support. When such a machine is created and it requires a tuned kernel, send a patch. http://bugzilla.kernel.org/show_bug.cgi?id=1364 Signed-off-by: Len Brown --- include/linux/acpi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 6882b32aa40f..026c3c011dc0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -445,7 +445,7 @@ int acpi_gsi_to_irq (u32 gsi, unsigned int *irq); */ void acpi_unregister_gsi (u32 gsi); -#ifdef CONFIG_ACPI_PCI +#ifdef CONFIG_ACPI struct acpi_prt_entry { struct list_head node; @@ -479,7 +479,7 @@ struct acpi_pci_driver { int acpi_pci_register_driver(struct acpi_pci_driver *driver); void acpi_pci_unregister_driver(struct acpi_pci_driver *driver); -#endif /*CONFIG_ACPI_PCI*/ +#endif /* CONFIG_ACPI */ #ifdef CONFIG_ACPI_EC -- cgit v1.2.3 From b73fc89f6d1f84326e5e897ad249d00a9f218fd7 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Fri, 26 Aug 2005 16:03:19 +0100 Subject: [PATCH] libata: regularize dma_start/stop arguments Needed for a few PATA drivers. Also fix up a wrong comment. Signed-off-by: Jeff Garzik --- include/linux/libata.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 724b7d1c18ea..33f3ab4eb827 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -365,7 +365,7 @@ struct ata_port_operations { void (*host_stop) (struct ata_host_set *host_set); - void (*bmdma_stop) (struct ata_port *ap); + void (*bmdma_stop) (struct ata_queued_cmd *qc); u8 (*bmdma_status) (struct ata_port *ap); }; @@ -424,9 +424,10 @@ extern unsigned int ata_dev_classify(struct ata_taskfile *tf); extern void ata_dev_id_string(u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern void ata_dev_config(struct ata_port *ap, unsigned int i); +extern void ata_dev_set_protocol(struct ata_device *dev); extern void ata_bmdma_setup (struct ata_queued_cmd *qc); extern void ata_bmdma_start (struct ata_queued_cmd *qc); -extern void ata_bmdma_stop(struct ata_port *ap); +extern void ata_bmdma_stop(struct ata_queued_cmd *qc); extern u8 ata_bmdma_status(struct ata_port *ap); extern void ata_bmdma_irq_clear(struct ata_port *ap); extern void ata_qc_complete(struct ata_queued_cmd *qc, u8 drv_stat); -- cgit v1.2.3 From d18d36b4edbb980c9de7fe00724c3ded5de1b7a7 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Sat, 27 Aug 2005 04:13:52 -0400 Subject: libata: fix a few alan-isms --- include/linux/libata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 33f3ab4eb827..7c09540c52bc 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -424,7 +424,6 @@ extern unsigned int ata_dev_classify(struct ata_taskfile *tf); extern void ata_dev_id_string(u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern void ata_dev_config(struct ata_port *ap, unsigned int i); -extern void ata_dev_set_protocol(struct ata_device *dev); extern void ata_bmdma_setup (struct ata_queued_cmd *qc); extern void ata_bmdma_start (struct ata_queued_cmd *qc); extern void ata_bmdma_stop(struct ata_queued_cmd *qc); -- cgit v1.2.3 From caca1779870b1bcc0fb07e48ebd2403901f356b8 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Tue, 16 Aug 2005 17:26:10 -0500 Subject: [SCSI] add missing attribute container function prototype attribute_container_classdev_to_container is an exported function of the attribute_container.c file. However, there's no prototype for it. Now I actually want to use it, so add one. Signed-off-by: James Bottomley --- include/linux/attribute_container.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/attribute_container.h b/include/linux/attribute_container.h index f54b05b052b3..ee83fe64a102 100644 --- a/include/linux/attribute_container.h +++ b/include/linux/attribute_container.h @@ -64,6 +64,7 @@ int attribute_container_add_class_device_adapter(struct attribute_container *con struct class_device *classdev); void attribute_container_remove_attrs(struct class_device *classdev); void attribute_container_class_device_del(struct class_device *classdev); +struct attribute_container *attribute_container_classdev_to_container(struct class_device *); struct class_device *attribute_container_find_class_device(struct attribute_container *, struct device *); struct class_device_attribute **attribute_container_classdev_to_attrs(const struct class_device *classdev); -- cgit v1.2.3 From af36d7f0df56de3e3e4bbfb15d0915097ecb8cab Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Sun, 28 Aug 2005 20:18:39 -0400 Subject: [libata] license change, other bits - changes license of all code from OSL+GPL to plain ole GPL - except for NVIDIA, who hasn't yet responded about sata_nv - copyright holders were already contacted privately - adds info in each driver about where hardware/protocol docs may be obtained - where I have made major contributions, updated copyright dates --- include/linux/ata.h | 43 ++++++++++++++++++++++++------------------- include/linux/libata.h | 41 ++++++++++++++++++++++------------------- 2 files changed, 46 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index ca5fcadf9981..19c3e2853f17 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -1,24 +1,29 @@ /* - Copyright 2003-2004 Red Hat, Inc. All rights reserved. - Copyright 2003-2004 Jeff Garzik - - The contents of this file are subject to the Open - Software License version 1.1 that can be found at - http://www.opensource.org/licenses/osl-1.1.txt and is included herein - by reference. - - Alternatively, the contents of this file may be used under the terms - of the GNU General Public License version 2 (the "GPL") as distributed - in the kernel source COPYING file, in which case the provisions of - the GPL are applicable instead of the above. If you wish to allow - the use of your version of this file only under the terms of the - GPL and not to allow others to use your version of this file under - the OSL, indicate your decision by deleting the provisions above and - replace them with the notice and other provisions required by the GPL. - If you do not delete the provisions above, a recipient may use your - version of this file under either the OSL or the GPL. - + * Copyright 2003-2004 Red Hat, Inc. All rights reserved. + * Copyright 2003-2004 Jeff Garzik + * + * + * 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, or (at your option) + * any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; see the file COPYING. If not, write to + * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + * + * + * libata documentation is available via 'make {ps|pdf}docs', + * as Documentation/DocBook/libata.* + * + * Hardware documentation available from http://www.t13.org/ + * */ #ifndef __LINUX_ATA_H__ diff --git a/include/linux/libata.h b/include/linux/libata.h index 6cd9ba63563b..51d2b20d34f2 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1,23 +1,26 @@ /* - Copyright 2003-2004 Red Hat, Inc. All rights reserved. - Copyright 2003-2004 Jeff Garzik - - The contents of this file are subject to the Open - Software License version 1.1 that can be found at - http://www.opensource.org/licenses/osl-1.1.txt and is included herein - by reference. - - Alternatively, the contents of this file may be used under the terms - of the GNU General Public License version 2 (the "GPL") as distributed - in the kernel source COPYING file, in which case the provisions of - the GPL are applicable instead of the above. If you wish to allow - the use of your version of this file only under the terms of the - GPL and not to allow others to use your version of this file under - the OSL, indicate your decision by deleting the provisions above and - replace them with the notice and other provisions required by the GPL. - If you do not delete the provisions above, a recipient may use your - version of this file under either the OSL or the GPL. - + * Copyright 2003-2005 Red Hat, Inc. All rights reserved. + * Copyright 2003-2005 Jeff Garzik + * + * + * 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, or (at your option) + * any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; see the file COPYING. If not, write to + * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + * + * + * libata documentation is available via 'make {ps|pdf}docs', + * as Documentation/DocBook/libata.* + * */ #ifndef __LINUX_LIBATA_H__ -- cgit v1.2.3 From e13934563db047043ccead26412f552375cea90c Mon Sep 17 00:00:00 2001 From: Andy Fleming Date: Wed, 24 Aug 2005 18:46:21 -0500 Subject: [PATCH] PHY Layer fixup This patch adds back the code that was taken out, thus re-enabling: * The PHY Layer to initialize without crashing * Drivers to actually connect to PHYs * The entire PHY Control Layer This patch is used by the gianfar driver, and other drivers which are in development. Signed-off-by: Andy Fleming Signed-off-by: Jeff Garzik --- include/linux/phy.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 4f2b5effc16b..72cb67b66e0c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -334,11 +334,26 @@ int phy_write(struct phy_device *phydev, u16 regnum, u16 val); struct phy_device* get_phy_device(struct mii_bus *bus, int addr); int phy_clear_interrupt(struct phy_device *phydev); int phy_config_interrupt(struct phy_device *phydev, u32 interrupts); +struct phy_device * phy_attach(struct net_device *dev, + const char *phy_id, u32 flags); +struct phy_device * phy_connect(struct net_device *dev, const char *phy_id, + void (*handler)(struct net_device *), u32 flags); +void phy_disconnect(struct phy_device *phydev); +void phy_detach(struct phy_device *phydev); +void phy_start(struct phy_device *phydev); +void phy_stop(struct phy_device *phydev); +int phy_start_aneg(struct phy_device *phydev); + +int mdiobus_register(struct mii_bus *bus); +void mdiobus_unregister(struct mii_bus *bus); +void phy_sanitize_settings(struct phy_device *phydev); +int phy_stop_interrupts(struct phy_device *phydev); static inline int phy_read_status(struct phy_device *phydev) { return phydev->drv->read_status(phydev); } +int genphy_config_advert(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_config_aneg(struct phy_device *phydev); @@ -355,6 +370,8 @@ int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct mii_ioctl_data *mii_data, int cmd); +int phy_start_interrupts(struct phy_device *phydev); +void phy_print_status(struct phy_device *phydev); extern struct bus_type mdio_bus_type; #endif /* __PHY_H */ -- cgit v1.2.3 From 9e2d3cd34a159948dc753a14573e16bffc04dba8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 28 Aug 2005 03:19:14 +0100 Subject: [PATCH] mod_devicetable.h fixes * ieee1394_device_id has kernel_ulong_t field after an odd number of __u32 ones. Since mod_devicetable.h is included both from kernel and from host build helper, we may be in trouble if we are building on 32bit host for 64bit target - userland sees unsigned long long, kernel sees unsigned long and while their sizes match, alignments might not. Fixed by forcing alignment. Fortunately, almost nobody else needs that - the rest of such fields is naturally aligned as it is. * of_device_id has void * in it. Host userland helpers need kernel_ulong_t instead, since their void * might have nothing to do with the kernel one. Fixed in the same way it's done for similar problems in pcmcia_device_id (ifdef __KERNEL__). * pcmcia_device_id has the same problem as ieee1394_device_id. Fixed the same way. Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/mod_devicetable.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index dce53ac1625d..97bbccdbcca3 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -33,7 +33,8 @@ struct ieee1394_device_id { __u32 model_id; __u32 specifier_id; __u32 version; - kernel_ulong_t driver_data; + kernel_ulong_t driver_data + __attribute__((aligned(sizeof(kernel_ulong_t)))); }; @@ -182,7 +183,11 @@ struct of_device_id char name[32]; char type[32]; char compatible[128]; +#if __KERNEL__ void *data; +#else + kernel_ulong_t data; +#endif }; @@ -208,7 +213,8 @@ struct pcmcia_device_id { #ifdef __KERNEL__ const char * prod_id[4]; #else - kernel_ulong_t prod_id[4]; + kernel_ulong_t prod_id[4] + __attribute__((aligned(sizeof(kernel_ulong_t)))); #endif /* not matched against */ -- cgit v1.2.3 From bf3a46aa9b96f6eb3a49a568f72a2801c3e830c0 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:22:01 -0700 Subject: [NETFILTER]: convert nfmark and conntrack mark to 32bit As discussed at netconf'05, we convert nfmark and conntrack-mark to be 32bits even on 64bit architectures. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack.h | 2 +- include/linux/skbuff.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index 08fe5f7d14a0..4ed720f0c4cd 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -171,7 +171,7 @@ struct ip_conntrack #endif /* CONFIG_IP_NF_NAT_NEEDED */ #if defined(CONFIG_IP_NF_CONNTRACK_MARK) - unsigned long mark; + u_int32_t mark; #endif /* Traversed often, so hopefully in different cacheline to top */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 948527e42a60..2e40f4c9f7a6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -259,7 +259,7 @@ struct sk_buff { void (*destructor)(struct sk_buff *skb); #ifdef CONFIG_NETFILTER - unsigned long nfmark; + __u32 nfmark; __u32 nfcache; __u32 nfctinfo; struct nf_conntrack *nfct; -- cgit v1.2.3 From 6869c4d8e066e21623c812c448a05f1ed931c9c6 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:24:19 -0700 Subject: [NETFILTER]: reduce netfilter sk_buff enlargement As discussed at netconf'05, we're trying to save every bit in sk_buff. The patch below makes sk_buff 8 bytes smaller. I did some basic testing on my notebook and it seems to work. The only real in-tree user of nfcache was IPVS, who only needs a single bit. Unfortunately I couldn't find some other free bit in sk_buff to stuff that bit into, so I introduced a separate field for them. Maybe the IPVS guys can resolve that to further save space. Initially I wanted to shrink pkt_type to three bits (PACKET_HOST and alike are only 6 values defined), but unfortunately the bluetooth code overloads pkt_type :( The conntrack-event-api (out-of-tree) uses nfcache, but Rusty just came up with a way how to do it without any skb fields, so it's safe to remove it. - remove all never-implemented 'nfcache' code - don't have ipvs code abuse 'nfcache' field. currently get's their own compile-conditional skb->ipvs_property field. IPVS maintainers can decide to move this bit elswhere, but nfcache needs to die. - remove skb->nfcache field to save 4 bytes - move skb->nfctinfo into three unused bits to save further 4 bytes Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter.h | 3 +++ include/linux/netfilter_decnet.h | 3 +++ include/linux/netfilter_ipv4.h | 3 +++ include/linux/netfilter_ipv6.h | 3 +++ include/linux/skbuff.h | 10 +++++----- 5 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 2e2045482cb1..ec60856408fd 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -21,10 +21,13 @@ #define NF_STOP 5 #define NF_MAX_VERDICT NF_STOP +/* only for userspace compatibility */ +#ifndef __KERNEL__ /* Generic cache responses from hook functions. <= 0x2000 is used for protocol-flags. */ #define NFC_UNKNOWN 0x4000 #define NFC_ALTERED 0x8000 +#endif #ifdef __KERNEL__ #include diff --git a/include/linux/netfilter_decnet.h b/include/linux/netfilter_decnet.h index 3064eec9cb8e..018979484150 100644 --- a/include/linux/netfilter_decnet.h +++ b/include/linux/netfilter_decnet.h @@ -9,6 +9,8 @@ #include +/* only for userspace compatibility */ +#ifndef __KERNEL__ /* IP Cache bits. */ /* Src IP address. */ #define NFC_DN_SRC 0x0001 @@ -18,6 +20,7 @@ #define NFC_DN_IF_IN 0x0004 /* Output device. */ #define NFC_DN_IF_OUT 0x0008 +#endif /* ! __KERNEL__ */ /* DECnet Hooks */ /* After promisc drops, checksum checks. */ diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 3ebc36afae1a..552815b8193e 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -8,6 +8,8 @@ #include #include +/* only for userspace compatibility */ +#ifndef __KERNEL__ /* IP Cache bits. */ /* Src IP address. */ #define NFC_IP_SRC 0x0001 @@ -35,6 +37,7 @@ #define NFC_IP_DST_PT 0x0400 /* Something else about the proto */ #define NFC_IP_PROTO_UNKNOWN 0x2000 +#endif /* ! __KERNEL__ */ /* IP Hooks */ /* After promisc drops, checksum checks. */ diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index bee7a5ec7c66..20c069a5e4ac 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -10,6 +10,8 @@ #include +/* only for userspace compatibility */ +#ifndef __KERNEL__ /* IP Cache bits. */ /* Src IP address. */ #define NFC_IP6_SRC 0x0001 @@ -38,6 +40,7 @@ #define NFC_IP6_DST_PT 0x0400 /* Something else about the proto */ #define NFC_IP6_PROTO_UNKNOWN 0x2000 +#endif /* ! __KERNEL__ */ /* IP6 Hooks */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2e40f4c9f7a6..4b929c3c1a98 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -190,7 +190,6 @@ struct skb_shared_info { * @end: End pointer * @destructor: Destruct function * @nfmark: Can be used for communication between hooks - * @nfcache: Cache info * @nfct: Associated connection, if any * @nfctinfo: Relationship of this skb to the connection * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c @@ -252,17 +251,18 @@ struct sk_buff { __u8 local_df:1, cloned:1, ip_summed:2, - nohdr:1; - /* 3 bits spare */ + nohdr:1, + nfctinfo:3; __u8 pkt_type; __be16 protocol; void (*destructor)(struct sk_buff *skb); #ifdef CONFIG_NETFILTER __u32 nfmark; - __u32 nfcache; - __u32 nfctinfo; struct nf_conntrack *nfct; +#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) + __u8 ipvs_property:1; +#endif #ifdef CONFIG_BRIDGE_NETFILTER struct nf_bridge_info *nf_bridge; #endif -- cgit v1.2.3 From 8728b834b226ffcf2c94a58530090e292af2a7bf Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 9 Aug 2005 19:25:21 -0700 Subject: [NET]: Kill skb->list Remove the "list" member of struct sk_buff, as it is entirely redundant. All SKB list removal callers know which list the SKB is on, so storing this in sk_buff does nothing other than taking up some space. Two tricky bits were SCTP, which I took care of, and two ATM drivers which Francois Romieu fixed up. Signed-off-by: David S. Miller Signed-off-by: Francois Romieu --- include/linux/skbuff.h | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4b929c3c1a98..76c68851474c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -204,7 +204,6 @@ struct sk_buff { struct sk_buff *next; struct sk_buff *prev; - struct sk_buff_head *list; struct sock *sk; struct timeval stamp; struct net_device *dev; @@ -597,7 +596,6 @@ static inline void __skb_queue_head(struct sk_buff_head *list, { struct sk_buff *prev, *next; - newsk->list = list; list->qlen++; prev = (struct sk_buff *)list; next = prev->next; @@ -622,7 +620,6 @@ static inline void __skb_queue_tail(struct sk_buff_head *list, { struct sk_buff *prev, *next; - newsk->list = list; list->qlen++; next = (struct sk_buff *)list; prev = next->prev; @@ -655,7 +652,6 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) next->prev = prev; prev->next = next; result->next = result->prev = NULL; - result->list = NULL; } return result; } @@ -664,7 +660,7 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) /* * Insert a packet on a list. */ -extern void skb_insert(struct sk_buff *old, struct sk_buff *newsk); +extern void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) @@ -672,24 +668,23 @@ static inline void __skb_insert(struct sk_buff *newsk, newsk->next = next; newsk->prev = prev; next->prev = prev->next = newsk; - newsk->list = list; list->qlen++; } /* * Place a packet after a given packet in a list. */ -extern void skb_append(struct sk_buff *old, struct sk_buff *newsk); -static inline void __skb_append(struct sk_buff *old, struct sk_buff *newsk) +extern void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); +static inline void __skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list) { - __skb_insert(newsk, old, old->next, old->list); + __skb_insert(newsk, old, old->next, list); } /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ -extern void skb_unlink(struct sk_buff *skb); +extern void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list); static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; @@ -698,7 +693,6 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; - skb->list = NULL; next->prev = prev; prev->next = next; } -- cgit v1.2.3 From abc3bc58047efa72ee9c2e208cbeb73d261ad703 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 9 Aug 2005 19:25:56 -0700 Subject: [NET]: Kill skb->tc_classid Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 76c68851474c..f10a8b9628b0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -196,7 +196,6 @@ struct skb_shared_info { * @private: Data which is private to the HIPPI implementation * @tc_index: Traffic control index * @tc_verd: traffic control verdict - * @tc_classid: traffic control classid */ struct sk_buff { @@ -275,9 +274,7 @@ struct sk_buff { __u32 tc_index; /* traffic control index */ #ifdef CONFIG_NET_CLS_ACT __u32 tc_verd; /* traffic control verdict */ - __u32 tc_classid; /* traffic control classid */ #endif - #endif -- cgit v1.2.3 From ac3247baf8ecadf168642e3898b0212c29c79715 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:28:03 -0700 Subject: [NETFILTER]: connection tracking event notifiers This adds a notifier chain based event mechanism for ip_conntrack state changes. As opposed to the previous implementations in patch-o-matic, we do no longer need a field in the skb to achieve this. Thanks to the valuable input from Patrick McHardy and Rusty on the idea of a per_cpu implementation. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack.h | 144 +++++++++++++++++++++++ include/linux/netfilter_ipv4/ip_conntrack_core.h | 17 ++- 2 files changed, 157 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index 4ed720f0c4cd..ae1270c97b50 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -65,6 +65,63 @@ enum ip_conntrack_status { /* Both together */ IPS_NAT_DONE_MASK = (IPS_DST_NAT_DONE | IPS_SRC_NAT_DONE), + + /* Connection is dying (removed from lists), can not be unset. */ + IPS_DYING_BIT = 9, + IPS_DYING = (1 << IPS_DYING_BIT), +}; + +/* Connection tracking event bits */ +enum ip_conntrack_events +{ + /* New conntrack */ + IPCT_NEW_BIT = 0, + IPCT_NEW = (1 << IPCT_NEW_BIT), + + /* Expected connection */ + IPCT_RELATED_BIT = 1, + IPCT_RELATED = (1 << IPCT_RELATED_BIT), + + /* Destroyed conntrack */ + IPCT_DESTROY_BIT = 2, + IPCT_DESTROY = (1 << IPCT_DESTROY_BIT), + + /* Timer has been refreshed */ + IPCT_REFRESH_BIT = 3, + IPCT_REFRESH = (1 << IPCT_REFRESH_BIT), + + /* Status has changed */ + IPCT_STATUS_BIT = 4, + IPCT_STATUS = (1 << IPCT_STATUS_BIT), + + /* Update of protocol info */ + IPCT_PROTOINFO_BIT = 5, + IPCT_PROTOINFO = (1 << IPCT_PROTOINFO_BIT), + + /* Volatile protocol info */ + IPCT_PROTOINFO_VOLATILE_BIT = 6, + IPCT_PROTOINFO_VOLATILE = (1 << IPCT_PROTOINFO_VOLATILE_BIT), + + /* New helper for conntrack */ + IPCT_HELPER_BIT = 7, + IPCT_HELPER = (1 << IPCT_HELPER_BIT), + + /* Update of helper info */ + IPCT_HELPINFO_BIT = 8, + IPCT_HELPINFO = (1 << IPCT_HELPINFO_BIT), + + /* Volatile helper info */ + IPCT_HELPINFO_VOLATILE_BIT = 9, + IPCT_HELPINFO_VOLATILE = (1 << IPCT_HELPINFO_VOLATILE_BIT), + + /* NAT info */ + IPCT_NATINFO_BIT = 10, + IPCT_NATINFO = (1 << IPCT_NATINFO_BIT), +}; + +enum ip_conntrack_expect_events { + IPEXP_NEW_BIT = 0, + IPEXP_NEW = (1 << IPEXP_NEW_BIT), }; #ifdef __KERNEL__ @@ -280,6 +337,11 @@ static inline int is_confirmed(struct ip_conntrack *ct) return test_bit(IPS_CONFIRMED_BIT, &ct->status); } +static inline int is_dying(struct ip_conntrack *ct) +{ + return test_bit(IPS_DYING_BIT, &ct->status); +} + extern unsigned int ip_conntrack_htable_size; struct ip_conntrack_stat @@ -303,6 +365,88 @@ struct ip_conntrack_stat #define CONNTRACK_STAT_INC(count) (__get_cpu_var(ip_conntrack_stat).count++) +#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS +#include + +struct ip_conntrack_ecache { + struct ip_conntrack *ct; + unsigned int events; +}; +DECLARE_PER_CPU(struct ip_conntrack_ecache, ip_conntrack_ecache); + +#define CONNTRACK_ECACHE(x) (__get_cpu_var(ip_conntrack_ecache).x) + +extern struct notifier_block *ip_conntrack_chain; +extern struct notifier_block *ip_conntrack_expect_chain; + +static inline int ip_conntrack_register_notifier(struct notifier_block *nb) +{ + return notifier_chain_register(&ip_conntrack_chain, nb); +} + +static inline int ip_conntrack_unregister_notifier(struct notifier_block *nb) +{ + return notifier_chain_unregister(&ip_conntrack_chain, nb); +} + +static inline int +ip_conntrack_expect_register_notifier(struct notifier_block *nb) +{ + return notifier_chain_register(&ip_conntrack_expect_chain, nb); +} + +static inline int +ip_conntrack_expect_unregister_notifier(struct notifier_block *nb) +{ + return notifier_chain_unregister(&ip_conntrack_expect_chain, nb); +} + +static inline void +ip_conntrack_event_cache(enum ip_conntrack_events event, + const struct sk_buff *skb) +{ + struct ip_conntrack_ecache *ecache = + &__get_cpu_var(ip_conntrack_ecache); + + if (unlikely((struct ip_conntrack *) skb->nfct != ecache->ct)) { + if (net_ratelimit()) { + printk(KERN_ERR "ctevent: skb->ct != ecache->ct !!!\n"); + dump_stack(); + } + } + ecache->events |= event; +} + +extern void +ip_conntrack_deliver_cached_events_for(const struct ip_conntrack *ct); +extern void ip_conntrack_event_cache_init(const struct sk_buff *skb); + +static inline void ip_conntrack_event(enum ip_conntrack_events event, + struct ip_conntrack *ct) +{ + if (is_confirmed(ct) && !is_dying(ct)) + notifier_call_chain(&ip_conntrack_chain, event, ct); +} + +static inline void +ip_conntrack_expect_event(enum ip_conntrack_expect_events event, + struct ip_conntrack_expect *exp) +{ + notifier_call_chain(&ip_conntrack_expect_chain, event, exp); +} +#else /* CONFIG_IP_NF_CONNTRACK_EVENTS */ +static inline void ip_conntrack_event_cache(enum ip_conntrack_events event, + const struct sk_buff *skb) {} +static inline void ip_conntrack_event(enum ip_conntrack_events event, + struct ip_conntrack *ct) {} +static inline void ip_conntrack_deliver_cached_events_for( + struct ip_conntrack *ct) {} +static inline void ip_conntrack_event_cache_init(const struct sk_buff *skb) {} +static inline void +ip_conntrack_expect_event(enum ip_conntrack_expect_events event, + struct ip_conntrack_expect *exp) {} +#endif /* CONFIG_IP_NF_CONNTRACK_EVENTS */ + #ifdef CONFIG_IP_NF_NAT_NEEDED static inline int ip_nat_initialized(struct ip_conntrack *conntrack, enum ip_nat_manip_type manip) diff --git a/include/linux/netfilter_ipv4/ip_conntrack_core.h b/include/linux/netfilter_ipv4/ip_conntrack_core.h index 694aec9b4784..46eeea1e2733 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_core.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_core.h @@ -38,12 +38,21 @@ extern int __ip_conntrack_confirm(struct sk_buff **pskb); /* Confirm a connection: returns NF_DROP if packet must be dropped. */ static inline int ip_conntrack_confirm(struct sk_buff **pskb) { - if ((*pskb)->nfct - && !is_confirmed((struct ip_conntrack *)(*pskb)->nfct)) - return __ip_conntrack_confirm(pskb); - return NF_ACCEPT; + struct ip_conntrack *ct = (struct ip_conntrack *)(*pskb)->nfct; + int ret = NF_ACCEPT; + + if (ct && !is_confirmed(ct)) + ret = __ip_conntrack_confirm(pskb); + ip_conntrack_deliver_cached_events_for(ct); + + return ret; } +#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS +struct ip_conntrack_ecache; +extern void __ip_ct_deliver_cached_events(struct ip_conntrack_ecache *ec); +#endif + extern struct list_head *ip_conntrack_hash; extern struct list_head ip_conntrack_expect_list; extern rwlock_t ip_conntrack_lock; -- cgit v1.2.3 From f9e815b376dc19e6afc551cd755ac64e9e42d81f Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:30:24 -0700 Subject: [NETFITLER]: Add nfnetlink layer. Introduce "nfnetlink" (netfilter netlink) layer. This layer is used as transport layer for all userspace communication of the new upcoming netfilter subsystems, such as ctnetlink, nfnetlink_queue and some day even the mythical pkttables ;) Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 145 ++++++++++++++++++++++++++++++++++++ 1 file changed, 145 insertions(+) create mode 100644 include/linux/netfilter/nfnetlink.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h new file mode 100644 index 000000000000..8f1bfb8d650b --- /dev/null +++ b/include/linux/netfilter/nfnetlink.h @@ -0,0 +1,145 @@ +#ifndef _NFNETLINK_H +#define _NFNETLINK_H +#include + +/* nfnetlink groups: Up to 32 maximum */ +#define NF_NETLINK_CONNTRACK_NEW 0x00000001 +#define NF_NETLINK_CONNTRACK_UPDATE 0x00000002 +#define NF_NETLINK_CONNTRACK_DESTROY 0x00000004 +#define NF_NETLINK_CONNTRACK_EXP_NEW 0x00000008 +#define NF_NETLINK_CONNTRACK_EXP_UPDATE 0x00000010 +#define NF_NETLINK_CONNTRACK_EXP_DESTROY 0x00000020 + +/* Generic structure for encapsulation optional netfilter information. + * It is reminiscent of sockaddr, but with sa_family replaced + * with attribute type. + * ! This should someday be put somewhere generic as now rtnetlink and + * ! nfnetlink use the same attributes methods. - J. Schulist. + */ + +struct nfattr +{ + u_int16_t nfa_len; + u_int16_t nfa_type; +} __attribute__ ((packed)); + +/* FIXME: Shamelessly copy and pasted from rtnetlink.h, it's time + * to put this in a generic file */ + +#define NFA_ALIGNTO 4 +#define NFA_ALIGN(len) (((len) + NFA_ALIGNTO - 1) & ~(NFA_ALIGNTO - 1)) +#define NFA_OK(nfa,len) ((len) > 0 && (nfa)->nfa_len >= sizeof(struct nfattr) \ + && (nfa)->nfa_len <= (len)) +#define NFA_NEXT(nfa,attrlen) ((attrlen) -= NFA_ALIGN((nfa)->nfa_len), \ + (struct nfattr *)(((char *)(nfa)) + NFA_ALIGN((nfa)->nfa_len))) +#define NFA_LENGTH(len) (NFA_ALIGN(sizeof(struct nfattr)) + (len)) +#define NFA_SPACE(len) NFA_ALIGN(NFA_LENGTH(len)) +#define NFA_DATA(nfa) ((void *)(((char *)(nfa)) + NFA_LENGTH(0))) +#define NFA_PAYLOAD(nfa) ((int)((nfa)->nfa_len) - NFA_LENGTH(0)) +#define NFA_NEST(skb, type) \ +({ struct nfattr *__start = (struct nfattr *) (skb)->tail; \ + NFA_PUT(skb, type, 0, NULL); \ + __start; }) +#define NFA_NEST_END(skb, start) \ +({ (start)->nfa_len = ((skb)->tail - (unsigned char *) (start)); \ + (skb)->len; }) +#define NFA_NEST_CANCEL(skb, start) \ +({ if (start) \ + skb_trim(skb, (unsigned char *) (start) - (skb)->data); \ + -1; }) + +/* General form of address family dependent message. + */ +struct nfgenmsg { + u_int8_t nfgen_family; /* AF_xxx */ + u_int8_t version; /* nfnetlink version */ + u_int16_t res_id; /* resource id */ +} __attribute__ ((packed)); + +#define NFNETLINK_V1 1 + +#define NFM_NFA(n) ((struct nfattr *)(((char *)(n)) \ + + NLMSG_ALIGN(sizeof(struct nfgenmsg)))) +#define NFM_PAYLOAD(n) NLMSG_PAYLOAD(n, sizeof(struct nfgenmsg)) + +/* netfilter netlink message types are split in two pieces: + * 8 bit subsystem, 8bit operation. + */ + +#define NFNL_SUBSYS_ID(x) ((x & 0xff00) >> 8) +#define NFNL_MSG_TYPE(x) (x & 0x00ff) + +enum nfnl_subsys_id { + NFNL_SUBSYS_NONE = 0, + NFNL_SUBSYS_CTNETLINK, + NFNL_SUBSYS_CTNETLINK_EXP, + NFNL_SUBSYS_IPTNETLINK, + NFNL_SUBSYS_QUEUE, + NFNL_SUBSYS_ULOG, + NFNL_SUBSYS_COUNT, +}; + +#ifdef __KERNEL__ + +#include + +struct nfnl_callback +{ + kernel_cap_t cap_required; /* capabilities required for this msg */ + int (*call)(struct sock *nl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nfattr *cda[], int *errp); +}; + +struct nfnetlink_subsystem +{ + const char *name; + __u8 subsys_id; /* nfnetlink subsystem ID */ + __u8 cb_count; /* number of callbacks */ + u_int32_t attr_count; /* number of nfattr's */ + struct nfnl_callback *cb; /* callback for individual types */ +}; + +extern void __nfa_fill(struct sk_buff *skb, int attrtype, + int attrlen, const void *data); +#define NFA_PUT(skb, attrtype, attrlen, data) \ +({ if (skb_tailroom(skb) < (int)NFA_SPACE(attrlen)) goto nfattr_failure; \ + __nfa_fill(skb, attrtype, attrlen, data); }) + +extern struct semaphore nfnl_sem; + +#define nfnl_shlock() down(&nfnl_sem) +#define nfnl_shlock_nowait() down_trylock(&nfnl_sem) + +#define nfnl_shunlock() do { up(&nfnl_sem); \ + if(nfnl && nfnl->sk_receive_queue.qlen) \ + nfnl->sk_data_ready(nfnl, 0); \ + } while(0) + +extern void nfnl_lock(void); +extern void nfnl_unlock(void); + +extern int nfnetlink_subsys_register(struct nfnetlink_subsystem *n); +extern int nfnetlink_subsys_unregister(struct nfnetlink_subsystem *n); + +extern int nfattr_parse(struct nfattr *tb[], int maxattr, + struct nfattr *nfa, int len); + +#define nfattr_parse_nested(tb, max, nfa) \ + nfattr_parse((tb), (max), NFA_DATA((nfa)), NFA_PAYLOAD((nfa))) + +#define nfattr_bad_size(tb, max, cta_min) \ +({ int __i, __res = 0; \ + for (__i=0; __i Date: Tue, 9 Aug 2005 19:31:17 -0700 Subject: [NET]: Remove HIPPI private from skbuff.h This removes the private element from skbuff, that is only used by HIPPI. Instead it uses skb->cb[] to hold the additional data that is needed in the output path from hard_header to device driver. PS: The only qdisc that might potentially corrupt this cb[] is if netem was used over HIPPI. I will take care of that by fixing netem to use skb->stamp. I don't expect many users of netem over HIPPI Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/hippidevice.h | 5 +++++ include/linux/skbuff.h | 6 ------ 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hippidevice.h b/include/linux/hippidevice.h index 9debe6bbe5f0..9bc3b688d2ee 100644 --- a/include/linux/hippidevice.h +++ b/include/linux/hippidevice.h @@ -26,6 +26,11 @@ #include #ifdef __KERNEL__ + +struct hippi_cb { + __u32 ifield; +}; + extern unsigned short hippi_type_trans(struct sk_buff *skb, struct net_device *dev); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f10a8b9628b0..4aeadb102589 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -193,7 +193,6 @@ struct skb_shared_info { * @nfct: Associated connection, if any * @nfctinfo: Relationship of this skb to the connection * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c - * @private: Data which is private to the HIPPI implementation * @tc_index: Traffic control index * @tc_verd: traffic control verdict */ @@ -265,11 +264,6 @@ struct sk_buff { struct nf_bridge_info *nf_bridge; #endif #endif /* CONFIG_NETFILTER */ -#if defined(CONFIG_HIPPI) - union { - __u32 ifield; - } private; -#endif #ifdef CONFIG_NET_SCHED __u32 tc_index; /* traffic control index */ #ifdef CONFIG_NET_CLS_ACT -- cgit v1.2.3 From 080774a243f56ce2195ace96fba3d18548ee48ce Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:32:58 -0700 Subject: [NETFILTER]: Add ctnetlink subsystem Add ctnetlink subsystem for userspace-access to ip_conntrack table. This allows reading and updating of existing entries, as well as creating new ones (and new expect's) via nfnetlink. Please note the 'strange' byte order: nfattr (tag+length) are in host byte order, while the payload is always guaranteed to be in network byte order. This allows a simple userspace process to encapsulate netlink messages into arch-independent udp packets by just processing/swapping the headers and not knowing anything about the actual payload. Signed-off-by: Harald Welte Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 3 +- include/linux/netfilter/nfnetlink_conntrack.h | 123 +++++++++++++++++++++ include/linux/netfilter_ipv4/ip_conntrack.h | 46 +++++++- include/linux/netfilter_ipv4/ip_conntrack_core.h | 5 + include/linux/netfilter_ipv4/ip_conntrack_helper.h | 2 + .../linux/netfilter_ipv4/ip_conntrack_protocol.h | 24 ++-- include/linux/netfilter_ipv4/ip_nat_protocol.h | 25 +++-- 7 files changed, 210 insertions(+), 18 deletions(-) create mode 100644 include/linux/netfilter/nfnetlink_conntrack.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 8f1bfb8d650b..ace7a7be0742 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -56,7 +56,7 @@ struct nfgenmsg { u_int16_t res_id; /* resource id */ } __attribute__ ((packed)); -#define NFNETLINK_V1 1 +#define NFNETLINK_V0 0 #define NFM_NFA(n) ((struct nfattr *)(((char *)(n)) \ + NLMSG_ALIGN(sizeof(struct nfgenmsg)))) @@ -81,6 +81,7 @@ enum nfnl_subsys_id { #ifdef __KERNEL__ +#include #include struct nfnl_callback diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h new file mode 100644 index 000000000000..fb528e0e3bd9 --- /dev/null +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -0,0 +1,123 @@ +#ifndef _IPCONNTRACK_NETLINK_H +#define _IPCONNTRACK_NETLINK_H +#include + +enum cntl_msg_types { + IPCTNL_MSG_CT_NEW, + IPCTNL_MSG_CT_GET, + IPCTNL_MSG_CT_DELETE, + IPCTNL_MSG_CT_GET_CTRZERO, + + IPCTNL_MSG_MAX +}; + +enum ctnl_exp_msg_types { + IPCTNL_MSG_EXP_NEW, + IPCTNL_MSG_EXP_GET, + IPCTNL_MSG_EXP_DELETE, + + IPCTNL_MSG_EXP_MAX +}; + + +enum ctattr_type { + CTA_UNSPEC, + CTA_TUPLE_ORIG, + CTA_TUPLE_REPLY, + CTA_STATUS, + CTA_PROTOINFO, + CTA_HELP, + CTA_NAT, + CTA_TIMEOUT, + CTA_MARK, + CTA_COUNTERS_ORIG, + CTA_COUNTERS_REPLY, + CTA_USE, + CTA_EXPECT, + CTA_ID, + __CTA_MAX +}; +#define CTA_MAX (__CTA_MAX - 1) + +enum ctattr_tuple { + CTA_TUPLE_UNSPEC, + CTA_TUPLE_IP, + CTA_TUPLE_PROTO, + __CTA_TUPLE_MAX +}; +#define CTA_TUPLE_MAX (__CTA_TUPLE_MAX - 1) + +enum ctattr_ip { + CTA_IP_UNSPEC, + CTA_IP_V4_SRC, + CTA_IP_V4_DST, + CTA_IP_V6_SRC, + CTA_IP_V6_DST, + __CTA_IP_MAX +}; +#define CTA_IP_MAX (__CTA_IP_MAX - 1) + +enum ctattr_l4proto { + CTA_PROTO_UNSPEC, + CTA_PROTO_NUM, + CTA_PROTO_SRC_PORT, + CTA_PROTO_DST_PORT, + CTA_PROTO_ICMP_ID, + CTA_PROTO_ICMP_TYPE, + CTA_PROTO_ICMP_CODE, + __CTA_PROTO_MAX +}; +#define CTA_PROTO_MAX (__CTA_PROTO_MAX - 1) + +enum ctattr_protoinfo { + CTA_PROTOINFO_UNSPEC, + CTA_PROTOINFO_TCP_STATE, + __CTA_PROTOINFO_MAX +}; +#define CTA_PROTOINFO_MAX (__CTA_PROTOINFO_MAX - 1) + +enum ctattr_counters { + CTA_COUNTERS_UNSPEC, + CTA_COUNTERS_PACKETS, + CTA_COUNTERS_BYTES, + __CTA_COUNTERS_MAX +}; +#define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1) + +enum ctattr_nat { + CTA_NAT_UNSPEC, + CTA_NAT_MINIP, + CTA_NAT_MAXIP, + CTA_NAT_PROTO, + __CTA_NAT_MAX +}; +#define CTA_NAT_MAX (__CTA_NAT_MAX - 1) + +enum ctattr_protonat { + CTA_PROTONAT_UNSPEC, + CTA_PROTONAT_PORT_MIN, + CTA_PROTONAT_PORT_MAX, + __CTA_PROTONAT_MAX +}; +#define CTA_PROTONAT_MAX (__CTA_PROTONAT_MAX - 1) + +enum ctattr_expect { + CTA_EXPECT_UNSPEC, + CTA_EXPECT_TUPLE, + CTA_EXPECT_MASK, + CTA_EXPECT_TIMEOUT, + CTA_EXPECT_ID, + __CTA_EXPECT_MAX +}; +#define CTA_EXPECT_MAX (__CTA_EXPECT_MAX - 1) + +enum ctattr_help { + CTA_HELP_UNSPEC, + CTA_HELP_NAME, + __CTA_HELP_MAX +}; +#define CTA_HELP_MAX (__CTA_HELP_MAX - 1) + +#define CTA_HELP_MAXNAMESIZE 32 + +#endif /* _IPCONNTRACK_NETLINK_H */ diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index ae1270c97b50..ff2c1c6001f9 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -209,6 +209,9 @@ struct ip_conntrack /* Current number of expected connections */ unsigned int expecting; + /* Unique ID that identifies this conntrack*/ + unsigned int id; + /* Helper, if any. */ struct ip_conntrack_helper *helper; @@ -257,6 +260,9 @@ struct ip_conntrack_expect /* Usage count. */ atomic_t use; + /* Unique ID */ + unsigned int id; + #ifdef CONFIG_IP_NF_NAT_NEEDED /* This is the original per-proto part, used to map the * expected connection the way the recipient expects. */ @@ -296,7 +302,12 @@ ip_conntrack_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo) } /* decrement reference count on a conntrack */ -extern void ip_conntrack_put(struct ip_conntrack *ct); +static inline void +ip_conntrack_put(struct ip_conntrack *ct) +{ + IP_NF_ASSERT(ct); + nf_conntrack_put(&ct->ct_general); +} /* call to create an explicit dependency on ip_conntrack. */ extern void need_ip_conntrack(void); @@ -331,6 +342,39 @@ extern void ip_ct_iterate_cleanup(int (*iter)(struct ip_conntrack *i, void *data), void *data); +extern struct ip_conntrack_helper * +__ip_conntrack_helper_find_byname(const char *); +extern struct ip_conntrack_helper * +ip_conntrack_helper_find_get(const struct ip_conntrack_tuple *tuple); +extern void ip_conntrack_helper_put(struct ip_conntrack_helper *helper); + +extern struct ip_conntrack_protocol * +__ip_conntrack_proto_find(u_int8_t protocol); +extern struct ip_conntrack_protocol * +ip_conntrack_proto_find_get(u_int8_t protocol); +extern void ip_conntrack_proto_put(struct ip_conntrack_protocol *proto); + +extern void ip_ct_remove_expectations(struct ip_conntrack *ct); + +extern struct ip_conntrack *ip_conntrack_alloc(struct ip_conntrack_tuple *, + struct ip_conntrack_tuple *); + +extern void ip_conntrack_free(struct ip_conntrack *ct); + +extern void ip_conntrack_hash_insert(struct ip_conntrack *ct); + +extern struct ip_conntrack_expect * +__ip_conntrack_expect_find(const struct ip_conntrack_tuple *tuple); + +extern struct ip_conntrack_expect * +ip_conntrack_expect_find_get(const struct ip_conntrack_tuple *tuple); + +extern struct ip_conntrack_tuple_hash * +__ip_conntrack_find(const struct ip_conntrack_tuple *tuple, + const struct ip_conntrack *ignored_conntrack); + +extern void ip_conntrack_flush(void); + /* It's confirmed if it is, or has been in the hash table. */ static inline int is_confirmed(struct ip_conntrack *ct) { diff --git a/include/linux/netfilter_ipv4/ip_conntrack_core.h b/include/linux/netfilter_ipv4/ip_conntrack_core.h index 46eeea1e2733..fbf6c3e41647 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_core.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_core.h @@ -2,6 +2,9 @@ #define _IP_CONNTRACK_CORE_H #include +#define MAX_IP_CT_PROTO 256 +extern struct ip_conntrack_protocol *ip_ct_protos[MAX_IP_CT_PROTO]; + /* This header is used to share core functionality between the standalone connection tracking module, and the compatibility layer's use of connection tracking. */ @@ -53,6 +56,8 @@ struct ip_conntrack_ecache; extern void __ip_ct_deliver_cached_events(struct ip_conntrack_ecache *ec); #endif +extern void __ip_ct_expect_unlink_destroy(struct ip_conntrack_expect *exp); + extern struct list_head *ip_conntrack_hash; extern struct list_head ip_conntrack_expect_list; extern rwlock_t ip_conntrack_lock; diff --git a/include/linux/netfilter_ipv4/ip_conntrack_helper.h b/include/linux/netfilter_ipv4/ip_conntrack_helper.h index 3692daa93dec..8d69279ccfe4 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_helper.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_helper.h @@ -24,6 +24,8 @@ struct ip_conntrack_helper int (*help)(struct sk_buff **pskb, struct ip_conntrack *ct, enum ip_conntrack_info conntrackinfo); + + int (*to_nfattr)(struct sk_buff *skb, const struct ip_conntrack *ct); }; extern int ip_conntrack_helper_register(struct ip_conntrack_helper *); diff --git a/include/linux/netfilter_ipv4/ip_conntrack_protocol.h b/include/linux/netfilter_ipv4/ip_conntrack_protocol.h index e20b57c5e1b7..b6b99be8632a 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_protocol.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_protocol.h @@ -2,6 +2,7 @@ #ifndef _IP_CONNTRACK_PROTOCOL_H #define _IP_CONNTRACK_PROTOCOL_H #include +#include struct seq_file; @@ -47,22 +48,22 @@ struct ip_conntrack_protocol int (*error)(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, unsigned int hooknum); + /* convert protoinfo to nfnetink attributes */ + int (*to_nfattr)(struct sk_buff *skb, struct nfattr *nfa, + const struct ip_conntrack *ct); + + int (*tuple_to_nfattr)(struct sk_buff *skb, + const struct ip_conntrack_tuple *t); + int (*nfattr_to_tuple)(struct nfattr *tb[], + struct ip_conntrack_tuple *t); + /* Module (if any) which this is connected to. */ struct module *me; }; -#define MAX_IP_CT_PROTO 256 -extern struct ip_conntrack_protocol *ip_ct_protos[MAX_IP_CT_PROTO]; - /* Protocol registration. */ extern int ip_conntrack_protocol_register(struct ip_conntrack_protocol *proto); extern void ip_conntrack_protocol_unregister(struct ip_conntrack_protocol *proto); - -static inline struct ip_conntrack_protocol *ip_ct_find_proto(u_int8_t protocol) -{ - return ip_ct_protos[protocol]; -} - /* Existing built-in protocols */ extern struct ip_conntrack_protocol ip_conntrack_protocol_tcp; extern struct ip_conntrack_protocol ip_conntrack_protocol_udp; @@ -73,6 +74,11 @@ extern int ip_conntrack_protocol_tcp_init(void); /* Log invalid packets */ extern unsigned int ip_ct_log_invalid; +extern int ip_ct_port_tuple_to_nfattr(struct sk_buff *, + const struct ip_conntrack_tuple *); +extern int ip_ct_port_nfattr_to_tuple(struct nfattr *tb[], + struct ip_conntrack_tuple *); + #ifdef CONFIG_SYSCTL #ifdef DEBUG_INVALID_PACKETS #define LOG_INVALID(proto) \ diff --git a/include/linux/netfilter_ipv4/ip_nat_protocol.h b/include/linux/netfilter_ipv4/ip_nat_protocol.h index 129708c22386..ef63aa991a06 100644 --- a/include/linux/netfilter_ipv4/ip_nat_protocol.h +++ b/include/linux/netfilter_ipv4/ip_nat_protocol.h @@ -4,6 +4,9 @@ #include #include +#include +#include + struct iphdr; struct ip_nat_range; @@ -15,6 +18,8 @@ struct ip_nat_protocol /* Protocol number. */ unsigned int protonum; + struct module *me; + /* Translate a packet to the target according to manip type. Return true if succeeded. */ int (*manip_pkt)(struct sk_buff **pskb, @@ -43,19 +48,20 @@ struct ip_nat_protocol unsigned int (*print_range)(char *buffer, const struct ip_nat_range *range); -}; -#define MAX_IP_NAT_PROTO 256 -extern struct ip_nat_protocol *ip_nat_protos[MAX_IP_NAT_PROTO]; + int (*range_to_nfattr)(struct sk_buff *skb, + const struct ip_nat_range *range); + + int (*nfattr_to_range)(struct nfattr *tb[], + struct ip_nat_range *range); +}; /* Protocol registration. */ extern int ip_nat_protocol_register(struct ip_nat_protocol *proto); extern void ip_nat_protocol_unregister(struct ip_nat_protocol *proto); -static inline struct ip_nat_protocol *ip_nat_find_proto(u_int8_t protocol) -{ - return ip_nat_protos[protocol]; -} +extern struct ip_nat_protocol *ip_nat_proto_find_get(u_int8_t protocol); +extern void ip_nat_proto_put(struct ip_nat_protocol *proto); /* Built-in protocols. */ extern struct ip_nat_protocol ip_nat_protocol_tcp; @@ -67,4 +73,9 @@ extern int init_protocols(void) __init; extern void cleanup_protocols(void); extern struct ip_nat_protocol *find_nat_proto(u_int16_t protonum); +extern int ip_nat_port_range_to_nfattr(struct sk_buff *skb, + const struct ip_nat_range *range); +extern int ip_nat_port_nfattr_to_range(struct nfattr *tb[], + struct ip_nat_range *range); + #endif /*_IP_NAT_PROTO_H*/ -- cgit v1.2.3 From b6b99eb5409d75ae35390057cd28f3aedfbd4cf4 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 9 Aug 2005 19:33:51 -0700 Subject: [NET]: Reduce tc_index/tc_verd to u16 Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4aeadb102589..af4f02e98243 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -265,9 +265,9 @@ struct sk_buff { #endif #endif /* CONFIG_NETFILTER */ #ifdef CONFIG_NET_SCHED - __u32 tc_index; /* traffic control index */ + __u16 tc_index; /* traffic control index */ #ifdef CONFIG_NET_CLS_ACT - __u32 tc_verd; /* traffic control verdict */ + __u16 tc_verd; /* traffic control verdict */ #endif #endif -- cgit v1.2.3 From f2ccd8fa06c8e302116e71df372f5c1f83432e03 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 9 Aug 2005 19:34:12 -0700 Subject: [NET]: Kill skb->real_dev Bonding just wants the device before the skb_bond() decapsulation occurs, so simply pass that original device into packet_type->func() as an argument. It remains to be seen whether we can use this same exact thing to get rid of skb->input_dev as well. Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 1 - include/linux/netdevice.h | 10 ++++++---- include/linux/skbuff.h | 2 -- 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 62a9d89dfbe2..17d0c0d40b0e 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -155,7 +155,6 @@ static inline int __vlan_hwaccel_rx(struct sk_buff *skb, { struct net_device_stats *stats; - skb->real_dev = skb->dev; skb->dev = grp->vlan_devices[vlan_tag & VLAN_VID_MASK]; if (skb->dev == NULL) { dev_kfree_skb_any(skb); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3a0ed7f9e801..296cf93a65e0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -497,10 +497,12 @@ static inline void *netdev_priv(struct net_device *dev) #define SET_NETDEV_DEV(net, pdev) ((net)->class_dev.dev = (pdev)) struct packet_type { - __be16 type; /* This is really htons(ether_type). */ - struct net_device *dev; /* NULL is wildcarded here */ - int (*func) (struct sk_buff *, struct net_device *, - struct packet_type *); + __be16 type; /* This is really htons(ether_type). */ + struct net_device *dev; /* NULL is wildcarded here */ + int (*func) (struct sk_buff *, + struct net_device *, + struct packet_type *, + struct net_device *); void *af_packet_priv; struct list_head list; }; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index af4f02e98243..60b32151f76a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -164,7 +164,6 @@ struct skb_shared_info { * @stamp: Time we arrived * @dev: Device we arrived on/are leaving by * @input_dev: Device we arrived on - * @real_dev: The real device we are using * @h: Transport layer header * @nh: Network layer header * @mac: Link layer header @@ -206,7 +205,6 @@ struct sk_buff { struct timeval stamp; struct net_device *dev; struct net_device *input_dev; - struct net_device *real_dev; union { struct tcphdr *th; -- cgit v1.2.3 From 089af26c706d1473f641c909fee7c878d29c1f1a Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:37:23 -0700 Subject: [NETFILTER]: Rename skb_ip_make_writable() to skb_make_writable() There is nothing IPv4-specific in it. In fact, it was already used by IPv6, too... Upcoming nfnetlink_queue code will use it for any kind of packet. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter.h | 5 +++++ include/linux/netfilter_ipv4.h | 5 ----- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index ec60856408fd..54b97a1baba5 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -193,6 +193,11 @@ extern void nf_ct_attach(struct sk_buff *, struct sk_buff *); /* FIXME: Before cache is ever used, this must be implemented for real. */ extern void nf_invalidate_cache(int pf); +/* Call this before modifying an existing packet: ensures it is + modifiable and linear to the point you care about (writable_len). + Returns true or false. */ +extern int skb_make_writable(struct sk_buff **pskb, unsigned int writable_len); + #else /* !CONFIG_NETFILTER */ #define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb) static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 552815b8193e..fdc4a9527343 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -80,11 +80,6 @@ enum nf_ip_hook_priorities { #ifdef __KERNEL__ extern int ip_route_me_harder(struct sk_buff **pskb); -/* Call this before modifying an existing IP packet: ensures it is - modifiable and linear to the point you care about (writable_len). - Returns true or false. */ -extern int skb_ip_make_writable(struct sk_buff **pskb, - unsigned int writable_len); #endif /*__KERNEL__*/ #endif /*__LINUX_IP_NETFILTER_H*/ -- cgit v1.2.3 From 4fdb3bb723db469717c6d38fda667d8b0fa86ebd Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:40:55 -0700 Subject: [NETLINK]: Add properly module refcounting for kernel netlink sockets. - Remove bogus code for compiling netlink as module - Add module refcounting support for modules implementing a netlink protocol - Add support for autoloading modules that implement a netlink protocol as soon as someone opens a socket for that protocol Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/net.h | 3 +++ include/linux/netlink.h | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 20cb226b2268..39906619b9d7 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -282,5 +282,8 @@ static struct proto_ops name##_ops = { \ #define MODULE_ALIAS_NETPROTO(proto) \ MODULE_ALIAS("net-pf-" __stringify(proto)) +#define MODULE_ALIAS_NET_PF_PROTO(pf, proto) \ + MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto)) + #endif /* __KERNEL__ */ #endif /* _LINUX_NET_H */ diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 6552b71bfa73..1c50fea8995b 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -117,7 +117,7 @@ struct netlink_skb_parms #define NETLINK_CREDS(skb) (&NETLINK_CB((skb)).creds) -extern struct sock *netlink_kernel_create(int unit, void (*input)(struct sock *sk, int len)); +extern struct sock *netlink_kernel_create(int unit, void (*input)(struct sock *sk, int len), struct module *module); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid, -- cgit v1.2.3 From 2cc7d5730957c4a3f3659d17d2ba5e06d5581c1f Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:42:34 -0700 Subject: [NETFILTER]: Move reroute-after-queue code up to the nf_queue layer. The rerouting functionality is required by the core, therefore it has to be implemented by the core and not in individual queue handlers. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter.h | 11 +++++++++++ include/linux/netfilter_ipv6.h | 3 +++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 54b97a1baba5..d163e20ca8d9 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -198,6 +198,17 @@ extern void nf_invalidate_cache(int pf); Returns true or false. */ extern int skb_make_writable(struct sk_buff **pskb, unsigned int writable_len); +struct nf_queue_rerouter { + void (*save)(const struct sk_buff *skb, struct nf_info *info); + int (*reroute)(struct sk_buff **skb, const struct nf_info *info); + int rer_size; +}; + +#define nf_info_reroute(x) ((void *)x + sizeof(struct nf_info)) + +extern int nf_register_queue_rerouter(int pf, struct nf_queue_rerouter *rer); +extern int nf_unregister_queue_rerouter(int pf); + #else /* !CONFIG_NETFILTER */ #define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb) static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 20c069a5e4ac..5d204ee7a312 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -71,4 +71,7 @@ enum nf_ip6_hook_priorities { NF_IP6_PRI_LAST = INT_MAX, }; +int ipv6_netfilter_init(void); +void ipv6_netfilter_fini(void); + #endif /*__LINUX_IP6_NETFILTER_H*/ -- cgit v1.2.3 From 0ab43f84995f2c2fcc5cc58a9accaa1095e1317f Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:43:44 -0700 Subject: [NETFILTER]: Core changes required by upcoming nfnetlink_queue code - split netfiler verdict in 16bit verdict and 16bit queue number - add 'queuenum' argument to nf_queue_outfn_t and its users ip[6]_queue - move NFNL_SUBSYS_ definitions from enum to #define - introduce autoloading for nfnetlink subsystem modules - add MODULE_ALIAS_NFNL_SUBSYS macro - add nf_unregister_queue_handlers() to register all handlers for a given nf_queue_outfn_t - add more verbose DEBUGP macro definition to nfnetlink.c - make nfnetlink_subsys_register fail if subsys already exists - add some more comments and debug statements to nfnetlink.c Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter.h | 14 +++++++++++++- include/linux/netfilter/nfnetlink.h | 20 +++++++++++--------- 2 files changed, 24 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index d163e20ca8d9..711e05f33d68 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -21,6 +21,16 @@ #define NF_STOP 5 #define NF_MAX_VERDICT NF_STOP +/* we overload the higher bits for encoding auxiliary data such as the queue + * number. Not nice, but better than additional function arguments. */ +#define NF_VERDICT_MASK 0x0000ffff +#define NF_VERDICT_BITS 16 + +#define NF_VERDICT_QMASK 0xffff0000 +#define NF_VERDICT_QBITS 16 + +#define NF_QUEUE_NR(x) ((x << NF_VERDICT_QBITS) & NF_VERDICT_QMASK || NF_QUEUE) + /* only for userspace compatibility */ #ifndef __KERNEL__ /* Generic cache responses from hook functions. @@ -179,10 +189,12 @@ int nf_getsockopt(struct sock *sk, int pf, int optval, char __user *opt, /* Packet queuing */ typedef int (*nf_queue_outfn_t)(struct sk_buff *skb, - struct nf_info *info, void *data); + struct nf_info *info, + unsigned int queuenum, void *data); extern int nf_register_queue_handler(int pf, nf_queue_outfn_t outfn, void *data); extern int nf_unregister_queue_handler(int pf); +extern void nf_unregister_queue_handlers(nf_queue_outfn_t outfn); extern void nf_reinject(struct sk_buff *skb, struct nf_info *info, unsigned int verdict); diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index ace7a7be0742..561f9df28808 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -69,15 +69,14 @@ struct nfgenmsg { #define NFNL_SUBSYS_ID(x) ((x & 0xff00) >> 8) #define NFNL_MSG_TYPE(x) (x & 0x00ff) -enum nfnl_subsys_id { - NFNL_SUBSYS_NONE = 0, - NFNL_SUBSYS_CTNETLINK, - NFNL_SUBSYS_CTNETLINK_EXP, - NFNL_SUBSYS_IPTNETLINK, - NFNL_SUBSYS_QUEUE, - NFNL_SUBSYS_ULOG, - NFNL_SUBSYS_COUNT, -}; +/* No enum here, otherwise __stringify() trick of MODULE_ALIAS_NFNL_SUBSYS() + * won't work anymore */ +#define NFNL_SUBSYS_NONE 0 +#define NFNL_SUBSYS_CTNETLINK 1 +#define NFNL_SUBSYS_CTNETLINK_EXP 2 +#define NFNL_SUBSYS_QUEUE 3 +#define NFNL_SUBSYS_ULOG 4 +#define NFNL_SUBSYS_COUNT 5 #ifdef __KERNEL__ @@ -142,5 +141,8 @@ extern int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo); extern int nfnetlink_unicast(struct sk_buff *skb, u_int32_t pid, int flags); +#define MODULE_ALIAS_NFNL_SUBSYS(subsys) \ + MODULE_ALIAS("nfnetlink-subsys-" __stringify(subsys)) + #endif /* __KERNEL__ */ #endif /* _NFNETLINK_H */ -- cgit v1.2.3 From 7af4cc3fa158ff1dda6e7451c7e6afa6b0bb85cb Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:44:15 -0700 Subject: [NETFILTER]: Add "nfnetlink_queue" netfilter queue handler over nfnetlink - Add new nfnetlink_queue module - Add new ipt_NFQUEUE and ip6t_NFQUEUE modules to access queue numbers 1-65535 - Mark ip_queue and ip6_queue Kconfig options as OBSOLETE - Update feature-removal-schedule to remove ip[6]_queue in December Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink_queue.h | 85 ++++++++++++++++++++++++++++++ include/linux/netfilter_ipv4/ipt_NFQUEUE.h | 16 ++++++ 2 files changed, 101 insertions(+) create mode 100644 include/linux/netfilter/nfnetlink_queue.h create mode 100644 include/linux/netfilter_ipv4/ipt_NFQUEUE.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h new file mode 100644 index 000000000000..edb463a87eb4 --- /dev/null +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -0,0 +1,85 @@ +#ifndef _NFNETLINK_QUEUE_H +#define _NFNETLINK_QUEUE_H + +#include + +enum nfqnl_msg_types { + NFQNL_MSG_PACKET, /* packet from kernel to userspace */ + NFQNL_MSG_VERDICT, /* verdict from userspace to kernel */ + NFQNL_MSG_CONFIG, /* connect to a particular queue */ + + NFQNL_MSG_MAX +}; + +struct nfqnl_msg_packet_hdr { + u_int32_t packet_id; /* unique ID of packet in queue */ + u_int16_t hw_protocol; /* hw protocol (network order) */ + u_int8_t hook; /* netfilter hook */ +} __attribute__ ((packed)); + +struct nfqnl_msg_packet_hw { + u_int16_t hw_addrlen; + u_int16_t _pad; + u_int8_t hw_addr[8]; +} __attribute__ ((packed)); + +struct nfqnl_msg_packet_timestamp { + u_int64_t sec; + u_int64_t usec; +} __attribute__ ((packed)); + +enum nfqnl_attr_type { + NFQA_UNSPEC, + NFQA_PACKET_HDR, + NFQA_VERDICT_HDR, /* nfqnl_msg_verdict_hrd */ + NFQA_MARK, /* u_int32_t nfmark */ + NFQA_TIMESTAMP, /* nfqnl_msg_packet_timestamp */ + NFQA_IFINDEX_INDEV, /* u_int32_t ifindex */ + NFQA_IFINDEX_OUTDEV, /* u_int32_t ifindex */ + NFQA_HWADDR, /* nfqnl_msg_packet_hw */ + NFQA_PAYLOAD, /* opaque data payload */ + + __NFQA_MAX +}; +#define NFQA_MAX (__NFQA_MAX - 1) + +struct nfqnl_msg_verdict_hdr { + u_int32_t verdict; + u_int32_t id; +} __attribute__ ((packed)); + + +enum nfqnl_msg_config_cmds { + NFQNL_CFG_CMD_NONE, + NFQNL_CFG_CMD_BIND, + NFQNL_CFG_CMD_UNBIND, + NFQNL_CFG_CMD_PF_BIND, + NFQNL_CFG_CMD_PF_UNBIND, +}; + +struct nfqnl_msg_config_cmd { + u_int8_t command; /* nfqnl_msg_config_cmds */ + u_int8_t _pad; + u_int16_t pf; /* AF_xxx for PF_[UN]BIND */ +} __attribute__ ((packed)); + +enum nfqnl_config_mode { + NFQNL_COPY_NONE, + NFQNL_COPY_META, + NFQNL_COPY_PACKET, +}; + +struct nfqnl_msg_config_params { + u_int32_t copy_range; + u_int8_t copy_mode; /* enum nfqnl_config_mode */ +} __attribute__ ((packed)); + + +enum nfqnl_attr_config { + NFQA_CFG_UNSPEC, + NFQA_CFG_CMD, /* nfqnl_msg_config_cmd */ + NFQA_CFG_PARAMS, /* nfqnl_msg_config_params */ + __NFQA_CFG_MAX +}; + +#endif /* _NFNETLINK_QUEUE_H */ diff --git a/include/linux/netfilter_ipv4/ipt_NFQUEUE.h b/include/linux/netfilter_ipv4/ipt_NFQUEUE.h new file mode 100644 index 000000000000..b5b2943b0c66 --- /dev/null +++ b/include/linux/netfilter_ipv4/ipt_NFQUEUE.h @@ -0,0 +1,16 @@ +/* iptables module for using NFQUEUE mechanism + * + * (C) 2005 Harald Welte + * + * This software is distributed under GNU GPL v2, 1991 + * +*/ +#ifndef _IPT_NFQ_TARGET_H +#define _IPT_NFQ_TARGET_H + +/* target info */ +struct ipt_NFQ_info { + u_int16_t queuenum; +}; + +#endif /* _IPT_DSCP_TARGET_H */ -- cgit v1.2.3 From 32519f11d38ea8f4f60896763bacec7db1760f9c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 19:50:02 -0700 Subject: [INET]: Introduce inet_sk_rebuild_header From tcp_v4_rebuild_header, that already was pretty generic, I only needed to use sk->sk_protocol instead of the hardcoded IPPROTO_TCP and establish the requirement that INET transport layer protocols that want to use this function map TCP_SYN_SENT to its equivalent state. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/ip.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ip.h b/include/linux/ip.h index 31e7cedd9f84..33e8a19a1a0f 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -196,6 +196,8 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to, #endif #endif +extern int inet_sk_rebuild_header(struct sock *sk); + struct iphdr { #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 ihl:4, -- cgit v1.2.3 From 838ab6364956d9bdcefe84712de1621cf20a40b3 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:50:45 -0700 Subject: [NETFILTER]: Add refcounting and /proc/net/netfilter interface to nfnetlink_queue Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink_queue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h index edb463a87eb4..e142b0ff7c08 100644 --- a/include/linux/netfilter/nfnetlink_queue.h +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -81,5 +81,6 @@ enum nfqnl_attr_config { NFQA_CFG_PARAMS, /* nfqnl_msg_config_params */ __NFQA_CFG_MAX }; +#define NFQA_CFG_MAX (__NFQA_CFG_MAX-1) #endif /* _NFNETLINK_QUEUE_H */ -- cgit v1.2.3 From 608c8e4f7b6e61cc783283e9dff8a465a5ad59bb Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:58:27 -0700 Subject: [NETFILTER]: Extend netfilter logging API This patch is in preparation to nfnetlink_log: - loggers now have to register struct nf_logger instead of nf_logfn - nf_log_unregister() replaced by nf_log_unregister_pf() and nf_log_unregister_logger() - add comment to ip[6]t_LOG.h to assure nobody redefines flags - add /proc/net/netfilter/nf_log to tell user which logger is currently registered for which address family - if user has configured logging, but no logging backend (logger) is available, always spit a message to syslog, not just the first time. - split ip[6]t_LOG.c into two parts: Backend: Always try to register as logger for the respective address family Frontend: Always log via nf_log_packet() API - modify all users of nf_log_packet() to accomodate additional argument Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter.h | 48 ++++++++++++++++++++++++++++++--- include/linux/netfilter_ipv4/ipt_LOG.h | 1 + include/linux/netfilter_ipv6/ip6t_LOG.h | 1 + 3 files changed, 47 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 711e05f33d68..815583af06c2 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -114,15 +114,51 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg); extern struct list_head nf_hooks[NPROTO][NF_MAX_HOOKS]; -typedef void nf_logfn(unsigned int hooknum, +/* those NF_LOG_* defines and struct nf_loginfo are legacy definitios that will + * disappear once iptables is replaced with pkttables. Please DO NOT use them + * for any new code! */ +#define NF_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ +#define NF_LOG_TCPOPT 0x02 /* Log TCP options */ +#define NF_LOG_IPOPT 0x04 /* Log IP options */ +#define NF_LOG_UID 0x08 /* Log UID owning local socket */ +#define NF_LOG_MASK 0x0f + +#define NF_LOG_TYPE_LOG 0x01 +#define NF_LOG_TYPE_ULOG 0x02 + +struct nf_loginfo { + u_int8_t type; + union { + struct { + u_int32_t copy_len; + u_int16_t group; + u_int16_t qthreshold; + } ulog; + struct { + u_int8_t level; + u_int8_t logflags; + } log; + } u; +}; + +typedef void nf_logfn(unsigned int pf, + unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct nf_loginfo *li, const char *prefix); +struct nf_logger { + struct module *me; + nf_logfn *logfn; + char *name; +}; + /* Function to register/unregister log function. */ -int nf_log_register(int pf, nf_logfn *logfn); -void nf_log_unregister(int pf, nf_logfn *logfn); +int nf_log_register(int pf, struct nf_logger *logger); +void nf_log_unregister_pf(int pf); +void nf_log_unregister_logger(struct nf_logger *logger); /* Calls the registered backend logging function */ void nf_log_packet(int pf, @@ -130,6 +166,7 @@ void nf_log_packet(int pf, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + struct nf_loginfo *li, const char *fmt, ...); /* Activate hook; either okfn or kfree_skb called, unless a hook @@ -221,6 +258,11 @@ struct nf_queue_rerouter { extern int nf_register_queue_rerouter(int pf, struct nf_queue_rerouter *rer); extern int nf_unregister_queue_rerouter(int pf); +#ifdef CONFIG_PROC_FS +#include +extern struct proc_dir_entry *proc_net_netfilter; +#endif + #else /* !CONFIG_NETFILTER */ #define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb) static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} diff --git a/include/linux/netfilter_ipv4/ipt_LOG.h b/include/linux/netfilter_ipv4/ipt_LOG.h index d25f782e57d1..22d16177319b 100644 --- a/include/linux/netfilter_ipv4/ipt_LOG.h +++ b/include/linux/netfilter_ipv4/ipt_LOG.h @@ -1,6 +1,7 @@ #ifndef _IPT_LOG_H #define _IPT_LOG_H +/* make sure not to change this without changing netfilter.h:NF_LOG_* (!) */ #define IPT_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ #define IPT_LOG_TCPOPT 0x02 /* Log TCP options */ #define IPT_LOG_IPOPT 0x04 /* Log IP options */ diff --git a/include/linux/netfilter_ipv6/ip6t_LOG.h b/include/linux/netfilter_ipv6/ip6t_LOG.h index 42996a43bb39..9008ff5c40ae 100644 --- a/include/linux/netfilter_ipv6/ip6t_LOG.h +++ b/include/linux/netfilter_ipv6/ip6t_LOG.h @@ -1,6 +1,7 @@ #ifndef _IP6T_LOG_H #define _IP6T_LOG_H +/* make sure not to change this without changing netfilter.h:NF_LOG_* (!) */ #define IP6T_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ #define IP6T_LOG_TCPOPT 0x02 /* Log TCP options */ #define IP6T_LOG_IPOPT 0x04 /* Log IP options */ -- cgit v1.2.3 From 0597f2680d666a3bcf101ac0c771ba7e50016bbd Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 19:58:39 -0700 Subject: [NETFILTER]: Add new "nfnetlink_log" userspace packet logging facility This is a generic (layer3 independent) version of what ipt_ULOG is already doing for IPv4 today. ipt_ULOG, ebt_ulog and finally also ip[6]t_LOG will be deprecated by this mechanism in the long term. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink_log.h | 85 +++++++++++++++++++++++++++++++++ 1 file changed, 85 insertions(+) create mode 100644 include/linux/netfilter/nfnetlink_log.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_log.h b/include/linux/netfilter/nfnetlink_log.h new file mode 100644 index 000000000000..420ff4625cbf --- /dev/null +++ b/include/linux/netfilter/nfnetlink_log.h @@ -0,0 +1,85 @@ +#ifndef _NFNETLINK_LOG_H +#define _NFNETLINK_LOG_H + +/* This file describes the netlink messages (i.e. 'protocol packets'), + * and not any kind of function definitions. It is shared between kernel and + * userspace. Don't put kernel specific stuff in here */ + +#include + +enum nfulnl_msg_types { + NFULNL_MSG_PACKET, /* packet from kernel to userspace */ + NFULNL_MSG_CONFIG, /* connect to a particular queue */ + + NFULNL_MSG_MAX +}; + +struct nfulnl_msg_packet_hdr { + u_int16_t hw_protocol; /* hw protocol (network order) */ + u_int8_t hook; /* netfilter hook */ + u_int8_t _pad; +} __attribute__ ((packed)); + +struct nfulnl_msg_packet_hw { + u_int16_t hw_addrlen; + u_int16_t _pad; + u_int8_t hw_addr[8]; +} __attribute__ ((packed)); + +struct nfulnl_msg_packet_timestamp { + u_int64_t sec; + u_int64_t usec; +} __attribute__ ((packed)); + +#define NFULNL_PREFIXLEN 30 /* just like old log target */ + +enum nfulnl_attr_type { + NFULA_UNSPEC, + NFULA_PACKET_HDR, + NFULA_MARK, /* u_int32_t nfmark */ + NFULA_TIMESTAMP, /* nfulnl_msg_packet_timestamp */ + NFULA_IFINDEX_INDEV, /* u_int32_t ifindex */ + NFULA_IFINDEX_OUTDEV, /* u_int32_t ifindex */ + NFULA_HWADDR, /* nfulnl_msg_packet_hw */ + NFULA_PAYLOAD, /* opaque data payload */ + NFULA_PREFIX, /* string prefix */ + NFULA_UID, /* user id of socket */ + + __NFULA_MAX +}; +#define NFULA_MAX (__NFULA_MAX - 1) + +enum nfulnl_msg_config_cmds { + NFULNL_CFG_CMD_NONE, + NFULNL_CFG_CMD_BIND, + NFULNL_CFG_CMD_UNBIND, + NFULNL_CFG_CMD_PF_BIND, + NFULNL_CFG_CMD_PF_UNBIND, +}; + +struct nfulnl_msg_config_cmd { + u_int8_t command; /* nfulnl_msg_config_cmds */ +} __attribute__ ((packed)); + +struct nfulnl_msg_config_mode { + u_int32_t copy_range; + u_int8_t copy_mode; + u_int8_t _pad; +} __attribute__ ((packed)); + +enum nfulnl_attr_config { + NFULA_CFG_UNSPEC, + NFULA_CFG_CMD, /* nfulnl_msg_config_cmd */ + NFULA_CFG_MODE, /* nfulnl_msg_config_mode */ + NFULA_CFG_NLBUFSIZ, /* u_int32_t buffer size */ + NFULA_CFG_TIMEOUT, /* u_int32_t in 1/100 s */ + NFULA_CFG_QTHRESH, /* u_int32_t */ + __NFULA_CFG_MAX +}; +#define NFULA_CFG_MAX (__NFULA_CFG_MAX -1) + +#define NFULNL_COPY_NONE 0x00 +#define NFULNL_COPY_META 0x01 +#define NFULNL_COPY_PACKET 0x02 + +#endif /* _NFNETLINK_LOG_H */ -- cgit v1.2.3 From 0f7ff9274e72fd254fbd1ab117bbc1db6e7cdb34 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 19:59:44 -0700 Subject: [INET]: Just rename the TCP hashtable functions/structs to inet_ This is to break down the complexity of the series of patches, making it very clear that this one just does: 1. renames tcp_ prefixed hashtable functions and data structures that were already mostly generic to inet_ to share it with DCCP and other INET transport protocols. 2. Removes not used functions (__tb_head & tb_head) 3. Removes some leftover prototypes in the headers (tcp_bucket_unlock & tcp_v4_build_header) Next changesets will move tcp_sk(sk)->bind_hash to inet_sock so that we can make functions such as tcp_inherit_port, __tcp_inherit_port, tcp_v4_get_port, __tcp_put_port, generic and get others like tcp_destroy_sock closer to generic (tcp_orphan_count will go to sk->sk_prot to allow this). Eventually most of these functions will be used passing the transport protocol inet_hashinfo structure. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e4fd82e42104..ec580a560e8c 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -258,7 +258,7 @@ struct tcp_sock { __u32 snd_sml; /* Last byte of the most recently transmitted small packet */ __u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ __u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ - struct tcp_bind_bucket *bind_hash; + struct inet_bind_bucket *bind_hash; /* Delayed ACK control data */ struct { __u8 pending; /* ACK is pending */ -- cgit v1.2.3 From a55ebcc4c4532107ad9eee1c9bb698ab5f12c00f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:01:14 -0700 Subject: [INET]: Move bind_hash from tcp_sk to inet_sk This should really be in a inet_connection_sock, but I'm leaving it for a later optimization, when some more fields common to INET transport protocols now in tcp_sk or inet_sk will be chunked out into inet_connection_sock, for now its better to concentrate on getting the changes in the core merged to leave the DCCP tree with only DCCP specific code. Next changesets will take advantage of this move to generalise things like tcp_bind_hash, tcp_put_port, tcp_inherit_port, making the later receive a inet_hashinfo parameter, and even __tcp_tw_hashdance, etc in the future, when tcp_tw_bucket gets transformed into the struct timewait_sock hierarchy. tcp_destroy_sock also is eligible as soon as tcp_orphan_count gets moved to sk_prot. A cascade of incremental changes will ultimately make the tcp_lookup functions be fully generic. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/ip.h | 2 ++ include/linux/tcp.h | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ip.h b/include/linux/ip.h index 33e8a19a1a0f..2c54bbd3da76 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -128,6 +128,7 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) return (struct inet_request_sock *)sk; } +struct inet_bind_bucket; struct ipv6_pinfo; struct inet_sock { @@ -157,6 +158,7 @@ struct inet_sock { int mc_index; /* Multicast device index */ __u32 mc_addr; struct ip_mc_socklist *mc_list; /* Group array */ + struct inet_bind_bucket *bind_hash; /* * Following members are used to retain the infomation to build * an ip header on each ip fragmentation while the socket is corked. diff --git a/include/linux/tcp.h b/include/linux/tcp.h index ec580a560e8c..e70ab19652db 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -258,7 +258,6 @@ struct tcp_sock { __u32 snd_sml; /* Last byte of the most recently transmitted small packet */ __u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ __u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ - struct inet_bind_bucket *bind_hash; /* Delayed ACK control data */ struct { __u8 pending; /* ACK is pending */ -- cgit v1.2.3 From a86888b925299330053d20e0eba03ac4d2648c4b Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 9 Aug 2005 20:02:13 -0700 Subject: [NETFILTER]: Fix multiple problems with the conntrack event cache refcnt underflow: the reference count is decremented when a conntrack entry is removed from the hash but it is not incremented when entering new entries. missing protection of process context against softirq context: all cache operations need to locally disable softirqs to avoid races. Additionally the event cache can't be initialized when a packet enteres the conntrack code but needs to be initialized whenever we cache an event and the stored conntrack entry doesn't match the current one. incorrect flushing of the event cache in ip_ct_iterate_cleanup: without real locking we can't flush the cache for different CPUs without incurring races. The cache for different CPUs can only be flushed when no packets are going through the code. ip_ct_iterate_cleanup doesn't need to drop all references, so flushing is moved to the cleanup path. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack.h | 29 +++++++++++------------- include/linux/netfilter_ipv4/ip_conntrack_core.h | 14 ++++-------- 2 files changed, 18 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index ff2c1c6001f9..088742befe49 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -411,6 +411,7 @@ struct ip_conntrack_stat #ifdef CONFIG_IP_NF_CONNTRACK_EVENTS #include +#include struct ip_conntrack_ecache { struct ip_conntrack *ct; @@ -445,26 +446,24 @@ ip_conntrack_expect_unregister_notifier(struct notifier_block *nb) return notifier_chain_unregister(&ip_conntrack_expect_chain, nb); } +extern void ip_ct_deliver_cached_events(const struct ip_conntrack *ct); +extern void __ip_ct_event_cache_init(struct ip_conntrack *ct); + static inline void ip_conntrack_event_cache(enum ip_conntrack_events event, const struct sk_buff *skb) { - struct ip_conntrack_ecache *ecache = - &__get_cpu_var(ip_conntrack_ecache); - - if (unlikely((struct ip_conntrack *) skb->nfct != ecache->ct)) { - if (net_ratelimit()) { - printk(KERN_ERR "ctevent: skb->ct != ecache->ct !!!\n"); - dump_stack(); - } - } + struct ip_conntrack *ct = (struct ip_conntrack *)skb->nfct; + struct ip_conntrack_ecache *ecache; + + local_bh_disable(); + ecache = &__get_cpu_var(ip_conntrack_ecache); + if (ct != ecache->ct) + __ip_ct_event_cache_init(ct); ecache->events |= event; + local_bh_enable(); } -extern void -ip_conntrack_deliver_cached_events_for(const struct ip_conntrack *ct); -extern void ip_conntrack_event_cache_init(const struct sk_buff *skb); - static inline void ip_conntrack_event(enum ip_conntrack_events event, struct ip_conntrack *ct) { @@ -483,9 +482,7 @@ static inline void ip_conntrack_event_cache(enum ip_conntrack_events event, const struct sk_buff *skb) {} static inline void ip_conntrack_event(enum ip_conntrack_events event, struct ip_conntrack *ct) {} -static inline void ip_conntrack_deliver_cached_events_for( - struct ip_conntrack *ct) {} -static inline void ip_conntrack_event_cache_init(const struct sk_buff *skb) {} +static inline void ip_ct_deliver_cached_events(const struct ip_conntrack *ct) {} static inline void ip_conntrack_expect_event(enum ip_conntrack_expect_events event, struct ip_conntrack_expect *exp) {} diff --git a/include/linux/netfilter_ipv4/ip_conntrack_core.h b/include/linux/netfilter_ipv4/ip_conntrack_core.h index fbf6c3e41647..dc4d2a0575de 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_core.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_core.h @@ -44,18 +44,14 @@ static inline int ip_conntrack_confirm(struct sk_buff **pskb) struct ip_conntrack *ct = (struct ip_conntrack *)(*pskb)->nfct; int ret = NF_ACCEPT; - if (ct && !is_confirmed(ct)) - ret = __ip_conntrack_confirm(pskb); - ip_conntrack_deliver_cached_events_for(ct); - + if (ct) { + if (!is_confirmed(ct)) + ret = __ip_conntrack_confirm(pskb); + ip_ct_deliver_cached_events(ct); + } return ret; } -#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS -struct ip_conntrack_ecache; -extern void __ip_ct_deliver_cached_events(struct ip_conntrack_ecache *ec); -#endif - extern void __ip_ct_expect_unlink_destroy(struct ip_conntrack_expect *exp); extern struct list_head *ip_conntrack_hash; -- cgit v1.2.3 From 927ccbcc28dceee29dad876982768cca29738564 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 20:03:40 -0700 Subject: [NETFILTER]: attribute count is an attribute of message type, not subsytem Prior to this patch, every nfnetlink subsystem had to specify it's attribute count. However, in reality the attribute count depends on the message type within the subsystem, not the subsystem itself. This patch moves 'attr_count' from 'struct nfnetlink_subsys' into nfnl_callback to fix this. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 561f9df28808..b0feb2374079 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -85,9 +85,10 @@ struct nfgenmsg { struct nfnl_callback { - kernel_cap_t cap_required; /* capabilities required for this msg */ int (*call)(struct sock *nl, struct sk_buff *skb, struct nlmsghdr *nlh, struct nfattr *cda[], int *errp); + kernel_cap_t cap_required; /* capabilities required for this msg */ + u_int16_t attr_count; /* number of nfattr's */ }; struct nfnetlink_subsystem @@ -95,7 +96,6 @@ struct nfnetlink_subsystem const char *name; __u8 subsys_id; /* nfnetlink subsystem ID */ __u8 cb_count; /* number of callbacks */ - u_int32_t attr_count; /* number of nfattr's */ struct nfnl_callback *cb; /* callback for individual types */ }; -- cgit v1.2.3 From 1444fc559b01aa5d4fedf4ee4f306a9e9cd56f95 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 20:04:07 -0700 Subject: [NETFILTER]: don't use nested attributes for conntrack_expect We used to use nested nfattr structures for ip_conntrack_expect. This is bogus, since ip_conntrack and ip_conntrack_expect are communicated in different netlink message types. both should be encoded at the top level attributes, no extra nesting required. This patch addresses the issue. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink_conntrack.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index fb528e0e3bd9..5c55751c78e4 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -33,7 +33,6 @@ enum ctattr_type { CTA_COUNTERS_ORIG, CTA_COUNTERS_REPLY, CTA_USE, - CTA_EXPECT, CTA_ID, __CTA_MAX }; @@ -103,10 +102,12 @@ enum ctattr_protonat { enum ctattr_expect { CTA_EXPECT_UNSPEC, + CTA_EXPECT_MASTER, CTA_EXPECT_TUPLE, CTA_EXPECT_MASK, CTA_EXPECT_TIMEOUT, CTA_EXPECT_ID, + CTA_EXPECT_HELP_NAME, __CTA_EXPECT_MAX }; #define CTA_EXPECT_MAX (__CTA_EXPECT_MAX - 1) -- cgit v1.2.3 From c752f0739f09b803aed191c4765a3b6650a08653 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:08:28 -0700 Subject: [TCP]: Move the tcp sock states to net/tcp_states.h Lots of places just needs the states, not even linux/tcp.h, where this enum was, needs it. This speeds up development of the refactorings as less sources are rebuilt when things get moved from net/tcp.h. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/tcp.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e70ab19652db..b88fe05fdcbf 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -55,24 +55,6 @@ struct tcphdr { __u16 urg_ptr; }; - -enum { - TCP_ESTABLISHED = 1, - TCP_SYN_SENT, - TCP_SYN_RECV, - TCP_FIN_WAIT1, - TCP_FIN_WAIT2, - TCP_TIME_WAIT, - TCP_CLOSE, - TCP_CLOSE_WAIT, - TCP_LAST_ACK, - TCP_LISTEN, - TCP_CLOSING, /* now a valid state */ - - TCP_MAX_STATES /* Leave at the end! */ -}; - -#define TCP_STATE_MASK 0xF #define TCP_ACTION_FIN (1 << 7) enum { -- cgit v1.2.3 From 8feaf0c0a5488b3d898a9c207eb6678f44ba3f26 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:09:30 -0700 Subject: [INET]: Generalise tcp_tw_bucket, aka TIME_WAIT sockets This paves the way to generalise the rest of the sock ID lookup routines and saves some bytes in TCPv4 TIME_WAIT sockets on distro kernels (where IPv6 is always built as a module): [root@qemu ~]# grep tw_sock /proc/slabinfo tw_sock_TCPv6 0 0 128 31 1 tw_sock_TCP 0 0 96 41 1 [root@qemu ~]# Now if a protocol wants to use the TIME_WAIT generic infrastructure it only has to set the sk_prot->twsk_obj_size field with the size of its inet_timewait_sock derived sock and proto_register will create sk_prot->twsk_slab, for now its only for INET sockets, but we can introduce timewait_sock later if some non INET transport protocolo wants to use this stuff. Next changesets will take advantage of this new infrastructure to generalise even more TCP code. [acme@toy net-2.6.14]$ grep built-in /tmp/before.size /tmp/after.size /tmp/before.size: 188646 11764 5068 205478 322a6 net/ipv4/built-in.o /tmp/after.size: 188144 11764 5068 204976 320b0 net/ipv4/built-in.o [acme@toy net-2.6.14]$ Tested with both IPv4 & IPv6 (::1 (localhost) & ::ffff:172.20.0.1 (qemu host)). Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/ipv6.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++++--- include/linux/tcp.h | 15 +++++++++++++++ 2 files changed, 64 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 6fcd6a0ade24..98fa32316e40 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -308,6 +308,41 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to, #define __ipv6_only_sock(sk) (inet6_sk(sk)->ipv6only) #define ipv6_only_sock(sk) ((sk)->sk_family == PF_INET6 && __ipv6_only_sock(sk)) + +#include + +struct tcp6_timewait_sock { + struct tcp_timewait_sock tw_v6_sk; + struct in6_addr tw_v6_daddr; + struct in6_addr tw_v6_rcv_saddr; +}; + +static inline struct tcp6_timewait_sock *tcp6_twsk(const struct sock *sk) +{ + return (struct tcp6_timewait_sock *)sk; +} + +static inline struct in6_addr *__tcp_v6_rcv_saddr(const struct sock *sk) +{ + return likely(sk->sk_state != TCP_TIME_WAIT) ? + &inet6_sk(sk)->rcv_saddr : &tcp6_twsk(sk)->tw_v6_rcv_saddr; +} + +static inline struct in6_addr *tcp_v6_rcv_saddr(const struct sock *sk) +{ + return sk->sk_family == AF_INET6 ? __tcp_v6_rcv_saddr(sk) : NULL; +} + +static inline int tcp_twsk_ipv6only(const struct sock *sk) +{ + return inet_twsk(sk)->tw_ipv6only; +} + +static inline int tcp_v6_ipv6only(const struct sock *sk) +{ + return likely(sk->sk_state != TCP_TIME_WAIT) ? + ipv6_only_sock(sk) : tcp_twsk_ipv6only(sk); +} #else #define __ipv6_only_sock(sk) 0 #define ipv6_only_sock(sk) 0 @@ -322,8 +357,19 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) return NULL; } -#endif +#define __tcp_v6_rcv_saddr(__sk) NULL +#define tcp_v6_rcv_saddr(__sk) NULL +#define tcp_twsk_ipv6only(__sk) 0 +#define tcp_v6_ipv6only(__sk) 0 +#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ -#endif +#define INET6_MATCH(__sk, __saddr, __daddr, __ports, __dif) \ + (((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ + ((__sk)->sk_family == AF_INET6) && \ + ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr)) && \ + ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr)) && \ + (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) -#endif +#endif /* __KERNEL__ */ + +#endif /* _IPV6_H */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b88fe05fdcbf..5d295b1b3de7 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -179,6 +179,7 @@ struct tcp_info #include #include #include +#include /* This defines a selective acknowledgement block. */ struct tcp_sack_block { @@ -387,6 +388,20 @@ static inline struct tcp_sock *tcp_sk(const struct sock *sk) return (struct tcp_sock *)sk; } +struct tcp_timewait_sock { + struct inet_timewait_sock tw_sk; + __u32 tw_rcv_nxt; + __u32 tw_snd_nxt; + __u32 tw_rcv_wnd; + __u32 tw_ts_recent; + long tw_ts_recent_stamp; +}; + +static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) +{ + return (struct tcp_timewait_sock *)sk; +} + static inline void *tcp_ca(const struct tcp_sock *tp) { return (void *) tp->ca_priv; -- cgit v1.2.3 From 463c84b97f24010a67cd871746d6a7e4c925a5f9 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:10:42 -0700 Subject: [NET]: Introduce inet_connection_sock This creates struct inet_connection_sock, moving members out of struct tcp_sock that are shareable with other INET connection oriented protocols, such as DCCP, that in my private tree already uses most of these members. The functions that operate on these members were renamed, using a inet_csk_ prefix while not being moved yet to a new file, so as to ease the review of these changes. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/ip.h | 2 -- include/linux/ipv6.h | 8 ++++---- include/linux/tcp.h | 39 +++++++-------------------------------- 3 files changed, 11 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ip.h b/include/linux/ip.h index 2c54bbd3da76..33e8a19a1a0f 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -128,7 +128,6 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) return (struct inet_request_sock *)sk; } -struct inet_bind_bucket; struct ipv6_pinfo; struct inet_sock { @@ -158,7 +157,6 @@ struct inet_sock { int mc_index; /* Multicast device index */ __u32 mc_addr; struct ip_mc_socklist *mc_list; /* Group array */ - struct inet_bind_bucket *bind_hash; /* * Following members are used to retain the infomation to build * an ip header on each ip fragmentation while the socket is corked. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 98fa32316e40..88591913c94f 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -333,15 +333,15 @@ static inline struct in6_addr *tcp_v6_rcv_saddr(const struct sock *sk) return sk->sk_family == AF_INET6 ? __tcp_v6_rcv_saddr(sk) : NULL; } -static inline int tcp_twsk_ipv6only(const struct sock *sk) +static inline int inet_twsk_ipv6only(const struct sock *sk) { return inet_twsk(sk)->tw_ipv6only; } -static inline int tcp_v6_ipv6only(const struct sock *sk) +static inline int inet_v6_ipv6only(const struct sock *sk) { return likely(sk->sk_state != TCP_TIME_WAIT) ? - ipv6_only_sock(sk) : tcp_twsk_ipv6only(sk); + ipv6_only_sock(sk) : inet_twsk_ipv6only(sk); } #else #define __ipv6_only_sock(sk) 0 @@ -360,7 +360,7 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) #define __tcp_v6_rcv_saddr(__sk) NULL #define tcp_v6_rcv_saddr(__sk) NULL #define tcp_twsk_ipv6only(__sk) 0 -#define tcp_v6_ipv6only(__sk) 0 +#define inet_v6_ipv6only(__sk) 0 #endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ #define INET6_MATCH(__sk, __saddr, __daddr, __ports, __dif) \ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 5d295b1b3de7..800930fac388 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -177,8 +177,8 @@ struct tcp_info #include #include -#include #include +#include #include /* This defines a selective acknowledgement block. */ @@ -219,8 +219,8 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) } struct tcp_sock { - /* inet_sock has to be the first member of tcp_sock */ - struct inet_sock inet; + /* inet_connection_sock has to be the first member of tcp_sock */ + struct inet_connection_sock inet_conn; int tcp_header_len; /* Bytes of tcp header to send */ /* @@ -241,18 +241,6 @@ struct tcp_sock { __u32 snd_sml; /* Last byte of the most recently transmitted small packet */ __u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ __u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ - /* Delayed ACK control data */ - struct { - __u8 pending; /* ACK is pending */ - __u8 quick; /* Scheduled number of quick acks */ - __u8 pingpong; /* The session is interactive */ - __u8 blocked; /* Delayed ACK was blocked by socket lock*/ - __u32 ato; /* Predicted tick of soft clock */ - unsigned long timeout; /* Currently scheduled timeout */ - __u32 lrcvtime; /* timestamp of last received data packet*/ - __u16 last_seg_size; /* Size of last incoming segment */ - __u16 rcv_mss; /* MSS used for delayed ACK decisions */ - } ack; /* Data for direct copy to user */ struct { @@ -271,8 +259,8 @@ struct tcp_sock { __u16 xmit_size_goal; /* Goal for segmenting output packets */ __u16 ext_header_len; /* Network protocol overhead (IP/IPv6 options) */ __u8 ca_state; /* State of fast-retransmit machine */ - __u8 retransmits; /* Number of unrecovered RTO timeouts. */ + __u8 keepalive_probes; /* num of allowed keep alive probes */ __u16 advmss; /* Advertised MSS */ __u32 window_clamp; /* Maximal window to advertise */ __u32 rcv_ssthresh; /* Current window clamp */ @@ -281,7 +269,7 @@ struct tcp_sock { __u8 reordering; /* Packet reordering metric. */ __u8 frto_counter; /* Number of new acks after RTO */ - __u8 unused; + __u8 nonagle; /* Disable Nagle algorithm? */ __u8 defer_accept; /* User waits for some data after accept() */ /* RTT measurement */ @@ -290,19 +278,13 @@ struct tcp_sock { __u32 mdev_max; /* maximal mdev for the last rtt period */ __u32 rttvar; /* smoothed mdev_max */ __u32 rtt_seq; /* sequence number to update rttvar */ - __u32 rto; /* retransmit timeout */ __u32 packets_out; /* Packets which are "in flight" */ __u32 left_out; /* Packets which leaved network */ __u32 retrans_out; /* Retransmitted packets out */ - __u8 backoff; /* backoff */ /* * Options received (usually on last packet, some only on SYN packets). */ - __u8 nonagle; /* Disable Nagle algorithm? */ - __u8 keepalive_probes; /* num of allowed keep alive probes */ - - __u8 probes_out; /* unanswered 0 window probes */ struct tcp_options_received rx_opt; /* @@ -315,11 +297,6 @@ struct tcp_sock { __u32 snd_cwnd_used; __u32 snd_cwnd_stamp; - /* Two commonly used timers in both sender and receiver paths. */ - unsigned long timeout; - struct timer_list retransmit_timer; /* Resend (no ack) */ - struct timer_list delack_timer; /* Ack delay */ - struct sk_buff_head out_of_order_queue; /* Out of order segments go here */ struct tcp_func *af_specific; /* Operations which are AF_INET{4,6} specific */ @@ -334,7 +311,7 @@ struct tcp_sock { struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */ struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/ - __u8 syn_retries; /* num of allowed syn retries */ + __u8 probes_out; /* unanswered 0 window probes */ __u8 ecn_flags; /* ECN status bits. */ __u16 prior_ssthresh; /* ssthresh saved at recovery start */ __u32 lost_out; /* Lost packets */ @@ -349,14 +326,12 @@ struct tcp_sock { int undo_retrans; /* number of undoable retransmissions. */ __u32 urg_seq; /* Seq of received urgent pointer */ __u16 urg_data; /* Saved octet of OOB data and control flags */ - __u8 pending; /* Scheduled timer event */ __u8 urg_mode; /* In urgent mode */ + /* ONE BYTE HOLE, TRY TO PACK! */ __u32 snd_up; /* Urgent pointer */ __u32 total_retrans; /* Total retransmits for entire connection */ - struct request_sock_queue accept_queue; /* FIFO of established children */ - unsigned int keepalive_time; /* time before keep alive takes place */ unsigned int keepalive_intvl; /* time interval between keep alive probes */ int linger2; -- cgit v1.2.3 From 3f421baa4720b708022f8bcc52a61e5cd6f10bf8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:11:08 -0700 Subject: [NET]: Just move the inet_connection_sock function from tcp sources Completing the previous changeset, this also generalises tcp_v4_synq_add, renaming it to inet_csk_reqsk_queue_hash_add, already geing used in the DCCP tree, which I plan to merge RSN. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/ipv6.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 88591913c94f..777339b68464 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -333,15 +333,10 @@ static inline struct in6_addr *tcp_v6_rcv_saddr(const struct sock *sk) return sk->sk_family == AF_INET6 ? __tcp_v6_rcv_saddr(sk) : NULL; } -static inline int inet_twsk_ipv6only(const struct sock *sk) -{ - return inet_twsk(sk)->tw_ipv6only; -} - static inline int inet_v6_ipv6only(const struct sock *sk) { return likely(sk->sk_state != TCP_TIME_WAIT) ? - ipv6_only_sock(sk) : inet_twsk_ipv6only(sk); + ipv6_only_sock(sk) : inet_twsk(sk)->tw_ipv6only; } #else #define __ipv6_only_sock(sk) 0 -- cgit v1.2.3 From 295f7324ff8d9ea58b4d3ec93b1aaa1d80e048a9 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:11:56 -0700 Subject: [ICSK]: Introduce reqsk_queue_prune from code in tcp_synack_timer With this we're very close to getting all of the current TCP refactorings in my dccp-2.6 tree merged, next changeset will export some functions needed by the current DCCP code and then dccp-2.6.git will be born! Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 800930fac388..620096840744 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -270,7 +270,7 @@ struct tcp_sock { __u8 frto_counter; /* Number of new acks after RTO */ __u8 nonagle; /* Disable Nagle algorithm? */ - __u8 defer_accept; /* User waits for some data after accept() */ + /* ONE BYTE HOLE, TRY TO PACK */ /* RTT measurement */ __u32 srtt; /* smoothed round trip time << 3 */ -- cgit v1.2.3 From c4365c9235f80128c3c3d5993074173941b1c1f0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:12:30 -0700 Subject: [RANDOM]: Introduce secure_dccp_sequence_number Code contributed by Stephen Hemminger. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/random.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index cc6703449916..7b2adb3322d5 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -59,6 +59,8 @@ extern __u32 secure_tcp_sequence_number(__u32 saddr, __u32 daddr, __u16 sport, __u16 dport); extern __u32 secure_tcpv6_sequence_number(__u32 *saddr, __u32 *daddr, __u16 sport, __u16 dport); +extern u64 secure_dccp_sequence_number(__u32 saddr, __u32 daddr, + __u16 sport, __u16 dport); #ifndef MODULE extern struct file_operations random_fops, urandom_fops; -- cgit v1.2.3 From 7c657876b63cb1d8a2ec06f8fc6c37bb8412e66c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:14:34 -0700 Subject: [DCCP]: Initial implementation Development to this point was done on a subversion repository at: http://oops.ghostprotocols.net:81/cgi-bin/viewcvs.cgi/dccp-2.6/ This repository will be kept at this site for the foreseable future, so that interested parties can see the history of this code, attributions, etc. If I ever decide to take this offline I'll provide the full history at some other suitable place. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 432 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/in.h | 1 + include/linux/net.h | 1 + include/linux/socket.h | 1 + 4 files changed, 435 insertions(+) create mode 100644 include/linux/dccp.h (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h new file mode 100644 index 000000000000..e3b4bf7346bb --- /dev/null +++ b/include/linux/dccp.h @@ -0,0 +1,432 @@ +#ifndef _LINUX_DCCP_H +#define _LINUX_DCCP_H + +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +/* FIXME: this is utterly wrong */ +struct sockaddr_dccp { + struct sockaddr_in in; + unsigned int service; +}; + +enum dccp_state { + DCCP_OPEN = TCP_ESTABLISHED, + DCCP_REQUESTING = TCP_SYN_SENT, + DCCP_PARTOPEN = TCP_FIN_WAIT1, /* FIXME: + This mapping is horrible, but TCP has + no matching state for DCCP_PARTOPEN, + as TCP_SYN_RECV is already used by + DCCP_RESPOND, why don't stop using TCP + mapping of states? OK, now we don't use + sk_stream_sendmsg anymore, so doesn't + seem to exist any reason for us to + do the TCP mapping here */ + DCCP_LISTEN = TCP_LISTEN, + DCCP_RESPOND = TCP_SYN_RECV, + DCCP_CLOSING = TCP_CLOSING, + DCCP_TIME_WAIT = TCP_TIME_WAIT, + DCCP_CLOSED = TCP_CLOSE, + DCCP_MAX_STATES = TCP_MAX_STATES, +}; + +#define DCCP_STATE_MASK 0xf +#define DCCP_ACTION_FIN (1<<7) + +enum { + DCCPF_OPEN = TCPF_ESTABLISHED, + DCCPF_REQUESTING = TCPF_SYN_SENT, + DCCPF_PARTOPEN = TCPF_FIN_WAIT1, + DCCPF_LISTEN = TCPF_LISTEN, + DCCPF_RESPOND = TCPF_SYN_RECV, + DCCPF_CLOSING = TCPF_CLOSING, + DCCPF_TIME_WAIT = TCPF_TIME_WAIT, + DCCPF_CLOSED = TCPF_CLOSE, +}; + +/** + * struct dccp_hdr - generic part of DCCP packet header + * + * @dccph_sport - Relevant port on the endpoint that sent this packet + * @dccph_dport - Relevant port on the other endpoint + * @dccph_doff - Data Offset from the start of the DCCP header, in 32-bit words + * @dccph_ccval - Used by the HC-Sender CCID + * @dccph_cscov - Parts of the packet that are covered by the Checksum field + * @dccph_checksum - Internet checksum, depends on dccph_cscov + * @dccph_x - 0 = 24 bit sequence number, 1 = 48 + * @dccph_type - packet type, see DCCP_PKT_ prefixed macros + * @dccph_seq - sequence number high or low order 24 bits, depends on dccph_x + */ +struct dccp_hdr { + __u16 dccph_sport, + dccph_dport; + __u8 dccph_doff; +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u8 dccph_cscov:4, + dccph_ccval:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u8 dccph_ccval:4, + dccph_cscov:4; +#else +#error "Adjust your defines" +#endif + __u16 dccph_checksum; +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u32 dccph_x:1, + dccph_type:4, + dccph_reserved:3, + dccph_seq:24; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u32 dccph_reserved:3, + dccph_type:4, + dccph_x:1, + dccph_seq:24; +#else +#error "Adjust your defines" +#endif +}; + +static inline struct dccp_hdr *dccp_hdr(const struct sk_buff *skb) +{ + return (struct dccp_hdr *)skb->h.raw; +} + +/** + * struct dccp_hdr_ext - the low bits of a 48 bit seq packet + * + * @dccph_seq_low - low 24 bits of a 48 bit seq packet + */ +struct dccp_hdr_ext { + __u32 dccph_seq_low; +}; + +static inline struct dccp_hdr_ext *dccp_hdrx(const struct sk_buff *skb) +{ + return (struct dccp_hdr_ext *)(skb->h.raw + sizeof(struct dccp_hdr)); +} + +static inline unsigned int dccp_basic_hdr_len(const struct sk_buff *skb) +{ + const struct dccp_hdr *dh = dccp_hdr(skb); + return sizeof(*dh) + (dh->dccph_x ? sizeof(struct dccp_hdr_ext) : 0); +} + +static inline __u64 dccp_hdr_seq(const struct sk_buff *skb) +{ + const struct dccp_hdr *dh = dccp_hdr(skb); +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u64 seq_nr = ntohl(dh->dccph_seq << 8); +#elif defined(__BIG_ENDIAN_BITFIELD) + __u64 seq_nr = ntohl(dh->dccph_seq); +#else +#error "Adjust your defines" +#endif + + if (dh->dccph_x != 0) + seq_nr = (seq_nr << 32) + ntohl(dccp_hdrx(skb)->dccph_seq_low); + + return seq_nr; +} + +/** + * struct dccp_hdr_request - Conection initiation request header + * + * @dccph_req_service - Service to which the client app wants to connect + * @dccph_req_options - list of options (must be a multiple of 32 bits + */ +struct dccp_hdr_request { + __u32 dccph_req_service; +}; + +static inline struct dccp_hdr_request *dccp_hdr_request(struct sk_buff *skb) +{ + return (struct dccp_hdr_request *)(skb->h.raw + dccp_basic_hdr_len(skb)); +} + +/** + * struct dccp_hdr_ack_bits - acknowledgment bits common to most packets + * + * @dccph_resp_ack_nr_high - 48 bit ack number high order bits, contains GSR + * @dccph_resp_ack_nr_low - 48 bit ack number low order bits, contains GSR + */ +struct dccp_hdr_ack_bits { + __u32 dccph_reserved1:8, + dccph_ack_nr_high:24; + __u32 dccph_ack_nr_low; +}; + +static inline struct dccp_hdr_ack_bits *dccp_hdr_ack_bits(const struct sk_buff *skb) +{ + return (struct dccp_hdr_ack_bits *)(skb->h.raw + dccp_basic_hdr_len(skb)); +} + +static inline u64 dccp_hdr_ack_seq(const struct sk_buff *skb) +{ + const struct dccp_hdr_ack_bits *dhack = dccp_hdr_ack_bits(skb); +#if defined(__LITTLE_ENDIAN_BITFIELD) + return (((u64)ntohl(dhack->dccph_ack_nr_high << 8)) << 32) + ntohl(dhack->dccph_ack_nr_low); +#elif defined(__BIG_ENDIAN_BITFIELD) + return (((u64)ntohl(dhack->dccph_ack_nr_high)) << 32) + ntohl(dhack->dccph_ack_nr_low); +#else +#error "Adjust your defines" +#endif +} + +/** + * struct dccp_hdr_response - Conection initiation response header + * + * @dccph_resp_ack_nr_high - 48 bit ack number high order bits, contains GSR + * @dccph_resp_ack_nr_low - 48 bit ack number low order bits, contains GSR + * @dccph_resp_service - Echoes the Service Code on a received DCCP-Request + * @dccph_resp_options - list of options (must be a multiple of 32 bits + */ +struct dccp_hdr_response { + struct dccp_hdr_ack_bits dccph_resp_ack; + __u32 dccph_resp_service; +}; + +static inline struct dccp_hdr_response *dccp_hdr_response(struct sk_buff *skb) +{ + return (struct dccp_hdr_response *)(skb->h.raw + dccp_basic_hdr_len(skb)); +} + +/** + * struct dccp_hdr_reset - Unconditionally shut down a connection + * + * @dccph_reset_service - Echoes the Service Code on a received DCCP-Request + * @dccph_reset_options - list of options (must be a multiple of 32 bits + */ +struct dccp_hdr_reset { + struct dccp_hdr_ack_bits dccph_reset_ack; + __u8 dccph_reset_code, + dccph_reset_data[3]; +}; + +static inline struct dccp_hdr_reset *dccp_hdr_reset(struct sk_buff *skb) +{ + return (struct dccp_hdr_reset *)(skb->h.raw + dccp_basic_hdr_len(skb)); +} + +enum dccp_pkt_type { + DCCP_PKT_REQUEST = 0, + DCCP_PKT_RESPONSE, + DCCP_PKT_DATA, + DCCP_PKT_ACK, + DCCP_PKT_DATAACK, + DCCP_PKT_CLOSEREQ, + DCCP_PKT_CLOSE, + DCCP_PKT_RESET, + DCCP_PKT_SYNC, + DCCP_PKT_SYNCACK, + DCCP_PKT_INVALID, +}; + +#define DCCP_NR_PKT_TYPES DCCP_PKT_INVALID + +static inline unsigned int dccp_packet_hdr_len(const __u8 type) +{ + if (type == DCCP_PKT_DATA) + return 0; + if (type == DCCP_PKT_DATAACK || + type == DCCP_PKT_ACK || + type == DCCP_PKT_SYNC || + type == DCCP_PKT_SYNCACK || + type == DCCP_PKT_CLOSE || + type == DCCP_PKT_CLOSEREQ) + return sizeof(struct dccp_hdr_ack_bits); + if (type == DCCP_PKT_REQUEST) + return sizeof(struct dccp_hdr_request); + if (type == DCCP_PKT_RESPONSE) + return sizeof(struct dccp_hdr_response); + return sizeof(struct dccp_hdr_reset); +} + +static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) +{ + return dccp_basic_hdr_len(skb) + + dccp_packet_hdr_len(dccp_hdr(skb)->dccph_type); +} + +enum dccp_reset_codes { + DCCP_RESET_CODE_UNSPECIFIED = 0, + DCCP_RESET_CODE_CLOSED, + DCCP_RESET_CODE_ABORTED, + DCCP_RESET_CODE_NO_CONNECTION, + DCCP_RESET_CODE_PACKET_ERROR, + DCCP_RESET_CODE_OPTION_ERROR, + DCCP_RESET_CODE_MANDATORY_ERROR, + DCCP_RESET_CODE_CONNECTION_REFUSED, + DCCP_RESET_CODE_BAD_SERVICE_CODE, + DCCP_RESET_CODE_TOO_BUSY, + DCCP_RESET_CODE_BAD_INIT_COOKIE, + DCCP_RESET_CODE_AGGRESSION_PENALTY, +}; + +/* DCCP options */ +enum { + DCCPO_PADDING = 0, + DCCPO_MANDATORY = 1, + DCCPO_MIN_RESERVED = 3, + DCCPO_MAX_RESERVED = 31, + DCCPO_NDP_COUNT = 37, + DCCPO_ACK_VECTOR_0 = 38, + DCCPO_ACK_VECTOR_1 = 39, + DCCPO_TIMESTAMP = 41, + DCCPO_TIMESTAMP_ECHO = 42, + DCCPO_ELAPSED_TIME = 43, + DCCPO_MAX = 45, + DCCPO_MIN_CCID_SPECIFIC = 128, + DCCPO_MAX_CCID_SPECIFIC = 255, +}; + +/* DCCP features */ +enum { + DCCPF_RESERVED = 0, + DCCPF_SEQUENCE_WINDOW = 3, + DCCPF_SEND_ACK_VECTOR = 6, + DCCPF_SEND_NDP_COUNT = 7, + /* 10-127 reserved */ + DCCPF_MIN_CCID_SPECIFIC = 128, + DCCPF_MAX_CCID_SPECIFIC = 255, +}; + +/* initial values for each feature */ +#define DCCPF_INITIAL_SEQUENCE_WINDOW 100 +/* FIXME: for now we're using CCID 3 (TFRC) */ +#define DCCPF_INITIAL_CCID 3 +#define DCCPF_INITIAL_SEND_ACK_VECTOR 0 +/* FIXME: for now we're default to 1 but it should really be 0 */ +#define DCCPF_INITIAL_SEND_NDP_COUNT 1 + +#define DCCP_NDP_LIMIT 0xFFFFFF + +/** + * struct dccp_options - option values for a DCCP connection + * @dccpo_sequence_window - Sequence Window Feature (section 7.5.2) + * @dccpo_ccid - Congestion Control Id (CCID) (section 10) + * @dccpo_send_ack_vector - Send Ack Vector Feature (section 11.5) + * @dccpo_send_ndp_count - Send NDP Count Feature (7.7.2) + */ +struct dccp_options { + __u64 dccpo_sequence_window; + __u8 dccpo_ccid; + __u8 dccpo_send_ack_vector; + __u8 dccpo_send_ndp_count; +}; + +extern void __dccp_options_init(struct dccp_options *dccpo); +extern void dccp_options_init(struct dccp_options *dccpo); +extern int dccp_parse_options(struct sock *sk, struct sk_buff *skb); + +struct dccp_request_sock { + struct inet_request_sock dreq_inet_rsk; + __u64 dreq_iss; + __u64 dreq_isr; + __u32 dreq_service; +}; + +static inline struct dccp_request_sock *dccp_rsk(const struct request_sock *req) +{ + return (struct dccp_request_sock *)req; +} + +/* Read about the ECN nonce to see why it is 253 */ +#define DCCP_MAX_ACK_VECTOR_LEN 253 + +struct dccp_options_received { + u32 dccpor_ndp:24, + dccpor_ack_vector_len:8; + u32 dccpor_ack_vector_idx:10; + /* 22 bits hole, try to pack */ + u32 dccpor_timestamp; + u32 dccpor_timestamp_echo; + u32 dccpor_elapsed_time; +}; + +struct ccid; + +enum dccp_role { + DCCP_ROLE_UNDEFINED, + DCCP_ROLE_LISTEN, + DCCP_ROLE_CLIENT, + DCCP_ROLE_SERVER, +}; + +/** + * struct dccp_sock - DCCP socket state + * + * @dccps_swl - sequence number window low + * @dccps_swh - sequence number window high + * @dccps_awl - acknowledgement number window low + * @dccps_awh - acknowledgement number window high + * @dccps_iss - initial sequence number sent + * @dccps_isr - initial sequence number received + * @dccps_osr - first OPEN sequence number received + * @dccps_gss - greatest sequence number sent + * @dccps_gsr - greatest valid sequence number received + * @dccps_gar - greatest valid ack number received on a non-Sync; initialized to %dccps_iss + * @dccps_timestamp_time - time of latest TIMESTAMP option + * @dccps_timestamp_echo - latest timestamp received on a TIMESTAMP option + * @dccps_ext_header_len - network protocol overhead (IP/IPv6 options) + * @dccps_pmtu_cookie - Last pmtu seen by socket + * @dccps_avg_packet_size - FIXME: has to be set by the app thru some setsockopt or ioctl, CCID3 uses it + * @dccps_role - Role of this sock, one of %dccp_role + * @dccps_ndp_count - number of Non Data Packets since last data packet + * @dccps_hc_rx_ackpkts - receiver half connection acked packets + */ +struct dccp_sock { + /* inet_connection_sock has to be the first member of dccp_sock */ + struct inet_connection_sock dccps_inet_connection; + __u64 dccps_swl; + __u64 dccps_swh; + __u64 dccps_awl; + __u64 dccps_awh; + __u64 dccps_iss; + __u64 dccps_isr; + __u64 dccps_osr; + __u64 dccps_gss; + __u64 dccps_gsr; + __u64 dccps_gar; + unsigned long dccps_service; + unsigned long dccps_timestamp_time; + __u32 dccps_timestamp_echo; + __u32 dccps_avg_packet_size; + unsigned long dccps_ndp_count; + __u16 dccps_ext_header_len; + __u32 dccps_pmtu_cookie; + __u32 dccps_mss_cache; + struct dccp_options dccps_options; + struct dccp_ackpkts *dccps_hc_rx_ackpkts; + void *dccps_hc_rx_ccid_private; + void *dccps_hc_tx_ccid_private; + struct ccid *dccps_hc_rx_ccid; + struct ccid *dccps_hc_tx_ccid; + struct dccp_options_received dccps_options_received; + enum dccp_role dccps_role:2; +}; + +static inline struct dccp_sock *dccp_sk(const struct sock *sk) +{ + return (struct dccp_sock *)sk; +} + +static inline const char *dccp_role(const struct sock *sk) +{ + switch (dccp_sk(sk)->dccps_role) { + case DCCP_ROLE_UNDEFINED: return "undefined"; + case DCCP_ROLE_LISTEN: return "listen"; + case DCCP_ROLE_SERVER: return "server"; + case DCCP_ROLE_CLIENT: return "client"; + } + return NULL; +} + +#endif /* _LINUX_DCCP_H */ diff --git a/include/linux/in.h b/include/linux/in.h index fb88c66d748d..ba355384016a 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -32,6 +32,7 @@ enum { IPPROTO_PUP = 12, /* PUP protocol */ IPPROTO_UDP = 17, /* User Datagram Protocol */ IPPROTO_IDP = 22, /* XNS IDP protocol */ + IPPROTO_DCCP = 33, /* Datagram Congestion Control Protocol */ IPPROTO_RSVP = 46, /* RSVP protocol */ IPPROTO_GRE = 47, /* Cisco GRE tunnels (rfc 1701,1702) */ diff --git a/include/linux/net.h b/include/linux/net.h index 39906619b9d7..5f8b632ff653 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -84,6 +84,7 @@ enum sock_type { SOCK_RAW = 3, SOCK_RDM = 4, SOCK_SEQPACKET = 5, + SOCK_DCCP = 6, SOCK_PACKET = 10, }; diff --git a/include/linux/socket.h b/include/linux/socket.h index a5c7d96e4d2e..ddf22559f484 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -271,6 +271,7 @@ struct ucred { #define SOL_IRDA 266 #define SOL_NETBEUI 267 #define SOL_LLC 268 +#define SOL_DCCP 269 /* IPX options */ #define IPX_TYPE 1 -- cgit v1.2.3 From 74459dc7bacda04d14626d239c8f5c4dac22560d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:15:51 -0700 Subject: [LIST]: Introduce list_for_each_entry_safe_continue Used in the dccp CCID3 code, that is going to be submitted RSN. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/list.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index aab2db21b013..597094e0fdb5 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -418,6 +418,19 @@ static inline void list_splice_init(struct list_head *list, &pos->member != (head); \ pos = n, n = list_entry(n->member.next, typeof(*n), member)) +/** + * list_for_each_entry_safe_continue - iterate over list of given type + * continuing after existing point safe against removal of list entry + * @pos: the type * to use as a loop counter. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + */ +#define list_for_each_entry_safe_continue(pos, n, head, member) \ + for (pos = n, n = list_entry(n->member.next, typeof(*n), member); \ + &pos->member != (head); \ + pos = n, n = list_entry(n->member.next, typeof(*n), member)) + /** * list_for_each_rcu - iterate over an rcu-protected list * @pos: the &struct list_head to use as a loop counter. -- cgit v1.2.3 From fbcd923c3e0c8ec9e4ed64f5a4e5766807b32729 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 20:22:10 -0700 Subject: [NETFILTER]: add correct bridging support to nfnetlink_{queue,log} This patch adds support for passing the real 'physical' device ifindex down to userspace via nfnetlink_log and nfnetlink_queue. This feature basically obsoletes net/bridge/netfilter/ebt_ulog.c, and it is likely ebt_ulog.c will die with one of the next couple of patches. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink_log.h | 2 ++ include/linux/netfilter/nfnetlink_queue.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_log.h b/include/linux/netfilter/nfnetlink_log.h index 420ff4625cbf..a61836a083e7 100644 --- a/include/linux/netfilter/nfnetlink_log.h +++ b/include/linux/netfilter/nfnetlink_log.h @@ -40,6 +40,8 @@ enum nfulnl_attr_type { NFULA_TIMESTAMP, /* nfulnl_msg_packet_timestamp */ NFULA_IFINDEX_INDEV, /* u_int32_t ifindex */ NFULA_IFINDEX_OUTDEV, /* u_int32_t ifindex */ + NFULA_IFINDEX_PHYSINDEV, /* u_int32_t ifindex */ + NFULA_IFINDEX_PHYSOUTDEV, /* u_int32_t ifindex */ NFULA_HWADDR, /* nfulnl_msg_packet_hw */ NFULA_PAYLOAD, /* opaque data payload */ NFULA_PREFIX, /* string prefix */ diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h index e142b0ff7c08..2d8d2b2cfcaa 100644 --- a/include/linux/netfilter/nfnetlink_queue.h +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -36,6 +36,8 @@ enum nfqnl_attr_type { NFQA_TIMESTAMP, /* nfqnl_msg_packet_timestamp */ NFQA_IFINDEX_INDEV, /* u_int32_t ifindex */ NFQA_IFINDEX_OUTDEV, /* u_int32_t ifindex */ + NFQA_IFINDEX_PHYSINDEV, /* u_int32_t ifindex */ + NFQA_IFINDEX_PHYSOUTDEV, /* u_int32_t ifindex */ NFQA_HWADDR, /* nfqnl_msg_packet_hw */ NFQA_PAYLOAD, /* opaque data payload */ -- cgit v1.2.3 From bbd86b9fc469b7e91dc7444e6abb8930811d79cb Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 20:23:11 -0700 Subject: [NETFILTER]: add /proc/net/netfilter interface to nf_queue This patch adds a /proc/net/netfilter/nf_queue file, similar to the recently-added /proc/net/netfilter/nf_log. It indicates which queue handler is registered to which protocol family. This is useful since there are now multiple queue handlers in the treee (ip[6]_queue, nfnetlink_queue). Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 815583af06c2..bf430fcbe364 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -225,13 +225,16 @@ int nf_getsockopt(struct sock *sk, int pf, int optval, char __user *opt, int *len); /* Packet queuing */ -typedef int (*nf_queue_outfn_t)(struct sk_buff *skb, - struct nf_info *info, - unsigned int queuenum, void *data); +struct nf_queue_handler { + int (*outfn)(struct sk_buff *skb, struct nf_info *info, + unsigned int queuenum, void *data); + void *data; + char *name; +}; extern int nf_register_queue_handler(int pf, - nf_queue_outfn_t outfn, void *data); + struct nf_queue_handler *qh); extern int nf_unregister_queue_handler(int pf); -extern void nf_unregister_queue_handlers(nf_queue_outfn_t outfn); +extern void nf_unregister_queue_handlers(struct nf_queue_handler *qh); extern void nf_reinject(struct sk_buff *skb, struct nf_info *info, unsigned int verdict); -- cgit v1.2.3 From 8a61fadb3908454ccfa538aaa75eb1d22def5700 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 20:23:53 -0700 Subject: [NETFILTER]: check nf_log function call arguments Check whether pf is too large in order to prevent array overflow. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index bf430fcbe364..ac3c61411d4b 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -157,7 +157,7 @@ struct nf_logger { /* Function to register/unregister log function. */ int nf_log_register(int pf, struct nf_logger *logger); -void nf_log_unregister_pf(int pf); +int nf_log_unregister_pf(int pf); void nf_log_unregister_logger(struct nf_logger *logger); /* Calls the registered backend logging function */ -- cgit v1.2.3 From 5a47a470e602eecb168ddd3b78841b84ceddd319 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 20:26:03 -0700 Subject: [DCCP]: make include-able from userspace The protocol header files in are usually structured in a way to be included by userspace code. The top section consists of general protocol structure definitions, typedefs, enums - followed by an #ifdef __KERNEL__ section. Currently doesn't follow that convention and can therefore not be used from userspace. However, for example iptables' libipt_dccp.c actually needs various definitions from there. Signed-off-by: Harald Welte Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 238 ++++++++++++++++++++++++++------------------------- 1 file changed, 121 insertions(+), 117 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index e3b4bf7346bb..add4908b8e57 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -1,16 +1,8 @@ #ifndef _LINUX_DCCP_H #define _LINUX_DCCP_H -#include -#include #include -#include -#include - -#include -#include -#include -#include +#include /* FIXME: this is utterly wrong */ struct sockaddr_dccp { @@ -18,40 +10,6 @@ struct sockaddr_dccp { unsigned int service; }; -enum dccp_state { - DCCP_OPEN = TCP_ESTABLISHED, - DCCP_REQUESTING = TCP_SYN_SENT, - DCCP_PARTOPEN = TCP_FIN_WAIT1, /* FIXME: - This mapping is horrible, but TCP has - no matching state for DCCP_PARTOPEN, - as TCP_SYN_RECV is already used by - DCCP_RESPOND, why don't stop using TCP - mapping of states? OK, now we don't use - sk_stream_sendmsg anymore, so doesn't - seem to exist any reason for us to - do the TCP mapping here */ - DCCP_LISTEN = TCP_LISTEN, - DCCP_RESPOND = TCP_SYN_RECV, - DCCP_CLOSING = TCP_CLOSING, - DCCP_TIME_WAIT = TCP_TIME_WAIT, - DCCP_CLOSED = TCP_CLOSE, - DCCP_MAX_STATES = TCP_MAX_STATES, -}; - -#define DCCP_STATE_MASK 0xf -#define DCCP_ACTION_FIN (1<<7) - -enum { - DCCPF_OPEN = TCPF_ESTABLISHED, - DCCPF_REQUESTING = TCPF_SYN_SENT, - DCCPF_PARTOPEN = TCPF_FIN_WAIT1, - DCCPF_LISTEN = TCPF_LISTEN, - DCCPF_RESPOND = TCPF_SYN_RECV, - DCCPF_CLOSING = TCPF_CLOSING, - DCCPF_TIME_WAIT = TCPF_TIME_WAIT, - DCCPF_CLOSED = TCPF_CLOSE, -}; - /** * struct dccp_hdr - generic part of DCCP packet header * @@ -94,11 +52,6 @@ struct dccp_hdr { #endif }; -static inline struct dccp_hdr *dccp_hdr(const struct sk_buff *skb) -{ - return (struct dccp_hdr *)skb->h.raw; -} - /** * struct dccp_hdr_ext - the low bits of a 48 bit seq packet * @@ -108,34 +61,6 @@ struct dccp_hdr_ext { __u32 dccph_seq_low; }; -static inline struct dccp_hdr_ext *dccp_hdrx(const struct sk_buff *skb) -{ - return (struct dccp_hdr_ext *)(skb->h.raw + sizeof(struct dccp_hdr)); -} - -static inline unsigned int dccp_basic_hdr_len(const struct sk_buff *skb) -{ - const struct dccp_hdr *dh = dccp_hdr(skb); - return sizeof(*dh) + (dh->dccph_x ? sizeof(struct dccp_hdr_ext) : 0); -} - -static inline __u64 dccp_hdr_seq(const struct sk_buff *skb) -{ - const struct dccp_hdr *dh = dccp_hdr(skb); -#if defined(__LITTLE_ENDIAN_BITFIELD) - __u64 seq_nr = ntohl(dh->dccph_seq << 8); -#elif defined(__BIG_ENDIAN_BITFIELD) - __u64 seq_nr = ntohl(dh->dccph_seq); -#else -#error "Adjust your defines" -#endif - - if (dh->dccph_x != 0) - seq_nr = (seq_nr << 32) + ntohl(dccp_hdrx(skb)->dccph_seq_low); - - return seq_nr; -} - /** * struct dccp_hdr_request - Conection initiation request header * @@ -145,12 +70,6 @@ static inline __u64 dccp_hdr_seq(const struct sk_buff *skb) struct dccp_hdr_request { __u32 dccph_req_service; }; - -static inline struct dccp_hdr_request *dccp_hdr_request(struct sk_buff *skb) -{ - return (struct dccp_hdr_request *)(skb->h.raw + dccp_basic_hdr_len(skb)); -} - /** * struct dccp_hdr_ack_bits - acknowledgment bits common to most packets * @@ -162,24 +81,6 @@ struct dccp_hdr_ack_bits { dccph_ack_nr_high:24; __u32 dccph_ack_nr_low; }; - -static inline struct dccp_hdr_ack_bits *dccp_hdr_ack_bits(const struct sk_buff *skb) -{ - return (struct dccp_hdr_ack_bits *)(skb->h.raw + dccp_basic_hdr_len(skb)); -} - -static inline u64 dccp_hdr_ack_seq(const struct sk_buff *skb) -{ - const struct dccp_hdr_ack_bits *dhack = dccp_hdr_ack_bits(skb); -#if defined(__LITTLE_ENDIAN_BITFIELD) - return (((u64)ntohl(dhack->dccph_ack_nr_high << 8)) << 32) + ntohl(dhack->dccph_ack_nr_low); -#elif defined(__BIG_ENDIAN_BITFIELD) - return (((u64)ntohl(dhack->dccph_ack_nr_high)) << 32) + ntohl(dhack->dccph_ack_nr_low); -#else -#error "Adjust your defines" -#endif -} - /** * struct dccp_hdr_response - Conection initiation response header * @@ -193,11 +94,6 @@ struct dccp_hdr_response { __u32 dccph_resp_service; }; -static inline struct dccp_hdr_response *dccp_hdr_response(struct sk_buff *skb) -{ - return (struct dccp_hdr_response *)(skb->h.raw + dccp_basic_hdr_len(skb)); -} - /** * struct dccp_hdr_reset - Unconditionally shut down a connection * @@ -210,11 +106,6 @@ struct dccp_hdr_reset { dccph_reset_data[3]; }; -static inline struct dccp_hdr_reset *dccp_hdr_reset(struct sk_buff *skb) -{ - return (struct dccp_hdr_reset *)(skb->h.raw + dccp_basic_hdr_len(skb)); -} - enum dccp_pkt_type { DCCP_PKT_REQUEST = 0, DCCP_PKT_RESPONSE, @@ -248,13 +139,6 @@ static inline unsigned int dccp_packet_hdr_len(const __u8 type) return sizeof(struct dccp_hdr_response); return sizeof(struct dccp_hdr_reset); } - -static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) -{ - return dccp_basic_hdr_len(skb) + - dccp_packet_hdr_len(dccp_hdr(skb)->dccph_type); -} - enum dccp_reset_codes { DCCP_RESET_CODE_UNSPECIFIED = 0, DCCP_RESET_CODE_CLOSED, @@ -298,6 +182,124 @@ enum { DCCPF_MAX_CCID_SPECIFIC = 255, }; +#ifdef __KERNEL__ + +#include +#include +#include +#include + +#include +#include +#include +#include + +enum dccp_state { + DCCP_OPEN = TCP_ESTABLISHED, + DCCP_REQUESTING = TCP_SYN_SENT, + DCCP_PARTOPEN = TCP_FIN_WAIT1, /* FIXME: + This mapping is horrible, but TCP has + no matching state for DCCP_PARTOPEN, + as TCP_SYN_RECV is already used by + DCCP_RESPOND, why don't stop using TCP + mapping of states? OK, now we don't use + sk_stream_sendmsg anymore, so doesn't + seem to exist any reason for us to + do the TCP mapping here */ + DCCP_LISTEN = TCP_LISTEN, + DCCP_RESPOND = TCP_SYN_RECV, + DCCP_CLOSING = TCP_CLOSING, + DCCP_TIME_WAIT = TCP_TIME_WAIT, + DCCP_CLOSED = TCP_CLOSE, + DCCP_MAX_STATES = TCP_MAX_STATES, +}; + +#define DCCP_STATE_MASK 0xf +#define DCCP_ACTION_FIN (1<<7) + +enum { + DCCPF_OPEN = TCPF_ESTABLISHED, + DCCPF_REQUESTING = TCPF_SYN_SENT, + DCCPF_PARTOPEN = TCPF_FIN_WAIT1, + DCCPF_LISTEN = TCPF_LISTEN, + DCCPF_RESPOND = TCPF_SYN_RECV, + DCCPF_CLOSING = TCPF_CLOSING, + DCCPF_TIME_WAIT = TCPF_TIME_WAIT, + DCCPF_CLOSED = TCPF_CLOSE, +}; + +static inline struct dccp_hdr *dccp_hdr(const struct sk_buff *skb) +{ + return (struct dccp_hdr *)skb->h.raw; +} + +static inline struct dccp_hdr_ext *dccp_hdrx(const struct sk_buff *skb) +{ + return (struct dccp_hdr_ext *)(skb->h.raw + sizeof(struct dccp_hdr)); +} + +static inline unsigned int dccp_basic_hdr_len(const struct sk_buff *skb) +{ + const struct dccp_hdr *dh = dccp_hdr(skb); + return sizeof(*dh) + (dh->dccph_x ? sizeof(struct dccp_hdr_ext) : 0); +} + +static inline __u64 dccp_hdr_seq(const struct sk_buff *skb) +{ + const struct dccp_hdr *dh = dccp_hdr(skb); +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u64 seq_nr = ntohl(dh->dccph_seq << 8); +#elif defined(__BIG_ENDIAN_BITFIELD) + __u64 seq_nr = ntohl(dh->dccph_seq); +#else +#error "Adjust your defines" +#endif + + if (dh->dccph_x != 0) + seq_nr = (seq_nr << 32) + ntohl(dccp_hdrx(skb)->dccph_seq_low); + + return seq_nr; +} + +static inline struct dccp_hdr_request *dccp_hdr_request(struct sk_buff *skb) +{ + return (struct dccp_hdr_request *)(skb->h.raw + dccp_basic_hdr_len(skb)); +} + +static inline struct dccp_hdr_ack_bits *dccp_hdr_ack_bits(const struct sk_buff *skb) +{ + return (struct dccp_hdr_ack_bits *)(skb->h.raw + dccp_basic_hdr_len(skb)); +} + +static inline u64 dccp_hdr_ack_seq(const struct sk_buff *skb) +{ + const struct dccp_hdr_ack_bits *dhack = dccp_hdr_ack_bits(skb); +#if defined(__LITTLE_ENDIAN_BITFIELD) + return (((u64)ntohl(dhack->dccph_ack_nr_high << 8)) << 32) + ntohl(dhack->dccph_ack_nr_low); +#elif defined(__BIG_ENDIAN_BITFIELD) + return (((u64)ntohl(dhack->dccph_ack_nr_high)) << 32) + ntohl(dhack->dccph_ack_nr_low); +#else +#error "Adjust your defines" +#endif +} + +static inline struct dccp_hdr_response *dccp_hdr_response(struct sk_buff *skb) +{ + return (struct dccp_hdr_response *)(skb->h.raw + dccp_basic_hdr_len(skb)); +} + +static inline struct dccp_hdr_reset *dccp_hdr_reset(struct sk_buff *skb) +{ + return (struct dccp_hdr_reset *)(skb->h.raw + dccp_basic_hdr_len(skb)); +} + +static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) +{ + return dccp_basic_hdr_len(skb) + + dccp_packet_hdr_len(dccp_hdr(skb)->dccph_type); +} + + /* initial values for each feature */ #define DCCPF_INITIAL_SEQUENCE_WINDOW 100 /* FIXME: for now we're using CCID 3 (TFRC) */ @@ -429,4 +431,6 @@ static inline const char *dccp_role(const struct sock *sk) return NULL; } +#endif /* __KERNEL__ */ + #endif /* _LINUX_DCCP_H */ -- cgit v1.2.3 From e2e268665f6c01686b477a6b0cc5a70bab689d54 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:26:28 -0700 Subject: [DCCP]: Fix struct sockaddr_dccp definition Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index add4908b8e57..fd1412ddb3ff 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -4,10 +4,14 @@ #include #include -/* FIXME: this is utterly wrong */ +/* Structure describing an Internet (DCCP) socket address. */ struct sockaddr_dccp { - struct sockaddr_in in; - unsigned int service; + __u16 sdccp_family; /* Address family */ + __u16 sdccp_port; /* Port number */ + __u32 sdccp_addr; /* Internet address */ + __u32 sdccp_service; /* Service */ + /* Pad to size of `struct sockaddr': 16 bytes . */ + __u32 sdccp_pad; }; /** -- cgit v1.2.3 From 1d3de414eb20d937d82c5219fd13ee4cedc499cb Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Tue, 9 Aug 2005 20:26:55 -0700 Subject: [NETFILTER]: New iptables DCCP protocol header match Using this new iptables DCCP protocol header match, it is possible to create simplistic stateless packet filtering rules for DCCP. It permits matching of port numbers, packet type and options. Signed-off-by: Harald Welte Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 16 +++++++++++++--- include/linux/netfilter_ipv4/ipt_dccp.h | 23 +++++++++++++++++++++++ 2 files changed, 36 insertions(+), 3 deletions(-) create mode 100644 include/linux/netfilter_ipv4/ipt_dccp.h (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index fd1412ddb3ff..431d58923ba9 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -242,10 +242,15 @@ static inline struct dccp_hdr_ext *dccp_hdrx(const struct sk_buff *skb) return (struct dccp_hdr_ext *)(skb->h.raw + sizeof(struct dccp_hdr)); } +static inline unsigned int __dccp_basic_hdr_len(const struct dccp_hdr *dh) +{ + return sizeof(*dh) + (dh->dccph_x ? sizeof(struct dccp_hdr_ext) : 0); +} + static inline unsigned int dccp_basic_hdr_len(const struct sk_buff *skb) { const struct dccp_hdr *dh = dccp_hdr(skb); - return sizeof(*dh) + (dh->dccph_x ? sizeof(struct dccp_hdr_ext) : 0); + return __dccp_basic_hdr_len(dh); } static inline __u64 dccp_hdr_seq(const struct sk_buff *skb) @@ -297,10 +302,15 @@ static inline struct dccp_hdr_reset *dccp_hdr_reset(struct sk_buff *skb) return (struct dccp_hdr_reset *)(skb->h.raw + dccp_basic_hdr_len(skb)); } +static inline unsigned int __dccp_hdr_len(const struct dccp_hdr *dh) +{ + return __dccp_basic_hdr_len(dh) + + dccp_packet_hdr_len(dh->dccph_type); +} + static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) { - return dccp_basic_hdr_len(skb) + - dccp_packet_hdr_len(dccp_hdr(skb)->dccph_type); + return __dccp_hdr_len(dccp_hdr(skb)); } diff --git a/include/linux/netfilter_ipv4/ipt_dccp.h b/include/linux/netfilter_ipv4/ipt_dccp.h new file mode 100644 index 000000000000..3cb3a522e62b --- /dev/null +++ b/include/linux/netfilter_ipv4/ipt_dccp.h @@ -0,0 +1,23 @@ +#ifndef _IPT_DCCP_H_ +#define _IPT_DCCP_H_ + +#define IPT_DCCP_SRC_PORTS 0x01 +#define IPT_DCCP_DEST_PORTS 0x02 +#define IPT_DCCP_TYPE 0x04 +#define IPT_DCCP_OPTION 0x08 + +#define IPT_DCCP_VALID_FLAGS 0x0f + +struct ipt_dccp_info { + u_int16_t dpts[2]; /* Min, Max */ + u_int16_t spts[2]; /* Min, Max */ + + u_int16_t flags; + u_int16_t invflags; + + u_int16_t typemask; + u_int8_t option; +}; + +#endif /* _IPT_DCCP_H_ */ + -- cgit v1.2.3 From 64cf1e5d8b5f88d56509260e08fa0d8314277350 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:45:21 -0700 Subject: [DCCP]: Finish the TIMEWAIT minisock support Using most of the infrastructure TCP uses, with a dccp_death_row, etc. As per my current interpretation of the draft what we have with this changeset seems to be all we need (or very close to it 8)). Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 431d58923ba9..3dccdd5108b5 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -194,6 +194,7 @@ enum { #include #include +#include #include #include #include @@ -354,6 +355,8 @@ static inline struct dccp_request_sock *dccp_rsk(const struct request_sock *req) return (struct dccp_request_sock *)req; } +extern struct inet_timewait_death_row dccp_death_row; + /* Read about the ECN nonce to see why it is 253 */ #define DCCP_MAX_ACK_VECTOR_LEN 253 -- cgit v1.2.3 From 6687e988d9aeaccad6774e6a8304f681f3ec0a03 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 10 Aug 2005 04:03:31 -0300 Subject: [ICSK]: Move TCP congestion avoidance members to icsk This changeset basically moves tcp_sk()->{ca_ops,ca_state,etc} to inet_csk(), minimal renaming/moving done in this changeset to ease review. Most of it is just changes of struct tcp_sock * to struct sock * parameters. With this we move to a state closer to two interesting goals: 1. Generalisation of net/ipv4/tcp_diag.c, becoming inet_diag.c, being used for any INET transport protocol that has struct inet_hashinfo and are derived from struct inet_connection_sock. Keeps the userspace API, that will just not display DCCP sockets, while newer versions of tools can support DCCP. 2. INET generic transport pluggable Congestion Avoidance infrastructure, using the current TCP CA infrastructure with DCCP. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/tcp.h | 21 +++------------------ 1 file changed, 3 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 620096840744..ac4ca44c75ca 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -258,19 +258,15 @@ struct tcp_sock { __u32 mss_cache; /* Cached effective mss, not including SACKS */ __u16 xmit_size_goal; /* Goal for segmenting output packets */ __u16 ext_header_len; /* Network protocol overhead (IP/IPv6 options) */ - __u8 ca_state; /* State of fast-retransmit machine */ - __u8 keepalive_probes; /* num of allowed keep alive probes */ - __u16 advmss; /* Advertised MSS */ __u32 window_clamp; /* Maximal window to advertise */ __u32 rcv_ssthresh; /* Current window clamp */ __u32 frto_highmark; /* snd_nxt when RTO occurred */ __u8 reordering; /* Packet reordering metric. */ __u8 frto_counter; /* Number of new acks after RTO */ - __u8 nonagle; /* Disable Nagle algorithm? */ - /* ONE BYTE HOLE, TRY TO PACK */ + __u8 keepalive_probes; /* num of allowed keep alive probes */ /* RTT measurement */ __u32 srtt; /* smoothed round trip time << 3 */ @@ -311,8 +307,7 @@ struct tcp_sock { struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */ struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/ - __u8 probes_out; /* unanswered 0 window probes */ - __u8 ecn_flags; /* ECN status bits. */ + __u16 advmss; /* Advertised MSS */ __u16 prior_ssthresh; /* ssthresh saved at recovery start */ __u32 lost_out; /* Lost packets */ __u32 sacked_out; /* SACK'd packets */ @@ -327,7 +322,7 @@ struct tcp_sock { __u32 urg_seq; /* Seq of received urgent pointer */ __u16 urg_data; /* Saved octet of OOB data and control flags */ __u8 urg_mode; /* In urgent mode */ - /* ONE BYTE HOLE, TRY TO PACK! */ + __u8 ecn_flags; /* ECN status bits. */ __u32 snd_up; /* Urgent pointer */ __u32 total_retrans; /* Total retransmits for entire connection */ @@ -351,11 +346,6 @@ struct tcp_sock { __u32 seq; __u32 time; } rcvq_space; - - /* Pluggable TCP congestion control hook */ - struct tcp_congestion_ops *ca_ops; - u32 ca_priv[16]; -#define TCP_CA_PRIV_SIZE (16*sizeof(u32)) }; static inline struct tcp_sock *tcp_sk(const struct sock *sk) @@ -377,11 +367,6 @@ static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) return (struct tcp_timewait_sock *)sk; } -static inline void *tcp_ca(const struct tcp_sock *tp) -{ - return (void *) tp->ca_priv; -} - #endif #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From 540722ffc3a0d7e11d97a13e1ce6f3bc23b061c1 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 10 Aug 2005 05:54:28 -0300 Subject: [TCPDIAG]: Implement cheapest way of supporting DCCPDIAG_GETSOCK With ugly ifdefs, etc, but this actually: 1. keeps the existing ABI, i.e. no need to recompile the iproute2 utilities if not interested in DCCP. 2. Provides all the tcp_diag functionality in DCCP, with just a small patch that makes iproute2 support DCCP. Of course I'll get this cleaned-up in time, but for now I think its OK to be this way to quickly get this functionality. iproute2-ss050808 patch at: http://vger.kernel.org/~acme/iproute2-ss050808.dccp.patch Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/tcp_diag.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp_diag.h b/include/linux/tcp_diag.h index 7a5996743946..190494ebcfb8 100644 --- a/include/linux/tcp_diag.h +++ b/include/linux/tcp_diag.h @@ -3,6 +3,7 @@ /* Just some random number */ #define TCPDIAG_GETSOCK 18 +#define DCCPDIAG_GETSOCK 19 /* Socket identity */ struct tcpdiag_sockid -- cgit v1.2.3 From 8c60f3fab55712f23f2bd557ceedfbb00c649f37 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 10 Aug 2005 12:59:38 -0300 Subject: [CCID3]: Separate most of the packet history code This also changes the list_for_each_entry_safe_continue behaviour to match its kerneldoc comment, that is, to start after the pos passed. Also adds several helper functions from previously open coded fragments, making the code more clear. Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/list.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 597094e0fdb5..0f2435f92db3 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -427,7 +427,8 @@ static inline void list_splice_init(struct list_head *list, * @member: the name of the list_struct within the struct. */ #define list_for_each_entry_safe_continue(pos, n, head, member) \ - for (pos = n, n = list_entry(n->member.next, typeof(*n), member); \ + for (pos = list_entry(pos->member.next, typeof(*pos), member), \ + n = list_entry(pos->member.next, typeof(*pos), member); \ &pos->member != (head); \ pos = n, n = list_entry(n->member.next, typeof(*n), member)) -- cgit v1.2.3 From 5917ed961def82a4dba9198d11a75f79d115a8cb Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Thu, 11 Aug 2005 15:31:15 -0700 Subject: [NETFILTER]: Fix NF_QUEUE_NR() macro I obviously wanted to use bitwise-or, not logical or. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index ac3c61411d4b..189ba67ba603 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -29,7 +29,7 @@ #define NF_VERDICT_QMASK 0xffff0000 #define NF_VERDICT_QBITS 16 -#define NF_QUEUE_NR(x) ((x << NF_VERDICT_QBITS) & NF_VERDICT_QMASK || NF_QUEUE) +#define NF_QUEUE_NR(x) ((x << NF_VERDICT_QBITS) & NF_VERDICT_QMASK | NF_QUEUE) /* only for userspace compatibility */ #ifndef __KERNEL__ -- cgit v1.2.3 From 0a242efc4fb859b2da506cdf8f3366231602e4ff Mon Sep 17 00:00:00 2001 From: Denis Vlasenko Date: Thu, 11 Aug 2005 15:32:53 -0700 Subject: [NET]: Deinline netif_carrier_{on,off}(). # grep -r 'netif_carrier_o[nf]' linux-2.6.12 | wc -l 246 # size vmlinux.org vmlinux.carrier text data bss dec hex filename 4339634 1054414 259296 5653344 564360 vmlinux.org 4337710 1054414 259296 5651420 563bdc vmlinux.carrier And this ain't an allyesconfig kernel! Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 296cf93a65e0..d8e52edfd526 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -699,19 +699,9 @@ static inline int netif_carrier_ok(const struct net_device *dev) extern void __netdev_watchdog_up(struct net_device *dev); -static inline void netif_carrier_on(struct net_device *dev) -{ - if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) - linkwatch_fire_event(dev); - if (netif_running(dev)) - __netdev_watchdog_up(dev); -} +extern void netif_carrier_on(struct net_device *dev); -static inline void netif_carrier_off(struct net_device *dev) -{ - if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) - linkwatch_fire_event(dev); -} +extern void netif_carrier_off(struct net_device *dev); /* Hot-plugging. */ static inline int netif_device_present(struct net_device *dev) -- cgit v1.2.3 From b766b305d3f2d8be173e5d9853534ea1afdbabba Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Fri, 12 Aug 2005 11:36:44 -0700 Subject: [NETFILTER]: Fix gcc-3.4.x warning about iplicit operator precedence Fix gcc-3.4.x warning about iplicit operator precedence in NF_QUEUE_NR() Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 189ba67ba603..be365e70ee99 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -29,7 +29,7 @@ #define NF_VERDICT_QMASK 0xffff0000 #define NF_VERDICT_QBITS 16 -#define NF_QUEUE_NR(x) ((x << NF_VERDICT_QBITS) & NF_VERDICT_QMASK | NF_QUEUE) +#define NF_QUEUE_NR(x) (((x << NF_VERDICT_QBITS) & NF_VERDICT_QMASK) | NF_QUEUE) /* only for userspace compatibility */ #ifndef __KERNEL__ -- cgit v1.2.3 From 505cbfc577f3fa778005e2800b869eca25727d5f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 12 Aug 2005 09:19:38 -0300 Subject: [IPV6]: Generalise the tcp_v6_lookup routines In the same way as was done with the v4 counterparts, this will be moved to inet6_hashtables.c. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/ipv6.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 777339b68464..3c7dbc6a0a70 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -193,6 +193,11 @@ struct inet6_skb_parm { #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) +static inline int inet6_iif(const struct sk_buff *skb) +{ + return IP6CB(skb)->iif; +} + struct tcp6_request_sock { struct tcp_request_sock req; struct in6_addr loc_addr; -- cgit v1.2.3 From 4f5736c4c7cf6f9bd8db82b712cfdd51c87e06b9 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 12 Aug 2005 09:27:49 -0300 Subject: [TCPDIAG]: Introduce inet_diag_{register,unregister} Next changeset will rename tcp_diag to inet_diag and move the tcp_diag code out of it and into a new tcp_diag.c, similar to the net/dccp/diag.c introduced in this changeset, completing the transition to a generic inet_diag infrastructure. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/tcp_diag.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp_diag.h b/include/linux/tcp_diag.h index 190494ebcfb8..910c34ba19c0 100644 --- a/include/linux/tcp_diag.h +++ b/include/linux/tcp_diag.h @@ -5,6 +5,8 @@ #define TCPDIAG_GETSOCK 18 #define DCCPDIAG_GETSOCK 19 +#define INET_DIAG_GETSOCK_MAX 24 + /* Socket identity */ struct tcpdiag_sockid { @@ -125,4 +127,21 @@ struct tcpvegas_info { __u32 tcpv_minrtt; }; +#ifdef __KERNEL__ +struct sock; +struct inet_hashinfo; + +struct inet_diag_handler { + struct inet_hashinfo *idiag_hashinfo; + void (*idiag_get_info)(struct sock *sk, + struct tcpdiagmsg *r, + void *info); + __u16 idiag_info_size; + __u16 idiag_type; +}; + +extern int inet_diag_register(const struct inet_diag_handler *handler); +extern void inet_diag_unregister(const struct inet_diag_handler *handler); +#endif /* __KERNEL__ */ + #endif /* _TCP_DIAG_H_ */ -- cgit v1.2.3 From 73c1f4a033675f168df7e98bbeeafca3c644b8a6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 12 Aug 2005 12:51:49 -0300 Subject: [TCPDIAG]: Just rename everything to inet_diag Next changeset will rename tcp_diag.[ch] to inet_diag.[ch]. I'm taking this longer route so as to easy review, making clear the changes made all along the way. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- include/linux/tcp_diag.h | 135 ++++++++++++++++++++++------------------------- 2 files changed, 64 insertions(+), 73 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 1c50fea8995b..d5e09bcd80f9 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -8,7 +8,7 @@ #define NETLINK_W1 1 /* 1-wire subsystem */ #define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */ #define NETLINK_FIREWALL 3 /* Firewalling hook */ -#define NETLINK_TCPDIAG 4 /* TCP socket monitoring */ +#define NETLINK_INET_DIAG 4 /* INET socket monitoring */ #define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */ #define NETLINK_XFRM 6 /* ipsec */ #define NETLINK_SELINUX 7 /* SELinux event notifications */ diff --git a/include/linux/tcp_diag.h b/include/linux/tcp_diag.h index 910c34ba19c0..a4606e5810e5 100644 --- a/include/linux/tcp_diag.h +++ b/include/linux/tcp_diag.h @@ -1,5 +1,5 @@ -#ifndef _TCP_DIAG_H_ -#define _TCP_DIAG_H_ 1 +#ifndef _INET_DIAG_H_ +#define _INET_DIAG_H_ 1 /* Just some random number */ #define TCPDIAG_GETSOCK 18 @@ -8,39 +8,36 @@ #define INET_DIAG_GETSOCK_MAX 24 /* Socket identity */ -struct tcpdiag_sockid -{ - __u16 tcpdiag_sport; - __u16 tcpdiag_dport; - __u32 tcpdiag_src[4]; - __u32 tcpdiag_dst[4]; - __u32 tcpdiag_if; - __u32 tcpdiag_cookie[2]; -#define TCPDIAG_NOCOOKIE (~0U) +struct inet_diag_sockid { + __u16 idiag_sport; + __u16 idiag_dport; + __u32 idiag_src[4]; + __u32 idiag_dst[4]; + __u32 idiag_if; + __u32 idiag_cookie[2]; +#define INET_DIAG_NOCOOKIE (~0U) }; /* Request structure */ -struct tcpdiagreq -{ - __u8 tcpdiag_family; /* Family of addresses. */ - __u8 tcpdiag_src_len; - __u8 tcpdiag_dst_len; - __u8 tcpdiag_ext; /* Query extended information */ +struct inet_diag_req { + __u8 idiag_family; /* Family of addresses. */ + __u8 idiag_src_len; + __u8 idiag_dst_len; + __u8 idiag_ext; /* Query extended information */ - struct tcpdiag_sockid id; + struct inet_diag_sockid id; - __u32 tcpdiag_states; /* States to dump */ - __u32 tcpdiag_dbs; /* Tables to dump (NI) */ + __u32 idiag_states; /* States to dump */ + __u32 idiag_dbs; /* Tables to dump (NI) */ }; -enum -{ - TCPDIAG_REQ_NONE, - TCPDIAG_REQ_BYTECODE, +enum { + INET_DIAG_REQ_NONE, + INET_DIAG_REQ_BYTECODE, }; -#define TCPDIAG_REQ_MAX TCPDIAG_REQ_BYTECODE +#define INET_DIAG_REQ_MAX INET_DIAG_REQ_BYTECODE /* Bytecode is sequence of 4 byte commands followed by variable arguments. * All the commands identified by "code" are conditional jumps forward: @@ -48,28 +45,25 @@ enum * length of the command and its arguments. */ -struct tcpdiag_bc_op -{ +struct inet_diag_bc_op { unsigned char code; unsigned char yes; unsigned short no; }; -enum -{ - TCPDIAG_BC_NOP, - TCPDIAG_BC_JMP, - TCPDIAG_BC_S_GE, - TCPDIAG_BC_S_LE, - TCPDIAG_BC_D_GE, - TCPDIAG_BC_D_LE, - TCPDIAG_BC_AUTO, - TCPDIAG_BC_S_COND, - TCPDIAG_BC_D_COND, +enum { + INET_DIAG_BC_NOP, + INET_DIAG_BC_JMP, + INET_DIAG_BC_S_GE, + INET_DIAG_BC_S_LE, + INET_DIAG_BC_D_GE, + INET_DIAG_BC_D_LE, + INET_DIAG_BC_AUTO, + INET_DIAG_BC_S_COND, + INET_DIAG_BC_D_COND, }; -struct tcpdiag_hostcond -{ +struct inet_diag_hostcond { __u8 family; __u8 prefix_len; int port; @@ -78,47 +72,44 @@ struct tcpdiag_hostcond /* Base info structure. It contains socket identity (addrs/ports/cookie) * and, alas, the information shown by netstat. */ -struct tcpdiagmsg -{ - __u8 tcpdiag_family; - __u8 tcpdiag_state; - __u8 tcpdiag_timer; - __u8 tcpdiag_retrans; - - struct tcpdiag_sockid id; - - __u32 tcpdiag_expires; - __u32 tcpdiag_rqueue; - __u32 tcpdiag_wqueue; - __u32 tcpdiag_uid; - __u32 tcpdiag_inode; +struct inet_diag_msg { + __u8 idiag_family; + __u8 idiag_state; + __u8 idiag_timer; + __u8 idiag_retrans; + + struct inet_diag_sockid id; + + __u32 idiag_expires; + __u32 idiag_rqueue; + __u32 idiag_wqueue; + __u32 idiag_uid; + __u32 idiag_inode; }; /* Extensions */ -enum -{ - TCPDIAG_NONE, - TCPDIAG_MEMINFO, - TCPDIAG_INFO, - TCPDIAG_VEGASINFO, - TCPDIAG_CONG, +enum { + INET_DIAG_NONE, + INET_DIAG_MEMINFO, + INET_DIAG_INFO, + INET_DIAG_VEGASINFO, + INET_DIAG_CONG, }; -#define TCPDIAG_MAX TCPDIAG_CONG +#define INET_DIAG_MAX INET_DIAG_CONG -/* TCPDIAG_MEM */ +/* INET_DIAG_MEM */ -struct tcpdiag_meminfo -{ - __u32 tcpdiag_rmem; - __u32 tcpdiag_wmem; - __u32 tcpdiag_fmem; - __u32 tcpdiag_tmem; +struct inet_diag_meminfo { + __u32 idiag_rmem; + __u32 idiag_wmem; + __u32 idiag_fmem; + __u32 idiag_tmem; }; -/* TCPDIAG_VEGASINFO */ +/* INET_DIAG_VEGASINFO */ struct tcpvegas_info { __u32 tcpv_enabled; @@ -134,7 +125,7 @@ struct inet_hashinfo; struct inet_diag_handler { struct inet_hashinfo *idiag_hashinfo; void (*idiag_get_info)(struct sock *sk, - struct tcpdiagmsg *r, + struct inet_diag_msg *r, void *info); __u16 idiag_info_size; __u16 idiag_type; @@ -144,4 +135,4 @@ extern int inet_diag_register(const struct inet_diag_handler *handler); extern void inet_diag_unregister(const struct inet_diag_handler *handler); #endif /* __KERNEL__ */ -#endif /* _TCP_DIAG_H_ */ +#endif /* _INET_DIAG_H_ */ -- cgit v1.2.3 From a8c2190ee7da1a1dc68ff1a6b5f03feb61e523a5 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 12 Aug 2005 12:56:38 -0300 Subject: [INET_DIAG]: Rename tcp_diag.[ch] to inet_diag.[ch] Next changeset will introduce net/ipv4/tcp_diag.c, moving the code that was put transitioanlly in inet_diag.c. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 138 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/tcp_diag.h | 138 ---------------------------------------------- 2 files changed, 138 insertions(+), 138 deletions(-) create mode 100644 include/linux/inet_diag.h delete mode 100644 include/linux/tcp_diag.h (limited to 'include/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h new file mode 100644 index 000000000000..a4606e5810e5 --- /dev/null +++ b/include/linux/inet_diag.h @@ -0,0 +1,138 @@ +#ifndef _INET_DIAG_H_ +#define _INET_DIAG_H_ 1 + +/* Just some random number */ +#define TCPDIAG_GETSOCK 18 +#define DCCPDIAG_GETSOCK 19 + +#define INET_DIAG_GETSOCK_MAX 24 + +/* Socket identity */ +struct inet_diag_sockid { + __u16 idiag_sport; + __u16 idiag_dport; + __u32 idiag_src[4]; + __u32 idiag_dst[4]; + __u32 idiag_if; + __u32 idiag_cookie[2]; +#define INET_DIAG_NOCOOKIE (~0U) +}; + +/* Request structure */ + +struct inet_diag_req { + __u8 idiag_family; /* Family of addresses. */ + __u8 idiag_src_len; + __u8 idiag_dst_len; + __u8 idiag_ext; /* Query extended information */ + + struct inet_diag_sockid id; + + __u32 idiag_states; /* States to dump */ + __u32 idiag_dbs; /* Tables to dump (NI) */ +}; + +enum { + INET_DIAG_REQ_NONE, + INET_DIAG_REQ_BYTECODE, +}; + +#define INET_DIAG_REQ_MAX INET_DIAG_REQ_BYTECODE + +/* Bytecode is sequence of 4 byte commands followed by variable arguments. + * All the commands identified by "code" are conditional jumps forward: + * to offset cc+"yes" or to offset cc+"no". "yes" is supposed to be + * length of the command and its arguments. + */ + +struct inet_diag_bc_op { + unsigned char code; + unsigned char yes; + unsigned short no; +}; + +enum { + INET_DIAG_BC_NOP, + INET_DIAG_BC_JMP, + INET_DIAG_BC_S_GE, + INET_DIAG_BC_S_LE, + INET_DIAG_BC_D_GE, + INET_DIAG_BC_D_LE, + INET_DIAG_BC_AUTO, + INET_DIAG_BC_S_COND, + INET_DIAG_BC_D_COND, +}; + +struct inet_diag_hostcond { + __u8 family; + __u8 prefix_len; + int port; + __u32 addr[0]; +}; + +/* Base info structure. It contains socket identity (addrs/ports/cookie) + * and, alas, the information shown by netstat. */ +struct inet_diag_msg { + __u8 idiag_family; + __u8 idiag_state; + __u8 idiag_timer; + __u8 idiag_retrans; + + struct inet_diag_sockid id; + + __u32 idiag_expires; + __u32 idiag_rqueue; + __u32 idiag_wqueue; + __u32 idiag_uid; + __u32 idiag_inode; +}; + +/* Extensions */ + +enum { + INET_DIAG_NONE, + INET_DIAG_MEMINFO, + INET_DIAG_INFO, + INET_DIAG_VEGASINFO, + INET_DIAG_CONG, +}; + +#define INET_DIAG_MAX INET_DIAG_CONG + + +/* INET_DIAG_MEM */ + +struct inet_diag_meminfo { + __u32 idiag_rmem; + __u32 idiag_wmem; + __u32 idiag_fmem; + __u32 idiag_tmem; +}; + +/* INET_DIAG_VEGASINFO */ + +struct tcpvegas_info { + __u32 tcpv_enabled; + __u32 tcpv_rttcnt; + __u32 tcpv_rtt; + __u32 tcpv_minrtt; +}; + +#ifdef __KERNEL__ +struct sock; +struct inet_hashinfo; + +struct inet_diag_handler { + struct inet_hashinfo *idiag_hashinfo; + void (*idiag_get_info)(struct sock *sk, + struct inet_diag_msg *r, + void *info); + __u16 idiag_info_size; + __u16 idiag_type; +}; + +extern int inet_diag_register(const struct inet_diag_handler *handler); +extern void inet_diag_unregister(const struct inet_diag_handler *handler); +#endif /* __KERNEL__ */ + +#endif /* _INET_DIAG_H_ */ diff --git a/include/linux/tcp_diag.h b/include/linux/tcp_diag.h deleted file mode 100644 index a4606e5810e5..000000000000 --- a/include/linux/tcp_diag.h +++ /dev/null @@ -1,138 +0,0 @@ -#ifndef _INET_DIAG_H_ -#define _INET_DIAG_H_ 1 - -/* Just some random number */ -#define TCPDIAG_GETSOCK 18 -#define DCCPDIAG_GETSOCK 19 - -#define INET_DIAG_GETSOCK_MAX 24 - -/* Socket identity */ -struct inet_diag_sockid { - __u16 idiag_sport; - __u16 idiag_dport; - __u32 idiag_src[4]; - __u32 idiag_dst[4]; - __u32 idiag_if; - __u32 idiag_cookie[2]; -#define INET_DIAG_NOCOOKIE (~0U) -}; - -/* Request structure */ - -struct inet_diag_req { - __u8 idiag_family; /* Family of addresses. */ - __u8 idiag_src_len; - __u8 idiag_dst_len; - __u8 idiag_ext; /* Query extended information */ - - struct inet_diag_sockid id; - - __u32 idiag_states; /* States to dump */ - __u32 idiag_dbs; /* Tables to dump (NI) */ -}; - -enum { - INET_DIAG_REQ_NONE, - INET_DIAG_REQ_BYTECODE, -}; - -#define INET_DIAG_REQ_MAX INET_DIAG_REQ_BYTECODE - -/* Bytecode is sequence of 4 byte commands followed by variable arguments. - * All the commands identified by "code" are conditional jumps forward: - * to offset cc+"yes" or to offset cc+"no". "yes" is supposed to be - * length of the command and its arguments. - */ - -struct inet_diag_bc_op { - unsigned char code; - unsigned char yes; - unsigned short no; -}; - -enum { - INET_DIAG_BC_NOP, - INET_DIAG_BC_JMP, - INET_DIAG_BC_S_GE, - INET_DIAG_BC_S_LE, - INET_DIAG_BC_D_GE, - INET_DIAG_BC_D_LE, - INET_DIAG_BC_AUTO, - INET_DIAG_BC_S_COND, - INET_DIAG_BC_D_COND, -}; - -struct inet_diag_hostcond { - __u8 family; - __u8 prefix_len; - int port; - __u32 addr[0]; -}; - -/* Base info structure. It contains socket identity (addrs/ports/cookie) - * and, alas, the information shown by netstat. */ -struct inet_diag_msg { - __u8 idiag_family; - __u8 idiag_state; - __u8 idiag_timer; - __u8 idiag_retrans; - - struct inet_diag_sockid id; - - __u32 idiag_expires; - __u32 idiag_rqueue; - __u32 idiag_wqueue; - __u32 idiag_uid; - __u32 idiag_inode; -}; - -/* Extensions */ - -enum { - INET_DIAG_NONE, - INET_DIAG_MEMINFO, - INET_DIAG_INFO, - INET_DIAG_VEGASINFO, - INET_DIAG_CONG, -}; - -#define INET_DIAG_MAX INET_DIAG_CONG - - -/* INET_DIAG_MEM */ - -struct inet_diag_meminfo { - __u32 idiag_rmem; - __u32 idiag_wmem; - __u32 idiag_fmem; - __u32 idiag_tmem; -}; - -/* INET_DIAG_VEGASINFO */ - -struct tcpvegas_info { - __u32 tcpv_enabled; - __u32 tcpv_rttcnt; - __u32 tcpv_rtt; - __u32 tcpv_minrtt; -}; - -#ifdef __KERNEL__ -struct sock; -struct inet_hashinfo; - -struct inet_diag_handler { - struct inet_hashinfo *idiag_hashinfo; - void (*idiag_get_info)(struct sock *sk, - struct inet_diag_msg *r, - void *info); - __u16 idiag_info_size; - __u16 idiag_type; -}; - -extern int inet_diag_register(const struct inet_diag_handler *handler); -extern void inet_diag_unregister(const struct inet_diag_handler *handler); -#endif /* __KERNEL__ */ - -#endif /* _INET_DIAG_H_ */ -- cgit v1.2.3 From 0ba2c6e8c0fb5cde5a23a213c2e7cb851b85c310 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Sat, 13 Aug 2005 13:55:44 -0700 Subject: [NETFILTER]: introduce and use aligned_u64 data type As proposed by Andi Kleen, this is required esp. for x86_64 architecture, where 64bit code needs 8byte aligned 64bit data types, but 32bit userspace apps will only align to 4bytes. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink_log.h | 5 +++-- include/linux/netfilter/nfnetlink_queue.h | 5 +++-- include/linux/types.h | 3 +++ 3 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_log.h b/include/linux/netfilter/nfnetlink_log.h index a61836a083e7..b04b03880595 100644 --- a/include/linux/netfilter/nfnetlink_log.h +++ b/include/linux/netfilter/nfnetlink_log.h @@ -5,6 +5,7 @@ * and not any kind of function definitions. It is shared between kernel and * userspace. Don't put kernel specific stuff in here */ +#include #include enum nfulnl_msg_types { @@ -27,8 +28,8 @@ struct nfulnl_msg_packet_hw { } __attribute__ ((packed)); struct nfulnl_msg_packet_timestamp { - u_int64_t sec; - u_int64_t usec; + aligned_u64 sec; + aligned_u64 usec; } __attribute__ ((packed)); #define NFULNL_PREFIXLEN 30 /* just like old log target */ diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h index 2d8d2b2cfcaa..9e774373244c 100644 --- a/include/linux/netfilter/nfnetlink_queue.h +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -1,6 +1,7 @@ #ifndef _NFNETLINK_QUEUE_H #define _NFNETLINK_QUEUE_H +#include #include enum nfqnl_msg_types { @@ -24,8 +25,8 @@ struct nfqnl_msg_packet_hw { } __attribute__ ((packed)); struct nfqnl_msg_packet_timestamp { - u_int64_t sec; - u_int64_t usec; + aligned_u64 sec; + aligned_u64 usec; } __attribute__ ((packed)); enum nfqnl_attr_type { diff --git a/include/linux/types.h b/include/linux/types.h index dcb13f865df9..2b678c22ca4a 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -123,6 +123,9 @@ typedef __u64 u_int64_t; typedef __s64 int64_t; #endif +/* this is a special 64bit data type that is 8-byte aligned */ +#define aligned_u64 unsigned long long __attribute__((aligned(8))) + /* * The type used for indexing onto a disc or disc partition. * If required, asm/types.h can override it and define -- cgit v1.2.3 From 9d810fd2d28a9d672eca3136476af1a54a380bb2 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Sat, 13 Aug 2005 13:56:26 -0700 Subject: [NETFILTER]: Add new iptables "connbytes" match This patch ads a new "connbytes" match that utilizes the CONFIG_NF_CT_ACCT per-connection byte and packet counters. Using it you can do things like packet classification on average packet size within a connection. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ipt_connbytes.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/netfilter_ipv4/ipt_connbytes.h (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ipt_connbytes.h b/include/linux/netfilter_ipv4/ipt_connbytes.h new file mode 100644 index 000000000000..abaa65afd4e9 --- /dev/null +++ b/include/linux/netfilter_ipv4/ipt_connbytes.h @@ -0,0 +1,25 @@ +#ifndef _IPT_CONNBYTES_H +#define _IPT_CONNBYTES_H + +enum ipt_connbytes_what { + IPT_CONNBYTES_WHAT_PKTS, + IPT_CONNBYTES_WHAT_BYTES, + IPT_CONNBYTES_WHAT_AVGPKT, +}; + +enum ipt_connbytes_direction { + IPT_CONNBYTES_DIR_ORIGINAL, + IPT_CONNBYTES_DIR_REPLY, + IPT_CONNBYTES_DIR_BOTH, +}; + +struct ipt_connbytes_info +{ + struct { + aligned_u64 from; /* count to be matched */ + aligned_u64 to; /* count to be matched */ + } count; + u_int8_t what; /* ipt_connbytes_what */ + u_int8_t direction; /* ipt_connbytes_direction */ +}; +#endif -- cgit v1.2.3 From 25ed891019b84498c83903ecf53df7ce35e9cff6 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 13 Aug 2005 13:58:21 -0700 Subject: [NETFILTER]: Nicer names for ipt_connbytes constants Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ipt_connbytes.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ipt_connbytes.h b/include/linux/netfilter_ipv4/ipt_connbytes.h index abaa65afd4e9..9e5532f8d8ac 100644 --- a/include/linux/netfilter_ipv4/ipt_connbytes.h +++ b/include/linux/netfilter_ipv4/ipt_connbytes.h @@ -2,9 +2,9 @@ #define _IPT_CONNBYTES_H enum ipt_connbytes_what { - IPT_CONNBYTES_WHAT_PKTS, - IPT_CONNBYTES_WHAT_BYTES, - IPT_CONNBYTES_WHAT_AVGPKT, + IPT_CONNBYTES_PKTS, + IPT_CONNBYTES_BYTES, + IPT_CONNBYTES_AVGPKT, }; enum ipt_connbytes_direction { -- cgit v1.2.3 From a61bbcf28a8cb0ba56f8193d512f7222e711a294 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 14 Aug 2005 17:24:31 -0700 Subject: [NET]: Store skb->timestamp as offset to a base timestamp Reduces skb size by 8 bytes on 64-bit. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/skbuff.h | 47 +++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 45 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 60b32151f76a..32635c401d4d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -155,13 +155,20 @@ struct skb_shared_info { #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) +extern struct timeval skb_tv_base; + +struct skb_timeval { + u32 off_sec; + u32 off_usec; +}; + /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list * @list: List we are on * @sk: Socket we are owned by - * @stamp: Time we arrived + * @tstamp: Time we arrived stored as offset to skb_tv_base * @dev: Device we arrived on/are leaving by * @input_dev: Device we arrived on * @h: Transport layer header @@ -202,7 +209,7 @@ struct sk_buff { struct sk_buff *prev; struct sock *sk; - struct timeval stamp; + struct skb_timeval tstamp; struct net_device *dev; struct net_device *input_dev; @@ -1213,6 +1220,42 @@ static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, extern void skb_init(void); extern void skb_add_mtu(int mtu); +/** + * skb_get_timestamp - get timestamp from a skb + * @skb: skb to get stamp from + * @stamp: pointer to struct timeval to store stamp in + * + * Timestamps are stored in the skb as offsets to a base timestamp. + * This function converts the offset back to a struct timeval and stores + * it in stamp. + */ +static inline void skb_get_timestamp(struct sk_buff *skb, struct timeval *stamp) +{ + stamp->tv_sec = skb->tstamp.off_sec; + stamp->tv_usec = skb->tstamp.off_usec; + if (skb->tstamp.off_sec) { + stamp->tv_sec += skb_tv_base.tv_sec; + stamp->tv_usec += skb_tv_base.tv_usec; + } +} + +/** + * skb_set_timestamp - set timestamp of a skb + * @skb: skb to set stamp of + * @stamp: pointer to struct timeval to get stamp from + * + * Timestamps are stored in the skb as offsets to a base timestamp. + * This function converts a struct timeval to an offset and stores + * it in the skb. + */ +static inline void skb_set_timestamp(struct sk_buff *skb, struct timeval *stamp) +{ + skb->tstamp.off_sec = stamp->tv_sec - skb_tv_base.tv_sec; + skb->tstamp.off_usec = stamp->tv_usec - skb_tv_base.tv_usec; +} + +extern void __net_timestamp(struct sk_buff *skb); + #ifdef CONFIG_NETFILTER static inline void nf_conntrack_put(struct nf_conntrack *nfct) { -- cgit v1.2.3 From fb13ab2849074244a51ae5147483610529a29ced Mon Sep 17 00:00:00 2001 From: Domen Puncer Date: Sun, 14 Aug 2005 17:32:05 -0700 Subject: [NETFILTER]: Remove two unused files Signed-off-by: Domen Puncer Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_logging.h | 20 -------------------- include/linux/netfilter_ipv6/ip6_logging.h | 20 -------------------- 2 files changed, 40 deletions(-) delete mode 100644 include/linux/netfilter_ipv4/ip_logging.h delete mode 100644 include/linux/netfilter_ipv6/ip6_logging.h (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_logging.h b/include/linux/netfilter_ipv4/ip_logging.h deleted file mode 100644 index 0c5c52cb6589..000000000000 --- a/include/linux/netfilter_ipv4/ip_logging.h +++ /dev/null @@ -1,20 +0,0 @@ -/* IPv4 macros for the internal logging interface. */ -#ifndef __IP_LOGGING_H -#define __IP_LOGGING_H - -#ifdef __KERNEL__ -#include -#include - -#define nf_log_ip_packet(pskb,hooknum,in,out,fmt,args...) \ - nf_log_packet(AF_INET,pskb,hooknum,in,out,fmt,##args) - -#define nf_log_ip(pfh,len,fmt,args...) \ - nf_log(AF_INET,pfh,len,fmt,##args) - -#define nf_ip_log_register(logging) nf_log_register(AF_INET,logging) -#define nf_ip_log_unregister(logging) nf_log_unregister(AF_INET,logging) - -#endif /*__KERNEL__*/ - -#endif /*__IP_LOGGING_H*/ diff --git a/include/linux/netfilter_ipv6/ip6_logging.h b/include/linux/netfilter_ipv6/ip6_logging.h deleted file mode 100644 index a0b2ee3043aa..000000000000 --- a/include/linux/netfilter_ipv6/ip6_logging.h +++ /dev/null @@ -1,20 +0,0 @@ -/* IPv6 macros for the nternal logging interface. */ -#ifndef __IP6_LOGGING_H -#define __IP6_LOGGING_H - -#ifdef __KERNEL__ -#include -#include - -#define nf_log_ip6_packet(pskb,hooknum,in,out,fmt,args...) \ - nf_log_packet(AF_INET6,pskb,hooknum,in,out,fmt,##args) - -#define nf_log_ip6(pfh,len,fmt,args...) \ - nf_log(AF_INET6,pfh,len,fmt,##args) - -#define nf_ip6_log_register(logging) nf_log_register(AF_INET6,logging) -#define nf_ip6_log_unregister(logging) nf_log_unregister(AF_INET6,logging) - -#endif /*__KERNEL__*/ - -#endif /*__IP6_LOGGING_H*/ -- cgit v1.2.3 From db080529798b497eb5a37b92a25e966be5a7dd5d Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 14 Aug 2005 19:26:34 -0700 Subject: [NETLINK]: Remove unused groups member from struct netlink_skb_parms Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index d5e09bcd80f9..eab51f9c9c86 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -106,7 +106,6 @@ struct netlink_skb_parms { struct ucred creds; /* Skb credentials */ __u32 pid; - __u32 groups; __u32 dst_pid; __u32 dst_groups; kernel_cap_t eff_cap; -- cgit v1.2.3 From d629b836d151d43332492651dd841d32e57ebe3b Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 14 Aug 2005 19:27:50 -0700 Subject: [NETLINK]: Use group numbers instead of bitmasks internally Using the group number allows increasing the number of groups without beeing limited by the size of the bitmask. It introduces one limitation for netlink users: messages can't be broadcasted to multiple groups anymore, however this feature was never used inside the kernel. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index eab51f9c9c86..c724c9d4984a 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -107,7 +107,7 @@ struct netlink_skb_parms struct ucred creds; /* Skb credentials */ __u32 pid; __u32 dst_pid; - __u32 dst_groups; + __u32 dst_group; kernel_cap_t eff_cap; __u32 loginuid; /* Login (audit) uid */ }; -- cgit v1.2.3 From ac6d439d2097b72ea0cbc2322ce1263a38bc1fd0 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 14 Aug 2005 19:29:52 -0700 Subject: [NETLINK]: Convert netlink users to use group numbers instead of bitmasks Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 23 +++++++++++++++++++- include/linux/netfilter_decnet.h | 14 +++++++++++++ include/linux/rtnetlink.h | 42 ++++++++++++++++++++++++++++++++++--- include/linux/selinux_netlink.h | 13 +++++++++++- include/linux/xfrm.h | 18 ++++++++++++++++ 5 files changed, 105 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index b0feb2374079..1d5b10ae2399 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -2,13 +2,34 @@ #define _NFNETLINK_H #include -/* nfnetlink groups: Up to 32 maximum */ +#ifndef __KERNEL__ +/* nfnetlink groups: Up to 32 maximum - backwards compatibility for userspace */ #define NF_NETLINK_CONNTRACK_NEW 0x00000001 #define NF_NETLINK_CONNTRACK_UPDATE 0x00000002 #define NF_NETLINK_CONNTRACK_DESTROY 0x00000004 #define NF_NETLINK_CONNTRACK_EXP_NEW 0x00000008 #define NF_NETLINK_CONNTRACK_EXP_UPDATE 0x00000010 #define NF_NETLINK_CONNTRACK_EXP_DESTROY 0x00000020 +#endif + +enum nfnetlink_groups { + NFNLGRP_NONE, +#define NFNLGRP_NONE NFNLGRP_NONE + NFNLGRP_CONNTRACK_NEW, +#define NFNLGRP_CONNTRACK_NEW NFNLGRP_CONNTRACK_NEW + NFNLGRP_CONNTRACK_UPDATE, +#define NFNLGRP_CONNTRACK_UPDATE NFNLGRP_CONNTRACK_UPDATE + NFNLGRP_CONNTRACK_DESTROY, +#define NFNLGRP_CONNTRACK_DESTROY NFNLGRP_CONNTRACK_DESTROY + NFNLGRP_CONNTRACK_EXP_NEW, +#define NFNLGRP_CONNTRACK_EXP_NEW NFNLGRP_CONNTRACK_EXP_NEW + NFNLGRP_CONNTRACK_EXP_UPDATE, +#define NFNLGRP_CONNTRACK_EXP_UPDATE NFNLGRP_CONNTRACK_EXP_UPDATE + NFNLGRP_CONNTRACK_EXP_DESTROY, +#define NFNLGRP_CONNTRACK_EXP_DESTROY NFNLGRP_CONNTRACK_EXP_DESTROY + __NFNLGRP_MAX, +}; +#define NFNLGRP_MAX (__NFNLGRP_MAX - 1) /* Generic structure for encapsulation optional netfilter information. * It is reminiscent of sockaddr, but with sa_family replaced diff --git a/include/linux/netfilter_decnet.h b/include/linux/netfilter_decnet.h index 018979484150..6f425369ee29 100644 --- a/include/linux/netfilter_decnet.h +++ b/include/linux/netfilter_decnet.h @@ -56,7 +56,21 @@ struct nf_dn_rtmsg { #define NFDN_RTMSG(r) ((unsigned char *)(r) + NLMSG_ALIGN(sizeof(struct nf_dn_rtmsg))) +#ifndef __KERNEL__ +/* backwards compatibility for userspace */ #define DNRMG_L1_GROUP 0x01 #define DNRMG_L2_GROUP 0x02 +#endif + +enum { + DNRNG_NLGRP_NONE, +#define DNRNG_NLGRP_NONE DNRNG_NLGRP_NONE + DNRNG_NLGRP_L1, +#define DNRNG_NLGRP_L1 DNRNG_NLGRP_L1 + DNRNG_NLGRP_L2, +#define DNRNG_NLGRP_L2 DNRNG_NLGRP_L2 + __DNRNG_NLGRP_MAX +}; +#define DNRNG_NLGRP_MAX (__DNRNG_NLGRP_MAX - 1) #endif /*__LINUX_DECNET_NETFILTER_H*/ diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 657c05ab8f9e..c231e9a08f0b 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -826,9 +826,8 @@ enum #define TCA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg)))) #define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg)) - -/* RTnetlink multicast groups */ - +#ifndef __KERNEL__ +/* RTnetlink multicast groups - backwards compatibility for userspace */ #define RTMGRP_LINK 1 #define RTMGRP_NOTIFY 2 #define RTMGRP_NEIGH 4 @@ -847,6 +846,43 @@ enum #define RTMGRP_DECnet_ROUTE 0x4000 #define RTMGRP_IPV6_PREFIX 0x20000 +#endif + +/* RTnetlink multicast groups */ +enum rtnetlink_groups { + RTNLGRP_NONE, +#define RTNLGRP_NONE RTNLGRP_NONE + RTNLGRP_LINK, +#define RTNLGRP_LINK RTNLGRP_LINK + RTNLGRP_NOTIFY, +#define RTNLGRP_NOTIFY RTNLGRP_NOTIFY + RTNLGRP_NEIGH, +#define RTNLGRP_NEIGH RTNLGRP_NEIGH + RTNLGRP_TC, +#define RTNLGRP_TC RTNLGRP_TC + RTNLGRP_IPV4_IFADDR, +#define RTNLGRP_IPV4_IFADDR RTNLGRP_IPV4_IFADDR + RTNLGRP_IPV4_MROUTE, +#define RTNLGRP_IPV4_MROUTE RTNLGRP_IPV4_MROUTE + RTNLGRP_IPV4_ROUTE, +#define RTNLGRP_IPV4_ROUTE RTNLGRP_IPV4_ROUTE + RTNLGRP_IPV6_IFADDR, +#define RTNLGRP_IPV6_IFADDR RTNLGRP_IPV6_IFADDR + RTNLGRP_IPV6_MROUTE, +#define RTNLGRP_IPV6_MROUTE RTNLGRP_IPV6_MROUTE + RTNLGRP_IPV6_ROUTE, +#define RTNLGRP_IPV6_ROUTE RTNLGRP_IPV6_ROUTE + RTNLGRP_IPV6_IFINFO, +#define RTNLGRP_IPV6_IFINFO RTNLGRP_IPV6_IFINFO + RTNLGRP_DECnet_IFADDR, +#define RTNLGRP_DECnet_IFADDR RTNLGRP_DECnet_IFADDR + RTNLGRP_DECnet_ROUTE, +#define RTNLGRP_DECnet_ROUTE RTNLGRP_DECnet_ROUTE + RTNLGRP_IPV6_PREFIX, +#define RTNLGRP_IPV6_PREFIX RTNLGRP_IPV6_PREFIX + __RTNLGRP_MAX +}; +#define RTNLGRP_MAX (__RTNLGRP_MAX - 1) /* TC action piece */ struct tcamsg diff --git a/include/linux/selinux_netlink.h b/include/linux/selinux_netlink.h index 957e6ebca4e6..bbf489decd84 100644 --- a/include/linux/selinux_netlink.h +++ b/include/linux/selinux_netlink.h @@ -20,10 +20,21 @@ enum { SELNL_MSG_MAX }; -/* Multicast groups */ +#ifndef __KERNEL__ +/* Multicast groups - backwards compatiblility for userspace */ #define SELNL_GRP_NONE 0x00000000 #define SELNL_GRP_AVC 0x00000001 /* AVC notifications */ #define SELNL_GRP_ALL 0xffffffff +#endif + +enum selinux_nlgroups { + SELNLGRP_NONE, +#define SELNLGRP_NONE SELNLGRP_NONE + SELNLGRP_AVC, +#define SELNLGRP_AVC SELNLGRP_AVC + __SELNLGRP_MAX +}; +#define SELNLGRP_MAX (__SELNLGRP_MAX - 1) /* Message structures */ struct selnl_msg_setenforce { diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index f0d423300d84..0fb077d68441 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -258,9 +258,27 @@ struct xfrm_usersa_flush { __u8 proto; }; +#ifndef __KERNEL__ +/* backwards compatibility for userspace */ #define XFRMGRP_ACQUIRE 1 #define XFRMGRP_EXPIRE 2 #define XFRMGRP_SA 4 #define XFRMGRP_POLICY 8 +#endif + +enum xfrm_nlgroups { + XFRMNLGRP_NONE, +#define XFRMNLGRP_NONE XFRMNLGRP_NONE + XFRMNLGRP_ACQUIRE, +#define XFRMNLGRP_ACQUIRE XFRMNLGRP_ACQUIRE + XFRMNLGRP_EXPIRE, +#define XFRMNLGRP_EXPIRE XFRMNLGRP_EXPIRE + XFRMNLGRP_SA, +#define XFRMNLGRP_SA XFRMNLGRP_SA + XFRMNLGRP_POLICY, +#define XFRMNLGRP_POLICY XFRMNLGRP_POLICY + __XFRMNLGRP_MAX +}; +#define XFRMNLGRP_MAX (__XFRMNLGRP_MAX - 1) #endif /* _LINUX_XFRM_H */ -- cgit v1.2.3 From 9a4595bc7e67962f13232ee55a64e063062c3a99 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 15 Aug 2005 12:32:15 -0700 Subject: [NETLINK]: Add set/getsockopt options to support more than 32 groups NETLINK_ADD_MEMBERSHIP/NETLINK_DROP_MEMBERSHIP are used to join/leave groups, NETLINK_PKTINFO is used to enable nl_pktinfo control messages for received packets to get the extended destination group number. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netlink.h | 9 +++++++++ include/linux/socket.h | 1 + 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index c724c9d4984a..36a40449f9f1 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -90,6 +90,15 @@ struct nlmsgerr struct nlmsghdr msg; }; +#define NETLINK_ADD_MEMBERSHIP 1 +#define NETLINK_DROP_MEMBERSHIP 2 +#define NETLINK_PKTINFO 3 + +struct nl_pktinfo +{ + __u32 group; +}; + #define NET_MAJOR 36 /* Major 36 is reserved for networking */ enum { diff --git a/include/linux/socket.h b/include/linux/socket.h index ddf22559f484..acc55aac8a43 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -272,6 +272,7 @@ struct ucred { #define SOL_NETBEUI 267 #define SOL_LLC 268 #define SOL_DCCP 269 +#define SOL_NETLINK 270 /* IPX options */ #define IPX_TYPE 1 -- cgit v1.2.3 From 066286071d3542243baa68166acb779187c848b3 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 15 Aug 2005 12:33:26 -0700 Subject: [NETLINK]: Add "groups" argument to netlink_kernel_create Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 36a40449f9f1..7d1d9683b246 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -125,7 +125,7 @@ struct netlink_skb_parms #define NETLINK_CREDS(skb) (&NETLINK_CB((skb)).creds) -extern struct sock *netlink_kernel_create(int unit, void (*input)(struct sock *sk, int len), struct module *module); +extern struct sock *netlink_kernel_create(int unit, unsigned int groups, void (*input)(struct sock *sk, int len), struct module *module); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid, -- cgit v1.2.3 From 20380731bc2897f2952ae055420972ded4cd786e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 16 Aug 2005 02:18:02 -0300 Subject: [NET]: Fix sparse warnings Of this type, mostly: CHECK net/ipv6/netfilter.c net/ipv6/netfilter.c:96:12: warning: symbol 'ipv6_netfilter_init' was not declared. Should it be static? net/ipv6/netfilter.c:101:6: warning: symbol 'ipv6_netfilter_fini' was not declared. Should it be static? Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/if_ether.h | 2 ++ include/linux/if_frad.h | 6 ++++-- include/linux/if_tr.h | 4 ++++ include/linux/igmp.h | 3 +++ include/linux/net.h | 7 +++++++ include/linux/netdevice.h | 10 ++++++++++ include/linux/netfilter_ipv6.h | 4 ++-- include/linux/security.h | 6 ++++-- include/linux/skbuff.h | 2 ++ include/linux/socket.h | 7 +++++++ 10 files changed, 45 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index b5b58e9c054c..fc2d4c8225aa 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -110,6 +110,8 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb->mac.raw; } + +extern struct ctl_table ether_table[]; #endif #endif /* _LINUX_IF_ETHER_H */ diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h index 3c94b1736570..511999c7eeda 100644 --- a/include/linux/if_frad.h +++ b/include/linux/if_frad.h @@ -191,10 +191,12 @@ struct frad_local int buffer; /* current buffer for S508 firmware */ }; -extern void dlci_ioctl_set(int (*hook)(unsigned int, void __user *)); - #endif /* __KERNEL__ */ #endif /* CONFIG_DLCI || CONFIG_DLCI_MODULE */ +#ifdef __KERNEL__ +extern void dlci_ioctl_set(int (*hook)(unsigned int, void __user *)); +#endif + #endif diff --git a/include/linux/if_tr.h b/include/linux/if_tr.h index 3fba9e2f5427..5502f597cf0e 100644 --- a/include/linux/if_tr.h +++ b/include/linux/if_tr.h @@ -43,12 +43,16 @@ struct trh_hdr { }; #ifdef __KERNEL__ +#include #include static inline struct trh_hdr *tr_hdr(const struct sk_buff *skb) { return (struct trh_hdr *)skb->mac.raw; } +#ifdef CONFIG_SYSCTL +extern struct ctl_table tr_table[]; +#endif #endif /* This is an Token-Ring LLC structure */ diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 0c31ef0b5bad..28f4f3b36950 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -129,6 +129,9 @@ struct igmpv3_query { #include #include +extern int sysctl_igmp_max_memberships; +extern int sysctl_igmp_max_msf; + struct ip_sf_socklist { unsigned int sl_max; diff --git a/include/linux/net.h b/include/linux/net.h index 5f8b632ff653..4e981585a89a 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -286,5 +286,12 @@ static struct proto_ops name##_ops = { \ #define MODULE_ALIAS_NET_PF_PROTO(pf, proto) \ MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto)) +#ifdef CONFIG_SYSCTL +#include +extern ctl_table net_table[]; +extern int net_msg_cost; +extern int net_msg_burst; +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_NET_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d8e52edfd526..1fcaa88b8625 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -244,6 +244,7 @@ struct netdev_boot_setup { }; #define NETDEV_BOOT_SETUP_MAX 8 +extern int __init netdev_boot_setup(char *str); /* * The DEVICE structure. @@ -673,6 +674,7 @@ extern void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); extern void dev_init(void); extern int netdev_nit; +extern int netdev_budget; /* Called by rtnetlink.c:rtnl_unlock() */ extern void netdev_run_todo(void); @@ -908,6 +910,14 @@ extern int skb_checksum_help(struct sk_buff *skb, int inward); extern void net_enable_timestamp(void); extern void net_disable_timestamp(void); +#ifdef CONFIG_PROC_FS +extern void *dev_seq_start(struct seq_file *seq, loff_t *pos); +extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos); +extern void dev_seq_stop(struct seq_file *seq, void *v); +#endif + +extern void linkwatch_run_queue(void); + #endif /* __KERNEL__ */ #endif /* _LINUX_DEV_H */ diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 5d204ee7a312..edcc2c6eb5c7 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -71,7 +71,7 @@ enum nf_ip6_hook_priorities { NF_IP6_PRI_LAST = INT_MAX, }; -int ipv6_netfilter_init(void); -void ipv6_netfilter_fini(void); +extern int ipv6_netfilter_init(void); +extern void ipv6_netfilter_fini(void); #endif /*__LINUX_IP6_NETFILTER_H*/ diff --git a/include/linux/security.h b/include/linux/security.h index b42095a68b1c..7aab6ab7c57f 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2727,7 +2727,8 @@ static inline int security_socket_getpeersec(struct socket *sock, char __user *o return security_ops->socket_getpeersec(sock, optval, optlen, len); } -static inline int security_sk_alloc(struct sock *sk, int family, int priority) +static inline int security_sk_alloc(struct sock *sk, int family, + unsigned int __nocast priority) { return security_ops->sk_alloc_security(sk, family, priority); } @@ -2844,7 +2845,8 @@ static inline int security_socket_getpeersec(struct socket *sock, char __user *o return -ENOPROTOOPT; } -static inline int security_sk_alloc(struct sock *sk, int family, int priority) +static inline int security_sk_alloc(struct sock *sk, int family, + unsigned int __nocast priority) { return 0; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 32635c401d4d..db10335e4192 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1203,6 +1203,8 @@ extern void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); extern void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); +extern void skb_release_data(struct sk_buff *skb); + static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { diff --git a/include/linux/socket.h b/include/linux/socket.h index acc55aac8a43..1739c2d5b95b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -26,6 +26,13 @@ struct __kernel_sockaddr_storage { #include /* pid_t */ #include /* __user */ +extern int sysctl_somaxconn; +extern void sock_init(void); +#ifdef CONFIG_PROC_FS +struct seq_file; +extern void socket_seq_show(struct seq_file *seq); +#endif + typedef unsigned short sa_family_t; /* -- cgit v1.2.3 From 6ed8a48582c08432e84e5610564c1d25fe00dd7f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 16 Aug 2005 19:02:15 -0300 Subject: [NETLINK]: Fix sparse warnings Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 7d1d9683b246..167518668936 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -129,7 +129,7 @@ extern struct sock *netlink_kernel_create(int unit, unsigned int groups, void (* extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid, - __u32 group, int allocation); + __u32 group, unsigned int __nocast allocation); extern void netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code); extern int netlink_register_notifier(struct notifier_block *nb); extern int netlink_unregister_notifier(struct notifier_block *nb); -- cgit v1.2.3 From d179cd12928443f3ec29cfbc3567439644bd0afc Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 17 Aug 2005 14:57:30 -0700 Subject: [NET]: Implement SKB fast cloning. Protocols that make extensive use of SKB cloning, for example TCP, eat at least 2 allocations per packet sent as a result. To cut the kmalloc() count in half, we implement a pre-allocation scheme wherein we allocate 2 sk_buff objects in advance, then use a simple reference count to free up the memory at the correct time. Based upon an initial patch by Thomas Graf and suggestions from Herbert Xu. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index db10335e4192..42edce6abe23 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -162,6 +162,13 @@ struct skb_timeval { u32 off_usec; }; + +enum { + SKB_FCLONE_UNAVAILABLE, + SKB_FCLONE_ORIG, + SKB_FCLONE_CLONE, +}; + /** * struct sk_buff - socket buffer * @next: Next buffer in list @@ -255,7 +262,8 @@ struct sk_buff { ip_summed:2, nohdr:1, nfctinfo:3; - __u8 pkt_type; + __u8 pkt_type:3, + fclone:2; __be16 protocol; void (*destructor)(struct sk_buff *skb); @@ -295,8 +303,20 @@ struct sk_buff { #include extern void __kfree_skb(struct sk_buff *skb); -extern struct sk_buff *alloc_skb(unsigned int size, - unsigned int __nocast priority); +extern struct sk_buff *__alloc_skb(unsigned int size, + unsigned int __nocast priority, int fclone); +static inline struct sk_buff *alloc_skb(unsigned int size, + unsigned int __nocast priority) +{ + return __alloc_skb(size, priority, 0); +} + +static inline struct sk_buff *alloc_skb_fclone(unsigned int size, + unsigned int __nocast priority) +{ + return __alloc_skb(size, priority, 1); +} + extern struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp, unsigned int size, unsigned int __nocast priority); -- cgit v1.2.3 From 1bc0986957b63a2fbbc46ab95d3d1d72830bda83 Mon Sep 17 00:00:00 2001 From: Ian McDonald Date: Sat, 20 Aug 2005 00:23:43 -0300 Subject: [DCCP]: Fix the timestamp options This changes timestamp, timestamp echo, and elapsed time to use units of 10 usecs as per DCCP spec. This has been tested to verify that times are correct. Also fixed up length and used hton/ntoh more. Still to add in later patches: - actually use elapsed time to adjust RTT (commented out as was prior to this patch) - send options at times more closely following the spec (content is now correct) Signed-off-by: Ian McDonald Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 3dccdd5108b5..9e3a1370b906 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -415,7 +415,7 @@ struct dccp_sock { __u64 dccps_gsr; __u64 dccps_gar; unsigned long dccps_service; - unsigned long dccps_timestamp_time; + struct timeval dccps_timestamp_time; __u32 dccps_timestamp_echo; __u32 dccps_avg_packet_size; unsigned long dccps_ndp_count; -- cgit v1.2.3 From a6f9a70578b981321b63786ac8015f17cca4fcbd Mon Sep 17 00:00:00 2001 From: Jon Wetzel Date: Sat, 20 Aug 2005 17:15:54 -0700 Subject: [NET]: Add support for getting the permanent hardware address. This patch adds a new field to net device to hold the permanent hardware address, and adds a new generic ethtool_op function to get that address. Signed-off-by: Jon Wetzel Signed-off-by: John W. Linville Signed-off-by: David S. Miller --- include/linux/ethtool.h | 13 ++++++++++++- include/linux/netdevice.h | 1 + 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index d7021c391b2b..ed1440ea4c91 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -250,6 +250,12 @@ struct ethtool_stats { u64 data[0]; }; +struct ethtool_perm_addr { + u32 cmd; /* ETHTOOL_GPERMADDR */ + u32 size; + u8 data[0]; +}; + struct net_device; /* Some generic methods drivers may use in their ethtool_ops */ @@ -261,6 +267,8 @@ u32 ethtool_op_get_sg(struct net_device *dev); int ethtool_op_set_sg(struct net_device *dev, u32 data); u32 ethtool_op_get_tso(struct net_device *dev); int ethtool_op_set_tso(struct net_device *dev, u32 data); +int ethtool_op_get_perm_addr(struct net_device *dev, + struct ethtool_perm_addr *addr, u8 *data); /** * ðtool_ops - Alter and report network device settings @@ -294,7 +302,8 @@ int ethtool_op_set_tso(struct net_device *dev, u32 data); * get_strings: Return a set of strings that describe the requested objects * phys_id: Identify the device * get_stats: Return statistics about the device - * + * get_perm_addr: Gets the permanent hardware address + * * Description: * * get_settings: @@ -352,6 +361,7 @@ struct ethtool_ops { int (*phys_id)(struct net_device *, u32); int (*get_stats_count)(struct net_device *); void (*get_ethtool_stats)(struct net_device *, struct ethtool_stats *, u64 *); + int (*get_perm_addr)(struct net_device *, struct ethtool_perm_addr *, u8 *); int (*begin)(struct net_device *); void (*complete)(struct net_device *); }; @@ -389,6 +399,7 @@ struct ethtool_ops { #define ETHTOOL_GSTATS 0x0000001d /* get NIC-specific statistics */ #define ETHTOOL_GTSO 0x0000001e /* Get TSO enable (ethtool_value) */ #define ETHTOOL_STSO 0x0000001f /* Set TSO enable (ethtool_value) */ +#define ETHTOOL_GPERMADDR 0x00000020 /* Get permanent hardware address */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1fcaa88b8625..7c717907896d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -337,6 +337,7 @@ struct net_device /* Interface address info. */ unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ unsigned char dev_addr[MAX_ADDR_LEN]; /* hw address */ + unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */ unsigned char addr_len; /* hardware address length */ unsigned short dev_id; /* for shared network cards */ -- cgit v1.2.3 From 7567662ba896ee0c33d6215f32e2011488a6d1bf Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 21 Aug 2005 23:30:34 -0700 Subject: [NETFILTER]: Add string match Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ipt_string.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/netfilter_ipv4/ipt_string.h (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ipt_string.h b/include/linux/netfilter_ipv4/ipt_string.h new file mode 100644 index 000000000000..a265f6e44eab --- /dev/null +++ b/include/linux/netfilter_ipv4/ipt_string.h @@ -0,0 +1,18 @@ +#ifndef _IPT_STRING_H +#define _IPT_STRING_H + +#define IPT_STRING_MAX_PATTERN_SIZE 128 +#define IPT_STRING_MAX_ALGO_NAME_SIZE 16 + +struct ipt_string_info +{ + u_int16_t from_offset; + u_int16_t to_offset; + char algo[IPT_STRING_MAX_ALGO_NAME_SIZE]; + char pattern[IPT_STRING_MAX_PATTERN_SIZE]; + u_int8_t patlen; + u_int8_t invert; + struct ts_config __attribute__((aligned(8))) *config; +}; + +#endif /*_IPT_STRING_H*/ -- cgit v1.2.3 From 764d8a9f240729534a1d8a0ffd39e722cf5cc5af Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 21 Aug 2005 23:31:06 -0700 Subject: [NETFILTER]: Add IPv6 REJECT target Originally written by Yasuyuki Kozakai , taken from netfilter patch-o-matic and fixed up to work with current kernels. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv6/ip6t_REJECT.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/netfilter_ipv6/ip6t_REJECT.h (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6/ip6t_REJECT.h b/include/linux/netfilter_ipv6/ip6t_REJECT.h new file mode 100644 index 000000000000..6be6504162bb --- /dev/null +++ b/include/linux/netfilter_ipv6/ip6t_REJECT.h @@ -0,0 +1,18 @@ +#ifndef _IP6T_REJECT_H +#define _IP6T_REJECT_H + +enum ip6t_reject_with { + IP6T_ICMP6_NO_ROUTE, + IP6T_ICMP6_ADM_PROHIBITED, + IP6T_ICMP6_NOT_NEIGHBOUR, + IP6T_ICMP6_ADDR_UNREACH, + IP6T_ICMP6_PORT_UNREACH, + IP6T_ICMP6_ECHOREPLY, + IP6T_TCP_RESET +}; + +struct ip6t_reject_info { + u_int32_t with; /* reject type */ +}; + +#endif /*_IP6T_REJECT_H*/ -- cgit v1.2.3 From 05465343bf74e00c8c2c5a310740157de3149f27 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 21 Aug 2005 23:31:43 -0700 Subject: [NETFILTER]: Add goto target Originally written by Henrik Nordstrom , taken from netfilter patch-o-matic and added ip6_tables support. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_tables.h | 3 ++- include/linux/netfilter_ipv6/ip6_tables.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 12ce47808e7d..d19d65cf4530 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -109,7 +109,8 @@ struct ipt_counters /* Values for "flag" field in struct ipt_ip (general ip structure). */ #define IPT_F_FRAG 0x01 /* Set if rule is a fragment rule */ -#define IPT_F_MASK 0x01 /* All possible flag bits mask. */ +#define IPT_F_GOTO 0x02 /* Set if jump is a goto */ +#define IPT_F_MASK 0x03 /* All possible flag bits mask. */ /* Values for "inv" field in struct ipt_ip. */ #define IPT_INV_VIA_IN 0x01 /* Invert the sense of IN IFACE. */ diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index f1ce3b009853..58c72a52dc65 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -111,7 +111,8 @@ struct ip6t_counters #define IP6T_F_PROTO 0x01 /* Set if rule cares about upper protocols */ #define IP6T_F_TOS 0x02 /* Match the TOS. */ -#define IP6T_F_MASK 0x03 /* All possible flag bits mask. */ +#define IP6T_F_GOTO 0x04 /* Set if jump is a goto */ +#define IP6T_F_MASK 0x07 /* All possible flag bits mask. */ /* Values for "inv" field in struct ip6t_ip6. */ #define IP6T_INV_VIA_IN 0x01 /* Invert the sense of IN IFACE. */ -- cgit v1.2.3 From e5b4376074e02b783e56a8f7c42d544e18112c4e Mon Sep 17 00:00:00 2001 From: Robert Olsson Date: Thu, 25 Aug 2005 13:01:03 -0700 Subject: [IPV4]: Prepare FIB core for RCU. * RCU versions of hlist_***_rcu * fib_alias partial rcu port just whats needed now. Signed-off-by: Robert Olsson Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/list.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 0f2435f92db3..9b9b0eec1e8a 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -634,6 +634,27 @@ static inline void hlist_add_after(struct hlist_node *n, next->next->pprev = &next->next; } +static inline void hlist_add_before_rcu(struct hlist_node *n, + struct hlist_node *next) +{ + n->pprev = next->pprev; + n->next = next; + smp_wmb(); + next->pprev = &n->next; + *(n->pprev) = n; +} + +static inline void hlist_add_after_rcu(struct hlist_node *prev, + struct hlist_node *n) +{ + n->next = prev->next; + n->pprev = &prev->next; + smp_wmb(); + prev->next = n; + if (n->next) + n->next->pprev = &n->next; +} + #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ -- cgit v1.2.3 From 57bf1451ac79640c5a0a4f31284c43539fac2903 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 25 Aug 2005 16:06:19 -0700 Subject: [NET]: net/802: more endian annotations The rest of endian warnings now belongs to tr.c exclusively. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/linux/hippidevice.h | 3 +-- include/linux/if_fc.h | 2 +- include/linux/if_fddi.h | 2 +- include/linux/if_hippi.h | 6 +++--- 4 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hippidevice.h b/include/linux/hippidevice.h index 9bc3b688d2ee..bab303dafd6e 100644 --- a/include/linux/hippidevice.h +++ b/include/linux/hippidevice.h @@ -31,8 +31,7 @@ struct hippi_cb { __u32 ifield; }; -extern unsigned short hippi_type_trans(struct sk_buff *skb, - struct net_device *dev); +extern __be16 hippi_type_trans(struct sk_buff *skb, struct net_device *dev); extern struct net_device *alloc_hippi_dev(int sizeof_priv); #endif diff --git a/include/linux/if_fc.h b/include/linux/if_fc.h index 33330b458b95..376a34ea4723 100644 --- a/include/linux/if_fc.h +++ b/include/linux/if_fc.h @@ -44,7 +44,7 @@ struct fcllc { __u8 ssap; /* source SAP */ __u8 llc; /* LLC control field */ __u8 protid[3]; /* protocol id */ - __u16 ethertype; /* ether type field */ + __be16 ethertype; /* ether type field */ }; #endif /* _LINUX_IF_FC_H */ diff --git a/include/linux/if_fddi.h b/include/linux/if_fddi.h index a912818e6361..1288a161bc0b 100644 --- a/include/linux/if_fddi.h +++ b/include/linux/if_fddi.h @@ -85,7 +85,7 @@ struct fddi_snap_hdr __u8 ssap; /* always 0xAA */ __u8 ctrl; /* always 0x03 */ __u8 oui[FDDI_K_OUI_LEN]; /* organizational universal id */ - __u16 ethertype; /* packet type ID field */ + __be16 ethertype; /* packet type ID field */ } __attribute__ ((packed)); /* Define FDDI LLC frame header */ diff --git a/include/linux/if_hippi.h b/include/linux/if_hippi.h index c8ca72c46f76..94d31ca7d71a 100644 --- a/include/linux/if_hippi.h +++ b/include/linux/if_hippi.h @@ -102,9 +102,9 @@ struct hippi_fp_hdr #error "Please fix " #endif #else - __u32 fixed; + __be32 fixed; #endif - __u32 d2_size; + __be32 d2_size; } __attribute__ ((packed)); struct hippi_le_hdr @@ -144,7 +144,7 @@ struct hippi_snap_hdr __u8 ssap; /* always 0xAA */ __u8 ctrl; /* always 0x03 */ __u8 oui[HIPPI_OUI_LEN]; /* organizational universal id (zero)*/ - __u16 ethertype; /* packet type ID field */ + __be16 ethertype; /* packet type ID field */ } __attribute__ ((packed)); struct hippi_hdr -- cgit v1.2.3 From cf4ef01440ca5c6d96f2ea2b793a37a0a863a045 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 25 Aug 2005 16:08:37 -0700 Subject: [LIST]: Add docbook header comments for hlist_add_{before,after}_rcu() Signed-off-by: David S. Miller --- include/linux/list.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 9b9b0eec1e8a..e6ec59682274 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -634,6 +634,21 @@ static inline void hlist_add_after(struct hlist_node *n, next->next->pprev = &next->next; } +/** + * hlist_add_before_rcu - adds the specified element to the specified hlist + * before the specified node while permitting racing traversals. + * @n: the new element to add to the hash list. + * @next: the existing element to add the new element before. + * + * 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_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. + */ static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { @@ -644,6 +659,21 @@ static inline void hlist_add_before_rcu(struct hlist_node *n, *(n->pprev) = n; } +/** + * hlist_add_after_rcu - adds the specified element to the specified hlist + * after the specified node while permitting racing traversals. + * @prev: the existing element to add the new element after. + * @n: the new element to add to the hash list. + * + * 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_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. + */ static inline void hlist_add_after_rcu(struct hlist_node *prev, struct hlist_node *n) { -- cgit v1.2.3 From 5f2c3b910744f68e1a507f027398f404b3feb5fb Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Sat, 27 Aug 2005 22:37:03 -0700 Subject: [NETFILTER]: Add new iptables TTL target This new iptables target allows manipulation of the TTL of an IPv4 packet. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ipt_TTL.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/netfilter_ipv4/ipt_TTL.h (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ipt_TTL.h b/include/linux/netfilter_ipv4/ipt_TTL.h new file mode 100644 index 000000000000..ee6611edc112 --- /dev/null +++ b/include/linux/netfilter_ipv4/ipt_TTL.h @@ -0,0 +1,21 @@ +/* TTL modification module for IP tables + * (C) 2000 by Harald Welte */ + +#ifndef _IPT_TTL_H +#define _IPT_TTL_H + +enum { + IPT_TTL_SET = 0, + IPT_TTL_INC, + IPT_TTL_DEC +}; + +#define IPT_TTL_MAXMODE IPT_TTL_DEC + +struct ipt_TTL_info { + u_int8_t mode; + u_int8_t ttl; +}; + + +#endif -- cgit v1.2.3 From 0ac4f893f20ed524198da5ebf591fc0b9e2ced2f Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Sat, 27 Aug 2005 22:37:30 -0700 Subject: [NETFILTER6]: Add new ip6tables HOPLIMIT target This target allows users to modify the hoplimit header field of the IPv6 header. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv6/ip6t_HL.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 include/linux/netfilter_ipv6/ip6t_HL.h (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6/ip6t_HL.h b/include/linux/netfilter_ipv6/ip6t_HL.h new file mode 100644 index 000000000000..afb7813d45ab --- /dev/null +++ b/include/linux/netfilter_ipv6/ip6t_HL.h @@ -0,0 +1,22 @@ +/* Hop Limit modification module for ip6tables + * Maciej Soltysiak + * Based on HW's TTL module */ + +#ifndef _IP6T_HL_H +#define _IP6T_HL_H + +enum { + IP6T_HL_SET = 0, + IP6T_HL_INC, + IP6T_HL_DEC +}; + +#define IP6T_HL_MAXMODE IP6T_HL_DEC + +struct ip6t_HL_info { + u_int8_t mode; + u_int8_t hop_limit; +}; + + +#endif -- cgit v1.2.3 From a84ffe430342db6ee585a5038f3242a6b4112d69 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 28 Aug 2005 04:51:32 -0300 Subject: [DCCP]: Introduce DCCP_SOCKOPT_PACKET_SIZE So that applications can set dccp_sock->dccps_pkt_size, that in turn is used in the CCID3 half connection init routines to set ccid3hc[tr]x_s and use it in its rate calculations. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 9e3a1370b906..007c290f74d4 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -186,6 +186,9 @@ enum { DCCPF_MAX_CCID_SPECIFIC = 255, }; +/* DCCP socket options */ +#define DCCP_SOCKOPT_PACKET_SIZE 1 + #ifdef __KERNEL__ #include @@ -396,7 +399,7 @@ enum dccp_role { * @dccps_timestamp_echo - latest timestamp received on a TIMESTAMP option * @dccps_ext_header_len - network protocol overhead (IP/IPv6 options) * @dccps_pmtu_cookie - Last pmtu seen by socket - * @dccps_avg_packet_size - FIXME: has to be set by the app thru some setsockopt or ioctl, CCID3 uses it + * @dccps_packet_size - Set thru setsockopt * @dccps_role - Role of this sock, one of %dccp_role * @dccps_ndp_count - number of Non Data Packets since last data packet * @dccps_hc_rx_ackpkts - receiver half connection acked packets @@ -417,7 +420,7 @@ struct dccp_sock { unsigned long dccps_service; struct timeval dccps_timestamp_time; __u32 dccps_timestamp_echo; - __u32 dccps_avg_packet_size; + __u32 dccps_packet_size; unsigned long dccps_ndp_count; __u16 dccps_ext_header_len; __u32 dccps_pmtu_cookie; -- cgit v1.2.3 From fb120da678c517f72d4b39932062c2191827b331 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 17 Aug 2005 16:42:59 +1000 Subject: [PATCH] Make MODULE_DEVICE_TABLE work for vio devices Make MODULE_DEVICE_TABLE work for vio devices. Signed-off-by: Stephen Rothwell Signed-off-by: Paul Mackerras --- include/linux/mod_devicetable.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 97bbccdbcca3..47da39ba3f03 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -1,6 +1,6 @@ /* * Device tables which are exported to userspace via - * scripts/table2alias.c. You must keep that file in sync with this + * scripts/mod/file2alias.c. You must keep that file in sync with this * header. */ @@ -190,6 +190,11 @@ struct of_device_id #endif }; +/* VIO */ +struct vio_device_id { + char type[32]; + char compat[32]; +}; /* PCMCIA */ -- cgit v1.2.3 From d568121ce3151c36cc4718dd4e977f217c6144c2 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 30 Aug 2005 08:58:37 +0200 Subject: [PATCH] Assign device pointer to OSS devices Add register_sound_special_device() function to allow assignment of device pointer to a specific OSS device for HAL. Signed-off-by: Takashi Iwai --- include/linux/sound.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sound.h b/include/linux/sound.h index 428f59794f48..72b9af4c3fd4 100644 --- a/include/linux/sound.h +++ b/include/linux/sound.h @@ -29,7 +29,9 @@ * Sound core interface functions */ +struct device; extern int register_sound_special(struct file_operations *fops, int unit); +extern int register_sound_special_device(struct file_operations *fops, int unit, struct device *dev); extern int register_sound_mixer(struct file_operations *fops, int dev); extern int register_sound_midi(struct file_operations *fops, int dev); extern int register_sound_dsp(struct file_operations *fops, int dev); -- cgit v1.2.3 From 1623c81eece58740279b8de802fa5895221f2044 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Tue, 30 Aug 2005 03:37:42 -0400 Subject: [libata] allow ATAPI to be enabled with new atapi_enabled module option ATAPI is getting close to being ready. To increase exposure, we enable the code in the upstream kernel, but default it to off (present behavior). Users must pass atapi_enabled=1 as a module option (if module) or on the kernel command line (if built in) to turn on discovery of their ATAPI devices. --- include/linux/libata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index fc05a9899288..1eaba4077e15 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -40,7 +40,6 @@ #undef ATA_VERBOSE_DEBUG /* yet more debugging output */ #undef ATA_IRQ_TRAP /* define to ack screaming irqs */ #undef ATA_NDEBUG /* define to disable quick runtime checks */ -#undef ATA_ENABLE_ATAPI /* define to enable ATAPI support */ #undef ATA_ENABLE_PATA /* define to enable PATA support in some * low-level drivers */ #undef ATAPI_ENABLE_DMADIR /* enables ATAPI DMADIR bridge support */ -- cgit v1.2.3 From 374b1873571bf80dc0c1fcceaaad067980f3b9de Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Tue, 30 Aug 2005 05:42:52 -0400 Subject: [libata] update several drivers to use pci_iomap()/pci_iounmap() --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index fc05a9899288..bd0f79dfb9cd 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -450,6 +450,7 @@ struct pci_bits { unsigned long val; }; +extern void ata_pci_host_stop (struct ata_host_set *host_set); extern struct ata_probe_ent * ata_pci_init_native_mode(struct pci_dev *pdev, struct ata_port_info **port); extern int pci_test_config_bits(struct pci_dev *pdev, struct pci_bits *bits); -- cgit v1.2.3 From 53c165e0a6c8a4ff7df316557528fa7a52d20711 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Mon, 22 Aug 2005 10:06:19 -0500 Subject: [SCSI] correct attribute_container list usage One of the changes in the attribute_container code in the scsi-misc tree was to add a lock to protect the list of devices per container. This, unfortunately, leads to potential scheduling while atomic problems if there's a sleep in the function called by a trigger. The correct solution is to use the kernel klist infrastructure instead which allows lockless traversal of a list. Signed-off-by: James Bottomley --- include/linux/attribute_container.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/attribute_container.h b/include/linux/attribute_container.h index ee83fe64a102..93bfb0beb62a 100644 --- a/include/linux/attribute_container.h +++ b/include/linux/attribute_container.h @@ -11,12 +11,12 @@ #include #include +#include #include struct attribute_container { struct list_head node; - struct list_head containers; - spinlock_t containers_lock; + struct klist containers; struct class *class; struct class_device_attribute **attrs; int (*match)(struct attribute_container *, struct device *); -- cgit v1.2.3 From 61a7afa2c476a3be261cf88a95b0dea0c3bd29d4 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Tue, 16 Aug 2005 18:27:34 -0500 Subject: [SCSI] embryonic RAID class The idea behind a RAID class is to provide a uniform interface to all RAID subsystems (both hardware and software) in the kernel. To do that, I've made this class a transport class that's entirely subsystem independent (although the matching routines have to match per subsystem, as you'll see looking at the code). I put it in the scsi subdirectory purely because I needed somewhere to play with it, but it's not a scsi specific module. I used a fusion raid card as the test bed for this; with that kind of card, this is the type of class output you get: jejb@titanic> ls -l /sys/class/raid_devices/20\:0\:0\:0/ total 0 lrwxrwxrwx 1 root root 0 Aug 16 17:21 component-0 -> ../../../devices/pci0000:80/0000:80:04.0/host20/target20:1:0/20:1:0:0/ lrwxrwxrwx 1 root root 0 Aug 16 17:21 component-1 -> ../../../devices/pci0000:80/0000:80:04.0/host20/target20:1:1/20:1:1:0/ lrwxrwxrwx 1 root root 0 Aug 16 17:21 device -> ../../../devices/pci0000:80/0000:80:04.0/host20/target20:0:0/20:0:0:0/ -r--r--r-- 1 root root 16384 Aug 16 17:21 level -r--r--r-- 1 root root 16384 Aug 16 17:21 resync -r--r--r-- 1 root root 16384 Aug 16 17:21 state So it's really simple: for a SCSI device representing a hardware raid, it shows the raid level, the array state, the resync % complete (if the state is resyncing) and the underlying components of the RAID (these are exposed in fusion on the virtual channel 1). As you can see, this type of information can be exported by almost anything, including software raid. The more difficult trick, of course, is going to be getting it to perform configuration type actions with writable attributes. Signed-off-by: James Bottomley --- include/linux/raid_class.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 include/linux/raid_class.h (limited to 'include/linux') diff --git a/include/linux/raid_class.h b/include/linux/raid_class.h new file mode 100644 index 000000000000..a71123c28272 --- /dev/null +++ b/include/linux/raid_class.h @@ -0,0 +1,59 @@ +/* + */ +#include + +struct raid_template { + struct transport_container raid_attrs; +}; + +struct raid_function_template { + void *cookie; + int (*is_raid)(struct device *); + void (*get_resync)(struct device *); + void (*get_state)(struct device *); +}; + +enum raid_state { + RAID_ACTIVE = 1, + RAID_DEGRADED, + RAID_RESYNCING, + RAID_OFFLINE, +}; + +struct raid_data { + struct list_head component_list; + int component_count; + int level; + enum raid_state state; + int resync; +}; + +#define DEFINE_RAID_ATTRIBUTE(type, attr) \ +static inline void \ +raid_set_##attr(struct raid_template *r, struct device *dev, type value) { \ + struct class_device *cdev = \ + attribute_container_find_class_device(&r->raid_attrs.ac, dev);\ + struct raid_data *rd; \ + BUG_ON(!cdev); \ + rd = class_get_devdata(cdev); \ + rd->attr = value; \ +} \ +static inline type \ +raid_get_##attr(struct raid_template *r, struct device *dev) { \ + struct class_device *cdev = \ + attribute_container_find_class_device(&r->raid_attrs.ac, dev);\ + struct raid_data *rd; \ + BUG_ON(!cdev); \ + rd = class_get_devdata(cdev); \ + return rd->attr; \ +} + +DEFINE_RAID_ATTRIBUTE(int, level) +DEFINE_RAID_ATTRIBUTE(int, resync) +DEFINE_RAID_ATTRIBUTE(enum raid_state, state) + +struct raid_template *raid_class_attach(struct raid_function_template *); +void raid_class_release(struct raid_template *); + +void raid_component_add(struct raid_template *, struct device *, + struct device *); -- cgit v1.2.3 From 0f302dc35412dc67035efc188b9d5c40711b4222 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Wed, 31 Aug 2005 21:48:47 +0100 Subject: [ARM] 2866/1: add i.MX set_mctrl / get_mctrl functions Patch from Sascha Hauer This patch adds support for setting and getting RTS / CTS via set_mtctrl / get_mctrl functions. Signed-off-by: Sascha Hauer Signed-off-by: Russell King --- include/linux/serial.h | 4 ---- include/linux/serial_core.h | 2 -- 2 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial.h b/include/linux/serial.h index 9f2d85284d0b..12cd9cf65e8f 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -176,10 +176,6 @@ struct serial_icounter_struct { #ifdef __KERNEL__ #include -/* Export to allow PCMCIA to use this - Dave Hinds */ -extern int __deprecated register_serial(struct serial_struct *req); -extern void __deprecated unregister_serial(int line); - /* Allow architectures to override entries in serial8250_ports[] at run time: */ struct uart_port; /* forward declaration */ extern int early_serial_setup(struct uart_port *port); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 1c53302db041..cf0f64ea2bc0 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -360,8 +360,6 @@ struct tty_driver *uart_console_device(struct console *co, int *index); */ int uart_register_driver(struct uart_driver *uart); void uart_unregister_driver(struct uart_driver *uart); -void __deprecated uart_unregister_port(struct uart_driver *reg, int line); -int __deprecated uart_register_port(struct uart_driver *reg, struct uart_port *port); int uart_add_one_port(struct uart_driver *reg, struct uart_port *port); int uart_remove_one_port(struct uart_driver *reg, struct uart_port *port); int uart_match_port(struct uart_port *port1, struct uart_port *port2); -- cgit v1.2.3 From bc49a661e6e82bfa8219c3d0a2e4dea51c847d23 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 1 Sep 2005 15:56:26 +0100 Subject: [SERIAL] Move serial8250_*_port prototypes to linux/serial_8250.h Signed-off-by: Russell King --- include/linux/serial_8250.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 3e3c1fa35b06..d8a023d804d4 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -14,6 +14,9 @@ #include #include +/* + * This is the platform device platform_data structure + */ struct plat_serial8250_port { unsigned long iobase; /* io base address */ void __iomem *membase; /* ioremap cookie or NULL */ @@ -26,4 +29,17 @@ struct plat_serial8250_port { unsigned int flags; /* UPF_* flags */ }; +/* + * This should be used by drivers which want to register + * their own 8250 ports without registering their own + * platform device. Using these will make your driver + * dependent on the 8250 driver. + */ +struct uart_port; + +int serial8250_register_port(struct uart_port *); +void serial8250_unregister_port(int line); +void serial8250_suspend_port(int line); +void serial8250_resume_port(int line); + #endif -- cgit v1.2.3 From ff4cc3ac93e1d0369928fd60ec1fe82417afc576 Mon Sep 17 00:00:00 2001 From: Mike Kershaw Date: Thu, 1 Sep 2005 17:40:05 -0700 Subject: [TUNTAP]: Allow setting the linktype of the tap device from userspace Currently tun/tap only supports the EN10MB ARP type. For use with wireless and other networking types it should be possible to set the ARP type via an ioctl. Patch v2: Included check that the tap interface is down before changing the link type out from underneath it Signed-off-by: Mike Kershaw Signed-off-by: David S. Miller --- include/linux/if_tun.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 096a85a58ae5..88aef7b86ef4 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -77,6 +77,7 @@ struct tun_struct { #define TUNSETIFF _IOW('T', 202, int) #define TUNSETPERSIST _IOW('T', 203, int) #define TUNSETOWNER _IOW('T', 204, int) +#define TUNSETLINK _IOW('T', 205, int) /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 -- cgit v1.2.3 From 64baf3cfea974d2b9e671ccfdbc03e030ea5ebc6 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 1 Sep 2005 17:43:05 -0700 Subject: [CRYPTO]: Added CRYPTO_TFM_REQ_MAY_SLEEP flag The crypto layer currently uses in_atomic() to determine whether it is allowed to sleep. This is incorrect since spin locks don't always cause in_atomic() to return true. Instead of that, this patch returns to an earlier idea of a per-tfm flag which determines whether sleeping is allowed. Unlike the earlier version, the default is to not allow sleeping. This ensures that no existing code can break. As usual, this flag may either be set through crypto_alloc_tfm(), or just before a specific crypto operation. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/crypto.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 5e2bcc636a02..3c89df6e7768 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -45,6 +45,7 @@ #define CRYPTO_TFM_MODE_CTR 0x00000008 #define CRYPTO_TFM_REQ_WEAK_KEY 0x00000100 +#define CRYPTO_TFM_REQ_MAY_SLEEP 0x00000200 #define CRYPTO_TFM_RES_WEAK_KEY 0x00100000 #define CRYPTO_TFM_RES_BAD_KEY_LEN 0x00200000 #define CRYPTO_TFM_RES_BAD_KEY_SCHED 0x00400000 -- cgit v1.2.3 From d51fe1be3f738e7d73f63bb5aa0df88bafb41a21 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Fri, 2 Sep 2005 08:59:25 +0200 Subject: [PATCH] remove driverfs references from include/linux/cpu.h and net/sunrpc/rpc_pipe.c This patch is against 2.6.10, but still applies cleanly. It's just s/driverfs/sysfs/ in these two files. Signed-off-by: Rolf Eike Beer Signed-off-by: Linus Torvalds --- include/linux/cpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index e8904c0da686..86980c68234a 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -8,7 +8,7 @@ * Basic handling of the devices is done in drivers/base/cpu.c * and system devices are handled in drivers/base/sys.c. * - * CPUs are exported via driverfs in the class/cpu/devices/ + * CPUs are exported via sysfs in the class/cpu/devices/ * directory. * * Per-cpu interfaces can be implemented using a struct device_interface. -- cgit v1.2.3 From 865e9f13c94891daed4f6a5f69c5d6ec04d4932f Mon Sep 17 00:00:00 2001 From: Pierre Ossman Date: Sat, 3 Sep 2005 16:45:02 +0100 Subject: [MMC] ios for mmc chip select Adds a new ios for setting the chip select pin on MMC cards. Needed on SD controllers which use this pin for other things and therefore cannot have it pulled high at all times. Signed-off-by: Pierre Ossman Signed-off-by: Russell King --- include/linux/mmc/host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 9a0893f3249e..30f68c0c8c6e 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -46,6 +46,12 @@ struct mmc_ios { #define MMC_BUSMODE_OPENDRAIN 1 #define MMC_BUSMODE_PUSHPULL 2 + unsigned char chip_select; /* SPI chip select */ + +#define MMC_CS_DONTCARE 0 +#define MMC_CS_HIGH 1 +#define MMC_CS_LOW 2 + unsigned char power_mode; /* power supply mode */ #define MMC_POWER_OFF 0 -- cgit v1.2.3 From 8a409b0118c2d78f84f740f60fe03abda1fe3333 Mon Sep 17 00:00:00 2001 From: Vojtech Pavlik Date: Mon, 5 Sep 2005 00:08:08 -0500 Subject: Input: HID - add more consumer usages Extend mapping of the consumer usage page in hid-input.c to handle more cases appearing on new USB keyboards. Signed-off-by: Vojtech Pavlik Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index bdc53c6cc962..227a497c0678 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -287,6 +287,8 @@ struct input_absinfo { #define KEY_SCROLLDOWN 178 #define KEY_KPLEFTPAREN 179 #define KEY_KPRIGHTPAREN 180 +#define KEY_NEW 181 +#define KEY_REDO 182 #define KEY_F13 183 #define KEY_F14 184 @@ -333,6 +335,12 @@ struct input_absinfo { #define KEY_KBDILLUMDOWN 229 #define KEY_KBDILLUMUP 230 +#define KEY_SEND 231 +#define KEY_REPLY 232 +#define KEY_FORWARDMAIL 233 +#define KEY_SAVE 234 +#define KEY_DOCUMENTS 235 + #define KEY_UNKNOWN 240 #define BTN_MISC 0x100 -- cgit v1.2.3 From 802f192e4a600f7ef84ca25c8b818c8830acef5a Mon Sep 17 00:00:00 2001 From: Bob Picco Date: Sat, 3 Sep 2005 15:54:26 -0700 Subject: [PATCH] SPARSEMEM EXTREME A new option for SPARSEMEM is ARCH_SPARSEMEM_EXTREME. Architecture platforms with a very sparse physical address space would likely want to select this option. For those architecture platforms that don't select the option, the code generated is equivalent to SPARSEMEM currently in -mm. I'll be posting a patch on ia64 ml which uses this new SPARSEMEM feature. ARCH_SPARSEMEM_EXTREME makes mem_section a one dimensional array of pointers to mem_sections. This two level layout scheme is able to achieve smaller memory requirements for SPARSEMEM with the tradeoff of an additional shift and load when fetching the memory section. The current SPARSEMEM -mm implementation is a one dimensional array of mem_sections which is the default SPARSEMEM configuration. The patch attempts isolates the implementation details of the physical layout of the sparsemem section array. ARCH_SPARSEMEM_EXTREME depends on 64BIT and is by default boolean false. I've boot tested under aim load ia64 configured for ARCH_SPARSEMEM_EXTREME. I've also boot tested a 4 way Opteron machine with !ARCH_SPARSEMEM_EXTREME and tested with aim. Signed-off-by: Andy Whitcroft Signed-off-by: Bob Picco Signed-off-by: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 30 ++++++++++++++++++++++++++++-- 1 file changed, 28 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6c90461ed99f..b97054bbc394 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -487,6 +487,28 @@ struct mem_section { unsigned long section_mem_map; }; +#ifdef CONFIG_ARCH_SPARSEMEM_EXTREME +/* + * Should we ever require GCC 4 or later then the flat array scheme + * can be eliminated and a uniform solution for EXTREME and !EXTREME can + * be arrived at. + */ +#define SECTION_ROOT_SHIFT (PAGE_SHIFT-3) +#define SECTION_ROOT_MASK ((1UL<> SECTION_ROOT_SHIFT) +#define NR_SECTION_ROOTS (NR_MEM_SECTIONS >> SECTION_ROOT_SHIFT) + +extern struct mem_section *mem_section[NR_SECTION_ROOTS]; + +static inline struct mem_section *__nr_to_section(unsigned long nr) +{ + if (!mem_section[SECTION_TO_ROOT(nr)]) + return NULL; + return &mem_section[SECTION_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; +} + +#else + extern struct mem_section mem_section[NR_MEM_SECTIONS]; static inline struct mem_section *__nr_to_section(unsigned long nr) @@ -494,6 +516,10 @@ static inline struct mem_section *__nr_to_section(unsigned long nr) return &mem_section[nr]; } +#define sparse_index_init(_sec, _nid) do {} while (0) + +#endif + /* * We use the lower bits of the mem_map pointer to store * a little bit of information. There should be at least @@ -513,12 +539,12 @@ static inline struct page *__section_mem_map_addr(struct mem_section *section) static inline int valid_section(struct mem_section *section) { - return (section->section_mem_map & SECTION_MARKED_PRESENT); + return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } static inline int section_has_mem_map(struct mem_section *section) { - return (section->section_mem_map & SECTION_HAS_MEM_MAP); + return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } static inline int valid_section_nr(unsigned long nr) -- cgit v1.2.3 From 3e347261a80b57df792ab9464b5f0ed59add53a8 Mon Sep 17 00:00:00 2001 From: Bob Picco Date: Sat, 3 Sep 2005 15:54:28 -0700 Subject: [PATCH] sparsemem extreme implementation With cleanups from Dave Hansen SPARSEMEM_EXTREME makes mem_section a one dimensional array of pointers to mem_sections. This two level layout scheme is able to achieve smaller memory requirements for SPARSEMEM with the tradeoff of an additional shift and load when fetching the memory section. The current SPARSEMEM implementation is a one dimensional array of mem_sections which is the default SPARSEMEM configuration. The patch attempts isolates the implementation details of the physical layout of the sparsemem section array. SPARSEMEM_EXTREME requires bootmem to be functioning at the time of memory_present() calls. This is not always feasible, so architectures which do not need it may allocate everything statically by using SPARSEMEM_STATIC. Signed-off-by: Andy Whitcroft Signed-off-by: Bob Picco Signed-off-by: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 40 +++++++++++++++------------------------- 1 file changed, 15 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b97054bbc394..79cf578e21b9 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -487,39 +487,29 @@ struct mem_section { unsigned long section_mem_map; }; -#ifdef CONFIG_ARCH_SPARSEMEM_EXTREME -/* - * Should we ever require GCC 4 or later then the flat array scheme - * can be eliminated and a uniform solution for EXTREME and !EXTREME can - * be arrived at. - */ -#define SECTION_ROOT_SHIFT (PAGE_SHIFT-3) -#define SECTION_ROOT_MASK ((1UL<> SECTION_ROOT_SHIFT) -#define NR_SECTION_ROOTS (NR_MEM_SECTIONS >> SECTION_ROOT_SHIFT) +#ifdef CONFIG_SPARSEMEM_EXTREME +#define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section)) +#else +#define SECTIONS_PER_ROOT 1 +#endif -extern struct mem_section *mem_section[NR_SECTION_ROOTS]; - -static inline struct mem_section *__nr_to_section(unsigned long nr) -{ - if (!mem_section[SECTION_TO_ROOT(nr)]) - return NULL; - return &mem_section[SECTION_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; -} +#define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) +#define NR_SECTION_ROOTS (NR_MEM_SECTIONS / SECTIONS_PER_ROOT) +#define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) +#ifdef CONFIG_SPARSEMEM_EXTREME +extern struct mem_section *mem_section[NR_SECTION_ROOTS]; #else - -extern struct mem_section mem_section[NR_MEM_SECTIONS]; +extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; +#endif static inline struct mem_section *__nr_to_section(unsigned long nr) { - return &mem_section[nr]; + if (!mem_section[SECTION_NR_TO_ROOT(nr)]) + return NULL; + return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; } -#define sparse_index_init(_sec, _nid) do {} while (0) - -#endif - /* * We use the lower bits of the mem_map pointer to store * a little bit of information. There should be at least -- cgit v1.2.3 From 28ae55c98e4d16eac9a05a8a259d7763ef3aeb18 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Sat, 3 Sep 2005 15:54:29 -0700 Subject: [PATCH] sparsemem extreme: hotplug preparation This splits up sparse_index_alloc() into two pieces. This is needed because we'll allocate the memory for the second level in a different place from where we actually consume it to keep the allocation from happening underneath a lock Signed-off-by: Dave Hansen Signed-off-by: Bob Picco Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 79cf578e21b9..5ed471b58f4f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -588,6 +588,7 @@ static inline int pfn_valid(unsigned long pfn) void sparse_init(void); #else #define sparse_init() do {} while (0) +#define sparse_index_init(_sec, _nid) do {} while (0) #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_NODES_SPAN_OTHER_NODES -- cgit v1.2.3 From 11d31886dbcb61039ed3789e583d21c6e70960fd Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 3 Sep 2005 15:54:34 -0700 Subject: [PATCH] swap: swap extent list is ordered There are several comments that swap's extent_list.prev points to the lowest extent: that's not so, it's extent_list.next which points to it, as you'd expect. And a couple of loops in add_swap_extent which go all the way through the list, when they should just add to the other end. Fix those up, and let map_swap_page search the list forwards: profiles shows it to be twice as quick that way - because prefetch works better on how the structs are typically kmalloc'ed? or because usually more is written to than read from swap, and swap is allocated ascendingly? Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index bfe3e763ccf2..38f288475e67 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -116,8 +116,6 @@ enum { /* * The in-memory structure used to track swap areas. - * extent_list.prev points at the lowest-index extent. That list is - * sorted. */ struct swap_info_struct { unsigned int flags; -- cgit v1.2.3 From 53092a7402f227151a681b0c92ec8598c5618b1a Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 3 Sep 2005 15:54:34 -0700 Subject: [PATCH] swap: show span of swap extents The "Adding %dk swap" message shows the number of swap extents, as a guide to how fragmented the swapfile may be. But a useful further guide is what total extent they span across (sometimes scarily large). And there's no need to keep nr_extents in swap_info: it's unused after the initial message, so save a little space by keeping it on stack. Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 38f288475e67..f2b16ac0b539 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -123,7 +123,6 @@ struct swap_info_struct { struct file *swap_file; struct block_device *bdev; struct list_head extent_list; - int nr_extents; struct swap_extent *curr_swap_extent; unsigned old_block_size; unsigned short * swap_map; -- cgit v1.2.3 From 6eb396dc4a9781c5e7951143ab56ce5710687ab3 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 3 Sep 2005 15:54:35 -0700 Subject: [PATCH] swap: swap unsigned int consistency The swap header's unsigned int last_page determines the range of swap pages, but swap_info has been using int or unsigned long in some cases: use unsigned int throughout (except, in several places a local unsigned long is useful to avoid overflows when adding). Signed-off-by: Hugh Dickins Signed-off-by: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index f2b16ac0b539..93f0eca7f916 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -130,10 +130,10 @@ struct swap_info_struct { unsigned int highest_bit; unsigned int cluster_next; unsigned int cluster_nr; + unsigned int pages; + unsigned int max; + unsigned int inuse_pages; int prio; /* swap priority */ - int pages; - unsigned long max; - unsigned long inuse_pages; int next; /* next entry on swap list */ }; -- cgit v1.2.3 From 52b7efdbe5f5696fc80338560a3fc51e0b0a993c Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 3 Sep 2005 15:54:39 -0700 Subject: [PATCH] swap: scan_swap_map drop swap_device_lock get_swap_page has often shown up on latency traces, doing lengthy scans while holding two spinlocks. swap_list_lock is already dropped, now scan_swap_map drop swap_device_lock before scanning the swap_map. While scanning for an empty cluster, don't worry that racing tasks may allocate what was free and free what was allocated; but when allocating an entry, check it's still free after retaking the lock. Avoid dropping the lock in the expected common path. No barriers beyond the locks, just let the cookie crumble; highest_bit limit is volatile, but benign. Guard against swapoff: must check SWP_WRITEOK before allocating, must raise SWP_SCANNING reference count while in scan_swap_map, swapoff wait for that to fall - just use schedule_timeout, we don't want to burden scan_swap_map itself, and it's very unlikely that anyone can really still be in scan_swap_map once swapoff gets this far. Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 93f0eca7f916..db3b5de7c92f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -107,6 +107,8 @@ enum { SWP_USED = (1 << 0), /* is slot in swap_info[] used? */ SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */ SWP_ACTIVE = (SWP_USED | SWP_WRITEOK), + /* add others here before... */ + SWP_SCANNING = (1 << 8), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32 -- cgit v1.2.3 From 5d337b9194b1ce3b6fd5f3cb2799455ed2f9a3d1 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 3 Sep 2005 15:54:41 -0700 Subject: [PATCH] swap: swap_lock replace list+device The idea of a swap_device_lock per device, and a swap_list_lock over them all, is appealing; but in practice almost every holder of swap_device_lock must already hold swap_list_lock, which defeats the purpose of the split. The only exceptions have been swap_duplicate, valid_swaphandles and an untrodden path in try_to_unuse (plus a few places added in this series). valid_swaphandles doesn't show up high in profiles, but swap_duplicate does demand attention. However, with the hold time in get_swap_pages so much reduced, I've not yet found a load and set of swap device priorities to show even swap_duplicate benefitting from the split. Certainly the split is mere overhead in the common case of a single swap device. So, replace swap_list_lock and swap_device_lock by spinlock_t swap_lock (generally we seem to prefer an _ in the name, and not hide in a macro). If someone can show a regression in swap_duplicate, then probably we should add a hashlock for the swap_map entries alone (shorts being anatomic), so as to help the case of the single swap device too. Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index db3b5de7c92f..3c9ff0048153 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -121,7 +121,7 @@ enum { */ struct swap_info_struct { unsigned int flags; - spinlock_t sdev_lock; + int prio; /* swap priority */ struct file *swap_file; struct block_device *bdev; struct list_head extent_list; @@ -135,7 +135,6 @@ struct swap_info_struct { unsigned int pages; unsigned int max; unsigned int inuse_pages; - int prio; /* swap priority */ int next; /* next entry on swap list */ }; @@ -221,13 +220,7 @@ extern int can_share_swap_page(struct page *); extern int remove_exclusive_swap_page(struct page *); struct backing_dev_info; -extern struct swap_list_t swap_list; -extern spinlock_t swaplock; - -#define swap_list_lock() spin_lock(&swaplock) -#define swap_list_unlock() spin_unlock(&swaplock) -#define swap_device_lock(p) spin_lock(&p->sdev_lock) -#define swap_device_unlock(p) spin_unlock(&p->sdev_lock) +extern spinlock_t swap_lock; /* linux/mm/thrash.c */ extern struct mm_struct * swap_token_mm; -- cgit v1.2.3 From 6e21c8f145f5052c1c2fb4a4b41bee01c848159b Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Sat, 3 Sep 2005 15:54:45 -0700 Subject: [PATCH] /proc//numa_maps to show on which nodes pages reside This patch was recently discussed on linux-mm: http://marc.theaimsgroup.com/?t=112085728500002&r=1&w=2 I inherited a large code base from Ray for page migration. There was a small patch in there that I find to be very useful since it allows the display of the locality of the pages in use by a process. I reworked that patch and came up with a /proc//numa_maps that gives more information about the vma's of a process. numa_maps is indexes by the start address found in /proc//maps. F.e. with this patch you can see the page use of the "getty" process: margin:/proc/12008 # cat maps 00000000-00004000 r--p 00000000 00:00 0 2000000000000000-200000000002c000 r-xp 00000000 08:04 516 /lib/ld-2.3.3.so 2000000000038000-2000000000040000 rw-p 00028000 08:04 516 /lib/ld-2.3.3.so 2000000000040000-2000000000044000 rw-p 2000000000040000 00:00 0 2000000000058000-2000000000260000 r-xp 00000000 08:04 54707842 /lib/tls/libc.so.6.1 2000000000260000-2000000000268000 ---p 00208000 08:04 54707842 /lib/tls/libc.so.6.1 2000000000268000-2000000000274000 rw-p 00200000 08:04 54707842 /lib/tls/libc.so.6.1 2000000000274000-2000000000280000 rw-p 2000000000274000 00:00 0 2000000000280000-20000000002b4000 r--p 00000000 08:04 9126923 /usr/lib/locale/en_US.utf8/LC_CTYPE 2000000000300000-2000000000308000 r--s 00000000 08:04 60071467 /usr/lib/gconv/gconv-modules.cache 2000000000318000-2000000000328000 rw-p 2000000000318000 00:00 0 4000000000000000-4000000000008000 r-xp 00000000 08:04 29576399 /sbin/mingetty 6000000000004000-6000000000008000 rw-p 00004000 08:04 29576399 /sbin/mingetty 6000000000008000-600000000002c000 rw-p 6000000000008000 00:00 0 [heap] 60000fff7fffc000-60000fff80000000 rw-p 60000fff7fffc000 00:00 0 60000ffffff44000-60000ffffff98000 rw-p 60000ffffff44000 00:00 0 [stack] a000000000000000-a000000000020000 ---p 00000000 00:00 0 [vdso] cat numa_maps 2000000000000000 default MaxRef=43 Pages=11 Mapped=11 N0=4 N1=3 N2=2 N3=2 2000000000038000 default MaxRef=1 Pages=2 Mapped=2 Anon=2 N0=2 2000000000040000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 2000000000058000 default MaxRef=43 Pages=61 Mapped=61 N0=14 N1=15 N2=16 N3=16 2000000000268000 default MaxRef=1 Pages=2 Mapped=2 Anon=2 N0=2 2000000000274000 default MaxRef=1 Pages=3 Mapped=3 Anon=3 N0=3 2000000000280000 default MaxRef=8 Pages=3 Mapped=3 N0=3 2000000000300000 default MaxRef=8 Pages=2 Mapped=2 N0=2 2000000000318000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N2=1 4000000000000000 default MaxRef=6 Pages=2 Mapped=2 N1=2 6000000000004000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 6000000000008000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 60000fff7fffc000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 60000ffffff44000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 getty uses ld.so. The first vma is the code segment which is used by 43 other processes and the pages are evenly distributed over the 4 nodes. The second vma is the process specific data portion for ld.so. This is only one page. The display format is: Links to information in /proc//map This can be "default" "interleave={}", "prefer=" or "bind={}" MaxRef= Pages= Mapped= Anon= Nx= The content of the proc-file is self-evident. If this would be tied into the sparsemem system then the contents of this file would not be too useful. Signed-off-by: Christoph Lameter Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 8480aef10e62..94a46f38c532 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -150,6 +150,9 @@ void mpol_free_shared_policy(struct shared_policy *p); struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx); +struct mempolicy *get_vma_policy(struct task_struct *task, + struct vm_area_struct *vma, unsigned long addr); + extern void numa_default_policy(void); extern void numa_policy_init(void); -- cgit v1.2.3 From 242e54686257493f0b10ac557e730419d9af7d24 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sat, 3 Sep 2005 15:54:50 -0700 Subject: [PATCH] mm: remove atomic This bitop does not need to be atomic because it is performed when there will be no references to the page (ie. the page is being freed). Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f5a6695d4d21..99f7cc495065 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -194,6 +194,7 @@ extern void __mod_page_state(unsigned long offset, unsigned long delta); #define SetPageDirty(page) set_bit(PG_dirty, &(page)->flags) #define TestSetPageDirty(page) test_and_set_bit(PG_dirty, &(page)->flags) #define ClearPageDirty(page) clear_bit(PG_dirty, &(page)->flags) +#define __ClearPageDirty(page) __clear_bit(PG_dirty, &(page)->flags) #define TestClearPageDirty(page) test_and_clear_bit(PG_dirty, &(page)->flags) #define SetPageLRU(page) set_bit(PG_lru, &(page)->flags) -- cgit v1.2.3 From bce5f6ba340b09d8b29902add204bb95a6d3d88b Mon Sep 17 00:00:00 2001 From: Martin Hicks Date: Sat, 3 Sep 2005 15:54:50 -0700 Subject: [PATCH] VM: add capabilites check to set_zone_reclaim Add a capability check to sys_set_zone_reclaim(). This syscall is not something that should be available to a user. Signed-off-by: Martin Hicks Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/capability.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index 8d139f4acf23..6b4618902d3d 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -233,6 +233,7 @@ typedef __u32 kernel_cap_t; /* Allow enabling/disabling tagged queuing on SCSI controllers and sending arbitrary SCSI commands */ /* Allow setting encryption key on loopback filesystem */ +/* Allow setting zone reclaim policy */ #define CAP_SYS_ADMIN 21 -- cgit v1.2.3 From e83a9596712eb784e7e6604f43a2c140eb912743 Mon Sep 17 00:00:00 2001 From: Paolo 'Blaisorblade' Giarrusso Date: Sat, 3 Sep 2005 15:54:53 -0700 Subject: [PATCH] comment typo fix smp_entry_t -> swap_entry_t Signed-off-by: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index d4c7db35e708..87b9d14c710d 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -4,7 +4,7 @@ * the low-order bits. * * We arrange the `type' and `offset' fields so that `type' is at the five - * high-order bits of the smp_entry_t and `offset' is right-aligned in the + * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. -- cgit v1.2.3 From fd195c49fb17a21e232f50bddb2267150053cf34 Mon Sep 17 00:00:00 2001 From: Deepak Saxena Date: Sat, 3 Sep 2005 15:54:58 -0700 Subject: [PATCH] arm: allow for arch-specific IOREMAP_MAX_ORDER Version 6 of the ARM architecture introduces the concept of 16MB pages (supersections) and 36-bit (40-bit actually, but nobody uses this) physical addresses. 36-bit addressed memory and I/O and ARMv6 can only be mapped using supersections and the requirement on these is that both virtual and physical addresses be 16MB aligned. In trying to add support for ioremap() of 36-bit I/O, we run into the issue that get_vm_area() allows for a maximum of 512K alignment via the IOREMAP_MAX_ORDER constant. To work around this, we can: - Allocate a larger VM area than needed (size + (1ul << IOREMAP_MAX_ORDER)) and then align the pointer ourselves, but this ends up with 512K of wasted VM per ioremap(). - Provide a new __get_vm_area_aligned() API and make __get_vm_area() sit on top of this. I did this and it works but I don't like the idea adding another VM API just for this one case. - My preferred solution which is to allow the architecture to override the IOREMAP_MAX_ORDER constant with it's own version. Signed-off-by: Deepak Saxena Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 6409d9cf5965..b244f69ef682 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -10,6 +10,14 @@ #define VM_MAP 0x00000004 /* vmap()ed pages */ /* bits [20..32] reserved for arch specific ioremap internals */ +/* + * Maximum alignment for ioremap() regions. + * Can be overriden by arch-specific value. + */ +#ifndef IOREMAP_MAX_ORDER +#define IOREMAP_MAX_ORDER (7 + PAGE_SHIFT) /* 128 pages */ +#endif + struct vm_struct { void *addr; unsigned long size; -- cgit v1.2.3 From 0e5c9f39f64d8a55c5db37a5ea43e37d3422fd92 Mon Sep 17 00:00:00 2001 From: "Chen, Kenneth W" Date: Sat, 3 Sep 2005 15:55:02 -0700 Subject: [PATCH] remove hugetlb_clean_stale_pgtable() and fix huge_pte_alloc() I don't think we need to call hugetlb_clean_stale_pgtable() anymore in 2.6.13 because of the rework with free_pgtables(). It now collect all the pte page at the time of munmap. It used to only collect page table pages when entire one pgd can be freed and left with staled pte pages. Not anymore with 2.6.13. This function will never be called and We should turn it into a BUG_ON. I also spotted two problems here, not Adam's fault :-) (1) in huge_pte_alloc(), it looks like a bug to me that pud is not checked before calling pmd_alloc() (2) in hugetlb_clean_stale_pgtable(), it also missed a call to pmd_free_tlb. I think a tlb flush is required to flush the mapping for the page table itself when we clear out the pmd pointing to a pte page. However, since hugetlb_clean_stale_pgtable() is never called, so it won't trigger the bug. Signed-off-by: Ken Chen Cc: Adam Litke Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index f529d1442815..e670b0d13fe0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -70,12 +70,6 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, void hugetlb_prefault_arch_hook(struct mm_struct *mm); #endif -#ifndef ARCH_HAS_HUGETLB_CLEAN_STALE_PGTABLE -#define hugetlb_clean_stale_pgtable(pte) BUG() -#else -void hugetlb_clean_stale_pgtable(pte_t *pte); -#endif - #else /* !CONFIG_HUGETLB_PAGE */ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) -- cgit v1.2.3 From c07e02db76940c75fc92f2f2c9adcdbb09ed70d0 Mon Sep 17 00:00:00 2001 From: Martin Hicks Date: Sat, 3 Sep 2005 15:55:11 -0700 Subject: [PATCH] VM: add page_state info to per-node meminfo Add page_state info to the per-node meminfo file in sysfs. This is mostly just for informational purposes. The lack of this information was brought up recently during a discussion regarding pagecache clearing, and I put this patch together to test out one of the suggestions. It seems like interesting info to have, so I'm submitting the patch. Signed-off-by: Martin Hicks Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 99f7cc495065..f34767c5fc79 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -134,6 +134,7 @@ struct page_state { }; extern void get_page_state(struct page_state *ret); +extern void get_page_state_node(struct page_state *ret, int node); extern void get_full_page_state(struct page_state *ret); extern unsigned long __read_page_state(unsigned long offset); extern void __mod_page_state(unsigned long offset, unsigned long delta); -- cgit v1.2.3 From d01c08c9ae91c1526d4564b400b3e0e04b49d1ba Mon Sep 17 00:00:00 2001 From: "Mark A. Greer" Date: Sat, 3 Sep 2005 15:55:56 -0700 Subject: [PATCH] ppc32: mv64x60 updates & enhancements Updates and enhancement to the ppc32 mv64x60 code: - move code to get mem size from mem ctlr to bootwrapper - address some errata in the mv64360 pic code - some minor cleanups - export one of the bridge's regs via sysfs so user daemon can watch for extraction events Signed-off-by: Mark A. Greer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mv643xx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mv643xx.h b/include/linux/mv643xx.h index 5773ea42f6e4..0b08cd692201 100644 --- a/include/linux/mv643xx.h +++ b/include/linux/mv643xx.h @@ -980,7 +980,7 @@ /* I2C Registers */ /****************************************/ -#define MV64XXX_I2C_CTLR_NAME "mv64xxx i2c" +#define MV64XXX_I2C_CTLR_NAME "mv64xxx_i2c" #define MV64XXX_I2C_OFFSET 0xc000 #define MV64XXX_I2C_REG_BLOCK_SIZE 0x0020 -- cgit v1.2.3 From dc4ec916f6ea0c2818e9b81c4e9b33231f5f70e4 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Sat, 3 Sep 2005 15:56:12 -0700 Subject: [PATCH] MIPS Technologies PCI ID bits - MIPS Denmark does no longer exist; the PCI vendor ID is now owned by MIPS Technologies. - Add ID for SOC-it, MIPS's system controller. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d513c1634006..95c941f8c747 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2147,6 +2147,9 @@ #define PCI_DEVICE_ID_ENE_1420 0x1420 #define PCI_VENDOR_ID_CHELSIO 0x1425 +#define PCI_VENDOR_ID_MIPS 0x153f +#define PCI_DEVICE_ID_SOC_IT 0x0001 + #define PCI_VENDOR_ID_SYBA 0x1592 #define PCI_DEVICE_ID_SYBA_2P_EPP 0x0782 #define PCI_DEVICE_ID_SYBA_1P_ECP 0x0783 -- cgit v1.2.3 From 7ae65fd334232468a9d6b523a4fc141cd6ec5ea4 Mon Sep 17 00:00:00 2001 From: Matt Tolentino Date: Sat, 3 Sep 2005 15:56:27 -0700 Subject: [PATCH] x86: fix EFI memory map parsing The memory descriptors that comprise the EFI memory map are not fixed in stone such that the size could change in the future. This uses the memory descriptor size obtained from EFI to iterate over the memory map entries during boot. This enables the removal of an x86 specific pad (and ifdef) in the EFI header. I also couldn't stomach the broken up nature of the function to put EFI runtime calls into virtual mode any longer so I fixed that up a bit as well. For reference, this patch only impacts x86. Signed-off-by: Matt Tolentino Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/efi.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 73781ec165b4..c7c5dd316182 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -91,11 +91,6 @@ typedef struct { #define EFI_PAGE_SHIFT 12 -/* - * For current x86 implementations of EFI, there is - * additional padding in the mem descriptors. This is not - * the case in ia64. Need to have this fixed in the f/w. - */ typedef struct { u32 type; u32 pad; @@ -103,9 +98,6 @@ typedef struct { u64 virt_addr; u64 num_pages; u64 attribute; -#if defined (__i386__) - u64 pad1; -#endif } efi_memory_desc_t; typedef int (*efi_freemem_callback_t) (unsigned long start, unsigned long end, void *arg); @@ -240,10 +232,12 @@ typedef struct { } efi_system_table_t; struct efi_memory_map { - efi_memory_desc_t *phys_map; - efi_memory_desc_t *map; + void *phys_map; + void *map; + void *map_end; int nr_map; unsigned long desc_version; + unsigned long desc_size; }; /* -- cgit v1.2.3 From ca078bae813dd46c0f9b102fdfb4a3384641ff48 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Sat, 3 Sep 2005 15:56:57 -0700 Subject: [PATCH] swsusp: switch pm_message_t to struct This adds type-checking to pm_message_t, so that people can't confuse it with int or u32. It also allows us to fix "disk yoyo" during suspend (disk spinning down/up/down). [We've tried that before; since that cpufreq problems were fixed and I've tried make allyes config and fixed resulting damage.] Signed-off-by: Pavel Machek Signed-off-by: Alexander Nyberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pm.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 7aeb208ed713..5cfb07648eca 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -186,7 +186,9 @@ extern int pm_suspend(suspend_state_t state); struct device; -typedef u32 __bitwise pm_message_t; +typedef struct pm_message { + int event; +} pm_message_t; /* * There are 4 important states driver can be in: @@ -207,9 +209,13 @@ typedef u32 __bitwise pm_message_t; * or something similar soon. */ -#define PMSG_FREEZE ((__force pm_message_t) 3) -#define PMSG_SUSPEND ((__force pm_message_t) 3) -#define PMSG_ON ((__force pm_message_t) 0) +#define PM_EVENT_ON 0 +#define PM_EVENT_FREEZE 1 +#define PM_EVENT_SUSPEND 2 + +#define PMSG_FREEZE ((struct pm_message){ .event = PM_EVENT_FREEZE, }) +#define PMSG_SUSPEND ((struct pm_message){ .event = PM_EVENT_SUSPEND, }) +#define PMSG_ON ((struct pm_message){ .event = PM_EVENT_ON, }) struct dev_pm_info { pm_message_t power_state; -- cgit v1.2.3 From ed75e8d58010fdc06e2c3a81bfbebae92314c7e3 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Sat, 3 Sep 2005 15:57:18 -0700 Subject: [PATCH] UML Support - Ptrace: adds the host SYSEMU support, for UML and general usage Jeff Dike , Paolo 'Blaisorblade' Giarrusso , Bodo Stroesser Adds a new ptrace(2) mode, called PTRACE_SYSEMU, resembling PTRACE_SYSCALL except that the kernel does not execute the requested syscall; this is useful to improve performance for virtual environments, like UML, which want to run the syscall on their own. In fact, using PTRACE_SYSCALL means stopping child execution twice, on entry and on exit, and each time you also have two context switches; with SYSEMU you avoid the 2nd stop and so save two context switches per syscall. Also, some architectures don't have support in the host for changing the syscall number via ptrace(), which is currently needed to skip syscall execution (UML turns any syscall into getpid() to avoid it being executed on the host). Fixing that is hard, while SYSEMU is easier to implement. * This version of the patch includes some suggestions of Jeff Dike to avoid adding any instructions to the syscall fast path, plus some other little changes, by myself, to make it work even when the syscall is executed with SYSENTER (but I'm unsure about them). It has been widely tested for quite a lot of time. * Various fixed were included to handle the various switches between various states, i.e. when for instance a syscall entry is traced with one of PT_SYSCALL / _SYSEMU / _SINGLESTEP and another one is used on exit. Basically, this is done by remembering which one of them was used even after the call to ptrace_notify(). * We're combining TIF_SYSCALL_EMU with TIF_SYSCALL_TRACE or TIF_SINGLESTEP to make do_syscall_trace() notice that the current syscall was started with SYSEMU on entry, so that no notification ought to be done in the exit path; this is a bit of a hack, so this problem is solved in another way in next patches. * Also, the effects of the patch: "Ptrace - i386: fix Syscall Audit interaction with singlestep" are cancelled; they are restored back in the last patch of this series. Detailed descriptions of the patches doing this kind of processing follow (but I've already summed everything up). * Fix behaviour when changing interception kind #1. In do_syscall_trace(), we check the status of the TIF_SYSCALL_EMU flag only after doing the debugger notification; but the debugger might have changed the status of this flag because he continued execution with PTRACE_SYSCALL, so this is wrong. This patch fixes it by saving the flag status before calling ptrace_notify(). * Fix behaviour when changing interception kind #2: avoid intercepting syscall on return when using SYSCALL again. A guest process switching from using PTRACE_SYSEMU to PTRACE_SYSCALL crashes. The problem is in arch/i386/kernel/entry.S. The current SYSEMU patch inhibits the syscall-handler to be called, but does not prevent do_syscall_trace() to be called after this for syscall completion interception. The appended patch fixes this. It reuses the flag TIF_SYSCALL_EMU to remember "we come from PTRACE_SYSEMU and now are in PTRACE_SYSCALL", since the flag is unused in the depicted situation. * Fix behaviour when changing interception kind #3: avoid intercepting syscall on return when using SINGLESTEP. When testing 2.6.9 and the skas3.v6 patch, with my latest patch and had problems with singlestepping on UML in SKAS with SYSEMU. It looped receiving SIGTRAPs without moving forward. EIP of the traced process was the same for all SIGTRAPs. What's missing is to handle switching from PTRACE_SYSCALL_EMU to PTRACE_SINGLESTEP in a way very similar to what is done for the change from PTRACE_SYSCALL_EMU to PTRACE_SYSCALL_TRACE. I.e., after calling ptrace(PTRACE_SYSEMU), on the return path, the debugger is notified and then wake ups the process; the syscall is executed (or skipped, when do_syscall_trace() returns 0, i.e. when using PTRACE_SYSEMU), and do_syscall_trace() is called again. Since we are on the return path of a SYSEMU'd syscall, if the wake up is performed through ptrace(PTRACE_SYSCALL), we must still avoid notifying the parent of the syscall exit. Now, this behaviour is extended even to resuming with PTRACE_SINGLESTEP. Signed-off-by: Paolo 'Blaisorblade' Giarrusso Cc: Jeff Dike Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index a373fc254df2..7528afb6b2ad 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -20,6 +20,7 @@ #define PTRACE_DETACH 0x11 #define PTRACE_SYSCALL 24 +#define PTRACE_SYSEMU 31 /* 0x4200-0x4300 are reserved for architecture-independent additions. */ #define PTRACE_SETOPTIONS 0x4200 -- cgit v1.2.3 From 1b38f0064e4e0b9ec626e39f0740b1cf2e295743 Mon Sep 17 00:00:00 2001 From: Bodo Stroesser Date: Sat, 3 Sep 2005 15:57:20 -0700 Subject: [PATCH] Uml support: add PTRACE_SYSEMU_SINGLESTEP option to i386 This patch implements the new ptrace option PTRACE_SYSEMU_SINGLESTEP, which can be used by UML to singlestep a process: it will receive SINGLESTEP interceptions for normal instructions and syscalls, but syscall execution will be skipped just like with PTRACE_SYSEMU. Signed-off-by: Bodo Stroesser Signed-off-by: Paolo 'Blaisorblade' Giarrusso Cc: Jeff Dike Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 7528afb6b2ad..2afdafb62123 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -21,6 +21,7 @@ #define PTRACE_SYSCALL 24 #define PTRACE_SYSEMU 31 +#define PTRACE_SYSEMU_SINGLESTEP 32 /* 0x4200-0x4300 are reserved for architecture-independent additions. */ #define PTRACE_SETOPTIONS 0x4200 -- cgit v1.2.3 From a61fc683ae1b7871d8d81ac5025af1a923731547 Mon Sep 17 00:00:00 2001 From: "bgardner@wabtec.com" Date: Wed, 27 Jul 2005 12:43:03 -0500 Subject: [PATCH] I2C: add kobj_to_i2c_client Move the inline function kobj_to_i2c_client() from max6875.c to i2c.h. Signed-off-by: Ben Gardner Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index be837b13f297..017445943816 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -160,6 +160,11 @@ struct i2c_client { }; #define to_i2c_client(d) container_of(d, struct i2c_client, dev) +static inline struct i2c_client *kobj_to_i2c_client(struct kobject *kobj) +{ + return to_i2c_client(container_of(kobj, struct device, kobj)); +} + static inline void *i2c_get_clientdata (struct i2c_client *dev) { return dev_get_drvdata (&dev->dev); -- cgit v1.2.3 From 1236441f38b6a98caf4c7983e7efdecc2d1527b5 Mon Sep 17 00:00:00 2001 From: "Mark M. Hoffman" Date: Fri, 15 Jul 2005 21:38:08 -0400 Subject: [PATCH] I2C hwmon: hwmon sysfs class This patch adds the sysfs class "hwmon" for use by hardware monitoring (sensors) chip drivers. It also fixes up the related Kconfig/Makefile bits. Signed-off-by: Mark M. Hoffman Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/hwmon.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100644 include/linux/hwmon.h (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h new file mode 100644 index 000000000000..bf90e6001e3b --- /dev/null +++ b/include/linux/hwmon.h @@ -0,0 +1,24 @@ +/* + hwmon.h - part of lm_sensors, Linux kernel modules for hardware monitoring + + This file declares helper functions for the sysfs class "hwmon", + for use by sensors drivers. + + Copyright (C) 2005 Mark M. Hoffman + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; version 2 of the License. +*/ + +#ifndef _HWMON_H_ +#define _HWMON_H_ + +#include + +struct class_device *hwmon_device_register(struct device *dev); + +void hwmon_device_unregister(struct class_device *cdev); + +#endif + -- cgit v1.2.3 From efde723fdac02111872bff606ef362074fc1efa8 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 20 Jul 2005 23:03:50 +0200 Subject: [PATCH] I2C: Separate non-i2c hwmon drivers from i2c-core (1/9) Temporarily export a few structures and functions from i2c-core, because we will soon need them in i2c-isa. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 017445943816..3be06105034c 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -34,6 +34,13 @@ #include /* for struct device */ #include +/* --- For i2c-isa ---------------------------------------------------- */ + +extern void i2c_adapter_dev_release(struct device *dev); +extern struct device_driver i2c_adapter_driver; +extern struct class i2c_adapter_class; +extern struct bus_type i2c_bus_type; + /* --- General options ------------------------------------------------ */ struct i2c_msg; -- cgit v1.2.3 From 400c455eaa0d0819d18cd42a74070e0e238a73dc Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 19 Jul 2005 23:48:43 +0200 Subject: [PATCH] I2C: Separate non-i2c hwmon drivers from i2c-core (2/9) Convert i2c-isa from a dumb i2c_adapter into a pseudo i2c-core for ISA hardware monitoring drivers. The isa i2c_adapter is no more registered with i2c-core, drivers have to explicitely connect to it using the new i2c_isa_{add,del}_driver interface. At this point, all ISA chip drivers are useless, because they still register with i2c-core in the hope i2c-isa is registered there as well, but it isn't anymore. The fake bus will be named i2c-9191 in sysfs. This is the number it already had internally in various places, so it's not exactly new, except that now the number is seen in userspace as well. This shouldn't be a problem until someone really has 9192 I2C busses in a given system ;) The fake bus will no more show in "i2cdetect -l", as it won't be seen by i2c-dev anymore (not being registered with i2c-core), which is a good thing, as i2cdetect/i2cdump/i2cset cannot operate on this fake bus anyway. Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-isa.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/linux/i2c-isa.h (limited to 'include/linux') diff --git a/include/linux/i2c-isa.h b/include/linux/i2c-isa.h new file mode 100644 index 000000000000..b5727d7702e1 --- /dev/null +++ b/include/linux/i2c-isa.h @@ -0,0 +1,29 @@ +/* + * i2c-isa.h - definitions for the i2c-isa pseudo-i2c-adapter interface + * + * Copyright (C) 2005 Jean Delvare + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef _LINUX_I2C_ISA_H +#define _LINUX_I2C_ISA_H + +#include + +extern int i2c_isa_add_driver(struct i2c_driver *driver); +extern int i2c_isa_del_driver(struct i2c_driver *driver); + +#endif /* _LINUX_I2C_ISA_H */ -- cgit v1.2.3 From 5071860aba7fc69279ab822638ed2c2e4549f9fd Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 20 Jul 2005 00:02:32 +0200 Subject: [PATCH] I2C: Separate non-i2c hwmon drivers from i2c-core (7/9) Kill normal_isa in header files, documentation and all chip drivers, as it is no more used. normal_i2c could be renamed to normal, but I decided not to do so at the moment, so as to limit the number of changes. This might be done later as part of the i2c_probe/i2c_detect merge. Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-sensor.h | 36 +++++++++++++++--------------------- include/linux/i2c.h | 8 ++------ 2 files changed, 17 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-sensor.h b/include/linux/i2c-sensor.h index 21b625204956..ae73b9e789cb 100644 --- a/include/linux/i2c-sensor.h +++ b/include/linux/i2c-sensor.h @@ -27,11 +27,10 @@ that place. If a specific chip is given, the module blindly assumes this chip type is present; if a general force (kind == 0) is given, the module will still try to figure out what type of chip is present. This is useful - if for some reasons the detect for SMBus or ISA address space filled - fails. - probe: insmod parameter. Initialize this list with I2C_CLIENT_ISA_END values. - A list of pairs. The first value is a bus number (ANY_I2C_ISA_BUS for - the ISA bus, -1 for any I2C bus), the second is the address. + if for some reasons the detect for SMBus address space filled fails. + probe: insmod parameter. Initialize this list with I2C_CLIENT_END values. + A list of pairs. The first value is a bus number (ANY_I2C_BUS for any + I2C bus), the second is the address. kind: The kind of chip. 0 equals any chip. */ struct i2c_force_data { @@ -40,25 +39,22 @@ struct i2c_force_data { }; /* A structure containing the detect information. - normal_i2c: filled in by the module writer. Terminated by I2C_CLIENT_ISA_END. + normal_i2c: filled in by the module writer. Terminated by I2C_CLIENT_END. A list of I2C addresses which should normally be examined. - normal_isa: filled in by the module writer. Terminated by SENSORS_ISA_END. - A list of ISA addresses which should normally be examined. - probe: insmod parameter. Initialize this list with I2C_CLIENT_ISA_END values. - A list of pairs. The first value is a bus number (ANY_I2C_ISA_BUS for - the ISA bus, -1 for any I2C bus), the second is the address. These - addresses are also probed, as if they were in the 'normal' list. - ignore: insmod parameter. Initialize this list with I2C_CLIENT_ISA_END values. - A list of pairs. The first value is a bus number (ANY_I2C_ISA_BUS for - the ISA bus, -1 for any I2C bus), the second is the I2C address. These - addresses are never probed. This parameter overrules 'normal' and - 'probe', but not the 'force' lists. + probe: insmod parameter. Initialize this list with I2C_CLIENT_END values. + A list of pairs. The first value is a bus number (ANY_I2C_BUS for any + I2C bus), the second is the address. These addresses are also probed, + as if they were in the 'normal' list. + ignore: insmod parameter. Initialize this list with I2C_CLIENT_END values. + A list of pairs. The first value is a bus number (ANY_I2C_BUS for any + I2C bus), the second is the I2C address. These addresses are never + probed. This parameter overrules 'normal' and probe', but not the + 'force' lists. force_data: insmod parameters. A list, ending with an element of which the force field is NULL. */ struct i2c_address_data { unsigned short *normal_i2c; - unsigned int *normal_isa; unsigned short *probe; unsigned short *ignore; struct i2c_force_data *forces; @@ -78,7 +74,6 @@ struct i2c_address_data { "List of adapter,address pairs not to scan"); \ static struct i2c_address_data addr_data = { \ .normal_i2c = normal_i2c, \ - .normal_isa = normal_isa, \ .probe = probe, \ .ignore = ignore, \ .forces = forces, \ @@ -242,8 +237,7 @@ struct i2c_address_data { /* Detect function. It iterates over all possible addresses itself. For SMBus addresses, it will only call found_proc if some client is connected - to the SMBus (unless a 'force' matched); for ISA detections, this is not - done. */ + to the SMBus (unless a 'force' matched). */ extern int i2c_detect(struct i2c_adapter *adapter, struct i2c_address_data *address_data, int (*found_proc) (struct i2c_adapter *, int, int)); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 3be06105034c..39ff363eadec 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -150,12 +150,9 @@ struct i2c_driver { */ struct i2c_client { unsigned int flags; /* div., see below */ - unsigned int addr; /* chip address - NOTE: 7bit */ + unsigned short addr; /* chip address - NOTE: 7bit */ /* addresses are stored in the */ - /* _LOWER_ 7 bits of this char */ - /* addr: unsigned int to make lm_sensors i2c-isa adapter work - more cleanly. It does not take any more memory space, due to - alignment considerations */ + /* _LOWER_ 7 bits */ struct i2c_adapter *adapter; /* the adapter we sit on */ struct i2c_driver *driver; /* and our access routines */ int usage_count; /* How many accesses currently */ @@ -309,7 +306,6 @@ struct i2c_client_address_data { /* Internal numbers to terminate lists */ #define I2C_CLIENT_END 0xfffeU -#define I2C_CLIENT_ISA_END 0xfffefffeU /* The numbers to use to set I2C bus address */ #define ANY_I2C_BUS 0xffff -- cgit v1.2.3 From 570aefc361d3315ec6749f573009286106b0b2d8 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 20 Jul 2005 00:09:03 +0200 Subject: [PATCH] I2C: Separate non-i2c hwmon drivers from i2c-core (9/9) Move the definitions of i2c_is_isa_client and i2c_is_isa_adapter from i2c.h to i2c-isa.h. Only hybrid drivers still need them. Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-isa.h | 7 +++++++ include/linux/i2c.h | 7 ------- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-isa.h b/include/linux/i2c-isa.h index b5727d7702e1..db793b68356c 100644 --- a/include/linux/i2c-isa.h +++ b/include/linux/i2c-isa.h @@ -26,4 +26,11 @@ extern int i2c_isa_add_driver(struct i2c_driver *driver); extern int i2c_isa_del_driver(struct i2c_driver *driver); +/* Detect whether we are on the isa bus. This is only useful to hybrid + (i2c+isa) drivers. */ +#define i2c_is_isa_client(clientptr) \ + ((clientptr)->adapter->algo->id == I2C_ALGO_ISA) +#define i2c_is_isa_adapter(adapptr) \ + ((adapptr)->algo->id == I2C_ALGO_ISA) + #endif /* _LINUX_I2C_ISA_H */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 39ff363eadec..da4faa016b17 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -580,11 +580,4 @@ union i2c_smbus_data { .force = force, \ } -/* Detect whether we are on the isa bus. If this returns true, all i2c - access will fail! */ -#define i2c_is_isa_client(clientptr) \ - ((clientptr)->adapter->algo->id == I2C_ALGO_ISA) -#define i2c_is_isa_adapter(adapptr) \ - ((adapptr)->algo->id == I2C_ALGO_ISA) - #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From 5563e27d3a42667734e81c1cb8ad72bff76321f6 Mon Sep 17 00:00:00 2001 From: "R.Marek@sh.cvut.cz" Date: Wed, 27 Jul 2005 11:43:47 +0000 Subject: [PATCH] I2C: W83792D driver 1/3 I would like to announce support for W83792D chip. This driver was developed by Winbond Electronics Corp. I added sysfs attributes callbacks infrastructure plus various code fixes and codingstyle cleanups. I would like to thank Winbond for supporting free software. This patch is against 2.6.13rc3 plus hwmon-class and hwmon-split. Separate patch for documantation and hwmon class register will follow. Signed-off-by: Rudolf Marek Signed-off-by: Chunhao Huang Signed-off-by: Greg Kroah-Hartman --- include/linux/hwmon-sysfs.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwmon-sysfs.h b/include/linux/hwmon-sysfs.h index 1b5018a965f5..7eb4004b3601 100644 --- a/include/linux/hwmon-sysfs.h +++ b/include/linux/hwmon-sysfs.h @@ -33,4 +33,19 @@ struct sensor_device_attribute sensor_dev_attr_##_name = { \ .index = _index, \ } +struct sensor_device_attribute_2 { + struct device_attribute dev_attr; + u8 index; + u8 nr; +}; +#define to_sensor_dev_attr_2(_dev_attr) \ + container_of(_dev_attr, struct sensor_device_attribute_2, dev_attr) + +#define SENSOR_DEVICE_ATTR_2(_name,_mode,_show,_store,_nr,_index) \ +struct sensor_device_attribute_2 sensor_dev_attr_##_name = { \ + .dev_attr = __ATTR(_name,_mode,_show,_store), \ + .index = _index, \ + .nr = _nr, \ +} + #endif /* _LINUX_HWMON_SYSFS_H */ -- cgit v1.2.3 From cdcb19219714c796ddef1202e952566c5f86354d Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 28 Jul 2005 23:09:40 +0200 Subject: [PATCH] I2C: inline i2c_adapter_id We could inline i2c_adapter_id, as it is really, really short. Doing so saves a few bytes both in i2c-core and in the drivers using this function. before after diff drivers/hwmon/adm1026.ko 41344 41305 -39 drivers/hwmon/asb100.ko 27325 27246 -79 drivers/hwmon/gl518sm.ko 20824 20785 -39 drivers/hwmon/it87.ko 26419 26380 -39 drivers/hwmon/lm78.ko 21424 21385 -39 drivers/hwmon/lm85.ko 41034 40939 -95 drivers/hwmon/w83781d.ko 39561 39514 -47 drivers/hwmon/w83792d.ko 32979 32932 -47 drivers/i2c/i2c-core.ko 24708 24531 -177 Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index da4faa016b17..ad1c0fb164bc 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -364,10 +364,6 @@ extern int i2c_probe(struct i2c_adapter *adapter, */ extern int i2c_control(struct i2c_client *,unsigned int, unsigned long); -/* This call returns a unique low identifier for each registered adapter, - * or -1 if the adapter was not registered. - */ -extern int i2c_adapter_id(struct i2c_adapter *adap); extern struct i2c_adapter* i2c_get_adapter(int id); extern void i2c_put_adapter(struct i2c_adapter *adap); @@ -384,6 +380,12 @@ static inline int i2c_check_functionality(struct i2c_adapter *adap, u32 func) return (func & i2c_get_functionality(adap)) == func; } +/* Return id number for a specific adapter */ +static inline int i2c_adapter_id(struct i2c_adapter *adap) +{ + return adap->nr; +} + /* * I2C Message - used for pure i2c transaction, also from /dev interface */ -- cgit v1.2.3 From 53ae11b08353268c4012ef107bf205a0724d71aa Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 28 Jul 2005 23:14:59 +0200 Subject: [PATCH] hwmon: move SENSORS_LIMIT to hwmon.h Move SENSORS_LIMIT from i2c-sensor.h to hwmon.h, as it is in no way related to i2c. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/hwmon.h | 11 +++++++++++ include/linux/i2c-sensor.h | 12 ------------ 2 files changed, 11 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index bf90e6001e3b..0efd994c37f1 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -20,5 +20,16 @@ struct class_device *hwmon_device_register(struct device *dev); void hwmon_device_unregister(struct class_device *cdev); +/* Scale user input to sensible values */ +static inline int SENSORS_LIMIT(long value, long low, long high) +{ + if (value < low) + return low; + else if (value > high) + return high; + else + return value; +} + #endif diff --git a/include/linux/i2c-sensor.h b/include/linux/i2c-sensor.h index ae73b9e789cb..e832d3286a46 100644 --- a/include/linux/i2c-sensor.h +++ b/include/linux/i2c-sensor.h @@ -242,16 +242,4 @@ extern int i2c_detect(struct i2c_adapter *adapter, struct i2c_address_data *address_data, int (*found_proc) (struct i2c_adapter *, int, int)); - -/* This macro is used to scale user-input to sensible values in almost all - chip drivers. */ -static inline int SENSORS_LIMIT(long value, long low, long high) -{ - if (value < low) - return low; - else if (value > high) - return high; - else - return value; -} #endif /* def _LINUX_I2C_SENSOR_H */ -- cgit v1.2.3 From 9fc6adfa9adf2be84119a3c2592287f33bd1dff2 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 31 Jul 2005 21:20:43 +0200 Subject: [PATCH] hwmon: hwmon vs i2c, second round (01/11) Add support for kind-forced addresses to i2c_probe, like i2c_detect has for (essentially) hardware monitoring drivers. Note that this change will slightly increase the size of the drivers using I2C_CLIENT_INSMOD, with no immediate benefit. This is a requirement if we want to merge i2c_probe and i2c_detect though, and seems a reasonable price to pay in comparison with the previous cleanups which saved much more than that (such as the i2c-isa cleanup or the i2c address ranges removal.) Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index ad1c0fb164bc..9419bc5584ad 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -48,7 +48,6 @@ struct i2c_algorithm; struct i2c_adapter; struct i2c_client; struct i2c_driver; -struct i2c_client_address_data; union i2c_smbus_data; /* @@ -301,7 +300,7 @@ struct i2c_client_address_data { unsigned short *normal_i2c; unsigned short *probe; unsigned short *ignore; - unsigned short *force; + unsigned short **forces; }; /* Internal numbers to terminate lists */ @@ -575,11 +574,15 @@ union i2c_smbus_data { I2C_CLIENT_MODULE_PARM(force, \ "List of adapter,address pairs to boldly assume " \ "to be present"); \ + static unsigned short *addr_forces[] = { \ + force, \ + NULL \ + }; \ static struct i2c_client_address_data addr_data = { \ .normal_i2c = normal_i2c, \ .probe = probe, \ .ignore = ignore, \ - .force = force, \ + .forces = addr_forces, \ } #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From ef8dec5d8b3e96e359f377f35cd8caff42fe6d58 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 31 Jul 2005 21:33:23 +0200 Subject: [PATCH] hwmon: hwmon vs i2c, second round (02/11) The way i2c-sensor handles forced addresses could be optimized. It defines a structure (i2c_force_data) to associate a module parameter with a given kind value, but in fact this kind value is always the index of the structure in each array it is used in. So this additional value can be omitted, and still be deduced in the code handling these arrays. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-sensor.h | 133 +++++++++++++++++++++------------------------ 1 file changed, 61 insertions(+), 72 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-sensor.h b/include/linux/i2c-sensor.h index e832d3286a46..4facaa0b9054 100644 --- a/include/linux/i2c-sensor.h +++ b/include/linux/i2c-sensor.h @@ -22,22 +22,6 @@ #ifndef _LINUX_I2C_SENSOR_H #define _LINUX_I2C_SENSOR_H -/* A structure containing detect information. - Force variables overrule all other variables; they force a detection on - that place. If a specific chip is given, the module blindly assumes this - chip type is present; if a general force (kind == 0) is given, the module - will still try to figure out what type of chip is present. This is useful - if for some reasons the detect for SMBus address space filled fails. - probe: insmod parameter. Initialize this list with I2C_CLIENT_END values. - A list of pairs. The first value is a bus number (ANY_I2C_BUS for any - I2C bus), the second is the address. - kind: The kind of chip. 0 equals any chip. -*/ -struct i2c_force_data { - unsigned short *force; - unsigned short kind; -}; - /* A structure containing the detect information. normal_i2c: filled in by the module writer. Terminated by I2C_CLIENT_END. A list of I2C addresses which should normally be examined. @@ -50,14 +34,18 @@ struct i2c_force_data { I2C bus), the second is the I2C address. These addresses are never probed. This parameter overrules 'normal' and probe', but not the 'force' lists. - force_data: insmod parameters. A list, ending with an element of which - the force field is NULL. + forces: insmod parameters. A list, ending with a NULL element. + Force variables overrule all other variables; they force a detection on + that place. If a specific chip is given, the module blindly assumes this + chip type is present; if a general force (kind == 0) is given, the module + will still try to figure out what type of chip is present. This is useful + if for some reasons the detect for SMBus address space filled fails. */ struct i2c_address_data { unsigned short *normal_i2c; unsigned short *probe; unsigned short *ignore; - struct i2c_force_data *forces; + unsigned short **forces; }; #define SENSORS_MODULE_PARM_FORCE(name) \ @@ -88,7 +76,8 @@ struct i2c_address_data { I2C_CLIENT_MODULE_PARM(force, \ "List of adapter,address pairs to boldly assume " \ "to be present"); \ - static struct i2c_force_data forces[] = {{force,any_chip},{NULL}}; \ + static unsigned short *forces[] = { force, \ + NULL }; \ SENSORS_INSMOD #define SENSORS_INSMOD_1(chip1) \ @@ -97,9 +86,9 @@ struct i2c_address_data { "List of adapter,address pairs to boldly assume " \ "to be present"); \ SENSORS_MODULE_PARM_FORCE(chip1); \ - static struct i2c_force_data forces[] = {{force,any_chip},\ - {force_ ## chip1,chip1}, \ - {NULL}}; \ + static unsigned short *forces[] = { force, \ + force_##chip1, \ + NULL }; \ SENSORS_INSMOD #define SENSORS_INSMOD_2(chip1,chip2) \ @@ -109,10 +98,10 @@ struct i2c_address_data { "to be present"); \ SENSORS_MODULE_PARM_FORCE(chip1); \ SENSORS_MODULE_PARM_FORCE(chip2); \ - static struct i2c_force_data forces[] = {{force,any_chip}, \ - {force_ ## chip1,chip1}, \ - {force_ ## chip2,chip2}, \ - {NULL}}; \ + static unsigned short *forces[] = { force, \ + force_##chip1, \ + force_##chip2, \ + NULL }; \ SENSORS_INSMOD #define SENSORS_INSMOD_3(chip1,chip2,chip3) \ @@ -123,11 +112,11 @@ struct i2c_address_data { SENSORS_MODULE_PARM_FORCE(chip1); \ SENSORS_MODULE_PARM_FORCE(chip2); \ SENSORS_MODULE_PARM_FORCE(chip3); \ - static struct i2c_force_data forces[] = {{force,any_chip}, \ - {force_ ## chip1,chip1}, \ - {force_ ## chip2,chip2}, \ - {force_ ## chip3,chip3}, \ - {NULL}}; \ + static unsigned short *forces[] = { force, \ + force_##chip1, \ + force_##chip2, \ + force_##chip3, \ + NULL }; \ SENSORS_INSMOD #define SENSORS_INSMOD_4(chip1,chip2,chip3,chip4) \ @@ -139,12 +128,12 @@ struct i2c_address_data { SENSORS_MODULE_PARM_FORCE(chip2); \ SENSORS_MODULE_PARM_FORCE(chip3); \ SENSORS_MODULE_PARM_FORCE(chip4); \ - static struct i2c_force_data forces[] = {{force,any_chip}, \ - {force_ ## chip1,chip1}, \ - {force_ ## chip2,chip2}, \ - {force_ ## chip3,chip3}, \ - {force_ ## chip4,chip4}, \ - {NULL}}; \ + static unsigned short *forces[] = { force, \ + force_##chip1, \ + force_##chip2, \ + force_##chip3, \ + force_##chip4, \ + NULL}; \ SENSORS_INSMOD #define SENSORS_INSMOD_5(chip1,chip2,chip3,chip4,chip5) \ @@ -157,13 +146,13 @@ struct i2c_address_data { SENSORS_MODULE_PARM_FORCE(chip3); \ SENSORS_MODULE_PARM_FORCE(chip4); \ SENSORS_MODULE_PARM_FORCE(chip5); \ - static struct i2c_force_data forces[] = {{force,any_chip}, \ - {force_ ## chip1,chip1}, \ - {force_ ## chip2,chip2}, \ - {force_ ## chip3,chip3}, \ - {force_ ## chip4,chip4}, \ - {force_ ## chip5,chip5}, \ - {NULL}}; \ + static unsigned short *forces[] = { force, \ + force_##chip1, \ + force_##chip2, \ + force_##chip3, \ + force_##chip4, \ + force_##chip5, \ + NULL }; \ SENSORS_INSMOD #define SENSORS_INSMOD_6(chip1,chip2,chip3,chip4,chip5,chip6) \ @@ -177,14 +166,14 @@ struct i2c_address_data { SENSORS_MODULE_PARM_FORCE(chip4); \ SENSORS_MODULE_PARM_FORCE(chip5); \ SENSORS_MODULE_PARM_FORCE(chip6); \ - static struct i2c_force_data forces[] = {{force,any_chip}, \ - {force_ ## chip1,chip1}, \ - {force_ ## chip2,chip2}, \ - {force_ ## chip3,chip3}, \ - {force_ ## chip4,chip4}, \ - {force_ ## chip5,chip5}, \ - {force_ ## chip6,chip6}, \ - {NULL}}; \ + static unsigned short *forces[] = { force, \ + force_##chip1, \ + force_##chip2, \ + force_##chip3, \ + force_##chip4, \ + force_##chip5, \ + force_##chip6, \ + NULL }; \ SENSORS_INSMOD #define SENSORS_INSMOD_7(chip1,chip2,chip3,chip4,chip5,chip6,chip7) \ @@ -199,15 +188,15 @@ struct i2c_address_data { SENSORS_MODULE_PARM_FORCE(chip5); \ SENSORS_MODULE_PARM_FORCE(chip6); \ SENSORS_MODULE_PARM_FORCE(chip7); \ - static struct i2c_force_data forces[] = {{force,any_chip}, \ - {force_ ## chip1,chip1}, \ - {force_ ## chip2,chip2}, \ - {force_ ## chip3,chip3}, \ - {force_ ## chip4,chip4}, \ - {force_ ## chip5,chip5}, \ - {force_ ## chip6,chip6}, \ - {force_ ## chip7,chip7}, \ - {NULL}}; \ + static unsigned short *forces[] = { force, \ + force_##chip1, \ + force_##chip2, \ + force_##chip3, \ + force_##chip4, \ + force_##chip5, \ + force_##chip6, \ + force_##chip7, \ + NULL }; \ SENSORS_INSMOD #define SENSORS_INSMOD_8(chip1,chip2,chip3,chip4,chip5,chip6,chip7,chip8) \ @@ -223,16 +212,16 @@ struct i2c_address_data { SENSORS_MODULE_PARM_FORCE(chip6); \ SENSORS_MODULE_PARM_FORCE(chip7); \ SENSORS_MODULE_PARM_FORCE(chip8); \ - static struct i2c_force_data forces[] = {{force,any_chip}, \ - {force_ ## chip1,chip1}, \ - {force_ ## chip2,chip2}, \ - {force_ ## chip3,chip3}, \ - {force_ ## chip4,chip4}, \ - {force_ ## chip5,chip5}, \ - {force_ ## chip6,chip6}, \ - {force_ ## chip7,chip7}, \ - {force_ ## chip8,chip8}, \ - {NULL}}; \ + static unsigned short *forces[] = { force, \ + force_##chip1, \ + force_##chip2, \ + force_##chip3, \ + force_##chip4, \ + force_##chip5, \ + force_##chip6, \ + force_##chip7, \ + force_##chip8, \ + NULL }; \ SENSORS_INSMOD /* Detect function. It iterates over all possible addresses itself. For -- cgit v1.2.3 From b78ec31582c60578ee1d3bb470791d6dde96ccf7 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 31 Jul 2005 21:36:24 +0200 Subject: [PATCH] hwmon: hwmon vs i2c, second round (03/11) We now have two identical structures, i2c_address_data in i2c-sensor.h and i2c_client_address_data in i2c.h. We can kill one of them, I choose to keep the one in i2c.h as it makes more sense (this structure is not specific to sensors.) Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-sensor.h | 30 +++--------------------------- 1 file changed, 3 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-sensor.h b/include/linux/i2c-sensor.h index 4facaa0b9054..fc9284af9fae 100644 --- a/include/linux/i2c-sensor.h +++ b/include/linux/i2c-sensor.h @@ -22,31 +22,7 @@ #ifndef _LINUX_I2C_SENSOR_H #define _LINUX_I2C_SENSOR_H -/* A structure containing the detect information. - normal_i2c: filled in by the module writer. Terminated by I2C_CLIENT_END. - A list of I2C addresses which should normally be examined. - probe: insmod parameter. Initialize this list with I2C_CLIENT_END values. - A list of pairs. The first value is a bus number (ANY_I2C_BUS for any - I2C bus), the second is the address. These addresses are also probed, - as if they were in the 'normal' list. - ignore: insmod parameter. Initialize this list with I2C_CLIENT_END values. - A list of pairs. The first value is a bus number (ANY_I2C_BUS for any - I2C bus), the second is the I2C address. These addresses are never - probed. This parameter overrules 'normal' and probe', but not the - 'force' lists. - forces: insmod parameters. A list, ending with a NULL element. - Force variables overrule all other variables; they force a detection on - that place. If a specific chip is given, the module blindly assumes this - chip type is present; if a general force (kind == 0) is given, the module - will still try to figure out what type of chip is present. This is useful - if for some reasons the detect for SMBus address space filled fails. -*/ -struct i2c_address_data { - unsigned short *normal_i2c; - unsigned short *probe; - unsigned short *ignore; - unsigned short **forces; -}; +#include #define SENSORS_MODULE_PARM_FORCE(name) \ I2C_CLIENT_MODULE_PARM(force_ ## name, \ @@ -60,7 +36,7 @@ struct i2c_address_data { "List of adapter,address pairs to scan additionally"); \ I2C_CLIENT_MODULE_PARM(ignore, \ "List of adapter,address pairs not to scan"); \ - static struct i2c_address_data addr_data = { \ + static struct i2c_client_address_data addr_data = { \ .normal_i2c = normal_i2c, \ .probe = probe, \ .ignore = ignore, \ @@ -228,7 +204,7 @@ struct i2c_address_data { SMBus addresses, it will only call found_proc if some client is connected to the SMBus (unless a 'force' matched). */ extern int i2c_detect(struct i2c_adapter *adapter, - struct i2c_address_data *address_data, + struct i2c_client_address_data *address_data, int (*found_proc) (struct i2c_adapter *, int, int)); #endif /* def _LINUX_I2C_SENSOR_H */ -- cgit v1.2.3 From 96478ef3f3f71fa929cc905cc794993e312d9a5d Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 31 Jul 2005 21:45:27 +0200 Subject: [PATCH] hwmon: hwmon vs i2c, second round (05/11) The i2c_detect function has no more user, delete it. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-sensor.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-sensor.h b/include/linux/i2c-sensor.h index fc9284af9fae..1563d445dfd1 100644 --- a/include/linux/i2c-sensor.h +++ b/include/linux/i2c-sensor.h @@ -200,11 +200,4 @@ NULL }; \ SENSORS_INSMOD -/* Detect function. It iterates over all possible addresses itself. For - SMBus addresses, it will only call found_proc if some client is connected - to the SMBus (unless a 'force' matched). */ -extern int i2c_detect(struct i2c_adapter *adapter, - struct i2c_client_address_data *address_data, - int (*found_proc) (struct i2c_adapter *, int, int)); - #endif /* def _LINUX_I2C_SENSOR_H */ -- cgit v1.2.3 From f4b50261207c987913f076d867c2e154d71fd012 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 31 Jul 2005 21:49:03 +0200 Subject: [PATCH] hwmon: hwmon vs i2c, second round (06/11) The only thing left in i2c-sensor.h are module parameter definition macros. It's only an extension of what i2c.h offers, and this extension is not sensors-specific. As a matter of fact, a few non-sensors drivers use them. So we better merge them in i2c.h, and get rid of i2c-sensor.h altogether. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-sensor.h | 203 --------------------------------------------- include/linux/i2c.h | 148 ++++++++++++++++++++++++++++++--- 2 files changed, 136 insertions(+), 215 deletions(-) delete mode 100644 include/linux/i2c-sensor.h (limited to 'include/linux') diff --git a/include/linux/i2c-sensor.h b/include/linux/i2c-sensor.h deleted file mode 100644 index 1563d445dfd1..000000000000 --- a/include/linux/i2c-sensor.h +++ /dev/null @@ -1,203 +0,0 @@ -/* - i2c-sensor.h - Part of the i2c package - was originally sensors.h - Part of lm_sensors, Linux kernel modules - for hardware monitoring - Copyright (c) 1998, 1999 Frodo Looijaard - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. -*/ - -#ifndef _LINUX_I2C_SENSOR_H -#define _LINUX_I2C_SENSOR_H - -#include - -#define SENSORS_MODULE_PARM_FORCE(name) \ - I2C_CLIENT_MODULE_PARM(force_ ## name, \ - "List of adapter,address pairs which are unquestionably" \ - " assumed to contain a `" # name "' chip") - - -/* This defines several insmod variables, and the addr_data structure */ -#define SENSORS_INSMOD \ - I2C_CLIENT_MODULE_PARM(probe, \ - "List of adapter,address pairs to scan additionally"); \ - I2C_CLIENT_MODULE_PARM(ignore, \ - "List of adapter,address pairs not to scan"); \ - static struct i2c_client_address_data addr_data = { \ - .normal_i2c = normal_i2c, \ - .probe = probe, \ - .ignore = ignore, \ - .forces = forces, \ - } - -/* The following functions create an enum with the chip names as elements. - The first element of the enum is any_chip. These are the only macros - a module will want to use. */ - -#define SENSORS_INSMOD_0 \ - enum chips { any_chip }; \ - I2C_CLIENT_MODULE_PARM(force, \ - "List of adapter,address pairs to boldly assume " \ - "to be present"); \ - static unsigned short *forces[] = { force, \ - NULL }; \ - SENSORS_INSMOD - -#define SENSORS_INSMOD_1(chip1) \ - enum chips { any_chip, chip1 }; \ - I2C_CLIENT_MODULE_PARM(force, \ - "List of adapter,address pairs to boldly assume " \ - "to be present"); \ - SENSORS_MODULE_PARM_FORCE(chip1); \ - static unsigned short *forces[] = { force, \ - force_##chip1, \ - NULL }; \ - SENSORS_INSMOD - -#define SENSORS_INSMOD_2(chip1,chip2) \ - enum chips { any_chip, chip1, chip2 }; \ - I2C_CLIENT_MODULE_PARM(force, \ - "List of adapter,address pairs to boldly assume " \ - "to be present"); \ - SENSORS_MODULE_PARM_FORCE(chip1); \ - SENSORS_MODULE_PARM_FORCE(chip2); \ - static unsigned short *forces[] = { force, \ - force_##chip1, \ - force_##chip2, \ - NULL }; \ - SENSORS_INSMOD - -#define SENSORS_INSMOD_3(chip1,chip2,chip3) \ - enum chips { any_chip, chip1, chip2, chip3 }; \ - I2C_CLIENT_MODULE_PARM(force, \ - "List of adapter,address pairs to boldly assume " \ - "to be present"); \ - SENSORS_MODULE_PARM_FORCE(chip1); \ - SENSORS_MODULE_PARM_FORCE(chip2); \ - SENSORS_MODULE_PARM_FORCE(chip3); \ - static unsigned short *forces[] = { force, \ - force_##chip1, \ - force_##chip2, \ - force_##chip3, \ - NULL }; \ - SENSORS_INSMOD - -#define SENSORS_INSMOD_4(chip1,chip2,chip3,chip4) \ - enum chips { any_chip, chip1, chip2, chip3, chip4 }; \ - I2C_CLIENT_MODULE_PARM(force, \ - "List of adapter,address pairs to boldly assume " \ - "to be present"); \ - SENSORS_MODULE_PARM_FORCE(chip1); \ - SENSORS_MODULE_PARM_FORCE(chip2); \ - SENSORS_MODULE_PARM_FORCE(chip3); \ - SENSORS_MODULE_PARM_FORCE(chip4); \ - static unsigned short *forces[] = { force, \ - force_##chip1, \ - force_##chip2, \ - force_##chip3, \ - force_##chip4, \ - NULL}; \ - SENSORS_INSMOD - -#define SENSORS_INSMOD_5(chip1,chip2,chip3,chip4,chip5) \ - enum chips { any_chip, chip1, chip2, chip3, chip4, chip5 }; \ - I2C_CLIENT_MODULE_PARM(force, \ - "List of adapter,address pairs to boldly assume " \ - "to be present"); \ - SENSORS_MODULE_PARM_FORCE(chip1); \ - SENSORS_MODULE_PARM_FORCE(chip2); \ - SENSORS_MODULE_PARM_FORCE(chip3); \ - SENSORS_MODULE_PARM_FORCE(chip4); \ - SENSORS_MODULE_PARM_FORCE(chip5); \ - static unsigned short *forces[] = { force, \ - force_##chip1, \ - force_##chip2, \ - force_##chip3, \ - force_##chip4, \ - force_##chip5, \ - NULL }; \ - SENSORS_INSMOD - -#define SENSORS_INSMOD_6(chip1,chip2,chip3,chip4,chip5,chip6) \ - enum chips { any_chip, chip1, chip2, chip3, chip4, chip5, chip6 }; \ - I2C_CLIENT_MODULE_PARM(force, \ - "List of adapter,address pairs to boldly assume " \ - "to be present"); \ - SENSORS_MODULE_PARM_FORCE(chip1); \ - SENSORS_MODULE_PARM_FORCE(chip2); \ - SENSORS_MODULE_PARM_FORCE(chip3); \ - SENSORS_MODULE_PARM_FORCE(chip4); \ - SENSORS_MODULE_PARM_FORCE(chip5); \ - SENSORS_MODULE_PARM_FORCE(chip6); \ - static unsigned short *forces[] = { force, \ - force_##chip1, \ - force_##chip2, \ - force_##chip3, \ - force_##chip4, \ - force_##chip5, \ - force_##chip6, \ - NULL }; \ - SENSORS_INSMOD - -#define SENSORS_INSMOD_7(chip1,chip2,chip3,chip4,chip5,chip6,chip7) \ - enum chips { any_chip, chip1, chip2, chip3, chip4, chip5, chip6, chip7 }; \ - I2C_CLIENT_MODULE_PARM(force, \ - "List of adapter,address pairs to boldly assume " \ - "to be present"); \ - SENSORS_MODULE_PARM_FORCE(chip1); \ - SENSORS_MODULE_PARM_FORCE(chip2); \ - SENSORS_MODULE_PARM_FORCE(chip3); \ - SENSORS_MODULE_PARM_FORCE(chip4); \ - SENSORS_MODULE_PARM_FORCE(chip5); \ - SENSORS_MODULE_PARM_FORCE(chip6); \ - SENSORS_MODULE_PARM_FORCE(chip7); \ - static unsigned short *forces[] = { force, \ - force_##chip1, \ - force_##chip2, \ - force_##chip3, \ - force_##chip4, \ - force_##chip5, \ - force_##chip6, \ - force_##chip7, \ - NULL }; \ - SENSORS_INSMOD - -#define SENSORS_INSMOD_8(chip1,chip2,chip3,chip4,chip5,chip6,chip7,chip8) \ - enum chips { any_chip, chip1, chip2, chip3, chip4, chip5, chip6, chip7, chip8 }; \ - I2C_CLIENT_MODULE_PARM(force, \ - "List of adapter,address pairs to boldly assume " \ - "to be present"); \ - SENSORS_MODULE_PARM_FORCE(chip1); \ - SENSORS_MODULE_PARM_FORCE(chip2); \ - SENSORS_MODULE_PARM_FORCE(chip3); \ - SENSORS_MODULE_PARM_FORCE(chip4); \ - SENSORS_MODULE_PARM_FORCE(chip5); \ - SENSORS_MODULE_PARM_FORCE(chip6); \ - SENSORS_MODULE_PARM_FORCE(chip7); \ - SENSORS_MODULE_PARM_FORCE(chip8); \ - static unsigned short *forces[] = { force, \ - force_##chip1, \ - force_##chip2, \ - force_##chip3, \ - force_##chip4, \ - force_##chip5, \ - force_##chip6, \ - force_##chip7, \ - force_##chip8, \ - NULL }; \ - SENSORS_INSMOD - -#endif /* def _LINUX_I2C_SENSOR_H */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 9419bc5584ad..3ad3969b6f0d 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -565,24 +565,148 @@ union i2c_smbus_data { module_param_array(var, short, &var##_num, 0); \ MODULE_PARM_DESC(var,desc) -/* This is the one you want to use in your own modules */ +#define I2C_CLIENT_MODULE_PARM_FORCE(name) \ +I2C_CLIENT_MODULE_PARM(force_##name, \ + "List of adapter,address pairs which are " \ + "unquestionably assumed to contain a `" \ + # name "' chip") + + +#define I2C_CLIENT_INSMOD_COMMON \ +I2C_CLIENT_MODULE_PARM(probe, "List of adapter,address pairs to scan " \ + "additionally"); \ +I2C_CLIENT_MODULE_PARM(ignore, "List of adapter,address pairs not to " \ + "scan"); \ +static struct i2c_client_address_data addr_data = { \ + .normal_i2c = normal_i2c, \ + .probe = probe, \ + .ignore = ignore, \ + .forces = forces, \ +} + +/* These are the ones you want to use in your own drivers. Pick the one + which matches the number of devices the driver differenciates between. */ #define I2C_CLIENT_INSMOD \ - I2C_CLIENT_MODULE_PARM(probe, \ - "List of adapter,address pairs to scan additionally"); \ - I2C_CLIENT_MODULE_PARM(ignore, \ - "List of adapter,address pairs not to scan"); \ I2C_CLIENT_MODULE_PARM(force, \ "List of adapter,address pairs to boldly assume " \ "to be present"); \ - static unsigned short *addr_forces[] = { \ + static unsigned short *forces[] = { \ force, \ NULL \ }; \ - static struct i2c_client_address_data addr_data = { \ - .normal_i2c = normal_i2c, \ - .probe = probe, \ - .ignore = ignore, \ - .forces = addr_forces, \ - } +I2C_CLIENT_INSMOD_COMMON + +#define I2C_CLIENT_INSMOD_1(chip1) \ +enum chips { any_chip, chip1 }; \ +I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ + "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ +static unsigned short *forces[] = { force, force_##chip1, NULL }; \ +I2C_CLIENT_INSMOD_COMMON + +#define I2C_CLIENT_INSMOD_2(chip1, chip2) \ +enum chips { any_chip, chip1, chip2 }; \ +I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ + "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ +static unsigned short *forces[] = { force, force_##chip1, \ + force_##chip2, NULL }; \ +I2C_CLIENT_INSMOD_COMMON + +#define I2C_CLIENT_INSMOD_3(chip1, chip2, chip3) \ +enum chips { any_chip, chip1, chip2, chip3 }; \ +I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ + "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip3); \ +static unsigned short *forces[] = { force, force_##chip1, \ + force_##chip2, force_##chip3, \ + NULL }; \ +I2C_CLIENT_INSMOD_COMMON + +#define I2C_CLIENT_INSMOD_4(chip1, chip2, chip3, chip4) \ +enum chips { any_chip, chip1, chip2, chip3, chip4 }; \ +I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ + "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip3); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip4); \ +static unsigned short *forces[] = { force, force_##chip1, \ + force_##chip2, force_##chip3, \ + force_##chip4, NULL}; \ +I2C_CLIENT_INSMOD_COMMON + +#define I2C_CLIENT_INSMOD_5(chip1, chip2, chip3, chip4, chip5) \ +enum chips { any_chip, chip1, chip2, chip3, chip4, chip5 }; \ +I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ + "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip3); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip4); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip5); \ +static unsigned short *forces[] = { force, force_##chip1, \ + force_##chip2, force_##chip3, \ + force_##chip4, force_##chip5, \ + NULL }; \ +I2C_CLIENT_INSMOD_COMMON + +#define I2C_CLIENT_INSMOD_6(chip1, chip2, chip3, chip4, chip5, chip6) \ +enum chips { any_chip, chip1, chip2, chip3, chip4, chip5, chip6 }; \ +I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ + "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip3); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip4); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip5); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip6); \ +static unsigned short *forces[] = { force, force_##chip1, \ + force_##chip2, force_##chip3, \ + force_##chip4, force_##chip5, \ + force_##chip6, NULL }; \ +I2C_CLIENT_INSMOD_COMMON + +#define I2C_CLIENT_INSMOD_7(chip1, chip2, chip3, chip4, chip5, chip6, chip7) \ +enum chips { any_chip, chip1, chip2, chip3, chip4, chip5, chip6, \ + chip7 }; \ +I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ + "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip3); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip4); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip5); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip6); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip7); \ +static unsigned short *forces[] = { force, force_##chip1, \ + force_##chip2, force_##chip3, \ + force_##chip4, force_##chip5, \ + force_##chip6, force_##chip7, \ + NULL }; \ +I2C_CLIENT_INSMOD_COMMON + +#define I2C_CLIENT_INSMOD_8(chip1, chip2, chip3, chip4, chip5, chip6, chip7, chip8) \ +enum chips { any_chip, chip1, chip2, chip3, chip4, chip5, chip6, \ + chip7, chip8 }; \ +I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ + "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip3); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip4); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip5); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip6); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip7); \ +I2C_CLIENT_MODULE_PARM_FORCE(chip8); \ +static unsigned short *forces[] = { force, force_##chip1, \ + force_##chip2, force_##chip3, \ + force_##chip4, force_##chip5, \ + force_##chip6, force_##chip7, \ + force_##chip8, NULL }; \ +I2C_CLIENT_INSMOD_COMMON #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From 303760b44a7a142cb9f4c9df4609fb63bbda98db Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 31 Jul 2005 21:52:01 +0200 Subject: [PATCH] hwmon: hwmon vs i2c, second round (07/11) The only part left in i2c-sensor is the VRM/VRD/VID handling code. This is in no way related to i2c, so it doesn't belong there. Move the code to hwmon, where it belongs. Note that not all hardware monitoring drivers do VRM/VRD/VID operations, so less drivers depend on hwmon-vid than there were depending on i2c-sensor. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/hwmon-vid.h | 112 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/i2c-vid.h | 111 --------------------------------------------- 2 files changed, 112 insertions(+), 111 deletions(-) create mode 100644 include/linux/hwmon-vid.h delete mode 100644 include/linux/i2c-vid.h (limited to 'include/linux') diff --git a/include/linux/hwmon-vid.h b/include/linux/hwmon-vid.h new file mode 100644 index 000000000000..c45cd872c55e --- /dev/null +++ b/include/linux/hwmon-vid.h @@ -0,0 +1,112 @@ +/* + hwmon-vid.h - VID/VRM/VRD voltage conversions + + Originally part of lm_sensors + Copyright (c) 2002 Mark D. Studebaker + With assistance from Trent Piepho + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. +*/ + +/* + This file contains common code for decoding VID pins. + This file is #included in various chip drivers in this directory. + As the user is unlikely to load more than one driver which + includes this code we don't worry about the wasted space. + Reference: VRM x.y DC-DC Converter Design Guidelines, + available at http://developer.intel.com +*/ + +/* + AMD Opteron processors don't follow the Intel VRM spec. + I'm going to "make up" 2.4 as the VRM spec for the Opterons. + No good reason just a mnemonic for the 24x Opteron processor + series + + Opteron VID encoding is: + + 00000 = 1.550 V + 00001 = 1.525 V + . . . . + 11110 = 0.800 V + 11111 = 0.000 V (off) + */ + +/* + Legal val values 0x00 - 0x1f; except for VRD 10.0, 0x00 - 0x3f. + vrm is the Intel VRM document version. + Note: vrm version is scaled by 10 and the return value is scaled by 1000 + to avoid floating point in the kernel. +*/ + +int vid_which_vrm(void); + +#define DEFAULT_VRM 82 + +static inline int vid_from_reg(int val, int vrm) +{ + int vid; + + switch(vrm) { + + case 0: + return 0; + + case 100: /* VRD 10.0 */ + if((val & 0x1f) == 0x1f) + return 0; + if((val & 0x1f) <= 0x09 || val == 0x0a) + vid = 10875 - (val & 0x1f) * 250; + else + vid = 18625 - (val & 0x1f) * 250; + if(val & 0x20) + vid -= 125; + vid /= 10; /* only return 3 dec. places for now */ + return vid; + + case 24: /* Opteron processor */ + return(val == 0x1f ? 0 : 1550 - val * 25); + + case 91: /* VRM 9.1 */ + case 90: /* VRM 9.0 */ + return(val == 0x1f ? 0 : + 1850 - val * 25); + + case 85: /* VRM 8.5 */ + return((val & 0x10 ? 25 : 0) + + ((val & 0x0f) > 0x04 ? 2050 : 1250) - + ((val & 0x0f) * 50)); + + case 84: /* VRM 8.4 */ + val &= 0x0f; + /* fall through */ + default: /* VRM 8.2 */ + return(val == 0x1f ? 0 : + val & 0x10 ? 5100 - (val) * 100 : + 2050 - (val) * 50); + } +} + +static inline int vid_to_reg(int val, int vrm) +{ + switch (vrm) { + case 91: /* VRM 9.1 */ + case 90: /* VRM 9.0 */ + return ((val >= 1100) && (val <= 1850) ? + ((18499 - val * 10) / 25 + 5) / 10 : -1); + default: + return -1; + } +} diff --git a/include/linux/i2c-vid.h b/include/linux/i2c-vid.h deleted file mode 100644 index 41d0635e0ba9..000000000000 --- a/include/linux/i2c-vid.h +++ /dev/null @@ -1,111 +0,0 @@ -/* - i2c-vid.h - Part of lm_sensors, Linux kernel modules for hardware - monitoring - Copyright (c) 2002 Mark D. Studebaker - With assistance from Trent Piepho - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. -*/ - -/* - This file contains common code for decoding VID pins. - This file is #included in various chip drivers in this directory. - As the user is unlikely to load more than one driver which - includes this code we don't worry about the wasted space. - Reference: VRM x.y DC-DC Converter Design Guidelines, - available at http://developer.intel.com -*/ - -/* - AMD Opteron processors don't follow the Intel VRM spec. - I'm going to "make up" 2.4 as the VRM spec for the Opterons. - No good reason just a mnemonic for the 24x Opteron processor - series - - Opteron VID encoding is: - - 00000 = 1.550 V - 00001 = 1.525 V - . . . . - 11110 = 0.800 V - 11111 = 0.000 V (off) - */ - -/* - Legal val values 0x00 - 0x1f; except for VRD 10.0, 0x00 - 0x3f. - vrm is the Intel VRM document version. - Note: vrm version is scaled by 10 and the return value is scaled by 1000 - to avoid floating point in the kernel. -*/ - -int i2c_which_vrm(void); - -#define DEFAULT_VRM 82 - -static inline int vid_from_reg(int val, int vrm) -{ - int vid; - - switch(vrm) { - - case 0: - return 0; - - case 100: /* VRD 10.0 */ - if((val & 0x1f) == 0x1f) - return 0; - if((val & 0x1f) <= 0x09 || val == 0x0a) - vid = 10875 - (val & 0x1f) * 250; - else - vid = 18625 - (val & 0x1f) * 250; - if(val & 0x20) - vid -= 125; - vid /= 10; /* only return 3 dec. places for now */ - return vid; - - case 24: /* Opteron processor */ - return(val == 0x1f ? 0 : 1550 - val * 25); - - case 91: /* VRM 9.1 */ - case 90: /* VRM 9.0 */ - return(val == 0x1f ? 0 : - 1850 - val * 25); - - case 85: /* VRM 8.5 */ - return((val & 0x10 ? 25 : 0) + - ((val & 0x0f) > 0x04 ? 2050 : 1250) - - ((val & 0x0f) * 50)); - - case 84: /* VRM 8.4 */ - val &= 0x0f; - /* fall through */ - default: /* VRM 8.2 */ - return(val == 0x1f ? 0 : - val & 0x10 ? 5100 - (val) * 100 : - 2050 - (val) * 50); - } -} - -static inline int vid_to_reg(int val, int vrm) -{ - switch (vrm) { - case 91: /* VRM 9.1 */ - case 90: /* VRM 9.0 */ - return ((val >= 1100) && (val <= 1850) ? - ((18499 - val * 10) / 25 + 5) / 10 : -1); - default: - return -1; - } -} -- cgit v1.2.3 From ee70d3a33368038d41985474d9e70ac07f19651c Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 31 Jul 2005 21:57:33 +0200 Subject: [PATCH] hwmon: hwmon vs i2c, second round (09/11) Delete DEFAULT_VRM from hwmon-vid.h, it has no more users. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/hwmon-vid.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hwmon-vid.h b/include/linux/hwmon-vid.h index c45cd872c55e..6d9d4f9bad58 100644 --- a/include/linux/hwmon-vid.h +++ b/include/linux/hwmon-vid.h @@ -53,8 +53,6 @@ int vid_which_vrm(void); -#define DEFAULT_VRM 82 - static inline int vid_from_reg(int val, int vrm) { int vid; -- cgit v1.2.3 From d0f282706df877f8fd8869419e308d24eedb523b Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 1 Aug 2005 22:50:08 +0200 Subject: [PATCH] hwmon: hwmon vs i2c, second round (10/11) I see very little reason why vid_from_reg is inlined. It is not exactly short, its parameters are seldom known in advance, and it is never called in speed critical areas. Uninlining it should cause little performance loss if any, and saves a signficant space as well as compilation time. As suggested by Alexey Dobriyan, I am leaving vid_to_reg inline for now, as it is short and has a single user so far. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/hwmon-vid.h | 83 +++++------------------------------------------ 1 file changed, 9 insertions(+), 74 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hwmon-vid.h b/include/linux/hwmon-vid.h index 6d9d4f9bad58..cd4b7a042b86 100644 --- a/include/linux/hwmon-vid.h +++ b/include/linux/hwmon-vid.h @@ -20,83 +20,16 @@ Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -/* - This file contains common code for decoding VID pins. - This file is #included in various chip drivers in this directory. - As the user is unlikely to load more than one driver which - includes this code we don't worry about the wasted space. - Reference: VRM x.y DC-DC Converter Design Guidelines, - available at http://developer.intel.com -*/ - -/* - AMD Opteron processors don't follow the Intel VRM spec. - I'm going to "make up" 2.4 as the VRM spec for the Opterons. - No good reason just a mnemonic for the 24x Opteron processor - series - - Opteron VID encoding is: - - 00000 = 1.550 V - 00001 = 1.525 V - . . . . - 11110 = 0.800 V - 11111 = 0.000 V (off) - */ - -/* - Legal val values 0x00 - 0x1f; except for VRD 10.0, 0x00 - 0x3f. - vrm is the Intel VRM document version. - Note: vrm version is scaled by 10 and the return value is scaled by 1000 - to avoid floating point in the kernel. -*/ +#ifndef _LINUX_HWMON_VID_H +#define _LINUX_HWMON_VID_H +int vid_from_reg(int val, int vrm); int vid_which_vrm(void); -static inline int vid_from_reg(int val, int vrm) -{ - int vid; - - switch(vrm) { - - case 0: - return 0; - - case 100: /* VRD 10.0 */ - if((val & 0x1f) == 0x1f) - return 0; - if((val & 0x1f) <= 0x09 || val == 0x0a) - vid = 10875 - (val & 0x1f) * 250; - else - vid = 18625 - (val & 0x1f) * 250; - if(val & 0x20) - vid -= 125; - vid /= 10; /* only return 3 dec. places for now */ - return vid; - - case 24: /* Opteron processor */ - return(val == 0x1f ? 0 : 1550 - val * 25); - - case 91: /* VRM 9.1 */ - case 90: /* VRM 9.0 */ - return(val == 0x1f ? 0 : - 1850 - val * 25); - - case 85: /* VRM 8.5 */ - return((val & 0x10 ? 25 : 0) + - ((val & 0x0f) > 0x04 ? 2050 : 1250) - - ((val & 0x0f) * 50)); - - case 84: /* VRM 8.4 */ - val &= 0x0f; - /* fall through */ - default: /* VRM 8.2 */ - return(val == 0x1f ? 0 : - val & 0x10 ? 5100 - (val) * 100 : - 2050 - (val) * 50); - } -} - +/* vrm is the VRM/VRD document version multiplied by 10. + val is in mV to avoid floating point in the kernel. + Returned value is the 4-, 5- or 6-bit VID code. + Note that only VRM 9.x is supported for now. */ static inline int vid_to_reg(int val, int vrm) { switch (vrm) { @@ -108,3 +41,5 @@ static inline int vid_to_reg(int val, int vrm) return -1; } } + +#endif /* _LINUX_HWMON_VID_H */ -- cgit v1.2.3 From 975185880d55676b1352047e82a0cb84173c6c28 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 11 Aug 2005 23:33:24 +0200 Subject: [PATCH] I2C: Kill i2c_algorithm.name (1/7) The name member of the i2c_algorithm is never used, although all drivers conscientiously fill it. We can drop it completely, this structure doesn't need to have a name. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 3ad3969b6f0d..f04b1fc6a0fa 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -192,7 +192,6 @@ static inline char *i2c_clientname(struct i2c_client *c) * to name two of the most common. */ struct i2c_algorithm { - char name[32]; /* textual description */ unsigned int id; /* If an adapter algorithm can't do I2C-level access, set master_xfer -- cgit v1.2.3 From e51cc6b3a365e170d3ebe51c2308fdd42e027a46 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 11 Aug 2005 23:36:49 +0200 Subject: [PATCH] I2C: Kill i2c_algorithm.id (2/7) Use the adapter id rather than the algorithm id to detect the i2c-isa pseudo-adapter. This saves one level of dereferencing, and the algorithm ids will soon be gone anyway. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-isa.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-isa.h b/include/linux/i2c-isa.h index db793b68356c..54c27e88d101 100644 --- a/include/linux/i2c-isa.h +++ b/include/linux/i2c-isa.h @@ -28,9 +28,9 @@ extern int i2c_isa_del_driver(struct i2c_driver *driver); /* Detect whether we are on the isa bus. This is only useful to hybrid (i2c+isa) drivers. */ -#define i2c_is_isa_client(clientptr) \ - ((clientptr)->adapter->algo->id == I2C_ALGO_ISA) #define i2c_is_isa_adapter(adapptr) \ - ((adapptr)->algo->id == I2C_ALGO_ISA) + ((adapptr)->id == (I2C_ALGO_ISA | I2C_HW_ISA)) +#define i2c_is_isa_client(clientptr) \ + i2c_is_isa_adapter((clientptr)->adapter) #endif /* _LINUX_I2C_ISA_H */ -- cgit v1.2.3 From 1d8b9e1bad35fa3ea829990b9056c2a257d8fe79 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 11 Aug 2005 23:40:19 +0200 Subject: [PATCH] I2C: Kill i2c_algorithm.id (4/7) There are no more users of i2c_algorithm.id, so we can finally drop this structure member. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index f04b1fc6a0fa..af4983b488b6 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -192,8 +192,6 @@ static inline char *i2c_clientname(struct i2c_client *c) * to name two of the most common. */ struct i2c_algorithm { - unsigned int id; - /* If an adapter algorithm can't do I2C-level access, set master_xfer to NULL. If an adapter algorithm can do SMBus access, set smbus_xfer. If set to NULL, the SMBus protocol is simulated -- cgit v1.2.3 From c7a46533ff7ef9e1c51bae6e54208527c5275b24 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 11 Aug 2005 23:41:56 +0200 Subject: [PATCH] I2C: Kill i2c_algorithm.id (5/7) Merge the algorithm id part (16 upper bits) of the i2c adapters ids into the definition of the adapters ids directly. After that, we don't need to OR both ids together for each i2c_adapter structure. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-id.h | 128 ++++++++++++++++++++++++------------------------ include/linux/i2c-isa.h | 2 +- 2 files changed, 65 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 33f08258f22b..5b72f664cc21 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -218,103 +218,103 @@ */ /* --- Bit algorithm adapters */ -#define I2C_HW_B_LP 0x00 /* Parallel port Philips style adapter */ -#define I2C_HW_B_LPC 0x01 /* Parallel port, over control reg. */ -#define I2C_HW_B_SER 0x02 /* Serial line interface */ -#define I2C_HW_B_ELV 0x03 /* ELV Card */ -#define I2C_HW_B_VELLE 0x04 /* Vellemann K8000 */ -#define I2C_HW_B_BT848 0x05 /* BT848 video boards */ -#define I2C_HW_B_WNV 0x06 /* Winnov Videums */ -#define I2C_HW_B_VIA 0x07 /* Via vt82c586b */ -#define I2C_HW_B_HYDRA 0x08 /* Apple Hydra Mac I/O */ -#define I2C_HW_B_G400 0x09 /* Matrox G400 */ -#define I2C_HW_B_I810 0x0a /* Intel I810 */ -#define I2C_HW_B_VOO 0x0b /* 3dfx Voodoo 3 / Banshee */ -#define I2C_HW_B_PPORT 0x0c /* Primitive parallel port adapter */ -#define I2C_HW_B_SAVG 0x0d /* Savage 4 */ -#define I2C_HW_B_SCX200 0x0e /* Nat'l Semi SCx200 I2C */ -#define I2C_HW_B_RIVA 0x10 /* Riva based graphics cards */ -#define I2C_HW_B_IOC 0x11 /* IOC bit-wiggling */ -#define I2C_HW_B_TSUNA 0x12 /* DEC Tsunami chipset */ -#define I2C_HW_B_FRODO 0x13 /* 2d3D, Inc. SA-1110 Development Board */ -#define I2C_HW_B_OMAHA 0x14 /* Omaha I2C interface (ARM) */ -#define I2C_HW_B_GUIDE 0x15 /* Guide bit-basher */ -#define I2C_HW_B_IXP2000 0x16 /* GPIO on IXP2000 systems */ -#define I2C_HW_B_IXP4XX 0x17 /* GPIO on IXP4XX systems */ -#define I2C_HW_B_S3VIA 0x18 /* S3Via ProSavage adapter */ -#define I2C_HW_B_ZR36067 0x19 /* Zoran-36057/36067 based boards */ -#define I2C_HW_B_PCILYNX 0x1a /* TI PCILynx I2C adapter */ -#define I2C_HW_B_CX2388x 0x1b /* connexant 2388x based tv cards */ +#define I2C_HW_B_LP 0x010000 /* Parallel port Philips style */ +#define I2C_HW_B_LPC 0x010001 /* Parallel port control reg. */ +#define I2C_HW_B_SER 0x010002 /* Serial line interface */ +#define I2C_HW_B_ELV 0x010003 /* ELV Card */ +#define I2C_HW_B_VELLE 0x010004 /* Vellemann K8000 */ +#define I2C_HW_B_BT848 0x010005 /* BT848 video boards */ +#define I2C_HW_B_WNV 0x010006 /* Winnov Videums */ +#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_PPORT 0x01000c /* Primitive parallel port adapter */ +#define I2C_HW_B_SAVG 0x01000d /* Savage 4 */ +#define I2C_HW_B_SCX200 0x01000e /* Nat'l Semi SCx200 I2C */ +#define I2C_HW_B_RIVA 0x010010 /* Riva based graphics cards */ +#define I2C_HW_B_IOC 0x010011 /* IOC bit-wiggling */ +#define I2C_HW_B_TSUNA 0x010012 /* DEC Tsunami chipset */ +#define I2C_HW_B_FRODO 0x010013 /* 2d3D SA-1110 Development Board */ +#define I2C_HW_B_OMAHA 0x010014 /* Omaha I2C interface (ARM) */ +#define I2C_HW_B_GUIDE 0x010015 /* Guide bit-basher */ +#define I2C_HW_B_IXP2000 0x010016 /* GPIO on IXP2000 systems */ +#define I2C_HW_B_IXP4XX 0x010017 /* GPIO on IXP4XX systems */ +#define I2C_HW_B_S3VIA 0x010018 /* S3Via ProSavage adapter */ +#define I2C_HW_B_ZR36067 0x010019 /* Zoran-36057/36067 based boards */ +#define I2C_HW_B_PCILYNX 0x01001a /* TI PCILynx I2C adapter */ +#define I2C_HW_B_CX2388x 0x01001b /* connexant 2388x based tv cards */ /* --- PCF 8584 based algorithms */ -#define I2C_HW_P_LP 0x00 /* Parallel port interface */ -#define I2C_HW_P_ISA 0x01 /* generic ISA Bus inteface card */ -#define I2C_HW_P_ELEK 0x02 /* Elektor ISA Bus inteface card */ +#define I2C_HW_P_LP 0x020000 /* Parallel port interface */ +#define I2C_HW_P_ISA 0x020001 /* generic ISA Bus inteface card */ +#define I2C_HW_P_ELEK 0x020002 /* Elektor ISA Bus inteface card */ /* --- PCA 9564 based algorithms */ -#define I2C_HW_A_ISA 0x00 /* generic ISA Bus interface card */ +#define I2C_HW_A_ISA 0x1a0000 /* generic ISA Bus interface card */ /* --- ACPI Embedded controller algorithms */ -#define I2C_HW_ACPI_EC 0x00 +#define I2C_HW_ACPI_EC 0x1f0000 /* --- MPC824x PowerPC adapters */ -#define I2C_HW_MPC824X 0x00 /* Motorola 8240 / 8245 */ +#define I2C_HW_MPC824X 0x100001 /* Motorola 8240 / 8245 */ /* --- MPC8xx PowerPC adapters */ -#define I2C_HW_MPC8XX_EPON 0x00 /* Eponymous MPC8xx I2C adapter */ +#define I2C_HW_MPC8XX_EPON 0x110000 /* Eponymous MPC8xx I2C adapter */ /* --- ITE based algorithms */ -#define I2C_HW_I_IIC 0x00 /* controller on the ITE */ +#define I2C_HW_I_IIC 0x080000 /* controller on the ITE */ /* --- PowerPC on-chip adapters */ -#define I2C_HW_OCP 0x00 /* IBM on-chip I2C adapter */ +#define I2C_HW_OCP 0x120000 /* IBM on-chip I2C adapter */ /* --- Broadcom SiByte adapters */ -#define I2C_HW_SIBYTE 0x00 +#define I2C_HW_SIBYTE 0x150000 /* --- SGI adapters */ -#define I2C_HW_SGI_VINO 0x00 -#define I2C_HW_SGI_MACE 0x01 +#define I2C_HW_SGI_VINO 0x160000 +#define I2C_HW_SGI_MACE 0x160001 /* --- XSCALE on-chip adapters */ -#define I2C_HW_IOP3XX 0x00 +#define I2C_HW_IOP3XX 0x140000 /* --- Au1550 PSC adapters adapters */ -#define I2C_HW_AU1550_PSC 0x00 +#define I2C_HW_AU1550_PSC 0x1b0000 /* --- SMBus only adapters */ -#define I2C_HW_SMBUS_PIIX4 0x00 -#define I2C_HW_SMBUS_ALI15X3 0x01 -#define I2C_HW_SMBUS_VIA2 0x02 -#define I2C_HW_SMBUS_VOODOO3 0x03 -#define I2C_HW_SMBUS_I801 0x04 -#define I2C_HW_SMBUS_AMD756 0x05 -#define I2C_HW_SMBUS_SIS5595 0x06 -#define I2C_HW_SMBUS_ALI1535 0x07 -#define I2C_HW_SMBUS_SIS630 0x08 -#define I2C_HW_SMBUS_SIS96X 0x09 -#define I2C_HW_SMBUS_AMD8111 0x0a -#define I2C_HW_SMBUS_SCX200 0x0b -#define I2C_HW_SMBUS_NFORCE2 0x0c -#define I2C_HW_SMBUS_W9968CF 0x0d -#define I2C_HW_SMBUS_OV511 0x0e /* OV511(+) USB 1.1 webcam ICs */ -#define I2C_HW_SMBUS_OV518 0x0f /* OV518(+) USB 1.1 webcam ICs */ -#define I2C_HW_SMBUS_OV519 0x10 /* OV519 USB 1.1 webcam IC */ -#define I2C_HW_SMBUS_OVFX2 0x11 /* Cypress/OmniVision FX2 webcam */ +#define I2C_HW_SMBUS_PIIX4 0x040000 +#define I2C_HW_SMBUS_ALI15X3 0x040001 +#define I2C_HW_SMBUS_VIA2 0x040002 +#define I2C_HW_SMBUS_VOODOO3 0x040003 +#define I2C_HW_SMBUS_I801 0x040004 +#define I2C_HW_SMBUS_AMD756 0x040005 +#define I2C_HW_SMBUS_SIS5595 0x040006 +#define I2C_HW_SMBUS_ALI1535 0x040007 +#define I2C_HW_SMBUS_SIS630 0x040008 +#define I2C_HW_SMBUS_SIS96X 0x040009 +#define I2C_HW_SMBUS_AMD8111 0x04000a +#define I2C_HW_SMBUS_SCX200 0x04000b +#define I2C_HW_SMBUS_NFORCE2 0x04000c +#define I2C_HW_SMBUS_W9968CF 0x04000d +#define I2C_HW_SMBUS_OV511 0x04000e /* OV511(+) USB 1.1 webcam ICs */ +#define I2C_HW_SMBUS_OV518 0x04000f /* OV518(+) USB 1.1 webcam ICs */ +#define I2C_HW_SMBUS_OV519 0x040010 /* OV519 USB 1.1 webcam IC */ +#define I2C_HW_SMBUS_OVFX2 0x040011 /* Cypress/OmniVision FX2 webcam */ /* --- ISA pseudo-adapter */ -#define I2C_HW_ISA 0x00 +#define I2C_HW_ISA 0x050000 /* --- IPMI pseudo-adapter */ -#define I2C_HW_IPMI 0x00 +#define I2C_HW_IPMI 0x0b0000 /* --- IPMB adapter */ -#define I2C_HW_IPMB 0x00 +#define I2C_HW_IPMB 0x0c0000 /* --- MCP107 adapter */ -#define I2C_HW_MPC107 0x00 +#define I2C_HW_MPC107 0x0d0000 /* --- Marvell mv64xxx i2c adapter */ -#define I2C_HW_MV64XXX 0x00 +#define I2C_HW_MV64XXX 0x190000 #endif /* LINUX_I2C_ID_H */ diff --git a/include/linux/i2c-isa.h b/include/linux/i2c-isa.h index 54c27e88d101..67e3598c4cec 100644 --- a/include/linux/i2c-isa.h +++ b/include/linux/i2c-isa.h @@ -29,7 +29,7 @@ extern int i2c_isa_del_driver(struct i2c_driver *driver); /* Detect whether we are on the isa bus. This is only useful to hybrid (i2c+isa) drivers. */ #define i2c_is_isa_adapter(adapptr) \ - ((adapptr)->id == (I2C_ALGO_ISA | I2C_HW_ISA)) + ((adapptr)->id == I2C_HW_ISA) #define i2c_is_isa_client(clientptr) \ i2c_is_isa_adapter((clientptr)->adapter) -- cgit v1.2.3 From 1684a984303abbfc39aa8b59b0fe825c717811a9 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 11 Aug 2005 23:51:10 +0200 Subject: [PATCH] I2C: Kill i2c_algorithm.id (6/7) In theory, there should be no more users of I2C_ALGO_* at this point. However, it happens that several drivers were using I2C_ALGO_* for adapter ids, so we need to correct these before we can get rid of all the I2C_ALGO_* definitions. Note that this also fixes a bug in media/video/tvaudio.c: /* don't attach on saa7146 based cards, because dedicated drivers are used */ if ((adap->id & I2C_ALGO_SAA7146)) return 0; This test was plain broken, as it would succeed for many more adapters than just the saa7146: any those id would share at least one bit with the saa7146 id. We are really lucky that the few other adapters we want this driver to work with did not fulfill that condition. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-id.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 5b72f664cc21..d044e738d383 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -245,6 +245,9 @@ #define I2C_HW_B_ZR36067 0x010019 /* Zoran-36057/36067 based boards */ #define I2C_HW_B_PCILYNX 0x01001a /* TI PCILynx I2C adapter */ #define I2C_HW_B_CX2388x 0x01001b /* connexant 2388x based tv cards */ +#define I2C_HW_B_NVIDIA 0x01001c /* nvidia framebuffer driver */ +#define I2C_HW_B_SAVAGE 0x01001d /* savage framebuffer driver */ +#define I2C_HW_B_RADEON 0x01001e /* radeon framebuffer driver */ /* --- PCF 8584 based algorithms */ #define I2C_HW_P_LP 0x020000 /* Parallel port interface */ @@ -317,4 +320,8 @@ /* --- Marvell mv64xxx i2c adapter */ #define I2C_HW_MV64XXX 0x190000 +/* --- Miscellaneous adapters */ +#define I2C_HW_SAA7146 0x060000 /* SAA7146 video decoder bus */ +#define I2C_HW_SAA7134 0x090000 /* SAA7134 video decoder bus */ + #endif /* LINUX_I2C_ID_H */ -- cgit v1.2.3 From c2459cf257106cea5adbc83f084b76d0030eb700 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 11 Aug 2005 23:52:35 +0200 Subject: [PATCH] I2C: Kill i2c_algorithm.id (7/7) The I2C_ALGO_* constants have no more users, delete them. Also update the comments in i2c-id.h so that they reflect the current state of the file. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-id.h | 57 +------------------------------------------------- 1 file changed, 1 insertion(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index d044e738d383..44f30876a1c9 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -1,6 +1,6 @@ /* ------------------------------------------------------------------------- */ /* */ -/* i2c.h - definitions for the i2c-bus interface */ +/* i2c-id.h - identifier values for i2c drivers and adapters */ /* */ /* ------------------------------------------------------------------------- */ /* Copyright (C) 1995-1999 Simon G. Vogl @@ -23,16 +23,6 @@ #ifndef LINUX_I2C_ID_H #define LINUX_I2C_ID_H -/* - * This file is part of the i2c-bus package and contains the identifier - * values for drivers, adapters and other folk populating these serial - * worlds. - * - * These will change often (i.e. additions) , therefore this has been - * separated from the functional interface definitions of the i2c api. - * - */ - /* * ---- Driver types ----------------------------------------------------- * device id name + number function description, i2c address(es) @@ -170,51 +160,6 @@ /* * ---- Adapter types ---------------------------------------------------- - * - * First, we distinguish between several algorithms to access the hardware - * interface types, as a PCF 8584 needs other care than a bit adapter. - */ - -#define I2C_ALGO_NONE 0x000000 -#define I2C_ALGO_BIT 0x010000 /* bit style adapters */ -#define I2C_ALGO_PCF 0x020000 /* PCF 8584 style adapters */ -#define I2C_ALGO_ATI 0x030000 /* ATI video card */ -#define I2C_ALGO_SMBUS 0x040000 -#define I2C_ALGO_ISA 0x050000 /* lm_sensors ISA pseudo-adapter */ -#define I2C_ALGO_SAA7146 0x060000 /* SAA 7146 video decoder bus */ -#define I2C_ALGO_ACB 0x070000 /* ACCESS.bus algorithm */ -#define I2C_ALGO_IIC 0x080000 /* ITE IIC bus */ -#define I2C_ALGO_SAA7134 0x090000 -#define I2C_ALGO_MPC824X 0x0a0000 /* Motorola 8240 / 8245 */ -#define I2C_ALGO_IPMI 0x0b0000 /* IPMI dummy adapter */ -#define I2C_ALGO_IPMB 0x0c0000 /* IPMB adapter */ -#define I2C_ALGO_MPC107 0x0d0000 -#define I2C_ALGO_EC 0x100000 /* ACPI embedded controller */ - -#define I2C_ALGO_MPC8XX 0x110000 /* MPC8xx PowerPC I2C algorithm */ -#define I2C_ALGO_OCP 0x120000 /* IBM or otherwise On-chip I2C algorithm */ -#define I2C_ALGO_BITHS 0x130000 /* enhanced bit style adapters */ -#define I2C_ALGO_IOP3XX 0x140000 /* XSCALE IOP3XX On-chip I2C alg */ -#define I2C_ALGO_SIBYTE 0x150000 /* Broadcom SiByte SOCs */ -#define I2C_ALGO_SGI 0x160000 /* SGI algorithm */ - -#define I2C_ALGO_USB 0x170000 /* USB algorithm */ -#define I2C_ALGO_VIRT 0x180000 /* Virtual bus adapter */ - -#define I2C_ALGO_MV64XXX 0x190000 /* Marvell mv64xxx i2c ctlr */ -#define I2C_ALGO_PCA 0x1a0000 /* PCA 9564 style adapters */ -#define I2C_ALGO_AU1550 0x1b0000 /* Au1550 PSC algorithm */ - -#define I2C_ALGO_EXP 0x800000 /* experimental */ - -#define I2C_ALGO_MASK 0xff0000 /* Mask for algorithms */ -#define I2C_ALGO_SHIFT 0x10 /* right shift to get index values */ - -#define I2C_HW_ADAPS 0x10000 /* # adapter types */ -#define I2C_HW_MASK 0xffff - - -/* hw specific modules that are defined per algorithm layer */ /* --- Bit algorithm adapters */ -- cgit v1.2.3 From 020789e9cb688ac8b15a9950d25fe45492b23398 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sat, 13 Aug 2005 13:04:32 +0200 Subject: [PATCH] I2C: Outdated i2c_adapter comment Delete an outdated comment about i2c_algorithm.id being computed from algo->id. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index af4983b488b6..233c153b12b1 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -219,8 +219,7 @@ struct i2c_algorithm { */ struct i2c_adapter { struct module *owner; - unsigned int id;/* == is algo->id | hwdep.struct->id, */ - /* for registered values see below */ + unsigned int id; unsigned int class; struct i2c_algorithm *algo;/* the algorithm to access the bus */ void *algo_data; -- cgit v1.2.3 From fae91e72b79ba9a21f0ce7551a1fd7e8984c85a6 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 15 Aug 2005 19:57:04 +0200 Subject: [PATCH] I2C: Drop I2C_DEVNAME and i2c_clientname I2C_DEVNAME and i2c_clientname were introduced in 2.5.68 [1] to help media/video driver authors who wanted their code to be compatible with both Linux 2.4 and 2.6. The cause of the incompatibility has gone since [2], so I think we can get rid of them, as they tend to make the code harder to read and longer to preprocess/compile for no more benefit. I'd hope nobody seriously attempts to keep media/video driver compatible across Linux trees anymore, BTW. [1] http://marc.theaimsgroup.com/?l=linux-kernel&m=104930186524598&w=2 [2] http://www.linuxhq.com/kernel/v2.6/0-test3/include/linux/i2c.h Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 233c153b12b1..1ead5195fde4 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -178,13 +178,6 @@ static inline void i2c_set_clientdata (struct i2c_client *dev, void *data) dev_set_drvdata (&dev->dev, data); } -#define I2C_DEVNAME(str) .name = str - -static inline char *i2c_clientname(struct i2c_client *c) -{ - return &c->name[0]; -} - /* * The following structs are for those who like to implement new bus drivers: * i2c_algorithm is the interface to a class of hardware solutions which can -- cgit v1.2.3 From 77ae84554cc0178e03862391599a0cedf96fa4c4 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sat, 3 Sep 2005 10:52:11 +0200 Subject: [PATCH] I2C: Drop the I2C_ACK_TEST ioctl Drop the I2C_ACK_TEST ioctl, which was commented out. It never really existed (not after 1999 anyway), and there is no such thing as a ack test on I2C/SMBus anyway. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 1ead5195fde4..be35332b67e6 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -508,9 +508,6 @@ union i2c_smbus_data { #define I2C_FUNCS 0x0705 /* Get the adapter functionality */ #define I2C_RDWR 0x0707 /* Combined R/W transfer (one stop only)*/ #define I2C_PEC 0x0708 /* != 0 for SMBus PEC */ -#if 0 -#define I2C_ACK_TEST 0x0710 /* See if a slave is at a specific address */ -#endif #define I2C_SMBUS 0x0720 /* SMBus-level access */ -- cgit v1.2.3 From d856f1e337782326c638c70c0b4df2b909350dec Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Fri, 19 Aug 2005 09:14:01 -0400 Subject: [PATCH] klist: fix klist to have the same klist_add semantics as list_head at the moment, the list_head semantics are list_add(node, head) whereas current klist semantics are klist_add(head, node) This is bound to cause confusion, and since klist is the newcomer, it should follow the list_head semantics. I also added missing include guards to klist.h Signed-off-by: James Bottomley Signed-off-by: Greg Kroah-Hartman --- include/linux/klist.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/klist.h b/include/linux/klist.h index eebf5e5696ec..c4d1fae4dd89 100644 --- a/include/linux/klist.h +++ b/include/linux/klist.h @@ -9,6 +9,9 @@ * This file is rleased under the GPL v2. */ +#ifndef _LINUX_KLIST_H +#define _LINUX_KLIST_H + #include #include #include @@ -31,8 +34,8 @@ struct klist_node { struct completion n_removed; }; -extern void klist_add_tail(struct klist * k, struct klist_node * n); -extern void klist_add_head(struct klist * k, struct klist_node * n); +extern void klist_add_tail(struct klist_node * n, struct klist * k); +extern void klist_add_head(struct klist_node * n, struct klist * k); extern void klist_del(struct klist_node * n); extern void klist_remove(struct klist_node * n); @@ -53,3 +56,4 @@ extern void klist_iter_init_node(struct klist * k, struct klist_iter * i, extern void klist_iter_exit(struct klist_iter * i); extern struct klist_node * klist_next(struct klist_iter * i); +#endif -- cgit v1.2.3 From 93c37f292110a37dd77e4cc0aaf1c341d79bf6aa Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 6 Sep 2005 13:57:08 -0700 Subject: [SERIAL]: Avoid 'statement with no effect' warnings. When SUPPORT_SYSRQ is false, gcc can emit warnings for the uart_handle_sysrq_char() that results. Using an empty inline returning zero kills the warning. Signed-off-by: David S. Miller --- include/linux/serial_core.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index cf0f64ea2bc0..9b12fe731612 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -385,11 +385,11 @@ int uart_resume_port(struct uart_driver *reg, struct uart_port *port); /* * The following are helper functions for the low level drivers. */ -#ifdef SUPPORT_SYSRQ static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch, struct pt_regs *regs) { +#ifdef SUPPORT_SYSRQ if (port->sysrq) { if (ch && time_before(jiffies, port->sysrq)) { handle_sysrq(ch, regs, NULL); @@ -398,11 +398,9 @@ uart_handle_sysrq_char(struct uart_port *port, unsigned int ch, } port->sysrq = 0; } +#endif return 0; } -#else -#define uart_handle_sysrq_char(port,ch,regs) (0) -#endif /* * We do the SysRQ and SAK checking like this... -- cgit v1.2.3 From 2248bcfcd8fb622ec88b8587d0c1f139635ffd2e Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 6 Sep 2005 15:06:42 -0700 Subject: [NETFILTER]: Add support for permanent expectations A permanent expectation exists until timeing out and can expect multiple related connections. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index 088742befe49..7e033e9271a8 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -263,6 +263,9 @@ struct ip_conntrack_expect /* Unique ID */ unsigned int id; + /* Flags */ + unsigned int flags; + #ifdef CONFIG_IP_NF_NAT_NEEDED /* This is the original per-proto part, used to map the * expected connection the way the recipient expects. */ @@ -272,6 +275,8 @@ struct ip_conntrack_expect #endif }; +#define IP_CT_EXPECT_PERMANENT 0x1 + static inline struct ip_conntrack * tuplehash_to_ctrack(const struct ip_conntrack_tuple_hash *hash) { -- cgit v1.2.3 From 03486a4f838c55481317fca5ac2e7d12550a4fb7 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 6 Sep 2005 15:09:43 -0700 Subject: [NETFILTER]: Handle NAT module load race When the NAT module is loaded when connections are already confirmed it must not change their tuples anymore. This is especially important with CONFIG_NETFILTER_DEBUG, the netfilter listhelp functions will refuse to remove an entry from a list when it can not be found on the list, so when a changed tuple hashes to a new bucket the entry is kept in the list until and after the conntrack is freed. Allocate the exact conntrack tuple for NAT for already confirmed connections or drop them if that fails. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_nat_rule.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_nat_rule.h b/include/linux/netfilter_ipv4/ip_nat_rule.h index fecd2a06dcd8..73b9552e6a89 100644 --- a/include/linux/netfilter_ipv4/ip_nat_rule.h +++ b/include/linux/netfilter_ipv4/ip_nat_rule.h @@ -19,5 +19,10 @@ extern unsigned int alloc_null_binding(struct ip_conntrack *conntrack, struct ip_nat_info *info, unsigned int hooknum); + +extern unsigned int +alloc_null_binding_confirmed(struct ip_conntrack *conntrack, + struct ip_nat_info *info, + unsigned int hooknum); #endif #endif /* _IP_NAT_RULE_H */ -- cgit v1.2.3 From 49719eb355d32fa07793017b4b46b1c02e88b275 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 6 Sep 2005 15:10:46 -0700 Subject: [NETFILTER]: kill __ip_ct_expect_unlink_destroy The following patch kills __ip_ct_expect_unlink_destroy and export unlink_expect as ip_ct_unlink_expect. As it was discussed [1], the function __ip_ct_expect_unlink_destroy is a bit confusing so better do the following sequence: ip_ct_destroy_expect and ip_conntrack_expect_put. [1] https://lists.netfilter.org/pipermail/netfilter-devel/2005-August/020794.html Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack_core.h b/include/linux/netfilter_ipv4/ip_conntrack_core.h index dc4d2a0575de..907d4f5ca5dc 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_core.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_core.h @@ -52,7 +52,7 @@ static inline int ip_conntrack_confirm(struct sk_buff **pskb) return ret; } -extern void __ip_ct_expect_unlink_destroy(struct ip_conntrack_expect *exp); +extern void ip_ct_unlink_expect(struct ip_conntrack_expect *exp); extern struct list_head *ip_conntrack_hash; extern struct list_head ip_conntrack_expect_list; -- cgit v1.2.3 From f2c383988d68c91a7d474b7cf26c0a2df49bbafe Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 6 Sep 2005 15:48:03 -0700 Subject: [NET]: skb_get/set_timestamp use const The new timestamp get/set routines should have const attribute on parameters (helps to indicate direction). Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 42edce6abe23..da7da9c0ed1b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1251,7 +1251,7 @@ extern void skb_add_mtu(int mtu); * This function converts the offset back to a struct timeval and stores * it in stamp. */ -static inline void skb_get_timestamp(struct sk_buff *skb, struct timeval *stamp) +static inline void skb_get_timestamp(const struct sk_buff *skb, struct timeval *stamp) { stamp->tv_sec = skb->tstamp.off_sec; stamp->tv_usec = skb->tstamp.off_usec; @@ -1270,7 +1270,7 @@ static inline void skb_get_timestamp(struct sk_buff *skb, struct timeval *stamp) * This function converts a struct timeval to an offset and stores * it in the skb. */ -static inline void skb_set_timestamp(struct sk_buff *skb, struct timeval *stamp) +static inline void skb_set_timestamp(struct sk_buff *skb, const struct timeval *stamp) { skb->tstamp.off_sec = stamp->tv_sec - skb_tv_base.tv_sec; skb->tstamp.off_usec = stamp->tv_usec - skb_tv_base.tv_usec; -- cgit v1.2.3 From aaec0fab5f8809fe1509fdc204e769bb35ebe41a Mon Sep 17 00:00:00 2001 From: Jens Osterkamp Date: Mon, 5 Sep 2005 15:19:29 -0700 Subject: [PATCH] net: add driver for the NIC on Cell Blades This patch adds a driver for a new 1000 Mbit ethernet NIC. It is integrated on the south bridge that is used for our Cell Blades. The code gets the MAC address from the Open Firmware device tree, so it won't compile on platforms other than ppc64. This is the first public release, so I don't expect the first version to get merged, but I'd aim for integration within the 2.6.13 time frame. Cc: Utz Bacher Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Jeff Garzik --- 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 95c941f8c747..ee0ab7a5f91b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1612,6 +1612,7 @@ #define PCI_DEVICE_ID_TOSHIBA_TC35815CF 0x0030 #define PCI_DEVICE_ID_TOSHIBA_TX4927 0x0180 #define PCI_DEVICE_ID_TOSHIBA_TC86C001_MISC 0x0108 +#define PCI_DEVICE_ID_TOSHIBA_SPIDER_NET 0x01b3 #define PCI_VENDOR_ID_RICOH 0x1180 #define PCI_DEVICE_ID_RICOH_RL5C465 0x0465 -- cgit v1.2.3 From 6582c164f2b3b6e58d1f13c1c031b19ee691eb14 Mon Sep 17 00:00:00 2001 From: Jean Tourrilhes Date: Fri, 2 Sep 2005 11:32:28 -0700 Subject: [PATCH] WE-19 for kernel 2.6.13 Hi Jeff, This is version 19 of the Wireless Extensions. It was supposed to be the fallback of the WPA API changes, but people seem quite happy about it (especially Jouni), so the patch is rather small. The patch has been fully tested with 2.6.13 and various wireless drivers, and is in its final version. Would you mind pushing that into Linus's kernel so that the driver and the apps can take advantage ot it ? It includes : o iwstat improvement (explicit dBm). This is the result of long discussions with Dan Williams, the authors of NetworkManager. Thanks to him for all the fruitful feedback. o remove pointer from event stream. I was not totally sure if this pointer was 32-64 bits clean, so I'd rather remove it and be at peace with it. o remove linux header from wireless.h. This has long been requested by people writting user space apps, now it's done, and it was not even painful. o final deprecation of spy_offset. You did not like it, it's now gone for good. o Start deprecating dev->get_wireless_stats -> debloat netdev o Add "check" version of event macros for ieee802.11 stack. Jiri Benc doesn't like the current macros, we aim to please ;-) All those changes, except the last one, have been bit-roting on my web pages for a while... Patches for most kernel drivers will follow. Patches for the Orinoco and the HostAP drivers have been sent to their respective maintainers. Have fun... Jean Signed-off-by: Jeff Garzik --- include/linux/wireless.h | 47 +++++++++++++++++++++++++++++++++-------------- 1 file changed, 33 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wireless.h b/include/linux/wireless.h index ae485f9c916e..dab5afdaf71c 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -1,7 +1,7 @@ /* * This file define a set of standard wireless extensions * - * Version : 18 12.3.05 + * Version : 19 18.3.05 * * Authors : Jean Tourrilhes - HPL - * Copyright (c) 1997-2005 Jean Tourrilhes, All Rights Reserved. @@ -69,11 +69,12 @@ /***************************** INCLUDES *****************************/ -/* To minimise problems in user space, I might remove those headers - * at some point. Jean II */ -#include /* for "caddr_t" et al */ -#include /* for "struct sockaddr" et al */ -#include /* for IFNAMSIZ and co... */ +/* Do not put any header in this file, this creates a mess when + * exported to user space. Most users have included all the + * relevant headers anyway... Jean II */ +/*#include */ /* for "caddr_t" et al */ +/*#include */ /* for "struct sockaddr" et al */ +/*#include */ /* for IFNAMSIZ and co... */ /***************************** VERSION *****************************/ /* @@ -82,7 +83,7 @@ * (there is some stuff that will be added in the future...) * I just plan to increment with each new version. */ -#define WIRELESS_EXT 18 +#define WIRELESS_EXT 19 /* * Changes : @@ -197,6 +198,15 @@ * related parameters (extensible up to 4096 parameter values) * - Add wireless events: IWEVGENIE, IWEVMICHAELMICFAILURE, * IWEVASSOCREQIE, IWEVASSOCRESPIE, IWEVPMKIDCAND + * + * V18 to V19 + * ---------- + * - Remove (struct iw_point *)->pointer from events and streams + * - Remove header includes to help user space + * - Increase IW_ENCODING_TOKEN_MAX from 32 to 64 + * - Add IW_QUAL_ALL_UPDATED and IW_QUAL_ALL_INVALID macros + * - Add explicit flag to tell stats are in dBm : IW_QUAL_DBM + * - Add IW_IOCTL_IDX() and IW_EVENT_IDX() macros */ /**************************** CONSTANTS ****************************/ @@ -322,6 +332,7 @@ /* The first and the last (range) */ #define SIOCIWFIRST 0x8B00 #define SIOCIWLAST SIOCIWLASTPRIV /* 0x8BFF */ +#define IW_IOCTL_IDX(cmd) ((cmd) - SIOCIWFIRST) /* Even : get (world access), odd : set (root access) */ #define IW_IS_SET(cmd) (!((cmd) & 0x1)) @@ -366,6 +377,7 @@ * (struct iw_pmkid_cand) */ #define IWEVFIRST 0x8C00 +#define IW_EVENT_IDX(cmd) ((cmd) - IWEVFIRST) /* ------------------------- PRIVATE INFO ------------------------- */ /* @@ -427,12 +439,15 @@ #define IW_MODE_MONITOR 6 /* Passive monitor (listen only) */ /* Statistics flags (bitmask in updated) */ -#define IW_QUAL_QUAL_UPDATED 0x1 /* Value was updated since last read */ -#define IW_QUAL_LEVEL_UPDATED 0x2 -#define IW_QUAL_NOISE_UPDATED 0x4 +#define IW_QUAL_QUAL_UPDATED 0x01 /* Value was updated since last read */ +#define IW_QUAL_LEVEL_UPDATED 0x02 +#define IW_QUAL_NOISE_UPDATED 0x04 +#define IW_QUAL_ALL_UPDATED 0x07 +#define IW_QUAL_DBM 0x08 /* Level + Noise are dBm */ #define IW_QUAL_QUAL_INVALID 0x10 /* Driver doesn't provide value */ #define IW_QUAL_LEVEL_INVALID 0x20 #define IW_QUAL_NOISE_INVALID 0x40 +#define IW_QUAL_ALL_INVALID 0x70 /* Frequency flags */ #define IW_FREQ_AUTO 0x00 /* Let the driver decides */ @@ -443,7 +458,7 @@ #define IW_MAX_ENCODING_SIZES 8 /* Maximum size of the encoding token in bytes */ -#define IW_ENCODING_TOKEN_MAX 32 /* 256 bits (for now) */ +#define IW_ENCODING_TOKEN_MAX 64 /* 512 bits (for now) */ /* Flags for encoding (along with the token) */ #define IW_ENCODE_INDEX 0x00FF /* Token index (if needed) */ @@ -1039,12 +1054,16 @@ struct iw_event #define IW_EV_CHAR_LEN (IW_EV_LCP_LEN + IFNAMSIZ) #define IW_EV_UINT_LEN (IW_EV_LCP_LEN + sizeof(__u32)) #define IW_EV_FREQ_LEN (IW_EV_LCP_LEN + sizeof(struct iw_freq)) -#define IW_EV_POINT_LEN (IW_EV_LCP_LEN + sizeof(struct iw_point)) #define IW_EV_PARAM_LEN (IW_EV_LCP_LEN + sizeof(struct iw_param)) #define IW_EV_ADDR_LEN (IW_EV_LCP_LEN + sizeof(struct sockaddr)) #define IW_EV_QUAL_LEN (IW_EV_LCP_LEN + sizeof(struct iw_quality)) -/* Note : in the case of iw_point, the extra data will come at the - * end of the event */ +/* iw_point events are special. First, the payload (extra data) come at + * the end of the event, so they are bigger than IW_EV_POINT_LEN. Second, + * we omit the pointer, so start at an offset. */ +#define IW_EV_POINT_OFF (((char *) &(((struct iw_point *) NULL)->length)) - \ + (char *) NULL) +#define IW_EV_POINT_LEN (IW_EV_LCP_LEN + sizeof(struct iw_point) - \ + IW_EV_POINT_OFF) #endif /* _LINUX_WIRELESS_H */ -- cgit v1.2.3 From bbeec90b98a3066f6f2b8d41c80561f5665e4631 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Wed, 7 Sep 2005 00:27:54 -0400 Subject: [wireless] build fixes after merging WE-19 --- include/linux/wireless.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wireless.h b/include/linux/wireless.h index dab5afdaf71c..a555a0f7a7b4 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -69,12 +69,9 @@ /***************************** INCLUDES *****************************/ -/* Do not put any header in this file, this creates a mess when - * exported to user space. Most users have included all the - * relevant headers anyway... Jean II */ -/*#include */ /* for "caddr_t" et al */ -/*#include */ /* for "struct sockaddr" et al */ -/*#include */ /* for IFNAMSIZ and co... */ +#include /* for "caddr_t" et al */ +#include /* for "struct sockaddr" et al */ +#include /* for IFNAMSIZ and co... */ /***************************** VERSION *****************************/ /* -- cgit v1.2.3 From 54d5d42404e7705cf3804593189e963350d470e5 Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Tue, 6 Sep 2005 15:16:15 -0700 Subject: [PATCH] x86/x86_64: deferred handling of writes to /proc/irqxx/smp_affinity When handling writes to /proc/irq, current code is re-programming rte entries directly. This is not recommended and could potentially cause chipset's to lockup, or cause missing interrupts. CONFIG_IRQ_BALANCE does this correctly, where it re-programs only when the interrupt is pending. The same needs to be done for /proc/irq handling as well. Otherwise user space irq balancers are really not doing the right thing. - Changed pending_irq_balance_cpumask to pending_irq_migrate_cpumask for lack of a generic name. - added move_irq out of IRQ_BALANCE, and added this same to X86_64 - Added new proc handler for write, so we can do deferred write at irq handling time. - Display of /proc/irq/XX/smp_affinity used to display CPU_MASKALL, instead it now shows only active cpu masks, or exactly what was set. - Provided a common move_irq implementation, instead of duplicating when using generic irq framework. Tested on i386/x86_64 and ia64 with CONFIG_PCI_MSI turned on and off. Tested UP builds as well. MSI testing: tbd: I have cards, need to look for a x-over cable, although I did test an earlier version of this patch. Will test in a couple days. Signed-off-by: Ashok Raj Acked-by: Zwane Mwaikambo Grudgingly-acked-by: Andi Kleen Signed-off-by: Coywolf Qi Hunt Signed-off-by: Ashok Raj Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irq.h | 123 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 123 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 069d3b84d311..4a362b9ec966 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -71,16 +71,139 @@ typedef struct irq_desc { unsigned int irq_count; /* For detecting broken interrupts */ unsigned int irqs_unhandled; spinlock_t lock; +#if defined (CONFIG_GENERIC_PENDING_IRQ) || defined (CONFIG_IRQBALANCE) + unsigned int move_irq; /* Flag need to re-target intr dest*/ +#endif } ____cacheline_aligned irq_desc_t; extern irq_desc_t irq_desc [NR_IRQS]; +/* Return a pointer to the irq descriptor for IRQ. */ +static inline irq_desc_t * +irq_descp (int irq) +{ + return irq_desc + irq; +} + #include /* the arch dependent stuff */ extern int setup_irq(unsigned int irq, struct irqaction * new); #ifdef CONFIG_GENERIC_HARDIRQS extern cpumask_t irq_affinity[NR_IRQS]; + +#ifdef CONFIG_SMP +static inline void set_native_irq_info(int irq, cpumask_t mask) +{ + irq_affinity[irq] = mask; +} +#else +static inline void set_native_irq_info(int irq, cpumask_t mask) +{ +} +#endif + +#ifdef CONFIG_SMP + +#if defined (CONFIG_GENERIC_PENDING_IRQ) || defined (CONFIG_IRQBALANCE) +extern cpumask_t pending_irq_cpumask[NR_IRQS]; + +static inline void set_pending_irq(unsigned int irq, cpumask_t mask) +{ + irq_desc_t *desc = irq_desc + irq; + unsigned long flags; + + spin_lock_irqsave(&desc->lock, flags); + desc->move_irq = 1; + pending_irq_cpumask[irq] = mask; + spin_unlock_irqrestore(&desc->lock, flags); +} + +static inline void +move_native_irq(int irq) +{ + cpumask_t tmp; + irq_desc_t *desc = irq_descp(irq); + + if (likely (!desc->move_irq)) + return; + + desc->move_irq = 0; + + if (likely(cpus_empty(pending_irq_cpumask[irq]))) + return; + + if (!desc->handler->set_affinity) + return; + + /* note - we hold the desc->lock */ + cpus_and(tmp, pending_irq_cpumask[irq], cpu_online_map); + + /* + * If there was a valid mask to work with, please + * do the disable, re-program, enable sequence. + * This is *not* particularly important for level triggered + * but in a edge trigger case, we might be setting rte + * when an active trigger is comming in. This could + * cause some ioapics to mal-function. + * Being paranoid i guess! + */ + if (unlikely(!cpus_empty(tmp))) { + desc->handler->disable(irq); + desc->handler->set_affinity(irq,tmp); + desc->handler->enable(irq); + } + cpus_clear(pending_irq_cpumask[irq]); +} + +#ifdef CONFIG_PCI_MSI +/* + * Wonder why these are dummies? + * For e.g the set_ioapic_affinity_vector() calls the set_ioapic_affinity_irq() + * counter part after translating the vector to irq info. We need to perform + * this operation on the real irq, when we dont use vector, i.e when + * pci_use_vector() is false. + */ +static inline void move_irq(int irq) +{ +} + +static inline void set_irq_info(int irq, cpumask_t mask) +{ +} + +#else // CONFIG_PCI_MSI + +static inline void move_irq(int irq) +{ + move_native_irq(irq); +} + +static inline void set_irq_info(int irq, cpumask_t mask) +{ + set_native_irq_info(irq, mask); +} +#endif // CONFIG_PCI_MSI + +#else // CONFIG_GENERIC_PENDING_IRQ || CONFIG_IRQBALANCE + +#define move_irq(x) +#define move_native_irq(x) +#define set_pending_irq(x,y) +static inline void set_irq_info(int irq, cpumask_t mask) +{ + set_native_irq_info(irq, mask); +} + +#endif // CONFIG_GENERIC_PENDING_IRQ + +#else // CONFIG_SMP + +#define move_irq(x) +#define move_native_irq(x) + +#endif // CONFIG_SMP + extern int no_irq_affinity; extern int noirqdebug_setup(char *str); -- cgit v1.2.3 From 4732efbeb997189d9f9b04708dc26bf8613ed721 Mon Sep 17 00:00:00 2001 From: Jakub Jelinek Date: Tue, 6 Sep 2005 15:16:25 -0700 Subject: [PATCH] FUTEX_WAKE_OP: pthread_cond_signal() speedup ATM pthread_cond_signal is unnecessarily slow, because it wakes one waiter (which at least on UP usually means an immediate context switch to one of the waiter threads). This waiter wakes up and after a few instructions it attempts to acquire the cv internal lock, but that lock is still held by the thread calling pthread_cond_signal. So it goes to sleep and eventually the signalling thread is scheduled in, unlocks the internal lock and wakes the waiter again. Now, before 2003-09-21 NPTL was using FUTEX_REQUEUE in pthread_cond_signal to avoid this performance issue, but it was removed when locks were redesigned to the 3 state scheme (unlocked, locked uncontended, locked contended). Following scenario shows why simply using FUTEX_REQUEUE in pthread_cond_signal together with using lll_mutex_unlock_force in place of lll_mutex_unlock is not enough and probably why it has been disabled at that time: The number is value in cv->__data.__lock. thr1 thr2 thr3 0 pthread_cond_wait 1 lll_mutex_lock (cv->__data.__lock) 0 lll_mutex_unlock (cv->__data.__lock) 0 lll_futex_wait (&cv->__data.__futex, futexval) 0 pthread_cond_signal 1 lll_mutex_lock (cv->__data.__lock) 1 pthread_cond_signal 2 lll_mutex_lock (cv->__data.__lock) 2 lll_futex_wait (&cv->__data.__lock, 2) 2 lll_futex_requeue (&cv->__data.__futex, 0, 1, &cv->__data.__lock) # FUTEX_REQUEUE, not FUTEX_CMP_REQUEUE 2 lll_mutex_unlock_force (cv->__data.__lock) 0 cv->__data.__lock = 0 0 lll_futex_wake (&cv->__data.__lock, 1) 1 lll_mutex_lock (cv->__data.__lock) 0 lll_mutex_unlock (cv->__data.__lock) # Here, lll_mutex_unlock doesn't know there are threads waiting # on the internal cv's lock Now, I believe it is possible to use FUTEX_REQUEUE in pthread_cond_signal, but it will cost us not one, but 2 extra syscalls and, what's worse, one of these extra syscalls will be done for every single waiting loop in pthread_cond_*wait. We would need to use lll_mutex_unlock_force in pthread_cond_signal after requeue and lll_mutex_cond_lock in pthread_cond_*wait after lll_futex_wait. Another alternative is to do the unlocking pthread_cond_signal needs to do (the lock can't be unlocked before lll_futex_wake, as that is racy) in the kernel. I have implemented both variants, futex-requeue-glibc.patch is the first one and futex-wake_op{,-glibc}.patch is the unlocking inside of the kernel. The kernel interface allows userland to specify how exactly an unlocking operation should look like (some atomic arithmetic operation with optional constant argument and comparison of the previous futex value with another constant). It has been implemented just for ppc*, x86_64 and i?86, for other architectures I'm including just a stub header which can be used as a starting point by maintainers to write support for their arches and ATM will just return -ENOSYS for FUTEX_WAKE_OP. The requeue patch has been (lightly) tested just on x86_64, the wake_op patch on ppc64 kernel running 32-bit and 64-bit NPTL and x86_64 kernel running 32-bit and 64-bit NPTL. With the following benchmark on UP x86-64 I get: for i in nptl-orig nptl-requeue nptl-wake_op; do echo time elf/ld.so --library-path .:$i /tmp/bench; \ for j in 1 2; do echo ( time elf/ld.so --library-path .:$i /tmp/bench ) 2>&1; done; done time elf/ld.so --library-path .:nptl-orig /tmp/bench real 0m0.655s user 0m0.253s sys 0m0.403s real 0m0.657s user 0m0.269s sys 0m0.388s time elf/ld.so --library-path .:nptl-requeue /tmp/bench real 0m0.496s user 0m0.225s sys 0m0.271s real 0m0.531s user 0m0.242s sys 0m0.288s time elf/ld.so --library-path .:nptl-wake_op /tmp/bench real 0m0.380s user 0m0.176s sys 0m0.204s real 0m0.382s user 0m0.175s sys 0m0.207s The benchmark is at: http://sourceware.org/ml/libc-alpha/2005-03/txt00001.txt Older futex-requeue-glibc.patch version is at: http://sourceware.org/ml/libc-alpha/2005-03/txt00002.txt Older futex-wake_op-glibc.patch version is at: http://sourceware.org/ml/libc-alpha/2005-03/txt00003.txt Will post a new version (just x86-64 fixes so that the patch applies against pthread_cond_signal.S) to libc-hacker ml soon. Attached is the kernel FUTEX_WAKE_OP patch as well as a simple-minded testcase that will not test the atomicity of the operation, but at least check if the threads that should have been woken up are woken up and whether the arithmetic operation in the kernel gave the expected results. Acked-by: Ingo Molnar Cc: Ulrich Drepper Cc: Jamie Lokier Cc: Rusty Russell Signed-off-by: Yoichi Yuasa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/futex.h | 36 +++++++++++++++++++++++++++++++----- 1 file changed, 31 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 65d6cfdb6d39..10f96c31971e 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -4,14 +4,40 @@ /* Second argument to futex syscall */ -#define FUTEX_WAIT (0) -#define FUTEX_WAKE (1) -#define FUTEX_FD (2) -#define FUTEX_REQUEUE (3) -#define FUTEX_CMP_REQUEUE (4) +#define FUTEX_WAIT 0 +#define FUTEX_WAKE 1 +#define FUTEX_FD 2 +#define FUTEX_REQUEUE 3 +#define FUTEX_CMP_REQUEUE 4 +#define FUTEX_WAKE_OP 5 long do_futex(unsigned long uaddr, int op, int val, unsigned long timeout, unsigned long uaddr2, int val2, int val3); +#define FUTEX_OP_SET 0 /* *(int *)UADDR2 = OPARG; */ +#define FUTEX_OP_ADD 1 /* *(int *)UADDR2 += OPARG; */ +#define FUTEX_OP_OR 2 /* *(int *)UADDR2 |= OPARG; */ +#define FUTEX_OP_ANDN 3 /* *(int *)UADDR2 &= ~OPARG; */ +#define FUTEX_OP_XOR 4 /* *(int *)UADDR2 ^= OPARG; */ + +#define FUTEX_OP_OPARG_SHIFT 8 /* Use (1 << OPARG) instead of OPARG. */ + +#define FUTEX_OP_CMP_EQ 0 /* if (oldval == CMPARG) wake */ +#define FUTEX_OP_CMP_NE 1 /* if (oldval != CMPARG) wake */ +#define FUTEX_OP_CMP_LT 2 /* if (oldval < CMPARG) wake */ +#define FUTEX_OP_CMP_LE 3 /* if (oldval <= CMPARG) wake */ +#define FUTEX_OP_CMP_GT 4 /* if (oldval > CMPARG) wake */ +#define FUTEX_OP_CMP_GE 5 /* if (oldval >= CMPARG) wake */ + +/* FUTEX_WAKE_OP will perform atomically + int oldval = *(int *)UADDR2; + *(int *)UADDR2 = oldval OP OPARG; + if (oldval CMP CMPARG) + wake UADDR2; */ + +#define FUTEX_OP(op, oparg, cmp, cmparg) \ + (((op & 0xf) << 28) | ((cmp & 0xf) << 24) \ + | ((oparg & 0xfff) << 12) | (cmparg & 0xfff)) + #endif -- cgit v1.2.3 From 8446f1d391f3d27e6bf9c43d4cbcdac0ca720417 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 6 Sep 2005 15:16:27 -0700 Subject: [PATCH] detect soft lockups This patch adds a new kernel debug feature: CONFIG_DETECT_SOFTLOCKUP. When enabled then per-CPU watchdog threads are started, which try to run once per second. If they get delayed for more than 10 seconds then a callback from the timer interrupt detects this condition and prints out a warning message and a stack dump (once per lockup incident). The feature is otherwise non-intrusive, it doesnt try to unlock the box in any way, it only gets the debug info out, automatically, and on all CPUs affected by the lockup. Signed-off-by: Ingo Molnar Signed-off-by: Nishanth Aravamudan Signed-Off-By: Matthias Urlichs Signed-off-by: Richard Purdie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index dec5827c7742..5fb31bede103 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -176,6 +176,23 @@ extern void trap_init(void); extern void update_process_times(int user); extern void scheduler_tick(void); +#ifdef CONFIG_DETECT_SOFTLOCKUP +extern void softlockup_tick(struct pt_regs *regs); +extern void spawn_softlockup_task(void); +extern void touch_softlockup_watchdog(void); +#else +static inline void softlockup_tick(struct pt_regs *regs) +{ +} +static inline void spawn_softlockup_task(void) +{ +} +static inline void touch_softlockup_watchdog(void) +{ +} +#endif + + /* Attach to any functions which should be ignored in wchan output. */ #define __sched __attribute__((__section__(".sched.text"))) /* Is this address in the __sched functions? */ -- cgit v1.2.3 From e82894f84dbba130ab46c97748c03647f8204f92 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Tue, 6 Sep 2005 15:16:30 -0700 Subject: [PATCH] relayfs Here's the latest version of relayfs, against linux-2.6.11-mm2. I'm hoping you'll consider putting this version back into your tree - the previous rounds of comment seem to have shaken out all the API issues and the number of comments on the code itself have also steadily dwindled. This patch is essentially the same as the relayfs redux part 5 patch, with some minor changes based on reviewer comments. Thanks again to Pekka Enberg for those. The patch size without documentation is now a little smaller at just over 40k. Here's a detailed list of the changes: - removed the attribute_flags in relay open and changed it to a boolean specifying either overwrite or no-overwrite mode, and removed everything referencing the attribute flags. - added a check for NULL names in relayfs_create_entry() - got rid of the unnecessary multiple labels in relay_create_buf() - some minor simplification of relay_alloc_buf() which got rid of a couple params - updated the Documentation In addition, this version (through code contained in the relay-apps tarball linked to below, not as part of the relayfs patch) tries to make it as easy as possible to create the cooperating kernel/user pieces of a typical and common type of logging application, one where kernel logging is kicked off when a user space data collection app starts and stops when the collection app exits, with the data being automatically logged to disk in between. To create this type of application, you basically just include a header file (relay-app.h, included in the relay-apps tarball) in your kernel module, define a couple of callbacks and call an initialization function, and on the user side call a single function that sets up and continuously monitors the buffers, and writes data to files as it becomes available. Channels are created when the collection app is started and destroyed when it exits, not when the kernel module is inserted, so different channel buffer sizes can be specified for each separate run via command-line options. See the README in the relay-apps tarball for details. Also included in the relay-apps tarball are a couple examples demonstrating how you can use this to create quick and dirty kernel logging/debugging applications. They are: - tprintk, short for 'tee printk', which temporarily puts a kprobe on printk() and writes a duplicate stream of printk output to a relayfs channel. This could be used anywhere there's printk() debugging code in the kernel which you'd like to exercise, but would rather not have your system logs cluttered with debugging junk. You'd probably want to kill klogd while you do this, otherwise there wouldn't be much point (since putting a kprobe on printk() doesn't change the output of printk()). I've used this method to temporarily divert the packet logging output of the iptables LOG target from the system logs to relayfs files instead, for instance. - klog, which just provides a printk-like formatted logging function on top of relayfs. Again, you can use this to keep stuff out of your system logs if used in place of printk. The example applications can be found here: http://prdownloads.sourceforge.net/dprobes/relay-apps.tar.gz?download From: Christoph Hellwig avoid lookup_hash usage in relayfs Signed-off-by: Tom Zanussi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/relayfs_fs.h | 255 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 255 insertions(+) create mode 100644 include/linux/relayfs_fs.h (limited to 'include/linux') diff --git a/include/linux/relayfs_fs.h b/include/linux/relayfs_fs.h new file mode 100644 index 000000000000..cfafc3e76bc2 --- /dev/null +++ b/include/linux/relayfs_fs.h @@ -0,0 +1,255 @@ +/* + * linux/include/linux/relayfs_fs.h + * + * Copyright (C) 2002, 2003 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp + * Copyright (C) 1999, 2000, 2001, 2002 - Karim Yaghmour (karim@opersys.com) + * + * RelayFS definitions and declarations + */ + +#ifndef _LINUX_RELAYFS_FS_H +#define _LINUX_RELAYFS_FS_H + +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Tracks changes to rchan_buf struct + */ +#define RELAYFS_CHANNEL_VERSION 5 + +/* + * Per-cpu relay channel buffer + */ +struct rchan_buf +{ + void *start; /* start of channel buffer */ + void *data; /* start of current sub-buffer */ + size_t offset; /* current offset into sub-buffer */ + size_t subbufs_produced; /* count of sub-buffers produced */ + size_t subbufs_consumed; /* count of sub-buffers consumed */ + struct rchan *chan; /* associated channel */ + wait_queue_head_t read_wait; /* reader wait queue */ + struct work_struct wake_readers; /* reader wake-up work struct */ + struct dentry *dentry; /* channel file dentry */ + struct kref kref; /* channel buffer refcount */ + struct page **page_array; /* array of current buffer pages */ + unsigned int page_count; /* number of current buffer pages */ + unsigned int finalized; /* buffer has been finalized */ + size_t *padding; /* padding counts per sub-buffer */ + size_t prev_padding; /* temporary variable */ + size_t bytes_consumed; /* bytes consumed in cur read subbuf */ + unsigned int cpu; /* this buf's cpu */ +} ____cacheline_aligned; + +/* + * Relay channel data structure + */ +struct rchan +{ + u32 version; /* the version of this struct */ + size_t subbuf_size; /* sub-buffer size */ + size_t n_subbufs; /* number of sub-buffers per buffer */ + size_t alloc_size; /* total buffer size allocated */ + struct rchan_callbacks *cb; /* client callbacks */ + struct kref kref; /* channel refcount */ + void *private_data; /* for user-defined data */ + struct rchan_buf *buf[NR_CPUS]; /* per-cpu channel buffers */ +}; + +/* + * Relayfs inode + */ +struct relayfs_inode_info +{ + struct inode vfs_inode; + struct rchan_buf *buf; +}; + +static inline struct relayfs_inode_info *RELAYFS_I(struct inode *inode) +{ + return container_of(inode, struct relayfs_inode_info, vfs_inode); +} + +/* + * Relay channel client callbacks + */ +struct rchan_callbacks +{ + /* + * subbuf_start - called on buffer-switch to a new sub-buffer + * @buf: the channel buffer containing the new sub-buffer + * @subbuf: the start of the new sub-buffer + * @prev_subbuf: the start of the previous sub-buffer + * @prev_padding: unused space at the end of previous sub-buffer + * + * The client should return 1 to continue logging, 0 to stop + * logging. + * + * NOTE: subbuf_start will also be invoked when the buffer is + * created, so that the first sub-buffer can be initialized + * if necessary. In this case, prev_subbuf will be NULL. + * + * NOTE: the client can reserve bytes at the beginning of the new + * sub-buffer by calling subbuf_start_reserve() in this callback. + */ + int (*subbuf_start) (struct rchan_buf *buf, + void *subbuf, + void *prev_subbuf, + size_t prev_padding); + + /* + * buf_mapped - relayfs buffer mmap notification + * @buf: the channel buffer + * @filp: relayfs file pointer + * + * Called when a relayfs file is successfully mmapped + */ + void (*buf_mapped)(struct rchan_buf *buf, + struct file *filp); + + /* + * buf_unmapped - relayfs buffer unmap notification + * @buf: the channel buffer + * @filp: relayfs file pointer + * + * Called when a relayfs file is successfully unmapped + */ + void (*buf_unmapped)(struct rchan_buf *buf, + struct file *filp); +}; + +/* + * relayfs kernel API, fs/relayfs/relay.c + */ + +struct rchan *relay_open(const char *base_filename, + struct dentry *parent, + size_t subbuf_size, + size_t n_subbufs, + struct rchan_callbacks *cb); +extern void relay_close(struct rchan *chan); +extern void relay_flush(struct rchan *chan); +extern void relay_subbufs_consumed(struct rchan *chan, + unsigned int cpu, + size_t consumed); +extern void relay_reset(struct rchan *chan); +extern int relay_buf_full(struct rchan_buf *buf); + +extern size_t relay_switch_subbuf(struct rchan_buf *buf, + size_t length); +extern struct dentry *relayfs_create_dir(const char *name, + struct dentry *parent); +extern int relayfs_remove_dir(struct dentry *dentry); + +/** + * relay_write - write data into the channel + * @chan: relay channel + * @data: data to be written + * @length: number of bytes to write + * + * Writes data into the current cpu's channel buffer. + * + * Protects the buffer by disabling interrupts. Use this + * if you might be logging from interrupt context. Try + * __relay_write() if you know you won't be logging from + * interrupt context. + */ +static inline void relay_write(struct rchan *chan, + const void *data, + size_t length) +{ + unsigned long flags; + struct rchan_buf *buf; + + local_irq_save(flags); + buf = chan->buf[smp_processor_id()]; + if (unlikely(buf->offset + length > chan->subbuf_size)) + length = relay_switch_subbuf(buf, length); + memcpy(buf->data + buf->offset, data, length); + buf->offset += length; + local_irq_restore(flags); +} + +/** + * __relay_write - write data into the channel + * @chan: relay channel + * @data: data to be written + * @length: number of bytes to write + * + * Writes data into the current cpu's channel buffer. + * + * Protects the buffer by disabling preemption. Use + * relay_write() if you might be logging from interrupt + * context. + */ +static inline void __relay_write(struct rchan *chan, + const void *data, + size_t length) +{ + struct rchan_buf *buf; + + buf = chan->buf[get_cpu()]; + if (unlikely(buf->offset + length > buf->chan->subbuf_size)) + length = relay_switch_subbuf(buf, length); + memcpy(buf->data + buf->offset, data, length); + buf->offset += length; + put_cpu(); +} + +/** + * relay_reserve - reserve slot in channel buffer + * @chan: relay channel + * @length: number of bytes to reserve + * + * Returns pointer to reserved slot, NULL if full. + * + * Reserves a slot in the current cpu's channel buffer. + * Does not protect the buffer at all - caller must provide + * appropriate synchronization. + */ +static inline void *relay_reserve(struct rchan *chan, size_t length) +{ + void *reserved; + struct rchan_buf *buf = chan->buf[smp_processor_id()]; + + if (unlikely(buf->offset + length > buf->chan->subbuf_size)) { + length = relay_switch_subbuf(buf, length); + if (!length) + return NULL; + } + reserved = buf->data + buf->offset; + buf->offset += length; + + return reserved; +} + +/** + * subbuf_start_reserve - reserve bytes at the start of a sub-buffer + * @buf: relay channel buffer + * @length: number of bytes to reserve + * + * Helper function used to reserve bytes at the beginning of + * a sub-buffer in the subbuf_start() callback. + */ +static inline void subbuf_start_reserve(struct rchan_buf *buf, + size_t length) +{ + BUG_ON(length >= buf->chan->subbuf_size - 1); + buf->offset = length; +} + +/* + * exported relayfs file operations, fs/relayfs/inode.c + */ + +extern struct file_operations relayfs_file_operations; + +#endif /* _LINUX_RELAYFS_FS_H */ + -- cgit v1.2.3 From 202e5979af4d91c7ca05892641131dee22653259 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Tue, 6 Sep 2005 15:16:40 -0700 Subject: [PATCH] compat: be more consistent about [ug]id_t When I first wrote the compat layer patches, I was somewhat cavalier about the definition of compat_uid_t and compat_gid_t (or maybe I just misunderstood :-)). This patch makes the compat types much more consistent with the types we are being compatible with and hopefully will fix a few bugs along the way. compat type type in compat arch __compat_[ug]id_t __kernel_[ug]id_t __compat_[ug]id32_t __kernel_[ug]id32_t compat_[ug]id_t [ug]id_t The difference is that compat_uid_t is always 32 bits (for the archs we care about) but __compat_uid_t may be 16 bits on some. Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index b58b7d6f2fdb..f9ca534787e2 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -18,6 +18,9 @@ #define compat_jiffies_to_clock_t(x) \ (((unsigned long)(x) * COMPAT_USER_HZ) / HZ) +typedef __compat_uid32_t compat_uid_t; +typedef __compat_gid32_t compat_gid_t; + struct rusage; struct compat_itimerspec { -- cgit v1.2.3 From 022a4a7bbdefdedc2706a13c81c832d8c3173c6d Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 6 Sep 2005 15:16:41 -0700 Subject: [PATCH] fs/jbd/: cleanups This patch contains the following cleanups: - make needlessly global functions static - journal.c: remove the unused global function __journal_internal_check and move the check to journal_init - remove the following write-only global variable: - journal.c: current_journal - remove the following unneeded EXPORT_SYMBOL: - journal.c: journal_recover Signed-off-by: Adrian Bunk Acked-by: Andreas Dilger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jbd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 593407e865b1..84321a4cac93 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -914,7 +914,6 @@ extern int journal_wipe (journal_t *, int); extern int journal_skip_recovery (journal_t *); extern void journal_update_superblock (journal_t *, int); extern void __journal_abort_hard (journal_t *); -extern void __journal_abort_soft (journal_t *, int); extern void journal_abort (journal_t *, int); extern int journal_errno (journal_t *); extern void journal_ack_err (journal_t *); -- cgit v1.2.3 From 3676347a5e216a7fec7f8eedbbcf8bed6b9c4e40 Mon Sep 17 00:00:00 2001 From: Peter Osterlund Date: Tue, 6 Sep 2005 15:16:42 -0700 Subject: [PATCH] kill bio->bi_set Jens: ->bi_set is totally unnecessary bloat of struct bio. Just define a proper destructor for the bio and it already knows what bio_set it belongs too. Peter: Fixed the bugs. Signed-off-by: Jens Axboe Signed-off-by: Peter Osterlund Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 36ef29fa0d8b..69e047989f1c 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -111,7 +111,6 @@ struct bio { void *bi_private; bio_destructor_t *bi_destructor; /* destructor */ - struct bio_set *bi_set; /* memory pools set */ }; /* @@ -280,6 +279,7 @@ extern void bioset_free(struct bio_set *); extern struct bio *bio_alloc(unsigned int __nocast, int); extern struct bio *bio_alloc_bioset(unsigned int __nocast, int, struct bio_set *); extern void bio_put(struct bio *); +extern void bio_free(struct bio *, struct bio_set *); extern void bio_endio(struct bio *, unsigned int, int); struct request_queue; -- cgit v1.2.3 From 5dd42c262bd742fa3602180bbe5550b4828de8f3 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 6 Sep 2005 15:16:43 -0700 Subject: [PATCH] remove register_ioctl32_conversion and unregister_ioctl32_conversion All users have been converted. Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ioctl32.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioctl32.h b/include/linux/ioctl32.h index e8c4af32b3bb..948809d99917 100644 --- a/include/linux/ioctl32.h +++ b/include/linux/ioctl32.h @@ -14,26 +14,4 @@ struct ioctl_trans { struct ioctl_trans *next; }; -/* - * Register an 32bit ioctl translation handler for ioctl cmd. - * - * handler == NULL: use 64bit ioctl handler. - * arguments to handler: fd: file descriptor - * cmd: ioctl command. - * arg: ioctl argument - * struct file *file: file descriptor pointer. - */ - -#ifdef CONFIG_COMPAT -extern int __deprecated register_ioctl32_conversion(unsigned int cmd, - ioctl_trans_handler_t handler); -extern int __deprecated unregister_ioctl32_conversion(unsigned int cmd); - -#else - -#define register_ioctl32_conversion(cmd, handler) ({ 0; }) -#define unregister_ioctl32_conversion(cmd) ({ 0; }) - -#endif - #endif -- cgit v1.2.3 From 36d57ac4a818cb4aa3edbdf63ad2ebc31106f925 Mon Sep 17 00:00:00 2001 From: "H. J. Lu" Date: Tue, 6 Sep 2005 15:16:49 -0700 Subject: [PATCH] auxiliary vector cleanups The size of auxiliary vector is fixed at 42 in linux/sched.h. But it isn't very obvious when looking at linux/elf.h. This patch adds AT_VECTOR_SIZE so that we can change it if necessary when a new vector is added. Because of include file ordering problems, doing this necessitated the extraction of the AT_* symbols into a standalone header file. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/auxvec.h | 31 +++++++++++++++++++++++++++++++ include/linux/elf.h | 24 +----------------------- include/linux/sched.h | 4 +++- 3 files changed, 35 insertions(+), 24 deletions(-) create mode 100644 include/linux/auxvec.h (limited to 'include/linux') diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h new file mode 100644 index 000000000000..9a7b374c9fb4 --- /dev/null +++ b/include/linux/auxvec.h @@ -0,0 +1,31 @@ +#ifndef _LINUX_AUXVEC_H +#define _LINUX_AUXVEC_H + +#include + +/* Symbolic values for the entries in the auxiliary table + put on the initial stack */ +#define AT_NULL 0 /* end of vector */ +#define AT_IGNORE 1 /* entry should be ignored */ +#define AT_EXECFD 2 /* file descriptor of program */ +#define AT_PHDR 3 /* program headers for program */ +#define AT_PHENT 4 /* size of program header entry */ +#define AT_PHNUM 5 /* number of program headers */ +#define AT_PAGESZ 6 /* system page size */ +#define AT_BASE 7 /* base address of interpreter */ +#define AT_FLAGS 8 /* flags */ +#define AT_ENTRY 9 /* entry point of program */ +#define AT_NOTELF 10 /* program is not ELF */ +#define AT_UID 11 /* real uid */ +#define AT_EUID 12 /* effective uid */ +#define AT_GID 13 /* real gid */ +#define AT_EGID 14 /* effective gid */ +#define AT_PLATFORM 15 /* string identifying CPU for optimizations */ +#define AT_HWCAP 16 /* arch dependent hints at CPU capabilities */ +#define AT_CLKTCK 17 /* frequency at which times() increments */ + +#define AT_SECURE 23 /* secure mode boolean */ + +#define AT_VECTOR_SIZE 42 /* Size of auxiliary table. */ + +#endif /* _LINUX_AUXVEC_H */ diff --git a/include/linux/elf.h b/include/linux/elf.h index f5b3ba5a317d..ff955dbf510d 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -2,6 +2,7 @@ #define _LINUX_ELF_H #include +#include #include #ifndef elf_read_implies_exec @@ -158,29 +159,6 @@ typedef __s64 Elf64_Sxword; #define ELF64_ST_BIND(x) ELF_ST_BIND(x) #define ELF64_ST_TYPE(x) ELF_ST_TYPE(x) -/* Symbolic values for the entries in the auxiliary table - put on the initial stack */ -#define AT_NULL 0 /* end of vector */ -#define AT_IGNORE 1 /* entry should be ignored */ -#define AT_EXECFD 2 /* file descriptor of program */ -#define AT_PHDR 3 /* program headers for program */ -#define AT_PHENT 4 /* size of program header entry */ -#define AT_PHNUM 5 /* number of program headers */ -#define AT_PAGESZ 6 /* system page size */ -#define AT_BASE 7 /* base address of interpreter */ -#define AT_FLAGS 8 /* flags */ -#define AT_ENTRY 9 /* entry point of program */ -#define AT_NOTELF 10 /* program is not ELF */ -#define AT_UID 11 /* real uid */ -#define AT_EUID 12 /* effective uid */ -#define AT_GID 13 /* real gid */ -#define AT_EGID 14 /* effective gid */ -#define AT_PLATFORM 15 /* string identifying CPU for optimizations */ -#define AT_HWCAP 16 /* arch dependent hints at CPU capabilities */ -#define AT_CLKTCK 17 /* frequency at which times() increments */ - -#define AT_SECURE 23 /* secure mode boolean */ - typedef struct dynamic{ Elf32_Sword d_tag; union{ diff --git a/include/linux/sched.h b/include/linux/sched.h index 5fb31bede103..b5a22ea80045 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -35,6 +35,8 @@ #include #include +#include /* For AT_VECTOR_SIZE */ + struct exec_domain; /* @@ -261,7 +263,7 @@ struct mm_struct { mm_counter_t _rss; mm_counter_t _anon_rss; - unsigned long saved_auxv[42]; /* for /proc/PID/auxv */ + unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ unsigned dumpable:2; cpumask_t cpu_vm_mask; -- cgit v1.2.3 From 8fc2751beb0941966d3a97b26544e8585e428c08 Mon Sep 17 00:00:00 2001 From: Mark Bellon Date: Tue, 6 Sep 2005 15:16:54 -0700 Subject: [PATCH] disk quotas fail when /etc/mtab is symlinked to /proc/mounts If /etc/mtab is a regular file all of the mount options (of a file system) are written to /etc/mtab by the mount command. The quota tools look there for the quota strings for their operation. If, however, /etc/mtab is a symlink to /proc/mounts (a "good thing" in some environments) the tools don't write anything - they assume the kernel will take care of things. While the quota options are sent down to the kernel via the mount system call and the file system codes handle them properly unfortunately there is no code to echo the quota strings into /proc/mounts and the quota tools fail in the symlink case. The attached patchs modify the EXT[2|3] and JFS codes to add the necessary hooks. The show_options function of each file system in these patches currently deal with only those things that seemed related to quotas; especially in the EXT3 case more can be done (later?). Jan Kara also noted the difficulty in moving these changes above the FS codes responding similarly to myself to Andrew's comment about possible VFS migration. Issue summary: - FS codes have to process the entire string of options anyway. - Only FS codes that use quotas must have a show_options function (for quotas to work properly) however quotas are only used in a small number of FS. - Since most of the quota using FS support other options these FS codes should have the a show_options function to show those options - and the quota echoing becomes virtually negligible. Based on feedback I have modified my patches from the original: JFS a missing patch has been restored to the posting EXT[2|3] and JFS always use the show_options function - Each FS has at least one FS specific option displayed - QUOTA output is under a CONFIG_QUOTA ifdef - a follow-on patch will add a multitude of options for each FS EXT[2|3] and JFS "quota" is treated as "usrquota" EXT3 journalled data check for journalled quota removed EXT[2|3] mount when quota specified but not compiled in - no changes from my original patch. I tested the patch and the codes warn but - still mount. With all due respection I believe the comments otherwise were a - misread of the patch. Please reread/test and comment. XFS patch removed - the XFS team already made the necessary changes EXT3 mixing old and new quotas are handled differently (not purely exclusive) - if old and new quotas for the same type are used together the old type is silently depricated for compatability (e.g. usrquota and usrjquota) - mixing of old and new quotas is an error (e.g. usrjquota and grpquota) Signed-off-by: Mark Bellon Acked-by: Dave Kleikamp Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext2_fs.h | 3 +++ include/linux/ext3_fs.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h index a657130ba03a..f7bd1c7ebefb 100644 --- a/include/linux/ext2_fs.h +++ b/include/linux/ext2_fs.h @@ -313,6 +313,9 @@ struct ext2_inode { #define EXT2_MOUNT_XATTR_USER 0x004000 /* Extended user attributes */ #define EXT2_MOUNT_POSIX_ACL 0x008000 /* POSIX Access Control Lists */ #define EXT2_MOUNT_XIP 0x010000 /* Execute in place */ +#define EXT2_MOUNT_USRQUOTA 0x020000 /* user quota */ +#define EXT2_MOUNT_GRPQUOTA 0x040000 /* group quota */ + #define clear_opt(o, opt) o &= ~EXT2_MOUNT_##opt #define set_opt(o, opt) o |= EXT2_MOUNT_##opt diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index c16662836c58..c0272d73ab20 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -373,6 +373,8 @@ struct ext3_inode { #define EXT3_MOUNT_BARRIER 0x20000 /* Use block barriers */ #define EXT3_MOUNT_NOBH 0x40000 /* No bufferheads */ #define EXT3_MOUNT_QUOTA 0x80000 /* Some quota option set */ +#define EXT3_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ +#define EXT3_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ /* Compatibility, for having both ext2_fs.h and ext3_fs.h included at once */ #ifndef _LINUX_EXT2_FS_H -- cgit v1.2.3 From 2865cf001878d22d5fd12e5215621dffbcad76dc Mon Sep 17 00:00:00 2001 From: Zhigang Huo Date: Tue, 6 Sep 2005 15:17:00 -0700 Subject: [PATCH] remove pipe definitions These no longer have any users. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pipe_fs_i.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 36725e7c02c6..1767073df26f 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -39,9 +39,6 @@ struct pipe_inode_info { #define PIPE_SEM(inode) (&(inode).i_sem) #define PIPE_WAIT(inode) (&(inode).i_pipe->wait) -#define PIPE_BASE(inode) ((inode).i_pipe->base) -#define PIPE_START(inode) ((inode).i_pipe->start) -#define PIPE_LEN(inode) ((inode).i_pipe->len) #define PIPE_READERS(inode) ((inode).i_pipe->readers) #define PIPE_WRITERS(inode) ((inode).i_pipe->writers) #define PIPE_WAITING_WRITERS(inode) ((inode).i_pipe->waiting_writers) -- cgit v1.2.3 From d2052c1676a39cae101a81f3da8a4ade8b668c88 Mon Sep 17 00:00:00 2001 From: Erik Waling Date: Tue, 6 Sep 2005 15:17:02 -0700 Subject: [PATCH] sonypi SPIC initialisation fix Newer Sony VAIO models (VGN-S480, VGN-S460, VGN-S3XP etc) use a new method to initialize the SPIC device. The new way to initialize (and disable) the device comes directly from the AML code in the _CRS, _SRS and _DIS methods from the DSDT table. This patch adds support for the new models. Signed-off-by: Erik Waling Signed-off-by: Stelian Pop Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sonypi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sonypi.h b/include/linux/sonypi.h index 768cbba617d0..f56d24734950 100644 --- a/include/linux/sonypi.h +++ b/include/linux/sonypi.h @@ -99,6 +99,8 @@ #define SONYPI_EVENT_BATTERY_INSERT 57 #define SONYPI_EVENT_BATTERY_REMOVE 58 #define SONYPI_EVENT_FNKEY_RELEASED 59 +#define SONYPI_EVENT_WIRELESS_ON 60 +#define SONYPI_EVENT_WIRELESS_OFF 61 /* get/set brightness */ #define SONYPI_IOCGBRT _IOR('v', 0, __u8) -- cgit v1.2.3 From e139aa595c5d3bd01699530cbe017dec75fdb07f Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 6 Sep 2005 15:17:05 -0700 Subject: [PATCH] PNP: make pnp_dbg conditional directly on CONFIG_PNP_DEBUG Seems pointless to require .c files to test CONFIG_PNP_DEBUG and conditionally define DEBUG before including . Just test CONFIG_PNP_DEBUG directly in pnp.h. Signed-off-by: Bjorn Helgaas Cc: Adam Belay Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pnp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pnp.h b/include/linux/pnp.h index 5ec2bd0c2848..aadbac29103c 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -443,7 +443,7 @@ static inline void pnp_unregister_driver(struct pnp_driver *drv) { ; } #define pnp_info(format, arg...) printk(KERN_INFO "pnp: " format "\n" , ## arg) #define pnp_warn(format, arg...) printk(KERN_WARNING "pnp: " format "\n" , ## arg) -#ifdef DEBUG +#ifdef CONFIG_PNP_DEBUG #define pnp_dbg(format, arg...) printk(KERN_DEBUG "pnp: " format "\n" , ## arg) #else #define pnp_dbg(format, arg...) do {} while (0) -- cgit v1.2.3 From f35279d3f713e5c97b98cbdbf47d98f79942c11f Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Tue, 6 Sep 2005 15:17:08 -0700 Subject: [PATCH] sunrpc: cache_register can use wrong module reference When registering an RPC cache, cache_register() always sets the owner as the sunrpc module. However, there are RPC caches owned by other modules. With the incorrect owner setting, the real owning module can be removed potentially with an open reference to the cache from userspace. For example, if one were to stop the nfs server and unmount the nfsd filesystem, the nfsd module could be removed eventhough rpc.idmapd had references to the idtoname and nametoid caches (i.e. /proc/net/rpc/nfs4./channel is still open). This resulted in a system panic on one of our machines when attempting to restart the nfs services after reloading the nfsd module. The following patch adds a 'struct module *owner' field in struct cache_detail. The owner is further assigned to the struct proc_dir_entry in cache_register() so that the module cannot be unloaded while user-space daemons have an open reference on the associated file under /proc. Signed-off-by: Bruce Allan Cc: Trond Myklebust Cc: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/cache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 6864063d1b9f..c4e3ea7cf154 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -60,6 +60,7 @@ struct cache_head { #define CACHE_NEW_EXPIRY 120 /* keep new things pending confirmation for 120 seconds */ struct cache_detail { + struct module * owner; int hash_size; struct cache_head ** hash_table; rwlock_t hash_lock; -- cgit v1.2.3 From 19b4946ca9d1e35d4c641dcebe27378de34f3ddd Mon Sep 17 00:00:00 2001 From: Mike Waychison Date: Tue, 6 Sep 2005 15:17:10 -0700 Subject: [PATCH] ipc: convert /proc/sysvipc/* to generic seq_file interface Change the /proc/sysvipc/shm|sem|msg files to use the generic seq_file implementation for struct ipc_ids. Signed-off-by: Mike Waychison Cc: Manfred Spraul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/msg.h | 1 + include/linux/sem.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msg.h b/include/linux/msg.h index 2c4c6aa643ff..903e0ab8101f 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -77,6 +77,7 @@ struct msg_msg { /* one msq_queue structure for each present queue on the system */ struct msg_queue { struct kern_ipc_perm q_perm; + int q_id; time_t q_stime; /* last msgsnd time */ time_t q_rtime; /* last msgrcv time */ time_t q_ctime; /* last change time */ diff --git a/include/linux/sem.h b/include/linux/sem.h index 2d8516be9fd7..106f9757339a 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -88,6 +88,7 @@ struct sem { /* One sem_array data structure for each set of semaphores in the system. */ struct sem_array { struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ + int sem_id; time_t sem_otime; /* last semop time */ time_t sem_ctime; /* last change time */ struct sem *sem_base; /* ptr to first semaphore in array */ -- cgit v1.2.3 From 6e3eaab02028c4087a92711b20abb9e72cc803a7 Mon Sep 17 00:00:00 2001 From: Abhay Salunke Date: Tue, 6 Sep 2005 15:17:13 -0700 Subject: [PATCH] modified firmware_class.c to support no hotplug Upgrade the request_firmware_nowait function to not start the hotplug action on a firmware update. This patch is tested along with dell_rbu driver on i386 and x86-64 systems. Signed-off-by: Abhay Salunke Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/firmware.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 886255b69bb9..2063c0839d4f 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -3,6 +3,9 @@ #include #include #define FIRMWARE_NAME_MAX 30 +#define FW_ACTION_NOHOTPLUG 0 +#define FW_ACTION_HOTPLUG 1 + struct firmware { size_t size; u8 *data; @@ -11,7 +14,7 @@ struct device; int request_firmware(const struct firmware **fw, const char *name, struct device *device); int request_firmware_nowait( - struct module *module, + struct module *module, int hotplug, const char *name, struct device *device, void *context, void (*cont)(const struct firmware *fw, void *context)); -- cgit v1.2.3 From f26fdd59929e1144c6caf72adcaf4561d6e682a4 Mon Sep 17 00:00:00 2001 From: Karsten Wiese Date: Tue, 6 Sep 2005 15:17:25 -0700 Subject: [PATCH] CHECK_IRQ_PER_CPU() to avoid dead code in __do_IRQ() IRQ_PER_CPU is not used by all architectures. This patch introduces the macros ARCH_HAS_IRQ_PER_CPU and CHECK_IRQ_PER_CPU() to avoid the generation of dead code in __do_IRQ(). ARCH_HAS_IRQ_PER_CPU is defined by architectures using IRQ_PER_CPU in their include/asm_ARCH/irq.h file. Through grepping the tree I found the following architectures currently use IRQ_PER_CPU: cris, ia64, ppc, ppc64 and parisc. Signed-off-by: Karsten Wiese Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irq.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 4a362b9ec966..69681c3b1f05 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -32,7 +32,12 @@ #define IRQ_WAITING 32 /* IRQ not yet seen - for autodetection */ #define IRQ_LEVEL 64 /* IRQ level triggered */ #define IRQ_MASKED 128 /* IRQ masked - shouldn't be seen again */ -#define IRQ_PER_CPU 256 /* IRQ is per CPU */ +#if defined(ARCH_HAS_IRQ_PER_CPU) +# define IRQ_PER_CPU 256 /* IRQ is per CPU */ +# define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU) +#else +# define CHECK_IRQ_PER_CPU(var) 0 +#endif /* * Interrupt controller descriptor. This is all we need -- cgit v1.2.3 From f23ef184b486ac021b6a471b4e94cfa04860d3b0 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Tue, 6 Sep 2005 15:17:29 -0700 Subject: [PATCH] Delete unused do_nanosleep declaration There is no do_nanosleep function so kill it's declaration in . Signed-off-by: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/time.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 5634497ff5df..c10d4c21c183 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -97,7 +97,6 @@ extern int do_settimeofday(struct timespec *tv); extern int do_sys_settimeofday(struct timespec *tv, struct timezone *tz); extern void clock_was_set(void); // call when ever the clock is set extern int do_posix_clock_monotonic_gettime(struct timespec *tp); -extern long do_nanosleep(struct timespec *t); extern long do_utimes(char __user * filename, struct timeval * times); struct itimerval; extern int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue); -- cgit v1.2.3 From 2832e9366a1fcd6f76957a42157be041240f994e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Sep 2005 15:17:38 -0700 Subject: [PATCH] remove file.f_maxcount struct file cleanup: f_maxcount has an unique value (INT_MAX). Just use the hard-wired value. Signed-off-by: Eric Dumazet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 67e6732d4fdc..2036747c7d1f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -594,7 +594,6 @@ struct file { unsigned int f_uid, f_gid; struct file_ra_state f_ra; - size_t f_maxcount; unsigned long f_version; void *f_security; -- cgit v1.2.3 From b149ee2233edf08fb59b11e879a2c5941929bcb8 Mon Sep 17 00:00:00 2001 From: john stultz Date: Tue, 6 Sep 2005 15:17:46 -0700 Subject: [PATCH] NTP: ntp-helper functions This patch cleans up a commonly repeated set of changes to the NTP state variables by adding two helper inline functions: ntp_clear(): Clears the ntp state variables ntp_synced(): Returns 1 if the system is synced with a time server. This was compile tested for alpha, arm, i386, x86-64, ppc64, s390, sparc, sparc64. Signed-off-by: John Stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timex.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 74fdd07d3792..7e050a2cc35b 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -260,6 +260,29 @@ extern long pps_calcnt; /* calibration intervals */ extern long pps_errcnt; /* calibration errors */ extern long pps_stbcnt; /* stability limit exceeded */ +/** + * ntp_clear - Clears the NTP state variables + * + * Must be called while holding a write on the xtime_lock + */ +static inline void ntp_clear(void) +{ + time_adjust = 0; /* stop active adjtime() */ + time_status |= STA_UNSYNC; + time_maxerror = NTP_PHASE_LIMIT; + time_esterror = NTP_PHASE_LIMIT; +} + +/** + * ntp_synced - Returns 1 if the NTP status is not UNSYNC + * + */ +static inline int ntp_synced(void) +{ + return !(time_status & STA_UNSYNC); +} + + #ifdef CONFIG_TIME_INTERPOLATION #define TIME_SOURCE_CPU 0 -- cgit v1.2.3 From 9c45817f41af987277353e463c78a1c6beb37da2 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Tue, 6 Sep 2005 15:17:47 -0700 Subject: [PATCH] Remove non-arch consumers of asm/segment.h asm/segment.h varies greatly on different architectures but is clearly deprecated. Removing all non-architecture consumers will make it easier for us to get ride of asm/segment.h all together. Signed-off-by: Kumar Gala Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/isdn.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/isdn.h b/include/linux/isdn.h index 862083eb58ab..53eaee96065b 100644 --- a/include/linux/isdn.h +++ b/include/linux/isdn.h @@ -150,7 +150,6 @@ typedef struct { #include #include #include -#include #include #include #include -- cgit v1.2.3 From 7ea6040b0eff07d3a9a4e2d248ac137c6ad02d42 Mon Sep 17 00:00:00 2001 From: John McCutchan Date: Tue, 6 Sep 2005 15:18:02 -0700 Subject: [PATCH] inotify: fix event loss on hardlinked files People have run into a problem when they do this: watch (file1, all_events); watch (file2, some_events); if file2 is a hard link to file1, some events will be missed because by default we replace the mask. The patch below adds a flag IN_MASK_ADD which will cause inotify to add to the existing mask if present. Signed-off-by: John McCutchan Signed-off-by: Robert Love Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/inotify.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 93bb3afe646b..ee5b239092ed 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -47,6 +47,7 @@ struct inotify_event { #define IN_MOVE (IN_MOVED_FROM | IN_MOVED_TO) /* moves */ /* special flags */ +#define IN_MASK_ADD 0x20000000 /* add to the mask of an already existing watch */ #define IN_ISDIR 0x40000000 /* event occurred against dir */ #define IN_ONESHOT 0x80000000 /* only send event once */ -- cgit v1.2.3 From f90b1d2f1aaaa40c6519a32e69615edc25bb97d5 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Tue, 6 Sep 2005 15:18:10 -0700 Subject: [PATCH] cpusets: new __GFP_HARDWALL flag Add another GFP flag: __GFP_HARDWALL. A subsequent "cpuset_zone_allowed" patch will use this flag to mark GFP_USER allocations, and distinguish them from GFP_KERNEL allocations. Allocations (such as GFP_USER) marked GFP_HARDWALL are constrainted to the current tasks cpuset. Other allocations (such as GFP_KERNEL) can steal from the possibly larger nearest mem_exclusive cpuset ancestor, if memory is tight on every node in the current cpuset. This patch collides with Mel Gorman's patch to reduce fragmentation in the standard buddy allocator, which adds two GFP flags. This was discussed on linux-mm in July. Most likely, one of his flags for user reclaimable memory can be the same as my __GFP_HARDWALL flag, under some generic name meaning its user address space memory. Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 7c7400137e97..4dc990f3b5cc 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -40,6 +40,7 @@ struct vm_area_struct; #define __GFP_ZERO 0x8000u /* Return zeroed page on success */ #define __GFP_NOMEMALLOC 0x10000u /* Don't use emergency reserves */ #define __GFP_NORECLAIM 0x20000u /* No realy zone reclaim during allocation */ +#define __GFP_HARDWALL 0x40000u /* Enforce hardwall cpuset memory allocs */ #define __GFP_BITS_SHIFT 20 /* Room for 20 __GFP_FOO bits */ #define __GFP_BITS_MASK ((1 << __GFP_BITS_SHIFT) - 1) @@ -48,14 +49,15 @@ struct vm_area_struct; #define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \ __GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \ __GFP_NOFAIL|__GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP| \ - __GFP_NOMEMALLOC|__GFP_NORECLAIM) + __GFP_NOMEMALLOC|__GFP_NORECLAIM|__GFP_HARDWALL) #define GFP_ATOMIC (__GFP_HIGH) #define GFP_NOIO (__GFP_WAIT) #define GFP_NOFS (__GFP_WAIT | __GFP_IO) #define GFP_KERNEL (__GFP_WAIT | __GFP_IO | __GFP_FS) -#define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS) -#define GFP_HIGHUSER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HIGHMEM) +#define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL) +#define GFP_HIGHUSER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL | \ + __GFP_HIGHMEM) /* Flag - indicates that the buffer will be suitable for DMA. Ignored on some platforms, used as appropriate on others */ -- cgit v1.2.3 From 9bf2229f8817677127a60c177aefce1badd22d7b Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Tue, 6 Sep 2005 15:18:12 -0700 Subject: [PATCH] cpusets: formalize intermediate GFP_KERNEL containment This patch makes use of the previously underutilized cpuset flag 'mem_exclusive' to provide what amounts to another layer of memory placement resolution. With this patch, there are now the following four layers of memory placement available: 1) The whole system (interrupt and GFP_ATOMIC allocations can use this), 2) The nearest enclosing mem_exclusive cpuset (GFP_KERNEL allocations can use), 3) The current tasks cpuset (GFP_USER allocations constrained to here), and 4) Specific node placement, using mbind and set_mempolicy. These nest - each layer is a subset (same or within) of the previous. Layer (2) above is new, with this patch. The call used to check whether a zone (its node, actually) is in a cpuset (in its mems_allowed, actually) is extended to take a gfp_mask argument, and its logic is extended, in the case that __GFP_HARDWALL is not set in the flag bits, to look up the cpuset hierarchy for the nearest enclosing mem_exclusive cpuset, to determine if placement is allowed. The definition of GFP_USER, which used to be identical to GFP_KERNEL, is changed to also set the __GFP_HARDWALL bit, in the previous cpuset_gfp_hardwall_flag patch. GFP_ATOMIC and GFP_KERNEL allocations will stay within the current tasks cpuset, so long as any node therein is not too tight on memory, but will escape to the larger layer, if need be. The intended use is to allow something like a batch manager to handle several jobs, each job in its own cpuset, but using common kernel memory for caches and such. Swapper and oom_kill activity is also constrained to Layer (2). A task in or below one mem_exclusive cpuset should not cause swapping on nodes in another non-overlapping mem_exclusive cpuset, nor provoke oom_killing of a task in another such cpuset. Heavy use of kernel memory for i/o caching and such by one job should not impact the memory available to jobs in other non-overlapping mem_exclusive cpusets. This patch enables providing hardwall, inescapable cpusets for memory allocations of each job, while sharing kernel memory allocations between several jobs, in an enclosing mem_exclusive cpuset. Like Dinakar's patch earlier to enable administering sched domains using the cpu_exclusive flag, this patch also provides a useful meaning to a cpuset flag that had previously done nothing much useful other than restrict what cpuset configurations were allowed. Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 3438233305a3..1fe1c3ebad30 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -23,7 +23,7 @@ void cpuset_init_current_mems_allowed(void); void cpuset_update_current_mems_allowed(void); void cpuset_restrict_to_mems_allowed(unsigned long *nodes); int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl); -int cpuset_zone_allowed(struct zone *z); +extern int cpuset_zone_allowed(struct zone *z, unsigned int __nocast gfp_mask); extern struct file_operations proc_cpuset_operations; extern char *cpuset_task_status_allowed(struct task_struct *task, char *buffer); @@ -48,7 +48,8 @@ static inline int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl) return 1; } -static inline int cpuset_zone_allowed(struct zone *z) +static inline int cpuset_zone_allowed(struct zone *z, + unsigned int __nocast gfp_mask) { return 1; } -- cgit v1.2.3 From ef08e3b4981aebf2ba9bd7025ef7210e8eec07ce Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Tue, 6 Sep 2005 15:18:13 -0700 Subject: [PATCH] cpusets: confine oom_killer to mem_exclusive cpuset Now the real motivation for this cpuset mem_exclusive patch series seems trivial. This patch keeps a task in or under one mem_exclusive cpuset from provoking an oom kill of a task under a non-overlapping mem_exclusive cpuset. Since only interrupt and GFP_ATOMIC allocations are allowed to escape mem_exclusive containment, there is little to gain from oom killing a task under a non-overlapping mem_exclusive cpuset, as almost all kernel and user memory allocation must come from disjoint memory nodes. This patch enables configuring a system so that a runaway job under one mem_exclusive cpuset cannot cause the killing of a job in another such cpuset that might be using very high compute and memory resources for a prolonged time. Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 1fe1c3ebad30..24062a1dbf61 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -24,6 +24,7 @@ void cpuset_update_current_mems_allowed(void); void cpuset_restrict_to_mems_allowed(unsigned long *nodes); int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl); extern int cpuset_zone_allowed(struct zone *z, unsigned int __nocast gfp_mask); +extern int cpuset_excl_nodes_overlap(const struct task_struct *p); extern struct file_operations proc_cpuset_operations; extern char *cpuset_task_status_allowed(struct task_struct *task, char *buffer); @@ -54,6 +55,11 @@ static inline int cpuset_zone_allowed(struct zone *z, return 1; } +static inline int cpuset_excl_nodes_overlap(const struct task_struct *p) +{ + return 1; +} + static inline char *cpuset_task_status_allowed(struct task_struct *task, char *buffer) { -- cgit v1.2.3 From 9c1cfda20a508b181bdda8c0045f7c0c333880a5 Mon Sep 17 00:00:00 2001 From: John Hawkes Date: Tue, 6 Sep 2005 15:18:14 -0700 Subject: [PATCH] cpusets: Move the ia64 domain setup code to the generic code Signed-off-by: John Hawkes Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 7 ------- include/linux/topology.h | 23 +++++++++++++++++++++++ 2 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b5a22ea80045..ea1b5f32ec5c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -564,13 +564,6 @@ struct sched_domain { extern void partition_sched_domains(cpumask_t *partition1, cpumask_t *partition2); -#ifdef ARCH_HAS_SCHED_DOMAIN -/* Useful helpers that arch setup code may use. Defined in kernel/sched.c */ -extern cpumask_t cpu_isolated_map; -extern void init_sched_build_groups(struct sched_group groups[], - cpumask_t span, int (*group_fn)(int cpu)); -extern void cpu_attach_domain(struct sched_domain *sd, int cpu); -#endif /* ARCH_HAS_SCHED_DOMAIN */ #endif /* CONFIG_SMP */ diff --git a/include/linux/topology.h b/include/linux/topology.h index 0320225e96da..3df1d474e5c5 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -135,6 +135,29 @@ } #endif +/* sched_domains SD_ALLNODES_INIT for NUMA machines */ +#define SD_ALLNODES_INIT (struct sched_domain) { \ + .span = CPU_MASK_NONE, \ + .parent = NULL, \ + .groups = NULL, \ + .min_interval = 64, \ + .max_interval = 64*num_online_cpus(), \ + .busy_factor = 128, \ + .imbalance_pct = 133, \ + .cache_hot_time = (10*1000000), \ + .cache_nice_tries = 1, \ + .busy_idx = 3, \ + .idle_idx = 3, \ + .newidle_idx = 0, /* unused */ \ + .wake_idx = 0, /* unused */ \ + .forkexec_idx = 0, /* unused */ \ + .per_cpu_gain = 100, \ + .flags = SD_LOAD_BALANCE, \ + .last_balance = jiffies, \ + .balance_interval = 64, \ + .nr_balance_failed = 0, \ +} + #ifdef CONFIG_NUMA #ifndef SD_NODE_INIT #error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!! -- cgit v1.2.3 From 3f4bb1f4199b7dc0c958447b1e4898980013b884 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Sep 2005 15:18:16 -0700 Subject: [PATCH] struct dentry: place d_hash close to d_parent and d_name to speedup lookups dentry cache uses sophisticated RCU technology (and prefetching if available) but touches 2 cache lines per dentry during hlist lookup. This patch moves d_hash in the same cache line than d_parent and d_name fields so that : 1) One cache line is needed instead of two. 2) the hlist_for_each_rcu() prefetching has a chance to bring all the needed data in advance, not only the part that includes d_hash.next. I also changed one old comment that was wrong for 64bits. A further optimisation would be to separate dentry in two parts, one that is mostly read, and one writen (d_count/d_lock) to avoid false sharing on SMP/NUMA but this would need different field placement depending on 32bits or 64bits platform. Signed-off-by: Eric Dumazet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 50be290d24d2..ab04b4f9b0db 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -88,8 +88,9 @@ struct dentry { * negative */ /* * The next three fields are touched by __d_lookup. Place them here - * so they all fit in a 16-byte range, with 16-byte alignment. + * so they all fit in a cache line. */ + struct hlist_node d_hash; /* lookup hash list */ struct dentry *d_parent; /* parent directory */ struct qstr d_name; @@ -103,7 +104,6 @@ struct dentry { void *d_fsdata; /* fs-specific data */ struct rcu_head d_rcu; struct dcookie_struct *d_cookie; /* cookie, if any */ - struct hlist_node d_hash; /* lookup hash list */ int d_mounted; unsigned char d_iname[DNAME_INLINE_LEN_MIN]; /* small names */ }; -- cgit v1.2.3 From e89bbd3a0b3c054d9a94feb0db7bbae1cdb99e54 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 6 Sep 2005 15:18:21 -0700 Subject: [PATCH] remove iattr.ia_attr_flags Remove unused ia_attr_flags from struct iattr, and related defines. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2036747c7d1f..57e294bf83f4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -281,18 +281,8 @@ struct iattr { struct timespec ia_atime; struct timespec ia_mtime; struct timespec ia_ctime; - unsigned int ia_attr_flags; }; -/* - * This is the inode attributes flag definitions - */ -#define ATTR_FLAG_SYNCRONOUS 1 /* Syncronous write */ -#define ATTR_FLAG_NOATIME 2 /* Don't update atime */ -#define ATTR_FLAG_APPEND 4 /* Append-only file */ -#define ATTR_FLAG_IMMUTABLE 8 /* Immutable file */ -#define ATTR_FLAG_NODIRATIME 16 /* Don't update atime for directory */ - /* * Includes for diskquotas. */ -- cgit v1.2.3 From ab8d11beb46f0bd0617e04205c01f5c1fe845b61 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 6 Sep 2005 15:18:24 -0700 Subject: [PATCH] remove duplicated code from proc and ptrace Extract common code used by ptrace_attach() and may_ptrace_attach() into a separate function. Signed-off-by: Miklos Szeredi Cc: Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 2afdafb62123..dc6f3647bfbc 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -90,6 +90,7 @@ extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent); extern void __ptrace_unlink(struct task_struct *child); extern void ptrace_untrace(struct task_struct *child); +extern int ptrace_may_attach(struct task_struct *task); static inline void ptrace_link(struct task_struct *child, struct task_struct *new_parent) -- cgit v1.2.3 From e922efc342d565a38eed3af377ff403f52148864 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 6 Sep 2005 15:18:25 -0700 Subject: [PATCH] remove duplicated sys_open32() code from 64bit archs 64 bit architectures all implement their own compatibility sys_open(), when in fact the difference is simply not forcing the O_LARGEFILE flag. So use the a common function instead. Signed-off-by: Miklos Szeredi Cc: Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 57e294bf83f4..7e1b589842af 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1280,6 +1280,7 @@ static inline int break_lease(struct inode *inode, unsigned int mode) /* fs/open.c */ extern int do_truncate(struct dentry *, loff_t start); +extern long do_sys_open(const char __user *filename, int flags, int mode); extern struct file *filp_open(const char *, int, int); extern struct file * dentry_open(struct dentry *, struct vfsmount *, int); extern int filp_close(struct file *, fl_owner_t id); -- cgit v1.2.3 From ebad6a4230bdb5927495e28bc7837f515bf667a7 Mon Sep 17 00:00:00 2001 From: Andrey Panin Date: Tue, 6 Sep 2005 15:18:29 -0700 Subject: [PATCH] dmi: add onboard devices discovery This patch adds onboard devices and IPMI BMC discovery into DMI scan code. Drivers can use dmi_find_device() function to search for devices by type and name. Signed-off-by: Andrey Panin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dmi.h | 36 +++++++++++++++++++++++++++++++++--- 1 file changed, 33 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 5e93e6dce9a4..c30175e8dec6 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -1,6 +1,8 @@ #ifndef __DMI_H__ #define __DMI_H__ +#include + enum dmi_field { DMI_NONE, DMI_BIOS_VENDOR, @@ -16,6 +18,24 @@ enum dmi_field { DMI_STRING_MAX, }; +enum dmi_device_type { + DMI_DEV_TYPE_ANY = 0, + DMI_DEV_TYPE_OTHER, + DMI_DEV_TYPE_UNKNOWN, + DMI_DEV_TYPE_VIDEO, + DMI_DEV_TYPE_SCSI, + DMI_DEV_TYPE_ETHERNET, + DMI_DEV_TYPE_TOKENRING, + DMI_DEV_TYPE_SOUND, + DMI_DEV_TYPE_IPMI = -1 +}; + +struct dmi_header { + u8 type; + u8 length; + u16 handle; +}; + /* * DMI callbacks for problem boards */ @@ -26,22 +46,32 @@ struct dmi_strmatch { struct dmi_system_id { int (*callback)(struct dmi_system_id *); - char *ident; + const char *ident; struct dmi_strmatch matches[4]; void *driver_data; }; -#define DMI_MATCH(a,b) { a, b } +#define DMI_MATCH(a, b) { a, b } + +struct dmi_device { + struct list_head list; + int type; + const char *name; + void *device_data; /* Type specific data */ +}; #if defined(CONFIG_X86) && !defined(CONFIG_X86_64) extern int dmi_check_system(struct dmi_system_id *list); extern char * dmi_get_system_info(int field); - +extern struct dmi_device * dmi_find_device(int type, const char *name, + struct dmi_device *from); #else static inline int dmi_check_system(struct dmi_system_id *list) { return 0; } static inline char * dmi_get_system_info(int field) { return NULL; } +static struct dmi_device * dmi_find_device(int type, const char *name, + struct dmi_device *from) { return NULL; } #endif -- cgit v1.2.3 From dd3927105b6f65afb7dac17682172cdfb86d3f00 Mon Sep 17 00:00:00 2001 From: Pekka J Enberg Date: Tue, 6 Sep 2005 15:18:31 -0700 Subject: [PATCH] introduce and use kzalloc This patch introduces a kzalloc wrapper and converts kernel/ to use it. It saves a little program text. Signed-off-by: Pekka Enberg Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 80b2dfde2e80..42a6bea58af3 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -99,7 +99,21 @@ found: return __kmalloc(size, flags); } -extern void *kcalloc(size_t, size_t, unsigned int __nocast); +extern void *kzalloc(size_t, unsigned int __nocast); + +/** + * kcalloc - allocate memory for an array. The memory is set to zero. + * @n: number of elements. + * @size: element size. + * @flags: the type of memory to allocate. + */ +static inline void *kcalloc(size_t n, size_t size, unsigned int __nocast flags) +{ + if (n != 0 && size > INT_MAX / n) + return NULL; + return kzalloc(n * size, flags); +} + extern void kfree(const void *); extern unsigned int ksize(const void *); -- cgit v1.2.3 From c14979b993021377228958498937bcdd9539cbce Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Tue, 6 Sep 2005 15:18:38 -0700 Subject: [PATCH] ipmi: add per-channel IPMB addresses IPMI allows multiple IPMB channels on a single interface, and each channel might have a different IPMB address. However, the driver has only one IPMB address that it uses for everything. This patch adds new IOCTLS and a new internal interface for setting per-channel IPMB addresses and LUNs. New systems are coming out with support for multiple IPMB channels, and they are broken without this patch. Signed-off-by: Corey Minyard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipmi.h | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 596ca6130159..846b69899776 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -298,13 +298,19 @@ void ipmi_get_version(ipmi_user_t user, this user, so it will affect all users of this interface. This is so some initialization code can come in and do the OEM-specific things it takes to determine your address (if not the BMC) and set - it for everyone else. */ -void ipmi_set_my_address(ipmi_user_t user, - unsigned char address); -unsigned char ipmi_get_my_address(ipmi_user_t user); -void ipmi_set_my_LUN(ipmi_user_t user, - unsigned char LUN); -unsigned char ipmi_get_my_LUN(ipmi_user_t user); + it for everyone else. Note that each channel can have its own address. */ +int ipmi_set_my_address(ipmi_user_t user, + unsigned int channel, + unsigned char address); +int ipmi_get_my_address(ipmi_user_t user, + unsigned int channel, + unsigned char *address); +int ipmi_set_my_LUN(ipmi_user_t user, + unsigned int channel, + unsigned char LUN); +int ipmi_get_my_LUN(ipmi_user_t user, + unsigned int channel, + unsigned char *LUN); /* * Like ipmi_request, but lets you specify the number of retries and @@ -585,6 +591,16 @@ struct ipmi_cmdspec * things it takes to determine your address (if not the BMC) and set * it for everyone else. You should probably leave the LUN alone. */ +struct ipmi_channel_lun_address_set +{ + unsigned short channel; + unsigned char value; +}; +#define IPMICTL_SET_MY_CHANNEL_ADDRESS_CMD _IOR(IPMI_IOC_MAGIC, 24, struct ipmi_channel_lun_address_set) +#define IPMICTL_GET_MY_CHANNEL_ADDRESS_CMD _IOR(IPMI_IOC_MAGIC, 25, struct ipmi_channel_lun_address_set) +#define IPMICTL_SET_MY_CHANNEL_LUN_CMD _IOR(IPMI_IOC_MAGIC, 26, struct ipmi_channel_lun_address_set) +#define IPMICTL_GET_MY_CHANNEL_LUN_CMD _IOR(IPMI_IOC_MAGIC, 27, struct ipmi_channel_lun_address_set) +/* Legacy interfaces, these only set IPMB 0. */ #define IPMICTL_SET_MY_ADDRESS_CMD _IOR(IPMI_IOC_MAGIC, 17, unsigned int) #define IPMICTL_GET_MY_ADDRESS_CMD _IOR(IPMI_IOC_MAGIC, 18, unsigned int) #define IPMICTL_SET_MY_LUN_CMD _IOR(IPMI_IOC_MAGIC, 19, unsigned int) -- cgit v1.2.3 From 07766f241b54d67999907d529b99ffaa61d8b7d9 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Tue, 6 Sep 2005 15:18:40 -0700 Subject: [PATCH] ipmi: allow userland to include ipmi.h The IPMI driver include file needs to include compiler.h so it has definitions for __user and such. Signed-off-by: Corey Minyard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipmi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 846b69899776..dd30adedd07d 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -35,6 +35,7 @@ #define __LINUX_IPMI_H #include +#include /* * This file describes an interface to an IPMI driver. You have to -- cgit v1.2.3 From 56a55ec64806fb56e0cd43b0f726020b74c6689b Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Tue, 6 Sep 2005 15:18:42 -0700 Subject: [PATCH] ipmi: fix panic ipmb response The "null message handler" in the IPMI driver is used in startup and panic situations to handle messages. It was only designed to work with messages from the local management controller, but in some cases it was used to get messages from remote managmenet controllers, and the system would then panic. This patch makes the "null message handler" in the IPMI driver more general so it works with any kind of message. Signed-off-by: Corey Minyard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipmi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index dd30adedd07d..938d55b813a5 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -242,7 +242,8 @@ struct ipmi_recv_msg /* The user_msg_data is the data supplied when a message was sent, if this is a response to a sent message. If this is not a response to a sent message, then user_msg_data will - be NULL. */ + be NULL. If the user above is NULL, then this will be the + intf. */ void *user_msg_data; /* Call this when done with the message. It will presumably free -- cgit v1.2.3 From 8c702e16207c70119d03df924de35f8c3629a5c4 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Tue, 6 Sep 2005 15:18:46 -0700 Subject: [PATCH] ipmi poweroff: fix chassis control The IPMI power control function proc_write_chassctrl was badly written, it directly used userspace pointers, it assumed that strings were NULL terminated, and it used the evil sscanf function. This converts over to using the sysctl interface for this data and changes the semantics to be a little more logical. Signed-off-by: Corey Minyard Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 e82be96d4906..532a6c5c24e9 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -711,6 +711,7 @@ enum { DEV_RAID=4, DEV_MAC_HID=5, DEV_SCSI=6, + DEV_IPMI=7, }; /* /proc/sys/dev/cdrom */ @@ -776,6 +777,11 @@ enum { DEV_SCSI_LOGGING_LEVEL=1, }; +/* /proc/sys/dev/ipmi */ +enum { + DEV_IPMI_POWEROFF_POWERCYCLE=1, +}; + /* /proc/sys/abi */ enum { -- cgit v1.2.3 From 335eadf2ef6a1122a720aea98e758e5d431da87d Mon Sep 17 00:00:00 2001 From: Pierre Ossman Date: Tue, 6 Sep 2005 15:18:50 -0700 Subject: [PATCH] sd: initialize SD cards Support for the Secure Digital protocol in the MMC layer. A summary of the legal issues surrounding SD cards, as understood by yours truly: Members of the Secure Digital Association, hereafter SDA, are required to sign a NDA[1] before given access to any specifications. It has been speculated that including an SD implementation would forbid these members to redistribute Linux. This is the basic problem with SD support so it is unclear if it even is a problem since it has no effect on those of us that aren't members. The SDA doesn't seem to enforce these rules though since the patches included here are based on documentation made public by some of the members. The most complete specs[2] are actually released by Sandisk, one of the founding companies of the SDA. Because of this the NDA is considered a non-issue by most involved in the discussions concerning these patches. It might be that the SDA is only interested in protecting the so called "secure" bits of SD, which so far hasn't been found in any public spec. (The card is split into two sections, one "normal" and one "secure" which has an access scheme similar to TPM:s). (As a side note, Microsoft is working to make things easier for us since they want to be able to include the source code for a SD driver in one of their development kits. HP is making sure that the new NDA will allow a Linux implementation. So far only the SDIO specs have been opened up[3]. More will hopefully follow.) [1] http://www.sdcard.org/membership/images/ippolicy.pdf [2] http://www.sandisk.com/pdf/oem/ProdManualSDCardv1.9.pdf [3] http://www.sdcard.org/sdio/Simplified%20SDIO%20Card%20Specification.pdf This patch contains the central parts of the SD support. If no MMC cards are found on a bus then the MMC layer proceeds looking for SD cards. Helper functions are extended to handle the special needs of SD cards. Signed-off-by: Pierre Ossman Cc: Russell King Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/card.h | 3 +++ include/linux/mmc/host.h | 4 ++++ include/linux/mmc/mmc.h | 2 ++ 3 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index aefedf04b9bb..538e8c86336c 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -47,6 +47,7 @@ struct mmc_card { #define MMC_STATE_PRESENT (1<<0) /* present in sysfs */ #define MMC_STATE_DEAD (1<<1) /* device no longer in stack */ #define MMC_STATE_BAD (1<<2) /* unrecognised device */ +#define MMC_STATE_SDCARD (1<<3) /* is an SD card */ u32 raw_cid[4]; /* raw card CID */ u32 raw_csd[4]; /* raw card CSD */ struct mmc_cid cid; /* card identification */ @@ -56,10 +57,12 @@ struct mmc_card { #define mmc_card_present(c) ((c)->state & MMC_STATE_PRESENT) #define mmc_card_dead(c) ((c)->state & MMC_STATE_DEAD) #define mmc_card_bad(c) ((c)->state & MMC_STATE_BAD) +#define mmc_card_sd(c) ((c)->state & MMC_STATE_SDCARD) #define mmc_card_set_present(c) ((c)->state |= MMC_STATE_PRESENT) #define mmc_card_set_dead(c) ((c)->state |= MMC_STATE_DEAD) #define mmc_card_set_bad(c) ((c)->state |= MMC_STATE_BAD) +#define mmc_card_set_sd(c) ((c)->state |= MMC_STATE_SDCARD) #define mmc_card_name(c) ((c)->cid.prod_name) #define mmc_card_id(c) ((c)->dev.bus_id) diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 30f68c0c8c6e..845020d90c60 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -87,6 +87,10 @@ struct mmc_host { struct mmc_ios ios; /* current io bus settings */ u32 ocr; /* the current OCR setting */ + unsigned int mode; /* current card mode of host */ +#define MMC_MODE_MMC 0 +#define MMC_MODE_SD 1 + struct list_head cards; /* devices attached to this host */ wait_queue_head_t wq; diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 0d35d4ffb360..1ab78e8d6c53 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -88,6 +88,8 @@ struct mmc_card; extern int mmc_wait_for_req(struct mmc_host *, struct mmc_request *); extern int mmc_wait_for_cmd(struct mmc_host *, struct mmc_command *, int); +extern int mmc_wait_for_app_cmd(struct mmc_host *, unsigned int, + struct mmc_command *, int); extern int __mmc_claim_host(struct mmc_host *host, struct mmc_card *card); -- cgit v1.2.3 From a00fc09029f02ca833cf90e5d5625f08c4ac4f51 Mon Sep 17 00:00:00 2001 From: Pierre Ossman Date: Tue, 6 Sep 2005 15:18:52 -0700 Subject: [PATCH] sd: read-only switch Support for the read-only switch on SD cards which must be enforced by the host. Signed-off-by: Pierre Ossman Cc: Russell King Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/card.h | 3 +++ include/linux/mmc/host.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 538e8c86336c..0e9ec01b9c5b 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -48,6 +48,7 @@ struct mmc_card { #define MMC_STATE_DEAD (1<<1) /* device no longer in stack */ #define MMC_STATE_BAD (1<<2) /* unrecognised device */ #define MMC_STATE_SDCARD (1<<3) /* is an SD card */ +#define MMC_STATE_READONLY (1<<4) /* card is read-only */ u32 raw_cid[4]; /* raw card CID */ u32 raw_csd[4]; /* raw card CSD */ struct mmc_cid cid; /* card identification */ @@ -58,11 +59,13 @@ struct mmc_card { #define mmc_card_dead(c) ((c)->state & MMC_STATE_DEAD) #define mmc_card_bad(c) ((c)->state & MMC_STATE_BAD) #define mmc_card_sd(c) ((c)->state & MMC_STATE_SDCARD) +#define mmc_card_readonly(c) ((c)->state & MMC_STATE_READONLY) #define mmc_card_set_present(c) ((c)->state |= MMC_STATE_PRESENT) #define mmc_card_set_dead(c) ((c)->state |= MMC_STATE_DEAD) #define mmc_card_set_bad(c) ((c)->state |= MMC_STATE_BAD) #define mmc_card_set_sd(c) ((c)->state |= MMC_STATE_SDCARD) +#define mmc_card_set_readonly(c) ((c)->state |= MMC_STATE_READONLY) #define mmc_card_name(c) ((c)->cid.prod_name) #define mmc_card_id(c) ((c)->dev.bus_id) diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 845020d90c60..8c5f71376e41 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -62,6 +62,7 @@ struct mmc_ios { struct mmc_host_ops { void (*request)(struct mmc_host *host, struct mmc_request *req); void (*set_ios)(struct mmc_host *host, struct mmc_ios *ios); + int (*get_ro)(struct mmc_host *host); }; struct mmc_card; -- cgit v1.2.3 From b57c43ad81602589afca3948a5a7121e40026e17 Mon Sep 17 00:00:00 2001 From: Pierre Ossman Date: Tue, 6 Sep 2005 15:18:53 -0700 Subject: [PATCH] sd: SCR register Read the SD specific SCR register from the card. Signed-off-by: Pierre Ossman Cc: Russell King Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/card.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 0e9ec01b9c5b..18fc77f682de 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -33,6 +33,13 @@ struct mmc_csd { unsigned int capacity; }; +struct sd_scr { + unsigned char sda_vsn; + unsigned char bus_widths; +#define SD_SCR_BUS_WIDTH_1 (1<<0) +#define SD_SCR_BUS_WIDTH_4 (1<<2) +}; + struct mmc_host; /* @@ -51,8 +58,10 @@ struct mmc_card { #define MMC_STATE_READONLY (1<<4) /* card is read-only */ u32 raw_cid[4]; /* raw card CID */ u32 raw_csd[4]; /* raw card CSD */ + u32 raw_scr[2]; /* raw card SCR */ struct mmc_cid cid; /* card identification */ struct mmc_csd csd; /* card specific */ + struct sd_scr scr; /* extra SD information */ }; #define mmc_card_present(c) ((c)->state & MMC_STATE_PRESENT) -- cgit v1.2.3 From f218278a456b3c272b480443c89004c3d2a49f18 Mon Sep 17 00:00:00 2001 From: Pierre Ossman Date: Tue, 6 Sep 2005 15:18:55 -0700 Subject: [PATCH] sd: SD 4-bit bus Infrastructure for 4-bit bus transfers with SD cards. Signed-off-by: Pierre Ossman Cc: Russell King Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/host.h | 9 +++++++++ include/linux/mmc/protocol.h | 7 +++++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 8c5f71376e41..6014160d9c06 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -57,6 +57,11 @@ struct mmc_ios { #define MMC_POWER_OFF 0 #define MMC_POWER_UP 1 #define MMC_POWER_ON 2 + + unsigned char bus_width; /* data bus width */ + +#define MMC_BUS_WIDTH_1 0 +#define MMC_BUS_WIDTH_4 2 }; struct mmc_host_ops { @@ -77,6 +82,10 @@ struct mmc_host { unsigned int f_max; u32 ocr_avail; + unsigned long caps; /* Host capabilities */ + +#define MMC_CAP_4_BIT_DATA (1 << 0) /* Can the host do 4 bit transfers */ + /* host specific block data */ unsigned int max_seg_size; /* see blk_queue_max_segment_size */ unsigned short max_hw_segs; /* see blk_queue_max_hw_segments */ diff --git a/include/linux/mmc/protocol.h b/include/linux/mmc/protocol.h index 896342817b97..f819cae92266 100644 --- a/include/linux/mmc/protocol.h +++ b/include/linux/mmc/protocol.h @@ -236,5 +236,12 @@ struct _mmc_csd { #define CSD_SPEC_VER_2 2 /* Implements system specification 2.0 - 2.2 */ #define CSD_SPEC_VER_3 3 /* Implements system specification 3.1 */ + +/* + * SD bus widths + */ +#define SD_BUS_WIDTH_1 0 +#define SD_BUS_WIDTH_4 2 + #endif /* MMC_MMC_PROTOCOL_H */ -- cgit v1.2.3 From 3158106685acac8f8d4e74a17b974f160fe77c0b Mon Sep 17 00:00:00 2001 From: Richard Purdie Date: Tue, 6 Sep 2005 15:19:06 -0700 Subject: [PATCH] Input: Add a new switch event type The corgi keyboard has need of a switch event type with slightly type to the input system as recommended by the input maintainer. Signed-off-by: Richard Purdie Cc: Vojtech Pavlik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/input.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index bdc53c6cc962..4767e5429534 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -66,6 +66,7 @@ struct input_absinfo { #define EVIOCGKEY(len) _IOC(_IOC_READ, 'E', 0x18, len) /* get global keystate */ #define EVIOCGLED(len) _IOC(_IOC_READ, 'E', 0x19, len) /* get all LEDs */ #define EVIOCGSND(len) _IOC(_IOC_READ, 'E', 0x1a, len) /* get all sounds status */ +#define EVIOCGSW(len) _IOC(_IOC_READ, 'E', 0x1b, len) /* get all switch states */ #define EVIOCGBIT(ev,len) _IOC(_IOC_READ, 'E', 0x20 + ev, len) /* get event bits */ #define EVIOCGABS(abs) _IOR('E', 0x40 + abs, struct input_absinfo) /* get abs value/limits */ @@ -86,6 +87,7 @@ struct input_absinfo { #define EV_REL 0x02 #define EV_ABS 0x03 #define EV_MSC 0x04 +#define EV_SW 0x05 #define EV_LED 0x11 #define EV_SND 0x12 #define EV_REP 0x14 @@ -550,6 +552,20 @@ struct input_absinfo { #define ABS_MISC 0x28 #define ABS_MAX 0x3f +/* + * Switch events + */ + +#define SW_0 0x00 +#define SW_1 0x01 +#define SW_2 0x02 +#define SW_3 0x03 +#define SW_4 0x04 +#define SW_5 0x05 +#define SW_6 0x06 +#define SW_7 0x07 +#define SW_MAX 0x0f + /* * Misc events */ @@ -824,6 +840,7 @@ struct input_dev { unsigned long ledbit[NBITS(LED_MAX)]; unsigned long sndbit[NBITS(SND_MAX)]; unsigned long ffbit[NBITS(FF_MAX)]; + unsigned long swbit[NBITS(SW_MAX)]; int ff_effects_max; unsigned int keycodemax; @@ -844,6 +861,7 @@ struct input_dev { unsigned long key[NBITS(KEY_MAX)]; unsigned long led[NBITS(LED_MAX)]; unsigned long snd[NBITS(SND_MAX)]; + unsigned long sw[NBITS(SW_MAX)]; int absmax[ABS_MAX + 1]; int absmin[ABS_MAX + 1]; @@ -886,6 +904,7 @@ struct input_dev { #define INPUT_DEVICE_ID_MATCH_LEDBIT 0x200 #define INPUT_DEVICE_ID_MATCH_SNDBIT 0x400 #define INPUT_DEVICE_ID_MATCH_FFBIT 0x800 +#define INPUT_DEVICE_ID_MATCH_SWBIT 0x1000 #define INPUT_DEVICE_ID_MATCH_DEVICE\ (INPUT_DEVICE_ID_MATCH_BUS | INPUT_DEVICE_ID_MATCH_VENDOR | INPUT_DEVICE_ID_MATCH_PRODUCT) @@ -906,6 +925,7 @@ struct input_device_id { unsigned long ledbit[NBITS(LED_MAX)]; unsigned long sndbit[NBITS(SND_MAX)]; unsigned long ffbit[NBITS(FF_MAX)]; + unsigned long swbit[NBITS(SW_MAX)]; unsigned long driver_info; }; @@ -998,6 +1018,11 @@ static inline void input_report_ff_status(struct input_dev *dev, unsigned int co input_event(dev, EV_FF_STATUS, code, value); } +static inline void input_report_switch(struct input_dev *dev, unsigned int code, int value) +{ + input_event(dev, EV_SW, code, !!value); +} + static inline void input_regs(struct input_dev *dev, struct pt_regs *regs) { dev->regs = regs; -- cgit v1.2.3 From a7662236253374012d364106b6dc9161bd929e2e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 6 Sep 2005 15:19:10 -0700 Subject: [PATCH] Make ll_rw_block() wait for buffer lock Introduce new ll_rw_block() operation SWRITE meaning that block layer should wait for the buffer lock and write-out afterwards. Hence data in buffers at the time of call are guaranteed to be submitted to the disk. Signed-off-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7e1b589842af..fd93ab7da905 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -69,6 +69,7 @@ extern int dir_notify_enable; #define READ 0 #define WRITE 1 #define READA 2 /* read-ahead - don't block if no resources */ +#define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ #define SPECIAL 4 /* For non-blockdevice requests in request queue */ #define READ_SYNC (READ | (1 << BIO_RW_SYNC)) #define WRITE_SYNC (WRITE | (1 << BIO_RW_SYNC)) -- cgit v1.2.3 From d0aaff9796c3310326d10da44fc0faed352a1d29 Mon Sep 17 00:00:00 2001 From: Prasanna S Panchamukhi Date: Tue, 6 Sep 2005 15:19:26 -0700 Subject: [PATCH] Kprobes: prevent possible race conditions generic There are possible race conditions if probes are placed on routines within the kprobes files and routines used by the kprobes. For example if you put probe on get_kprobe() routines, the system can hang while inserting probes on any routine such as do_fork(). Because while inserting probes on do_fork(), register_kprobes() routine grabs the kprobes spin lock and executes get_kprobe() routine and to handle probe of get_kprobe(), kprobes_handler() gets executed and tries to grab kprobes spin lock, and spins forever. This patch avoids such possible race conditions by preventing probes on routines within the kprobes file and routines used by kprobes. I have modified the patches as per Andi Kleen's suggestion to move kprobes routines and other routines used by kprobes to a seperate section .kprobes.text. Also moved page fault and exception handlers, general protection fault to .kprobes.text section. These patches have been tested on i386, x86_64 and ppc64 architectures, also compiled on ia64 and sparc64 architectures. Signed-off-by: Prasanna S Panchamukhi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 3 +++ include/linux/linkage.h | 7 +++++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index e050fc2d4c26..e30afdca7917 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -42,6 +42,9 @@ #define KPROBE_REENTER 0x00000004 #define KPROBE_HIT_SSDONE 0x00000008 +/* Attach to insert probes on any functions which should be ignored*/ +#define __kprobes __attribute__((__section__(".kprobes.text"))) + struct kprobe; struct pt_regs; struct kretprobe; diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 338f7795d8a0..147eb01e0d4b 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -33,6 +33,13 @@ ALIGN; \ name: +#define KPROBE_ENTRY(name) \ + .section .kprobes.text, "ax"; \ + .globl name; \ + ALIGN; \ + name: + + #endif #define NORET_TYPE /**/ -- cgit v1.2.3 From 333fad5364d6b457c8d837f7d05802d2aaf8a961 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Thu, 8 Sep 2005 09:59:17 +0900 Subject: [IPV6]: Support several new sockopt / ancillary data in Advanced API (RFC3542). Support several new socket options / ancillary data: IPV6_RECVPKTINFO, IPV6_PKTINFO, IPV6_RECVHOPOPTS, IPV6_HOPOPTS, IPV6_RECVDSTOPTS, IPV6_DSTOPTS, IPV6_RTHDRDSTOPTS, IPV6_RECVRTHDR, IPV6_RTHDR, IPV6_RECVHOPOPTS, IPV6_HOPOPTS Old semantics are preserved as IPV6_2292xxxx so that we can maintain backward compatibility. Signed-off-by: YOSHIFUJI Hideaki --- include/linux/in6.h | 38 ++++++++++++++++++++++++++++++++------ include/linux/ipv6.h | 10 ++++++++-- 2 files changed, 40 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/in6.h b/include/linux/in6.h index dcf5720ffcbb..c11022f2f2ac 100644 --- a/include/linux/in6.h +++ b/include/linux/in6.h @@ -148,13 +148,13 @@ struct in6_flowlabel_req */ #define IPV6_ADDRFORM 1 -#define IPV6_PKTINFO 2 -#define IPV6_HOPOPTS 3 -#define IPV6_DSTOPTS 4 -#define IPV6_RTHDR 5 -#define IPV6_PKTOPTIONS 6 +#define IPV6_2292PKTINFO 2 +#define IPV6_2292HOPOPTS 3 +#define IPV6_2292DSTOPTS 4 +#define IPV6_2292RTHDR 5 +#define IPV6_2292PKTOPTIONS 6 #define IPV6_CHECKSUM 7 -#define IPV6_HOPLIMIT 8 +#define IPV6_2292HOPLIMIT 8 #define IPV6_NEXTHOP 9 #define IPV6_AUTHHDR 10 /* obsolete */ #define IPV6_FLOWINFO 11 @@ -198,4 +198,30 @@ struct in6_flowlabel_req * MCAST_MSFILTER 48 */ +/* RFC3542 advanced socket options (50-67) */ +#define IPV6_RECVPKTINFO 50 +#define IPV6_PKTINFO 51 +#if 0 +#define IPV6_RECVPATHMTU 52 +#define IPV6_PATHMTU 53 +#define IPV6_DONTFRAG 54 +#define IPV6_USE_MIN_MTU 55 +#endif +#define IPV6_RECVHOPOPTS 56 +#define IPV6_HOPOPTS 57 +#if 0 +#define IPV6_RECVRTHDRDSTOPTS 58 /* Unused, see net/ipv6/datagram.c */ +#endif +#define IPV6_RTHDRDSTOPTS 59 +#define IPV6_RECVRTHDR 60 +#define IPV6_RTHDR 61 +#define IPV6_RECVDSTOPTS 62 +#define IPV6_DSTOPTS 63 +#define IPV6_RECVHOPLIMIT 64 +#define IPV6_HOPLIMIT 65 +#if 0 +#define IPV6_RECVTCLASS 66 +#define IPV6_TCLASS 67 +#endif + #endif diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 3c7dbc6a0a70..2581f1c94df5 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -189,6 +189,7 @@ struct inet6_skb_parm { __u16 dst0; __u16 srcrt; __u16 dst1; + __u16 lastopt; }; #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) @@ -234,14 +235,19 @@ struct ipv6_pinfo { /* pktoption flags */ union { struct { - __u8 srcrt:2, + __u16 srcrt:2, + osrcrt:2, rxinfo:1, + rxoinfo:1, rxhlim:1, + rxohlim:1, hopopts:1, + ohopopts:1, dstopts:1, + odstopts:1, rxflow:1; } bits; - __u8 all; + __u16 all; } rxopt; /* sockopt flags */ -- cgit v1.2.3 From 41a1f8ea4fbfcdc4232f023732584aae2220de31 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Thu, 8 Sep 2005 10:19:03 +0900 Subject: [IPV6]: Support IPV6_{RECV,}TCLASS socket options / ancillary data. Based on patch from David L Stevens Signed-off-by: David L Stevens Signed-off-by: YOSHIFUJI Hideaki --- include/linux/in6.h | 2 -- include/linux/ipv6.h | 5 ++++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/in6.h b/include/linux/in6.h index c11022f2f2ac..bd32b79d6295 100644 --- a/include/linux/in6.h +++ b/include/linux/in6.h @@ -219,9 +219,7 @@ struct in6_flowlabel_req #define IPV6_DSTOPTS 63 #define IPV6_RECVHOPLIMIT 64 #define IPV6_HOPLIMIT 65 -#if 0 #define IPV6_RECVTCLASS 66 #define IPV6_TCLASS 67 -#endif #endif diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 2581f1c94df5..6c5f7b39a4b0 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -245,7 +245,8 @@ struct ipv6_pinfo { ohopopts:1, dstopts:1, odstopts:1, - rxflow:1; + rxflow:1, + rxtclass:1; } bits; __u16 all; } rxopt; @@ -256,6 +257,7 @@ struct ipv6_pinfo { sndflow:1, pmtudisc:2, ipv6only:1; + __u8 tclass; __u32 dst_cookie; @@ -269,6 +271,7 @@ struct ipv6_pinfo { struct ipv6_txoptions *opt; struct rt6_info *rt; int hop_limit; + int tclass; } cork; }; -- cgit v1.2.3 From 34bb61f9ddabd7a7f909cbfb05592eb775f6662a Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Tue, 6 Sep 2005 16:56:51 -0700 Subject: [PATCH] fix klist semantics for lists which have elements removed on traversal The problem is that klists claim to provide semantics for safe traversal of lists which are being modified. The failure case is when traversal of a list causes element removal (a fairly common case). The issue is that although the list node is refcounted, if it is embedded in an object (which is universally the case), then the object will be freed regardless of the klist refcount leading to slab corruption because the klist iterator refers to the prior element to get the next. The solution is to make the klist take and release references to the embedding object meaning that the embedding object won't be released until the list relinquishes the reference to it. (akpm: fast-track this because it's needed for the 2.6.13 scsi merge) Signed-off-by: James Bottomley Signed-off-by: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/klist.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/klist.h b/include/linux/klist.h index c4d1fae4dd89..74071254c9d3 100644 --- a/include/linux/klist.h +++ b/include/linux/klist.h @@ -17,15 +17,17 @@ #include #include - +struct klist_node; struct klist { spinlock_t k_lock; struct list_head k_list; + void (*get)(struct klist_node *); + void (*put)(struct klist_node *); }; -extern void klist_init(struct klist * k); - +extern void klist_init(struct klist * k, void (*get)(struct klist_node *), + void (*put)(struct klist_node *)); struct klist_node { struct klist * n_klist; -- cgit v1.2.3 From 6df29debb7fc04ac3f92038c57437f40bab4e72d Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 8 Sep 2005 16:04:41 +0100 Subject: [SERIAL] Use an enum for serial8250 platform device IDs Rather than hard-coding the platform device IDs, enumerate them. We don't particularly care about the actual ID we get, just as long as they're unique. Signed-off-by: Russell King --- include/linux/serial_8250.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index d8a023d804d4..317a979b24de 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -29,6 +29,21 @@ struct plat_serial8250_port { unsigned int flags; /* UPF_* flags */ }; +/* + * Allocate 8250 platform device IDs. Nothing is implied by + * the numbering here, except for the legacy entry being -1. + */ +enum { + PLAT8250_DEV_LEGACY = -1, + PLAT8250_DEV_PLATFORM, + PLAT8250_DEV_PLATFORM1, + PLAT8250_DEV_FOURPORT, + PLAT8250_DEV_ACCENT, + PLAT8250_DEV_BOCA, + PLAT8250_DEV_HUB6, + PLAT8250_DEV_MCA, +}; + /* * This should be used by drivers which want to register * their own 8250 ports without registering their own -- cgit v1.2.3 From 8dc003359cc3996abad9e53a7b2280b272610283 Mon Sep 17 00:00:00 2001 From: Richard Purdie Date: Thu, 8 Sep 2005 17:53:01 +0100 Subject: [MMC] Allow detection/removal to be delayed Change mmc_detect_change() to take a delay argument such that the detection of card insertions and removals can be delayed according to the requirements of the host driver or platform. Signed-off-by: Richard Purdie Signed-off-by: Russell King --- include/linux/mmc/host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 6014160d9c06..c5d73c0cf6bb 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -123,7 +123,7 @@ extern void mmc_free_host(struct mmc_host *); extern int mmc_suspend_host(struct mmc_host *, pm_message_t); extern int mmc_resume_host(struct mmc_host *); -extern void mmc_detect_change(struct mmc_host *); +extern void mmc_detect_change(struct mmc_host *, unsigned long delay); extern void mmc_request_done(struct mmc_host *, struct mmc_request *); #endif -- cgit v1.2.3 From 0e4e4220f10bf8f58a8606f0cb28538088c64b1a Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 8 Sep 2005 12:32:03 -0700 Subject: [NET]: Optimize pskb_trim_rcsum() Since packets almost never contain extra garbage at the end, it is worthwhile to optimize for that case. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index da7da9c0ed1b..2741c0c55e83 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1167,7 +1167,7 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { - if (len >= skb->len) + if (likely(len >= skb->len)) return 0; if (skb->ip_summed == CHECKSUM_HW) skb->ip_summed = CHECKSUM_NONE; -- cgit v1.2.3 From 7657ec1fcb69e266ab876af56332d0c484ca6d00 Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Wed, 17 Aug 2005 15:17:26 +0400 Subject: [PATCH] lib/crc16: added crc16 algorithm. Add the crc16 routines, as used by w1 devices. Signed-off-by: Ben Gardner Signed-off-by: Evgeniy Polyakov Signed-off-by: Greg Kroah-Hartman --- include/linux/crc16.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 include/linux/crc16.h (limited to 'include/linux') diff --git a/include/linux/crc16.h b/include/linux/crc16.h new file mode 100644 index 000000000000..bdedf825b04a --- /dev/null +++ b/include/linux/crc16.h @@ -0,0 +1,44 @@ +/* + * crc16.h - CRC-16 routine + * + * Implements the standard CRC-16, as used with 1-wire devices: + * Width 16 + * Poly 0x8005 (x^16 + x^15 + x^2 + 1) + * Init 0 + * + * For 1-wire devices, the CRC is stored inverted, LSB-first + * + * Example buffer with the CRC attached: + * 31 32 33 34 35 36 37 38 39 C2 44 + * + * The CRC over a buffer with the CRC attached is 0xB001. + * So, if (crc16(0, buf, size) == 0xB001) then the buffer is valid. + * + * Refer to "Application Note 937: Book of iButton Standards" for details. + * http://www.maxim-ic.com/appnotes.cfm/appnote_number/937 + * + * Copyright (c) 2005 Ben Gardner + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#ifndef __CRC16_H +#define __CRC16_H + +#include + +#define CRC16_INIT 0 +#define CRC16_VALID 0xb001 + +extern u16 const crc16_table[256]; + +extern u16 crc16(u16 crc, const u8 *buffer, size_t len); + +static inline u16 crc16_byte(u16 crc, const u8 data) +{ + return (crc >> 8) ^ crc16_table[(crc ^ data) & 0xff]; +} + +#endif /* __CRC16_H */ + -- cgit v1.2.3 From 01357dcac62ac028de65a1c315eb75c530c8a5d6 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 8 Sep 2005 22:46:00 +0100 Subject: [MMC] Ensure correct mmc_priv() behaviour mmc_priv() has some nasty effects if the wrong pointer type is passed to it. Introduce type checking, which also means we get the right type. Also add an additional member to mmc_host which is used to align host-private data appropriately. Signed-off-by: Russell King --- include/linux/mmc/host.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index c5d73c0cf6bb..c1f021eddffa 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -109,6 +109,8 @@ struct mmc_host { struct mmc_card *card_selected; /* the selected MMC card */ struct work_struct detect; + + unsigned long private[0] ____cacheline_aligned; }; extern struct mmc_host *mmc_alloc_host(int extra, struct device *); @@ -116,7 +118,11 @@ extern int mmc_add_host(struct mmc_host *); extern void mmc_remove_host(struct mmc_host *); extern void mmc_free_host(struct mmc_host *); -#define mmc_priv(x) ((void *)((x) + 1)) +static inline void *mmc_priv(struct mmc_host *host) +{ + return (void *)host->private; +} + #define mmc_dev(x) ((x)->dev) #define mmc_hostname(x) ((x)->class_dev.class_id) -- cgit v1.2.3 From 4e1491847ef5ca1c5a661601d5f96dcb7d90d2f0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 8 Sep 2005 14:47:12 -0700 Subject: Fix up ARM serial driver compile failure Proud member of Uglyhacks'R'US. Acked-by: David S. Miller Acked-by: Russell King Signed-off-by: Linus Torvalds --- include/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 9b12fe731612..27db8da43aa4 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -401,6 +401,9 @@ uart_handle_sysrq_char(struct uart_port *port, unsigned int ch, #endif return 0; } +#ifndef SUPPORT_SYSRQ +#define uart_handle_sysrq_char(port,ch,regs) uart_handle_sysrq_char(port, 0, NULL) +#endif /* * We do the SysRQ and SAK checking like this... -- cgit v1.2.3 From d42c69972b853fd33a26c8c7405624be41a22136 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 6 Jul 2005 19:56:03 +0200 Subject: [PATCH] PCI: Run PCI driver initialization on local node Run PCI driver initialization on local node Instead of adding messy kmalloc_node()s everywhere run the PCI driver probe on the node local to the device. This would not have helped for IDE, but should for other more clean drivers that do more initialization in probe(). It won't help for drivers that do most of the work on first open (like many network drivers) Signed-off-by: Andi Kleen Signed-off-by: Greg Kroah-Hartman --- include/linux/mempolicy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 94a46f38c532..58385ee1c0ac 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -155,6 +155,7 @@ struct mempolicy *get_vma_policy(struct task_struct *task, extern void numa_default_policy(void); extern void numa_policy_init(void); +extern struct mempolicy default_policy; #else -- cgit v1.2.3 From 74d863ee8a9da2b0f31e0f977daf127807b2e9d2 Mon Sep 17 00:00:00 2001 From: "akpm@osdl.org" Date: Mon, 25 Jul 2005 23:28:14 -0700 Subject: [PATCH] PCI: Move PCI fixup data into r/o section Make PCI fixup data const, so it'll end up in a r/o section. This also fixes the conversion into ECOFF which gets broken by too many changes between r/w and r/o sections. Call it a hack but it's a change that's correct by itself. Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index bc4c40000c0d..025bfc39771d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1067,7 +1067,7 @@ enum pci_fixup_pass { /* Anonymous variables would be nice... */ #define DECLARE_PCI_FIXUP_SECTION(section, name, vendor, device, hook) \ - static struct pci_fixup __pci_fixup_##name __attribute_used__ \ + static const struct pci_fixup __pci_fixup_##name __attribute_used__ \ __attribute__((__section__(#section))) = { vendor, device, hook }; #define DECLARE_PCI_FIXUP_EARLY(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_early, \ -- cgit v1.2.3 From 982245f01734e9d5a3ab98b2b2e9761ae7719094 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sun, 17 Jul 2005 04:22:20 +0200 Subject: [PATCH] PCI: remove CONFIG_PCI_NAMES This patch removes CONFIG_PCI_NAMES. Signed-off-by: Adrian Bunk Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 025bfc39771d..e7a228f2fdde 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -562,11 +562,6 @@ struct pci_dev { struct bin_attribute *rom_attr; /* attribute descriptor for sysfs ROM entry */ int rom_attr_enabled; /* has display of the rom attribute been enabled? */ struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for resources */ -#ifdef CONFIG_PCI_NAMES -#define PCI_NAME_SIZE 255 -#define PCI_NAME_HALF __stringify(43) /* less than half to handle slop */ - char pretty_name[PCI_NAME_SIZE]; /* pretty name for users to see */ -#endif }; #define pci_dev_g(n) list_entry(n, struct pci_dev, global_list) @@ -749,8 +744,6 @@ int pci_scan_slot(struct pci_bus *bus, int devfn); struct pci_dev * pci_scan_single_device(struct pci_bus *bus, int devfn); unsigned int pci_scan_child_bus(struct pci_bus *bus); void pci_bus_add_device(struct pci_dev *dev); -void pci_name_device(struct pci_dev *dev); -char *pci_class_name(u32 class); void pci_read_bridge_bases(struct pci_bus *child); struct resource *pci_find_parent_resource(const struct pci_dev *dev, struct resource *res); int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge); @@ -1025,13 +1018,6 @@ static inline char *pci_name(struct pci_dev *pdev) return pdev->dev.bus_id; } -/* Some archs want to see the pretty pci name, so use this macro */ -#ifdef CONFIG_PCI_NAMES -#define pci_pretty_name(dev) ((dev)->pretty_name) -#else -#define pci_pretty_name(dev) "" -#endif - /* Some archs don't want to expose struct resource to userland as-is * in sysfs and /proc -- cgit v1.2.3 From 4352dfd5cd9172f1ee425924a463b43e6157b840 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 28 Jul 2005 11:37:33 -0700 Subject: [PATCH] PCI: clean up pci.h and split pci register info to separate header file. This cleans up some of the #ifdef CONFIG_PCI stuff up, and moves the pci register info out to a separate file, where it belongs. Eventually we can stop including this file from within pci.h, but lots of code needs to be audited first. Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 488 +++-------------------------------------------- include/linux/pci_regs.h | 447 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 477 insertions(+), 458 deletions(-) create mode 100644 include/linux/pci_regs.h (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index e7a228f2fdde..830c1bae56cc 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -19,436 +19,10 @@ #include -/* - * Under PCI, each device has 256 bytes of configuration address space, - * of which the first 64 bytes are standardized as follows: - */ -#define PCI_VENDOR_ID 0x00 /* 16 bits */ -#define PCI_DEVICE_ID 0x02 /* 16 bits */ -#define PCI_COMMAND 0x04 /* 16 bits */ -#define PCI_COMMAND_IO 0x1 /* Enable response in I/O space */ -#define PCI_COMMAND_MEMORY 0x2 /* Enable response in Memory space */ -#define PCI_COMMAND_MASTER 0x4 /* Enable bus mastering */ -#define PCI_COMMAND_SPECIAL 0x8 /* Enable response to special cycles */ -#define PCI_COMMAND_INVALIDATE 0x10 /* Use memory write and invalidate */ -#define PCI_COMMAND_VGA_PALETTE 0x20 /* Enable palette snooping */ -#define PCI_COMMAND_PARITY 0x40 /* Enable parity checking */ -#define PCI_COMMAND_WAIT 0x80 /* Enable address/data stepping */ -#define PCI_COMMAND_SERR 0x100 /* Enable SERR */ -#define PCI_COMMAND_FAST_BACK 0x200 /* Enable back-to-back writes */ -#define PCI_COMMAND_INTX_DISABLE 0x400 /* INTx Emulation Disable */ - -#define PCI_STATUS 0x06 /* 16 bits */ -#define PCI_STATUS_CAP_LIST 0x10 /* Support Capability List */ -#define PCI_STATUS_66MHZ 0x20 /* Support 66 Mhz PCI 2.1 bus */ -#define PCI_STATUS_UDF 0x40 /* Support User Definable Features [obsolete] */ -#define PCI_STATUS_FAST_BACK 0x80 /* Accept fast-back to back */ -#define PCI_STATUS_PARITY 0x100 /* Detected parity error */ -#define PCI_STATUS_DEVSEL_MASK 0x600 /* DEVSEL timing */ -#define PCI_STATUS_DEVSEL_FAST 0x000 -#define PCI_STATUS_DEVSEL_MEDIUM 0x200 -#define PCI_STATUS_DEVSEL_SLOW 0x400 -#define PCI_STATUS_SIG_TARGET_ABORT 0x800 /* Set on target abort */ -#define PCI_STATUS_REC_TARGET_ABORT 0x1000 /* Master ack of " */ -#define PCI_STATUS_REC_MASTER_ABORT 0x2000 /* Set on master abort */ -#define PCI_STATUS_SIG_SYSTEM_ERROR 0x4000 /* Set when we drive SERR */ -#define PCI_STATUS_DETECTED_PARITY 0x8000 /* Set on parity error */ - -#define PCI_CLASS_REVISION 0x08 /* High 24 bits are class, low 8 - revision */ -#define PCI_REVISION_ID 0x08 /* Revision ID */ -#define PCI_CLASS_PROG 0x09 /* Reg. Level Programming Interface */ -#define PCI_CLASS_DEVICE 0x0a /* Device class */ - -#define PCI_CACHE_LINE_SIZE 0x0c /* 8 bits */ -#define PCI_LATENCY_TIMER 0x0d /* 8 bits */ -#define PCI_HEADER_TYPE 0x0e /* 8 bits */ -#define PCI_HEADER_TYPE_NORMAL 0 -#define PCI_HEADER_TYPE_BRIDGE 1 -#define PCI_HEADER_TYPE_CARDBUS 2 - -#define PCI_BIST 0x0f /* 8 bits */ -#define PCI_BIST_CODE_MASK 0x0f /* Return result */ -#define PCI_BIST_START 0x40 /* 1 to start BIST, 2 secs or less */ -#define PCI_BIST_CAPABLE 0x80 /* 1 if BIST capable */ - -/* - * Base addresses specify locations in memory or I/O space. - * Decoded size can be determined by writing a value of - * 0xffffffff to the register, and reading it back. Only - * 1 bits are decoded. - */ -#define PCI_BASE_ADDRESS_0 0x10 /* 32 bits */ -#define PCI_BASE_ADDRESS_1 0x14 /* 32 bits [htype 0,1 only] */ -#define PCI_BASE_ADDRESS_2 0x18 /* 32 bits [htype 0 only] */ -#define PCI_BASE_ADDRESS_3 0x1c /* 32 bits */ -#define PCI_BASE_ADDRESS_4 0x20 /* 32 bits */ -#define PCI_BASE_ADDRESS_5 0x24 /* 32 bits */ -#define PCI_BASE_ADDRESS_SPACE 0x01 /* 0 = memory, 1 = I/O */ -#define PCI_BASE_ADDRESS_SPACE_IO 0x01 -#define PCI_BASE_ADDRESS_SPACE_MEMORY 0x00 -#define PCI_BASE_ADDRESS_MEM_TYPE_MASK 0x06 -#define PCI_BASE_ADDRESS_MEM_TYPE_32 0x00 /* 32 bit address */ -#define PCI_BASE_ADDRESS_MEM_TYPE_1M 0x02 /* Below 1M [obsolete] */ -#define PCI_BASE_ADDRESS_MEM_TYPE_64 0x04 /* 64 bit address */ -#define PCI_BASE_ADDRESS_MEM_PREFETCH 0x08 /* prefetchable? */ -#define PCI_BASE_ADDRESS_MEM_MASK (~0x0fUL) -#define PCI_BASE_ADDRESS_IO_MASK (~0x03UL) -/* bit 1 is reserved if address_space = 1 */ - -/* Header type 0 (normal devices) */ -#define PCI_CARDBUS_CIS 0x28 -#define PCI_SUBSYSTEM_VENDOR_ID 0x2c -#define PCI_SUBSYSTEM_ID 0x2e -#define PCI_ROM_ADDRESS 0x30 /* Bits 31..11 are address, 10..1 reserved */ -#define PCI_ROM_ADDRESS_ENABLE 0x01 -#define PCI_ROM_ADDRESS_MASK (~0x7ffUL) - -#define PCI_CAPABILITY_LIST 0x34 /* Offset of first capability list entry */ - -/* 0x35-0x3b are reserved */ -#define PCI_INTERRUPT_LINE 0x3c /* 8 bits */ -#define PCI_INTERRUPT_PIN 0x3d /* 8 bits */ -#define PCI_MIN_GNT 0x3e /* 8 bits */ -#define PCI_MAX_LAT 0x3f /* 8 bits */ - -/* Header type 1 (PCI-to-PCI bridges) */ -#define PCI_PRIMARY_BUS 0x18 /* Primary bus number */ -#define PCI_SECONDARY_BUS 0x19 /* Secondary bus number */ -#define PCI_SUBORDINATE_BUS 0x1a /* Highest bus number behind the bridge */ -#define PCI_SEC_LATENCY_TIMER 0x1b /* Latency timer for secondary interface */ -#define PCI_IO_BASE 0x1c /* I/O range behind the bridge */ -#define PCI_IO_LIMIT 0x1d -#define PCI_IO_RANGE_TYPE_MASK 0x0fUL /* I/O bridging type */ -#define PCI_IO_RANGE_TYPE_16 0x00 -#define PCI_IO_RANGE_TYPE_32 0x01 -#define PCI_IO_RANGE_MASK (~0x0fUL) -#define PCI_SEC_STATUS 0x1e /* Secondary status register, only bit 14 used */ -#define PCI_MEMORY_BASE 0x20 /* Memory range behind */ -#define PCI_MEMORY_LIMIT 0x22 -#define PCI_MEMORY_RANGE_TYPE_MASK 0x0fUL -#define PCI_MEMORY_RANGE_MASK (~0x0fUL) -#define PCI_PREF_MEMORY_BASE 0x24 /* Prefetchable memory range behind */ -#define PCI_PREF_MEMORY_LIMIT 0x26 -#define PCI_PREF_RANGE_TYPE_MASK 0x0fUL -#define PCI_PREF_RANGE_TYPE_32 0x00 -#define PCI_PREF_RANGE_TYPE_64 0x01 -#define PCI_PREF_RANGE_MASK (~0x0fUL) -#define PCI_PREF_BASE_UPPER32 0x28 /* Upper half of prefetchable memory range */ -#define PCI_PREF_LIMIT_UPPER32 0x2c -#define PCI_IO_BASE_UPPER16 0x30 /* Upper half of I/O addresses */ -#define PCI_IO_LIMIT_UPPER16 0x32 -/* 0x34 same as for htype 0 */ -/* 0x35-0x3b is reserved */ -#define PCI_ROM_ADDRESS1 0x38 /* Same as PCI_ROM_ADDRESS, but for htype 1 */ -/* 0x3c-0x3d are same as for htype 0 */ -#define PCI_BRIDGE_CONTROL 0x3e -#define PCI_BRIDGE_CTL_PARITY 0x01 /* Enable parity detection on secondary interface */ -#define PCI_BRIDGE_CTL_SERR 0x02 /* The same for SERR forwarding */ -#define PCI_BRIDGE_CTL_NO_ISA 0x04 /* Disable bridging of ISA ports */ -#define PCI_BRIDGE_CTL_VGA 0x08 /* Forward VGA addresses */ -#define PCI_BRIDGE_CTL_MASTER_ABORT 0x20 /* Report master aborts */ -#define PCI_BRIDGE_CTL_BUS_RESET 0x40 /* Secondary bus reset */ -#define PCI_BRIDGE_CTL_FAST_BACK 0x80 /* Fast Back2Back enabled on secondary interface */ - -/* Header type 2 (CardBus bridges) */ -#define PCI_CB_CAPABILITY_LIST 0x14 -/* 0x15 reserved */ -#define PCI_CB_SEC_STATUS 0x16 /* Secondary status */ -#define PCI_CB_PRIMARY_BUS 0x18 /* PCI bus number */ -#define PCI_CB_CARD_BUS 0x19 /* CardBus bus number */ -#define PCI_CB_SUBORDINATE_BUS 0x1a /* Subordinate bus number */ -#define PCI_CB_LATENCY_TIMER 0x1b /* CardBus latency timer */ -#define PCI_CB_MEMORY_BASE_0 0x1c -#define PCI_CB_MEMORY_LIMIT_0 0x20 -#define PCI_CB_MEMORY_BASE_1 0x24 -#define PCI_CB_MEMORY_LIMIT_1 0x28 -#define PCI_CB_IO_BASE_0 0x2c -#define PCI_CB_IO_BASE_0_HI 0x2e -#define PCI_CB_IO_LIMIT_0 0x30 -#define PCI_CB_IO_LIMIT_0_HI 0x32 -#define PCI_CB_IO_BASE_1 0x34 -#define PCI_CB_IO_BASE_1_HI 0x36 -#define PCI_CB_IO_LIMIT_1 0x38 -#define PCI_CB_IO_LIMIT_1_HI 0x3a -#define PCI_CB_IO_RANGE_MASK (~0x03UL) -/* 0x3c-0x3d are same as for htype 0 */ -#define PCI_CB_BRIDGE_CONTROL 0x3e -#define PCI_CB_BRIDGE_CTL_PARITY 0x01 /* Similar to standard bridge control register */ -#define PCI_CB_BRIDGE_CTL_SERR 0x02 -#define PCI_CB_BRIDGE_CTL_ISA 0x04 -#define PCI_CB_BRIDGE_CTL_VGA 0x08 -#define PCI_CB_BRIDGE_CTL_MASTER_ABORT 0x20 -#define PCI_CB_BRIDGE_CTL_CB_RESET 0x40 /* CardBus reset */ -#define PCI_CB_BRIDGE_CTL_16BIT_INT 0x80 /* Enable interrupt for 16-bit cards */ -#define PCI_CB_BRIDGE_CTL_PREFETCH_MEM0 0x100 /* Prefetch enable for both memory regions */ -#define PCI_CB_BRIDGE_CTL_PREFETCH_MEM1 0x200 -#define PCI_CB_BRIDGE_CTL_POST_WRITES 0x400 -#define PCI_CB_SUBSYSTEM_VENDOR_ID 0x40 -#define PCI_CB_SUBSYSTEM_ID 0x42 -#define PCI_CB_LEGACY_MODE_BASE 0x44 /* 16-bit PC Card legacy mode base address (ExCa) */ -/* 0x48-0x7f reserved */ - -/* Capability lists */ - -#define PCI_CAP_LIST_ID 0 /* Capability ID */ -#define PCI_CAP_ID_PM 0x01 /* Power Management */ -#define PCI_CAP_ID_AGP 0x02 /* Accelerated Graphics Port */ -#define PCI_CAP_ID_VPD 0x03 /* Vital Product Data */ -#define PCI_CAP_ID_SLOTID 0x04 /* Slot Identification */ -#define PCI_CAP_ID_MSI 0x05 /* Message Signalled Interrupts */ -#define PCI_CAP_ID_CHSWP 0x06 /* CompactPCI HotSwap */ -#define PCI_CAP_ID_PCIX 0x07 /* PCI-X */ -#define PCI_CAP_ID_SHPC 0x0C /* PCI Standard Hot-Plug Controller */ -#define PCI_CAP_ID_EXP 0x10 /* PCI Express */ -#define PCI_CAP_ID_MSIX 0x11 /* MSI-X */ -#define PCI_CAP_LIST_NEXT 1 /* Next capability in the list */ -#define PCI_CAP_FLAGS 2 /* Capability defined flags (16 bits) */ -#define PCI_CAP_SIZEOF 4 - -/* Power Management Registers */ - -#define PCI_PM_PMC 2 /* PM Capabilities Register */ -#define PCI_PM_CAP_VER_MASK 0x0007 /* Version */ -#define PCI_PM_CAP_PME_CLOCK 0x0008 /* PME clock required */ -#define PCI_PM_CAP_RESERVED 0x0010 /* Reserved field */ -#define PCI_PM_CAP_DSI 0x0020 /* Device specific initialization */ -#define PCI_PM_CAP_AUX_POWER 0x01C0 /* Auxilliary power support mask */ -#define PCI_PM_CAP_D1 0x0200 /* D1 power state support */ -#define PCI_PM_CAP_D2 0x0400 /* D2 power state support */ -#define PCI_PM_CAP_PME 0x0800 /* PME pin supported */ -#define PCI_PM_CAP_PME_MASK 0xF800 /* PME Mask of all supported states */ -#define PCI_PM_CAP_PME_D0 0x0800 /* PME# from D0 */ -#define PCI_PM_CAP_PME_D1 0x1000 /* PME# from D1 */ -#define PCI_PM_CAP_PME_D2 0x2000 /* PME# from D2 */ -#define PCI_PM_CAP_PME_D3 0x4000 /* PME# from D3 (hot) */ -#define PCI_PM_CAP_PME_D3cold 0x8000 /* PME# from D3 (cold) */ -#define PCI_PM_CTRL 4 /* PM control and status register */ -#define PCI_PM_CTRL_STATE_MASK 0x0003 /* Current power state (D0 to D3) */ -#define PCI_PM_CTRL_PME_ENABLE 0x0100 /* PME pin enable */ -#define PCI_PM_CTRL_DATA_SEL_MASK 0x1e00 /* Data select (??) */ -#define PCI_PM_CTRL_DATA_SCALE_MASK 0x6000 /* Data scale (??) */ -#define PCI_PM_CTRL_PME_STATUS 0x8000 /* PME pin status */ -#define PCI_PM_PPB_EXTENSIONS 6 /* PPB support extensions (??) */ -#define PCI_PM_PPB_B2_B3 0x40 /* Stop clock when in D3hot (??) */ -#define PCI_PM_BPCC_ENABLE 0x80 /* Bus power/clock control enable (??) */ -#define PCI_PM_DATA_REGISTER 7 /* (??) */ -#define PCI_PM_SIZEOF 8 - -/* AGP registers */ - -#define PCI_AGP_VERSION 2 /* BCD version number */ -#define PCI_AGP_RFU 3 /* Rest of capability flags */ -#define PCI_AGP_STATUS 4 /* Status register */ -#define PCI_AGP_STATUS_RQ_MASK 0xff000000 /* Maximum number of requests - 1 */ -#define PCI_AGP_STATUS_SBA 0x0200 /* Sideband addressing supported */ -#define PCI_AGP_STATUS_64BIT 0x0020 /* 64-bit addressing supported */ -#define PCI_AGP_STATUS_FW 0x0010 /* FW transfers supported */ -#define PCI_AGP_STATUS_RATE4 0x0004 /* 4x transfer rate supported */ -#define PCI_AGP_STATUS_RATE2 0x0002 /* 2x transfer rate supported */ -#define PCI_AGP_STATUS_RATE1 0x0001 /* 1x transfer rate supported */ -#define PCI_AGP_COMMAND 8 /* Control register */ -#define PCI_AGP_COMMAND_RQ_MASK 0xff000000 /* Master: Maximum number of requests */ -#define PCI_AGP_COMMAND_SBA 0x0200 /* Sideband addressing enabled */ -#define PCI_AGP_COMMAND_AGP 0x0100 /* Allow processing of AGP transactions */ -#define PCI_AGP_COMMAND_64BIT 0x0020 /* Allow processing of 64-bit addresses */ -#define PCI_AGP_COMMAND_FW 0x0010 /* Force FW transfers */ -#define PCI_AGP_COMMAND_RATE4 0x0004 /* Use 4x rate */ -#define PCI_AGP_COMMAND_RATE2 0x0002 /* Use 2x rate */ -#define PCI_AGP_COMMAND_RATE1 0x0001 /* Use 1x rate */ -#define PCI_AGP_SIZEOF 12 - -/* Vital Product Data */ - -#define PCI_VPD_ADDR 2 /* Address to access (15 bits!) */ -#define PCI_VPD_ADDR_MASK 0x7fff /* Address mask */ -#define PCI_VPD_ADDR_F 0x8000 /* Write 0, 1 indicates completion */ -#define PCI_VPD_DATA 4 /* 32-bits of data returned here */ - -/* Slot Identification */ - -#define PCI_SID_ESR 2 /* Expansion Slot Register */ -#define PCI_SID_ESR_NSLOTS 0x1f /* Number of expansion slots available */ -#define PCI_SID_ESR_FIC 0x20 /* First In Chassis Flag */ -#define PCI_SID_CHASSIS_NR 3 /* Chassis Number */ - -/* Message Signalled Interrupts registers */ - -#define PCI_MSI_FLAGS 2 /* Various flags */ -#define PCI_MSI_FLAGS_64BIT 0x80 /* 64-bit addresses allowed */ -#define PCI_MSI_FLAGS_QSIZE 0x70 /* Message queue size configured */ -#define PCI_MSI_FLAGS_QMASK 0x0e /* Maximum queue size available */ -#define PCI_MSI_FLAGS_ENABLE 0x01 /* MSI feature enabled */ -#define PCI_MSI_FLAGS_MASKBIT 0x100 /* 64-bit mask bits allowed */ -#define PCI_MSI_RFU 3 /* Rest of capability flags */ -#define PCI_MSI_ADDRESS_LO 4 /* Lower 32 bits */ -#define PCI_MSI_ADDRESS_HI 8 /* Upper 32 bits (if PCI_MSI_FLAGS_64BIT set) */ -#define PCI_MSI_DATA_32 8 /* 16 bits of data for 32-bit devices */ -#define PCI_MSI_DATA_64 12 /* 16 bits of data for 64-bit devices */ -#define PCI_MSI_MASK_BIT 16 /* Mask bits register */ - -/* CompactPCI Hotswap Register */ - -#define PCI_CHSWP_CSR 2 /* Control and Status Register */ -#define PCI_CHSWP_DHA 0x01 /* Device Hiding Arm */ -#define PCI_CHSWP_EIM 0x02 /* ENUM# Signal Mask */ -#define PCI_CHSWP_PIE 0x04 /* Pending Insert or Extract */ -#define PCI_CHSWP_LOO 0x08 /* LED On / Off */ -#define PCI_CHSWP_PI 0x30 /* Programming Interface */ -#define PCI_CHSWP_EXT 0x40 /* ENUM# status - extraction */ -#define PCI_CHSWP_INS 0x80 /* ENUM# status - insertion */ - -/* PCI-X registers */ - -#define PCI_X_CMD 2 /* Modes & Features */ -#define PCI_X_CMD_DPERR_E 0x0001 /* Data Parity Error Recovery Enable */ -#define PCI_X_CMD_ERO 0x0002 /* Enable Relaxed Ordering */ -#define PCI_X_CMD_MAX_READ 0x000c /* Max Memory Read Byte Count */ -#define PCI_X_CMD_MAX_SPLIT 0x0070 /* Max Outstanding Split Transactions */ -#define PCI_X_CMD_VERSION(x) (((x) >> 12) & 3) /* Version */ -#define PCI_X_STATUS 4 /* PCI-X capabilities */ -#define PCI_X_STATUS_DEVFN 0x000000ff /* A copy of devfn */ -#define PCI_X_STATUS_BUS 0x0000ff00 /* A copy of bus nr */ -#define PCI_X_STATUS_64BIT 0x00010000 /* 64-bit device */ -#define PCI_X_STATUS_133MHZ 0x00020000 /* 133 MHz capable */ -#define PCI_X_STATUS_SPL_DISC 0x00040000 /* Split Completion Discarded */ -#define PCI_X_STATUS_UNX_SPL 0x00080000 /* Unexpected Split Completion */ -#define PCI_X_STATUS_COMPLEX 0x00100000 /* Device Complexity */ -#define PCI_X_STATUS_MAX_READ 0x00600000 /* Designed Max Memory Read Count */ -#define PCI_X_STATUS_MAX_SPLIT 0x03800000 /* Designed Max Outstanding Split Transactions */ -#define PCI_X_STATUS_MAX_CUM 0x1c000000 /* Designed Max Cumulative Read Size */ -#define PCI_X_STATUS_SPL_ERR 0x20000000 /* Rcvd Split Completion Error Msg */ -#define PCI_X_STATUS_266MHZ 0x40000000 /* 266 MHz capable */ -#define PCI_X_STATUS_533MHZ 0x80000000 /* 533 MHz capable */ - -/* PCI Express capability registers */ - -#define PCI_EXP_FLAGS 2 /* Capabilities register */ -#define PCI_EXP_FLAGS_VERS 0x000f /* Capability version */ -#define PCI_EXP_FLAGS_TYPE 0x00f0 /* Device/Port type */ -#define PCI_EXP_TYPE_ENDPOINT 0x0 /* Express Endpoint */ -#define PCI_EXP_TYPE_LEG_END 0x1 /* Legacy Endpoint */ -#define PCI_EXP_TYPE_ROOT_PORT 0x4 /* Root Port */ -#define PCI_EXP_TYPE_UPSTREAM 0x5 /* Upstream Port */ -#define PCI_EXP_TYPE_DOWNSTREAM 0x6 /* Downstream Port */ -#define PCI_EXP_TYPE_PCI_BRIDGE 0x7 /* PCI/PCI-X Bridge */ -#define PCI_EXP_FLAGS_SLOT 0x0100 /* Slot implemented */ -#define PCI_EXP_FLAGS_IRQ 0x3e00 /* Interrupt message number */ -#define PCI_EXP_DEVCAP 4 /* Device capabilities */ -#define PCI_EXP_DEVCAP_PAYLOAD 0x07 /* Max_Payload_Size */ -#define PCI_EXP_DEVCAP_PHANTOM 0x18 /* Phantom functions */ -#define PCI_EXP_DEVCAP_EXT_TAG 0x20 /* Extended tags */ -#define PCI_EXP_DEVCAP_L0S 0x1c0 /* L0s Acceptable Latency */ -#define PCI_EXP_DEVCAP_L1 0xe00 /* L1 Acceptable Latency */ -#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_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 */ -#define PCI_EXP_DEVCTL_CERE 0x0001 /* Correctable Error Reporting En. */ -#define PCI_EXP_DEVCTL_NFERE 0x0002 /* Non-Fatal Error Reporting Enable */ -#define PCI_EXP_DEVCTL_FERE 0x0004 /* Fatal Error Reporting Enable */ -#define PCI_EXP_DEVCTL_URRE 0x0008 /* Unsupported Request Reporting En. */ -#define PCI_EXP_DEVCTL_RELAX_EN 0x0010 /* Enable relaxed ordering */ -#define PCI_EXP_DEVCTL_PAYLOAD 0x00e0 /* Max_Payload_Size */ -#define PCI_EXP_DEVCTL_EXT_TAG 0x0100 /* Extended Tag Field Enable */ -#define PCI_EXP_DEVCTL_PHANTOM 0x0200 /* Phantom Functions Enable */ -#define PCI_EXP_DEVCTL_AUX_PME 0x0400 /* Auxiliary Power PM Enable */ -#define PCI_EXP_DEVCTL_NOSNOOP_EN 0x0800 /* Enable No Snoop */ -#define PCI_EXP_DEVCTL_READRQ 0x7000 /* Max_Read_Request_Size */ -#define PCI_EXP_DEVSTA 10 /* Device Status */ -#define PCI_EXP_DEVSTA_CED 0x01 /* Correctable Error Detected */ -#define PCI_EXP_DEVSTA_NFED 0x02 /* Non-Fatal Error Detected */ -#define PCI_EXP_DEVSTA_FED 0x04 /* Fatal Error Detected */ -#define PCI_EXP_DEVSTA_URD 0x08 /* Unsupported Request Detected */ -#define PCI_EXP_DEVSTA_AUXPD 0x10 /* AUX Power Detected */ -#define PCI_EXP_DEVSTA_TRPND 0x20 /* Transactions Pending */ -#define PCI_EXP_LNKCAP 12 /* Link Capabilities */ -#define PCI_EXP_LNKCTL 16 /* Link Control */ -#define PCI_EXP_LNKSTA 18 /* Link Status */ -#define PCI_EXP_SLTCAP 20 /* Slot Capabilities */ -#define PCI_EXP_SLTCTL 24 /* Slot Control */ -#define PCI_EXP_SLTSTA 26 /* Slot Status */ -#define PCI_EXP_RTCTL 28 /* Root Control */ -#define PCI_EXP_RTCTL_SECEE 0x01 /* System Error on Correctable Error */ -#define PCI_EXP_RTCTL_SENFEE 0x02 /* System Error on Non-Fatal Error */ -#define PCI_EXP_RTCTL_SEFEE 0x04 /* System Error on Fatal Error */ -#define PCI_EXP_RTCTL_PMEIE 0x08 /* PME Interrupt Enable */ -#define PCI_EXP_RTCTL_CRSSVE 0x10 /* CRS Software Visibility Enable */ -#define PCI_EXP_RTCAP 30 /* Root Capabilities */ -#define PCI_EXP_RTSTA 32 /* Root Status */ - -/* Extended Capabilities (PCI-X 2.0 and Express) */ -#define PCI_EXT_CAP_ID(header) (header & 0x0000ffff) -#define PCI_EXT_CAP_VER(header) ((header >> 16) & 0xf) -#define PCI_EXT_CAP_NEXT(header) ((header >> 20) & 0xffc) - -#define PCI_EXT_CAP_ID_ERR 1 -#define PCI_EXT_CAP_ID_VC 2 -#define PCI_EXT_CAP_ID_DSN 3 -#define PCI_EXT_CAP_ID_PWR 4 - -/* Advanced Error Reporting */ -#define PCI_ERR_UNCOR_STATUS 4 /* Uncorrectable Error Status */ -#define PCI_ERR_UNC_TRAIN 0x00000001 /* Training */ -#define PCI_ERR_UNC_DLP 0x00000010 /* Data Link Protocol */ -#define PCI_ERR_UNC_POISON_TLP 0x00001000 /* Poisoned TLP */ -#define PCI_ERR_UNC_FCP 0x00002000 /* Flow Control Protocol */ -#define PCI_ERR_UNC_COMP_TIME 0x00004000 /* Completion Timeout */ -#define PCI_ERR_UNC_COMP_ABORT 0x00008000 /* Completer Abort */ -#define PCI_ERR_UNC_UNX_COMP 0x00010000 /* Unexpected Completion */ -#define PCI_ERR_UNC_RX_OVER 0x00020000 /* Receiver Overflow */ -#define PCI_ERR_UNC_MALF_TLP 0x00040000 /* Malformed TLP */ -#define PCI_ERR_UNC_ECRC 0x00080000 /* ECRC Error Status */ -#define PCI_ERR_UNC_UNSUP 0x00100000 /* Unsupported Request */ -#define PCI_ERR_UNCOR_MASK 8 /* Uncorrectable Error Mask */ - /* Same bits as above */ -#define PCI_ERR_UNCOR_SEVER 12 /* Uncorrectable Error Severity */ - /* Same bits as above */ -#define PCI_ERR_COR_STATUS 16 /* Correctable Error Status */ -#define PCI_ERR_COR_RCVR 0x00000001 /* Receiver Error Status */ -#define PCI_ERR_COR_BAD_TLP 0x00000040 /* Bad TLP Status */ -#define PCI_ERR_COR_BAD_DLLP 0x00000080 /* Bad DLLP Status */ -#define PCI_ERR_COR_REP_ROLL 0x00000100 /* REPLAY_NUM Rollover */ -#define PCI_ERR_COR_REP_TIMER 0x00001000 /* Replay Timer Timeout */ -#define PCI_ERR_COR_MASK 20 /* Correctable Error Mask */ - /* Same bits as above */ -#define PCI_ERR_CAP 24 /* Advanced Error Capabilities */ -#define PCI_ERR_CAP_FEP(x) ((x) & 31) /* First Error Pointer */ -#define PCI_ERR_CAP_ECRC_GENC 0x00000020 /* ECRC Generation Capable */ -#define PCI_ERR_CAP_ECRC_GENE 0x00000040 /* ECRC Generation Enable */ -#define PCI_ERR_CAP_ECRC_CHKC 0x00000080 /* ECRC Check Capable */ -#define PCI_ERR_CAP_ECRC_CHKE 0x00000100 /* ECRC Check Enable */ -#define PCI_ERR_HEADER_LOG 28 /* Header Log Register (16 bytes) */ -#define PCI_ERR_ROOT_COMMAND 44 /* Root Error Command */ -#define PCI_ERR_ROOT_STATUS 48 -#define PCI_ERR_ROOT_COR_SRC 52 -#define PCI_ERR_ROOT_SRC 54 - -/* Virtual Channel */ -#define PCI_VC_PORT_REG1 4 -#define PCI_VC_PORT_REG2 8 -#define PCI_VC_PORT_CTRL 12 -#define PCI_VC_PORT_STATUS 14 -#define PCI_VC_RES_CAP 16 -#define PCI_VC_RES_CTRL 20 -#define PCI_VC_RES_STATUS 26 - -/* Power Budgeting */ -#define PCI_PWR_DSR 4 /* Data Select Register */ -#define PCI_PWR_DATA 8 /* Data Register */ -#define PCI_PWR_DATA_BASE(x) ((x) & 0xff) /* Base Power */ -#define PCI_PWR_DATA_SCALE(x) (((x) >> 8) & 3) /* Data Scale */ -#define PCI_PWR_DATA_PM_SUB(x) (((x) >> 10) & 7) /* PM Sub State */ -#define PCI_PWR_DATA_PM_STATE(x) (((x) >> 13) & 3) /* PM State */ -#define PCI_PWR_DATA_TYPE(x) (((x) >> 15) & 7) /* Type */ -#define PCI_PWR_DATA_RAIL(x) (((x) >> 18) & 7) /* Power Rail */ -#define PCI_PWR_CAP 12 /* Capability */ -#define PCI_PWR_CAP_BUDGET(x) ((x) & 1) /* Included in system budget */ +/* Include the pci register defines */ +#include /* Include the ID list */ - #include /* @@ -496,9 +70,9 @@ enum pci_mmap_state { typedef int __bitwise pci_power_t; -#define PCI_D0 ((pci_power_t __force) 0) -#define PCI_D1 ((pci_power_t __force) 1) -#define PCI_D2 ((pci_power_t __force) 2) +#define PCI_D0 ((pci_power_t __force) 0) +#define PCI_D1 ((pci_power_t __force) 1) +#define PCI_D2 ((pci_power_t __force) 2) #define PCI_D3hot ((pci_power_t __force) 3) #define PCI_D3cold ((pci_power_t __force) 4) #define PCI_POWER_ERROR ((pci_power_t __force) -1) @@ -577,15 +151,15 @@ struct pci_dev { * 7-10 bridges: address space assigned to buses behind the bridge */ -#define PCI_ROM_RESOURCE 6 -#define PCI_BRIDGE_RESOURCES 7 -#define PCI_NUM_RESOURCES 11 +#define PCI_ROM_RESOURCE 6 +#define PCI_BRIDGE_RESOURCES 7 +#define PCI_NUM_RESOURCES 11 #ifndef PCI_BUS_NUM_RESOURCES -#define PCI_BUS_NUM_RESOURCES 8 +#define PCI_BUS_NUM_RESOURCES 8 #endif - -#define PCI_REGION_FLAG_MASK 0x0fU /* These bits of resource flags tell us the PCI region flags */ + +#define PCI_REGION_FLAG_MASK 0x0fU /* These bits of resource flags tell us the PCI region flags */ struct pci_bus { struct list_head node; /* node in list of buses */ @@ -694,7 +268,7 @@ struct pci_driver { * @dev_class_mask: the class mask for this device * * This macro is used to create a struct pci_device_id that matches a - * specific PCI class. The vendor, device, subvendor, and subdevice + * specific PCI class. The vendor, device, subvendor, and subdevice * fields will be set to PCI_ANY_ID. */ #define PCI_DEVICE_CLASS(dev_class,dev_class_mask) \ @@ -702,7 +276,7 @@ struct pci_driver { .vendor = PCI_ANY_ID, .device = PCI_ANY_ID, \ .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID -/* +/* * pci_module_init is obsolete, this stays here till we fix up all usages of it * in the tree. */ @@ -905,18 +479,26 @@ extern void pci_disable_msix(struct pci_dev *dev); extern void msi_remove_pci_irq_vectors(struct pci_dev *dev); #endif -#endif /* CONFIG_PCI */ - -/* Include architecture-dependent settings and functions */ +/* + * PCI domain support. Sometimes called PCI segment (eg by ACPI), + * a PCI domain is defined to be a set of PCI busses which share + * configuration space. + */ +#ifndef CONFIG_PCI_DOMAINS +static inline int pci_domain_nr(struct pci_bus *bus) { return 0; } +static inline int pci_proc_domain(struct pci_bus *bus) +{ + return 0; +} +#endif -#include +#else /* CONFIG_PCI is not enabled */ /* * If the system does not have PCI, clearly these return errors. Define * these as simple inline functions to avoid hair in drivers. */ -#ifndef CONFIG_PCI #define _PCI_NOP(o,s,t) \ static inline int pci_##o##_config_##s (struct pci_dev *dev, int where, t val) \ { return PCIBIOS_FUNC_NOT_SUPPORTED; } @@ -967,21 +549,11 @@ static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state, int en #define pci_dma_burst_advice(pdev, strat, strategy_parameter) do { } while (0) -#else +#endif /* CONFIG_PCI */ -/* - * PCI domain support. Sometimes called PCI segment (eg by ACPI), - * a PCI domain is defined to be a set of PCI busses which share - * configuration space. - */ -#ifndef CONFIG_PCI_DOMAINS -static inline int pci_domain_nr(struct pci_bus *bus) { return 0; } -static inline int pci_proc_domain(struct pci_bus *bus) -{ - return 0; -} -#endif -#endif /* !CONFIG_PCI */ +/* Include architecture-dependent settings and functions */ + +#include /* these helpers provide future and backwards compatibility * for accessing popular PCI BAR info */ diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h new file mode 100644 index 000000000000..7dc391cad10d --- /dev/null +++ b/include/linux/pci_regs.h @@ -0,0 +1,447 @@ +/* + * pci_regs.h + * + * PCI standard defines + * Copyright 1994, Drew Eckhardt + * Copyright 1997--1999 Martin Mares + * + * For more information, please consult the following manuals (look at + * http://www.pcisig.com/ for how to get them): + * + * PCI BIOS Specification + * PCI Local Bus Specification + * PCI to PCI Bridge Specification + * PCI System Design Guide + */ + +#ifndef LINUX_PCI_REGS_H +#define LINUX_PCI_REGS_H + +/* + * Under PCI, each device has 256 bytes of configuration address space, + * of which the first 64 bytes are standardized as follows: + */ +#define PCI_VENDOR_ID 0x00 /* 16 bits */ +#define PCI_DEVICE_ID 0x02 /* 16 bits */ +#define PCI_COMMAND 0x04 /* 16 bits */ +#define PCI_COMMAND_IO 0x1 /* Enable response in I/O space */ +#define PCI_COMMAND_MEMORY 0x2 /* Enable response in Memory space */ +#define PCI_COMMAND_MASTER 0x4 /* Enable bus mastering */ +#define PCI_COMMAND_SPECIAL 0x8 /* Enable response to special cycles */ +#define PCI_COMMAND_INVALIDATE 0x10 /* Use memory write and invalidate */ +#define PCI_COMMAND_VGA_PALETTE 0x20 /* Enable palette snooping */ +#define PCI_COMMAND_PARITY 0x40 /* Enable parity checking */ +#define PCI_COMMAND_WAIT 0x80 /* Enable address/data stepping */ +#define PCI_COMMAND_SERR 0x100 /* Enable SERR */ +#define PCI_COMMAND_FAST_BACK 0x200 /* Enable back-to-back writes */ +#define PCI_COMMAND_INTX_DISABLE 0x400 /* INTx Emulation Disable */ + +#define PCI_STATUS 0x06 /* 16 bits */ +#define PCI_STATUS_CAP_LIST 0x10 /* Support Capability List */ +#define PCI_STATUS_66MHZ 0x20 /* Support 66 Mhz PCI 2.1 bus */ +#define PCI_STATUS_UDF 0x40 /* Support User Definable Features [obsolete] */ +#define PCI_STATUS_FAST_BACK 0x80 /* Accept fast-back to back */ +#define PCI_STATUS_PARITY 0x100 /* Detected parity error */ +#define PCI_STATUS_DEVSEL_MASK 0x600 /* DEVSEL timing */ +#define PCI_STATUS_DEVSEL_FAST 0x000 +#define PCI_STATUS_DEVSEL_MEDIUM 0x200 +#define PCI_STATUS_DEVSEL_SLOW 0x400 +#define PCI_STATUS_SIG_TARGET_ABORT 0x800 /* Set on target abort */ +#define PCI_STATUS_REC_TARGET_ABORT 0x1000 /* Master ack of " */ +#define PCI_STATUS_REC_MASTER_ABORT 0x2000 /* Set on master abort */ +#define PCI_STATUS_SIG_SYSTEM_ERROR 0x4000 /* Set when we drive SERR */ +#define PCI_STATUS_DETECTED_PARITY 0x8000 /* Set on parity error */ + +#define PCI_CLASS_REVISION 0x08 /* High 24 bits are class, low 8 revision */ +#define PCI_REVISION_ID 0x08 /* Revision ID */ +#define PCI_CLASS_PROG 0x09 /* Reg. Level Programming Interface */ +#define PCI_CLASS_DEVICE 0x0a /* Device class */ + +#define PCI_CACHE_LINE_SIZE 0x0c /* 8 bits */ +#define PCI_LATENCY_TIMER 0x0d /* 8 bits */ +#define PCI_HEADER_TYPE 0x0e /* 8 bits */ +#define PCI_HEADER_TYPE_NORMAL 0 +#define PCI_HEADER_TYPE_BRIDGE 1 +#define PCI_HEADER_TYPE_CARDBUS 2 + +#define PCI_BIST 0x0f /* 8 bits */ +#define PCI_BIST_CODE_MASK 0x0f /* Return result */ +#define PCI_BIST_START 0x40 /* 1 to start BIST, 2 secs or less */ +#define PCI_BIST_CAPABLE 0x80 /* 1 if BIST capable */ + +/* + * Base addresses specify locations in memory or I/O space. + * Decoded size can be determined by writing a value of + * 0xffffffff to the register, and reading it back. Only + * 1 bits are decoded. + */ +#define PCI_BASE_ADDRESS_0 0x10 /* 32 bits */ +#define PCI_BASE_ADDRESS_1 0x14 /* 32 bits [htype 0,1 only] */ +#define PCI_BASE_ADDRESS_2 0x18 /* 32 bits [htype 0 only] */ +#define PCI_BASE_ADDRESS_3 0x1c /* 32 bits */ +#define PCI_BASE_ADDRESS_4 0x20 /* 32 bits */ +#define PCI_BASE_ADDRESS_5 0x24 /* 32 bits */ +#define PCI_BASE_ADDRESS_SPACE 0x01 /* 0 = memory, 1 = I/O */ +#define PCI_BASE_ADDRESS_SPACE_IO 0x01 +#define PCI_BASE_ADDRESS_SPACE_MEMORY 0x00 +#define PCI_BASE_ADDRESS_MEM_TYPE_MASK 0x06 +#define PCI_BASE_ADDRESS_MEM_TYPE_32 0x00 /* 32 bit address */ +#define PCI_BASE_ADDRESS_MEM_TYPE_1M 0x02 /* Below 1M [obsolete] */ +#define PCI_BASE_ADDRESS_MEM_TYPE_64 0x04 /* 64 bit address */ +#define PCI_BASE_ADDRESS_MEM_PREFETCH 0x08 /* prefetchable? */ +#define PCI_BASE_ADDRESS_MEM_MASK (~0x0fUL) +#define PCI_BASE_ADDRESS_IO_MASK (~0x03UL) +/* bit 1 is reserved if address_space = 1 */ + +/* Header type 0 (normal devices) */ +#define PCI_CARDBUS_CIS 0x28 +#define PCI_SUBSYSTEM_VENDOR_ID 0x2c +#define PCI_SUBSYSTEM_ID 0x2e +#define PCI_ROM_ADDRESS 0x30 /* Bits 31..11 are address, 10..1 reserved */ +#define PCI_ROM_ADDRESS_ENABLE 0x01 +#define PCI_ROM_ADDRESS_MASK (~0x7ffUL) + +#define PCI_CAPABILITY_LIST 0x34 /* Offset of first capability list entry */ + +/* 0x35-0x3b are reserved */ +#define PCI_INTERRUPT_LINE 0x3c /* 8 bits */ +#define PCI_INTERRUPT_PIN 0x3d /* 8 bits */ +#define PCI_MIN_GNT 0x3e /* 8 bits */ +#define PCI_MAX_LAT 0x3f /* 8 bits */ + +/* Header type 1 (PCI-to-PCI bridges) */ +#define PCI_PRIMARY_BUS 0x18 /* Primary bus number */ +#define PCI_SECONDARY_BUS 0x19 /* Secondary bus number */ +#define PCI_SUBORDINATE_BUS 0x1a /* Highest bus number behind the bridge */ +#define PCI_SEC_LATENCY_TIMER 0x1b /* Latency timer for secondary interface */ +#define PCI_IO_BASE 0x1c /* I/O range behind the bridge */ +#define PCI_IO_LIMIT 0x1d +#define PCI_IO_RANGE_TYPE_MASK 0x0fUL /* I/O bridging type */ +#define PCI_IO_RANGE_TYPE_16 0x00 +#define PCI_IO_RANGE_TYPE_32 0x01 +#define PCI_IO_RANGE_MASK (~0x0fUL) +#define PCI_SEC_STATUS 0x1e /* Secondary status register, only bit 14 used */ +#define PCI_MEMORY_BASE 0x20 /* Memory range behind */ +#define PCI_MEMORY_LIMIT 0x22 +#define PCI_MEMORY_RANGE_TYPE_MASK 0x0fUL +#define PCI_MEMORY_RANGE_MASK (~0x0fUL) +#define PCI_PREF_MEMORY_BASE 0x24 /* Prefetchable memory range behind */ +#define PCI_PREF_MEMORY_LIMIT 0x26 +#define PCI_PREF_RANGE_TYPE_MASK 0x0fUL +#define PCI_PREF_RANGE_TYPE_32 0x00 +#define PCI_PREF_RANGE_TYPE_64 0x01 +#define PCI_PREF_RANGE_MASK (~0x0fUL) +#define PCI_PREF_BASE_UPPER32 0x28 /* Upper half of prefetchable memory range */ +#define PCI_PREF_LIMIT_UPPER32 0x2c +#define PCI_IO_BASE_UPPER16 0x30 /* Upper half of I/O addresses */ +#define PCI_IO_LIMIT_UPPER16 0x32 +/* 0x34 same as for htype 0 */ +/* 0x35-0x3b is reserved */ +#define PCI_ROM_ADDRESS1 0x38 /* Same as PCI_ROM_ADDRESS, but for htype 1 */ +/* 0x3c-0x3d are same as for htype 0 */ +#define PCI_BRIDGE_CONTROL 0x3e +#define PCI_BRIDGE_CTL_PARITY 0x01 /* Enable parity detection on secondary interface */ +#define PCI_BRIDGE_CTL_SERR 0x02 /* The same for SERR forwarding */ +#define PCI_BRIDGE_CTL_NO_ISA 0x04 /* Disable bridging of ISA ports */ +#define PCI_BRIDGE_CTL_VGA 0x08 /* Forward VGA addresses */ +#define PCI_BRIDGE_CTL_MASTER_ABORT 0x20 /* Report master aborts */ +#define PCI_BRIDGE_CTL_BUS_RESET 0x40 /* Secondary bus reset */ +#define PCI_BRIDGE_CTL_FAST_BACK 0x80 /* Fast Back2Back enabled on secondary interface */ + +/* Header type 2 (CardBus bridges) */ +#define PCI_CB_CAPABILITY_LIST 0x14 +/* 0x15 reserved */ +#define PCI_CB_SEC_STATUS 0x16 /* Secondary status */ +#define PCI_CB_PRIMARY_BUS 0x18 /* PCI bus number */ +#define PCI_CB_CARD_BUS 0x19 /* CardBus bus number */ +#define PCI_CB_SUBORDINATE_BUS 0x1a /* Subordinate bus number */ +#define PCI_CB_LATENCY_TIMER 0x1b /* CardBus latency timer */ +#define PCI_CB_MEMORY_BASE_0 0x1c +#define PCI_CB_MEMORY_LIMIT_0 0x20 +#define PCI_CB_MEMORY_BASE_1 0x24 +#define PCI_CB_MEMORY_LIMIT_1 0x28 +#define PCI_CB_IO_BASE_0 0x2c +#define PCI_CB_IO_BASE_0_HI 0x2e +#define PCI_CB_IO_LIMIT_0 0x30 +#define PCI_CB_IO_LIMIT_0_HI 0x32 +#define PCI_CB_IO_BASE_1 0x34 +#define PCI_CB_IO_BASE_1_HI 0x36 +#define PCI_CB_IO_LIMIT_1 0x38 +#define PCI_CB_IO_LIMIT_1_HI 0x3a +#define PCI_CB_IO_RANGE_MASK (~0x03UL) +/* 0x3c-0x3d are same as for htype 0 */ +#define PCI_CB_BRIDGE_CONTROL 0x3e +#define PCI_CB_BRIDGE_CTL_PARITY 0x01 /* Similar to standard bridge control register */ +#define PCI_CB_BRIDGE_CTL_SERR 0x02 +#define PCI_CB_BRIDGE_CTL_ISA 0x04 +#define PCI_CB_BRIDGE_CTL_VGA 0x08 +#define PCI_CB_BRIDGE_CTL_MASTER_ABORT 0x20 +#define PCI_CB_BRIDGE_CTL_CB_RESET 0x40 /* CardBus reset */ +#define PCI_CB_BRIDGE_CTL_16BIT_INT 0x80 /* Enable interrupt for 16-bit cards */ +#define PCI_CB_BRIDGE_CTL_PREFETCH_MEM0 0x100 /* Prefetch enable for both memory regions */ +#define PCI_CB_BRIDGE_CTL_PREFETCH_MEM1 0x200 +#define PCI_CB_BRIDGE_CTL_POST_WRITES 0x400 +#define PCI_CB_SUBSYSTEM_VENDOR_ID 0x40 +#define PCI_CB_SUBSYSTEM_ID 0x42 +#define PCI_CB_LEGACY_MODE_BASE 0x44 /* 16-bit PC Card legacy mode base address (ExCa) */ +/* 0x48-0x7f reserved */ + +/* Capability lists */ + +#define PCI_CAP_LIST_ID 0 /* Capability ID */ +#define PCI_CAP_ID_PM 0x01 /* Power Management */ +#define PCI_CAP_ID_AGP 0x02 /* Accelerated Graphics Port */ +#define PCI_CAP_ID_VPD 0x03 /* Vital Product Data */ +#define PCI_CAP_ID_SLOTID 0x04 /* Slot Identification */ +#define PCI_CAP_ID_MSI 0x05 /* Message Signalled Interrupts */ +#define PCI_CAP_ID_CHSWP 0x06 /* CompactPCI HotSwap */ +#define PCI_CAP_ID_PCIX 0x07 /* PCI-X */ +#define PCI_CAP_ID_SHPC 0x0C /* PCI Standard Hot-Plug Controller */ +#define PCI_CAP_ID_EXP 0x10 /* PCI Express */ +#define PCI_CAP_ID_MSIX 0x11 /* MSI-X */ +#define PCI_CAP_LIST_NEXT 1 /* Next capability in the list */ +#define PCI_CAP_FLAGS 2 /* Capability defined flags (16 bits) */ +#define PCI_CAP_SIZEOF 4 + +/* Power Management Registers */ + +#define PCI_PM_PMC 2 /* PM Capabilities Register */ +#define PCI_PM_CAP_VER_MASK 0x0007 /* Version */ +#define PCI_PM_CAP_PME_CLOCK 0x0008 /* PME clock required */ +#define PCI_PM_CAP_RESERVED 0x0010 /* Reserved field */ +#define PCI_PM_CAP_DSI 0x0020 /* Device specific initialization */ +#define PCI_PM_CAP_AUX_POWER 0x01C0 /* Auxilliary power support mask */ +#define PCI_PM_CAP_D1 0x0200 /* D1 power state support */ +#define PCI_PM_CAP_D2 0x0400 /* D2 power state support */ +#define PCI_PM_CAP_PME 0x0800 /* PME pin supported */ +#define PCI_PM_CAP_PME_MASK 0xF800 /* PME Mask of all supported states */ +#define PCI_PM_CAP_PME_D0 0x0800 /* PME# from D0 */ +#define PCI_PM_CAP_PME_D1 0x1000 /* PME# from D1 */ +#define PCI_PM_CAP_PME_D2 0x2000 /* PME# from D2 */ +#define PCI_PM_CAP_PME_D3 0x4000 /* PME# from D3 (hot) */ +#define PCI_PM_CAP_PME_D3cold 0x8000 /* PME# from D3 (cold) */ +#define PCI_PM_CTRL 4 /* PM control and status register */ +#define PCI_PM_CTRL_STATE_MASK 0x0003 /* Current power state (D0 to D3) */ +#define PCI_PM_CTRL_PME_ENABLE 0x0100 /* PME pin enable */ +#define PCI_PM_CTRL_DATA_SEL_MASK 0x1e00 /* Data select (??) */ +#define PCI_PM_CTRL_DATA_SCALE_MASK 0x6000 /* Data scale (??) */ +#define PCI_PM_CTRL_PME_STATUS 0x8000 /* PME pin status */ +#define PCI_PM_PPB_EXTENSIONS 6 /* PPB support extensions (??) */ +#define PCI_PM_PPB_B2_B3 0x40 /* Stop clock when in D3hot (??) */ +#define PCI_PM_BPCC_ENABLE 0x80 /* Bus power/clock control enable (??) */ +#define PCI_PM_DATA_REGISTER 7 /* (??) */ +#define PCI_PM_SIZEOF 8 + +/* AGP registers */ + +#define PCI_AGP_VERSION 2 /* BCD version number */ +#define PCI_AGP_RFU 3 /* Rest of capability flags */ +#define PCI_AGP_STATUS 4 /* Status register */ +#define PCI_AGP_STATUS_RQ_MASK 0xff000000 /* Maximum number of requests - 1 */ +#define PCI_AGP_STATUS_SBA 0x0200 /* Sideband addressing supported */ +#define PCI_AGP_STATUS_64BIT 0x0020 /* 64-bit addressing supported */ +#define PCI_AGP_STATUS_FW 0x0010 /* FW transfers supported */ +#define PCI_AGP_STATUS_RATE4 0x0004 /* 4x transfer rate supported */ +#define PCI_AGP_STATUS_RATE2 0x0002 /* 2x transfer rate supported */ +#define PCI_AGP_STATUS_RATE1 0x0001 /* 1x transfer rate supported */ +#define PCI_AGP_COMMAND 8 /* Control register */ +#define PCI_AGP_COMMAND_RQ_MASK 0xff000000 /* Master: Maximum number of requests */ +#define PCI_AGP_COMMAND_SBA 0x0200 /* Sideband addressing enabled */ +#define PCI_AGP_COMMAND_AGP 0x0100 /* Allow processing of AGP transactions */ +#define PCI_AGP_COMMAND_64BIT 0x0020 /* Allow processing of 64-bit addresses */ +#define PCI_AGP_COMMAND_FW 0x0010 /* Force FW transfers */ +#define PCI_AGP_COMMAND_RATE4 0x0004 /* Use 4x rate */ +#define PCI_AGP_COMMAND_RATE2 0x0002 /* Use 2x rate */ +#define PCI_AGP_COMMAND_RATE1 0x0001 /* Use 1x rate */ +#define PCI_AGP_SIZEOF 12 + +/* Vital Product Data */ + +#define PCI_VPD_ADDR 2 /* Address to access (15 bits!) */ +#define PCI_VPD_ADDR_MASK 0x7fff /* Address mask */ +#define PCI_VPD_ADDR_F 0x8000 /* Write 0, 1 indicates completion */ +#define PCI_VPD_DATA 4 /* 32-bits of data returned here */ + +/* Slot Identification */ + +#define PCI_SID_ESR 2 /* Expansion Slot Register */ +#define PCI_SID_ESR_NSLOTS 0x1f /* Number of expansion slots available */ +#define PCI_SID_ESR_FIC 0x20 /* First In Chassis Flag */ +#define PCI_SID_CHASSIS_NR 3 /* Chassis Number */ + +/* Message Signalled Interrupts registers */ + +#define PCI_MSI_FLAGS 2 /* Various flags */ +#define PCI_MSI_FLAGS_64BIT 0x80 /* 64-bit addresses allowed */ +#define PCI_MSI_FLAGS_QSIZE 0x70 /* Message queue size configured */ +#define PCI_MSI_FLAGS_QMASK 0x0e /* Maximum queue size available */ +#define PCI_MSI_FLAGS_ENABLE 0x01 /* MSI feature enabled */ +#define PCI_MSI_FLAGS_MASKBIT 0x100 /* 64-bit mask bits allowed */ +#define PCI_MSI_RFU 3 /* Rest of capability flags */ +#define PCI_MSI_ADDRESS_LO 4 /* Lower 32 bits */ +#define PCI_MSI_ADDRESS_HI 8 /* Upper 32 bits (if PCI_MSI_FLAGS_64BIT set) */ +#define PCI_MSI_DATA_32 8 /* 16 bits of data for 32-bit devices */ +#define PCI_MSI_DATA_64 12 /* 16 bits of data for 64-bit devices */ +#define PCI_MSI_MASK_BIT 16 /* Mask bits register */ + +/* CompactPCI Hotswap Register */ + +#define PCI_CHSWP_CSR 2 /* Control and Status Register */ +#define PCI_CHSWP_DHA 0x01 /* Device Hiding Arm */ +#define PCI_CHSWP_EIM 0x02 /* ENUM# Signal Mask */ +#define PCI_CHSWP_PIE 0x04 /* Pending Insert or Extract */ +#define PCI_CHSWP_LOO 0x08 /* LED On / Off */ +#define PCI_CHSWP_PI 0x30 /* Programming Interface */ +#define PCI_CHSWP_EXT 0x40 /* ENUM# status - extraction */ +#define PCI_CHSWP_INS 0x80 /* ENUM# status - insertion */ + +/* PCI-X registers */ + +#define PCI_X_CMD 2 /* Modes & Features */ +#define PCI_X_CMD_DPERR_E 0x0001 /* Data Parity Error Recovery Enable */ +#define PCI_X_CMD_ERO 0x0002 /* Enable Relaxed Ordering */ +#define PCI_X_CMD_MAX_READ 0x000c /* Max Memory Read Byte Count */ +#define PCI_X_CMD_MAX_SPLIT 0x0070 /* Max Outstanding Split Transactions */ +#define PCI_X_CMD_VERSION(x) (((x) >> 12) & 3) /* Version */ +#define PCI_X_STATUS 4 /* PCI-X capabilities */ +#define PCI_X_STATUS_DEVFN 0x000000ff /* A copy of devfn */ +#define PCI_X_STATUS_BUS 0x0000ff00 /* A copy of bus nr */ +#define PCI_X_STATUS_64BIT 0x00010000 /* 64-bit device */ +#define PCI_X_STATUS_133MHZ 0x00020000 /* 133 MHz capable */ +#define PCI_X_STATUS_SPL_DISC 0x00040000 /* Split Completion Discarded */ +#define PCI_X_STATUS_UNX_SPL 0x00080000 /* Unexpected Split Completion */ +#define PCI_X_STATUS_COMPLEX 0x00100000 /* Device Complexity */ +#define PCI_X_STATUS_MAX_READ 0x00600000 /* Designed Max Memory Read Count */ +#define PCI_X_STATUS_MAX_SPLIT 0x03800000 /* Designed Max Outstanding Split Transactions */ +#define PCI_X_STATUS_MAX_CUM 0x1c000000 /* Designed Max Cumulative Read Size */ +#define PCI_X_STATUS_SPL_ERR 0x20000000 /* Rcvd Split Completion Error Msg */ +#define PCI_X_STATUS_266MHZ 0x40000000 /* 266 MHz capable */ +#define PCI_X_STATUS_533MHZ 0x80000000 /* 533 MHz capable */ + +/* PCI Express capability registers */ + +#define PCI_EXP_FLAGS 2 /* Capabilities register */ +#define PCI_EXP_FLAGS_VERS 0x000f /* Capability version */ +#define PCI_EXP_FLAGS_TYPE 0x00f0 /* Device/Port type */ +#define PCI_EXP_TYPE_ENDPOINT 0x0 /* Express Endpoint */ +#define PCI_EXP_TYPE_LEG_END 0x1 /* Legacy Endpoint */ +#define PCI_EXP_TYPE_ROOT_PORT 0x4 /* Root Port */ +#define PCI_EXP_TYPE_UPSTREAM 0x5 /* Upstream Port */ +#define PCI_EXP_TYPE_DOWNSTREAM 0x6 /* Downstream Port */ +#define PCI_EXP_TYPE_PCI_BRIDGE 0x7 /* PCI/PCI-X Bridge */ +#define PCI_EXP_FLAGS_SLOT 0x0100 /* Slot implemented */ +#define PCI_EXP_FLAGS_IRQ 0x3e00 /* Interrupt message number */ +#define PCI_EXP_DEVCAP 4 /* Device capabilities */ +#define PCI_EXP_DEVCAP_PAYLOAD 0x07 /* Max_Payload_Size */ +#define PCI_EXP_DEVCAP_PHANTOM 0x18 /* Phantom functions */ +#define PCI_EXP_DEVCAP_EXT_TAG 0x20 /* Extended tags */ +#define PCI_EXP_DEVCAP_L0S 0x1c0 /* L0s Acceptable Latency */ +#define PCI_EXP_DEVCAP_L1 0xe00 /* L1 Acceptable Latency */ +#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_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 */ +#define PCI_EXP_DEVCTL_CERE 0x0001 /* Correctable Error Reporting En. */ +#define PCI_EXP_DEVCTL_NFERE 0x0002 /* Non-Fatal Error Reporting Enable */ +#define PCI_EXP_DEVCTL_FERE 0x0004 /* Fatal Error Reporting Enable */ +#define PCI_EXP_DEVCTL_URRE 0x0008 /* Unsupported Request Reporting En. */ +#define PCI_EXP_DEVCTL_RELAX_EN 0x0010 /* Enable relaxed ordering */ +#define PCI_EXP_DEVCTL_PAYLOAD 0x00e0 /* Max_Payload_Size */ +#define PCI_EXP_DEVCTL_EXT_TAG 0x0100 /* Extended Tag Field Enable */ +#define PCI_EXP_DEVCTL_PHANTOM 0x0200 /* Phantom Functions Enable */ +#define PCI_EXP_DEVCTL_AUX_PME 0x0400 /* Auxiliary Power PM Enable */ +#define PCI_EXP_DEVCTL_NOSNOOP_EN 0x0800 /* Enable No Snoop */ +#define PCI_EXP_DEVCTL_READRQ 0x7000 /* Max_Read_Request_Size */ +#define PCI_EXP_DEVSTA 10 /* Device Status */ +#define PCI_EXP_DEVSTA_CED 0x01 /* Correctable Error Detected */ +#define PCI_EXP_DEVSTA_NFED 0x02 /* Non-Fatal Error Detected */ +#define PCI_EXP_DEVSTA_FED 0x04 /* Fatal Error Detected */ +#define PCI_EXP_DEVSTA_URD 0x08 /* Unsupported Request Detected */ +#define PCI_EXP_DEVSTA_AUXPD 0x10 /* AUX Power Detected */ +#define PCI_EXP_DEVSTA_TRPND 0x20 /* Transactions Pending */ +#define PCI_EXP_LNKCAP 12 /* Link Capabilities */ +#define PCI_EXP_LNKCTL 16 /* Link Control */ +#define PCI_EXP_LNKSTA 18 /* Link Status */ +#define PCI_EXP_SLTCAP 20 /* Slot Capabilities */ +#define PCI_EXP_SLTCTL 24 /* Slot Control */ +#define PCI_EXP_SLTSTA 26 /* Slot Status */ +#define PCI_EXP_RTCTL 28 /* Root Control */ +#define PCI_EXP_RTCTL_SECEE 0x01 /* System Error on Correctable Error */ +#define PCI_EXP_RTCTL_SENFEE 0x02 /* System Error on Non-Fatal Error */ +#define PCI_EXP_RTCTL_SEFEE 0x04 /* System Error on Fatal Error */ +#define PCI_EXP_RTCTL_PMEIE 0x08 /* PME Interrupt Enable */ +#define PCI_EXP_RTCTL_CRSSVE 0x10 /* CRS Software Visibility Enable */ +#define PCI_EXP_RTCAP 30 /* Root Capabilities */ +#define PCI_EXP_RTSTA 32 /* Root Status */ + +/* Extended Capabilities (PCI-X 2.0 and Express) */ +#define PCI_EXT_CAP_ID(header) (header & 0x0000ffff) +#define PCI_EXT_CAP_VER(header) ((header >> 16) & 0xf) +#define PCI_EXT_CAP_NEXT(header) ((header >> 20) & 0xffc) + +#define PCI_EXT_CAP_ID_ERR 1 +#define PCI_EXT_CAP_ID_VC 2 +#define PCI_EXT_CAP_ID_DSN 3 +#define PCI_EXT_CAP_ID_PWR 4 + +/* Advanced Error Reporting */ +#define PCI_ERR_UNCOR_STATUS 4 /* Uncorrectable Error Status */ +#define PCI_ERR_UNC_TRAIN 0x00000001 /* Training */ +#define PCI_ERR_UNC_DLP 0x00000010 /* Data Link Protocol */ +#define PCI_ERR_UNC_POISON_TLP 0x00001000 /* Poisoned TLP */ +#define PCI_ERR_UNC_FCP 0x00002000 /* Flow Control Protocol */ +#define PCI_ERR_UNC_COMP_TIME 0x00004000 /* Completion Timeout */ +#define PCI_ERR_UNC_COMP_ABORT 0x00008000 /* Completer Abort */ +#define PCI_ERR_UNC_UNX_COMP 0x00010000 /* Unexpected Completion */ +#define PCI_ERR_UNC_RX_OVER 0x00020000 /* Receiver Overflow */ +#define PCI_ERR_UNC_MALF_TLP 0x00040000 /* Malformed TLP */ +#define PCI_ERR_UNC_ECRC 0x00080000 /* ECRC Error Status */ +#define PCI_ERR_UNC_UNSUP 0x00100000 /* Unsupported Request */ +#define PCI_ERR_UNCOR_MASK 8 /* Uncorrectable Error Mask */ + /* Same bits as above */ +#define PCI_ERR_UNCOR_SEVER 12 /* Uncorrectable Error Severity */ + /* Same bits as above */ +#define PCI_ERR_COR_STATUS 16 /* Correctable Error Status */ +#define PCI_ERR_COR_RCVR 0x00000001 /* Receiver Error Status */ +#define PCI_ERR_COR_BAD_TLP 0x00000040 /* Bad TLP Status */ +#define PCI_ERR_COR_BAD_DLLP 0x00000080 /* Bad DLLP Status */ +#define PCI_ERR_COR_REP_ROLL 0x00000100 /* REPLAY_NUM Rollover */ +#define PCI_ERR_COR_REP_TIMER 0x00001000 /* Replay Timer Timeout */ +#define PCI_ERR_COR_MASK 20 /* Correctable Error Mask */ + /* Same bits as above */ +#define PCI_ERR_CAP 24 /* Advanced Error Capabilities */ +#define PCI_ERR_CAP_FEP(x) ((x) & 31) /* First Error Pointer */ +#define PCI_ERR_CAP_ECRC_GENC 0x00000020 /* ECRC Generation Capable */ +#define PCI_ERR_CAP_ECRC_GENE 0x00000040 /* ECRC Generation Enable */ +#define PCI_ERR_CAP_ECRC_CHKC 0x00000080 /* ECRC Check Capable */ +#define PCI_ERR_CAP_ECRC_CHKE 0x00000100 /* ECRC Check Enable */ +#define PCI_ERR_HEADER_LOG 28 /* Header Log Register (16 bytes) */ +#define PCI_ERR_ROOT_COMMAND 44 /* Root Error Command */ +#define PCI_ERR_ROOT_STATUS 48 +#define PCI_ERR_ROOT_COR_SRC 52 +#define PCI_ERR_ROOT_SRC 54 + +/* Virtual Channel */ +#define PCI_VC_PORT_REG1 4 +#define PCI_VC_PORT_REG2 8 +#define PCI_VC_PORT_CTRL 12 +#define PCI_VC_PORT_STATUS 14 +#define PCI_VC_RES_CAP 16 +#define PCI_VC_RES_CTRL 20 +#define PCI_VC_RES_STATUS 26 + +/* Power Budgeting */ +#define PCI_PWR_DSR 4 /* Data Select Register */ +#define PCI_PWR_DATA 8 /* Data Register */ +#define PCI_PWR_DATA_BASE(x) ((x) & 0xff) /* Base Power */ +#define PCI_PWR_DATA_SCALE(x) (((x) >> 8) & 3) /* Data Scale */ +#define PCI_PWR_DATA_PM_SUB(x) (((x) >> 10) & 7) /* PM Sub State */ +#define PCI_PWR_DATA_PM_STATE(x) (((x) >> 13) & 3) /* PM State */ +#define PCI_PWR_DATA_TYPE(x) (((x) >> 15) & 7) /* Type */ +#define PCI_PWR_DATA_RAIL(x) (((x) >> 18) & 7) /* Power Rail */ +#define PCI_PWR_CAP 12 /* Capability */ +#define PCI_PWR_CAP_BUDGET(x) ((x) & 1) /* Included in system budget */ + +#endif /* LINUX_PCI_REGS_H */ -- cgit v1.2.3 From 064b53dbcc977dbf2753a67c2b8fc1c061d74f21 Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Wed, 27 Jul 2005 10:19:44 -0400 Subject: [PATCH] PCI: restore BAR values after D3hot->D0 for devices that need it Some PCI devices (e.g. 3c905B, 3c556B) lose all configuration (including BARs) when transitioning from D3hot->D0. This leaves such a device in an inaccessible state. The patch below causes the BARs to be restored when enabling such a device, so that its driver will be able to access it. The patch also adds pci_restore_bars as a new global symbol, and adds a correpsonding EXPORT_SYMBOL_GPL for that. Some firmware (e.g. Thinkpad T21) leaves devices in D3hot after a (re)boot. Most drivers call pci_enable_device very early, so devices left in D3hot that lose configuration during the D3hot->D0 transition will be inaccessible to their drivers. Drivers could be modified to account for this, but it would be difficult to know which drivers need modification. This is especially true since often many devices are covered by the same driver. It likely would be necessary to replicate code across dozens of drivers. The patch below should trigger only when transitioning from D3hot->D0 (or at boot), and only for devices that have the "no soft reset" bit cleared in the PM control register. I believe it is safe to include this patch as part of the PCI infrastructure. The cleanest implementation of pci_restore_bars was to call pci_update_resource. Unfortunately, that does not currently exist for the sparc64 architecture. The patch below includes a null implemenation of pci_update_resource for sparc64. Some have expressed interest in making general use of the the pci_restore_bars function, so that has been exported to GPL licensed modules. Signed-off-by: John W. Linville Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 2 ++ include/linux/pci_regs.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 830c1bae56cc..8878ccff9e3c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -384,7 +384,9 @@ int pci_set_mwi(struct pci_dev *dev); void pci_clear_mwi(struct pci_dev *dev); int pci_set_dma_mask(struct pci_dev *dev, u64 mask); int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask); +void pci_update_resource(struct pci_dev *dev, struct resource *res, int resno); int pci_assign_resource(struct pci_dev *dev, int i); +void pci_restore_bars(struct pci_dev *dev); /* ROM control related routines */ void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size); diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index 7dc391cad10d..e2a089b051ed 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -222,6 +222,7 @@ #define PCI_PM_CAP_PME_D3cold 0x8000 /* PME# from D3 (cold) */ #define PCI_PM_CTRL 4 /* PM control and status register */ #define PCI_PM_CTRL_STATE_MASK 0x0003 /* Current power state (D0 to D3) */ +#define PCI_PM_CTRL_NO_SOFT_RESET 0x0004 /* No reset for D3hot->D0 */ #define PCI_PM_CTRL_PME_ENABLE 0x0100 /* PME pin enable */ #define PCI_PM_CTRL_DATA_SEL_MASK 0x1e00 /* Data select (??) */ #define PCI_PM_CTRL_DATA_SCALE_MASK 0x6000 /* Data scale (??) */ -- cgit v1.2.3 From cecf4864cf52a4a243a62b2856a6a155edbb55e8 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Thu, 18 Aug 2005 14:33:01 +1000 Subject: [PATCH] PCI: Add pci_walk_bus function to PCI core (nonrecursive) The PCI error recovery infrastructure needs to be able to contact all the drivers affected by a PCI error event, which may mean traversing all the devices under a given PCI-PCI bridge. This patch adds a function to the PCI core that traverses all the PCI devices on a PCI bus and under any PCI-PCI bridges on that bus (and so on), calling a given function for each device. This provides a way for the error recovery code to iterate through all devices that are affected by an error event. This version is not implemented as a recursive function. Instead, when we reach a PCI-PCI bridge, we set the pointers to start doing the devices on the bus under the bridge, and when we reach the end of a bus's devices, we use the bus->self pointer to go back up to the next higher bus and continue doing its devices. Signed-off-by: Paul Mackerras Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 8878ccff9e3c..b0e244713281 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -434,6 +434,9 @@ const struct pci_device_id *pci_match_device(struct pci_driver *drv, struct pci_ const struct pci_device_id *pci_match_id(const struct pci_device_id *ids, struct pci_dev *dev); int pci_scan_bridge(struct pci_bus *bus, struct pci_dev * dev, int max, int pass); +void pci_walk_bus(struct pci_bus *top, void (*cb)(struct pci_dev *, void *), + void *userdata); + /* kmem_cache style wrapper around pci_alloc_consistent() */ #include -- cgit v1.2.3 From 3fe9d19f9e86a55679f5f2b38ec0a43a1a510cee Mon Sep 17 00:00:00 2001 From: Daniel Ritz Date: Wed, 17 Aug 2005 15:32:19 -0700 Subject: [PATCH] PCI: Support PCM PM CAP version 3 - support PCI PM CAP version 3 (as defined in PCI PM Interface Spec v1.2) - pci/probe.c sets the PM state initially to 4 which is D3cold. add a PCI_UNKNOWN - minor cleanups Signed-off-by: Daniel Ritz Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- 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 b0e244713281..7004dde7fef0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -75,6 +75,7 @@ typedef int __bitwise pci_power_t; #define PCI_D2 ((pci_power_t __force) 2) #define PCI_D3hot ((pci_power_t __force) 3) #define PCI_D3cold ((pci_power_t __force) 4) +#define PCI_UNKNOWN ((pci_power_t __force) 5) #define PCI_POWER_ERROR ((pci_power_t __force) -1) /* -- cgit v1.2.3 From a04ce0ffcaf561994ecf382cd3caad75556dc499 Mon Sep 17 00:00:00 2001 From: Brett M Russ Date: Mon, 15 Aug 2005 15:23:41 -0400 Subject: [PATCH] PCI/libata INTx cleanup Simple cleanup to eliminate X copies of the pci_enable_intx() function in libata. Moved ahci.c's pci_intx() to pci.c and use it throughout libata and msi.c. Signed-off-by: Brett Russ Signed-off-by: Greg Kroah-Hartman --- 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 7004dde7fef0..6caaba0af469 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -383,6 +383,7 @@ void pci_set_master(struct pci_dev *dev); #define HAVE_PCI_SET_MWI int pci_set_mwi(struct pci_dev *dev); void pci_clear_mwi(struct pci_dev *dev); +void pci_intx(struct pci_dev *dev, int enable); int pci_set_dma_mask(struct pci_dev *dev, u64 mask); int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask); void pci_update_resource(struct pci_dev *dev, struct resource *res, int resno); -- cgit v1.2.3 From fbf82fd2e1f4e679c60516d772d1862c941ca845 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sun, 31 Jul 2005 01:05:53 +0200 Subject: [PATCH] USB: real nodes instead of usbfs This patch introduces a /sys/class/usb_device/ class where every connected usb-device will show up: tree /sys/class/usb_device/ /sys/class/usb_device/ |-- usb1.1 | |-- dev | `-- device -> ../../../devices/pci0000:00/0000:00:1d.0/usb1 |-- usb2.1 | |-- dev | `-- device -> ../../../devices/pci0000:00/0000:00:1d.1/usb2 ... The presence of the "dev" file lets udev create real device nodes. kay@pim:~/src/linux-2.6> tree /dev/bus/usb/ /dev/bus/usb/ |-- 1 | `-- 1 |-- 2 | `-- 1 ... udev rule: SUBSYSTEM="usb_device", PROGRAM="/sbin/usb_device %k", NAME="%c" (echo $1 | /bin/sed 's/usb\([0-9]*\)\.\([0-9]*\)/bus\/usb\/\1\/\2/') This makes libusb pick up the real nodes instead of the mounted usbfs: export USB_DEVFS_PATH=/dev/bus/usb Background: All this makes it possible to manage usb devices with udev instead of the devfs solution. We are currently working on a pam_console/resmgr replacement driven by udev and a pam-helper. It applies ACL's to device nodes, which is required for modern desktop functionalty like "Fast User Switching" or multiple local login support. New patch with its own major. I've succesfully disabled usbfs and use real nodes only on my box. With: "export USB_DEVFS_PATH=/dev/bus/usb" libusb picks up the udev managed nodes instead of reading usbfs files. This makes udev to provide symlinks for libusb to pick up: SUBSYSTEM="usb_device", PROGRAM="/sbin/usbdevice %k", SYMLINK="%c" /sbin/usbdevice: #!/bin/sh echo $1 | /bin/sed 's/usbdev\([0-9]*\)\.\([0-9]*\)/bus\/usb\/\1\/\2/' Signed-off-by: Kay Sievers 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 724637792996..434e35120c65 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -5,6 +5,7 @@ #include #define USB_MAJOR 180 +#define USB_DEVICE_MAJOR 189 #ifdef __KERNEL__ @@ -349,6 +350,7 @@ struct usb_device { char *manufacturer; char *serial; /* static strings from the device */ struct list_head filelist; + struct class_device *class_dev; struct dentry *usbfs_dentry; /* usbfs dentry entry for the device */ /* -- cgit v1.2.3 From dc5bed091a7a5fe378055c30a2da874f77228b71 Mon Sep 17 00:00:00 2001 From: Olav Kongas Date: Thu, 4 Aug 2005 16:46:28 +0300 Subject: [PATCH] USB: isp116x-hcd: use fixed power-on-to-power-good-time This patch removes the power-on-to-power-good-time configuration option for isp116x-hcd. Signed-off-by: Olav Kongas Signed-off-by: Greg Kroah-Hartman --- include/linux/usb_isp116x.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb_isp116x.h b/include/linux/usb_isp116x.h index 5f5a9d9bd6c2..9f4fb5626816 100644 --- a/include/linux/usb_isp116x.h +++ b/include/linux/usb_isp116x.h @@ -26,8 +26,6 @@ struct isp116x_platform_data { /* Ganged port power switching (0) or individual port power switching (1) */ unsigned power_switching_mode:1; - /* Given port_power, msec/2 after power on till power good */ - u8 potpg; /* Hardware reset set/clear. If implemented, this function must: if set == 0, deassert chip's HW reset pin otherwise, assert chip's HW reset pin */ -- cgit v1.2.3 From d4d62861b5cdb0ecfcae448e4281623284de5d05 Mon Sep 17 00:00:00 2001 From: Olav Kongas Date: Thu, 4 Aug 2005 16:48:19 +0300 Subject: [PATCH] USB: isp116x-hcd: remove unnecessary ClockNotStop configuration option Signed-off-by: Olav Kongas Signed-off-by: Greg Kroah-Hartman --- include/linux/usb_isp116x.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb_isp116x.h b/include/linux/usb_isp116x.h index 9f4fb5626816..0d21407ccfc2 100644 --- a/include/linux/usb_isp116x.h +++ b/include/linux/usb_isp116x.h @@ -7,19 +7,17 @@ struct isp116x_platform_data { /* Enable internal resistors on downstream ports */ unsigned sel15Kres:1; - /* Chip's internal clock won't be stopped in suspended state. - Setting/unsetting this bit takes effect only if - 'remote_wakeup_enable' below is not set. */ - unsigned clknotstop:1; /* On-chip overcurrent protection */ unsigned oc_enable:1; /* INT output polarity */ unsigned int_act_high:1; /* INT edge or level triggered */ unsigned int_edge_triggered:1; - /* WAKEUP pin connected - NOT SUPPORTED */ - /* unsigned remote_wakeup_connected:1; */ - /* Wakeup by devices on usb bus enabled */ + /* Enable wakeup by devices on usb bus (e.g. wakeup + by attachment/detachment or by device activity + such as moving a mouse). When chosen, this option + prevents stopping internal clock, increasing + thereby power consumption in suspended state. */ unsigned remote_wakeup_enable:1; /* Switch or not to switch (keep always powered) */ unsigned no_power_switching:1; -- cgit v1.2.3 From 165c0f39390212d7a517b80c3bb61cb8f1782fef Mon Sep 17 00:00:00 2001 From: Olav Kongas Date: Thu, 4 Aug 2005 16:52:31 +0300 Subject: [PATCH] USB: isp116x-hcd: support only per-port power switching The isp116x chip will now always be in per-port power switching mode. Remove conf options to set any other mode. Signed-off-by: Olav Kongas Signed-off-by: Greg Kroah-Hartman --- include/linux/usb_isp116x.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb_isp116x.h b/include/linux/usb_isp116x.h index 0d21407ccfc2..c028d724be94 100644 --- a/include/linux/usb_isp116x.h +++ b/include/linux/usb_isp116x.h @@ -19,11 +19,6 @@ struct isp116x_platform_data { prevents stopping internal clock, increasing thereby power consumption in suspended state. */ unsigned remote_wakeup_enable:1; - /* Switch or not to switch (keep always powered) */ - unsigned no_power_switching:1; - /* Ganged port power switching (0) or individual port - power switching (1) */ - unsigned power_switching_mode:1; /* Hardware reset set/clear. If implemented, this function must: if set == 0, deassert chip's HW reset pin otherwise, assert chip's HW reset pin */ -- cgit v1.2.3 From 9d233d9faedfd8a4ee22288c1fdc698a6f75db21 Mon Sep 17 00:00:00 2001 From: Olav Kongas Date: Thu, 4 Aug 2005 16:54:08 +0300 Subject: [PATCH] USB: isp116x-hcd: per-port overcurrent reporting This patch sets the isp116x to report overcurrent always per-port. Signed-off-by: Olav Kongas Signed-off-by: Greg Kroah-Hartman --- include/linux/usb_isp116x.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb_isp116x.h b/include/linux/usb_isp116x.h index c028d724be94..8f0b3c226968 100644 --- a/include/linux/usb_isp116x.h +++ b/include/linux/usb_isp116x.h @@ -7,7 +7,7 @@ struct isp116x_platform_data { /* Enable internal resistors on downstream ports */ unsigned sel15Kres:1; - /* On-chip overcurrent protection */ + /* On-chip overcurrent detection */ unsigned oc_enable:1; /* INT output polarity */ unsigned int_act_high:1; -- cgit v1.2.3 From f8d23d309809ae69c763520dababb7e845938272 Mon Sep 17 00:00:00 2001 From: Olav Kongas Date: Thu, 4 Aug 2005 17:02:54 +0300 Subject: [PATCH] USB: isp116x-hcd: remove clock() and reset() This patch removes support for user-provided platform-specific hardware reset and clock starting/stopping functions. Hardware reset was needed earlier as getting the software reset working was tricky due to the lack of documentation. Recently, a number of people using isp116x have said the software reset is working for them. I haven't heard of anybody using the clock starting/stopping. Signed-off-by: Olav Kongas Signed-off-by: Greg Kroah-Hartman --- include/linux/usb_isp116x.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb_isp116x.h b/include/linux/usb_isp116x.h index 8f0b3c226968..436dd8a2b64a 100644 --- a/include/linux/usb_isp116x.h +++ b/include/linux/usb_isp116x.h @@ -19,15 +19,6 @@ struct isp116x_platform_data { prevents stopping internal clock, increasing thereby power consumption in suspended state. */ unsigned remote_wakeup_enable:1; - /* Hardware reset set/clear. If implemented, this function must: - if set == 0, deassert chip's HW reset pin - otherwise, assert chip's HW reset pin */ - void (*reset) (struct device * dev, int set); - /* Hardware clock start/stop. If implemented, this function must: - if start == 0, stop the external clock - otherwise, start the external clock - */ - void (*clock) (struct device * dev, int start); /* Inter-io delay (ns). The chip is picky about access timings; it expects at least: 150ns delay between consecutive accesses to DATA_REG, -- cgit v1.2.3 From b375a0495fd622037560c73c05f23ae6f127bb0c Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 29 Jul 2005 16:11:07 -0400 Subject: [PATCH] USB: URB_ASYNC_UNLINK flag removed from the kernel 29 July 2005, Cambridge, MA: This afternoon Alan Stern submitted a patch to remove the URB_ASYNC_UNLINK flag from the Linux kernel. Mr. Stern explained, "This flag is a relic from an earlier, less-well-designed system. For over a year it hasn't been used for anything other than printing warning messages." An anonymous spokesman for the Linux kernel development community commented, "This is exactly the sort of thing we see happening all the time. As the kernel evolves, support for old techniques and old code can be jettisoned and replaced by newer, better approaches. Proprietary operating systems do not have the freedom or flexibility to change so quickly." Mr. Stern, a staff member at Harvard University's Rowland Institute who works on Linux only as a hobby, noted that the patch (labelled as548) did not update two files, keyspan.c and option.c, in the USB drivers' "serial" subdirectory. "Those files need more extensive changes," he remarked. "They examine the status field of several URBs at times when they're not supposed to. That will need to be fixed before the URB_ASYNC_UNLINK flag is removed." Greg Kroah-Hartman, the kernel maintainer responsible for overseeing all of Linux's USB drivers, did not respond to our inquiries or return our calls. His only comment was "Applied, thanks." Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 434e35120c65..4dbe580f9335 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -616,7 +616,6 @@ extern int usb_disabled(void); #define URB_ISO_ASAP 0x0002 /* iso-only, urb->start_frame ignored */ #define URB_NO_TRANSFER_DMA_MAP 0x0004 /* urb->transfer_dma valid on submit */ #define URB_NO_SETUP_DMA_MAP 0x0008 /* urb->setup_dma valid on submit */ -#define URB_ASYNC_UNLINK 0x0010 /* usb_unlink_urb() returns asap */ #define URB_NO_FSBR 0x0020 /* UHCI-specific */ #define URB_ZERO_PACKET 0x0040 /* Finish bulk OUTs with short packet */ #define URB_NO_INTERRUPT 0x0080 /* HINT: no non-error interrupt needed */ @@ -724,13 +723,7 @@ typedef void (*usb_complete_t)(struct urb *, struct pt_regs *); * Initialization: * * All URBs submitted must initialize the dev, pipe, transfer_flags (may be - * zero), and complete fields. - * The URB_ASYNC_UNLINK transfer flag affects later invocations of - * the usb_unlink_urb() routine. Note: Failure to set URB_ASYNC_UNLINK - * with usb_unlink_urb() is deprecated. For synchronous unlinks use - * usb_kill_urb() instead. - * - * All URBs must also initialize + * zero), and complete fields. All URBs must also initialize * transfer_buffer and transfer_buffer_length. They may provide the * URB_SHORT_NOT_OK transfer flag, indicating that short reads are * to be treated as errors; that flag is invalid for write requests. -- cgit v1.2.3 From 507d37cf269ebbd1b32bcc435fe577e411f73151 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 9 Sep 2005 02:30:07 -0300 Subject: [CCID] Only call the HC insert_options methods when requested Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/dccp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 007c290f74d4..5e0af0d08a93 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -433,6 +433,8 @@ struct dccp_sock { struct ccid *dccps_hc_tx_ccid; struct dccp_options_received dccps_options_received; enum dccp_role dccps_role:2; + __u8 dccps_hc_rx_insert_options:1; + __u8 dccps_hc_tx_insert_options:1; }; static inline struct dccp_sock *dccp_sk(const struct sock *sk) -- cgit v1.2.3 From b0e567806d16586629468c824dfb2e71155df7da Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 9 Sep 2005 02:38:35 -0300 Subject: [DCCP] Introduce dccp_timestamp To start the timestamps with 0.0ms, easing the integer maths in the CCIDs, this probably will be reworked to use the to be introduced struct timeval_offset infrastructure out of skb_get_timestamp, etc. Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/dccp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 5e0af0d08a93..8bf4bacb5051 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -432,6 +432,7 @@ struct dccp_sock { struct ccid *dccps_hc_rx_ccid; struct ccid *dccps_hc_tx_ccid; struct dccp_options_received dccps_options_received; + struct timeval dccps_epoch; enum dccp_role dccps_role:2; __u8 dccps_hc_rx_insert_options:1; __u8 dccps_hc_tx_insert_options:1; -- cgit v1.2.3 From 144a50ea5e1487b8b8e722289b4177713354448a Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Tue, 9 Aug 2005 00:20:10 -0400 Subject: [PATCH] must_check attributes for PCI layer. Self explanatory really. Some newer gcc's print a warning if a function is used and we don't check its result. We do this for a bunch of things in the kernel already, this extends that to the PCI layer. Based on a patch originally from Arjan van de Ven. Signed-off-by: Dave Jones Signed-off-by: Arjan van de Ven Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 6caaba0af469..609499356e07 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -376,32 +376,32 @@ static inline int pci_write_config_dword(struct pci_dev *dev, int where, u32 val return pci_bus_write_config_dword (dev->bus, dev->devfn, where, val); } -int pci_enable_device(struct pci_dev *dev); -int pci_enable_device_bars(struct pci_dev *dev, int mask); +int __must_check pci_enable_device(struct pci_dev *dev); +int __must_check pci_enable_device_bars(struct pci_dev *dev, int mask); void pci_disable_device(struct pci_dev *dev); void pci_set_master(struct pci_dev *dev); #define HAVE_PCI_SET_MWI -int pci_set_mwi(struct pci_dev *dev); +int __must_check pci_set_mwi(struct pci_dev *dev); void pci_clear_mwi(struct pci_dev *dev); void pci_intx(struct pci_dev *dev, int enable); -int pci_set_dma_mask(struct pci_dev *dev, u64 mask); -int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask); +int __must_check pci_set_dma_mask(struct pci_dev *dev, u64 mask); +int __must_check pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask); void pci_update_resource(struct pci_dev *dev, struct resource *res, int resno); int pci_assign_resource(struct pci_dev *dev, int i); void pci_restore_bars(struct pci_dev *dev); /* ROM control related routines */ -void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size); -void __iomem *pci_map_rom_copy(struct pci_dev *pdev, size_t *size); +void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size); +void __iomem __must_check *pci_map_rom_copy(struct pci_dev *pdev, size_t *size); void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom); void pci_remove_rom(struct pci_dev *pdev); /* Power management related routines */ int pci_save_state(struct pci_dev *dev); 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); -int pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable); +int __must_check pci_set_power_state(struct pci_dev *dev, pci_power_t state); +pci_power_t __must_check pci_choose_state(struct pci_dev *dev, pm_message_t state); +int __must_check pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable); /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */ void pci_bus_assign_resources(struct pci_bus *bus); -- cgit v1.2.3 From 5e41ff9e0650f327a6c819841fa412da95d57319 Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Fri, 9 Sep 2005 13:01:35 -0700 Subject: [PATCH] security: enable atomic inode security labeling The following patch set enables atomic security labeling of newly created inodes by altering the fs code to invoke a new LSM hook to obtain the security attribute to apply to a newly created inode and to set up the incore inode security state during the inode creation transaction. This parallels the existing processing for setting ACLs on newly created inodes. Otherwise, it is possible for new inodes to be accessed by another thread via the dcache prior to complete security setup (presently handled by the post_create/mkdir/... LSM hooks in the VFS) and a newly created inode may be left unlabeled on the disk in the event of a crash. SELinux presently works around the issue by ensuring that the incore inode security label is initialized to a special SID that is inaccessible to unprivileged processes (in accordance with policy), thereby preventing inappropriate access but potentially causing false denials on legitimate accesses. A simple test program demonstrates such false denials on SELinux, and the patch solves the problem. Similar such false denials have been encountered in real applications. This patch defines a new inode_init_security LSM hook to obtain the security attribute to apply to a newly created inode and to set up the incore inode security state for it, and adds a corresponding hook function implementation to SELinux. Signed-off-by: Stephen Smalley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/security.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 7aab6ab7c57f..d4f3b7a94ea6 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -250,6 +250,25 @@ struct swap_info_struct; * @inode contains the inode structure. * Deallocate the inode security structure and set @inode->i_security to * NULL. + * @inode_init_security: + * Obtain the security attribute name suffix and value to set on a newly + * created inode and set up the incore security field for the new inode. + * This hook is called by the fs code as part of the inode creation + * transaction and provides for atomic labeling of the inode, unlike + * the post_create/mkdir/... hooks called by the VFS. The hook function + * is expected to allocate the name and value via kmalloc, with the caller + * being responsible for calling kfree after using them. + * If the security module does not use security attributes or does + * not wish to put a security attribute on this particular inode, + * then it should return -EOPNOTSUPP to skip this processing. + * @inode contains the inode structure of the newly created inode. + * @dir contains the inode structure of the parent directory. + * @name will be set to the allocated name suffix (e.g. selinux). + * @value will be set to the allocated attribute value. + * @len will be set to the length of the value. + * Returns 0 if @name and @value have been successfully set, + * -EOPNOTSUPP if no security attribute is needed, or + * -ENOMEM on memory allocation failure. * @inode_create: * Check permission to create a regular file. * @dir contains inode structure of the parent of the new file. @@ -1080,6 +1099,8 @@ struct security_operations { int (*inode_alloc_security) (struct inode *inode); void (*inode_free_security) (struct inode *inode); + int (*inode_init_security) (struct inode *inode, struct inode *dir, + char **name, void **value, size_t *len); int (*inode_create) (struct inode *dir, struct dentry *dentry, int mode); void (*inode_post_create) (struct inode *dir, @@ -1442,6 +1463,17 @@ static inline void security_inode_free (struct inode *inode) return; security_ops->inode_free_security (inode); } + +static inline int security_inode_init_security (struct inode *inode, + struct inode *dir, + char **name, + void **value, + size_t *len) +{ + if (unlikely (IS_PRIVATE (inode))) + return -EOPNOTSUPP; + return security_ops->inode_init_security (inode, dir, name, value, len); +} static inline int security_inode_create (struct inode *dir, struct dentry *dentry, @@ -2171,6 +2203,15 @@ static inline int security_inode_alloc (struct inode *inode) static inline void security_inode_free (struct inode *inode) { } + +static inline int security_inode_init_security (struct inode *inode, + struct inode *dir, + char **name, + void **value, + size_t *len) +{ + return -EOPNOTSUPP; +} static inline int security_inode_create (struct inode *dir, struct dentry *dentry, -- cgit v1.2.3 From a74574aafea3a63add3251047601611111f44562 Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Fri, 9 Sep 2005 13:01:44 -0700 Subject: [PATCH] Remove security_inode_post_create/mkdir/symlink/mknod hooks This patch removes the inode_post_create/mkdir/mknod/symlink LSM hooks as they are obsoleted by the new inode_init_security hook that enables atomic inode security labeling. If anyone sees any reason to retain these hooks, please speak now. Also, is anyone using the post_rename/link hooks; if not, those could also be removed. Signed-off-by: Stephen Smalley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/security.h | 90 ------------------------------------------------ 1 file changed, 90 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index d4f3b7a94ea6..875225bf8986 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -275,12 +275,6 @@ struct swap_info_struct; * @dentry contains the dentry structure for the file to be created. * @mode contains the file mode of the file to be created. * Return 0 if permission is granted. - * @inode_post_create: - * Set the security attributes on a newly created regular file. This hook - * is called after a file has been successfully created. - * @dir contains the inode structure of the parent directory of the new file. - * @dentry contains the the dentry structure for the newly created file. - * @mode contains the file mode. * @inode_link: * Check permission before creating a new hard link to a file. * @old_dentry contains the dentry structure for an existing link to the file. @@ -303,13 +297,6 @@ struct swap_info_struct; * @dentry contains the dentry structure of the symbolic link. * @old_name contains the pathname of file. * Return 0 if permission is granted. - * @inode_post_symlink: - * @dir contains the inode structure of the parent directory of the new link. - * @dentry contains the dentry structure of new symbolic link. - * @old_name contains the pathname of file. - * Set security attributes for a newly created symbolic link. Note that - * @dentry->d_inode may be NULL, since the filesystem might not - * instantiate the dentry (e.g. NFS). * @inode_mkdir: * Check permissions to create a new directory in the existing directory * associated with inode strcture @dir. @@ -317,11 +304,6 @@ struct swap_info_struct; * @dentry contains the dentry structure of new directory. * @mode contains the mode of new directory. * Return 0 if permission is granted. - * @inode_post_mkdir: - * Set security attributes on a newly created directory. - * @dir contains the inode structure of parent of the directory to be created. - * @dentry contains the dentry structure of new directory. - * @mode contains the mode of new directory. * @inode_rmdir: * Check the permission to remove a directory. * @dir contains the inode structure of parent of the directory to be removed. @@ -337,13 +319,6 @@ struct swap_info_struct; * @mode contains the mode of the new file. * @dev contains the the device number. * Return 0 if permission is granted. - * @inode_post_mknod: - * Set security attributes on a newly created special file (or socket or - * fifo file created via the mknod system call). - * @dir contains the inode structure of parent of the new node. - * @dentry contains the dentry structure of the new node. - * @mode contains the mode of the new node. - * @dev contains the the device number. * @inode_rename: * Check for permission to rename a file or directory. * @old_dir contains the inode structure for parent of the old link. @@ -1103,8 +1078,6 @@ struct security_operations { char **name, void **value, size_t *len); int (*inode_create) (struct inode *dir, struct dentry *dentry, int mode); - void (*inode_post_create) (struct inode *dir, - struct dentry *dentry, int mode); int (*inode_link) (struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry); void (*inode_post_link) (struct dentry *old_dentry, @@ -1112,17 +1085,10 @@ struct security_operations { int (*inode_unlink) (struct inode *dir, struct dentry *dentry); int (*inode_symlink) (struct inode *dir, struct dentry *dentry, const char *old_name); - void (*inode_post_symlink) (struct inode *dir, - struct dentry *dentry, - const char *old_name); int (*inode_mkdir) (struct inode *dir, struct dentry *dentry, int mode); - void (*inode_post_mkdir) (struct inode *dir, struct dentry *dentry, - int mode); int (*inode_rmdir) (struct inode *dir, struct dentry *dentry); int (*inode_mknod) (struct inode *dir, struct dentry *dentry, int mode, dev_t dev); - void (*inode_post_mknod) (struct inode *dir, struct dentry *dentry, - int mode, dev_t dev); int (*inode_rename) (struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); void (*inode_post_rename) (struct inode *old_dir, @@ -1484,15 +1450,6 @@ static inline int security_inode_create (struct inode *dir, return security_ops->inode_create (dir, dentry, mode); } -static inline void security_inode_post_create (struct inode *dir, - struct dentry *dentry, - int mode) -{ - if (dentry->d_inode && unlikely (IS_PRIVATE (dentry->d_inode))) - return; - security_ops->inode_post_create (dir, dentry, mode); -} - static inline int security_inode_link (struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) @@ -1528,15 +1485,6 @@ static inline int security_inode_symlink (struct inode *dir, return security_ops->inode_symlink (dir, dentry, old_name); } -static inline void security_inode_post_symlink (struct inode *dir, - struct dentry *dentry, - const char *old_name) -{ - if (dentry->d_inode && unlikely (IS_PRIVATE (dentry->d_inode))) - return; - security_ops->inode_post_symlink (dir, dentry, old_name); -} - static inline int security_inode_mkdir (struct inode *dir, struct dentry *dentry, int mode) @@ -1546,15 +1494,6 @@ static inline int security_inode_mkdir (struct inode *dir, return security_ops->inode_mkdir (dir, dentry, mode); } -static inline void security_inode_post_mkdir (struct inode *dir, - struct dentry *dentry, - int mode) -{ - if (dentry->d_inode && unlikely (IS_PRIVATE (dentry->d_inode))) - return; - security_ops->inode_post_mkdir (dir, dentry, mode); -} - static inline int security_inode_rmdir (struct inode *dir, struct dentry *dentry) { @@ -1572,15 +1511,6 @@ static inline int security_inode_mknod (struct inode *dir, return security_ops->inode_mknod (dir, dentry, mode, dev); } -static inline void security_inode_post_mknod (struct inode *dir, - struct dentry *dentry, - int mode, dev_t dev) -{ - if (dentry->d_inode && unlikely (IS_PRIVATE (dentry->d_inode))) - return; - security_ops->inode_post_mknod (dir, dentry, mode, dev); -} - static inline int security_inode_rename (struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, @@ -2220,11 +2150,6 @@ static inline int security_inode_create (struct inode *dir, return 0; } -static inline void security_inode_post_create (struct inode *dir, - struct dentry *dentry, - int mode) -{ } - static inline int security_inode_link (struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) @@ -2250,11 +2175,6 @@ static inline int security_inode_symlink (struct inode *dir, return 0; } -static inline void security_inode_post_symlink (struct inode *dir, - struct dentry *dentry, - const char *old_name) -{ } - static inline int security_inode_mkdir (struct inode *dir, struct dentry *dentry, int mode) @@ -2262,11 +2182,6 @@ static inline int security_inode_mkdir (struct inode *dir, return 0; } -static inline void security_inode_post_mkdir (struct inode *dir, - struct dentry *dentry, - int mode) -{ } - static inline int security_inode_rmdir (struct inode *dir, struct dentry *dentry) { @@ -2280,11 +2195,6 @@ static inline int security_inode_mknod (struct inode *dir, return 0; } -static inline void security_inode_post_mknod (struct inode *dir, - struct dentry *dentry, - int mode, dev_t dev) -{ } - static inline int security_inode_rename (struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, -- cgit v1.2.3 From e31e14ec356f36b131576be5bc31d8fef7e95483 Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Fri, 9 Sep 2005 13:01:45 -0700 Subject: [PATCH] remove the inode_post_link and inode_post_rename LSM hooks This patch removes the inode_post_link and inode_post_rename LSM hooks as they are unused (and likely useless). Signed-off-by: Stephen Smalley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/security.h | 49 ------------------------------------------------ 1 file changed, 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 875225bf8986..55b02e1c73f4 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -281,11 +281,6 @@ struct swap_info_struct; * @dir contains the inode structure of the parent directory of the new link. * @new_dentry contains the dentry structure for the new link. * Return 0 if permission is granted. - * @inode_post_link: - * Set security attributes for a new hard link to a file. - * @old_dentry contains the dentry structure for the existing link. - * @dir contains the inode structure of the parent directory of the new file. - * @new_dentry contains the dentry structure for the new file link. * @inode_unlink: * Check the permission to remove a hard link to a file. * @dir contains the inode structure of parent directory of the file. @@ -326,12 +321,6 @@ struct swap_info_struct; * @new_dir contains the inode structure for parent of the new link. * @new_dentry contains the dentry structure of the new link. * Return 0 if permission is granted. - * @inode_post_rename: - * Set security attributes on a renamed file or directory. - * @old_dir contains the inode structure for parent of the old link. - * @old_dentry contains the dentry structure of the old link. - * @new_dir contains the inode structure for parent of the new link. - * @new_dentry contains the dentry structure of the new link. * @inode_readlink: * Check the permission to read the symbolic link. * @dentry contains the dentry structure for the file link. @@ -1080,8 +1069,6 @@ struct security_operations { struct dentry *dentry, int mode); int (*inode_link) (struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry); - void (*inode_post_link) (struct dentry *old_dentry, - struct inode *dir, struct dentry *new_dentry); int (*inode_unlink) (struct inode *dir, struct dentry *dentry); int (*inode_symlink) (struct inode *dir, struct dentry *dentry, const char *old_name); @@ -1091,10 +1078,6 @@ struct security_operations { int mode, dev_t dev); int (*inode_rename) (struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); - void (*inode_post_rename) (struct inode *old_dir, - struct dentry *old_dentry, - 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); @@ -1459,15 +1442,6 @@ static inline int security_inode_link (struct dentry *old_dentry, return security_ops->inode_link (old_dentry, dir, new_dentry); } -static inline void security_inode_post_link (struct dentry *old_dentry, - struct inode *dir, - struct dentry *new_dentry) -{ - if (new_dentry->d_inode && unlikely (IS_PRIVATE (new_dentry->d_inode))) - return; - security_ops->inode_post_link (old_dentry, dir, new_dentry); -} - static inline int security_inode_unlink (struct inode *dir, struct dentry *dentry) { @@ -1523,18 +1497,6 @@ static inline int security_inode_rename (struct inode *old_dir, new_dir, new_dentry); } -static inline void security_inode_post_rename (struct inode *old_dir, - struct dentry *old_dentry, - struct inode *new_dir, - struct dentry *new_dentry) -{ - if (unlikely (IS_PRIVATE (old_dentry->d_inode) || - (new_dentry->d_inode && IS_PRIVATE (new_dentry->d_inode)))) - return; - security_ops->inode_post_rename (old_dir, old_dentry, - new_dir, new_dentry); -} - static inline int security_inode_readlink (struct dentry *dentry) { if (unlikely (IS_PRIVATE (dentry->d_inode))) @@ -2157,11 +2119,6 @@ static inline int security_inode_link (struct dentry *old_dentry, return 0; } -static inline void security_inode_post_link (struct dentry *old_dentry, - struct inode *dir, - struct dentry *new_dentry) -{ } - static inline int security_inode_unlink (struct inode *dir, struct dentry *dentry) { @@ -2203,12 +2160,6 @@ static inline int security_inode_rename (struct inode *old_dir, return 0; } -static inline void security_inode_post_rename (struct inode *old_dir, - struct dentry *old_dentry, - struct inode *new_dir, - struct dentry *new_dentry) -{ } - static inline int security_inode_readlink (struct dentry *dentry) { return 0; -- cgit v1.2.3 From 383f2835eb9afb723af71850037b2f074ac9db60 Mon Sep 17 00:00:00 2001 From: "Chen, Kenneth W" Date: Fri, 9 Sep 2005 13:02:02 -0700 Subject: [PATCH] Prefetch kernel stacks to speed up context switch For architecture like ia64, the switch stack structure is fairly large (currently 528 bytes). For context switch intensive application, we found that significant amount of cache misses occurs in switch_to() function. The following patch adds a hook in the schedule() function to prefetch switch stack structure as soon as 'next' task is determined. This allows maximum overlap in prefetch cache lines for that structure. Signed-off-by: Ken Chen Cc: Ingo Molnar Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ea1b5f32ec5c..c551e6a1447e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -604,6 +604,11 @@ extern int groups_search(struct group_info *group_info, gid_t grp); #define GROUP_AT(gi, i) \ ((gi)->blocks[(i)/NGROUPS_PER_BLOCK][(i)%NGROUPS_PER_BLOCK]) +#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK +extern void prefetch_stack(struct task_struct*); +#else +static inline void prefetch_stack(struct task_struct *t) { } +#endif struct audit_context; /* See audit.c */ struct mempolicy; -- cgit v1.2.3 From fac92becdaecff64dd91daab0292c5131de92f0d Mon Sep 17 00:00:00 2001 From: Andrew Stribblehill Date: Fri, 9 Sep 2005 13:02:04 -0700 Subject: [PATCH] bfs: fix endianness, signedness; add trivial bugfix * Makes BFS code endianness-clean. * Fixes some signedness warnings. * Fixes a problem in fs/bfs/inode.c:164 where inodes not synced to disk don't get fully marked as clean. Here's how to reproduce it: # mount -o loop -t bfs /bfs.img /mnt # df -i /mnt Filesystem Inodes IUsed IFree IUse% Mounted on /bfs.img 48 1 47 3% /mnt # df -k /mnt Filesystem 1K-blocks Used Available Use% Mounted on /bfs.img 512 5 508 1% /mnt # cp 60k-archive.zip /mnt/mt.zip # df -k /mnt Filesystem 1K-blocks Used Available Use% Mounted on /bfs.img 512 65 447 13% /mnt # df -i /mnt Filesystem Inodes IUsed IFree IUse% Mounted on /bfs.img 48 2 46 5% /mnt # rm /mnt/mt.zip # echo $? 0 [If the unlink happens before the buffers flush, the following happens:] # df -i /mnt Filesystem Inodes IUsed IFree IUse% Mounted on /bfs.img 48 2 46 5% /mnt # df -k /mnt Filesystem 1K-blocks Used Available Use% Mounted on /bfs.img 512 65 447 13% /mnt fs/bfs/bfs.h | 1 Signed-off-by: Andrew Stribblehill Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bfs_fs.h | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bfs_fs.h b/include/linux/bfs_fs.h index f7f0913cd110..c1237aa92e38 100644 --- a/include/linux/bfs_fs.h +++ b/include/linux/bfs_fs.h @@ -14,8 +14,9 @@ #define BFS_INODES_PER_BLOCK 8 /* SVR4 vnode type values (bfs_inode->i_vtype) */ -#define BFS_VDIR 2 -#define BFS_VREG 1 +#define BFS_VDIR 2L +#define BFS_VREG 1L + /* BFS inode layout on disk */ struct bfs_inode { @@ -58,22 +59,22 @@ struct bfs_super_block { __u32 s_padding[118]; }; -#define BFS_NZFILESIZE(ip) \ - (((ip)->i_eoffset + 1) - (ip)->i_sblock * BFS_BSIZE) - -#define BFS_FILESIZE(ip) \ - ((ip)->i_sblock == 0 ? 0 : BFS_NZFILESIZE(ip)) - -#define BFS_FILEBLOCKS(ip) \ - ((ip)->i_sblock == 0 ? 0 : ((ip)->i_eblock + 1) - (ip)->i_sblock) #define BFS_OFF2INO(offset) \ ((((offset) - BFS_BSIZE) / sizeof(struct bfs_inode)) + BFS_ROOT_INO) #define BFS_INO2OFF(ino) \ ((__u32)(((ino) - BFS_ROOT_INO) * sizeof(struct bfs_inode)) + BFS_BSIZE) +#define BFS_NZFILESIZE(ip) \ + ((cpu_to_le32((ip)->i_eoffset) + 1) - cpu_to_le32((ip)->i_sblock) * BFS_BSIZE) + +#define BFS_FILESIZE(ip) \ + ((ip)->i_sblock == 0 ? 0 : BFS_NZFILESIZE(ip)) +#define BFS_FILEBLOCKS(ip) \ + ((ip)->i_sblock == 0 ? 0 : (cpu_to_le32((ip)->i_eblock) + 1) - cpu_to_le32((ip)->i_sblock)) #define BFS_UNCLEAN(bfs_sb, sb) \ - ((bfs_sb->s_from != -1) && (bfs_sb->s_to != -1) && !(sb->s_flags & MS_RDONLY)) + ((cpu_to_le32(bfs_sb->s_from) != -1) && (cpu_to_le32(bfs_sb->s_to) != -1) && !(sb->s_flags & MS_RDONLY)) + #endif /* _LINUX_BFS_FS_H */ -- cgit v1.2.3 From b3743fa4442fc172e950ff0eaf6aa96e7d5ce9be Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Fri, 9 Sep 2005 13:03:23 -0700 Subject: [PATCH] yenta: share code with PCI core Share code between setup-bus.c and yenta_socket.c: use the write-out code of resources to the bridge also in yenta_socket.c, as it provides useful debug output. In addition, it fixes the bug that the CPU-centric resource view might need to be transferred to the PCI-centric view: setup-bus.c does that, while yenta-socket.c did not. Signed-off-by: Dominik Brodowski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 6caaba0af469..c62e89270237 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -326,6 +326,7 @@ extern struct pci_dev *pci_dev_get(struct pci_dev *dev); extern void pci_dev_put(struct pci_dev *dev); extern void pci_remove_bus(struct pci_bus *b); extern void pci_remove_bus_device(struct pci_dev *dev); +void pci_setup_cardbus(struct pci_bus *bus); /* Generic PCI functions exported to card drivers */ -- cgit v1.2.3 From 793cf9e6a54c698e109a599c8b8e303658fcaae6 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 9 Sep 2005 13:03:37 -0700 Subject: [PATCH] v4l: common part Updates and tuner additions - Remove $Id CVS logs for V4L files - Included newer cards. - Added a new NEC protocol for ir based on pulse distance. - Enable ATSC support for DViCO FusionHDTV5 Gold. - Added tuner LG NTSC (TALN mini series). - Fixed tea5767 autodetection. - Resolve more tuner types. - Commented debug function removed from mainstream. - Remove comments from mainstream. Still on development tree. - linux/version dependencies removed. - BTSC Lang1 now is set to auto_stereo mode. - New tuner standby API. - i2c-core.c uses hexadecimal for the i2c address, so it should stay consistent. Signed-off-by: Uli Luckas Signed-off-by: Mac Michaels Signed-off-by: Michael Krufky Signed-off-by: Hermann Pitton Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/videodev.h | 3 --- include/linux/videodev2.h | 4 ---- 2 files changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/videodev.h b/include/linux/videodev.h index 9d6fbde3d29c..1cc8c31b7988 100644 --- a/include/linux/videodev.h +++ b/include/linux/videodev.h @@ -3,7 +3,6 @@ #include #include -#include #define HAVE_V4L2 1 #include @@ -29,7 +28,6 @@ struct video_device void (*release)(struct video_device *vfd); -#if 1 /* to be removed in 2.7.x */ /* obsolete -- fops->owner is used instead */ struct module *owner; /* dev->driver_data will be used instead some day. @@ -37,7 +35,6 @@ struct video_device * so the switch over will be transparent for you. * Or use {pci|usb}_{get|set}_drvdata() directly. */ void *priv; -#endif /* for videodev.c intenal usage -- please don't touch */ int users; /* video_exclusive_{open|close} ... */ diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index acbfc525576d..f623a33b9abe 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -270,7 +270,6 @@ struct v4l2_timecode /* The above is based on SMPTE timecodes */ -#if 1 /* * M P E G C O M P R E S S I O N P A R A M E T E R S * @@ -357,7 +356,6 @@ struct v4l2_mpeg_compression { /* I don't expect the above being perfect yet ;) */ __u32 reserved_5[8]; }; -#endif struct v4l2_jpegcompression { @@ -871,10 +869,8 @@ struct v4l2_streamparm #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) -#if 1 /* experimental */ #define VIDIOC_G_MPEGCOMP _IOR ('V', 6, struct v4l2_mpeg_compression) #define VIDIOC_S_MPEGCOMP _IOW ('V', 7, struct v4l2_mpeg_compression) -#endif #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) -- cgit v1.2.3 From 8b6490e5faafb3a16ea45654fb55f9ff086f1495 Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Fri, 9 Sep 2005 13:04:07 -0700 Subject: [PATCH] files: fix rcu initializers First of a number of files_lock scaability patches. Here are the x86 numbers - tiobench on a 4(8)-way (HT) P4 system on ramdisk : (lockfree) Test 2.6.10-vanilla Stdev 2.6.10-fd Stdev ------------------------------------------------------------- Seqread 1400.8 11.52 1465.4 34.27 Randread 1594 8.86 2397.2 29.21 Seqwrite 242.72 3.47 238.46 6.53 Randwrite 445.74 9.15 446.4 9.75 The performance improvement is very significant. We are getting killed by the cacheline bouncing of the files_struct lock here. Writes on ramdisk (ext2) seems to vary just too much to get any meaningful number. Also, With Tridge's thread_perf test on a 4(8)-way (HT) P4 xeon system : 2.6.12-rc5-vanilla : Running test 'readwrite' with 8 tasks Threads 0.34 +/- 0.01 seconds Processes 0.16 +/- 0.00 seconds 2.6.12-rc5-fd : Running test 'readwrite' with 8 tasks Threads 0.17 +/- 0.02 seconds Processes 0.17 +/- 0.02 seconds I repeated the measurements on ramfs (as opposed to ext2 on ramdisk in the earlier measurement) and I got more consistent results from tiobench : 4(8) way xeon P4 ----------------- (lock-free) Test 2.6.12-rc5 Stdev 2.6.12-rc5-fd Stdev ------------------------------------------------------------- Seqread 1282 18.59 1343.6 26.37 Randread 1517 7 2415 34.27 Seqwrite 702.2 5.27 709.46 5.9 Randwrite 846.86 15.15 919.68 21.4 4-way ppc64 ------------ (lock-free) Test 2.6.12-rc5 Stdev 2.6.12-rc5-fd Stdev ------------------------------------------------------------- Seqread 1549 91.16 1569.6 47.2 Randread 1473.6 25.11 1585.4 69.99 Seqwrite 1096.8 20.03 1136 29.61 Randwrite 1189.6 4.04 1275.2 32.96 Also running Tridge's thread_perf test on ppc64 : 2.6.12-rc5-vanilla -------------------- Running test 'readwrite' with 4 tasks Threads 0.20 +/- 0.02 seconds Processes 0.16 +/- 0.01 seconds 2.6.12-rc5-fd -------------------- Running test 'readwrite' with 4 tasks Threads 0.18 +/- 0.04 seconds Processes 0.16 +/- 0.01 seconds The benefits are huge (upto ~60%) in some cases on x86 primarily due to the atomic operations during acquisition of ->file_lock and cache line bouncing in fast path. ppc64 benefits are modest due to LL/SC based locking, but still statistically significant. This patch: RCU head initilizer no longer needs the head varible name since we don't use list.h lists anymore. Signed-off-by: Dipankar Sarma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index fd276adf0fd5..4e65eb44adfd 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -52,8 +52,8 @@ struct rcu_head { void (*func)(struct rcu_head *head); }; -#define RCU_HEAD_INIT(head) { .next = NULL, .func = NULL } -#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT(head) +#define RCU_HEAD_INIT { .next = NULL, .func = NULL } +#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT #define INIT_RCU_HEAD(ptr) do { \ (ptr)->next = NULL; (ptr)->func = NULL; \ } while (0) -- cgit v1.2.3 From c0dfb2905126e9e94edebbce8d3e05001301f52d Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Fri, 9 Sep 2005 13:04:09 -0700 Subject: [PATCH] files: rcuref APIs Adds a set of primitives to do reference counting for objects that are looked up without locks using RCU. Signed-off-by: Ravikiran Thirumalai Signed-off-by: Dipankar Sarma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rcuref.h | 220 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 220 insertions(+) create mode 100644 include/linux/rcuref.h (limited to 'include/linux') diff --git a/include/linux/rcuref.h b/include/linux/rcuref.h new file mode 100644 index 000000000000..e1adbba14b67 --- /dev/null +++ b/include/linux/rcuref.h @@ -0,0 +1,220 @@ +/* + * rcuref.h + * + * Reference counting for elements of lists/arrays protected by + * RCU. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2005 + * + * Author: Dipankar Sarma + * Ravikiran Thirumalai + * + * See Documentation/RCU/rcuref.txt for detailed user guide. + * + */ + +#ifndef _RCUREF_H_ +#define _RCUREF_H_ + +#ifdef __KERNEL__ + +#include +#include +#include +#include + +/* + * These APIs work on traditional atomic_t counters used in the + * kernel for reference counting. Under special circumstances + * where a lock-free get() operation races with a put() operation + * these APIs can be used. See Documentation/RCU/rcuref.txt. + */ + +#ifdef __HAVE_ARCH_CMPXCHG + +/** + * rcuref_inc - increment refcount for object. + * @rcuref: reference counter in the object in question. + * + * This should be used only for objects where we use RCU and + * use the rcuref_inc_lf() api to acquire a reference + * in a lock-free reader-side critical section. + */ +static inline void rcuref_inc(atomic_t *rcuref) +{ + atomic_inc(rcuref); +} + +/** + * rcuref_dec - decrement refcount for object. + * @rcuref: reference counter in the object in question. + * + * This should be used only for objects where we use RCU and + * use the rcuref_inc_lf() api to acquire a reference + * in a lock-free reader-side critical section. + */ +static inline void rcuref_dec(atomic_t *rcuref) +{ + atomic_dec(rcuref); +} + +/** + * rcuref_dec_and_test - decrement refcount for object and test + * @rcuref: reference counter in the object. + * @release: pointer to the function that will clean up the object + * when the last reference to the object is released. + * This pointer is required. + * + * Decrement the refcount, and if 0, return 1. Else return 0. + * + * This should be used only for objects where we use RCU and + * use the rcuref_inc_lf() api to acquire a reference + * in a lock-free reader-side critical section. + */ +static inline int rcuref_dec_and_test(atomic_t *rcuref) +{ + return atomic_dec_and_test(rcuref); +} + +/* + * cmpxchg is needed on UP too, if deletions to the list/array can happen + * in interrupt context. + */ + +/** + * rcuref_inc_lf - Take reference to an object in a read-side + * critical section protected by RCU. + * @rcuref: reference counter in the object in question. + * + * Try and increment the refcount by 1. The increment might fail if + * the reference counter has been through a 1 to 0 transition and + * is no longer part of the lock-free list. + * Returns non-zero on successful increment and zero otherwise. + */ +static inline int rcuref_inc_lf(atomic_t *rcuref) +{ + int c, old; + c = atomic_read(rcuref); + while (c && (old = cmpxchg(&rcuref->counter, c, c + 1)) != c) + c = old; + return c; +} + +#else /* !__HAVE_ARCH_CMPXCHG */ + +extern spinlock_t __rcuref_hash[]; + +/* + * Use a hash table of locks to protect the reference count + * since cmpxchg is not available in this arch. + */ +#ifdef CONFIG_SMP +#define RCUREF_HASH_SIZE 4 +#define RCUREF_HASH(k) \ + (&__rcuref_hash[(((unsigned long)k)>>8) & (RCUREF_HASH_SIZE-1)]) +#else +#define RCUREF_HASH_SIZE 1 +#define RCUREF_HASH(k) &__rcuref_hash[0] +#endif /* CONFIG_SMP */ + +/** + * rcuref_inc - increment refcount for object. + * @rcuref: reference counter in the object in question. + * + * This should be used only for objects where we use RCU and + * use the rcuref_inc_lf() api to acquire a reference in a lock-free + * reader-side critical section. + */ +static inline void rcuref_inc(atomic_t *rcuref) +{ + unsigned long flags; + spin_lock_irqsave(RCUREF_HASH(rcuref), flags); + rcuref->counter += 1; + spin_unlock_irqrestore(RCUREF_HASH(rcuref), flags); +} + +/** + * rcuref_dec - decrement refcount for object. + * @rcuref: reference counter in the object in question. + * + * This should be used only for objects where we use RCU and + * use the rcuref_inc_lf() api to acquire a reference in a lock-free + * reader-side critical section. + */ +static inline void rcuref_dec(atomic_t *rcuref) +{ + unsigned long flags; + spin_lock_irqsave(RCUREF_HASH(rcuref), flags); + rcuref->counter -= 1; + spin_unlock_irqrestore(RCUREF_HASH(rcuref), flags); +} + +/** + * rcuref_dec_and_test - decrement refcount for object and test + * @rcuref: reference counter in the object. + * @release: pointer to the function that will clean up the object + * when the last reference to the object is released. + * This pointer is required. + * + * Decrement the refcount, and if 0, return 1. Else return 0. + * + * This should be used only for objects where we use RCU and + * use the rcuref_inc_lf() api to acquire a reference in a lock-free + * reader-side critical section. + */ +static inline int rcuref_dec_and_test(atomic_t *rcuref) +{ + unsigned long flags; + spin_lock_irqsave(RCUREF_HASH(rcuref), flags); + rcuref->counter--; + if (!rcuref->counter) { + spin_unlock_irqrestore(RCUREF_HASH(rcuref), flags); + return 1; + } else { + spin_unlock_irqrestore(RCUREF_HASH(rcuref), flags); + return 0; + } +} + +/** + * rcuref_inc_lf - Take reference to an object of a lock-free collection + * by traversing a lock-free list/array. + * @rcuref: reference counter in the object in question. + * + * Try and increment the refcount by 1. The increment might fail if + * the reference counter has been through a 1 to 0 transition and + * object is no longer part of the lock-free list. + * Returns non-zero on successful increment and zero otherwise. + */ +static inline int rcuref_inc_lf(atomic_t *rcuref) +{ + int ret; + unsigned long flags; + spin_lock_irqsave(RCUREF_HASH(rcuref), flags); + if (rcuref->counter) + ret = rcuref->counter++; + else + ret = 0; + spin_unlock_irqrestore(RCUREF_HASH(rcuref), flags); + return ret; +} + + +#endif /* !__HAVE_ARCH_CMPXCHG */ + +#endif /* __KERNEL__ */ +#endif /* _RCUREF_H_ */ -- cgit v1.2.3 From badf16621c1f9d1ac753be056fce11b43d6e0be5 Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Fri, 9 Sep 2005 13:04:10 -0700 Subject: [PATCH] files: break up files struct In order for the RCU to work, the file table array, sets and their sizes must be updated atomically. Instead of ensuring this through too many memory barriers, we put the arrays and their sizes in a separate structure. This patch takes the first step of putting the file table elements in a separate structure fdtable that is embedded withing files_struct. It also changes all the users to refer to the file table using files_fdtable() macro. Subsequent applciation of RCU becomes easier after this. Signed-off-by: Dipankar Sarma Signed-Off-By: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/file.h | 23 +++++++++++++++-------- include/linux/init_task.h | 13 +++++++++---- 2 files changed, 24 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 5206beb9a80e..db372230848e 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -16,23 +16,29 @@ */ #define NR_OPEN_DEFAULT BITS_PER_LONG +struct fdtable { + unsigned int max_fds; + int max_fdset; + int next_fd; + struct file ** fd; /* current fd array */ + fd_set *close_on_exec; + fd_set *open_fds; +}; + /* * Open file table structure */ struct files_struct { atomic_t count; spinlock_t file_lock; /* Protects all the below members. Nests inside tsk->alloc_lock */ - int max_fds; - int max_fdset; - int next_fd; - struct file ** fd; /* current fd array */ - fd_set *close_on_exec; - fd_set *open_fds; + struct fdtable fdtab; fd_set close_on_exec_init; fd_set open_fds_init; struct file * fd_array[NR_OPEN_DEFAULT]; }; +#define files_fdtable(files) (&(files)->fdtab) + extern void FASTCALL(__fput(struct file *)); extern void FASTCALL(fput(struct file *)); @@ -63,9 +69,10 @@ extern int expand_files(struct files_struct *, int nr); static inline struct file * fcheck_files(struct files_struct *files, unsigned int fd) { struct file * file = NULL; + struct fdtable *fdt = files_fdtable(files); - if (fd < files->max_fds) - file = files->fd[fd]; + if (fd < fdt->max_fds) + file = fdt->fd[fd]; return file; } diff --git a/include/linux/init_task.h b/include/linux/init_task.h index c727c195a91a..94aefa54a1b5 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -3,16 +3,21 @@ #include -#define INIT_FILES \ -{ \ - .count = ATOMIC_INIT(1), \ - .file_lock = SPIN_LOCK_UNLOCKED, \ +#define INIT_FDTABLE \ +{ \ .max_fds = NR_OPEN_DEFAULT, \ .max_fdset = __FD_SETSIZE, \ .next_fd = 0, \ .fd = &init_files.fd_array[0], \ .close_on_exec = &init_files.close_on_exec_init, \ .open_fds = &init_files.open_fds_init, \ +} + +#define INIT_FILES \ +{ \ + .count = ATOMIC_INIT(1), \ + .file_lock = SPIN_LOCK_UNLOCKED, \ + .fdtab = INIT_FDTABLE, \ .close_on_exec_init = { { 0, } }, \ .open_fds_init = { { 0, } }, \ .fd_array = { NULL, } \ -- cgit v1.2.3 From ab2af1f5005069321c5d130f09cce577b03f43ef Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Fri, 9 Sep 2005 13:04:13 -0700 Subject: [PATCH] files: files struct with RCU Patch to eliminate struct files_struct.file_lock spinlock on the reader side and use rcu refcounting rcuref_xxx api for the f_count refcounter. The updates to the fdtable are done by allocating a new fdtable structure and setting files->fdt to point to the new structure. The fdtable structure is protected by RCU thereby allowing lock-free lookup. For fd arrays/sets that are vmalloced, we use keventd to free them since RCU callbacks can't sleep. A global list of fdtable to be freed is not scalable, so we use a per-cpu list. If keventd is already handling the current cpu's work, we use a timer to defer queueing of that work. Since the last publication, this patch has been re-written to avoid using explicit memory barriers and use rcu_assign_pointer(), rcu_dereference() premitives instead. This required that the fd information is kept in a separate structure (fdtable) and updated atomically. Signed-off-by: Dipankar Sarma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/file.h | 11 +++++++++-- include/linux/fs.h | 4 +++- include/linux/init_task.h | 5 +++++ 3 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index db372230848e..f5bbd4c508b3 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -9,6 +9,7 @@ #include #include #include +#include /* * The default fd array needs to be at least BITS_PER_LONG, @@ -23,6 +24,9 @@ struct fdtable { struct file ** fd; /* current fd array */ fd_set *close_on_exec; fd_set *open_fds; + struct rcu_head rcu; + struct files_struct *free_files; + struct fdtable *next; }; /* @@ -31,13 +35,14 @@ struct fdtable { struct files_struct { atomic_t count; spinlock_t file_lock; /* Protects all the below members. Nests inside tsk->alloc_lock */ + struct fdtable *fdt; struct fdtable fdtab; fd_set close_on_exec_init; fd_set open_fds_init; struct file * fd_array[NR_OPEN_DEFAULT]; }; -#define files_fdtable(files) (&(files)->fdtab) +#define files_fdtable(files) (rcu_dereference((files)->fdt)) extern void FASTCALL(__fput(struct file *)); extern void FASTCALL(fput(struct file *)); @@ -65,6 +70,8 @@ extern fd_set *alloc_fdset(int); extern void free_fdset(fd_set *, int); extern int expand_files(struct files_struct *, int nr); +extern void free_fdtable(struct fdtable *fdt); +extern void __init files_defer_init(void); static inline struct file * fcheck_files(struct files_struct *files, unsigned int fd) { @@ -72,7 +79,7 @@ static inline struct file * fcheck_files(struct files_struct *files, unsigned in struct fdtable *fdt = files_fdtable(files); if (fd < fdt->max_fds) - file = fdt->fd[fd]; + file = rcu_dereference(fdt->fd[fd]); return file; } diff --git a/include/linux/fs.h b/include/linux/fs.h index fd93ab7da905..7f61227827d7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -9,6 +9,7 @@ #include #include #include +#include /* * It's silly to have NR_OPEN bigger than NR_FILE, but you can change @@ -597,12 +598,13 @@ struct file { spinlock_t f_ep_lock; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; + struct rcu_head f_rcuhead; }; 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 get_file(x) rcuref_inc(&(x)->f_count) #define file_count(x) atomic_read(&(x)->f_count) #define MAX_NON_LFS ((1UL<<31) - 1) diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 94aefa54a1b5..68ab5f2ab9cd 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -2,6 +2,7 @@ #define _LINUX__INIT_TASK_H #include +#include #define INIT_FDTABLE \ { \ @@ -11,12 +12,16 @@ .fd = &init_files.fd_array[0], \ .close_on_exec = &init_files.close_on_exec_init, \ .open_fds = &init_files.open_fds_init, \ + .rcu = RCU_HEAD_INIT, \ + .free_files = NULL, \ + .next = NULL, \ } #define INIT_FILES \ { \ .count = ATOMIC_INIT(1), \ .file_lock = SPIN_LOCK_UNLOCKED, \ + .fdt = &init_files.fdtab, \ .fdtab = INIT_FDTABLE, \ .close_on_exec_init = { { 0, } }, \ .open_fds_init = { { 0, } }, \ -- cgit v1.2.3 From 7726e9e10fc6e026ed2dc00e48f4a3ffc1254ad2 Mon Sep 17 00:00:00 2001 From: "Antonino A. Daplas" Date: Fri, 9 Sep 2005 13:04:29 -0700 Subject: [PATCH] fbdev: Add fbset -a support Add capability to fbdev to listen to the FB_ACTIVATE_ALL flag. If set, it notifies fbcon that all consoles must be set to the current var. Signed-off-by: Antonino Daplas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index bc24beeed971..70da819df0f5 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -495,6 +495,9 @@ struct fb_cursor_user { #define FB_EVENT_BLANK 0x08 /* Private modelist is to be replaced */ #define FB_EVENT_NEW_MODELIST 0x09 +/* The resolution of the passed in fb_info about to change and + all vc's should be changed */ +#define FB_EVENT_MODE_CHANGE_ALL 0x0A struct fb_event { struct fb_info *info; -- cgit v1.2.3 From d2d58384fc5d4c0fe2d8e34bc2d15a90a9bb372a Mon Sep 17 00:00:00 2001 From: "Antonino A. Daplas" Date: Fri, 9 Sep 2005 13:04:31 -0700 Subject: [PATCH] vesafb: Add blanking support Add rudimentary support by manipulating the VGA registers. However, not all vesa modes are VGA compatible, so VGA compatiblity is checked first. Only 2 levels are supported, powerup and powerdown. Signed-off-by: Antonino Daplas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tty.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 59ff42c629ec..1267f88ece6e 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -74,7 +74,8 @@ struct screen_info { u16 vesapm_off; /* 0x30 */ u16 pages; /* 0x32 */ u16 vesa_attributes; /* 0x34 */ - /* 0x36 -- 0x3f reserved for future expansion */ + u32 capabilities; /* 0x36 */ + /* 0x3a -- 0x3f reserved for future expansion */ }; extern struct screen_info screen_info; -- cgit v1.2.3 From 5e518d7672dea4cd7c60871e40d0490c52f01d13 Mon Sep 17 00:00:00 2001 From: "Antonino A. Daplas" Date: Fri, 9 Sep 2005 13:04:34 -0700 Subject: [PATCH] fbdev: Resurrect hooks to get EDID from firmware For the i386, code is already present in video.S that gets the EDID from the video BIOS. Make this visible so drivers can also use this data as fallback when i2c does not work. To ensure that the EDID block is returned for the primary graphics adapter only, by check if the IORESOURCE_ROM_SHADOW flag is set. Signed-off-by: Antonino Daplas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 70da819df0f5..e3e16f43b1bb 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -859,7 +859,9 @@ extern int fb_get_mode(int flags, u32 val, struct fb_var_screeninfo *var, extern int fb_validate_mode(const struct fb_var_screeninfo *var, struct fb_info *info); extern int fb_parse_edid(unsigned char *edid, struct fb_var_screeninfo *var); -extern void fb_edid_to_monspecs(unsigned char *edid, struct fb_monspecs *specs); +extern const unsigned char *fb_firmware_edid(struct device *device); +extern void fb_edid_to_monspecs(unsigned char *edid, + struct fb_monspecs *specs); extern void fb_destroy_modedb(struct fb_videomode *modedb); /* drivers/video/modedb.c */ -- cgit v1.2.3 From b8c909454f046b59065c6997b651fe20cd90c0f4 Mon Sep 17 00:00:00 2001 From: "Antonino A. Daplas" Date: Fri, 9 Sep 2005 13:04:37 -0700 Subject: [PATCH] fbdev: Fix greater than 1 bit monochrome color handling Currently, fbcon assumes that the visual FB_VISUAL_MONO* is always 1 bit. According to Geert, there are old hardware where it's possible to have monochrome at 8-bit, but has only 2 colors, black - 0x00 and white - 0xff. Fix color handlers (fb_get_color_depth, and get_color) for this special case. Signed-off-by: Antonino Daplas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index e3e16f43b1bb..c71a7162e098 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -823,7 +823,8 @@ extern void fb_pad_unaligned_buffer(u8 *dst, u32 d_pitch, u8 *src, u32 idx, u32 height, u32 shift_high, u32 shift_low, u32 mod); extern void fb_pad_aligned_buffer(u8 *dst, u32 d_pitch, u8 *src, u32 s_pitch, u32 height); extern void fb_set_suspend(struct fb_info *info, int state); -extern int fb_get_color_depth(struct fb_var_screeninfo *var); +extern int fb_get_color_depth(struct fb_var_screeninfo *var, + struct fb_fix_screeninfo *fix); extern int fb_get_options(char *name, char **option); extern int fb_new_modelist(struct fb_info *info); -- cgit v1.2.3 From 544393fe584d333480659a4bed30f5295355df11 Mon Sep 17 00:00:00 2001 From: Thomas Winischhofer Date: Fri, 9 Sep 2005 13:04:45 -0700 Subject: [PATCH] sisfb update This lifts sisfb from version 1.7.17 to version 1.8.9. Changes include: - Added support for XGI V3XT, V5, V8, Z7 chipsets, including POSTing of all of these chipsets. - Added support for latest SiS chipsets (761). - Added support for SiS76x memory "hybrid" mode. - Added support for new LCD resolutions (eg 1280x854, 856x480). - Fixed support for 320x240 STN panels (for embedded devices). - Fixed many HDTV modes (525p, 750p, 1080i). - Fixed PCI config register reading/writing to use proper kernel functions for this purpose. - Fixed PCI ROM handling to use the kernel's proper functions. - Removed lots of "typedef"s. - Removed lots of code which was for X.org/XFree86 only. - Fixed coding style in many places. - Removed lots of 2.4 cruft. - Reduced stack size by unifying two previously separate structs into one. - Added new hooks for memory allocation (for DRM). Now the driver can truly handle multiple cards, including memory management. - Fixed numerous minor bugs. Signed-off-by: Thomas Winischhofer Cc: "Antonino A. Daplas" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index c71a7162e098..34814a0b2378 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -107,6 +107,8 @@ #define FB_ACCEL_NV_20 44 /* nVidia Arch 20 */ #define FB_ACCEL_NV_30 45 /* nVidia Arch 30 */ #define FB_ACCEL_NV_40 46 /* nVidia Arch 40 */ +#define FB_ACCEL_XGI_VOLARI_V 47 /* XGI Volari V3XT, V5, V8 */ +#define FB_ACCEL_XGI_VOLARI_Z 48 /* XGI Volari Z7 */ #define FB_ACCEL_NEOMAGIC_NM2070 90 /* NeoMagic NM2070 */ #define FB_ACCEL_NEOMAGIC_NM2090 91 /* NeoMagic NM2090 */ #define FB_ACCEL_NEOMAGIC_NM2093 92 /* NeoMagic NM2093 */ -- cgit v1.2.3 From cdb9b9f730eac4f947a2c552806a3a550bf019ef Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Tue, 6 Sep 2005 09:31:03 +1000 Subject: [PATCH] PCI: Small rearrangement of PCI probing code This patch makes some small rearrangements of the PCI probing code in order to make it possible for arch code to set up the PCI tree without needing to duplicate code from the PCI layer unnecessarily. PPC64 will use this to set up the PCI tree from the Open Firmware device tree, which we need to do on logically-partitioned pSeries systems. Signed-off-by: Paul Mackerras Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 609499356e07..9c7aecf0c599 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -315,8 +315,11 @@ static inline struct pci_bus *pci_scan_bus(int bus, struct pci_ops *ops, void *s pci_bus_add_devices(root_bus); return root_bus; } +struct pci_bus *pci_create_bus(struct device *parent, int bus, struct pci_ops *ops, void *sysdata); +struct pci_bus * pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev, int busnr); int pci_scan_slot(struct pci_bus *bus, int devfn); struct pci_dev * pci_scan_single_device(struct pci_bus *bus, int devfn); +void pci_device_add(struct pci_dev *dev, struct pci_bus *bus); unsigned int pci_scan_child_bus(struct pci_bus *bus); void pci_bus_add_device(struct pci_dev *dev); void pci_read_bridge_bases(struct pci_bus *child); -- cgit v1.2.3 From 96fe6a2109db29cd15b90a093c16e6cb4b19371a Mon Sep 17 00:00:00 2001 From: "Antonino A. Daplas" Date: Fri, 9 Sep 2005 13:09:58 -0700 Subject: [PATCH] fbdev: Add VESA Coordinated Video Timings (CVT) support The Coordinated Video Timings (CVT) is the latest standard approved by VESA concerning video timings generation. It addresses the limitation of GTF which is designed mainly for CRT displays. CRT's have a high blanking requirement (as much as 25% of the horizontal frame length) which artificially increases the pixelclock. Digital displays, on the other hand, needs to conserve the pixelclock as much as possible. The GTF also does not take into account the different aspect ratios in its calculation. The new function added is fb_find_mode_cvt(). It is called by fb_find_mode() if it recognizes a mode option string formatted for CVT. The format is: x[M][R][-][][i][m] The 'M' tells the function to calculate using CVT. On it's own, it will compute a timing for CRT displays at 60Hz. If the 'R' is specified, 'reduced blanking' computation will be used, best for flatpanels. The 'i' and the 'm' is for 'interlaced mode' and 'with margins' respectively. To determine if CVT was used, check for dmesg for something like this: CVT Mode - M[-R], ie: .480M3-R (800x600 reduced blanking) where: pix - product of xres and yres, in MB M - is a CVT mode n - the aspect ratio (3 - 4:3; 4 - 5:4; 9 - 16:9, 15:9; A - 16:10) -R - reduced blanking Signed-off-by: Antonino Daplas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 34814a0b2378..9a4f035e9fdc 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -866,6 +866,7 @@ extern const unsigned char *fb_firmware_edid(struct device *device); extern void fb_edid_to_monspecs(unsigned char *edid, struct fb_monspecs *specs); extern void fb_destroy_modedb(struct fb_videomode *modedb); +extern int fb_find_mode_cvt(struct fb_videomode *mode, int margins, int rb); /* drivers/video/modedb.c */ #define VESA_MODEDB_SIZE 34 -- cgit v1.2.3 From 829e79b680210c4f4de435af6e1f90451922fc7d Mon Sep 17 00:00:00 2001 From: "Antonino A. Daplas" Date: Fri, 9 Sep 2005 13:10:04 -0700 Subject: [PATCH] fbcon: Break up bit_putcs into its component functions The function bit_putcs() in drivers/video/console/bitblit.c is becoming large. Break it up into its component functions (bit_putcs_unaligned and bit_putcs_aligned). Incorporated fb_pad_aligned_buffer() optimization by Roman Zippel. Signed-off-by: Antonino Daplas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 9a4f035e9fdc..82e39cd0c4fb 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -833,6 +833,21 @@ extern int fb_new_modelist(struct fb_info *info); extern struct fb_info *registered_fb[FB_MAX]; extern int num_registered_fb; +static inline void __fb_pad_aligned_buffer(u8 *dst, u32 d_pitch, + u8 *src, u32 s_pitch, u32 height) +{ + int i, j; + + d_pitch -= s_pitch; + + for (i = height; i--; ) { + /* s_pitch is a few bytes at the most, memcpy is suboptimal */ + for (j = 0; j < s_pitch; j++) + *dst++ = *src++; + dst += d_pitch; + } +} + /* drivers/video/fbsysfs.c */ extern struct fb_info *framebuffer_alloc(size_t size, struct device *dev); extern void framebuffer_release(struct fb_info *info); -- cgit v1.2.3 From d8a5ba45457e4a22aa39c939121efd7bb6c76672 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Sep 2005 13:10:26 -0700 Subject: [PATCH] FUSE - core This patch adds FUSE core. This contains the following files: o inode.c - superblock operations (alloc_inode, destroy_inode, read_inode, clear_inode, put_super, show_options) - registers FUSE filesystem o fuse_i.h - private header file Requirements ============ The most important difference between orinary filesystems and FUSE is the fact, that the filesystem data/metadata is provided by a userspace process run with the privileges of the mount "owner" instead of the kernel, or some remote entity usually running with elevated privileges. The security implication of this is that a non-privileged user must not be able to use this capability to compromise the system. Obvious requirements arising from this are: - mount owner should not be able to get elevated privileges with the help of the mounted filesystem - mount owner should not be able to induce undesired behavior in other users' or the super user's processes - mount owner should not get illegitimate access to information from other users' and the super user's processes These are currently ensured with the following constraints: 1) mount is only allowed to directory or file which the mount owner can modify without limitation (write access + no sticky bit for directories) 2) nosuid,nodev mount options are forced 3) any process running with fsuid different from the owner is denied all access to the filesystem 1) and 2) are ensured by the "fusermount" mount utility which is a setuid root application doing the actual mount operation. 3) is ensured by a check in the permission() method in kernel I started thinking about doing 3) in a different way because Christoph H. made a big deal out of it, saying that FUSE is unacceptable into mainline in this form. The suggested use of private namespaces would be OK, but in their current form have many limitations that make their use impractical (as discussed in this thread). Suggested improvements that would address these limitations: - implement shared subtrees - allow a process to join an existing namespace (make namespaces first-class objects) - implement the namespace creation/joining in a PAM module With all that in place the check of owner against current->fsuid may be removed from the FUSE kernel module, without compromising the security requirements. Suid programs still interesting questions, since they get access even to the private namespace causing some information leak (exact order/timing of filesystem operations performed), giving some ptrace-like capabilities to unprivileged users. BTW this problem is not strictly limited to the namespace approach, since suid programs setting fsuid and accessing users' files will succeed with the current approach too. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/linux/fuse.h (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h new file mode 100644 index 000000000000..2b1f4ae01e9d --- /dev/null +++ b/include/linux/fuse.h @@ -0,0 +1,38 @@ +/* + FUSE: Filesystem in Userspace + Copyright (C) 2001-2005 Miklos Szeredi + + This program can be distributed under the terms of the GNU GPL. + See the file COPYING. +*/ + +/* This file defines the kernel interface of FUSE */ + +#include + +/** Version number of this interface */ +#define FUSE_KERNEL_VERSION 5 + +/** Minor version number of this interface */ +#define FUSE_KERNEL_MINOR_VERSION 1 + +/** The node ID of the root inode */ +#define FUSE_ROOT_ID 1 + +struct fuse_attr { + __u64 ino; + __u64 size; + __u64 blocks; + __u64 atime; + __u64 mtime; + __u64 ctime; + __u32 atimensec; + __u32 mtimensec; + __u32 ctimensec; + __u32 mode; + __u32 nlink; + __u32 uid; + __u32 gid; + __u32 rdev; +}; + -- cgit v1.2.3 From 334f485df85ac7736ebe14940bf0a059c5f26d7d Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Sep 2005 13:10:27 -0700 Subject: [PATCH] FUSE - device functions This adds the FUSE device handling functions. This contains the following files: o dev.c - fuse device operations (read, write, release, poll) - registers misc device - support for sending requests to userspace Signed-off-by: Miklos Szeredi Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 36 +++++++++++++++++++++++++++++++++++- 1 file changed, 35 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index 2b1f4ae01e9d..a1aebd7104c4 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -11,7 +11,7 @@ #include /** Version number of this interface */ -#define FUSE_KERNEL_VERSION 5 +#define FUSE_KERNEL_VERSION 6 /** Minor version number of this interface */ #define FUSE_KERNEL_MINOR_VERSION 1 @@ -19,6 +19,12 @@ /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 +/** The major number of the fuse character device */ +#define FUSE_MAJOR 10 + +/** The minor number of the fuse character device */ +#define FUSE_MINOR 229 + struct fuse_attr { __u64 ino; __u64 size; @@ -36,3 +42,31 @@ struct fuse_attr { __u32 rdev; }; +enum fuse_opcode { + FUSE_INIT = 26 +}; + +/* Conservative buffer size for the client */ +#define FUSE_MAX_IN 8192 + +struct fuse_init_in_out { + __u32 major; + __u32 minor; +}; + +struct fuse_in_header { + __u32 len; + __u32 opcode; + __u64 unique; + __u64 nodeid; + __u32 uid; + __u32 gid; + __u32 pid; +}; + +struct fuse_out_header { + __u32 len; + __s32 error; + __u64 unique; +}; + -- cgit v1.2.3 From e5e5558e923f35839108a12718494ecb73fb782f Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Sep 2005 13:10:28 -0700 Subject: [PATCH] FUSE - read-only operations This patch adds the read-only filesystem operations of FUSE. This contains the following files: o dir.c - directory, symlink and file-inode operations The following operations are added: o lookup o getattr o readlink o follow_link o directory open o readdir o directory release o permission o dentry revalidate o statfs Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index a1aebd7104c4..21b9ba16f8d5 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -42,13 +42,61 @@ struct fuse_attr { __u32 rdev; }; +struct fuse_kstatfs { + __u64 blocks; + __u64 bfree; + __u64 bavail; + __u64 files; + __u64 ffree; + __u32 bsize; + __u32 namelen; +}; + enum fuse_opcode { + FUSE_LOOKUP = 1, + FUSE_FORGET = 2, /* no reply */ + FUSE_GETATTR = 3, + FUSE_READLINK = 5, + FUSE_GETDIR = 7, + FUSE_STATFS = 17, FUSE_INIT = 26 }; /* Conservative buffer size for the client */ #define FUSE_MAX_IN 8192 +#define FUSE_NAME_MAX 1024 + +struct fuse_entry_out { + __u64 nodeid; /* Inode ID */ + __u64 generation; /* Inode generation: nodeid:gen must + be unique for the fs's lifetime */ + __u64 entry_valid; /* Cache timeout for the name */ + __u64 attr_valid; /* Cache timeout for the attributes */ + __u32 entry_valid_nsec; + __u32 attr_valid_nsec; + struct fuse_attr attr; +}; + +struct fuse_forget_in { + __u64 version; +}; + +struct fuse_attr_out { + __u64 attr_valid; /* Cache timeout for the attributes */ + __u32 attr_valid_nsec; + __u32 dummy; + struct fuse_attr attr; +}; + +struct fuse_getdir_out { + __u32 fd; +}; + +struct fuse_statfs_out { + struct fuse_kstatfs st; +}; + struct fuse_init_in_out { __u32 major; __u32 minor; @@ -70,3 +118,15 @@ struct fuse_out_header { __u64 unique; }; +struct fuse_dirent { + __u64 ino; + __u64 off; + __u32 namelen; + __u32 type; + char name[0]; +}; + +#define FUSE_NAME_OFFSET ((unsigned) ((struct fuse_dirent *) 0)->name) +#define FUSE_DIRENT_ALIGN(x) (((x) + sizeof(__u64) - 1) & ~(sizeof(__u64) - 1)) +#define FUSE_DIRENT_SIZE(d) \ + FUSE_DIRENT_ALIGN(FUSE_NAME_OFFSET + (d)->namelen) -- cgit v1.2.3 From 9e6268db496a2592e89457537ea54a496feabb77 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Sep 2005 13:10:29 -0700 Subject: [PATCH] FUSE - read-write operations This patch adds the write filesystem operations of FUSE. The following operations are added: o setattr o symlink o mknod o mkdir o create o unlink o rmdir o rename o link Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 43 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 41 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index 21b9ba16f8d5..19d69a3e1623 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -11,7 +11,7 @@ #include /** Version number of this interface */ -#define FUSE_KERNEL_VERSION 6 +#define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ #define FUSE_KERNEL_MINOR_VERSION 1 @@ -52,12 +52,28 @@ struct fuse_kstatfs { __u32 namelen; }; +#define FATTR_MODE (1 << 0) +#define FATTR_UID (1 << 1) +#define FATTR_GID (1 << 2) +#define FATTR_SIZE (1 << 3) +#define FATTR_ATIME (1 << 4) +#define FATTR_MTIME (1 << 5) +#define FATTR_CTIME (1 << 6) + enum fuse_opcode { FUSE_LOOKUP = 1, FUSE_FORGET = 2, /* no reply */ FUSE_GETATTR = 3, + FUSE_SETATTR = 4, FUSE_READLINK = 5, + FUSE_SYMLINK = 6, FUSE_GETDIR = 7, + FUSE_MKNOD = 8, + FUSE_MKDIR = 9, + FUSE_UNLINK = 10, + FUSE_RMDIR = 11, + FUSE_RENAME = 12, + FUSE_LINK = 13, FUSE_STATFS = 17, FUSE_INIT = 26 }; @@ -66,6 +82,7 @@ enum fuse_opcode { #define FUSE_MAX_IN 8192 #define FUSE_NAME_MAX 1024 +#define FUSE_SYMLINK_MAX 4096 struct fuse_entry_out { __u64 nodeid; /* Inode ID */ @@ -79,7 +96,7 @@ struct fuse_entry_out { }; struct fuse_forget_in { - __u64 version; + __u64 nlookup; }; struct fuse_attr_out { @@ -93,6 +110,28 @@ struct fuse_getdir_out { __u32 fd; }; +struct fuse_mknod_in { + __u32 mode; + __u32 rdev; +}; + +struct fuse_mkdir_in { + __u32 mode; +}; + +struct fuse_rename_in { + __u64 newdir; +}; + +struct fuse_link_in { + __u64 oldnodeid; +}; + +struct fuse_setattr_in { + __u32 valid; + struct fuse_attr attr; +}; + struct fuse_statfs_out { struct fuse_kstatfs st; }; -- cgit v1.2.3 From b6aeadeda22a9aa322fdfcd3f4c69ccf0da5cbdd Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Sep 2005 13:10:30 -0700 Subject: [PATCH] FUSE - file operations This patch adds the file operations of FUSE. The following operations are added: o open o flush o release o fsync o readpage o commit_write Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index 19d69a3e1623..61f34636ffbc 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -74,7 +74,13 @@ enum fuse_opcode { FUSE_RMDIR = 11, FUSE_RENAME = 12, FUSE_LINK = 13, + FUSE_OPEN = 14, + FUSE_READ = 15, + FUSE_WRITE = 16, FUSE_STATFS = 17, + FUSE_RELEASE = 18, + FUSE_FSYNC = 20, + FUSE_FLUSH = 25, FUSE_INIT = 26 }; @@ -132,10 +138,51 @@ struct fuse_setattr_in { struct fuse_attr attr; }; +struct fuse_open_in { + __u32 flags; +}; + +struct fuse_open_out { + __u64 fh; + __u32 open_flags; +}; + +struct fuse_release_in { + __u64 fh; + __u32 flags; +}; + +struct fuse_flush_in { + __u64 fh; + __u32 flush_flags; +}; + +struct fuse_read_in { + __u64 fh; + __u64 offset; + __u32 size; +}; + +struct fuse_write_in { + __u64 fh; + __u64 offset; + __u32 size; + __u32 write_flags; +}; + +struct fuse_write_out { + __u32 size; +}; + struct fuse_statfs_out { struct fuse_kstatfs st; }; +struct fuse_fsync_in { + __u64 fh; + __u32 fsync_flags; +}; + struct fuse_init_in_out { __u32 major; __u32 minor; -- cgit v1.2.3 From 92a8780e1136c5ca0c7ed940000d399943d1576e Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Sep 2005 13:10:31 -0700 Subject: [PATCH] FUSE - extended attribute operations This patch adds the extended attribute operations to FUSE. The following operations are added: o getxattr o setxattr o listxattr o removexattr Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index 61f34636ffbc..bf564edf9905 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -80,6 +80,10 @@ enum fuse_opcode { FUSE_STATFS = 17, FUSE_RELEASE = 18, FUSE_FSYNC = 20, + FUSE_SETXATTR = 21, + FUSE_GETXATTR = 22, + FUSE_LISTXATTR = 23, + FUSE_REMOVEXATTR = 24, FUSE_FLUSH = 25, FUSE_INIT = 26 }; @@ -89,6 +93,7 @@ enum fuse_opcode { #define FUSE_NAME_MAX 1024 #define FUSE_SYMLINK_MAX 4096 +#define FUSE_XATTR_SIZE_MAX 4096 struct fuse_entry_out { __u64 nodeid; /* Inode ID */ @@ -183,6 +188,19 @@ struct fuse_fsync_in { __u32 fsync_flags; }; +struct fuse_setxattr_in { + __u32 size; + __u32 flags; +}; + +struct fuse_getxattr_in { + __u32 size; +}; + +struct fuse_getxattr_out { + __u32 size; +}; + struct fuse_init_in_out { __u32 major; __u32 minor; -- cgit v1.2.3 From 06663267b4b1e85ece73236ea720355668d4f736 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Sep 2005 13:10:32 -0700 Subject: [PATCH] FUSE: add padding Add padding to structures to make sizes the same on 32bit and 64bit archs. Initial testing and test machine generously provided by Franco Broi. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index bf564edf9905..e9b814e16c58 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -25,6 +25,9 @@ /** The minor number of the fuse character device */ #define FUSE_MINOR 229 +/* Make sure all structures are padded to 64bit boundary, so 32bit + userspace works under 64bit kernels */ + struct fuse_attr { __u64 ino; __u64 size; @@ -128,6 +131,7 @@ struct fuse_mknod_in { struct fuse_mkdir_in { __u32 mode; + __u32 padding; }; struct fuse_rename_in { @@ -140,32 +144,38 @@ struct fuse_link_in { struct fuse_setattr_in { __u32 valid; + __u32 padding; struct fuse_attr attr; }; struct fuse_open_in { __u32 flags; + __u32 padding; }; struct fuse_open_out { __u64 fh; __u32 open_flags; + __u32 padding; }; struct fuse_release_in { __u64 fh; __u32 flags; + __u32 padding; }; struct fuse_flush_in { __u64 fh; __u32 flush_flags; + __u32 padding; }; struct fuse_read_in { __u64 fh; __u64 offset; __u32 size; + __u32 padding; }; struct fuse_write_in { @@ -177,6 +187,7 @@ struct fuse_write_in { struct fuse_write_out { __u32 size; + __u32 padding; }; struct fuse_statfs_out { @@ -186,6 +197,7 @@ struct fuse_statfs_out { struct fuse_fsync_in { __u64 fh; __u32 fsync_flags; + __u32 padding; }; struct fuse_setxattr_in { @@ -195,10 +207,12 @@ struct fuse_setxattr_in { struct fuse_getxattr_in { __u32 size; + __u32 padding; }; struct fuse_getxattr_out { __u32 size; + __u32 padding; }; struct fuse_init_in_out { @@ -214,6 +228,7 @@ struct fuse_in_header { __u32 uid; __u32 gid; __u32 pid; + __u32 padding; }; struct fuse_out_header { -- cgit v1.2.3 From 04730fef1f9c7277e5c730b193e681ac095b0507 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Sep 2005 13:10:36 -0700 Subject: [PATCH] fuse: transfer readdir data through device This patch removes a long lasting "hack" in FUSE, which used a separate channel (a file descriptor refering to a disk-file) to transfer directory contents from userspace to the kernel. The patch adds three new operations (OPENDIR, READDIR, RELEASEDIR), which have semantics and implementation exactly maching the respective file operations (OPEN, READ, RELEASE). This simplifies the directory reading code. Also disk space is not necessary, which can be important in embedded systems. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index e9b814e16c58..cdfaa51b9018 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -70,7 +70,6 @@ enum fuse_opcode { FUSE_SETATTR = 4, FUSE_READLINK = 5, FUSE_SYMLINK = 6, - FUSE_GETDIR = 7, FUSE_MKNOD = 8, FUSE_MKDIR = 9, FUSE_UNLINK = 10, @@ -88,7 +87,10 @@ enum fuse_opcode { FUSE_LISTXATTR = 23, FUSE_REMOVEXATTR = 24, FUSE_FLUSH = 25, - FUSE_INIT = 26 + FUSE_INIT = 26, + FUSE_OPENDIR = 27, + FUSE_READDIR = 28, + FUSE_RELEASEDIR = 29 }; /* Conservative buffer size for the client */ @@ -120,10 +122,6 @@ struct fuse_attr_out { struct fuse_attr attr; }; -struct fuse_getdir_out { - __u32 fd; -}; - struct fuse_mknod_in { __u32 mode; __u32 rdev; -- cgit v1.2.3 From 45323fb76465a9576220c7427dbac7b1e7ad3caf Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Sep 2005 13:10:37 -0700 Subject: [PATCH] fuse: more flexible caching Make data caching behavior selectable on a per-open basis instead of per-mount. Compatibility for the old mount options 'kernel_cache' and 'direct_io' is retained in the userspace library (version 2.4.0-pre1 or later). Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index cdfaa51b9018..c65124a213a1 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -14,7 +14,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 1 +#define FUSE_KERNEL_MINOR_VERSION 2 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -63,6 +63,15 @@ struct fuse_kstatfs { #define FATTR_MTIME (1 << 5) #define FATTR_CTIME (1 << 6) +/** + * Flags returned by the OPEN request + * + * FOPEN_DIRECT_IO: bypass page cache for this open file + * FOPEN_KEEP_CACHE: don't invalidate the data cache on open + */ +#define FOPEN_DIRECT_IO (1 << 0) +#define FOPEN_KEEP_CACHE (1 << 1) + enum fuse_opcode { FUSE_LOOKUP = 1, FUSE_FORGET = 2, /* no reply */ -- cgit v1.2.3 From 8254798199332966e2ab647380c990193af7e854 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Sep 2005 13:10:38 -0700 Subject: [PATCH] FUSE: add fsync operation for directories This patch adds a new FSYNCDIR request, which is sent when fsync is called on directories. This operation is available in libfuse 2.3-pre1 or greater. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index c65124a213a1..acbeb96a3353 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -99,7 +99,8 @@ enum fuse_opcode { FUSE_INIT = 26, FUSE_OPENDIR = 27, FUSE_READDIR = 28, - FUSE_RELEASEDIR = 29 + FUSE_RELEASEDIR = 29, + FUSE_FSYNCDIR = 30 }; /* Conservative buffer size for the client */ -- cgit v1.2.3 From 8d06afab73a75f40ae2864e6c296356bab1ab473 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 9 Sep 2005 13:10:40 -0700 Subject: [PATCH] timer initialization cleanup: DEFINE_TIMER Clean up timer initialization by introducing DEFINE_TIMER a'la DEFINE_SPINLOCK. Build and boot-tested on x86. A similar patch has been been in the -RT tree for some time. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timer.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index 221f81ac2002..3340f3bd135d 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -32,6 +32,10 @@ extern struct timer_base_s __init_timer_base; .magic = TIMER_MAGIC, \ } +#define DEFINE_TIMER(_name, _function, _expires, _data) \ + struct timer_list _name = \ + TIMER_INITIALIZER(_function, _expires, _data) + void fastcall init_timer(struct timer_list * timer); /*** -- cgit v1.2.3 From 9c8550ee25e26d14a8f0fe1b761a676e23fe3cf0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 9 Sep 2005 15:43:46 -0700 Subject: Remove "must_check" attributes in PCI-land Don't just irritate all other kernel developers. Fix the users first, then you can re-introduce the must-check infrastructure to avoid new cases creeping in. Signed-off-by: Linus Torvalds --- include/linux/pci.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index e5e24e13a114..7349058ed778 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -380,16 +380,16 @@ static inline int pci_write_config_dword(struct pci_dev *dev, int where, u32 val return pci_bus_write_config_dword (dev->bus, dev->devfn, where, val); } -int __must_check pci_enable_device(struct pci_dev *dev); -int __must_check pci_enable_device_bars(struct pci_dev *dev, int mask); +int pci_enable_device(struct pci_dev *dev); +int pci_enable_device_bars(struct pci_dev *dev, int mask); void pci_disable_device(struct pci_dev *dev); void pci_set_master(struct pci_dev *dev); #define HAVE_PCI_SET_MWI -int __must_check pci_set_mwi(struct pci_dev *dev); +int pci_set_mwi(struct pci_dev *dev); void pci_clear_mwi(struct pci_dev *dev); void pci_intx(struct pci_dev *dev, int enable); -int __must_check pci_set_dma_mask(struct pci_dev *dev, u64 mask); -int __must_check pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask); +int pci_set_dma_mask(struct pci_dev *dev, u64 mask); +int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask); void pci_update_resource(struct pci_dev *dev, struct resource *res, int resno); int pci_assign_resource(struct pci_dev *dev, int i); void pci_restore_bars(struct pci_dev *dev); @@ -403,9 +403,9 @@ void pci_remove_rom(struct pci_dev *pdev); /* Power management related routines */ int pci_save_state(struct pci_dev *dev); int pci_restore_state(struct pci_dev *dev); -int __must_check pci_set_power_state(struct pci_dev *dev, pci_power_t state); -pci_power_t __must_check pci_choose_state(struct pci_dev *dev, pm_message_t state); -int __must_check pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable); +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); +int pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable); /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */ void pci_bus_assign_resources(struct pci_bus *bus); -- cgit v1.2.3 From 36fa30636fb84b209210299684e1be66d9e58217 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 9 Sep 2005 16:23:45 -0700 Subject: [PATCH] md: all hot-add and hot-remove of md intent logging bitmaps Both file-bitmaps and superblock bitmaps are supported. If you add a bitmap file on the array device, you lose. This introduces a 'default_bitmap_offset' field in mddev, as the ioctl used for adding a superblock bitmap doesn't have room for giving an offset. Later, this value will be setable via sysfs. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md_k.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 8c14ba565a45..817062bf7352 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -278,6 +278,10 @@ struct mddev_s * start of bitmap. May be * negative, but not '0' */ + long default_bitmap_offset; /* this is the offset to use when + * hot-adding a bitmap. It should + * eventually be settable by sysfs. + */ struct list_head all_mddevs; }; @@ -314,6 +318,12 @@ struct mdk_personality_s int (*resize) (mddev_t *mddev, sector_t sectors); int (*reshape) (mddev_t *mddev, int raid_disks); int (*reconfig) (mddev_t *mddev, int layout, int chunk_size); + /* quiesce moves between quiescence states + * 0 - fully active + * 1 - no new requests allowed + * others - reserved + */ + void (*quiesce) (mddev_t *mddev, int state); }; -- cgit v1.2.3 From 8ddf9efe6708f3674f0ddfeb6425fd27bea109a2 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 9 Sep 2005 16:23:45 -0700 Subject: [PATCH] md: support write-mostly device in raid1 This allows a device in a raid1 to be marked as "write mostly". Read requests will only be sent if there is no other option. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md_k.h | 3 +++ include/linux/raid/md_p.h | 11 +++++++++-- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 817062bf7352..7ef78e15ce04 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -181,6 +181,9 @@ struct mdk_rdev_s int faulty; /* if faulty do not issue IO requests */ int in_sync; /* device is a full member of the array */ + unsigned long flags; /* Should include faulty and in_sync here. */ +#define WriteMostly 4 /* Avoid reading if at all possible */ + int desc_nr; /* descriptor index in the superblock */ int raid_disk; /* role of device in array */ int saved_raid_disk; /* role that device used to have in the diff --git a/include/linux/raid/md_p.h b/include/linux/raid/md_p.h index dc65cd435494..4f047f84fb1f 100644 --- a/include/linux/raid/md_p.h +++ b/include/linux/raid/md_p.h @@ -79,6 +79,11 @@ #define MD_DISK_SYNC 2 /* disk is in sync with the raid set */ #define MD_DISK_REMOVED 3 /* disk is in sync with the raid set */ +#define MD_DISK_WRITEMOSTLY 9 /* disk is "write-mostly" is RAID1 config. + * read requests will only be sent here in + * dire need + */ + typedef struct mdp_device_descriptor_s { __u32 number; /* 0 Device number in the entire set */ __u32 major; /* 1 Device major number */ @@ -193,7 +198,7 @@ struct mdp_superblock_1 { __u64 ctime; /* lo 40 bits are seconds, top 24 are microseconds or 0*/ __u32 level; /* -4 (multipath), -1 (linear), 0,1,4,5 */ - __u32 layout; /* only for raid5 currently */ + __u32 layout; /* only for raid5 and raid10 currently */ __u64 size; /* used size of component devices, in 512byte sectors */ __u32 chunksize; /* in 512byte sectors */ @@ -212,7 +217,9 @@ struct mdp_superblock_1 { __u32 dev_number; /* permanent identifier of this device - not role in raid */ __u32 cnt_corrected_read; /* number of read errors that were corrected by re-writing */ __u8 device_uuid[16]; /* user-space setable, ignored by kernel */ - __u8 pad2[64-56]; /* set to 0 when writing */ + __u8 devflags; /* per-device flags. Only one defined...*/ +#define WriteMostly1 1 /* mask for writemostly flag in above */ + __u8 pad2[64-57]; /* set to 0 when writing */ /* array state information - 64 bytes */ __u64 utime; /* 40 bits second, 24 btes microseconds */ -- cgit v1.2.3 From 4b6d287f627b5fb6a49f78f9e81649ff98c62bb7 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 9 Sep 2005 16:23:47 -0700 Subject: [PATCH] md: add write-behind support for md/raid1 If a device is flagged 'WriteMostly' and the array has a bitmap, and the bitmap superblock indicates that write_behind is allowed, then write_behind is enabled for WriteMostly devices. Write requests will be acknowledges as complete to the caller (via b_end_io) when all non-WriteMostly devices have completed the write, but will not be cleared from the bitmap until all devices complete. This requires memory allocation to make a local copy of the data being written. If there is insufficient memory, then we fall-back on normal write semantics. Signed-Off-By: Paul Clements Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/bitmap.h | 15 ++++++++++----- include/linux/raid/md_k.h | 3 +++ include/linux/raid/raid1.h | 13 +++++++++++++ 3 files changed, 26 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h index 4bf1659f8aa8..9de99198caf1 100644 --- a/include/linux/raid/bitmap.h +++ b/include/linux/raid/bitmap.h @@ -7,7 +7,7 @@ #define BITMAP_H 1 #define BITMAP_MAJOR 3 -#define BITMAP_MINOR 38 +#define BITMAP_MINOR 39 /* * in-memory bitmap: @@ -147,8 +147,9 @@ typedef struct bitmap_super_s { __u32 state; /* 48 bitmap state information */ __u32 chunksize; /* 52 the bitmap chunk size in bytes */ __u32 daemon_sleep; /* 56 seconds between disk flushes */ + __u32 write_behind; /* 60 number of outstanding write-behind writes */ - __u8 pad[256 - 60]; /* set to zero */ + __u8 pad[256 - 64]; /* set to zero */ } bitmap_super_t; /* notes: @@ -226,6 +227,9 @@ struct bitmap { unsigned long flags; + unsigned long max_write_behind; /* write-behind mode */ + atomic_t behind_writes; + /* * the bitmap daemon - periodically wakes up and sweeps the bitmap * file, cleaning up bits and flushing out pages to disk as necessary @@ -260,9 +264,10 @@ int bitmap_setallbits(struct bitmap *bitmap); void bitmap_write_all(struct bitmap *bitmap); /* these are exported */ -int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors); -void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, - int success); +int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, + unsigned long sectors, int behind); +void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, + unsigned long sectors, int success, int behind); int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int degraded); void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted); void bitmap_close_sync(struct bitmap *bitmap); diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 7ef78e15ce04..2514e5fcda7f 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -275,6 +275,9 @@ struct mddev_s atomic_t writes_pending; request_queue_t *queue; /* for plugging ... */ + atomic_t write_behind; /* outstanding async IO */ + unsigned int max_write_behind; /* 0 = sync */ + struct bitmap *bitmap; /* the bitmap for the device */ struct file *bitmap_file; /* the bitmap file */ long bitmap_offset; /* offset from superblock of diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h index 9d93cf12e890..60e19b667548 100644 --- a/include/linux/raid/raid1.h +++ b/include/linux/raid/raid1.h @@ -80,6 +80,9 @@ struct r1bio_s { atomic_t remaining; /* 'have we finished' count, * used from IRQ handlers */ + atomic_t behind_remaining; /* number of write-behind ios remaining + * in this BehindIO request + */ sector_t sector; int sectors; unsigned long state; @@ -107,4 +110,14 @@ struct r1bio_s { #define R1BIO_Uptodate 0 #define R1BIO_IsSync 1 #define R1BIO_Degraded 2 +#define R1BIO_BehindIO 3 +/* For write-behind requests, we call bi_end_io when + * the last non-write-behind device completes, providing + * any write was successful. Otherwise we call when + * any write-behind write succeeds, otherwise we call + * with failure when last write completes (and all failed). + * Record that bi_end_io was called with this flag... + */ +#define R1BIO_Returned 4 + #endif -- cgit v1.2.3 From 15945fee6f09bff1f86b1a735b5888dc59cf38e3 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 9 Sep 2005 16:23:47 -0700 Subject: [PATCH] md: support md/linear array with components greater than 2 terabytes. linear currently uses division by the size of the smallest componenet device to find which device a request goes to. If that smallest device is larger than 2 terabytes, then the division will not work on some systems. So we introduce a pre-shift, and take care not to make the hash table too large, much like the code in raid0. Also get rid of conf->nr_zones, which is not needed. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/linear.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/linear.h b/include/linux/raid/linear.h index e04c4fe45b53..7eaf290e10e7 100644 --- a/include/linux/raid/linear.h +++ b/include/linux/raid/linear.h @@ -14,8 +14,8 @@ typedef struct dev_info dev_info_t; struct linear_private_data { dev_info_t **hash_table; - dev_info_t *smallest; - int nr_zones; + sector_t hash_spacing; + int preshift; /* shift before dividing by hash_spacing */ dev_info_t disks[0]; }; -- cgit v1.2.3 From 71c0805cb48462c99fbe0e5fcc6c12d7b9929c09 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 9 Sep 2005 16:23:51 -0700 Subject: [PATCH] md: allow md to load a superblock with feature-bit '1' set As this is used to flag an internal bitmap. Also, introduce symbolic names for feature bits. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md_p.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/md_p.h b/include/linux/raid/md_p.h index 4f047f84fb1f..c100fa5d4bfa 100644 --- a/include/linux/raid/md_p.h +++ b/include/linux/raid/md_p.h @@ -238,5 +238,10 @@ struct mdp_superblock_1 { __u16 dev_roles[0]; /* role in array, or 0xffff for a spare, or 0xfffe for faulty */ }; +/* feature_map bits */ +#define MD_FEATURE_BITMAP_OFFSET 1 + +#define MD_FEATURE_ALL 1 + #endif -- cgit v1.2.3 From 773f7834425e83144c95fbbc553ced3c2b74b828 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 9 Sep 2005 16:23:53 -0700 Subject: [PATCH] md: remove old cruft from md_k.h header file These inlines haven't been used for ages, they should go. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md_k.h | 64 ----------------------------------------------- 1 file changed, 64 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 2514e5fcda7f..8042f55dd323 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -85,70 +85,6 @@ typedef struct mdk_rdev_s mdk_rdev_t; #define MAX_CHUNK_SIZE (4096*1024) -/* - * default readahead - */ - -static inline int disk_faulty(mdp_disk_t * d) -{ - return d->state & (1 << MD_DISK_FAULTY); -} - -static inline int disk_active(mdp_disk_t * d) -{ - return d->state & (1 << MD_DISK_ACTIVE); -} - -static inline int disk_sync(mdp_disk_t * d) -{ - return d->state & (1 << MD_DISK_SYNC); -} - -static inline int disk_spare(mdp_disk_t * d) -{ - return !disk_sync(d) && !disk_active(d) && !disk_faulty(d); -} - -static inline int disk_removed(mdp_disk_t * d) -{ - return d->state & (1 << MD_DISK_REMOVED); -} - -static inline void mark_disk_faulty(mdp_disk_t * d) -{ - d->state |= (1 << MD_DISK_FAULTY); -} - -static inline void mark_disk_active(mdp_disk_t * d) -{ - d->state |= (1 << MD_DISK_ACTIVE); -} - -static inline void mark_disk_sync(mdp_disk_t * d) -{ - d->state |= (1 << MD_DISK_SYNC); -} - -static inline void mark_disk_spare(mdp_disk_t * d) -{ - d->state = 0; -} - -static inline void mark_disk_removed(mdp_disk_t * d) -{ - d->state = (1 << MD_DISK_FAULTY) | (1 << MD_DISK_REMOVED); -} - -static inline void mark_disk_inactive(mdp_disk_t * d) -{ - d->state &= ~(1 << MD_DISK_ACTIVE); -} - -static inline void mark_disk_nonsync(mdp_disk_t * d) -{ - d->state &= ~(1 << MD_DISK_SYNC); -} - /* * MD's 'extended' device */ -- cgit v1.2.3 From 0002b2718dd04da67c21f8a7830de8d95a9b0345 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 9 Sep 2005 16:23:53 -0700 Subject: [PATCH] md: limit size of sb read/written to appropriate amount version-1 superblocks are not (normally) 4K long, and can be of variable size. Writing the full 4K can cause corruption (but only in non-default configurations). With this patch the super-block-flavour can choose a size to read, and set a size to write based on what it finds. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 8042f55dd323..ebce949b1443 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -102,6 +102,7 @@ struct mdk_rdev_s int sb_loaded; sector_t data_offset; /* start of data in array */ sector_t sb_offset; + int sb_size; /* bytes in the superblock */ int preferred_minor; /* autorun support */ /* A device can be in one of three states based on two flags: -- cgit v1.2.3 From 72626685dc66d455742a7f215a0535c551628b9e Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 9 Sep 2005 16:23:54 -0700 Subject: [PATCH] md: add write-intent-bitmap support to raid5 Most awkward part of this is delaying write requests until bitmap updates have been flushed. To achieve this, we have a sequence number (seq_flush) which is incremented each time the raid5 is unplugged. If the raid thread notices that this has changed, it flushes bitmap changes, and assigned the value of seq_flush to seq_write. When a write request arrives, it is given the number from seq_write, and that write request may not complete until seq_flush is larger than the saved seq number. We have a new queue for storing stripes which are waiting for a bitmap flush and an extra flag for stripes to record if the write was 'degraded' and so should not clear the a bit in the bitmap. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid5.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index d63ddcb4afad..176fc653c284 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -134,6 +134,7 @@ struct stripe_head { unsigned long state; /* state flags */ atomic_t count; /* nr of active thread/requests */ spinlock_t lock; + int bm_seq; /* sequence number for bitmap flushes */ struct r5dev { struct bio req; struct bio_vec vec; @@ -165,12 +166,13 @@ struct stripe_head { /* * Stripe state */ -#define STRIPE_ERROR 1 #define STRIPE_HANDLE 2 #define STRIPE_SYNCING 3 #define STRIPE_INSYNC 4 #define STRIPE_PREREAD_ACTIVE 5 #define STRIPE_DELAYED 6 +#define STRIPE_DEGRADED 7 +#define STRIPE_BIT_DELAY 8 /* * Plugging: @@ -210,10 +212,20 @@ struct raid5_private_data { struct list_head handle_list; /* stripes needing handling */ struct list_head delayed_list; /* stripes that have plugged requests */ + struct list_head bitmap_list; /* stripes delaying awaiting bitmap update */ atomic_t preread_active_stripes; /* stripes with scheduled io */ char cache_name[20]; kmem_cache_t *slab_cache; /* for allocating stripes */ + + int seq_flush, seq_write; + int quiesce; + + int fullsync; /* set to 1 if a full sync is needed, + * (fresh device added). + * Cleared when a sync completes. + */ + /* * Free stripes pool */ -- cgit v1.2.3 From 9928890c1f94da58bf753ede937b7324f6832866 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Sat, 10 Sep 2005 11:26:34 +0900 Subject: [IPV6]: rearrange constants for new advanced API to solve conflicts. 64, 65 are already used in ip6_tables. Pointed out by Patrick McHardy . Signed-off-by: YOSHIFUJI Hideaki --- include/linux/in6.h | 42 ++++++++++++++++++++++-------------------- 1 file changed, 22 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/in6.h b/include/linux/in6.h index bd32b79d6295..50cdc3ad61a7 100644 --- a/include/linux/in6.h +++ b/include/linux/in6.h @@ -198,27 +198,29 @@ struct in6_flowlabel_req * MCAST_MSFILTER 48 */ -/* RFC3542 advanced socket options (50-67) */ -#define IPV6_RECVPKTINFO 50 -#define IPV6_PKTINFO 51 -#if 0 -#define IPV6_RECVPATHMTU 52 -#define IPV6_PATHMTU 53 -#define IPV6_DONTFRAG 54 -#define IPV6_USE_MIN_MTU 55 -#endif -#define IPV6_RECVHOPOPTS 56 -#define IPV6_HOPOPTS 57 -#if 0 -#define IPV6_RECVRTHDRDSTOPTS 58 /* Unused, see net/ipv6/datagram.c */ +/* + * Advanced API (RFC3542) (1) + * + * Note: IPV6_RECVRTHDRDSTOPTS does not exist. see net/ipv6/datagram.c. + */ + +#define IPV6_RECVPKTINFO 49 +#define IPV6_PKTINFO 50 +#define IPV6_RECVHOPLIMIT 51 +#define IPV6_HOPLIMIT 52 +#define IPV6_RECVHOPOPTS 53 +#define IPV6_HOPOPTS 54 +#define IPV6_RTHDRDSTOPTS 55 +#define IPV6_RECVRTHDR 56 +#define IPV6_RTHDR 57 +#define IPV6_RECVDSTOPTS 58 +#define IPV6_DSTOPTS 59 +#if 0 /* not yet */ +#define IPV6_RECVPATHMTU 60 +#define IPV6_PATHMTU 61 +#define IPV6_DONTFRAG 62 +#define IPV6_USE_MIN_MTU 63 #endif -#define IPV6_RTHDRDSTOPTS 59 -#define IPV6_RECVRTHDR 60 -#define IPV6_RTHDR 61 -#define IPV6_RECVDSTOPTS 62 -#define IPV6_DSTOPTS 63 -#define IPV6_RECVHOPLIMIT 64 -#define IPV6_HOPLIMIT 65 #define IPV6_RECVTCLASS 66 #define IPV6_TCLASS 67 -- cgit v1.2.3 From dd27466df9924706ae34639ce3f4f837875d45c1 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Sat, 10 Sep 2005 11:32:45 +0900 Subject: [IPV6]: Note values allocated for ip6_tables. To avoid future conflicts, add a note values allocated for ip6_tables. Signed-off-by: YOSHIFUJI Hideaki --- include/linux/in6.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/in6.h b/include/linux/in6.h index 50cdc3ad61a7..304aaedea305 100644 --- a/include/linux/in6.h +++ b/include/linux/in6.h @@ -221,6 +221,20 @@ struct in6_flowlabel_req #define IPV6_DONTFRAG 62 #define IPV6_USE_MIN_MTU 63 #endif + +/* + * Netfilter + * + * Following socket options are used in ip6_tables; + * see include/linux/netfilter_ipv6/ip6_tables.h. + * + * IP6T_SO_SET_REPLACE / IP6T_SO_GET_INFO 64 + * IP6T_SO_SET_ADD_COUNTERS / IP6T_SO_GET_ENTRIES 65 + */ + +/* + * Advanced API (RFC3542) (2) + */ #define IPV6_RECVTCLASS 66 #define IPV6_TCLASS 67 -- cgit v1.2.3 From e6df439b89dbf9eb977c2dc6f7b0644be3704df4 Mon Sep 17 00:00:00 2001 From: Brian Haley Date: Sat, 10 Sep 2005 00:15:06 -0700 Subject: [IPV6]: Bring Type 0 routing header in-line with rfc3542. Signed-off-by: Brian Haley Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 6c5f7b39a4b0..bb6f88e14061 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -68,7 +68,7 @@ struct ipv6_opt_hdr { struct rt0_hdr { struct ipv6_rt_hdr rt_hdr; - __u32 bitmap; /* strict/loose bit map */ + __u32 reserved; struct in6_addr addr[0]; #define rt0_type rt_hdr.type -- cgit v1.2.3 From fb1c8f93d869b34cacb8b8932e2b83d96a19d720 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 10 Sep 2005 00:25:56 -0700 Subject: [PATCH] spinlock consolidation This patch (written by me and also containing many suggestions of Arjan van de Ven) does a major cleanup of the spinlock code. It does the following things: - consolidates and enhances the spinlock/rwlock debugging code - simplifies the asm/spinlock.h files - encapsulates the raw spinlock type and moves generic spinlock features (such as ->break_lock) into the generic code. - cleans up the spinlock code hierarchy to get rid of the spaghetti. Most notably there's now only a single variant of the debugging code, located in lib/spinlock_debug.c. (previously we had one SMP debugging variant per architecture, plus a separate generic one for UP builds) Also, i've enhanced the rwlock debugging facility, it will now track write-owners. There is new spinlock-owner/CPU-tracking on SMP builds too. All locks have lockup detection now, which will work for both soft and hard spin/rwlock lockups. The arch-level include files now only contain the minimally necessary subset of the spinlock code - all the rest that can be generalized now lives in the generic headers: include/asm-i386/spinlock_types.h | 16 include/asm-x86_64/spinlock_types.h | 16 I have also split up the various spinlock variants into separate files, making it easier to see which does what. The new layout is: SMP | UP ----------------------------|----------------------------------- asm/spinlock_types_smp.h | linux/spinlock_types_up.h linux/spinlock_types.h | linux/spinlock_types.h asm/spinlock_smp.h | linux/spinlock_up.h linux/spinlock_api_smp.h | linux/spinlock_api_up.h linux/spinlock.h | linux/spinlock.h /* * here's the role of the various spinlock/rwlock related include files: * * on SMP builds: * * asm/spinlock_types.h: contains the raw_spinlock_t/raw_rwlock_t and the * initializers * * linux/spinlock_types.h: * defines the generic type and initializers * * asm/spinlock.h: contains the __raw_spin_*()/etc. lowlevel * implementations, mostly inline assembly code * * (also included on UP-debug builds:) * * linux/spinlock_api_smp.h: * contains the prototypes for the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. * * on UP builds: * * linux/spinlock_type_up.h: * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * * linux/spinlock_types.h: * defines the generic type and initializers * * linux/spinlock_up.h: * contains the __raw_spin_*()/etc. version of UP * builds. (which are NOPs on non-debug, non-preempt * builds) * * (included on UP-non-debug builds:) * * linux/spinlock_api_up.h: * builds the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. */ All SMP and UP architectures are converted by this patch. arm, i386, ia64, ppc, ppc64, s390/s390x, x64 was build-tested via crosscompilers. m32r, mips, sh, sparc, have not been tested yet, but should be mostly fine. From: Grant Grundler Booted and lightly tested on a500-44 (64-bit, SMP kernel, dual CPU). Builds 32-bit SMP kernel (not booted or tested). I did not try to build non-SMP kernels. That should be trivial to fix up later if necessary. I converted bit ops atomic_hash lock to raw_spinlock_t. Doing so avoids some ugly nesting of linux/*.h and asm/*.h files. Those particular locks are well tested and contained entirely inside arch specific code. I do NOT expect any new issues to arise with them. If someone does ever need to use debug/metrics with them, then they will need to unravel this hairball between spinlocks, atomic ops, and bit ops that exist only because parisc has exactly one atomic instruction: LDCW (load and clear word). From: "Luck, Tony" ia64 fix Signed-off-by: Ingo Molnar Signed-off-by: Arjan van de Ven Signed-off-by: Grant Grundler Cc: Matthew Wilcox Signed-off-by: Hirokazu Takata Signed-off-by: Mikael Pettersson Signed-off-by: Benoit Boissinot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bit_spinlock.h | 77 +++++ include/linux/jbd.h | 1 + include/linux/spinlock.h | 627 ++++++++------------------------------ include/linux/spinlock_api_smp.h | 57 ++++ include/linux/spinlock_api_up.h | 80 +++++ include/linux/spinlock_types.h | 67 ++++ include/linux/spinlock_types_up.h | 51 ++++ include/linux/spinlock_up.h | 74 +++++ 8 files changed, 532 insertions(+), 502 deletions(-) create mode 100644 include/linux/bit_spinlock.h create mode 100644 include/linux/spinlock_api_smp.h create mode 100644 include/linux/spinlock_api_up.h create mode 100644 include/linux/spinlock_types.h create mode 100644 include/linux/spinlock_types_up.h create mode 100644 include/linux/spinlock_up.h (limited to 'include/linux') diff --git a/include/linux/bit_spinlock.h b/include/linux/bit_spinlock.h new file mode 100644 index 000000000000..6b20af0bbb79 --- /dev/null +++ b/include/linux/bit_spinlock.h @@ -0,0 +1,77 @@ +#ifndef __LINUX_BIT_SPINLOCK_H +#define __LINUX_BIT_SPINLOCK_H + +/* + * bit-based spin_lock() + * + * Don't use this unless you really need to: spin_lock() and spin_unlock() + * are significantly faster. + */ +static inline void bit_spin_lock(int bitnum, unsigned long *addr) +{ + /* + * Assuming the lock is uncontended, this never enters + * the body of the outer loop. If it is contended, then + * within the inner loop a non-atomic test is used to + * busywait with less bus contention for a good time to + * attempt to acquire the lock bit. + */ + preempt_disable(); +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) + while (test_and_set_bit(bitnum, addr)) { + while (test_bit(bitnum, addr)) { + preempt_enable(); + cpu_relax(); + preempt_disable(); + } + } +#endif + __acquire(bitlock); +} + +/* + * Return true if it was acquired + */ +static inline int bit_spin_trylock(int bitnum, unsigned long *addr) +{ + preempt_disable(); +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) + if (test_and_set_bit(bitnum, addr)) { + preempt_enable(); + return 0; + } +#endif + __acquire(bitlock); + return 1; +} + +/* + * bit-based spin_unlock() + */ +static inline void bit_spin_unlock(int bitnum, unsigned long *addr) +{ +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) + BUG_ON(!test_bit(bitnum, addr)); + smp_mb__before_clear_bit(); + clear_bit(bitnum, addr); +#endif + preempt_enable(); + __release(bitlock); +} + +/* + * Return true if the lock is held. + */ +static inline int bit_spin_is_locked(int bitnum, unsigned long *addr) +{ +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) + return test_bit(bitnum, addr); +#elif defined CONFIG_PREEMPT + return preempt_count(); +#else + return 1; +#endif +} + +#endif /* __LINUX_BIT_SPINLOCK_H */ + diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 84321a4cac93..de097269bd7f 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #endif diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index d6ba068719b6..cdc99a27840d 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -2,7 +2,48 @@ #define __LINUX_SPINLOCK_H /* - * include/linux/spinlock.h - generic locking declarations + * include/linux/spinlock.h - generic spinlock/rwlock declarations + * + * here's the role of the various spinlock/rwlock related include files: + * + * on SMP builds: + * + * asm/spinlock_types.h: contains the raw_spinlock_t/raw_rwlock_t and the + * initializers + * + * linux/spinlock_types.h: + * defines the generic type and initializers + * + * asm/spinlock.h: contains the __raw_spin_*()/etc. lowlevel + * implementations, mostly inline assembly code + * + * (also included on UP-debug builds:) + * + * linux/spinlock_api_smp.h: + * contains the prototypes for the _spin_*() APIs. + * + * linux/spinlock.h: builds the final spin_*() APIs. + * + * on UP builds: + * + * linux/spinlock_type_up.h: + * contains the generic, simplified UP spinlock type. + * (which is an empty structure on non-debug builds) + * + * linux/spinlock_types.h: + * defines the generic type and initializers + * + * linux/spinlock_up.h: + * contains the __raw_spin_*()/etc. version of UP + * builds. (which are NOPs on non-debug, non-preempt + * builds) + * + * (included on UP-non-debug builds:) + * + * linux/spinlock_api_up.h: + * builds the _spin_*() APIs. + * + * linux/spinlock.h: builds the final spin_*() APIs. */ #include @@ -13,7 +54,6 @@ #include #include -#include /* for cpu relax */ #include /* @@ -35,423 +75,84 @@ #define __lockfunc fastcall __attribute__((section(".spinlock.text"))) /* - * If CONFIG_SMP is set, pull in the _raw_* definitions + * Pull the raw_spinlock_t and raw_rwlock_t definitions: */ -#ifdef CONFIG_SMP - -#define assert_spin_locked(x) BUG_ON(!spin_is_locked(x)) -#include - -int __lockfunc _spin_trylock(spinlock_t *lock); -int __lockfunc _read_trylock(rwlock_t *lock); -int __lockfunc _write_trylock(rwlock_t *lock); - -void __lockfunc _spin_lock(spinlock_t *lock) __acquires(spinlock_t); -void __lockfunc _read_lock(rwlock_t *lock) __acquires(rwlock_t); -void __lockfunc _write_lock(rwlock_t *lock) __acquires(rwlock_t); - -void __lockfunc _spin_unlock(spinlock_t *lock) __releases(spinlock_t); -void __lockfunc _read_unlock(rwlock_t *lock) __releases(rwlock_t); -void __lockfunc _write_unlock(rwlock_t *lock) __releases(rwlock_t); - -unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock) __acquires(spinlock_t); -unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock) __acquires(rwlock_t); -unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock) __acquires(rwlock_t); - -void __lockfunc _spin_lock_irq(spinlock_t *lock) __acquires(spinlock_t); -void __lockfunc _spin_lock_bh(spinlock_t *lock) __acquires(spinlock_t); -void __lockfunc _read_lock_irq(rwlock_t *lock) __acquires(rwlock_t); -void __lockfunc _read_lock_bh(rwlock_t *lock) __acquires(rwlock_t); -void __lockfunc _write_lock_irq(rwlock_t *lock) __acquires(rwlock_t); -void __lockfunc _write_lock_bh(rwlock_t *lock) __acquires(rwlock_t); - -void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) __releases(spinlock_t); -void __lockfunc _spin_unlock_irq(spinlock_t *lock) __releases(spinlock_t); -void __lockfunc _spin_unlock_bh(spinlock_t *lock) __releases(spinlock_t); -void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags) __releases(rwlock_t); -void __lockfunc _read_unlock_irq(rwlock_t *lock) __releases(rwlock_t); -void __lockfunc _read_unlock_bh(rwlock_t *lock) __releases(rwlock_t); -void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags) __releases(rwlock_t); -void __lockfunc _write_unlock_irq(rwlock_t *lock) __releases(rwlock_t); -void __lockfunc _write_unlock_bh(rwlock_t *lock) __releases(rwlock_t); - -int __lockfunc _spin_trylock_bh(spinlock_t *lock); -int __lockfunc generic_raw_read_trylock(rwlock_t *lock); -int in_lock_functions(unsigned long addr); - -#else +#include -#define in_lock_functions(ADDR) 0 +extern int __lockfunc generic__raw_read_trylock(raw_rwlock_t *lock); -#if !defined(CONFIG_PREEMPT) && !defined(CONFIG_DEBUG_SPINLOCK) -# define _atomic_dec_and_lock(atomic,lock) atomic_dec_and_test(atomic) -# define ATOMIC_DEC_AND_LOCK -#endif - -#ifdef CONFIG_DEBUG_SPINLOCK - -#define SPINLOCK_MAGIC 0x1D244B3C -typedef struct { - unsigned long magic; - volatile unsigned long lock; - volatile unsigned int babble; - const char *module; - char *owner; - int oline; -} spinlock_t; -#define SPIN_LOCK_UNLOCKED (spinlock_t) { SPINLOCK_MAGIC, 0, 10, __FILE__ , NULL, 0} - -#define spin_lock_init(x) \ - do { \ - (x)->magic = SPINLOCK_MAGIC; \ - (x)->lock = 0; \ - (x)->babble = 5; \ - (x)->module = __FILE__; \ - (x)->owner = NULL; \ - (x)->oline = 0; \ - } while (0) - -#define CHECK_LOCK(x) \ - do { \ - if ((x)->magic != SPINLOCK_MAGIC) { \ - printk(KERN_ERR "%s:%d: spin_is_locked on uninitialized spinlock %p.\n", \ - __FILE__, __LINE__, (x)); \ - } \ - } while(0) - -#define _raw_spin_lock(x) \ - do { \ - CHECK_LOCK(x); \ - if ((x)->lock&&(x)->babble) { \ - (x)->babble--; \ - printk("%s:%d: spin_lock(%s:%p) already locked by %s/%d\n", \ - __FILE__,__LINE__, (x)->module, \ - (x), (x)->owner, (x)->oline); \ - } \ - (x)->lock = 1; \ - (x)->owner = __FILE__; \ - (x)->oline = __LINE__; \ - } while (0) - -/* without debugging, spin_is_locked on UP always says - * FALSE. --> printk if already locked. */ -#define spin_is_locked(x) \ - ({ \ - CHECK_LOCK(x); \ - if ((x)->lock&&(x)->babble) { \ - (x)->babble--; \ - printk("%s:%d: spin_is_locked(%s:%p) already locked by %s/%d\n", \ - __FILE__,__LINE__, (x)->module, \ - (x), (x)->owner, (x)->oline); \ - } \ - 0; \ - }) - -/* with debugging, assert_spin_locked() on UP does check - * the lock value properly */ -#define assert_spin_locked(x) \ - ({ \ - CHECK_LOCK(x); \ - BUG_ON(!(x)->lock); \ - }) - -/* without debugging, spin_trylock on UP always says - * TRUE. --> printk if already locked. */ -#define _raw_spin_trylock(x) \ - ({ \ - CHECK_LOCK(x); \ - if ((x)->lock&&(x)->babble) { \ - (x)->babble--; \ - printk("%s:%d: spin_trylock(%s:%p) already locked by %s/%d\n", \ - __FILE__,__LINE__, (x)->module, \ - (x), (x)->owner, (x)->oline); \ - } \ - (x)->lock = 1; \ - (x)->owner = __FILE__; \ - (x)->oline = __LINE__; \ - 1; \ - }) - -#define spin_unlock_wait(x) \ - do { \ - CHECK_LOCK(x); \ - if ((x)->lock&&(x)->babble) { \ - (x)->babble--; \ - printk("%s:%d: spin_unlock_wait(%s:%p) owned by %s/%d\n", \ - __FILE__,__LINE__, (x)->module, (x), \ - (x)->owner, (x)->oline); \ - }\ - } while (0) - -#define _raw_spin_unlock(x) \ - do { \ - CHECK_LOCK(x); \ - if (!(x)->lock&&(x)->babble) { \ - (x)->babble--; \ - printk("%s:%d: spin_unlock(%s:%p) not locked\n", \ - __FILE__,__LINE__, (x)->module, (x));\ - } \ - (x)->lock = 0; \ - } while (0) -#else /* - * gcc versions before ~2.95 have a nasty bug with empty initializers. + * Pull the __raw*() functions/declarations (UP-nondebug doesnt need them): */ -#if (__GNUC__ > 2) - typedef struct { } spinlock_t; - #define SPIN_LOCK_UNLOCKED (spinlock_t) { } +#if defined(CONFIG_SMP) +# include #else - typedef struct { int gcc_is_buggy; } spinlock_t; - #define SPIN_LOCK_UNLOCKED (spinlock_t) { 0 } +# include #endif +#define spin_lock_init(lock) do { *(lock) = SPIN_LOCK_UNLOCKED; } while (0) +#define rwlock_init(lock) do { *(lock) = RW_LOCK_UNLOCKED; } while (0) + +#define spin_is_locked(lock) __raw_spin_is_locked(&(lock)->raw_lock) + +/** + * spin_unlock_wait - wait until the spinlock gets unlocked + * @lock: the spinlock in question. + */ +#define spin_unlock_wait(lock) __raw_spin_unlock_wait(&(lock)->raw_lock) + /* - * If CONFIG_SMP is unset, declare the _raw_* definitions as nops + * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: */ -#define spin_lock_init(lock) do { (void)(lock); } while(0) -#define _raw_spin_lock(lock) do { (void)(lock); } while(0) -#define spin_is_locked(lock) ((void)(lock), 0) -#define assert_spin_locked(lock) do { (void)(lock); } while(0) -#define _raw_spin_trylock(lock) (((void)(lock), 1)) -#define spin_unlock_wait(lock) (void)(lock) -#define _raw_spin_unlock(lock) do { (void)(lock); } while(0) -#endif /* CONFIG_DEBUG_SPINLOCK */ - -/* RW spinlocks: No debug version */ - -#if (__GNUC__ > 2) - typedef struct { } rwlock_t; - #define RW_LOCK_UNLOCKED (rwlock_t) { } +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) +# include #else - typedef struct { int gcc_is_buggy; } rwlock_t; - #define RW_LOCK_UNLOCKED (rwlock_t) { 0 } +# include #endif -#define rwlock_init(lock) do { (void)(lock); } while(0) -#define _raw_read_lock(lock) do { (void)(lock); } while(0) -#define _raw_read_unlock(lock) do { (void)(lock); } while(0) -#define _raw_write_lock(lock) do { (void)(lock); } while(0) -#define _raw_write_unlock(lock) do { (void)(lock); } while(0) -#define read_can_lock(lock) (((void)(lock), 1)) -#define write_can_lock(lock) (((void)(lock), 1)) -#define _raw_read_trylock(lock) ({ (void)(lock); (1); }) -#define _raw_write_trylock(lock) ({ (void)(lock); (1); }) - -#define _spin_trylock(lock) ({preempt_disable(); _raw_spin_trylock(lock) ? \ - 1 : ({preempt_enable(); 0;});}) - -#define _read_trylock(lock) ({preempt_disable();_raw_read_trylock(lock) ? \ - 1 : ({preempt_enable(); 0;});}) - -#define _write_trylock(lock) ({preempt_disable(); _raw_write_trylock(lock) ? \ - 1 : ({preempt_enable(); 0;});}) - -#define _spin_trylock_bh(lock) ({preempt_disable(); local_bh_disable(); \ - _raw_spin_trylock(lock) ? \ - 1 : ({preempt_enable_no_resched(); local_bh_enable(); 0;});}) - -#define _spin_lock(lock) \ -do { \ - preempt_disable(); \ - _raw_spin_lock(lock); \ - __acquire(lock); \ -} while(0) - -#define _write_lock(lock) \ -do { \ - preempt_disable(); \ - _raw_write_lock(lock); \ - __acquire(lock); \ -} while(0) - -#define _read_lock(lock) \ -do { \ - preempt_disable(); \ - _raw_read_lock(lock); \ - __acquire(lock); \ -} while(0) - -#define _spin_unlock(lock) \ -do { \ - _raw_spin_unlock(lock); \ - preempt_enable(); \ - __release(lock); \ -} while (0) - -#define _write_unlock(lock) \ -do { \ - _raw_write_unlock(lock); \ - preempt_enable(); \ - __release(lock); \ -} while(0) - -#define _read_unlock(lock) \ -do { \ - _raw_read_unlock(lock); \ - preempt_enable(); \ - __release(lock); \ -} while(0) - -#define _spin_lock_irqsave(lock, flags) \ -do { \ - local_irq_save(flags); \ - preempt_disable(); \ - _raw_spin_lock(lock); \ - __acquire(lock); \ -} while (0) - -#define _spin_lock_irq(lock) \ -do { \ - local_irq_disable(); \ - preempt_disable(); \ - _raw_spin_lock(lock); \ - __acquire(lock); \ -} while (0) - -#define _spin_lock_bh(lock) \ -do { \ - local_bh_disable(); \ - preempt_disable(); \ - _raw_spin_lock(lock); \ - __acquire(lock); \ -} while (0) - -#define _read_lock_irqsave(lock, flags) \ -do { \ - local_irq_save(flags); \ - preempt_disable(); \ - _raw_read_lock(lock); \ - __acquire(lock); \ -} while (0) - -#define _read_lock_irq(lock) \ -do { \ - local_irq_disable(); \ - preempt_disable(); \ - _raw_read_lock(lock); \ - __acquire(lock); \ -} while (0) - -#define _read_lock_bh(lock) \ -do { \ - local_bh_disable(); \ - preempt_disable(); \ - _raw_read_lock(lock); \ - __acquire(lock); \ -} while (0) - -#define _write_lock_irqsave(lock, flags) \ -do { \ - local_irq_save(flags); \ - preempt_disable(); \ - _raw_write_lock(lock); \ - __acquire(lock); \ -} while (0) +#ifdef CONFIG_DEBUG_SPINLOCK + extern void _raw_spin_lock(spinlock_t *lock); +#define _raw_spin_lock_flags(lock, flags) _raw_spin_lock(lock) + extern int _raw_spin_trylock(spinlock_t *lock); + extern void _raw_spin_unlock(spinlock_t *lock); + + extern void _raw_read_lock(rwlock_t *lock); + extern int _raw_read_trylock(rwlock_t *lock); + extern void _raw_read_unlock(rwlock_t *lock); + extern void _raw_write_lock(rwlock_t *lock); + extern int _raw_write_trylock(rwlock_t *lock); + extern void _raw_write_unlock(rwlock_t *lock); +#else +# define _raw_spin_unlock(lock) __raw_spin_unlock(&(lock)->raw_lock) +# define _raw_spin_trylock(lock) __raw_spin_trylock(&(lock)->raw_lock) +# define _raw_spin_lock(lock) __raw_spin_lock(&(lock)->raw_lock) +# define _raw_spin_lock_flags(lock, flags) \ + __raw_spin_lock_flags(&(lock)->raw_lock, *(flags)) +# define _raw_read_lock(rwlock) __raw_read_lock(&(rwlock)->raw_lock) +# define _raw_write_lock(rwlock) __raw_write_lock(&(rwlock)->raw_lock) +# define _raw_read_unlock(rwlock) __raw_read_unlock(&(rwlock)->raw_lock) +# define _raw_write_unlock(rwlock) __raw_write_unlock(&(rwlock)->raw_lock) +# define _raw_read_trylock(rwlock) __raw_read_trylock(&(rwlock)->raw_lock) +# define _raw_write_trylock(rwlock) __raw_write_trylock(&(rwlock)->raw_lock) +#endif -#define _write_lock_irq(lock) \ -do { \ - local_irq_disable(); \ - preempt_disable(); \ - _raw_write_lock(lock); \ - __acquire(lock); \ -} while (0) - -#define _write_lock_bh(lock) \ -do { \ - local_bh_disable(); \ - preempt_disable(); \ - _raw_write_lock(lock); \ - __acquire(lock); \ -} while (0) - -#define _spin_unlock_irqrestore(lock, flags) \ -do { \ - _raw_spin_unlock(lock); \ - local_irq_restore(flags); \ - preempt_enable(); \ - __release(lock); \ -} while (0) - -#define _spin_unlock_irq(lock) \ -do { \ - _raw_spin_unlock(lock); \ - local_irq_enable(); \ - preempt_enable(); \ - __release(lock); \ -} while (0) - -#define _spin_unlock_bh(lock) \ -do { \ - _raw_spin_unlock(lock); \ - preempt_enable_no_resched(); \ - local_bh_enable(); \ - __release(lock); \ -} while (0) - -#define _write_unlock_bh(lock) \ -do { \ - _raw_write_unlock(lock); \ - preempt_enable_no_resched(); \ - local_bh_enable(); \ - __release(lock); \ -} while (0) - -#define _read_unlock_irqrestore(lock, flags) \ -do { \ - _raw_read_unlock(lock); \ - local_irq_restore(flags); \ - preempt_enable(); \ - __release(lock); \ -} while (0) - -#define _write_unlock_irqrestore(lock, flags) \ -do { \ - _raw_write_unlock(lock); \ - local_irq_restore(flags); \ - preempt_enable(); \ - __release(lock); \ -} while (0) - -#define _read_unlock_irq(lock) \ -do { \ - _raw_read_unlock(lock); \ - local_irq_enable(); \ - preempt_enable(); \ - __release(lock); \ -} while (0) - -#define _read_unlock_bh(lock) \ -do { \ - _raw_read_unlock(lock); \ - preempt_enable_no_resched(); \ - local_bh_enable(); \ - __release(lock); \ -} while (0) - -#define _write_unlock_irq(lock) \ -do { \ - _raw_write_unlock(lock); \ - local_irq_enable(); \ - preempt_enable(); \ - __release(lock); \ -} while (0) - -#endif /* !SMP */ +#define read_can_lock(rwlock) __raw_read_can_lock(&(rwlock)->raw_lock) +#define write_can_lock(rwlock) __raw_write_can_lock(&(rwlock)->raw_lock) /* * Define the various spin_lock and rw_lock methods. Note we define these * regardless of whether CONFIG_SMP or CONFIG_PREEMPT are set. The various * methods are defined as nops in the case they are not required. */ -#define spin_trylock(lock) __cond_lock(_spin_trylock(lock)) -#define read_trylock(lock) __cond_lock(_read_trylock(lock)) -#define write_trylock(lock) __cond_lock(_write_trylock(lock)) +#define spin_trylock(lock) __cond_lock(_spin_trylock(lock)) +#define read_trylock(lock) __cond_lock(_read_trylock(lock)) +#define write_trylock(lock) __cond_lock(_write_trylock(lock)) -#define spin_lock(lock) _spin_lock(lock) -#define write_lock(lock) _write_lock(lock) -#define read_lock(lock) _read_lock(lock) +#define spin_lock(lock) _spin_lock(lock) +#define write_lock(lock) _write_lock(lock) +#define read_lock(lock) _read_lock(lock) -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define spin_lock_irqsave(lock, flags) flags = _spin_lock_irqsave(lock) #define read_lock_irqsave(lock, flags) flags = _read_lock_irqsave(lock) #define write_lock_irqsave(lock, flags) flags = _write_lock_irqsave(lock) @@ -470,137 +171,59 @@ do { \ #define write_lock_irq(lock) _write_lock_irq(lock) #define write_lock_bh(lock) _write_lock_bh(lock) -#define spin_unlock(lock) _spin_unlock(lock) -#define write_unlock(lock) _write_unlock(lock) -#define read_unlock(lock) _read_unlock(lock) +#define spin_unlock(lock) _spin_unlock(lock) +#define write_unlock(lock) _write_unlock(lock) +#define read_unlock(lock) _read_unlock(lock) -#define spin_unlock_irqrestore(lock, flags) _spin_unlock_irqrestore(lock, flags) +#define spin_unlock_irqrestore(lock, flags) \ + _spin_unlock_irqrestore(lock, flags) #define spin_unlock_irq(lock) _spin_unlock_irq(lock) #define spin_unlock_bh(lock) _spin_unlock_bh(lock) -#define read_unlock_irqrestore(lock, flags) _read_unlock_irqrestore(lock, flags) -#define read_unlock_irq(lock) _read_unlock_irq(lock) -#define read_unlock_bh(lock) _read_unlock_bh(lock) +#define read_unlock_irqrestore(lock, flags) \ + _read_unlock_irqrestore(lock, flags) +#define read_unlock_irq(lock) _read_unlock_irq(lock) +#define read_unlock_bh(lock) _read_unlock_bh(lock) -#define write_unlock_irqrestore(lock, flags) _write_unlock_irqrestore(lock, flags) -#define write_unlock_irq(lock) _write_unlock_irq(lock) -#define write_unlock_bh(lock) _write_unlock_bh(lock) +#define write_unlock_irqrestore(lock, flags) \ + _write_unlock_irqrestore(lock, flags) +#define write_unlock_irq(lock) _write_unlock_irq(lock) +#define write_unlock_bh(lock) _write_unlock_bh(lock) -#define spin_trylock_bh(lock) __cond_lock(_spin_trylock_bh(lock)) +#define spin_trylock_bh(lock) __cond_lock(_spin_trylock_bh(lock)) #define spin_trylock_irq(lock) \ ({ \ local_irq_disable(); \ _spin_trylock(lock) ? \ - 1 : ({local_irq_enable(); 0; }); \ + 1 : ({ local_irq_enable(); 0; }); \ }) #define spin_trylock_irqsave(lock, flags) \ ({ \ local_irq_save(flags); \ _spin_trylock(lock) ? \ - 1 : ({local_irq_restore(flags); 0;}); \ + 1 : ({ local_irq_restore(flags); 0; }); \ }) -#ifdef CONFIG_LOCKMETER -extern void _metered_spin_lock (spinlock_t *lock); -extern void _metered_spin_unlock (spinlock_t *lock); -extern int _metered_spin_trylock(spinlock_t *lock); -extern void _metered_read_lock (rwlock_t *lock); -extern void _metered_read_unlock (rwlock_t *lock); -extern void _metered_write_lock (rwlock_t *lock); -extern void _metered_write_unlock (rwlock_t *lock); -extern int _metered_read_trylock (rwlock_t *lock); -extern int _metered_write_trylock(rwlock_t *lock); -#endif - -/* "lock on reference count zero" */ -#ifndef ATOMIC_DEC_AND_LOCK -#include -extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); -#endif - -#define atomic_dec_and_lock(atomic,lock) __cond_lock(_atomic_dec_and_lock(atomic,lock)) - -/* - * bit-based spin_lock() - * - * Don't use this unless you really need to: spin_lock() and spin_unlock() - * are significantly faster. - */ -static inline void bit_spin_lock(int bitnum, unsigned long *addr) -{ - /* - * Assuming the lock is uncontended, this never enters - * the body of the outer loop. If it is contended, then - * within the inner loop a non-atomic test is used to - * busywait with less bus contention for a good time to - * attempt to acquire the lock bit. - */ - preempt_disable(); -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) - while (test_and_set_bit(bitnum, addr)) { - while (test_bit(bitnum, addr)) { - preempt_enable(); - cpu_relax(); - preempt_disable(); - } - } -#endif - __acquire(bitlock); -} - /* - * Return true if it was acquired + * Pull the atomic_t declaration: + * (asm-mips/atomic.h needs above definitions) */ -static inline int bit_spin_trylock(int bitnum, unsigned long *addr) -{ - preempt_disable(); -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) - if (test_and_set_bit(bitnum, addr)) { - preempt_enable(); - return 0; - } -#endif - __acquire(bitlock); - return 1; -} - -/* - * bit-based spin_unlock() - */ -static inline void bit_spin_unlock(int bitnum, unsigned long *addr) -{ -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) - BUG_ON(!test_bit(bitnum, addr)); - smp_mb__before_clear_bit(); - clear_bit(bitnum, addr); -#endif - preempt_enable(); - __release(bitlock); -} - -/* - * Return true if the lock is held. +#include +/** + * atomic_dec_and_lock - lock on reaching reference count zero + * @atomic: the atomic counter + * @lock: the spinlock in question */ -static inline int bit_spin_is_locked(int bitnum, unsigned long *addr) -{ -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) - return test_bit(bitnum, addr); -#elif defined CONFIG_PREEMPT - return preempt_count(); -#else - return 1; -#endif -} - -#define DEFINE_SPINLOCK(x) spinlock_t x = SPIN_LOCK_UNLOCKED -#define DEFINE_RWLOCK(x) rwlock_t x = RW_LOCK_UNLOCKED +extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); +#define atomic_dec_and_lock(atomic, lock) \ + __cond_lock(_atomic_dec_and_lock(atomic, lock)) /** * spin_can_lock - would spin_trylock() succeed? * @lock: the spinlock in question. */ -#define spin_can_lock(lock) (!spin_is_locked(lock)) +#define spin_can_lock(lock) (!spin_is_locked(lock)) #endif /* __LINUX_SPINLOCK_H */ diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h new file mode 100644 index 000000000000..78e6989ffb54 --- /dev/null +++ b/include/linux/spinlock_api_smp.h @@ -0,0 +1,57 @@ +#ifndef __LINUX_SPINLOCK_API_SMP_H +#define __LINUX_SPINLOCK_API_SMP_H + +#ifndef __LINUX_SPINLOCK_H +# error "please don't include this file directly" +#endif + +/* + * include/linux/spinlock_api_smp.h + * + * spinlock API declarations on SMP (and debug) + * (implemented in kernel/spinlock.c) + * + * portions Copyright 2005, Red Hat, Inc., Ingo Molnar + * Released under the General Public License (GPL). + */ + +int in_lock_functions(unsigned long addr); + +#define assert_spin_locked(x) BUG_ON(!spin_is_locked(x)) + +void __lockfunc _spin_lock(spinlock_t *lock) __acquires(spinlock_t); +void __lockfunc _read_lock(rwlock_t *lock) __acquires(rwlock_t); +void __lockfunc _write_lock(rwlock_t *lock) __acquires(rwlock_t); +void __lockfunc _spin_lock_bh(spinlock_t *lock) __acquires(spinlock_t); +void __lockfunc _read_lock_bh(rwlock_t *lock) __acquires(rwlock_t); +void __lockfunc _write_lock_bh(rwlock_t *lock) __acquires(rwlock_t); +void __lockfunc _spin_lock_irq(spinlock_t *lock) __acquires(spinlock_t); +void __lockfunc _read_lock_irq(rwlock_t *lock) __acquires(rwlock_t); +void __lockfunc _write_lock_irq(rwlock_t *lock) __acquires(rwlock_t); +unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock) + __acquires(spinlock_t); +unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock) + __acquires(rwlock_t); +unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock) + __acquires(rwlock_t); +int __lockfunc _spin_trylock(spinlock_t *lock); +int __lockfunc _read_trylock(rwlock_t *lock); +int __lockfunc _write_trylock(rwlock_t *lock); +int __lockfunc _spin_trylock_bh(spinlock_t *lock); +void __lockfunc _spin_unlock(spinlock_t *lock) __releases(spinlock_t); +void __lockfunc _read_unlock(rwlock_t *lock) __releases(rwlock_t); +void __lockfunc _write_unlock(rwlock_t *lock) __releases(rwlock_t); +void __lockfunc _spin_unlock_bh(spinlock_t *lock) __releases(spinlock_t); +void __lockfunc _read_unlock_bh(rwlock_t *lock) __releases(rwlock_t); +void __lockfunc _write_unlock_bh(rwlock_t *lock) __releases(rwlock_t); +void __lockfunc _spin_unlock_irq(spinlock_t *lock) __releases(spinlock_t); +void __lockfunc _read_unlock_irq(rwlock_t *lock) __releases(rwlock_t); +void __lockfunc _write_unlock_irq(rwlock_t *lock) __releases(rwlock_t); +void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) + __releases(spinlock_t); +void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags) + __releases(rwlock_t); +void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags) + __releases(rwlock_t); + +#endif /* __LINUX_SPINLOCK_API_SMP_H */ diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h new file mode 100644 index 000000000000..cd81cee566f4 --- /dev/null +++ b/include/linux/spinlock_api_up.h @@ -0,0 +1,80 @@ +#ifndef __LINUX_SPINLOCK_API_UP_H +#define __LINUX_SPINLOCK_API_UP_H + +#ifndef __LINUX_SPINLOCK_H +# error "please don't include this file directly" +#endif + +/* + * include/linux/spinlock_api_up.h + * + * spinlock API implementation on UP-nondebug (inlined implementation) + * + * portions Copyright 2005, Red Hat, Inc., Ingo Molnar + * Released under the General Public License (GPL). + */ + +#define in_lock_functions(ADDR) 0 + +#define assert_spin_locked(lock) do { (void)(lock); } while (0) + +/* + * In the UP-nondebug case there's no real locking going on, so the + * only thing we have to do is to keep the preempt counts and irq + * flags straight, to supress compiler warnings of unused lock + * variables, and to add the proper checker annotations: + */ +#define __LOCK(lock) \ + do { preempt_disable(); __acquire(lock); (void)(lock); } while (0) + +#define __LOCK_BH(lock) \ + do { local_bh_disable(); __LOCK(lock); } while (0) + +#define __LOCK_IRQ(lock) \ + do { local_irq_disable(); __LOCK(lock); } while (0) + +#define __LOCK_IRQSAVE(lock, flags) \ + do { local_irq_save(flags); __LOCK(lock); } while (0) + +#define __UNLOCK(lock) \ + do { preempt_enable(); __release(lock); (void)(lock); } while (0) + +#define __UNLOCK_BH(lock) \ + do { preempt_enable_no_resched(); local_bh_enable(); __release(lock); (void)(lock); } while (0) + +#define __UNLOCK_IRQ(lock) \ + do { local_irq_enable(); __UNLOCK(lock); } while (0) + +#define __UNLOCK_IRQRESTORE(lock, flags) \ + do { local_irq_restore(flags); __UNLOCK(lock); } while (0) + +#define _spin_lock(lock) __LOCK(lock) +#define _read_lock(lock) __LOCK(lock) +#define _write_lock(lock) __LOCK(lock) +#define _spin_lock_bh(lock) __LOCK_BH(lock) +#define _read_lock_bh(lock) __LOCK_BH(lock) +#define _write_lock_bh(lock) __LOCK_BH(lock) +#define _spin_lock_irq(lock) __LOCK_IRQ(lock) +#define _read_lock_irq(lock) __LOCK_IRQ(lock) +#define _write_lock_irq(lock) __LOCK_IRQ(lock) +#define _spin_lock_irqsave(lock, flags) __LOCK_IRQSAVE(lock, flags) +#define _read_lock_irqsave(lock, flags) __LOCK_IRQSAVE(lock, flags) +#define _write_lock_irqsave(lock, flags) __LOCK_IRQSAVE(lock, flags) +#define _spin_trylock(lock) ({ __LOCK(lock); 1; }) +#define _read_trylock(lock) ({ __LOCK(lock); 1; }) +#define _write_trylock(lock) ({ __LOCK(lock); 1; }) +#define _spin_trylock_bh(lock) ({ __LOCK_BH(lock); 1; }) +#define _spin_unlock(lock) __UNLOCK(lock) +#define _read_unlock(lock) __UNLOCK(lock) +#define _write_unlock(lock) __UNLOCK(lock) +#define _spin_unlock_bh(lock) __UNLOCK_BH(lock) +#define _write_unlock_bh(lock) __UNLOCK_BH(lock) +#define _read_unlock_bh(lock) __UNLOCK_BH(lock) +#define _spin_unlock_irq(lock) __UNLOCK_IRQ(lock) +#define _read_unlock_irq(lock) __UNLOCK_IRQ(lock) +#define _write_unlock_irq(lock) __UNLOCK_IRQ(lock) +#define _spin_unlock_irqrestore(lock, flags) __UNLOCK_IRQRESTORE(lock, flags) +#define _read_unlock_irqrestore(lock, flags) __UNLOCK_IRQRESTORE(lock, flags) +#define _write_unlock_irqrestore(lock, flags) __UNLOCK_IRQRESTORE(lock, flags) + +#endif /* __LINUX_SPINLOCK_API_UP_H */ diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h new file mode 100644 index 000000000000..9cb51e070390 --- /dev/null +++ b/include/linux/spinlock_types.h @@ -0,0 +1,67 @@ +#ifndef __LINUX_SPINLOCK_TYPES_H +#define __LINUX_SPINLOCK_TYPES_H + +/* + * include/linux/spinlock_types.h - generic spinlock type definitions + * and initializers + * + * portions Copyright 2005, Red Hat, Inc., Ingo Molnar + * Released under the General Public License (GPL). + */ + +#if defined(CONFIG_SMP) +# include +#else +# include +#endif + +typedef struct { + raw_spinlock_t raw_lock; +#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) + unsigned int break_lock; +#endif +#ifdef CONFIG_DEBUG_SPINLOCK + unsigned int magic, owner_cpu; + void *owner; +#endif +} spinlock_t; + +#define SPINLOCK_MAGIC 0xdead4ead + +typedef struct { + raw_rwlock_t raw_lock; +#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) + unsigned int break_lock; +#endif +#ifdef CONFIG_DEBUG_SPINLOCK + unsigned int magic, owner_cpu; + void *owner; +#endif +} rwlock_t; + +#define RWLOCK_MAGIC 0xdeaf1eed + +#define SPINLOCK_OWNER_INIT ((void *)-1L) + +#ifdef CONFIG_DEBUG_SPINLOCK +# define SPIN_LOCK_UNLOCKED \ + (spinlock_t) { .raw_lock = __RAW_SPIN_LOCK_UNLOCKED, \ + .magic = SPINLOCK_MAGIC, \ + .owner = SPINLOCK_OWNER_INIT, \ + .owner_cpu = -1 } +#define RW_LOCK_UNLOCKED \ + (rwlock_t) { .raw_lock = __RAW_RW_LOCK_UNLOCKED, \ + .magic = RWLOCK_MAGIC, \ + .owner = SPINLOCK_OWNER_INIT, \ + .owner_cpu = -1 } +#else +# define SPIN_LOCK_UNLOCKED \ + (spinlock_t) { .raw_lock = __RAW_SPIN_LOCK_UNLOCKED } +#define RW_LOCK_UNLOCKED \ + (rwlock_t) { .raw_lock = __RAW_RW_LOCK_UNLOCKED } +#endif + +#define DEFINE_SPINLOCK(x) spinlock_t x = SPIN_LOCK_UNLOCKED +#define DEFINE_RWLOCK(x) rwlock_t x = RW_LOCK_UNLOCKED + +#endif /* __LINUX_SPINLOCK_TYPES_H */ diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h new file mode 100644 index 000000000000..def2d173a8db --- /dev/null +++ b/include/linux/spinlock_types_up.h @@ -0,0 +1,51 @@ +#ifndef __LINUX_SPINLOCK_TYPES_UP_H +#define __LINUX_SPINLOCK_TYPES_UP_H + +#ifndef __LINUX_SPINLOCK_TYPES_H +# error "please don't include this file directly" +#endif + +/* + * include/linux/spinlock_types_up.h - spinlock type definitions for UP + * + * portions Copyright 2005, Red Hat, Inc., Ingo Molnar + * Released under the General Public License (GPL). + */ + +#ifdef CONFIG_DEBUG_SPINLOCK + +typedef struct { + volatile unsigned int slock; +} raw_spinlock_t; + +#define __RAW_SPIN_LOCK_UNLOCKED { 1 } + +#else + +/* + * All gcc 2.95 versions and early versions of 2.96 have a nasty bug + * with empty initializers. + */ +#if (__GNUC__ > 2) +typedef struct { } raw_spinlock_t; + +#define __RAW_SPIN_LOCK_UNLOCKED { } +#else +typedef struct { int gcc_is_buggy; } raw_spinlock_t; +#define __RAW_SPIN_LOCK_UNLOCKED (raw_spinlock_t) { 0 } +#endif + +#endif + +#if (__GNUC__ > 2) +typedef struct { + /* no debug version on UP */ +} raw_rwlock_t; + +#define __RAW_RW_LOCK_UNLOCKED { } +#else +typedef struct { int gcc_is_buggy; } raw_rwlock_t; +#define __RAW_RW_LOCK_UNLOCKED (raw_rwlock_t) { 0 } +#endif + +#endif /* __LINUX_SPINLOCK_TYPES_UP_H */ diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h new file mode 100644 index 000000000000..31accf2f0b13 --- /dev/null +++ b/include/linux/spinlock_up.h @@ -0,0 +1,74 @@ +#ifndef __LINUX_SPINLOCK_UP_H +#define __LINUX_SPINLOCK_UP_H + +#ifndef __LINUX_SPINLOCK_H +# error "please don't include this file directly" +#endif + +/* + * include/linux/spinlock_up.h - UP-debug version of spinlocks. + * + * portions Copyright 2005, Red Hat, Inc., Ingo Molnar + * Released under the General Public License (GPL). + * + * In the debug case, 1 means unlocked, 0 means locked. (the values + * are inverted, to catch initialization bugs) + * + * No atomicity anywhere, we are on UP. + */ + +#ifdef CONFIG_DEBUG_SPINLOCK + +#define __raw_spin_is_locked(x) ((x)->slock == 0) + +static inline void __raw_spin_lock(raw_spinlock_t *lock) +{ + lock->slock = 0; +} + +static inline void +__raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags) +{ + local_irq_save(flags); + lock->slock = 0; +} + +static inline int __raw_spin_trylock(raw_spinlock_t *lock) +{ + char oldval = lock->slock; + + lock->slock = 0; + + return oldval > 0; +} + +static inline void __raw_spin_unlock(raw_spinlock_t *lock) +{ + lock->slock = 1; +} + +/* + * Read-write spinlocks. No debug version. + */ +#define __raw_read_lock(lock) do { (void)(lock); } while (0) +#define __raw_write_lock(lock) do { (void)(lock); } while (0) +#define __raw_read_trylock(lock) ({ (void)(lock); 1; }) +#define __raw_write_trylock(lock) ({ (void)(lock); 1; }) +#define __raw_read_unlock(lock) do { (void)(lock); } while (0) +#define __raw_write_unlock(lock) do { (void)(lock); } while (0) + +#else /* DEBUG_SPINLOCK */ +#define __raw_spin_is_locked(lock) ((void)(lock), 0) +/* for sched.c and kernel_lock.c: */ +# define __raw_spin_lock(lock) do { (void)(lock); } while (0) +# define __raw_spin_unlock(lock) do { (void)(lock); } while (0) +# define __raw_spin_trylock(lock) ({ (void)(lock); 1; }) +#endif /* DEBUG_SPINLOCK */ + +#define __raw_read_can_lock(lock) (((void)(lock), 1)) +#define __raw_write_can_lock(lock) (((void)(lock), 1)) + +#define __raw_spin_unlock_wait(lock) \ + do { cpu_relax(); } while (__raw_spin_is_locked(lock)) + +#endif /* __LINUX_SPINLOCK_UP_H */ -- cgit v1.2.3 From 4247bdc60048018b98f71228b45cfbc5f5270c86 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Sat, 10 Sep 2005 00:26:06 -0700 Subject: [PATCH] cpuset semaphore depth check deadlock fix The cpusets-formalize-intermediate-gfp_kernel-containment patch has a deadlock problem. This patch was part of a set of four patches to make more extensive use of the cpuset 'mem_exclusive' attribute to manage kernel GFP_KERNEL memory allocations and to constrain the out-of-memory (oom) killer. A task that is changing cpusets in particular ways on a system when it is very short of free memory could double trip over the global cpuset_sem semaphore (get the lock and then deadlock trying to get it again). The second attempt to get cpuset_sem would be in the routine cpuset_zone_allowed(). This was discovered by code inspection. I can not reproduce the problem except with an artifically hacked kernel and a specialized stress test. In real life you cannot hit this unless you are manipulating cpusets, and are very unlikely to hit it unless you are rapidly modifying cpusets on a memory tight system. Even then it would be a rare occurence. If you did hit it, the task double tripping over cpuset_sem would deadlock in the kernel, and any other task also trying to manipulate cpusets would deadlock there too, on cpuset_sem. Your batch manager would be wedged solid (if it was cpuset savvy), but classic Unix shells and utilities would work well enough to reboot the system. The unusual condition that led to this bug is that unlike most semaphores, cpuset_sem _can_ be acquired while in the page allocation code, when __alloc_pages() calls cpuset_zone_allowed. So it easy to mistakenly perform the following sequence: 1) task makes system call to alter a cpuset 2) take cpuset_sem 3) try to allocate memory 4) memory allocator, via cpuset_zone_allowed, trys to take cpuset_sem 5) deadlock The reason that this is not a serious bug for most users is that almost all calls to allocate memory don't require taking cpuset_sem. Only some code paths off the beaten track require taking cpuset_sem -- which is good. Taking a global semaphore on the main code path for allocating memory would not scale well. This patch fixes this deadlock by wrapping the up() and down() calls on cpuset_sem in kernel/cpuset.c with code that tracks the nesting depth of the current task on that semaphore, and only does the real down() if the task doesn't hold the lock already, and only does the real up() if the nesting depth (number of unmatched downs) is exactly one. The previous required use of refresh_mems(), anytime that the cpuset_sem semaphore was acquired and the code executed while holding that semaphore might try to allocate memory, is no longer required. Two refresh_mems() calls were removed thanks to this. This is a good change, as failing to get all the necessary refresh_mems() calls placed was a primary source of bugs in this cpuset code. The only remaining call to refresh_mems() is made while doing a memory allocation, if certain task memory placement data needs to be updated from its cpuset, due to the cpuset having been changed behind the tasks back. Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c551e6a1447e..8a1fcfe80fc7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -782,6 +782,7 @@ struct task_struct { short il_next; #endif #ifdef CONFIG_CPUSETS + short cpuset_sem_nest_depth; struct cpuset *cpuset; nodemask_t mems_allowed; int cpuset_mems_generation; -- cgit v1.2.3 From d79fc0fc6645b0cf5cd980da76942ca6d6300fa4 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 10 Sep 2005 00:26:12 -0700 Subject: [PATCH] sched: TASK_NONINTERACTIVE This patch implements a task state bit (TASK_NONINTERACTIVE), which can be used by blocking points to mark the task's wait as "non-interactive". This does not mean the task will be considered a CPU-hog - the wait will simply not have an effect on the waiting task's priority - positive or negative alike. Right now only pipe_wait() will make use of it, because it's a common source of not-so-interactive waits (kernel compilation jobs, etc.). Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8a1fcfe80fc7..ac70f845b5b1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -114,6 +114,7 @@ extern unsigned long nr_iowait(void); #define TASK_TRACED 8 #define EXIT_ZOMBIE 16 #define EXIT_DEAD 32 +#define TASK_NONINTERACTIVE 64 #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) -- cgit v1.2.3 From 5ce7852cdf07ab903fb1c72d0915ac492c6e07c7 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sat, 10 Sep 2005 00:26:28 -0700 Subject: [PATCH] mm/filemap.c: make two functions static With Nick Piggin Give some things static scope. Signed-off-by: Adrian Bunk Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 -- include/linux/writeback.h | 2 -- 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7f61227827d7..e0b77c5af9a0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1509,8 +1509,6 @@ extern void do_generic_mapping_read(struct address_space *mapping, loff_t *, read_descriptor_t *, read_actor_t); extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); -extern ssize_t generic_file_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs); extern ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, unsigned long nr_segs, loff_t *ppos); ssize_t generic_file_writev(struct file *filp, const struct iovec *iov, diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 542dbaee6512..343d883d69c5 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -109,8 +109,6 @@ int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0); int do_writepages(struct address_space *mapping, struct writeback_control *wbc); int sync_page_range(struct inode *inode, struct address_space *mapping, loff_t pos, size_t count); -int sync_page_range_nolock(struct inode *inode, struct address_space - *mapping, loff_t pos, size_t count); /* pdflush.c */ extern int nr_pdflush_threads; /* Global so it can be exported to sysctl -- cgit v1.2.3 From b2d550736f8b2186b8ef7e206d0bfbfec2238ae8 Mon Sep 17 00:00:00 2001 From: Victor Fusco Date: Sat, 10 Sep 2005 00:26:36 -0700 Subject: [PATCH] mm/slab: fix sparse warnings Fix the sparse warning "implicit cast to nocast type" Signed-off-by: Victor Fusco Signed-off-by: Domen Puncer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 42a6bea58af3..1f356f3bbc64 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -118,7 +118,8 @@ extern void kfree(const void *); extern unsigned int ksize(const void *); #ifdef CONFIG_NUMA -extern void *kmem_cache_alloc_node(kmem_cache_t *, int flags, int node); +extern void *kmem_cache_alloc_node(kmem_cache_t *, + unsigned int __nocast flags, int node); extern void *kmalloc_node(size_t size, unsigned int __nocast flags, int node); #else static inline void *kmem_cache_alloc_node(kmem_cache_t *cachep, int flags, int node) -- cgit v1.2.3 From 00b61f51922e432fd92a482ba1e0b5f8f326ef46 Mon Sep 17 00:00:00 2001 From: Victor Fusco Date: Sat, 10 Sep 2005 00:26:48 -0700 Subject: [PATCH] lib/radix-tree: Fix "nocast type" warnings Fix the sparse warning "implicit cast to nocast type" Signed-off-by: Victor Fusco Signed-off-by: Domen Puncer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 8081a281fa5e..9c51917b1cce 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -24,7 +24,7 @@ struct radix_tree_root { unsigned int height; - int gfp_mask; + unsigned int gfp_mask; struct radix_tree_node *rnode; }; @@ -50,7 +50,7 @@ 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); -int radix_tree_preload(int gfp_mask); +int radix_tree_preload(unsigned int __nocast gfp_mask); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, int tag); -- cgit v1.2.3 From 3a11ec5e502cb61ee31095008318f9c107d9db60 Mon Sep 17 00:00:00 2001 From: Victor Fusco Date: Sat, 10 Sep 2005 00:26:49 -0700 Subject: [PATCH] dmapool: Fix "nocast type" warnings Fix the sparse warning "implicit cast to nocast type" Signed-off-by: Victor Fusco Signed-off-by: Domen Puncer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dmapool.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmapool.h b/include/linux/dmapool.h index e60bfdac348d..4932ee5c77f0 100644 --- a/include/linux/dmapool.h +++ b/include/linux/dmapool.h @@ -19,7 +19,8 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, void dma_pool_destroy(struct dma_pool *pool); -void *dma_pool_alloc(struct dma_pool *pool, int mem_flags, dma_addr_t *handle); +void *dma_pool_alloc(struct dma_pool *pool, unsigned int __nocast mem_flags, + dma_addr_t *handle); void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t addr); -- cgit v1.2.3 From 2befb9e36dc52d715c3a67a9dbad36ac1edc376f Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sat, 10 Sep 2005 00:27:17 -0700 Subject: [PATCH] include/linux/blkdev.h: "extern inline" -> "static inline" "extern inline" doesn't make much sense. Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index aefa26fbae8a..efdc9b5bc05c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -728,7 +728,7 @@ static inline unsigned int blksize_bits(unsigned int size) return bits; } -extern inline unsigned int block_size(struct block_device *bdev) +static inline unsigned int block_size(struct block_device *bdev) { return bdev->bd_block_size; } -- cgit v1.2.3 From 9adeb1b409e832c31d93106ce52482a5f0078439 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sat, 10 Sep 2005 00:27:18 -0700 Subject: [PATCH] "extern inline" -> "static inline" "extern inline" doesn't make much sense. Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 17e458e17e2b..af00b10294cd 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2097,7 +2097,7 @@ void reiserfs_free_block(struct reiserfs_transaction_handle *th, struct inode *, b_blocknr_t, int for_unformatted); int reiserfs_allocate_blocknrs(reiserfs_blocknr_hint_t *, b_blocknr_t *, int, int); -extern inline int reiserfs_new_form_blocknrs(struct tree_balance *tb, +static inline int reiserfs_new_form_blocknrs(struct tree_balance *tb, b_blocknr_t * new_blocknrs, int amount_needed) { @@ -2113,7 +2113,7 @@ extern inline int reiserfs_new_form_blocknrs(struct tree_balance *tb, 0); } -extern inline int reiserfs_new_unf_blocknrs(struct reiserfs_transaction_handle +static inline int reiserfs_new_unf_blocknrs(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t * new_blocknrs, struct path *path, long block) @@ -2130,7 +2130,7 @@ extern inline int reiserfs_new_unf_blocknrs(struct reiserfs_transaction_handle } #ifdef REISERFS_PREALLOCATE -extern inline int reiserfs_new_unf_blocknrs2(struct reiserfs_transaction_handle +static inline int reiserfs_new_unf_blocknrs2(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t * new_blocknrs, struct path *path, long block) -- cgit v1.2.3 From c2d08dade7743bd3a28cc5f68163e71c00a2a908 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sat, 10 Sep 2005 00:27:18 -0700 Subject: [PATCH] include/linux/bio.h: "extern inline" -> "static inline" "extern inline" doesn't make much sense. Signed-off-by: Adrian Bunk Acked-by: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bio.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index cdaf03a14a51..6e1c79c8b6bf 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -314,9 +314,8 @@ void zero_fill_bio(struct bio *bio); * bvec_kmap_irq and bvec_kunmap_irq!! * * This function MUST be inlined - it plays with the CPU interrupt flags. - * Hence the `extern inline'. */ -extern inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) +static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) { unsigned long addr; @@ -332,7 +331,7 @@ extern inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) return (char *) addr + bvec->bv_offset; } -extern inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) +static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) { unsigned long ptr = (unsigned long) buffer & PAGE_MASK; @@ -345,7 +344,7 @@ extern inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) #define bvec_kunmap_irq(buf, flags) do { *(flags) = 0; } while (0) #endif -extern inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx, +static inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx, unsigned long *flags) { return bvec_kmap_irq(bio_iovec_idx(bio, idx), flags); -- cgit v1.2.3 From 64ed93a268bc18fa6f72f61420d0e0022c5e38d1 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Sat, 10 Sep 2005 00:27:21 -0700 Subject: [PATCH] add schedule_timeout_{,un}interruptible() interfaces Add schedule_timeout_{,un}interruptible() interfaces so that schedule_timeout() callers don't have to worry about forgetting to add the set_current_state() call beforehand. Signed-off-by: Nishanth Aravamudan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ac70f845b5b1..4b83cb230006 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -203,6 +203,8 @@ extern int in_sched_functions(unsigned long addr); #define MAX_SCHEDULE_TIMEOUT LONG_MAX extern signed long FASTCALL(schedule_timeout(signed long timeout)); +extern signed long schedule_timeout_interruptible(signed long timeout); +extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); struct namespace; -- cgit v1.2.3 From 84f902c0903a98a315b45a4fba3d2ac0de388256 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Sat, 10 Sep 2005 00:27:22 -0700 Subject: [PATCH] include: update jiffies/{m,u}secs conversion functions Clarify the human-time units to jiffies conversion functions by using the constants in time.h. This makes many of the subsequent patches direct copies of the current code. Signed-off-by: Nishanth Aravamudan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jiffies.h | 40 ++++++++++++++++++++-------------------- include/linux/time.h | 2 ++ 2 files changed, 22 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index d7a2555a886c..6acfdbba734b 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -254,23 +254,23 @@ static inline u64 get_jiffies_64(void) */ static inline unsigned int jiffies_to_msecs(const unsigned long j) { -#if HZ <= 1000 && !(1000 % HZ) - return (1000 / HZ) * j; -#elif HZ > 1000 && !(HZ % 1000) - return (j + (HZ / 1000) - 1)/(HZ / 1000); +#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) + return (MSEC_PER_SEC / HZ) * j; +#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) + return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else - return (j * 1000) / HZ; + return (j * MSEC_PER_SEC) / HZ; #endif } static inline unsigned int jiffies_to_usecs(const unsigned long j) { -#if HZ <= 1000000 && !(1000000 % HZ) - return (1000000 / HZ) * j; -#elif HZ > 1000000 && !(HZ % 1000000) - return (j + (HZ / 1000000) - 1)/(HZ / 1000000); +#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) + return (USEC_PER_SEC / HZ) * j; +#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC) + return (j + (HZ / USEC_PER_SEC) - 1)/(HZ / USEC_PER_SEC); #else - return (j * 1000000) / HZ; + return (j * USEC_PER_SEC) / HZ; #endif } @@ -278,12 +278,12 @@ static inline unsigned long msecs_to_jiffies(const unsigned int m) { if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; -#if HZ <= 1000 && !(1000 % HZ) - return (m + (1000 / HZ) - 1) / (1000 / HZ); -#elif HZ > 1000 && !(HZ % 1000) - return m * (HZ / 1000); +#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) + return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ); +#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) + return m * (HZ / MSEC_PER_SEC); #else - return (m * HZ + 999) / 1000; + return (m * HZ + MSEC_PER_SEC - 1) / MSEC_PER_SEC; #endif } @@ -291,12 +291,12 @@ static inline unsigned long usecs_to_jiffies(const unsigned int u) { if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; -#if HZ <= 1000000 && !(1000000 % HZ) - return (u + (1000000 / HZ) - 1) / (1000000 / HZ); -#elif HZ > 1000000 && !(HZ % 1000000) - return u * (HZ / 1000000); +#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) + return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ); +#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC) + return u * (HZ / USEC_PER_SEC); #else - return (u * HZ + 999999) / 1000000; + return (u * HZ + USEC_PER_SEC - 1) / USEC_PER_SEC; #endif } diff --git a/include/linux/time.h b/include/linux/time.h index c10d4c21c183..36fb2ef13cff 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -28,6 +28,8 @@ struct timezone { #ifdef __KERNEL__ /* Parameters used to convert the timespec values */ +#define MSEC_PER_SEC (1000L) + #ifndef USEC_PER_SEC #define USEC_PER_SEC (1000000L) #endif -- cgit v1.2.3 From 373016e9e1353f2af871993d27d00768f08cc883 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sat, 10 Sep 2005 00:27:23 -0700 Subject: [PATCH] time.h: remove ifdefs Remove these ifdefs - there's no need to have more than one definition of these multipliers anywhere. Cc: Nishanth Aravamudan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/time.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 36fb2ef13cff..8e83f4e778bb 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -29,18 +29,9 @@ struct timezone { /* Parameters used to convert the timespec values */ #define MSEC_PER_SEC (1000L) - -#ifndef USEC_PER_SEC #define USEC_PER_SEC (1000000L) -#endif - -#ifndef NSEC_PER_SEC #define NSEC_PER_SEC (1000000000L) -#endif - -#ifndef NSEC_PER_USEC #define NSEC_PER_USEC (1000L) -#endif static __inline__ int timespec_equal(struct timespec *a, struct timespec *b) { -- cgit v1.2.3 From fe08ac3178243fbed61f24878ffcf5cfb53fceb1 Mon Sep 17 00:00:00 2001 From: "viro@ZenIV.linux.org.uk" Date: Fri, 9 Sep 2005 22:03:44 +0100 Subject: [PATCH] __user annotations (scsi/ch) Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/chio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/chio.h b/include/linux/chio.h index 63035ae67e63..a404c111c937 100644 --- a/include/linux/chio.h +++ b/include/linux/chio.h @@ -96,7 +96,7 @@ struct changer_position { */ struct changer_element_status { int ces_type; - unsigned char *ces_data; + unsigned char __user *ces_data; }; #define CESTATUS_FULL 0x01 /* full */ #define CESTATUS_IMPEXP 0x02 /* media was imported (inserted by sysop) */ -- cgit v1.2.3 From a2a979821b6ab75a4f143cfaa1c4672cc259ec10 Mon Sep 17 00:00:00 2001 From: Keith Owens Date: Sun, 11 Sep 2005 17:19:06 +1000 Subject: [PATCH] MCA/INIT: scheduler hooks Scheduler hooks to see/change which process is deemed to be on a cpu. Signed-off-by: Keith Owens Signed-off-by: Tony Luck --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4b83cb230006..ed3bb19d1337 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -904,6 +904,8 @@ extern int task_curr(const task_t *p); extern int idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, struct sched_param *); extern task_t *idle_task(int cpu); +extern task_t *curr_task(int cpu); +extern void set_curr_task(int cpu, task_t *p); void yield(void); -- cgit v1.2.3 From 7672d0b54411371e0b6a831c1cb2f0ce615de6dc Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Sun, 11 Sep 2005 19:15:07 -0700 Subject: [NET]: Add netlink connector. Kernel connector - new userspace <-> kernel space easy to use communication module which implements easy to use bidirectional message bus using netlink as it's backend. Connector was created to eliminate complex skb handling both in send and receive message bus direction. Connector driver adds possibility to connect various agents using as one of it's backends netlink based network. One must register callback and identifier. When driver receives special netlink message with appropriate identifier, appropriate callback will be called. From the userspace point of view it's quite straightforward: socket(); bind(); send(); recv(); But if kernelspace want to use full power of such connections, driver writer must create special sockets, must know about struct sk_buff handling... Connector allows any kernelspace agents to use netlink based networking for inter-process communication in a significantly easier way: int cn_add_callback(struct cb_id *id, char *name, void (*callback) (void *)); void cn_netlink_send(struct cn_msg *msg, u32 __groups, int gfp_mask); struct cb_id { __u32 idx; __u32 val; }; idx and val are unique identifiers which must be registered in connector.h for in-kernel usage. void (*callback) (void *) - is a callback function which will be called when message with above idx.val will be received by connector core. Using connector completely hides low-level transport layer from it's users. Connector uses new netlink ability to have many groups in one socket. [ Incorporating many cleanups and fixes by myself and Andrew Morton -DaveM ] Signed-off-by: Evgeniy Polyakov Signed-off-by: Andrew Morton Signed-off-by: David S. Miller --- include/linux/connector.h | 158 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/netlink.h | 1 + 2 files changed, 159 insertions(+) create mode 100644 include/linux/connector.h (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h new file mode 100644 index 000000000000..96de26301f84 --- /dev/null +++ b/include/linux/connector.h @@ -0,0 +1,158 @@ +/* + * connector.h + * + * 2004-2005 Copyright (c) Evgeniy Polyakov + * All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef __CONNECTOR_H +#define __CONNECTOR_H + +#include + +#define CN_IDX_CONNECTOR 0xffffffff +#define CN_VAL_CONNECTOR 0xffffffff + +#define CN_NETLINK_USERS 1 + +/* + * Maximum connector's message size. + */ +#define CONNECTOR_MAX_MSG_SIZE 1024 + +/* + * idx and val are unique identifiers which + * are used for message routing and + * must be registered in connector.h for in-kernel usage. + */ + +struct cb_id { + __u32 idx; + __u32 val; +}; + +struct cn_msg { + struct cb_id id; + + __u32 seq; + __u32 ack; + + __u16 len; /* Length of the following data */ + __u16 flags; + __u8 data[0]; +}; + +/* + * Notify structure - requests notification about + * registering/unregistering idx/val in range [first, first+range]. + */ +struct cn_notify_req { + __u32 first; + __u32 range; +}; + +/* + * Main notification control message + * *_notify_num - number of appropriate cn_notify_req structures after + * this struct. + * group - notification receiver's idx. + * len - total length of the attached data. + */ +struct cn_ctl_msg { + __u32 idx_notify_num; + __u32 val_notify_num; + __u32 group; + __u32 len; + __u8 data[0]; +}; + +#ifdef __KERNEL__ + +#include + +#include +#include + +#include + +#define CN_CBQ_NAMELEN 32 + +struct cn_queue_dev { + atomic_t refcnt; + unsigned char name[CN_CBQ_NAMELEN]; + + struct workqueue_struct *cn_queue; + + struct list_head queue_list; + spinlock_t queue_lock; + + int netlink_groups; + struct sock *nls; +}; + +struct cn_callback { + unsigned char name[CN_CBQ_NAMELEN]; + + struct cb_id id; + void (*callback) (void *); + void *priv; +}; + +struct cn_callback_entry { + struct list_head callback_entry; + struct cn_callback *cb; + struct work_struct work; + struct cn_queue_dev *pdev; + + void (*destruct_data) (void *); + void *ddata; + + int seq, group; + struct sock *nls; +}; + +struct cn_ctl_entry { + struct list_head notify_entry; + struct cn_ctl_msg *msg; +}; + +struct cn_dev { + struct cb_id id; + + u32 seq, groups; + struct sock *nls; + void (*input) (struct sock * sk, int len); + + struct cn_queue_dev *cbdev; +}; + +int cn_add_callback(struct cb_id *, char *, void (*callback) (void *)); +void cn_del_callback(struct cb_id *); +int cn_netlink_send(struct cn_msg *, u32, int); + +int cn_queue_add_callback(struct cn_queue_dev *dev, struct cn_callback *cb); +void cn_queue_del_callback(struct cn_queue_dev *dev, struct cb_id *id); + +struct cn_queue_dev *cn_queue_alloc_dev(char *name, struct sock *); +void cn_queue_free_dev(struct cn_queue_dev *dev); + +int cn_cb_equal(struct cb_id *, struct cb_id *); + +extern int cn_already_initialized; + +#endif /* __KERNEL__ */ +#endif /* __CONNECTOR_H */ diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 167518668936..7bbd25970c9e 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -15,6 +15,7 @@ #define NETLINK_ISCSI 8 /* Open-iSCSI */ #define NETLINK_AUDIT 9 /* auditing */ #define NETLINK_FIB_LOOKUP 10 +#define NETLINK_CONNECTOR 11 #define NETLINK_NETFILTER 12 /* netfilter subsystem */ #define NETLINK_IP6_FW 13 #define NETLINK_DNRTMSG 14 /* DECnet routing messages */ -- cgit v1.2.3 From f24ec7f6c6278c0ea4c00efe96d50b1e66796c44 Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Mon, 12 Sep 2005 17:12:43 +0400 Subject: [PATCH] crc16: remove w1 specific comments. Remove w1 comments from crc16.h and move specific constants into w1_ds2433.c where they are used. Replace %d with %zd. Signed-off-by: Evgeniy Polyakov Signed-off-by: Linus Torvalds --- include/linux/crc16.h | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crc16.h b/include/linux/crc16.h index bdedf825b04a..9443c084f881 100644 --- a/include/linux/crc16.h +++ b/include/linux/crc16.h @@ -1,22 +1,11 @@ /* * crc16.h - CRC-16 routine * - * Implements the standard CRC-16, as used with 1-wire devices: + * Implements the standard CRC-16: * Width 16 * Poly 0x8005 (x^16 + x^15 + x^2 + 1) * Init 0 * - * For 1-wire devices, the CRC is stored inverted, LSB-first - * - * Example buffer with the CRC attached: - * 31 32 33 34 35 36 37 38 39 C2 44 - * - * The CRC over a buffer with the CRC attached is 0xB001. - * So, if (crc16(0, buf, size) == 0xB001) then the buffer is valid. - * - * Refer to "Application Note 937: Book of iButton Standards" for details. - * http://www.maxim-ic.com/appnotes.cfm/appnote_number/937 - * * Copyright (c) 2005 Ben Gardner * * This source code is licensed under the GNU General Public License, @@ -28,9 +17,6 @@ #include -#define CRC16_INIT 0 -#define CRC16_VALID 0xb001 - extern u16 const crc16_table[256]; extern u16 crc16(u16 crc, const u8 *buffer, size_t len); -- cgit v1.2.3 From b3426599af9524104be6938bcb1fcaab314781c7 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Mon, 12 Sep 2005 04:30:30 -0700 Subject: [PATCH] cpuset semaphore depth check optimize Optimize the deadlock avoidance check on the global cpuset semaphore cpuset_sem. Instead of adding a depth counter to the task struct of each task, rather just two words are enough, one to store the depth and the other the current cpuset_sem holder. Thanks to Nikita Danilov for the idea. Signed-off-by: Paul Jackson [ We may want to change this further, but at least it's now a totally internal decision to the cpusets code ] Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ed3bb19d1337..38c8654aaa96 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -785,7 +785,6 @@ struct task_struct { short il_next; #endif #ifdef CONFIG_CPUSETS - short cpuset_sem_nest_depth; struct cpuset *cpuset; nodemask_t mems_allowed; int cpuset_mems_generation; -- cgit v1.2.3 From 3f74478b5fd7263e9311cdb320923d599c73a792 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 12 Sep 2005 18:49:24 +0200 Subject: [PATCH] x86-64: Some cleanup and optimization to the processor data area. - Remove unused irqrsp field - Remove pda->me - Optimize set_softirq_pending slightly Signed-off-by: Andi Kleen Signed-off-by: Linus Torvalds --- include/linux/interrupt.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index d99e7aeb7d33..0a90205184b0 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -57,6 +57,11 @@ extern void disable_irq(unsigned int irq); extern void enable_irq(unsigned int irq); #endif +#ifndef __ARCH_SET_SOFTIRQ_PENDING +#define set_softirq_pending(x) (local_softirq_pending() = (x)) +#define or_softirq_pending(x) (local_softirq_pending() |= (x)) +#endif + /* * Temporary defines for UP kernels, until all code gets fixed. */ @@ -123,7 +128,7 @@ struct softirq_action asmlinkage void do_softirq(void); extern void open_softirq(int nr, void (*action)(struct softirq_action*), void *data); extern void softirq_init(void); -#define __raise_softirq_irqoff(nr) do { local_softirq_pending() |= 1UL << (nr); } while (0) +#define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0) extern void FASTCALL(raise_softirq_irqoff(unsigned int nr)); extern void FASTCALL(raise_softirq(unsigned int nr)); -- cgit v1.2.3 From c47a3167d0454c0af5fb0a0322b01a0e3487798e Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 12 Sep 2005 18:49:25 +0200 Subject: [PATCH] x86-64: Make dmi_find_device for !DMI case inline Otherwise it will generate warnings and be generated many times. Signed-off-by: Andi Kleen Signed-off-by: Linus Torvalds --- include/linux/dmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmi.h b/include/linux/dmi.h index c30175e8dec6..a415f1d93e9a 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -70,7 +70,7 @@ extern struct dmi_device * dmi_find_device(int type, const char *name, static inline int dmi_check_system(struct dmi_system_id *list) { return 0; } static inline char * dmi_get_system_info(int field) { return NULL; } -static struct dmi_device * dmi_find_device(int type, const char *name, +static inline struct dmi_device * dmi_find_device(int type, const char *name, struct dmi_device *from) { return NULL; } #endif -- cgit v1.2.3 From ce441594e965e32965432404cfaba73e8fbc6ff7 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Sat, 3 Sep 2005 11:27:08 +0200 Subject: [PATCH] USB: fix usbdevice_fs header breakage [USBDEVFS] fix inclusion of to avoud header mess Without moving the include of compat.h down, userspace programs that use usbdevice_fs.h end up including half the kernel includes (and eventually fail to compile). Signed-off-by: Harald Welte Signed-off-by: Greg Kroah-Hartman --- include/linux/usbdevice_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usbdevice_fs.h b/include/linux/usbdevice_fs.h index fb57c2217468..9facf733800c 100644 --- a/include/linux/usbdevice_fs.h +++ b/include/linux/usbdevice_fs.h @@ -32,7 +32,6 @@ #define _LINUX_USBDEVICE_FS_H #include -#include /* --------------------------------------------------------------------- */ @@ -125,6 +124,7 @@ struct usbdevfs_hub_portinfo { }; #ifdef CONFIG_COMPAT +#include struct usbdevfs_urb32 { unsigned char type; unsigned char endpoint; -- cgit v1.2.3 From e21ce8c7c013fb223a002c70bb0a547de6c26c12 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Mon, 12 Sep 2005 14:27:37 -0700 Subject: [NETROM]: Implement G8PZT Circuit reset for NET/ROM NET/ROM is lacking a connection reset like TCP's RST flag which at times may result in a connecting having to slowly timing out instead of just being reset. An earlier attempt to reset the connection by sending a NR_CONNACK | NR_CHOKE_FLAG transport was inacceptable as it did result in crashes of BPQ systems. An alternative approach of introducing a new transport type 7 (NR_RESET) has be implemented several years ago in Paula Jayne Dowie G8PZT's Xrouter. Implement NR_RESET for Linux's NET/ROM but like any messing with the state engine consider this experimental for now and thus control it by a sysctl (net.netrom.reset) which for the time being defaults to off. Signed-off-by: Ralf Baechle DL5RB Signed-off-by: David S. Miller --- include/linux/sysctl.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 532a6c5c24e9..3a29a9f9b451 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -544,7 +544,8 @@ enum { NET_NETROM_TRANSPORT_REQUESTED_WINDOW_SIZE=8, NET_NETROM_TRANSPORT_NO_ACTIVITY_TIMEOUT=9, NET_NETROM_ROUTING_CONTROL=10, - NET_NETROM_LINK_FAILS_COUNT=11 + NET_NETROM_LINK_FAILS_COUNT=11, + NET_NETROM_RESET=12 }; /* /proc/sys/net/ax25 */ -- cgit v1.2.3