From f21e0e81d81b649ad309cedc7226f1bed72982e0 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 24 May 2011 08:12:40 +0800 Subject: regulator: Do bulk enables of regulators in parallel In order to reduce the impact of ramp times rather than enabling the regulators for a device in series use async tasks to run the actual enables. This means that the delays which the enables implement can all run in parallel, though it does mean that the order in which the supplies come on may be unstable. For super bonus fun points if any of the regulators are shared between multiple supplies on the same device (as is rather likely) then this will test our locking. Note that in this case we only delay once for each physical regulator so the threads shouldn't block each other while delaying. It'd be even nicer if we could coalesce writes to a shared enable registers in PMICs but that's definitely future work, and it may also be useful and is certainly more achievable to optimise out the parallelism if none of the regulators implement ramp delays. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/consumer.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 9e87c1cb7270..26f6ea4444e3 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -122,6 +122,9 @@ struct regulator; struct regulator_bulk_data { const char *supply; struct regulator *consumer; + + /* Internal use */ + int ret; }; #if defined(CONFIG_REGULATOR) -- cgit v1.2.3 From debf9507166eede1e676d27d3298cdfb27399cb4 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 8 Jun 2011 18:19:37 +0900 Subject: serial: sh-sci: Generalize overrun handling. This consolidates all of the broken out overrun handling and ensures that we have sensible defaults per-port type, in addition to making sure that overruns are flagged appropriately in the error mask for parts that haven't explicitly disabled support for it. Signed-off-by: Paul Mundt --- drivers/tty/serial/sh-sci.c | 51 ++++++++++++++++++++++++++++++++++++++------ drivers/tty/serial/sh-sci.h | 52 ++------------------------------------------- include/linux/serial_sci.h | 30 ++++++++++++++++++++++++++ 3 files changed, 77 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 280c02af0eae..bb27885ea2e5 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -563,13 +563,19 @@ static int sci_handle_errors(struct uart_port *port) int copied = 0; unsigned short status = sci_in(port, SCxSR); struct tty_struct *tty = port->state->port.tty; + struct sci_port *s = to_sci_port(port); - if (status & SCxSR_ORER(port)) { - /* overrun error */ - if (tty_insert_flip_char(tty, 0, TTY_OVERRUN)) - copied++; + /* + * Handle overruns, if supported. + */ + if (s->cfg->overrun_bit != SCIx_NOT_SUPPORTED) { + if (status & (1 << s->cfg->overrun_bit)) { + /* overrun error */ + if (tty_insert_flip_char(tty, 0, TTY_OVERRUN)) + copied++; - dev_notice(port->dev, "overrun error"); + dev_notice(port->dev, "overrun error"); + } } if (status & SCxSR_FER(port)) { @@ -617,12 +623,19 @@ static int sci_handle_errors(struct uart_port *port) static int sci_handle_fifo_overrun(struct uart_port *port) { struct tty_struct *tty = port->state->port.tty; + struct sci_port *s = to_sci_port(port); int copied = 0; + /* + * XXX: Technically not limited to non-SCIFs, it's simply the + * SCLSR check that is for the moment SCIF-specific. This + * probably wants to be revisited for SCIFA/B as well as for + * factoring in SCI overrun detection. + */ if (port->type != PORT_SCIF) return 0; - if ((sci_in(port, SCLSR) & SCIF_ORER) != 0) { + if ((sci_in(port, SCLSR) & (1 << s->cfg->overrun_bit))) { sci_out(port, SCLSR, 0); tty_insert_flip_char(tty, 0, TTY_OVERRUN); @@ -1755,6 +1768,32 @@ static int __devinit sci_init_single(struct platform_device *dev, sci_port->break_timer.function = sci_break_timer; init_timer(&sci_port->break_timer); + /* + * Establish some sensible defaults for the error detection. + */ + if (!p->error_mask) + p->error_mask = (p->type == PORT_SCI) ? + SCI_DEFAULT_ERROR_MASK : SCIF_DEFAULT_ERROR_MASK; + + /* + * Establish sensible defaults for the overrun detection, unless + * the part has explicitly disabled support for it. + */ + if (p->overrun_bit != SCIx_NOT_SUPPORTED) { + if (p->type == PORT_SCI) + p->overrun_bit = 5; + else if (p->scbrr_algo_id == SCBRR_ALGO_4) + p->overrun_bit = 9; + else + p->overrun_bit = 0; + + /* + * Make the error mask inclusive of overrun detection, if + * supported. + */ + p->error_mask |= (1 << p->overrun_bit); + } + sci_port->cfg = p; port->mapbase = p->mapbase; diff --git a/drivers/tty/serial/sh-sci.h b/drivers/tty/serial/sh-sci.h index ed1c09c0454a..caab353a98b5 100644 --- a/drivers/tty/serial/sh-sci.h +++ b/drivers/tty/serial/sh-sci.h @@ -19,11 +19,9 @@ defined(CONFIG_ARCH_SH7372) # define PORT_PTCR 0xA405011EUL # define PORT_PVCR 0xA4050122UL -# define SCIF_ORER 0x0200 /* overrun error bit */ #elif defined(CONFIG_SH_RTS7751R2D) # define SCSPTR1 0xFFE0001C /* 8 bit SCIF */ # define SCSPTR2 0xFFE80020 /* 16 bit SCIF */ -# define SCIF_ORER 0x0001 /* overrun error bit */ #elif defined(CONFIG_CPU_SUBTYPE_SH7750) || \ defined(CONFIG_CPU_SUBTYPE_SH7750R) || \ defined(CONFIG_CPU_SUBTYPE_SH7750S) || \ @@ -32,15 +30,12 @@ defined(CONFIG_CPU_SUBTYPE_SH7751R) # define SCSPTR1 0xffe0001c /* 8 bit SCI */ # define SCSPTR2 0xFFE80020 /* 16 bit SCIF */ -# define SCIF_ORER 0x0001 /* overrun error bit */ #elif defined(CONFIG_CPU_SUBTYPE_SH7760) # define SCSPTR0 0xfe600024 /* 16 bit SCIF */ # define SCSPTR1 0xfe610024 /* 16 bit SCIF */ # define SCSPTR2 0xfe620024 /* 16 bit SCIF */ -# define SCIF_ORER 0x0001 /* overrun error bit */ #elif defined(CONFIG_CPU_SUBTYPE_SH7710) || defined(CONFIG_CPU_SUBTYPE_SH7712) # define SCSPTR0 0xA4400000 /* 16 bit SCIF */ -# define SCIF_ORER 0x0001 /* overrun error bit */ # define PACR 0xa4050100 # define PBCR 0xa4050102 #elif defined(CONFIG_CPU_SUBTYPE_SH7343) @@ -48,35 +43,24 @@ #elif defined(CONFIG_CPU_SUBTYPE_SH7722) # define PWDR 0xA4050166 # define PSCR 0xA405011E -# define SCIF_ORER 0x0001 /* overrun error bit */ #elif defined(CONFIG_CPU_SUBTYPE_SH7366) # define SCPDR0 0xA405013E /* 16 bit SCIF0 PSDR */ # define SCSPTR0 SCPDR0 -# define SCIF_ORER 0x0001 /* overrun error bit */ #elif defined(CONFIG_CPU_SUBTYPE_SH7723) # define SCSPTR0 0xa4050160 -# define SCIF_ORER 0x0001 /* overrun error bit */ -#elif defined(CONFIG_CPU_SUBTYPE_SH7724) -# define SCIF_ORER 0x0001 /* overrun error bit */ #elif defined(CONFIG_CPU_SUBTYPE_SH4_202) # define SCSPTR2 0xffe80020 /* 16 bit SCIF */ -# define SCIF_ORER 0x0001 /* overrun error bit */ #elif defined(CONFIG_CPU_SUBTYPE_SH7757) # define SCSPTR0 0xfe4b0020 -# define SCIF_ORER 0x0001 #elif defined(CONFIG_CPU_SUBTYPE_SH7763) # define SCSPTR0 0xffe00024 /* 16 bit SCIF */ -# define SCIF_ORER 0x0001 /* overrun error bit */ #elif defined(CONFIG_CPU_SUBTYPE_SH7770) # define SCSPTR0 0xff923020 /* 16 bit SCIF */ -# define SCIF_ORER 0x0001 /* overrun error bit */ #elif defined(CONFIG_CPU_SUBTYPE_SH7780) # define SCSPTR0 0xffe00024 /* 16 bit SCIF */ -# define SCIF_ORER 0x0001 /* Overrun error bit */ #elif defined(CONFIG_CPU_SUBTYPE_SH7785) || \ defined(CONFIG_CPU_SUBTYPE_SH7786) # define SCSPTR0 0xffea0024 /* 16 bit SCIF */ -# define SCIF_ORER 0x0001 /* Overrun error bit */ #elif defined(CONFIG_CPU_SUBTYPE_SH7201) || \ defined(CONFIG_CPU_SUBTYPE_SH7203) || \ defined(CONFIG_CPU_SUBTYPE_SH7206) || \ @@ -84,36 +68,12 @@ # define SCSPTR0 0xfffe8020 /* 16 bit SCIF */ #elif defined(CONFIG_CPU_SUBTYPE_SH7619) # define SCSPTR0 0xf8400020 /* 16 bit SCIF */ -# define SCIF_ORER 0x0001 /* overrun error bit */ #elif defined(CONFIG_CPU_SUBTYPE_SHX3) # define SCSPTR0 0xffc30020 /* 16 bit SCIF */ -# define SCIF_ORER 0x0001 /* Overrun error bit */ #else # error CPU subtype not defined #endif -/* SCxSR SCI */ -#define SCI_TDRE 0x80 /* 7707 SCI, 7708 SCI, 7709 SCI, 7750 SCI */ -#define SCI_RDRF 0x40 /* 7707 SCI, 7708 SCI, 7709 SCI, 7750 SCI */ -#define SCI_ORER 0x20 /* 7707 SCI, 7708 SCI, 7709 SCI, 7750 SCI */ -#define SCI_FER 0x10 /* 7707 SCI, 7708 SCI, 7709 SCI, 7750 SCI */ -#define SCI_PER 0x08 /* 7707 SCI, 7708 SCI, 7709 SCI, 7750 SCI */ -#define SCI_TEND 0x04 /* 7707 SCI, 7708 SCI, 7709 SCI, 7750 SCI */ -/* SCI_MPB 0x02 * 7707 SCI, 7708 SCI, 7709 SCI, 7750 SCI */ -/* SCI_MPBT 0x01 * 7707 SCI, 7708 SCI, 7709 SCI, 7750 SCI */ - -#define SCI_ERRORS ( SCI_PER | SCI_FER | SCI_ORER) - -/* SCxSR SCIF */ -#define SCIF_ER 0x0080 /* 7705 SCIF, 7707 SCIF, 7709 SCIF, 7750 SCIF */ -#define SCIF_TEND 0x0040 /* 7705 SCIF, 7707 SCIF, 7709 SCIF, 7750 SCIF */ -#define SCIF_TDFE 0x0020 /* 7705 SCIF, 7707 SCIF, 7709 SCIF, 7750 SCIF */ -#define SCIF_BRK 0x0010 /* 7705 SCIF, 7707 SCIF, 7709 SCIF, 7750 SCIF */ -#define SCIF_FER 0x0008 /* 7705 SCIF, 7707 SCIF, 7709 SCIF, 7750 SCIF */ -#define SCIF_PER 0x0004 /* 7705 SCIF, 7707 SCIF, 7709 SCIF, 7750 SCIF */ -#define SCIF_RDF 0x0002 /* 7705 SCIF, 7707 SCIF, 7709 SCIF, 7750 SCIF */ -#define SCIF_DR 0x0001 /* 7705 SCIF, 7707 SCIF, 7709 SCIF, 7750 SCIF */ - #if defined(CONFIG_CPU_SUBTYPE_SH7705) || \ defined(CONFIG_CPU_SUBTYPE_SH7720) || \ defined(CONFIG_CPU_SUBTYPE_SH7721) || \ @@ -121,35 +81,27 @@ defined(CONFIG_ARCH_SH7367) || \ defined(CONFIG_ARCH_SH7377) || \ defined(CONFIG_ARCH_SH7372) -# define SCIF_ORER 0x0200 -# define SCIF_ERRORS ( SCIF_PER | SCIF_FER | SCIF_ER | SCIF_BRK | SCIF_ORER) # define SCIF_RFDC_MASK 0x007f # define SCIF_TXROOM_MAX 64 #elif defined(CONFIG_CPU_SUBTYPE_SH7763) -# define SCIF_ERRORS ( SCIF_PER | SCIF_FER | SCIF_ER | SCIF_BRK ) # define SCIF_RFDC_MASK 0x007f # define SCIF_TXROOM_MAX 64 /* SH7763 SCIF2 support */ # define SCIF2_RFDC_MASK 0x001f # define SCIF2_TXROOM_MAX 16 #else -# define SCIF_ERRORS ( SCIF_PER | SCIF_FER | SCIF_ER | SCIF_BRK) # define SCIF_RFDC_MASK 0x001f # define SCIF_TXROOM_MAX 16 #endif -#ifndef SCIF_ORER -#define SCIF_ORER 0x0000 -#endif - #define SCxSR_TEND(port) (((port)->type == PORT_SCI) ? SCI_TEND : SCIF_TEND) -#define SCxSR_ERRORS(port) (((port)->type == PORT_SCI) ? SCI_ERRORS : SCIF_ERRORS) #define SCxSR_RDxF(port) (((port)->type == PORT_SCI) ? SCI_RDRF : SCIF_RDF) #define SCxSR_TDxE(port) (((port)->type == PORT_SCI) ? SCI_TDRE : SCIF_TDFE) #define SCxSR_FER(port) (((port)->type == PORT_SCI) ? SCI_FER : SCIF_FER) #define SCxSR_PER(port) (((port)->type == PORT_SCI) ? SCI_PER : SCIF_PER) #define SCxSR_BRK(port) (((port)->type == PORT_SCI) ? 0x00 : SCIF_BRK) -#define SCxSR_ORER(port) (((port)->type == PORT_SCI) ? SCI_ORER : SCIF_ORER) + +#define SCxSR_ERRORS(port) (to_sci_port(port)->cfg->error_mask) #if defined(CONFIG_CPU_SUBTYPE_SH7705) || \ defined(CONFIG_CPU_SUBTYPE_SH7720) || \ diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index a2afc9fbe186..5fac3bccfd87 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -8,6 +8,8 @@ * Generic header for SuperH SCI(F) (used by sh/sh64/h8300 and related parts) */ +#define SCIx_NOT_SUPPORTED (-1) + enum { SCBRR_ALGO_1, /* ((clk + 16 * bps) / (16 * bps) - 1) */ SCBRR_ALGO_2, /* ((clk + 16 * bps) / (32 * bps) - 1) */ @@ -25,6 +27,28 @@ enum { #define SCSCR_CKE1 (1 << 1) #define SCSCR_CKE0 (1 << 0) +/* SCxSR SCI */ +#define SCI_TDRE 0x80 +#define SCI_RDRF 0x40 +#define SCI_ORER 0x20 +#define SCI_FER 0x10 +#define SCI_PER 0x08 +#define SCI_TEND 0x04 + +#define SCI_DEFAULT_ERROR_MASK (SCI_PER | SCI_FER) + +/* SCxSR SCIF */ +#define SCIF_ER 0x0080 +#define SCIF_TEND 0x0040 +#define SCIF_TDFE 0x0020 +#define SCIF_BRK 0x0010 +#define SCIF_FER 0x0008 +#define SCIF_PER 0x0004 +#define SCIF_RDF 0x0002 +#define SCIF_DR 0x0001 + +#define SCIF_DEFAULT_ERROR_MASK (SCIF_PER | SCIF_FER | SCIF_ER | SCIF_BRK) + /* Offsets into the sci_port->irqs array */ enum { SCIx_ERI_IRQ, @@ -56,6 +80,12 @@ struct plat_sci_port { unsigned int scbrr_algo_id; /* SCBRR calculation algo */ unsigned int scscr; /* SCSCR initialization */ + /* + * Platform overrides if necessary, defaults otherwise. + */ + int overrun_bit; + unsigned int error_mask; + struct device *dma_dev; unsigned int dma_slave_tx; -- cgit v1.2.3 From 514820eb982eb85677ed2ecef9710e90e24fbdab Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 8 Jun 2011 18:51:32 +0900 Subject: serial: sh-sci: Consolidate RXD pin handling. Non-SCI parts do not have the special port reg necessary for cases where the RX and SCI pins are muxed and need to be manually polled, so these like always fall back on the normal FIFO processing paths. SH7760 is in a class in and of itself with regards to mapping its SIM card interface via the SCI port class despite not having any of the RXD lines wired up and so implicitly behaving more like a SCIF in this regard. Out of the other CPUs, some support the port check via the same block while others do it through an external SuperI/O, so it's not even possible to perform the check relative to the ioremapped cookie offset, so the separate read semantics are preserved here, too. Signed-off-by: Paul Mundt --- arch/sh/kernel/cpu/sh3/setup-sh770x.c | 1 + arch/sh/kernel/cpu/sh4/setup-sh7750.c | 1 + drivers/tty/serial/sh-sci.c | 13 +++++++++++++ drivers/tty/serial/sh-sci.h | 29 ----------------------------- include/linux/serial_sci.h | 2 ++ 5 files changed, 17 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c index 4551ad647c2c..6d549792f791 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c @@ -108,6 +108,7 @@ static struct platform_device rtc_device = { static struct plat_sci_port scif0_platform_data = { .mapbase = 0xfffffe80, + .port_reg = 0xa4000136, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_TE | SCSCR_RE, .scbrr_algo_id = SCBRR_ALGO_2, diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7750.c b/arch/sh/kernel/cpu/sh4/setup-sh7750.c index e53b4b38bd11..8ea26e791187 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh7750.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh7750.c @@ -38,6 +38,7 @@ static struct platform_device rtc_device = { static struct plat_sci_port sci_platform_data = { .mapbase = 0xffe00000, + .port_reg = 0xffe0001C .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_TE | SCSCR_RE, .scbrr_algo_id = SCBRR_ALGO_2, diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index bb27885ea2e5..3248ddaa889d 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -363,6 +363,19 @@ static int sci_rxfill(struct uart_port *port) return (sci_in(port, SCxSR) & SCxSR_RDxF(port)) != 0; } +/* + * SCI helper for checking the state of the muxed port/RXD pins. + */ +static inline int sci_rxd_in(struct uart_port *port) +{ + struct sci_port *s = to_sci_port(port); + + if (s->cfg->port_reg <= 0) + return 1; + + return !!__raw_readb(s->cfg->port_reg); +} + /* ********************************************************************** * * the interrupt related routines * * ********************************************************************** */ diff --git a/drivers/tty/serial/sh-sci.h b/drivers/tty/serial/sh-sci.h index caab353a98b5..1c20f7f9ba4f 100644 --- a/drivers/tty/serial/sh-sci.h +++ b/drivers/tty/serial/sh-sci.h @@ -287,32 +287,3 @@ SCIF_FNS(SCLSR, 0, 0, 0x24, 16) #endif #define sci_in(port, reg) sci_##reg##_in(port) #define sci_out(port, reg, value) sci_##reg##_out(port, value) - -#if defined(CONFIG_CPU_SUBTYPE_SH7706) || \ - defined(CONFIG_CPU_SUBTYPE_SH7707) || \ - defined(CONFIG_CPU_SUBTYPE_SH7708) || \ - defined(CONFIG_CPU_SUBTYPE_SH7709) -static inline int sci_rxd_in(struct uart_port *port) -{ - if (port->mapbase == 0xfffffe80) - return __raw_readb(SCPDR)&0x01 ? 1 : 0; /* SCI */ - return 1; -} -#elif defined(CONFIG_CPU_SUBTYPE_SH7750) || \ - defined(CONFIG_CPU_SUBTYPE_SH7751) || \ - defined(CONFIG_CPU_SUBTYPE_SH7751R) || \ - defined(CONFIG_CPU_SUBTYPE_SH7750R) || \ - defined(CONFIG_CPU_SUBTYPE_SH7750S) || \ - defined(CONFIG_CPU_SUBTYPE_SH7091) -static inline int sci_rxd_in(struct uart_port *port) -{ - if (port->mapbase == 0xffe00000) - return __raw_readb(SCSPTR1)&0x01 ? 1 : 0; /* SCI */ - return 1; -} -#else /* default case for non-SCI processors */ -static inline int sci_rxd_in(struct uart_port *port) -{ - return 1; -} -#endif diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index 5fac3bccfd87..ecefec7c0b67 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -86,6 +86,8 @@ struct plat_sci_port { int overrun_bit; unsigned int error_mask; + int port_reg; + struct device *dma_dev; unsigned int dma_slave_tx; -- cgit v1.2.3 From 3801b86aa482d26a8ae460f67fca29e016491a86 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 9 Jun 2011 16:22:22 +0100 Subject: regulator: Refactor supply implementation to work as regular consumers Currently the regulator supply implementation is somewhat complex and fragile as it doesn't look like standard consumers but is instead a parallel implementation. This causes issues with locking and reference counting. Move the implementation over to using standard consumers to address this. Rather than only notifying the supply on the first enable/disable we do so every time the regulator is enabled or disabled, simplifying locking as we don't need to hold a lock on the consumer we are about to enable. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- drivers/regulator/core.c | 101 ++++++++++++++------------------------- include/linux/regulator/driver.h | 4 +- 2 files changed, 37 insertions(+), 68 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index e3b67ee48b23..f0cc3983ffee 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -82,8 +82,7 @@ struct regulator { }; static int _regulator_is_enabled(struct regulator_dev *rdev); -static int _regulator_disable(struct regulator_dev *rdev, - struct regulator_dev **supply_rdev_ptr); +static int _regulator_disable(struct regulator_dev *rdev); static int _regulator_get_voltage(struct regulator_dev *rdev); static int _regulator_get_current_limit(struct regulator_dev *rdev); static unsigned int _regulator_get_mode(struct regulator_dev *rdev); @@ -91,6 +90,9 @@ static void _notifier_call_chain(struct regulator_dev *rdev, unsigned long event, void *data); static int _regulator_do_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV); +static struct regulator *create_regulator(struct regulator_dev *rdev, + struct device *dev, + const char *supply_name); static const char *rdev_get_name(struct regulator_dev *rdev) { @@ -930,21 +932,20 @@ out: * core if it's child is enabled. */ static int set_supply(struct regulator_dev *rdev, - struct regulator_dev *supply_rdev) + struct regulator_dev *supply_rdev) { int err; - err = sysfs_create_link(&rdev->dev.kobj, &supply_rdev->dev.kobj, - "supply"); - if (err) { - rdev_err(rdev, "could not add device link %s err %d\n", - supply_rdev->dev.kobj.name, err); - goto out; + rdev_info(rdev, "supplied by %s\n", rdev_get_name(supply_rdev)); + + rdev->supply = create_regulator(supply_rdev, &rdev->dev, "SUPPLY"); + if (IS_ERR(rdev->supply)) { + err = PTR_ERR(rdev->supply); + rdev->supply = NULL; + return err; } - rdev->supply = supply_rdev; - list_add(&rdev->slist, &supply_rdev->supply_list); -out: - return err; + + return 0; } /** @@ -1303,19 +1304,6 @@ static int _regulator_enable(struct regulator_dev *rdev) { int ret, delay; - if (rdev->use_count == 0) { - /* do we need to enable the supply regulator first */ - if (rdev->supply) { - mutex_lock(&rdev->supply->mutex); - ret = _regulator_enable(rdev->supply); - mutex_unlock(&rdev->supply->mutex); - if (ret < 0) { - rdev_err(rdev, "failed to enable: %d\n", ret); - return ret; - } - } - } - /* check voltage and requested load before enabling */ if (rdev->constraints && (rdev->constraints->valid_ops_mask & REGULATOR_CHANGE_DRMS)) @@ -1390,19 +1378,27 @@ int regulator_enable(struct regulator *regulator) struct regulator_dev *rdev = regulator->rdev; int ret = 0; + if (rdev->supply) { + ret = regulator_enable(rdev->supply); + if (ret != 0) + return ret; + } + mutex_lock(&rdev->mutex); ret = _regulator_enable(rdev); mutex_unlock(&rdev->mutex); + + if (ret != 0) + regulator_disable(rdev->supply); + return ret; } EXPORT_SYMBOL_GPL(regulator_enable); /* locks held by regulator_disable() */ -static int _regulator_disable(struct regulator_dev *rdev, - struct regulator_dev **supply_rdev_ptr) +static int _regulator_disable(struct regulator_dev *rdev) { int ret = 0; - *supply_rdev_ptr = NULL; if (WARN(rdev->use_count <= 0, "unbalanced disables for %s\n", rdev_get_name(rdev))) @@ -1429,9 +1425,6 @@ static int _regulator_disable(struct regulator_dev *rdev, NULL); } - /* decrease our supplies ref count and disable if required */ - *supply_rdev_ptr = rdev->supply; - rdev->use_count = 0; } else if (rdev->use_count > 1) { @@ -1442,6 +1435,7 @@ static int _regulator_disable(struct regulator_dev *rdev, rdev->use_count--; } + return ret; } @@ -1460,29 +1454,21 @@ static int _regulator_disable(struct regulator_dev *rdev, int regulator_disable(struct regulator *regulator) { struct regulator_dev *rdev = regulator->rdev; - struct regulator_dev *supply_rdev = NULL; int ret = 0; mutex_lock(&rdev->mutex); - ret = _regulator_disable(rdev, &supply_rdev); + ret = _regulator_disable(rdev); mutex_unlock(&rdev->mutex); - /* decrease our supplies ref count and disable if required */ - while (supply_rdev != NULL) { - rdev = supply_rdev; - - mutex_lock(&rdev->mutex); - _regulator_disable(rdev, &supply_rdev); - mutex_unlock(&rdev->mutex); - } + if (ret == 0 && rdev->supply) + regulator_disable(rdev->supply); return ret; } EXPORT_SYMBOL_GPL(regulator_disable); /* locks held by regulator_force_disable() */ -static int _regulator_force_disable(struct regulator_dev *rdev, - struct regulator_dev **supply_rdev_ptr) +static int _regulator_force_disable(struct regulator_dev *rdev) { int ret = 0; @@ -1499,10 +1485,6 @@ static int _regulator_force_disable(struct regulator_dev *rdev, REGULATOR_EVENT_DISABLE, NULL); } - /* decrease our supplies ref count and disable if required */ - *supply_rdev_ptr = rdev->supply; - - rdev->use_count = 0; return ret; } @@ -1518,16 +1500,16 @@ static int _regulator_force_disable(struct regulator_dev *rdev, int regulator_force_disable(struct regulator *regulator) { struct regulator_dev *rdev = regulator->rdev; - struct regulator_dev *supply_rdev = NULL; int ret; mutex_lock(&rdev->mutex); regulator->uA_load = 0; - ret = _regulator_force_disable(rdev, &supply_rdev); + ret = _regulator_force_disable(regulator->rdev); mutex_unlock(&rdev->mutex); - if (supply_rdev) - regulator_disable(get_device_regulator(rdev_get_dev(supply_rdev))); + if (rdev->supply) + while (rdev->open_count--) + regulator_disable(rdev->supply); return ret; } @@ -2138,7 +2120,7 @@ int regulator_set_optimum_mode(struct regulator *regulator, int uA_load) /* get input voltage */ input_uV = 0; if (rdev->supply) - input_uV = _regulator_get_voltage(rdev->supply); + input_uV = regulator_get_voltage(rdev->supply); if (input_uV <= 0) input_uV = rdev->constraints->input_uV; if (input_uV <= 0) { @@ -2208,17 +2190,8 @@ EXPORT_SYMBOL_GPL(regulator_unregister_notifier); static void _notifier_call_chain(struct regulator_dev *rdev, unsigned long event, void *data) { - struct regulator_dev *_rdev; - /* call rdev chain first */ blocking_notifier_call_chain(&rdev->notifier, event, NULL); - - /* now notify regulator we supply */ - list_for_each_entry(_rdev, &rdev->supply_list, slist) { - mutex_lock(&_rdev->mutex); - _notifier_call_chain(_rdev, event, data); - mutex_unlock(&_rdev->mutex); - } } /** @@ -2610,9 +2583,7 @@ struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc, rdev->owner = regulator_desc->owner; rdev->desc = regulator_desc; INIT_LIST_HEAD(&rdev->consumer_list); - INIT_LIST_HEAD(&rdev->supply_list); INIT_LIST_HEAD(&rdev->list); - INIT_LIST_HEAD(&rdev->slist); BLOCKING_INIT_NOTIFIER_HEAD(&rdev->notifier); /* preform any regulator specific init */ @@ -2724,7 +2695,7 @@ void regulator_unregister(struct regulator_dev *rdev) unset_regulator_supplies(rdev); list_del(&rdev->list); if (rdev->supply) - sysfs_remove_link(&rdev->dev.kobj, "supply"); + regulator_put(rdev->supply); device_unregister(&rdev->dev); kfree(rdev->constraints); mutex_unlock(®ulator_list_mutex); diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 6c433b89c80d..1a80bc77517d 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -188,18 +188,16 @@ struct regulator_dev { /* lists we belong to */ struct list_head list; /* list of all regulators */ - struct list_head slist; /* list of supplied regulators */ /* lists we own */ struct list_head consumer_list; /* consumers we supply */ - struct list_head supply_list; /* regulators we supply */ struct blocking_notifier_head notifier; struct mutex mutex; /* consumer lock */ struct module *owner; struct device dev; struct regulation_constraints *constraints; - struct regulator_dev *supply; /* for tree */ + struct regulator *supply; /* for tree */ void *reg_data; /* regulator_dev data */ -- cgit v1.2.3 From 61a6976bf19a6cf5dfcf37c3536665b316f22d49 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Tue, 14 Jun 2011 12:40:19 +0900 Subject: serial: sh-sci: Abstract register maps. This takes a bit of a sledgehammer to the horribly CPU subtype ifdef-ridden header and abstracts all of the different register layouts in to distinct types which in turn can be overriden on a per-port basis, or permitted to default to the map matching the port type at probe time. In the process this ultimately fixes up inumerable bugs with mismatches on various CPU types (particularly the legacy ones that were obviously broken years ago and no one noticed) and provides a more tightly coupled and consolidated platform for extending and implementing generic features. Signed-off-by: Paul Mundt --- arch/sh/Makefile | 1 + arch/sh/include/cpu-sh3/cpu/serial.h | 10 + arch/sh/include/cpu-sh4a/cpu/serial.h | 7 + arch/sh/kernel/cpu/sh3/Makefile | 18 +- arch/sh/kernel/cpu/sh3/serial-sh770x.c | 33 +++ arch/sh/kernel/cpu/sh3/serial-sh7710.c | 20 ++ arch/sh/kernel/cpu/sh3/serial-sh7720.c | 36 ++++ arch/sh/kernel/cpu/sh3/setup-sh7705.c | 5 + arch/sh/kernel/cpu/sh3/setup-sh770x.c | 8 + arch/sh/kernel/cpu/sh3/setup-sh7720.c | 5 + arch/sh/kernel/cpu/sh4/setup-sh7750.c | 3 +- arch/sh/kernel/cpu/sh4/setup-sh7760.c | 4 + arch/sh/kernel/cpu/sh4a/Makefile | 2 +- arch/sh/kernel/cpu/sh4a/serial-sh7722.c | 23 ++ arch/sh/kernel/cpu/sh4a/setup-sh7366.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7722.c | 6 + arch/sh/kernel/cpu/sh4a/setup-sh7723.c | 9 + arch/sh/kernel/cpu/sh4a/setup-sh7724.c | 9 + arch/sh/kernel/cpu/sh4a/setup-sh7763.c | 3 + arch/sh/kernel/cpu/sh4a/setup-sh7780.c | 3 +- arch/sh/kernel/cpu/sh4a/setup-sh7785.c | 8 +- arch/sh/kernel/cpu/sh4a/setup-sh7786.c | 8 +- drivers/tty/serial/sh-sci.c | 364 ++++++++++++++++++++++++-------- drivers/tty/serial/sh-sci.h | 222 ------------------- include/linux/serial_sci.h | 36 ++++ 25 files changed, 516 insertions(+), 328 deletions(-) create mode 100644 arch/sh/include/cpu-sh3/cpu/serial.h create mode 100644 arch/sh/include/cpu-sh4a/cpu/serial.h create mode 100644 arch/sh/kernel/cpu/sh3/serial-sh770x.c create mode 100644 arch/sh/kernel/cpu/sh3/serial-sh7710.c create mode 100644 arch/sh/kernel/cpu/sh3/serial-sh7720.c create mode 100644 arch/sh/kernel/cpu/sh4a/serial-sh7722.c (limited to 'include/linux') diff --git a/arch/sh/Makefile b/arch/sh/Makefile index e3d8170ad00b..99385d0b3f3b 100644 --- a/arch/sh/Makefile +++ b/arch/sh/Makefile @@ -173,6 +173,7 @@ core-$(CONFIG_HD6446X_SERIES) += arch/sh/cchips/hd6446x/ cpuincdir-$(CONFIG_CPU_SH2A) += cpu-sh2a cpuincdir-$(CONFIG_CPU_SH2) += cpu-sh2 cpuincdir-$(CONFIG_CPU_SH3) += cpu-sh3 +cpuincdir-$(CONFIG_CPU_SH4A) += cpu-sh4a cpuincdir-$(CONFIG_CPU_SH4) += cpu-sh4 cpuincdir-$(CONFIG_CPU_SH5) += cpu-sh5 cpuincdir-y += cpu-common # Must be last diff --git a/arch/sh/include/cpu-sh3/cpu/serial.h b/arch/sh/include/cpu-sh3/cpu/serial.h new file mode 100644 index 000000000000..7766329bc103 --- /dev/null +++ b/arch/sh/include/cpu-sh3/cpu/serial.h @@ -0,0 +1,10 @@ +#ifndef __CPU_SH3_SERIAL_H +#define __CPU_SH3_SERIAL_H + +#include + +extern struct plat_sci_port_ops sh770x_sci_port_ops; +extern struct plat_sci_port_ops sh7710_sci_port_ops; +extern struct plat_sci_port_ops sh7720_sci_port_ops; + +#endif /* __CPU_SH3_SERIAL_H */ diff --git a/arch/sh/include/cpu-sh4a/cpu/serial.h b/arch/sh/include/cpu-sh4a/cpu/serial.h new file mode 100644 index 000000000000..ff1bc275d210 --- /dev/null +++ b/arch/sh/include/cpu-sh4a/cpu/serial.h @@ -0,0 +1,7 @@ +#ifndef __CPU_SH4A_SERIAL_H +#define __CPU_SH4A_SERIAL_H + +/* arch/sh/kernel/cpu/sh4a/serial-sh7722.c */ +extern struct plat_sci_port_ops sh7722_sci_port_ops; + +#endif /* __CPU_SH4A_SERIAL_H */ diff --git a/arch/sh/kernel/cpu/sh3/Makefile b/arch/sh/kernel/cpu/sh3/Makefile index ecab274141a8..6f13f33a35ff 100644 --- a/arch/sh/kernel/cpu/sh3/Makefile +++ b/arch/sh/kernel/cpu/sh3/Makefile @@ -7,15 +7,15 @@ obj-y := ex.o probe.o entry.o setup-sh3.o obj-$(CONFIG_HIBERNATION) += swsusp.o # CPU subtype setup -obj-$(CONFIG_CPU_SUBTYPE_SH7705) += setup-sh7705.o -obj-$(CONFIG_CPU_SUBTYPE_SH7706) += setup-sh770x.o -obj-$(CONFIG_CPU_SUBTYPE_SH7707) += setup-sh770x.o -obj-$(CONFIG_CPU_SUBTYPE_SH7708) += setup-sh770x.o -obj-$(CONFIG_CPU_SUBTYPE_SH7709) += setup-sh770x.o -obj-$(CONFIG_CPU_SUBTYPE_SH7710) += setup-sh7710.o -obj-$(CONFIG_CPU_SUBTYPE_SH7712) += setup-sh7710.o -obj-$(CONFIG_CPU_SUBTYPE_SH7720) += setup-sh7720.o -obj-$(CONFIG_CPU_SUBTYPE_SH7721) += setup-sh7720.o +obj-$(CONFIG_CPU_SUBTYPE_SH7705) += setup-sh7705.o serial-sh770x.o +obj-$(CONFIG_CPU_SUBTYPE_SH7706) += setup-sh770x.o serial-sh770x.o +obj-$(CONFIG_CPU_SUBTYPE_SH7707) += setup-sh770x.o serial-sh770x.o +obj-$(CONFIG_CPU_SUBTYPE_SH7708) += setup-sh770x.o serial-sh770x.o +obj-$(CONFIG_CPU_SUBTYPE_SH7709) += setup-sh770x.o serial-sh770x.o +obj-$(CONFIG_CPU_SUBTYPE_SH7710) += setup-sh7710.o serial-sh7710.o +obj-$(CONFIG_CPU_SUBTYPE_SH7712) += setup-sh7710.o serial-sh7710.o +obj-$(CONFIG_CPU_SUBTYPE_SH7720) += setup-sh7720.o serial-sh7720.o +obj-$(CONFIG_CPU_SUBTYPE_SH7721) += setup-sh7720.o serial-sh7720.o # Primary on-chip clocks (common) clock-$(CONFIG_CPU_SH3) := clock-sh3.o diff --git a/arch/sh/kernel/cpu/sh3/serial-sh770x.c b/arch/sh/kernel/cpu/sh3/serial-sh770x.c new file mode 100644 index 000000000000..4f7242c676b3 --- /dev/null +++ b/arch/sh/kernel/cpu/sh3/serial-sh770x.c @@ -0,0 +1,33 @@ +#include +#include +#include +#include + +#define SCPCR 0xA4000116 +#define SCPDR 0xA4000136 + +static void sh770x_sci_init_pins(struct uart_port *port, unsigned int cflag) +{ + unsigned short data; + + /* We need to set SCPCR to enable RTS/CTS */ + data = __raw_readw(SCPCR); + /* Clear out SCP7MD1,0, SCP6MD1,0, SCP4MD1,0*/ + __raw_writew(data & 0x0fcf, SCPCR); + + if (!(cflag & CRTSCTS)) { + /* We need to set SCPCR to enable RTS/CTS */ + data = __raw_readw(SCPCR); + /* Clear out SCP7MD1,0, SCP4MD1,0, + Set SCP6MD1,0 = {01} (output) */ + __raw_writew((data & 0x0fcf) | 0x1000, SCPCR); + + data = __raw_readb(SCPDR); + /* Set /RTS2 (bit6) = 0 */ + __raw_writeb(data & 0xbf, SCPDR); + } +} + +struct plat_sci_port_ops sh770x_sci_port_ops = { + .init_pins = sh770x_sci_init_pins, +}; diff --git a/arch/sh/kernel/cpu/sh3/serial-sh7710.c b/arch/sh/kernel/cpu/sh3/serial-sh7710.c new file mode 100644 index 000000000000..42190ef6aebf --- /dev/null +++ b/arch/sh/kernel/cpu/sh3/serial-sh7710.c @@ -0,0 +1,20 @@ +#include +#include +#include +#include + +#define PACR 0xa4050100 +#define PBCR 0xa4050102 + +static void sh7710_sci_init_pins(struct uart_port *port, unsigned int cflag) +{ + if (port->mapbase == 0xA4400000) { + __raw_writew(__raw_readw(PACR) & 0xffc0, PACR); + __raw_writew(__raw_readw(PBCR) & 0x0fff, PBCR); + } else if (port->mapbase == 0xA4410000) + __raw_writew(__raw_readw(PBCR) & 0xf003, PBCR); +} + +struct plat_sci_port_ops sh7710_sci_port_ops = { + .init_pins = sh7710_sci_init_pins, +}; diff --git a/arch/sh/kernel/cpu/sh3/serial-sh7720.c b/arch/sh/kernel/cpu/sh3/serial-sh7720.c new file mode 100644 index 000000000000..8234e1e7abd9 --- /dev/null +++ b/arch/sh/kernel/cpu/sh3/serial-sh7720.c @@ -0,0 +1,36 @@ +#include +#include +#include +#include + +static void sh7720_sci_init_pins(struct uart_port *port, unsigned int cflag) +{ + unsigned short data; + + if (cflag & CRTSCTS) { + /* enable RTS/CTS */ + if (port->mapbase == 0xa4430000) { /* SCIF0 */ + /* Clear PTCR bit 9-2; enable all scif pins but sck */ + data = __raw_readw(PORT_PTCR); + __raw_writew((data & 0xfc03), PORT_PTCR); + } else if (port->mapbase == 0xa4438000) { /* SCIF1 */ + /* Clear PVCR bit 9-2 */ + data = __raw_readw(PORT_PVCR); + __raw_writew((data & 0xfc03), PORT_PVCR); + } + } else { + if (port->mapbase == 0xa4430000) { /* SCIF0 */ + /* Clear PTCR bit 5-2; enable only tx and rx */ + data = __raw_readw(PORT_PTCR); + __raw_writew((data & 0xffc3), PORT_PTCR); + } else if (port->mapbase == 0xa4438000) { /* SCIF1 */ + /* Clear PVCR bit 5-2 */ + data = __raw_readw(PORT_PVCR); + __raw_writew((data & 0xffc3), PORT_PVCR); + } + } +} + +struct plat_sci_port_ops sh7720_sci_port_ops = { + .init_pins = sh7720_sci_init_pins, +}; diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7705.c b/arch/sh/kernel/cpu/sh3/setup-sh7705.c index cd2e702feb7e..2309618c015d 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh7705.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh7705.c @@ -15,6 +15,7 @@ #include #include #include +#include enum { UNUSED = 0, @@ -75,6 +76,8 @@ static struct plat_sci_port scif0_platform_data = { .scbrr_algo_id = SCBRR_ALGO_4, .type = PORT_SCIF, .irqs = { 56, 56, 56 }, + .ops = &sh770x_sci_port_ops, + .regtype = SCIx_SH7705_SCIF_REGTYPE, }; static struct platform_device scif0_device = { @@ -92,6 +95,8 @@ static struct plat_sci_port scif1_platform_data = { .scbrr_algo_id = SCBRR_ALGO_4, .type = PORT_SCIF, .irqs = { 52, 52, 52 }, + .ops = &sh770x_sci_port_ops, + .regtype = SCIx_SH7705_SCIF_REGTYPE, }; static struct platform_device scif1_device = { diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c index 6d549792f791..3f3d5fe5892d 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c @@ -19,6 +19,7 @@ #include #include #include +#include enum { UNUSED = 0, @@ -114,6 +115,8 @@ static struct plat_sci_port scif0_platform_data = { .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCI, .irqs = { 23, 23, 23, 0 }, + .ops = &sh770x_sci_port_ops, + .regshift = 1, }; static struct platform_device scif0_device = { @@ -133,6 +136,8 @@ static struct plat_sci_port scif1_platform_data = { .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 56, 56, 56, 56 }, + .ops = &sh770x_sci_port_ops, + .regtype = SCIx_SH3_SCIF_REGTYPE, }; static struct platform_device scif1_device = { @@ -147,11 +152,14 @@ static struct platform_device scif1_device = { defined(CONFIG_CPU_SUBTYPE_SH7709) static struct plat_sci_port scif2_platform_data = { .mapbase = 0xa4000140, + .port_reg = SCIx_NOT_SUPPORTED, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_TE | SCSCR_RE, .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_IRDA, .irqs = { 52, 52, 52, 52 }, + .ops = &sh770x_sci_port_ops, + .regshift = 1, }; static struct platform_device scif2_device = { diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7720.c b/arch/sh/kernel/cpu/sh3/setup-sh7720.c index 365b94a6fcb7..94920345c14d 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh7720.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh7720.c @@ -20,6 +20,7 @@ #include #include #include +#include static struct resource rtc_resources[] = { [0] = { @@ -55,6 +56,8 @@ static struct plat_sci_port scif0_platform_data = { .scbrr_algo_id = SCBRR_ALGO_4, .type = PORT_SCIF, .irqs = { 80, 80, 80, 80 }, + .ops = &sh7720_sci_port_ops, + .regtype = SCIx_SH7705_SCIF_REGTYPE, }; static struct platform_device scif0_device = { @@ -72,6 +75,8 @@ static struct plat_sci_port scif1_platform_data = { .scbrr_algo_id = SCBRR_ALGO_4, .type = PORT_SCIF, .irqs = { 81, 81, 81, 81 }, + .ops = &sh7720_sci_port_ops, + .regtype = SCIx_SH7705_SCIF_REGTYPE, }; static struct platform_device scif1_device = { diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7750.c b/arch/sh/kernel/cpu/sh4/setup-sh7750.c index 8ea26e791187..c10db5b96e59 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh7750.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh7750.c @@ -1,5 +1,5 @@ /* - * SH7750/SH7751 Setup + * SH7091/SH7750/SH7750S/SH7750R/SH7751/SH7751R Setup * * Copyright (C) 2006 Paul Mundt * Copyright (C) 2006 Jamie Lenehan @@ -44,6 +44,7 @@ static struct plat_sci_port sci_platform_data = { .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCI, .irqs = { 23, 23, 23, 0 }, + .regshift = 2, }; static struct platform_device sci_device = { diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7760.c b/arch/sh/kernel/cpu/sh4/setup-sh7760.c index 78bbf232e391..c0b4c774700e 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh7760.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh7760.c @@ -133,6 +133,7 @@ static struct plat_sci_port scif0_platform_data = { .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 52, 53, 55, 54 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif0_device = { @@ -150,6 +151,7 @@ static struct plat_sci_port scif1_platform_data = { .scscr = SCSCR_RE | SCSCR_TE | SCSCR_REIE, .scbrr_algo_id = SCBRR_ALGO_2, .irqs = { 72, 73, 75, 74 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif1_device = { @@ -167,6 +169,7 @@ static struct plat_sci_port scif2_platform_data = { .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 76, 77, 79, 78 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif2_device = { @@ -184,6 +187,7 @@ static struct plat_sci_port scif3_platform_data = { .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCI, .irqs = { 80, 81, 82, 0 }, + .regshift = 2, }; static struct platform_device scif3_device = { diff --git a/arch/sh/kernel/cpu/sh4a/Makefile b/arch/sh/kernel/cpu/sh4a/Makefile index cc122b1d3035..c57fb287011e 100644 --- a/arch/sh/kernel/cpu/sh4a/Makefile +++ b/arch/sh/kernel/cpu/sh4a/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_CPU_SUBTYPE_SH7780) += setup-sh7780.o obj-$(CONFIG_CPU_SUBTYPE_SH7785) += setup-sh7785.o obj-$(CONFIG_CPU_SUBTYPE_SH7786) += setup-sh7786.o intc-shx3.o obj-$(CONFIG_CPU_SUBTYPE_SH7343) += setup-sh7343.o -obj-$(CONFIG_CPU_SUBTYPE_SH7722) += setup-sh7722.o +obj-$(CONFIG_CPU_SUBTYPE_SH7722) += setup-sh7722.o serial-sh7722.o obj-$(CONFIG_CPU_SUBTYPE_SH7723) += setup-sh7723.o obj-$(CONFIG_CPU_SUBTYPE_SH7724) += setup-sh7724.o obj-$(CONFIG_CPU_SUBTYPE_SH7366) += setup-sh7366.o diff --git a/arch/sh/kernel/cpu/sh4a/serial-sh7722.c b/arch/sh/kernel/cpu/sh4a/serial-sh7722.c new file mode 100644 index 000000000000..59bc3a72702e --- /dev/null +++ b/arch/sh/kernel/cpu/sh4a/serial-sh7722.c @@ -0,0 +1,23 @@ +#include +#include +#include + +#define PSCR 0xA405011E + +static void sh7722_sci_init_pins(struct uart_port *port, unsigned int cflag) +{ + unsigned short data; + + if (port->mapbase == 0xffe00000) { + data = __raw_readw(PSCR); + data &= ~0x03cf; + if (!(cflag & CRTSCTS)) + data |= 0x0340; + + __raw_writew(data, PSCR); + } +} + +struct plat_sci_port_ops sh7722_sci_port_ops = { + .init_pins = sh7722_sci_init_pins, +}; diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c index 82616af64d62..87773869a2f3 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c @@ -20,6 +20,7 @@ static struct plat_sci_port scif0_platform_data = { .mapbase = 0xffe00000, + .port_reg = 0xa405013e, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE | SCSCR_REIE, .scbrr_algo_id = SCBRR_ALGO_2, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c index 5813d8023619..863249dbf05b 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c @@ -185,6 +185,8 @@ static struct plat_sci_port scif0_platform_data = { .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 80, 80, 80, 80 }, + .ops = &sh7722_sci_port_ops, + .regtype = SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE, }; static struct platform_device scif0_device = { @@ -202,6 +204,8 @@ static struct plat_sci_port scif1_platform_data = { .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 81, 81, 81, 81 }, + .ops = &sh7722_sci_port_ops, + .regtype = SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE, }; static struct platform_device scif1_device = { @@ -219,6 +223,8 @@ static struct plat_sci_port scif2_platform_data = { .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 82, 82, 82, 82 }, + .ops = &sh7722_sci_port_ops, + .regtype = SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE, }; static struct platform_device scif2_device = { diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c index 072382280f96..3c2810d8f72e 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c @@ -23,11 +23,13 @@ /* Serial */ static struct plat_sci_port scif0_platform_data = { .mapbase = 0xffe00000, + .port_reg = 0xa4050160, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE | SCSCR_REIE, .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 80, 80, 80, 80 }, + .regtype = SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE, }; static struct platform_device scif0_device = { @@ -40,11 +42,13 @@ static struct platform_device scif0_device = { static struct plat_sci_port scif1_platform_data = { .mapbase = 0xffe10000, + .port_reg = SCIx_NOT_SUPPORTED, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE | SCSCR_REIE, .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 81, 81, 81, 81 }, + .regtype = SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE, }; static struct platform_device scif1_device = { @@ -57,11 +61,13 @@ static struct platform_device scif1_device = { static struct plat_sci_port scif2_platform_data = { .mapbase = 0xffe20000, + .port_reg = SCIx_NOT_SUPPORTED, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE | SCSCR_REIE, .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 82, 82, 82, 82 }, + .regtype = SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE, }; static struct platform_device scif2_device = { @@ -75,6 +81,7 @@ static struct platform_device scif2_device = { static struct plat_sci_port scif3_platform_data = { .mapbase = 0xa4e30000, .flags = UPF_BOOT_AUTOCONF, + .port_reg = SCIx_NOT_SUPPORTED, .scscr = SCSCR_RE | SCSCR_TE | SCSCR_REIE, .scbrr_algo_id = SCBRR_ALGO_3, .type = PORT_SCIFA, @@ -91,6 +98,7 @@ static struct platform_device scif3_device = { static struct plat_sci_port scif4_platform_data = { .mapbase = 0xa4e40000, + .port_reg = SCIx_NOT_SUPPORTED, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE | SCSCR_REIE, .scbrr_algo_id = SCBRR_ALGO_3, @@ -108,6 +116,7 @@ static struct platform_device scif4_device = { static struct plat_sci_port scif5_platform_data = { .mapbase = 0xa4e50000, + .port_reg = SCIx_NOT_SUPPORTED, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE | SCSCR_REIE, .scbrr_algo_id = SCBRR_ALGO_3, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c index 0333fe9e3881..8c892887ebd7 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c @@ -256,11 +256,13 @@ static struct platform_device dma1_device = { /* Serial */ static struct plat_sci_port scif0_platform_data = { .mapbase = 0xffe00000, + .port_reg = SCIx_NOT_SUPPORTED, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE | SCSCR_REIE, .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 80, 80, 80, 80 }, + .regtype = SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE, }; static struct platform_device scif0_device = { @@ -273,11 +275,13 @@ static struct platform_device scif0_device = { static struct plat_sci_port scif1_platform_data = { .mapbase = 0xffe10000, + .port_reg = SCIx_NOT_SUPPORTED, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE | SCSCR_REIE, .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 81, 81, 81, 81 }, + .regtype = SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE, }; static struct platform_device scif1_device = { @@ -290,11 +294,13 @@ static struct platform_device scif1_device = { static struct plat_sci_port scif2_platform_data = { .mapbase = 0xffe20000, + .port_reg = SCIx_NOT_SUPPORTED, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE | SCSCR_REIE, .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 82, 82, 82, 82 }, + .regtype = SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE, }; static struct platform_device scif2_device = { @@ -307,6 +313,7 @@ static struct platform_device scif2_device = { static struct plat_sci_port scif3_platform_data = { .mapbase = 0xa4e30000, + .port_reg = SCIx_NOT_SUPPORTED, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE, .scbrr_algo_id = SCBRR_ALGO_3, @@ -324,6 +331,7 @@ static struct platform_device scif3_device = { static struct plat_sci_port scif4_platform_data = { .mapbase = 0xa4e40000, + .port_reg = SCIx_NOT_SUPPORTED, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE, .scbrr_algo_id = SCBRR_ALGO_3, @@ -341,6 +349,7 @@ static struct platform_device scif4_device = { static struct plat_sci_port scif5_platform_data = { .mapbase = 0xa4e50000, + .port_reg = SCIx_NOT_SUPPORTED, .flags = UPF_BOOT_AUTOCONF, .scscr = SCSCR_RE | SCSCR_TE, .scbrr_algo_id = SCBRR_ALGO_3, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7763.c b/arch/sh/kernel/cpu/sh4a/setup-sh7763.c index 593eca6509b5..00113515f233 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7763.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7763.c @@ -23,6 +23,7 @@ static struct plat_sci_port scif0_platform_data = { .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 40, 40, 40, 40 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif0_device = { @@ -40,6 +41,7 @@ static struct plat_sci_port scif1_platform_data = { .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 76, 76, 76, 76 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif1_device = { @@ -57,6 +59,7 @@ static struct plat_sci_port scif2_platform_data = { .scbrr_algo_id = SCBRR_ALGO_2, .type = PORT_SCIF, .irqs = { 104, 104, 104, 104 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif2_device = { diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c index 08add7fa6849..3d4d2075c19a 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c @@ -14,7 +14,6 @@ #include #include #include - #include static struct plat_sci_port scif0_platform_data = { @@ -24,6 +23,7 @@ static struct plat_sci_port scif0_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 40, 40, 40, 40 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif0_device = { @@ -41,6 +41,7 @@ static struct plat_sci_port scif1_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 76, 76, 76, 76 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif1_device = { diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c index 18d8fc136fb2..b29e6340414a 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c @@ -15,9 +15,7 @@ #include #include #include - #include - #include static struct plat_sci_port scif0_platform_data = { @@ -27,6 +25,7 @@ static struct plat_sci_port scif0_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 40, 40, 40, 40 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif0_device = { @@ -44,6 +43,7 @@ static struct plat_sci_port scif1_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 44, 44, 44, 44 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif1_device = { @@ -61,6 +61,7 @@ static struct plat_sci_port scif2_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 60, 60, 60, 60 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif2_device = { @@ -78,6 +79,7 @@ static struct plat_sci_port scif3_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 61, 61, 61, 61 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif3_device = { @@ -95,6 +97,7 @@ static struct plat_sci_port scif4_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 62, 62, 62, 62 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif4_device = { @@ -112,6 +115,7 @@ static struct plat_sci_port scif5_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 63, 63, 63, 63 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif5_device = { diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c index beba32beb6d9..dd5e709f9821 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c @@ -1,7 +1,7 @@ /* * SH7786 Setup * - * Copyright (C) 2009 - 2010 Renesas Solutions Corp. + * Copyright (C) 2009 - 2011 Renesas Solutions Corp. * Kuninori Morimoto * Paul Mundt * @@ -33,6 +33,7 @@ static struct plat_sci_port scif0_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 40, 41, 43, 42 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif0_device = { @@ -53,6 +54,7 @@ static struct plat_sci_port scif1_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 44, 44, 44, 44 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif1_device = { @@ -70,6 +72,7 @@ static struct plat_sci_port scif2_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 50, 50, 50, 50 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif2_device = { @@ -87,6 +90,7 @@ static struct plat_sci_port scif3_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 51, 51, 51, 51 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif3_device = { @@ -104,6 +108,7 @@ static struct plat_sci_port scif4_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 52, 52, 52, 52 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif4_device = { @@ -121,6 +126,7 @@ static struct plat_sci_port scif5_platform_data = { .scbrr_algo_id = SCBRR_ALGO_1, .type = PORT_SCIF, .irqs = { 53, 53, 53, 53 }, + .regtype = SCIx_SH4_SCIF_FIFODATA_REGTYPE, }; static struct platform_device scif5_device = { diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 3248ddaa889d..14e1bae50392 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -117,6 +117,255 @@ to_sci_port(struct uart_port *uart) return container_of(uart, struct sci_port, port); } +struct plat_sci_reg { + u8 offset, size; +}; + +/* Helper for invalidating specific entries of an inherited map. */ +#define sci_reg_invalid { .offset = 0, .size = 0 } + +static struct plat_sci_reg sci_regmap[SCIx_NR_REGTYPES][SCIx_NR_REGS] = { + [SCIx_PROBE_REGTYPE] = { + [0 ... SCIx_NR_REGS - 1] = sci_reg_invalid, + }, + + /* + * Common SCI definitions, dependent on the port's regshift + * value. + */ + [SCIx_SCI_REGTYPE] = { + [SCSMR] = { 0x00, 8 }, + [SCBRR] = { 0x01, 8 }, + [SCSCR] = { 0x02, 8 }, + [SCxTDR] = { 0x03, 8 }, + [SCxSR] = { 0x04, 8 }, + [SCxRDR] = { 0x05, 8 }, + [SCFCR] = sci_reg_invalid, + [SCFDR] = sci_reg_invalid, + [SCTFDR] = sci_reg_invalid, + [SCRFDR] = sci_reg_invalid, + [SCSPTR] = sci_reg_invalid, + [SCLSR] = sci_reg_invalid, + }, + + /* + * Common definitions for legacy IrDA ports, dependent on + * regshift value. + */ + [SCIx_IRDA_REGTYPE] = { + [SCSMR] = { 0x00, 8 }, + [SCBRR] = { 0x01, 8 }, + [SCSCR] = { 0x02, 8 }, + [SCxTDR] = { 0x03, 8 }, + [SCxSR] = { 0x04, 8 }, + [SCxRDR] = { 0x05, 8 }, + [SCFCR] = { 0x06, 8 }, + [SCFDR] = { 0x07, 16 }, + [SCTFDR] = sci_reg_invalid, + [SCRFDR] = sci_reg_invalid, + [SCSPTR] = sci_reg_invalid, + [SCLSR] = sci_reg_invalid, + }, + + /* + * Common SCIFA definitions. + */ + [SCIx_SCIFA_REGTYPE] = { + [SCSMR] = { 0x00, 16 }, + [SCBRR] = { 0x04, 8 }, + [SCSCR] = { 0x08, 16 }, + [SCxTDR] = { 0x20, 8 }, + [SCxSR] = { 0x14, 16 }, + [SCxRDR] = { 0x24, 8 }, + [SCFCR] = { 0x18, 16 }, + [SCFDR] = { 0x1c, 16 }, + [SCTFDR] = sci_reg_invalid, + [SCRFDR] = sci_reg_invalid, + [SCSPTR] = sci_reg_invalid, + [SCLSR] = sci_reg_invalid, + }, + + /* + * Common SCIFB definitions. + */ + [SCIx_SCIFB_REGTYPE] = { + [SCSMR] = { 0x00, 16 }, + [SCBRR] = { 0x04, 8 }, + [SCSCR] = { 0x08, 16 }, + [SCxTDR] = { 0x40, 8 }, + [SCxSR] = { 0x14, 16 }, + [SCxRDR] = { 0x60, 8 }, + [SCFCR] = { 0x18, 16 }, + [SCFDR] = { 0x1c, 16 }, + [SCTFDR] = sci_reg_invalid, + [SCRFDR] = sci_reg_invalid, + [SCSPTR] = sci_reg_invalid, + [SCLSR] = sci_reg_invalid, + }, + + /* + * Common SH-3 SCIF definitions. + */ + [SCIx_SH3_SCIF_REGTYPE] = { + [SCSMR] = { 0x00, 8 }, + [SCBRR] = { 0x02, 8 }, + [SCSCR] = { 0x04, 8 }, + [SCxTDR] = { 0x06, 8 }, + [SCxSR] = { 0x08, 16 }, + [SCxRDR] = { 0x0a, 8 }, + [SCFCR] = { 0x0c, 8 }, + [SCFDR] = { 0x0e, 16 }, + [SCTFDR] = sci_reg_invalid, + [SCRFDR] = sci_reg_invalid, + [SCSPTR] = sci_reg_invalid, + [SCLSR] = sci_reg_invalid, + }, + + /* + * Common SH-4(A) SCIF(B) definitions. + */ + [SCIx_SH4_SCIF_REGTYPE] = { + [SCSMR] = { 0x00, 16 }, + [SCBRR] = { 0x04, 8 }, + [SCSCR] = { 0x08, 16 }, + [SCxTDR] = { 0x0c, 8 }, + [SCxSR] = { 0x10, 16 }, + [SCxRDR] = { 0x14, 8 }, + [SCFCR] = { 0x18, 16 }, + [SCFDR] = { 0x1c, 16 }, + [SCTFDR] = sci_reg_invalid, + [SCRFDR] = sci_reg_invalid, + [SCSPTR] = { 0x20, 16 }, + [SCLSR] = { 0x24, 16 }, + }, + + /* + * Common SH-4(A) SCIF(B) definitions for ports without an SCSPTR + * register. + */ + [SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE] = { + [SCSMR] = { 0x00, 16 }, + [SCBRR] = { 0x04, 8 }, + [SCSCR] = { 0x08, 16 }, + [SCxTDR] = { 0x0c, 8 }, + [SCxSR] = { 0x10, 16 }, + [SCxRDR] = { 0x14, 8 }, + [SCFCR] = { 0x18, 16 }, + [SCFDR] = { 0x1c, 16 }, + [SCTFDR] = sci_reg_invalid, + [SCRFDR] = sci_reg_invalid, + [SCSPTR] = sci_reg_invalid, + [SCLSR] = { 0x24, 16 }, + }, + + /* + * Common SH-4(A) SCIF(B) definitions for ports with FIFO data + * count registers. + */ + [SCIx_SH4_SCIF_FIFODATA_REGTYPE] = { + [SCSMR] = { 0x00, 16 }, + [SCBRR] = { 0x04, 8 }, + [SCSCR] = { 0x08, 16 }, + [SCxTDR] = { 0x0c, 8 }, + [SCxSR] = { 0x10, 16 }, + [SCxRDR] = { 0x14, 8 }, + [SCFCR] = { 0x18, 16 }, + [SCFDR] = { 0x1c, 16 }, + [SCTFDR] = { 0x1c, 16 }, /* aliased to SCFDR */ + [SCRFDR] = { 0x20, 16 }, + [SCSPTR] = { 0x24, 16 }, + [SCLSR] = { 0x28, 16 }, + }, + + /* + * SH7705-style SCIF(B) ports, lacking both SCSPTR and SCLSR + * registers. + */ + [SCIx_SH7705_SCIF_REGTYPE] = { + [SCSMR] = { 0x00, 16 }, + [SCBRR] = { 0x04, 8 }, + [SCSCR] = { 0x08, 16 }, + [SCxTDR] = { 0x20, 8 }, + [SCxSR] = { 0x14, 16 }, + [SCxRDR] = { 0x24, 8 }, + [SCFCR] = { 0x18, 16 }, + [SCFDR] = { 0x1c, 16 }, + [SCTFDR] = sci_reg_invalid, + [SCRFDR] = sci_reg_invalid, + [SCSPTR] = sci_reg_invalid, + [SCLSR] = sci_reg_invalid, + }, +}; + +/* + * The "offset" here is rather misleading, in that it refers to an enum + * value relative to the port mapping rather than the fixed offset + * itself, which needs to be manually retrieved from the platform's + * register map for the given port. + */ +static unsigned int sci_serial_in(struct uart_port *p, int offset) +{ + struct sci_port *s = to_sci_port(p); + struct plat_sci_reg *reg = sci_regmap[s->cfg->regtype] + offset; + + if (reg->size == 8) + return ioread8(p->membase + (reg->offset << p->regshift)); + else if (reg->size == 16) + return ioread16(p->membase + (reg->offset << p->regshift)); + else + WARN(1, "Invalid register access\n"); + + return 0; +} + +static void sci_serial_out(struct uart_port *p, int offset, int value) +{ + struct sci_port *s = to_sci_port(p); + struct plat_sci_reg *reg = sci_regmap[s->cfg->regtype] + offset; + + if (reg->size == 8) + iowrite8(value, p->membase + (reg->offset << p->regshift)); + else if (reg->size == 16) + iowrite16(value, p->membase + (reg->offset << p->regshift)); + else + WARN(1, "Invalid register access\n"); +} + +#define sci_in(up, offset) (up->serial_in(up, offset)) +#define sci_out(up, offset, value) (up->serial_out(up, offset, value)) + +static int sci_probe_regmap(struct plat_sci_port *cfg) +{ + switch (cfg->type) { + case PORT_SCI: + cfg->regtype = SCIx_SCI_REGTYPE; + break; + case PORT_IRDA: + cfg->regtype = SCIx_IRDA_REGTYPE; + break; + case PORT_SCIFA: + cfg->regtype = SCIx_SCIFA_REGTYPE; + break; + case PORT_SCIFB: + cfg->regtype = SCIx_SCIFB_REGTYPE; + break; + case PORT_SCIF: + /* + * The SH-4 is a bit of a misnomer here, although that's + * where this particular port layout originated. This + * configuration (or some slight variation thereof) + * remains the dominant model for all SCIFs. + */ + cfg->regtype = SCIx_SH4_SCIF_REGTYPE; + break; + default: + printk(KERN_ERR "Can't probe register map for given port\n"); + return -EINVAL; + } + + return 0; +} + #if defined(CONFIG_CONSOLE_POLL) || defined(CONFIG_SERIAL_SH_SCI_CONSOLE) #ifdef CONFIG_CONSOLE_POLL @@ -160,103 +409,29 @@ static void sci_poll_put_char(struct uart_port *port, unsigned char c) } #endif /* CONFIG_CONSOLE_POLL || CONFIG_SERIAL_SH_SCI_CONSOLE */ -#if defined(CONFIG_CPU_SUBTYPE_SH7710) || defined(CONFIG_CPU_SUBTYPE_SH7712) -static inline void sci_init_pins(struct uart_port *port, unsigned int cflag) -{ - if (port->mapbase == 0xA4400000) { - __raw_writew(__raw_readw(PACR) & 0xffc0, PACR); - __raw_writew(__raw_readw(PBCR) & 0x0fff, PBCR); - } else if (port->mapbase == 0xA4410000) - __raw_writew(__raw_readw(PBCR) & 0xf003, PBCR); -} -#elif defined(CONFIG_CPU_SUBTYPE_SH7720) || defined(CONFIG_CPU_SUBTYPE_SH7721) -static inline void sci_init_pins(struct uart_port *port, unsigned int cflag) -{ - unsigned short data; - - if (cflag & CRTSCTS) { - /* enable RTS/CTS */ - if (port->mapbase == 0xa4430000) { /* SCIF0 */ - /* Clear PTCR bit 9-2; enable all scif pins but sck */ - data = __raw_readw(PORT_PTCR); - __raw_writew((data & 0xfc03), PORT_PTCR); - } else if (port->mapbase == 0xa4438000) { /* SCIF1 */ - /* Clear PVCR bit 9-2 */ - data = __raw_readw(PORT_PVCR); - __raw_writew((data & 0xfc03), PORT_PVCR); - } - } else { - if (port->mapbase == 0xa4430000) { /* SCIF0 */ - /* Clear PTCR bit 5-2; enable only tx and rx */ - data = __raw_readw(PORT_PTCR); - __raw_writew((data & 0xffc3), PORT_PTCR); - } else if (port->mapbase == 0xa4438000) { /* SCIF1 */ - /* Clear PVCR bit 5-2 */ - data = __raw_readw(PORT_PVCR); - __raw_writew((data & 0xffc3), PORT_PVCR); - } - } -} -#elif defined(CONFIG_CPU_SH3) -/* For SH7705, SH7706, SH7707, SH7709, SH7709A, SH7729 */ -static inline void sci_init_pins(struct uart_port *port, unsigned int cflag) +static void sci_init_pins(struct uart_port *port, unsigned int cflag) { - unsigned short data; - - /* We need to set SCPCR to enable RTS/CTS */ - data = __raw_readw(SCPCR); - /* Clear out SCP7MD1,0, SCP6MD1,0, SCP4MD1,0*/ - __raw_writew(data & 0x0fcf, SCPCR); - - if (!(cflag & CRTSCTS)) { - /* We need to set SCPCR to enable RTS/CTS */ - data = __raw_readw(SCPCR); - /* Clear out SCP7MD1,0, SCP4MD1,0, - Set SCP6MD1,0 = {01} (output) */ - __raw_writew((data & 0x0fcf) | 0x1000, SCPCR); + struct sci_port *s = to_sci_port(port); + struct plat_sci_reg *reg = sci_regmap[s->cfg->regtype] + SCSPTR; - data = __raw_readb(SCPDR); - /* Set /RTS2 (bit6) = 0 */ - __raw_writeb(data & 0xbf, SCPDR); + /* + * Use port-specific handler if provided. + */ + if (s->cfg->ops && s->cfg->ops->init_pins) { + s->cfg->ops->init_pins(port, cflag); + return; } -} -#elif defined(CONFIG_CPU_SUBTYPE_SH7722) -static inline void sci_init_pins(struct uart_port *port, unsigned int cflag) -{ - unsigned short data; - if (port->mapbase == 0xffe00000) { - data = __raw_readw(PSCR); - data &= ~0x03cf; - if (!(cflag & CRTSCTS)) - data |= 0x0340; + /* + * For the generic path SCSPTR is necessary. Bail out if that's + * unavailable, too. + */ + if (!reg->size) + return; - __raw_writew(data, PSCR); - } -} -#elif defined(CONFIG_CPU_SUBTYPE_SH7757) || \ - defined(CONFIG_CPU_SUBTYPE_SH7763) || \ - defined(CONFIG_CPU_SUBTYPE_SH7780) || \ - defined(CONFIG_CPU_SUBTYPE_SH7785) || \ - defined(CONFIG_CPU_SUBTYPE_SH7786) || \ - defined(CONFIG_CPU_SUBTYPE_SHX3) -static inline void sci_init_pins(struct uart_port *port, unsigned int cflag) -{ - if (!(cflag & CRTSCTS)) - __raw_writew(0x0080, SCSPTR0); /* Set RTS = 1 */ -} -#elif defined(CONFIG_CPU_SH4) && !defined(CONFIG_CPU_SH4A) -static inline void sci_init_pins(struct uart_port *port, unsigned int cflag) -{ if (!(cflag & CRTSCTS)) - __raw_writew(0x0080, SCSPTR2); /* Set RTS = 1 */ + sci_out(port, SCSPTR, 0x0080); /* Set RTS = 1 */ } -#else -static inline void sci_init_pins(struct uart_port *port, unsigned int cflag) -{ - /* Nothing to do */ -} -#endif #if defined(CONFIG_CPU_SUBTYPE_SH7760) || \ defined(CONFIG_CPU_SUBTYPE_SH7780) || \ @@ -1752,6 +1927,9 @@ static int __devinit sci_init_single(struct platform_device *dev, break; } + if (p->regtype == SCIx_PROBE_REGTYPE) + BUG_ON(sci_probe_regmap(p) != 0); + if (dev) { sci_port->iclk = clk_get(&dev->dev, "sci_ick"); if (IS_ERR(sci_port->iclk)) { @@ -1812,9 +1990,10 @@ static int __devinit sci_init_single(struct platform_device *dev, port->mapbase = p->mapbase; port->type = p->type; port->flags = p->flags; + port->regshift = p->regshift; /* - * The UART port needs an IRQ value, so we peg this to the TX IRQ + * The UART port needs an IRQ value, so we peg this to the RX IRQ * for the multi-IRQ ports, which is where we are primarily * concerned with the shutdown path synchronization. * @@ -1822,6 +2001,9 @@ static int __devinit sci_init_single(struct platform_device *dev, */ port->irq = p->irqs[SCIx_RXI_IRQ]; + port->serial_in = sci_serial_in; + port->serial_out = sci_serial_out; + if (p->dma_dev) dev_dbg(port->dev, "DMA device %p, tx %d, rx %d\n", p->dma_dev, p->dma_slave_tx, p->dma_slave_rx); diff --git a/drivers/tty/serial/sh-sci.h b/drivers/tty/serial/sh-sci.h index 5834f33d20ff..26de640a9d01 100644 --- a/drivers/tty/serial/sh-sci.h +++ b/drivers/tty/serial/sh-sci.h @@ -2,69 +2,6 @@ #include #include -#if defined(CONFIG_CPU_SUBTYPE_SH7705) || \ - defined(CONFIG_CPU_SUBTYPE_SH7706) || \ - defined(CONFIG_CPU_SUBTYPE_SH7707) || \ - defined(CONFIG_CPU_SUBTYPE_SH7708) || \ - defined(CONFIG_CPU_SUBTYPE_SH7709) -# define SCPCR 0xA4000116 /* 16 bit SCI and SCIF */ -# define SCPDR 0xA4000136 /* 8 bit SCI and SCIF */ -#elif defined(CONFIG_CPU_SUBTYPE_SH7720) || \ - defined(CONFIG_CPU_SUBTYPE_SH7721) || \ - defined(CONFIG_ARCH_SH73A0) || \ - defined(CONFIG_ARCH_SH7367) || \ - defined(CONFIG_ARCH_SH7377) || \ - defined(CONFIG_ARCH_SH7372) -# define PORT_PTCR 0xA405011EUL -# define PORT_PVCR 0xA4050122UL -#elif defined(CONFIG_CPU_SUBTYPE_SH7750) || \ - defined(CONFIG_CPU_SUBTYPE_SH7750R) || \ - defined(CONFIG_CPU_SUBTYPE_SH7750S) || \ - defined(CONFIG_CPU_SUBTYPE_SH7091) || \ - defined(CONFIG_CPU_SUBTYPE_SH7751) || \ - defined(CONFIG_CPU_SUBTYPE_SH7751R) || \ - defined(CONFIG_CPU_SUBTYPE_SH4_202) -# define SCSPTR2 0xFFE80020 /* 16 bit SCIF */ -#elif defined(CONFIG_CPU_SUBTYPE_SH7760) -# define SCSPTR0 0xfe600024 /* 16 bit SCIF */ -# define SCSPTR2 0xfe620024 /* 16 bit SCIF */ -#elif defined(CONFIG_CPU_SUBTYPE_SH7710) || defined(CONFIG_CPU_SUBTYPE_SH7712) -# define SCSPTR0 0xA4400000 /* 16 bit SCIF */ -# define PACR 0xa4050100 -# define PBCR 0xa4050102 -#elif defined(CONFIG_CPU_SUBTYPE_SH7343) -# define SCSPTR0 0xffe00010 /* 16 bit SCIF */ -#elif defined(CONFIG_CPU_SUBTYPE_SH7722) -# define PWDR 0xA4050166 -# define PSCR 0xA405011E -#elif defined(CONFIG_CPU_SUBTYPE_SH7366) -# define SCPDR0 0xA405013E /* 16 bit SCIF0 PSDR */ -# define SCSPTR0 SCPDR0 -#elif defined(CONFIG_CPU_SUBTYPE_SH7723) -# define SCSPTR0 0xa4050160 -#elif defined(CONFIG_CPU_SUBTYPE_SH7757) -# define SCSPTR0 0xfe4b0020 -#elif defined(CONFIG_CPU_SUBTYPE_SH7763) || \ - defined(CONFIG_CPU_SUBTYPE_SH7780) -# define SCSPTR0 0xffe00024 /* 16 bit SCIF */ -#elif defined(CONFIG_CPU_SUBTYPE_SH7770) -# define SCSPTR0 0xff923020 /* 16 bit SCIF */ -#elif defined(CONFIG_CPU_SUBTYPE_SH7785) || \ - defined(CONFIG_CPU_SUBTYPE_SH7786) -# define SCSPTR0 0xffea0024 /* 16 bit SCIF */ -#elif defined(CONFIG_CPU_SUBTYPE_SH7201) || \ - defined(CONFIG_CPU_SUBTYPE_SH7203) || \ - defined(CONFIG_CPU_SUBTYPE_SH7206) || \ - defined(CONFIG_CPU_SUBTYPE_SH7263) -# define SCSPTR0 0xfffe8020 /* 16 bit SCIF */ -#elif defined(CONFIG_CPU_SUBTYPE_SH7619) -# define SCSPTR0 0xf8400020 /* 16 bit SCIF */ -#elif defined(CONFIG_CPU_SUBTYPE_SHX3) -# define SCSPTR0 0xffc30020 /* 16 bit SCIF */ -#else -# error CPU subtype not defined -#endif - #if defined(CONFIG_CPU_SUBTYPE_SH7705) || \ defined(CONFIG_CPU_SUBTYPE_SH7720) || \ defined(CONFIG_CPU_SUBTYPE_SH7721) || \ @@ -119,162 +56,3 @@ #define SCI_MAJOR 204 #define SCI_MINOR_START 8 - -#define SCI_IN(size, offset) \ - ioread##size(port->membase + (offset)) - -#define SCI_OUT(size, offset, value) \ - iowrite##size(value, port->membase + (offset)) - -#define CPU_SCIx_FNS(name, sci_offset, sci_size, scif_offset, scif_size)\ - static inline unsigned int sci_##name##_in(struct uart_port *port) \ - { \ - if (port->type == PORT_SCIF || port->type == PORT_SCIFB) { \ - return SCI_IN(scif_size, scif_offset); \ - } else { /* PORT_SCI or PORT_SCIFA */ \ - return SCI_IN(sci_size, sci_offset); \ - } \ - } \ - static inline void sci_##name##_out(struct uart_port *port, unsigned int value) \ - { \ - if (port->type == PORT_SCIF || port->type == PORT_SCIFB) { \ - SCI_OUT(scif_size, scif_offset, value); \ - } else { /* PORT_SCI or PORT_SCIFA */ \ - SCI_OUT(sci_size, sci_offset, value); \ - } \ - } - -#define CPU_SCIF_FNS(name, scif_offset, scif_size) \ - static inline unsigned int sci_##name##_in(struct uart_port *port) \ - { \ - return SCI_IN(scif_size, scif_offset); \ - } \ - static inline void sci_##name##_out(struct uart_port *port, unsigned int value) \ - { \ - SCI_OUT(scif_size, scif_offset, value); \ - } - -#if defined(CONFIG_CPU_SH3) || \ - defined(CONFIG_ARCH_SH73A0) || \ - defined(CONFIG_ARCH_SH7367) || \ - defined(CONFIG_ARCH_SH7377) || \ - defined(CONFIG_ARCH_SH7372) -#if defined(CONFIG_CPU_SUBTYPE_SH7710) || defined(CONFIG_CPU_SUBTYPE_SH7712) -#define SCIx_FNS(name, sh3_sci_offset, sh3_sci_size, sh4_sci_offset, sh4_sci_size, \ - sh3_scif_offset, sh3_scif_size, sh4_scif_offset, sh4_scif_size) \ - CPU_SCIx_FNS(name, sh4_sci_offset, sh4_sci_size, sh4_scif_offset, sh4_scif_size) -#define SCIF_FNS(name, sh3_scif_offset, sh3_scif_size, sh4_scif_offset, sh4_scif_size) \ - CPU_SCIF_FNS(name, sh4_scif_offset, sh4_scif_size) -#elif defined(CONFIG_CPU_SUBTYPE_SH7705) || \ - defined(CONFIG_CPU_SUBTYPE_SH7720) || \ - defined(CONFIG_CPU_SUBTYPE_SH7721) || \ - defined(CONFIG_ARCH_SH7367) -#define SCIF_FNS(name, scif_offset, scif_size) \ - CPU_SCIF_FNS(name, scif_offset, scif_size) -#elif defined(CONFIG_ARCH_SH7377) || \ - defined(CONFIG_ARCH_SH7372) || \ - defined(CONFIG_ARCH_SH73A0) -#define SCIx_FNS(name, sh4_scifa_offset, sh4_scifa_size, sh4_scifb_offset, sh4_scifb_size) \ - CPU_SCIx_FNS(name, sh4_scifa_offset, sh4_scifa_size, sh4_scifb_offset, sh4_scifb_size) -#define SCIF_FNS(name, scif_offset, scif_size) \ - CPU_SCIF_FNS(name, scif_offset, scif_size) -#else -#define SCIx_FNS(name, sh3_sci_offset, sh3_sci_size, sh4_sci_offset, sh4_sci_size, \ - sh3_scif_offset, sh3_scif_size, sh4_scif_offset, sh4_scif_size) \ - CPU_SCIx_FNS(name, sh3_sci_offset, sh3_sci_size, sh3_scif_offset, sh3_scif_size) -#define SCIF_FNS(name, sh3_scif_offset, sh3_scif_size, sh4_scif_offset, sh4_scif_size) \ - CPU_SCIF_FNS(name, sh3_scif_offset, sh3_scif_size) -#endif -#elif defined(CONFIG_CPU_SUBTYPE_SH7723) ||\ - defined(CONFIG_CPU_SUBTYPE_SH7724) - #define SCIx_FNS(name, sh4_scifa_offset, sh4_scifa_size, sh4_scif_offset, sh4_scif_size) \ - CPU_SCIx_FNS(name, sh4_scifa_offset, sh4_scifa_size, sh4_scif_offset, sh4_scif_size) - #define SCIF_FNS(name, sh4_scif_offset, sh4_scif_size) \ - CPU_SCIF_FNS(name, sh4_scif_offset, sh4_scif_size) -#else -#define SCIx_FNS(name, sh3_sci_offset, sh3_sci_size, sh4_sci_offset, sh4_sci_size, \ - sh3_scif_offset, sh3_scif_size, sh4_scif_offset, sh4_scif_size) \ - CPU_SCIx_FNS(name, sh4_sci_offset, sh4_sci_size, sh4_scif_offset, sh4_scif_size) -#define SCIF_FNS(name, sh3_scif_offset, sh3_scif_size, sh4_scif_offset, sh4_scif_size) \ - CPU_SCIF_FNS(name, sh4_scif_offset, sh4_scif_size) -#endif - -#if defined(CONFIG_CPU_SUBTYPE_SH7705) || \ - defined(CONFIG_CPU_SUBTYPE_SH7720) || \ - defined(CONFIG_CPU_SUBTYPE_SH7721) || \ - defined(CONFIG_ARCH_SH7367) - -SCIF_FNS(SCSMR, 0x00, 16) -SCIF_FNS(SCBRR, 0x04, 8) -SCIF_FNS(SCSCR, 0x08, 16) -SCIF_FNS(SCxSR, 0x14, 16) -SCIF_FNS(SCFCR, 0x18, 16) -SCIF_FNS(SCFDR, 0x1c, 16) -SCIF_FNS(SCxTDR, 0x20, 8) -SCIF_FNS(SCxRDR, 0x24, 8) -SCIF_FNS(SCLSR, 0x00, 0) -#elif defined(CONFIG_ARCH_SH7377) || \ - defined(CONFIG_ARCH_SH7372) || \ - defined(CONFIG_ARCH_SH73A0) -SCIF_FNS(SCSMR, 0x00, 16) -SCIF_FNS(SCBRR, 0x04, 8) -SCIF_FNS(SCSCR, 0x08, 16) -SCIF_FNS(SCTDSR, 0x0c, 16) -SCIF_FNS(SCFER, 0x10, 16) -SCIF_FNS(SCxSR, 0x14, 16) -SCIF_FNS(SCFCR, 0x18, 16) -SCIF_FNS(SCFDR, 0x1c, 16) -SCIF_FNS(SCTFDR, 0x38, 16) -SCIF_FNS(SCRFDR, 0x3c, 16) -SCIx_FNS(SCxTDR, 0x20, 8, 0x40, 8) -SCIx_FNS(SCxRDR, 0x24, 8, 0x60, 8) -SCIF_FNS(SCLSR, 0x00, 0) -#elif defined(CONFIG_CPU_SUBTYPE_SH7723) ||\ - defined(CONFIG_CPU_SUBTYPE_SH7724) -SCIx_FNS(SCSMR, 0x00, 16, 0x00, 16) -SCIx_FNS(SCBRR, 0x04, 8, 0x04, 8) -SCIx_FNS(SCSCR, 0x08, 16, 0x08, 16) -SCIx_FNS(SCxTDR, 0x20, 8, 0x0c, 8) -SCIx_FNS(SCxSR, 0x14, 16, 0x10, 16) -SCIx_FNS(SCxRDR, 0x24, 8, 0x14, 8) -SCIx_FNS(SCSPTR, 0, 0, 0, 0) -SCIF_FNS(SCFCR, 0x18, 16) -SCIF_FNS(SCFDR, 0x1c, 16) -SCIF_FNS(SCLSR, 0x24, 16) -#else -/* reg SCI/SH3 SCI/SH4 SCIF/SH3 SCIF/SH4 */ -/* name off sz off sz off sz off sz */ -SCIx_FNS(SCSMR, 0x00, 8, 0x00, 8, 0x00, 8, 0x00, 16) -SCIx_FNS(SCBRR, 0x02, 8, 0x04, 8, 0x02, 8, 0x04, 8) -SCIx_FNS(SCSCR, 0x04, 8, 0x08, 8, 0x04, 8, 0x08, 16) -SCIx_FNS(SCxTDR, 0x06, 8, 0x0c, 8, 0x06, 8, 0x0C, 8) -SCIx_FNS(SCxSR, 0x08, 8, 0x10, 8, 0x08, 16, 0x10, 16) -SCIx_FNS(SCxRDR, 0x0a, 8, 0x14, 8, 0x0A, 8, 0x14, 8) -SCIF_FNS(SCFCR, 0x0c, 8, 0x18, 16) -#if defined(CONFIG_CPU_SUBTYPE_SH7760) || \ - defined(CONFIG_CPU_SUBTYPE_SH7780) || \ - defined(CONFIG_CPU_SUBTYPE_SH7785) || \ - defined(CONFIG_CPU_SUBTYPE_SH7786) -SCIF_FNS(SCFDR, 0x0e, 16, 0x1C, 16) -SCIF_FNS(SCTFDR, 0x0e, 16, 0x1C, 16) -SCIF_FNS(SCRFDR, 0x0e, 16, 0x20, 16) -SCIF_FNS(SCSPTR, 0, 0, 0x24, 16) -SCIF_FNS(SCLSR, 0, 0, 0x28, 16) -#elif defined(CONFIG_CPU_SUBTYPE_SH7763) -SCIF_FNS(SCFDR, 0, 0, 0x1C, 16) -SCIF_FNS(SCTFDR, 0x0e, 16, 0x1C, 16) -SCIF_FNS(SCRFDR, 0x0e, 16, 0x20, 16) -SCIF_FNS(SCSPTR, 0, 0, 0x24, 16) -SCIF_FNS(SCLSR, 0, 0, 0x28, 16) -#else -SCIF_FNS(SCFDR, 0x0e, 16, 0x1C, 16) -#if defined(CONFIG_CPU_SUBTYPE_SH7722) -SCIF_FNS(SCSPTR, 0, 0, 0, 0) -#else -SCIF_FNS(SCSPTR, 0, 0, 0x20, 16) -#endif -SCIF_FNS(SCLSR, 0, 0, 0x24, 16) -#endif -#endif -#define sci_in(port, reg) sci_##reg##_in(port) -#define sci_out(port, reg, value) sci_##reg##_out(port, value) diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index ecefec7c0b67..4ca130a90ea5 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -58,6 +58,22 @@ enum { SCIx_NR_IRQS, }; +enum { + SCIx_PROBE_REGTYPE, + + SCIx_SCI_REGTYPE, + SCIx_IRDA_REGTYPE, + SCIx_SCIFA_REGTYPE, + SCIx_SCIFB_REGTYPE, + SCIx_SH3_SCIF_REGTYPE, + SCIx_SH4_SCIF_REGTYPE, + SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE, + SCIx_SH4_SCIF_FIFODATA_REGTYPE, + SCIx_SH7705_SCIF_REGTYPE, + + SCIx_NR_REGTYPES, +}; + #define SCIx_IRQ_MUXED(irq) \ { \ [SCIx_ERI_IRQ] = (irq), \ @@ -66,8 +82,24 @@ enum { [SCIx_BRI_IRQ] = (irq), \ } +/* + * SCI register subset common for all port types. + * Not all registers will exist on all parts. + */ +enum { + SCSMR, SCBRR, SCSCR, SCxSR, + SCFCR, SCFDR, SCxTDR, SCxRDR, + SCLSR, SCTFDR, SCRFDR, SCSPTR, + + SCIx_NR_REGS, +}; + struct device; +struct plat_sci_port_ops { + void (*init_pins)(struct uart_port *, unsigned int cflag); +}; + /* * Platform device specific platform_data struct */ @@ -87,6 +119,10 @@ struct plat_sci_port { unsigned int error_mask; int port_reg; + unsigned char regshift; + unsigned char regtype; + + struct plat_sci_port_ops *ops; struct device *dma_dev; -- cgit v1.2.3 From 5899a723b336da241b492583d7e55f1055f8f3b3 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Fri, 17 Jun 2011 08:20:40 +0000 Subject: dmaengine: shdma: add chcr_write/read function CHCR register position is not same in all DMAC. This patch adds new "chcr_offset" to decide it. Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- drivers/dma/shdma.c | 35 +++++++++++++++++++++++++++-------- drivers/dma/shdma.h | 1 + include/linux/sh_dma.h | 1 + 3 files changed, 29 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c index 41a21b322960..40900c1cee9a 100644 --- a/drivers/dma/shdma.c +++ b/drivers/dma/shdma.c @@ -78,6 +78,20 @@ static void dmaor_write(struct sh_dmae_device *shdev, u16 data) __raw_writew(data, shdev->chan_reg + DMAOR / sizeof(u32)); } +static void chcr_write(struct sh_dmae_chan *sh_dc, u32 data) +{ + struct sh_dmae_device *shdev = to_sh_dev(sh_dc); + + __raw_writel(data, sh_dc->base + shdev->chcr_offset / sizeof(u32)); +} + +static u32 chcr_read(struct sh_dmae_chan *sh_dc) +{ + struct sh_dmae_device *shdev = to_sh_dev(sh_dc); + + return __raw_readl(sh_dc->base + shdev->chcr_offset / sizeof(u32)); +} + /* * Reset DMA controller * @@ -120,7 +134,7 @@ static int sh_dmae_rst(struct sh_dmae_device *shdev) static bool dmae_is_busy(struct sh_dmae_chan *sh_chan) { - u32 chcr = sh_dmae_readl(sh_chan, CHCR); + u32 chcr = chcr_read(sh_chan); if ((chcr & (CHCR_DE | CHCR_TE)) == CHCR_DE) return true; /* working */ @@ -167,18 +181,18 @@ static void dmae_set_reg(struct sh_dmae_chan *sh_chan, struct sh_dmae_regs *hw) static void dmae_start(struct sh_dmae_chan *sh_chan) { - u32 chcr = sh_dmae_readl(sh_chan, CHCR); + u32 chcr = chcr_read(sh_chan); chcr |= CHCR_DE | CHCR_IE; - sh_dmae_writel(sh_chan, chcr & ~CHCR_TE, CHCR); + chcr_write(sh_chan, chcr & ~CHCR_TE); } static void dmae_halt(struct sh_dmae_chan *sh_chan) { - u32 chcr = sh_dmae_readl(sh_chan, CHCR); + u32 chcr = chcr_read(sh_chan); chcr &= ~(CHCR_DE | CHCR_TE | CHCR_IE); - sh_dmae_writel(sh_chan, chcr, CHCR); + chcr_write(sh_chan, chcr); } static void dmae_init(struct sh_dmae_chan *sh_chan) @@ -190,7 +204,7 @@ static void dmae_init(struct sh_dmae_chan *sh_chan) u32 chcr = DM_INC | SM_INC | 0x400 | log2size_to_chcr(sh_chan, LOG2_DEFAULT_XFER_SIZE); sh_chan->xmit_shift = calc_xmit_shift(sh_chan, chcr); - sh_dmae_writel(sh_chan, chcr, CHCR); + chcr_write(sh_chan, chcr); } static int dmae_set_chcr(struct sh_dmae_chan *sh_chan, u32 val) @@ -200,7 +214,7 @@ static int dmae_set_chcr(struct sh_dmae_chan *sh_chan, u32 val) return -EBUSY; sh_chan->xmit_shift = calc_xmit_shift(sh_chan, val); - sh_dmae_writel(sh_chan, val, CHCR); + chcr_write(sh_chan, val); return 0; } @@ -840,7 +854,7 @@ static irqreturn_t sh_dmae_interrupt(int irq, void *data) spin_lock(&sh_chan->desc_lock); - chcr = sh_dmae_readl(sh_chan, CHCR); + chcr = chcr_read(sh_chan); if (chcr & CHCR_TE) { /* DMA stop */ @@ -1138,6 +1152,11 @@ static int __init sh_dmae_probe(struct platform_device *pdev) /* platform data */ shdev->pdata = pdata; + if (pdata->chcr_offset) + shdev->chcr_offset = pdata->chcr_offset; + else + shdev->chcr_offset = CHCR; + platform_set_drvdata(pdev, shdev); pm_runtime_enable(&pdev->dev); diff --git a/drivers/dma/shdma.h b/drivers/dma/shdma.h index 6c73b654a5c3..6f064cad6c0f 100644 --- a/drivers/dma/shdma.h +++ b/drivers/dma/shdma.h @@ -47,6 +47,7 @@ struct sh_dmae_device { struct list_head node; u32 __iomem *chan_reg; u16 __iomem *dmars; + unsigned int chcr_offset; }; #define to_sh_chan(chan) container_of(chan, struct sh_dmae_chan, common) diff --git a/include/linux/sh_dma.h b/include/linux/sh_dma.h index b08cd4efa15c..41fe4c2d6481 100644 --- a/include/linux/sh_dma.h +++ b/include/linux/sh_dma.h @@ -62,6 +62,7 @@ struct sh_dmae_pdata { const unsigned int *ts_shift; int ts_shift_num; u16 dmaor_init; + unsigned int chcr_offset; }; /* DMA register */ -- cgit v1.2.3 From 67c6269e5c998b53c2c08ce2befbbe20a7b6f57f Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Fri, 17 Jun 2011 08:20:51 +0000 Subject: dmaengine: shdma: add chcr_ie_bit IE bit position on CHCR register is not same in all DMAC. This patch adds new "chcr_ie_bit" to decide it. Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- drivers/dma/shdma.c | 11 +++++++++-- drivers/dma/shdma.h | 1 + include/linux/sh_dma.h | 1 + 3 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c index 40900c1cee9a..9412de3ef899 100644 --- a/drivers/dma/shdma.c +++ b/drivers/dma/shdma.c @@ -181,17 +181,19 @@ static void dmae_set_reg(struct sh_dmae_chan *sh_chan, struct sh_dmae_regs *hw) static void dmae_start(struct sh_dmae_chan *sh_chan) { + struct sh_dmae_device *shdev = to_sh_dev(sh_chan); u32 chcr = chcr_read(sh_chan); - chcr |= CHCR_DE | CHCR_IE; + chcr |= CHCR_DE | shdev->chcr_ie_bit; chcr_write(sh_chan, chcr & ~CHCR_TE); } static void dmae_halt(struct sh_dmae_chan *sh_chan) { + struct sh_dmae_device *shdev = to_sh_dev(sh_chan); u32 chcr = chcr_read(sh_chan); - chcr &= ~(CHCR_DE | CHCR_TE | CHCR_IE); + chcr &= ~(CHCR_DE | CHCR_TE | shdev->chcr_ie_bit); chcr_write(sh_chan, chcr); } @@ -1157,6 +1159,11 @@ static int __init sh_dmae_probe(struct platform_device *pdev) else shdev->chcr_offset = CHCR; + if (pdata->chcr_ie_bit) + shdev->chcr_ie_bit = pdata->chcr_ie_bit; + else + shdev->chcr_ie_bit = CHCR_IE; + platform_set_drvdata(pdev, shdev); pm_runtime_enable(&pdev->dev); diff --git a/drivers/dma/shdma.h b/drivers/dma/shdma.h index 6f064cad6c0f..dc56576f9fdb 100644 --- a/drivers/dma/shdma.h +++ b/drivers/dma/shdma.h @@ -48,6 +48,7 @@ struct sh_dmae_device { u32 __iomem *chan_reg; u16 __iomem *dmars; unsigned int chcr_offset; + u32 chcr_ie_bit; }; #define to_sh_chan(chan) container_of(chan, struct sh_dmae_chan, common) diff --git a/include/linux/sh_dma.h b/include/linux/sh_dma.h index 41fe4c2d6481..96803aa7b6bd 100644 --- a/include/linux/sh_dma.h +++ b/include/linux/sh_dma.h @@ -63,6 +63,7 @@ struct sh_dmae_pdata { int ts_shift_num; u16 dmaor_init; unsigned int chcr_offset; + u32 chcr_ie_bit; }; /* DMA register */ -- cgit v1.2.3 From e76c3af873025f5a704d56a28882be761e15657b Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Fri, 17 Jun 2011 08:20:56 +0000 Subject: dmaengine: shdma: add dmaor_is_32bit flag Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- drivers/dma/shdma.c | 14 ++++++++++++-- include/linux/sh_dma.h | 2 ++ 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c index 9412de3ef899..6a21cd843ab7 100644 --- a/drivers/dma/shdma.c +++ b/drivers/dma/shdma.c @@ -70,12 +70,22 @@ static u32 sh_dmae_readl(struct sh_dmae_chan *sh_dc, u32 reg) static u16 dmaor_read(struct sh_dmae_device *shdev) { - return __raw_readw(shdev->chan_reg + DMAOR / sizeof(u32)); + u32 __iomem *addr = shdev->chan_reg + DMAOR / sizeof(u32); + + if (shdev->pdata->dmaor_is_32bit) + return __raw_readl(addr); + else + return __raw_readw(addr); } static void dmaor_write(struct sh_dmae_device *shdev, u16 data) { - __raw_writew(data, shdev->chan_reg + DMAOR / sizeof(u32)); + u32 __iomem *addr = shdev->chan_reg + DMAOR / sizeof(u32); + + if (shdev->pdata->dmaor_is_32bit) + __raw_writel(data, addr); + else + __raw_writew(data, addr); } static void chcr_write(struct sh_dmae_chan *sh_dc, u32 data) diff --git a/include/linux/sh_dma.h b/include/linux/sh_dma.h index 96803aa7b6bd..f25afc61e1c6 100644 --- a/include/linux/sh_dma.h +++ b/include/linux/sh_dma.h @@ -64,6 +64,8 @@ struct sh_dmae_pdata { u16 dmaor_init; unsigned int chcr_offset; u32 chcr_ie_bit; + + unsigned int dmaor_is_32bit:1; }; /* DMA register */ -- cgit v1.2.3 From 260bf2c5f69f419b04b6861ca91565b5fb16ce48 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Fri, 17 Jun 2011 08:21:05 +0000 Subject: dmaengine: shdma: add .needs_tend_set / .no_dmars flags Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- drivers/dma/shdma.c | 6 ++++++ include/linux/sh_dma.h | 4 ++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c index 6a21cd843ab7..0f3ec8d57a7a 100644 --- a/drivers/dma/shdma.c +++ b/drivers/dma/shdma.c @@ -194,6 +194,9 @@ static void dmae_start(struct sh_dmae_chan *sh_chan) struct sh_dmae_device *shdev = to_sh_dev(sh_chan); u32 chcr = chcr_read(sh_chan); + if (shdev->pdata->needs_tend_set) + sh_dmae_writel(sh_chan, 0xFFFFFFFF, TEND); + chcr |= CHCR_DE | shdev->chcr_ie_bit; chcr_write(sh_chan, chcr & ~CHCR_TE); } @@ -242,6 +245,9 @@ static int dmae_set_dmars(struct sh_dmae_chan *sh_chan, u16 val) if (dmae_is_busy(sh_chan)) return -EBUSY; + if (pdata->no_dmars) + return 0; + /* in the case of a missing DMARS resource use first memory window */ if (!addr) addr = (u16 __iomem *)shdev->chan_reg; diff --git a/include/linux/sh_dma.h b/include/linux/sh_dma.h index f25afc61e1c6..cb2dd118cc0f 100644 --- a/include/linux/sh_dma.h +++ b/include/linux/sh_dma.h @@ -66,6 +66,8 @@ struct sh_dmae_pdata { u32 chcr_ie_bit; unsigned int dmaor_is_32bit:1; + unsigned int needs_tend_set:1; + unsigned int no_dmars:1; }; /* DMA register */ @@ -75,6 +77,8 @@ struct sh_dmae_pdata { #define CHCR 0x0C #define DMAOR 0x40 +#define TEND 0x18 /* USB-DMAC */ + /* DMAOR definitions */ #define DMAOR_AE 0x00000004 #define DMAOR_NMIF 0x00000002 -- cgit v1.2.3 From 9174fc8f111982e024a00512c521ad8f1056fccb Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Tue, 28 Jun 2011 15:25:36 +0900 Subject: serial: sh-sci: Fix up pretty name printing for port IRQs. Presently these were all using the same static string with no regard to dev_name() and the like. This implements a bit of rework to name the IRQ dynamically, as it should have been doing all along anyways. Signed-off-by: Paul Mundt --- drivers/tty/serial/sh-sci.c | 118 +++++++++++++++++++++++++++++++------------- include/linux/serial_sci.h | 7 +++ 2 files changed, 92 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 9c8624d9c803..d0a56235c50e 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -71,6 +71,8 @@ struct sci_port { /* Function clock */ struct clk *fclk; + char *irqstr[SCIx_NR_IRQS]; + struct dma_chan *chan_tx; struct dma_chan *chan_rx; @@ -954,53 +956,102 @@ static int sci_notifier(struct notifier_block *self, return NOTIFY_OK; } +static struct sci_irq_desc { + const char *desc; + irq_handler_t handler; +} sci_irq_desc[] = { + /* + * Split out handlers, the default case. + */ + [SCIx_ERI_IRQ] = { + .desc = "rx err", + .handler = sci_er_interrupt, + }, + + [SCIx_RXI_IRQ] = { + .desc = "rx full", + .handler = sci_rx_interrupt, + }, + + [SCIx_TXI_IRQ] = { + .desc = "tx empty", + .handler = sci_tx_interrupt, + }, + + [SCIx_BRI_IRQ] = { + .desc = "break", + .handler = sci_br_interrupt, + }, + + /* + * Special muxed handler. + */ + [SCIx_MUX_IRQ] = { + .desc = "mux", + .handler = sci_mpxed_interrupt, + }, +}; + static int sci_request_irq(struct sci_port *port) { - int i; - irqreturn_t (*handlers[4])(int irq, void *ptr) = { - sci_er_interrupt, sci_rx_interrupt, sci_tx_interrupt, - sci_br_interrupt, - }; - const char *desc[] = { "SCI Receive Error", "SCI Receive Data Full", - "SCI Transmit Data Empty", "SCI Break" }; - - if (port->cfg->irqs[0] == port->cfg->irqs[1]) { - if (unlikely(!port->cfg->irqs[0])) - return -ENODEV; - - if (request_irq(port->cfg->irqs[0], sci_mpxed_interrupt, - IRQF_DISABLED, "sci", port)) { - dev_err(port->port.dev, "Can't allocate IRQ\n"); - return -ENODEV; + struct uart_port *up = &port->port; + int i, j, ret = 0; + + for (i = j = 0; i < SCIx_NR_IRQS; i++, j++) { + struct sci_irq_desc *desc; + unsigned int irq; + + if (SCIx_IRQ_IS_MUXED(port)) { + i = SCIx_MUX_IRQ; + irq = up->irq; + } else + irq = port->cfg->irqs[i]; + + desc = sci_irq_desc + i; + port->irqstr[j] = kasprintf(GFP_KERNEL, "%s:%s", + dev_name(up->dev), desc->desc); + if (!port->irqstr[j]) { + dev_err(up->dev, "Failed to allocate %s IRQ string\n", + desc->desc); + goto out_nomem; } - } else { - for (i = 0; i < ARRAY_SIZE(handlers); i++) { - if (unlikely(!port->cfg->irqs[i])) - continue; - - if (request_irq(port->cfg->irqs[i], handlers[i], - IRQF_DISABLED, desc[i], port)) { - dev_err(port->port.dev, "Can't allocate IRQ\n"); - return -ENODEV; - } + + ret = request_irq(irq, desc->handler, up->irqflags, + port->irqstr[j], port); + if (unlikely(ret)) { + dev_err(up->dev, "Can't allocate %s IRQ\n", desc->desc); + goto out_noirq; } } return 0; + +out_noirq: + while (--i >= 0) + free_irq(port->cfg->irqs[i], port); + +out_nomem: + while (--j >= 0) + kfree(port->irqstr[j]); + + return ret; } static void sci_free_irq(struct sci_port *port) { int i; - if (port->cfg->irqs[0] == port->cfg->irqs[1]) - free_irq(port->cfg->irqs[0], port); - else { - for (i = 0; i < ARRAY_SIZE(port->cfg->irqs); i++) { - if (!port->cfg->irqs[i]) - continue; + /* + * Intentionally in reverse order so we iterate over the muxed + * IRQ first. + */ + for (i = 0; i < SCIx_NR_IRQS; i++) { + free_irq(port->cfg->irqs[i], port); + kfree(port->irqstr[i]); - free_irq(port->cfg->irqs[i], port); + if (SCIx_IRQ_IS_MUXED(port)) { + /* If there's only one IRQ, we're done. */ + return; } } } @@ -1910,6 +1961,7 @@ static int __devinit sci_init_single(struct platform_device *dev, * For the muxed case there's nothing more to do. */ port->irq = p->irqs[SCIx_RXI_IRQ]; + port->irqflags = IRQF_DISABLED; port->serial_in = sci_serial_in; port->serial_out = sci_serial_out; diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index 4ca130a90ea5..8bffe9ae2ca0 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -56,6 +56,8 @@ enum { SCIx_TXI_IRQ, SCIx_BRI_IRQ, SCIx_NR_IRQS, + + SCIx_MUX_IRQ = SCIx_NR_IRQS, /* special case */ }; enum { @@ -82,6 +84,11 @@ enum { [SCIx_BRI_IRQ] = (irq), \ } +#define SCIx_IRQ_IS_MUXED(port) \ + ((port)->cfg->irqs[SCIx_ERI_IRQ] == \ + (port)->cfg->irqs[SCIx_RXI_IRQ]) || \ + ((port)->cfg->irqs[SCIx_ERI_IRQ] && \ + !(port)->cfg->irqs[SCIx_RXI_IRQ]) /* * SCI register subset common for all port types. * Not all registers will exist on all parts. -- cgit v1.2.3 From 58ddafae2d7102d8f493840cb7aca0b4b2326b2a Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Tue, 24 May 2011 12:05:59 -0700 Subject: bq20z75: Add support for external notification Adding support for external power change notification. One problem found is that there is a lag time before the sensor will return a new status. To ensure that we only fire off the power_supply_changed event when the status returned from the sensor is actually different, we delay sending the the notification, and instead poll on it looking for a change. The amount of time to poll is configurable via platform data. Signed-off-by: Rhyland Klein Signed-off-by: Anton Vorontsov --- drivers/power/bq20z75.c | 101 ++++++++++++++++++++++++++++++++++++++---- include/linux/power/bq20z75.h | 3 ++ 2 files changed, 95 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/bq20z75.c b/drivers/power/bq20z75.c index 506585e31a5b..e1adc0e027ac 100644 --- a/drivers/power/bq20z75.c +++ b/drivers/power/bq20z75.c @@ -152,6 +152,10 @@ struct bq20z75_info { bool gpio_detect; bool enable_detection; int irq; + int last_state; + int poll_time; + struct delayed_work work; + int ignore_changes; }; static int bq20z75_read_word_data(struct i2c_client *client, u8 address) @@ -279,6 +283,7 @@ static int bq20z75_get_battery_property(struct i2c_client *client, int reg_offset, enum power_supply_property psp, union power_supply_propval *val) { + struct bq20z75_info *bq20z75_device = i2c_get_clientdata(client); s32 ret; ret = bq20z75_read_word_data(client, @@ -293,15 +298,24 @@ static int bq20z75_get_battery_property(struct i2c_client *client, if (ret >= bq20z75_data[reg_offset].min_value && ret <= bq20z75_data[reg_offset].max_value) { val->intval = ret; - if (psp == POWER_SUPPLY_PROP_STATUS) { - if (ret & BATTERY_FULL_CHARGED) - val->intval = POWER_SUPPLY_STATUS_FULL; - else if (ret & BATTERY_FULL_DISCHARGED) - val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING; - else if (ret & BATTERY_DISCHARGING) - val->intval = POWER_SUPPLY_STATUS_DISCHARGING; - else - val->intval = POWER_SUPPLY_STATUS_CHARGING; + if (psp != POWER_SUPPLY_PROP_STATUS) + return 0; + + if (ret & BATTERY_FULL_CHARGED) + val->intval = POWER_SUPPLY_STATUS_FULL; + else if (ret & BATTERY_FULL_DISCHARGED) + val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING; + else if (ret & BATTERY_DISCHARGING) + val->intval = POWER_SUPPLY_STATUS_DISCHARGING; + else + val->intval = POWER_SUPPLY_STATUS_CHARGING; + + if (bq20z75_device->poll_time == 0) + bq20z75_device->last_state = val->intval; + else if (bq20z75_device->last_state != val->intval) { + cancel_delayed_work_sync(&bq20z75_device->work); + power_supply_changed(&bq20z75_device->power_supply); + bq20z75_device->poll_time = 0; } } else { if (psp == POWER_SUPPLY_PROP_STATUS) @@ -545,6 +559,60 @@ static irqreturn_t bq20z75_irq(int irq, void *devid) return IRQ_HANDLED; } +static void bq20z75_external_power_changed(struct power_supply *psy) +{ + struct bq20z75_info *bq20z75_device; + + bq20z75_device = container_of(psy, struct bq20z75_info, power_supply); + + if (bq20z75_device->ignore_changes > 0) { + bq20z75_device->ignore_changes--; + return; + } + + /* cancel outstanding work */ + cancel_delayed_work_sync(&bq20z75_device->work); + + schedule_delayed_work(&bq20z75_device->work, HZ); + bq20z75_device->poll_time = bq20z75_device->pdata->poll_retry_count; +} + +static void bq20z75_delayed_work(struct work_struct *work) +{ + struct bq20z75_info *bq20z75_device; + s32 ret; + + bq20z75_device = container_of(work, struct bq20z75_info, work.work); + + ret = bq20z75_read_word_data(bq20z75_device->client, + bq20z75_data[REG_STATUS].addr); + /* if the read failed, give up on this work */ + if (ret < 0) { + bq20z75_device->poll_time = 0; + return; + } + + if (ret & BATTERY_FULL_CHARGED) + ret = POWER_SUPPLY_STATUS_FULL; + else if (ret & BATTERY_FULL_DISCHARGED) + ret = POWER_SUPPLY_STATUS_NOT_CHARGING; + else if (ret & BATTERY_DISCHARGING) + ret = POWER_SUPPLY_STATUS_DISCHARGING; + else + ret = POWER_SUPPLY_STATUS_CHARGING; + + if (bq20z75_device->last_state != ret) { + bq20z75_device->poll_time = 0; + power_supply_changed(&bq20z75_device->power_supply); + return; + } + if (bq20z75_device->poll_time > 0) { + schedule_delayed_work(&bq20z75_device->work, HZ); + bq20z75_device->poll_time--; + return; + } +} + static int __devinit bq20z75_probe(struct i2c_client *client, const struct i2c_device_id *id) { @@ -566,6 +634,13 @@ static int __devinit bq20z75_probe(struct i2c_client *client, bq20z75_device->power_supply.num_properties = ARRAY_SIZE(bq20z75_properties); bq20z75_device->power_supply.get_property = bq20z75_get_property; + /* ignore first notification of external change, it is generated + * from the power_supply_register call back + */ + bq20z75_device->ignore_changes = 1; + bq20z75_device->last_state = POWER_SUPPLY_STATUS_UNKNOWN; + bq20z75_device->power_supply.external_power_changed = + bq20z75_external_power_changed; if (pdata) { bq20z75_device->gpio_detect = @@ -625,6 +700,8 @@ skip_gpio: dev_info(&client->dev, "%s: battery gas gauge device registered\n", client->name); + INIT_DELAYED_WORK(&bq20z75_device->work, bq20z75_delayed_work); + return 0; exit_psupply: @@ -648,6 +725,9 @@ static int __devexit bq20z75_remove(struct i2c_client *client) gpio_free(bq20z75_device->pdata->battery_detect); power_supply_unregister(&bq20z75_device->power_supply); + + cancel_delayed_work_sync(&bq20z75_device->work); + kfree(bq20z75_device); bq20z75_device = NULL; @@ -661,6 +741,9 @@ static int bq20z75_suspend(struct i2c_client *client, struct bq20z75_info *bq20z75_device = i2c_get_clientdata(client); s32 ret; + if (bq20z75_device->poll_time > 0) + cancel_delayed_work_sync(&bq20z75_device->work); + /* write to manufacturer access with sleep command */ ret = bq20z75_write_word_data(client, bq20z75_data[REG_MANUFACTURER_DATA].addr, diff --git a/include/linux/power/bq20z75.h b/include/linux/power/bq20z75.h index b0843b68af92..1398eb004e83 100644 --- a/include/linux/power/bq20z75.h +++ b/include/linux/power/bq20z75.h @@ -29,11 +29,14 @@ * @battery_detect: GPIO which is used to detect battery presence * @battery_detect_present: gpio state when battery is present (0 / 1) * @i2c_retry_count: # of times to retry on i2c IO failure + * @poll_retry_count: # of times to retry looking for new status after + * external change notification */ struct bq20z75_platform_data { int battery_detect; int battery_detect_present; int i2c_retry_count; + int poll_retry_count; }; #endif -- cgit v1.2.3 From 149c077b4bd746eca2eeb241e55456eb4882b259 Mon Sep 17 00:00:00 2001 From: Donggeun Kim Date: Wed, 22 Jun 2011 19:40:06 +0900 Subject: power_supply: Add charger driver for MAX8997/8966 MAX8997/8966 chip is a multi-function device which includes PMIC, RTC, Fuel Gauge, MUIC, Haptic, Flash control, and Battery charging control. The driver for it is located at drivers/mfd. This patch supports battery charging control of MAX8997/8966 chip and provides power supply class information to userspace. Signed-off-by: Donggeun Kim Signed-off-by: MyungJoo Ham Signed-off-by: KyungMin Park Acked-by: Samuel Ortiz Signed-off-by: Anton Vorontsov --- drivers/power/Kconfig | 7 ++ drivers/power/Makefile | 1 + drivers/power/max8997_charger.c | 206 ++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/max8997.h | 7 +- 4 files changed, 220 insertions(+), 1 deletion(-) create mode 100644 drivers/power/max8997_charger.c (limited to 'include/linux') diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig index cc019c9812c2..f4f1a31d46a3 100644 --- a/drivers/power/Kconfig +++ b/drivers/power/Kconfig @@ -228,4 +228,11 @@ config CHARGER_GPIO This driver can be build as a module. If so, the module will be called gpio-charger. +config CHARGER_MAX8997 + tristate "Maxim MAX8997/MAX8966 PMIC battery charger driver" + depends on MFD_MAX8997 && REGULATOR_MAX8997 + help + Say Y to enable support for the battery charger control sysfs and + platform data of MAX8997/LP3974 PMICs. + endif # POWER_SUPPLY diff --git a/drivers/power/Makefile b/drivers/power/Makefile index 8fcd93ff2353..39793ef50cd5 100644 --- a/drivers/power/Makefile +++ b/drivers/power/Makefile @@ -35,3 +35,4 @@ obj-$(CONFIG_CHARGER_ISP1704) += isp1704_charger.o obj-$(CONFIG_CHARGER_MAX8903) += max8903_charger.o obj-$(CONFIG_CHARGER_TWL4030) += twl4030_charger.o obj-$(CONFIG_CHARGER_GPIO) += gpio-charger.o +obj-$(CONFIG_CHARGER_MAX8997) += max8997_charger.o diff --git a/drivers/power/max8997_charger.c b/drivers/power/max8997_charger.c new file mode 100644 index 000000000000..7106b49b26e4 --- /dev/null +++ b/drivers/power/max8997_charger.c @@ -0,0 +1,206 @@ +/* + * max8997_charger.c - Power supply consumer driver for the Maxim 8997/8966 + * + * Copyright (C) 2011 Samsung Electronics + * MyungJoo Ham + * + * 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 + */ + +#include +#include +#include +#include +#include +#include + +struct charger_data { + struct device *dev; + struct max8997_dev *iodev; + struct power_supply battery; +}; + +static enum power_supply_property max8997_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, /* "FULL" or "NOT FULL" only. */ + POWER_SUPPLY_PROP_PRESENT, /* the presence of battery */ + POWER_SUPPLY_PROP_ONLINE, /* charger is active or not */ +}; + +/* Note that the charger control is done by a current regulator "CHARGER" */ +static int max8997_battery_get_property(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) +{ + struct charger_data *charger = container_of(psy, + struct charger_data, battery); + struct i2c_client *i2c = charger->iodev->i2c; + int ret; + u8 reg; + + switch (psp) { + case POWER_SUPPLY_PROP_STATUS: + val->intval = 0; + ret = max8997_read_reg(i2c, MAX8997_REG_STATUS4, ®); + if (ret) + return ret; + if ((reg & (1 << 0)) == 0x1) + val->intval = POWER_SUPPLY_STATUS_FULL; + + break; + case POWER_SUPPLY_PROP_PRESENT: + val->intval = 0; + ret = max8997_read_reg(i2c, MAX8997_REG_STATUS4, ®); + if (ret) + return ret; + if ((reg & (1 << 2)) == 0x0) + val->intval = 1; + + break; + case POWER_SUPPLY_PROP_ONLINE: + val->intval = 0; + ret = max8997_read_reg(i2c, MAX8997_REG_STATUS4, ®); + if (ret) + return ret; + /* DCINOK */ + if (reg & (1 << 1)) + val->intval = 1; + + break; + default: + return -EINVAL; + } + + return 0; +} + +static __devinit int max8997_battery_probe(struct platform_device *pdev) +{ + int ret = 0; + struct charger_data *charger; + struct max8997_dev *iodev = dev_get_drvdata(pdev->dev.parent); + struct max8997_platform_data *pdata = dev_get_platdata(iodev->dev); + + if (!pdata) + return -EINVAL; + + if (pdata->eoc_mA) { + u8 val = (pdata->eoc_mA - 50) / 10; + if (val < 0) + val = 0; + if (val > 0xf) + val = 0xf; + + ret = max8997_update_reg(iodev->i2c, + MAX8997_REG_MBCCTRL5, val, 0xf); + if (ret < 0) { + dev_err(&pdev->dev, "Cannot use i2c bus.\n"); + return ret; + } + } + + switch (pdata->timeout) { + case 5: + ret = max8997_update_reg(iodev->i2c, MAX8997_REG_MBCCTRL1, + 0x2 << 4, 0x7 << 4); + break; + case 6: + ret = max8997_update_reg(iodev->i2c, MAX8997_REG_MBCCTRL1, + 0x3 << 4, 0x7 << 4); + break; + case 7: + ret = max8997_update_reg(iodev->i2c, MAX8997_REG_MBCCTRL1, + 0x4 << 4, 0x7 << 4); + break; + case 0: + ret = max8997_update_reg(iodev->i2c, MAX8997_REG_MBCCTRL1, + 0x7 << 4, 0x7 << 4); + break; + default: + dev_err(&pdev->dev, "incorrect timeout value (%d)\n", + pdata->timeout); + return -EINVAL; + } + if (ret < 0) { + dev_err(&pdev->dev, "Cannot use i2c bus.\n"); + return ret; + } + + charger = kzalloc(sizeof(struct charger_data), GFP_KERNEL); + if (charger == NULL) { + dev_err(&pdev->dev, "Cannot allocate memory.\n"); + return -ENOMEM; + } + + platform_set_drvdata(pdev, charger); + + charger->battery.name = "max8997_pmic"; + charger->battery.type = POWER_SUPPLY_TYPE_BATTERY; + charger->battery.get_property = max8997_battery_get_property; + charger->battery.properties = max8997_battery_props; + charger->battery.num_properties = ARRAY_SIZE(max8997_battery_props); + + charger->dev = &pdev->dev; + charger->iodev = iodev; + + ret = power_supply_register(&pdev->dev, &charger->battery); + if (ret) { + dev_err(&pdev->dev, "failed: power supply register\n"); + goto err; + } + + return 0; +err: + kfree(charger); + return ret; +} + +static int __devexit max8997_battery_remove(struct platform_device *pdev) +{ + struct charger_data *charger = platform_get_drvdata(pdev); + + power_supply_unregister(&charger->battery); + kfree(charger); + return 0; +} + +static const struct platform_device_id max8997_battery_id[] = { + { "max8997-battery", 0 }, +}; + +static struct platform_driver max8997_battery_driver = { + .driver = { + .name = "max8997-battery", + .owner = THIS_MODULE, + }, + .probe = max8997_battery_probe, + .remove = __devexit_p(max8997_battery_remove), + .id_table = max8997_battery_id, +}; + +static int __init max8997_battery_init(void) +{ + return platform_driver_register(&max8997_battery_driver); +} +subsys_initcall(max8997_battery_init); + +static void __exit max8997_battery_cleanup(void) +{ + platform_driver_unregister(&max8997_battery_driver); +} +module_exit(max8997_battery_cleanup); + +MODULE_DESCRIPTION("MAXIM 8997/8966 battery control driver"); +MODULE_AUTHOR("MyungJoo Ham "); +MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h index 60931d089422..0bbd13dbe336 100644 --- a/include/linux/mfd/max8997.h +++ b/include/linux/mfd/max8997.h @@ -107,11 +107,16 @@ struct max8997_platform_data { unsigned int buck5_voltage[8]; bool buck5_gpiodvs; + /* ---- Charger control ---- */ + /* eoc stands for 'end of charge' */ + int eoc_mA; /* 50 ~ 200mA by 10mA step */ + /* charge Full Timeout */ + int timeout; /* 0 (no timeout), 5, 6, 7 hours */ + /* MUIC: Not implemented */ /* HAPTIC: Not implemented */ /* RTC: Not implemented */ /* Flash: Not implemented */ - /* Charger control: Not implemented */ }; #endif /* __LINUX_MFD_MAX8998_H */ -- cgit v1.2.3 From bb4ce9708785f40849f1a64931e6cc3b26171201 Mon Sep 17 00:00:00 2001 From: Donggeun Kim Date: Fri, 24 Jun 2011 19:04:18 +0900 Subject: power_supply: Add charger driver for MAX8998/LP3974 This patch supports power supply APIs for MAX8998/LP3974. Signed-off-by: Donggeun Kim Signed-off-by: MyungJoo Ham Signed-off-by: KyungMin Park Acked-by: Samuel Ortiz Signed-off-by: Anton Vorontsov --- drivers/mfd/max8998.c | 2 + drivers/power/Kconfig | 7 ++ drivers/power/Makefile | 1 + drivers/power/max8998_charger.c | 218 ++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/max8998.h | 12 +++ 5 files changed, 240 insertions(+) create mode 100644 drivers/power/max8998_charger.c (limited to 'include/linux') diff --git a/drivers/mfd/max8998.c b/drivers/mfd/max8998.c index 9ec7570f5b81..de4096aee248 100644 --- a/drivers/mfd/max8998.c +++ b/drivers/mfd/max8998.c @@ -39,6 +39,8 @@ static struct mfd_cell max8998_devs[] = { .name = "max8998-pmic", }, { .name = "max8998-rtc", + }, { + .name = "max8998-battery", }, }; diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig index f4f1a31d46a3..fddc392369ed 100644 --- a/drivers/power/Kconfig +++ b/drivers/power/Kconfig @@ -235,4 +235,11 @@ config CHARGER_MAX8997 Say Y to enable support for the battery charger control sysfs and platform data of MAX8997/LP3974 PMICs. +config CHARGER_MAX8998 + tristate "Maxim MAX8998/LP3974 PMIC battery charger driver" + depends on MFD_MAX8998 && REGULATOR_MAX8998 + help + Say Y to enable support for the battery charger control sysfs and + platform data of MAX8998/LP3974 PMICs. + endif # POWER_SUPPLY diff --git a/drivers/power/Makefile b/drivers/power/Makefile index 39793ef50cd5..a18e899b1f46 100644 --- a/drivers/power/Makefile +++ b/drivers/power/Makefile @@ -36,3 +36,4 @@ obj-$(CONFIG_CHARGER_MAX8903) += max8903_charger.o obj-$(CONFIG_CHARGER_TWL4030) += twl4030_charger.o obj-$(CONFIG_CHARGER_GPIO) += gpio-charger.o obj-$(CONFIG_CHARGER_MAX8997) += max8997_charger.o +obj-$(CONFIG_CHARGER_MAX8998) += max8998_charger.o diff --git a/drivers/power/max8998_charger.c b/drivers/power/max8998_charger.c new file mode 100644 index 000000000000..cc21fa2120be --- /dev/null +++ b/drivers/power/max8998_charger.c @@ -0,0 +1,218 @@ +/* + * max8998_charger.c - Power supply consumer driver for the Maxim 8998/LP3974 + * + * Copyright (C) 2009-2010 Samsung Electronics + * MyungJoo Ham + * + * 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 + */ + +#include +#include +#include +#include +#include +#include + +struct max8998_battery_data { + struct device *dev; + struct max8998_dev *iodev; + struct power_supply battery; +}; + +static enum power_supply_property max8998_battery_props[] = { + POWER_SUPPLY_PROP_PRESENT, /* the presence of battery */ + POWER_SUPPLY_PROP_ONLINE, /* charger is active or not */ +}; + +/* Note that the charger control is done by a current regulator "CHARGER" */ +static int max8998_battery_get_property(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) +{ + struct max8998_battery_data *max8998 = container_of(psy, + struct max8998_battery_data, battery); + struct i2c_client *i2c = max8998->iodev->i2c; + int ret; + u8 reg; + + switch (psp) { + case POWER_SUPPLY_PROP_PRESENT: + ret = max8998_read_reg(i2c, MAX8998_REG_STATUS2, ®); + if (ret) + return ret; + if (reg & (1 << 4)) + val->intval = 0; + else + val->intval = 1; + break; + case POWER_SUPPLY_PROP_ONLINE: + ret = max8998_read_reg(i2c, MAX8998_REG_STATUS2, ®); + if (ret) + return ret; + if (reg & (1 << 3)) + val->intval = 0; + else + val->intval = 1; + break; + default: + return -EINVAL; + } + + return 0; +} + +static __devinit int max8998_battery_probe(struct platform_device *pdev) +{ + struct max8998_dev *iodev = dev_get_drvdata(pdev->dev.parent); + struct max8998_platform_data *pdata = dev_get_platdata(iodev->dev); + struct max8998_battery_data *max8998; + struct i2c_client *i2c; + int ret = 0; + + if (!pdata) { + dev_err(pdev->dev.parent, "No platform init data supplied\n"); + return -ENODEV; + } + + max8998 = kzalloc(sizeof(struct max8998_battery_data), GFP_KERNEL); + if (!max8998) + return -ENOMEM; + + max8998->dev = &pdev->dev; + max8998->iodev = iodev; + platform_set_drvdata(pdev, max8998); + i2c = max8998->iodev->i2c; + + /* Setup "End of Charge" */ + /* If EOC value equals 0, + * remain value set from bootloader or default value */ + if (pdata->eoc >= 10 && pdata->eoc <= 45) { + max8998_update_reg(i2c, MAX8998_REG_CHGR1, + (pdata->eoc / 5 - 2) << 5, 0x7 << 5); + } else if (pdata->eoc == 0) { + dev_dbg(max8998->dev, + "EOC value not set: leave it unchanged.\n"); + } else { + dev_err(max8998->dev, "Invalid EOC value\n"); + ret = -EINVAL; + goto err; + } + + /* Setup Charge Restart Level */ + switch (pdata->restart) { + case 100: + max8998_update_reg(i2c, MAX8998_REG_CHGR1, 0x1 << 3, 0x3 << 3); + break; + case 150: + max8998_update_reg(i2c, MAX8998_REG_CHGR1, 0x0 << 3, 0x3 << 3); + break; + case 200: + max8998_update_reg(i2c, MAX8998_REG_CHGR1, 0x2 << 3, 0x3 << 3); + break; + case -1: + max8998_update_reg(i2c, MAX8998_REG_CHGR1, 0x3 << 3, 0x3 << 3); + break; + case 0: + dev_dbg(max8998->dev, + "Restart Level not set: leave it unchanged.\n"); + break; + default: + dev_err(max8998->dev, "Invalid Restart Level\n"); + ret = -EINVAL; + goto err; + } + + /* Setup Charge Full Timeout */ + switch (pdata->timeout) { + case 5: + max8998_update_reg(i2c, MAX8998_REG_CHGR2, 0x0 << 4, 0x3 << 4); + break; + case 6: + max8998_update_reg(i2c, MAX8998_REG_CHGR2, 0x1 << 4, 0x3 << 4); + break; + case 7: + max8998_update_reg(i2c, MAX8998_REG_CHGR2, 0x2 << 4, 0x3 << 4); + break; + case -1: + max8998_update_reg(i2c, MAX8998_REG_CHGR2, 0x3 << 4, 0x3 << 4); + break; + case 0: + dev_dbg(max8998->dev, + "Full Timeout not set: leave it unchanged.\n"); + default: + dev_err(max8998->dev, "Invalid Full Timeout value\n"); + ret = -EINVAL; + goto err; + } + + max8998->battery.name = "max8998_pmic"; + max8998->battery.type = POWER_SUPPLY_TYPE_BATTERY; + max8998->battery.get_property = max8998_battery_get_property; + max8998->battery.properties = max8998_battery_props; + max8998->battery.num_properties = ARRAY_SIZE(max8998_battery_props); + + ret = power_supply_register(max8998->dev, &max8998->battery); + if (ret) { + dev_err(max8998->dev, "failed: power supply register\n"); + goto err; + } + + return 0; +err: + kfree(max8998); + return ret; +} + +static int __devexit max8998_battery_remove(struct platform_device *pdev) +{ + struct max8998_battery_data *max8998 = platform_get_drvdata(pdev); + + power_supply_unregister(&max8998->battery); + kfree(max8998); + + return 0; +} + +static const struct platform_device_id max8998_battery_id[] = { + { "max8998-battery", TYPE_MAX8998 }, +}; + +static struct platform_driver max8998_battery_driver = { + .driver = { + .name = "max8998-battery", + .owner = THIS_MODULE, + }, + .probe = max8998_battery_probe, + .remove = __devexit_p(max8998_battery_remove), + .id_table = max8998_battery_id, +}; + +static int __init max8998_battery_init(void) +{ + return platform_driver_register(&max8998_battery_driver); +} +module_init(max8998_battery_init); + +static void __exit max8998_battery_cleanup(void) +{ + platform_driver_unregister(&max8998_battery_driver); +} +module_exit(max8998_battery_cleanup); + +MODULE_DESCRIPTION("MAXIM 8998 battery control driver"); +MODULE_AUTHOR("MyungJoo Ham "); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:max8998-battery"); diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h index 61daa167b576..f4f0dfa4698a 100644 --- a/include/linux/mfd/max8998.h +++ b/include/linux/mfd/max8998.h @@ -87,6 +87,15 @@ struct max8998_regulator_data { * @wakeup: Allow to wake up from suspend * @rtc_delay: LP3974 RTC chip bug that requires delay after a register * write before reading it. + * @eoc: End of Charge Level in percent: 10% ~ 45% by 5% step + * If it equals 0, leave it unchanged. + * Otherwise, it is a invalid value. + * @restart: Restart Level in mV: 100, 150, 200, and -1 for disable. + * If it equals 0, leave it unchanged. + * Otherwise, it is a invalid value. + * @timeout: Full Timeout in hours: 5, 6, 7, and -1 for disable. + * If it equals 0, leave it unchanged. + * Otherwise, leave it unchanged. */ struct max8998_platform_data { struct max8998_regulator_data *regulators; @@ -107,6 +116,9 @@ struct max8998_platform_data { int buck2_default_idx; bool wakeup; bool rtc_delay; + int eoc; + int restart; + int timeout; }; #endif /* __LINUX_MFD_MAX8998_H */ -- cgit v1.2.3 From 086ef502c202503a19a491838098157cdab6238e Mon Sep 17 00:00:00 2001 From: Donggeun Kim Date: Thu, 30 Jun 2011 18:07:41 +0900 Subject: power_supply: MAX17042: Support additional properties This patch supports additional properties (PRESENT, CYCLE_COUNT, VOLTAGE_MAX, VOLTAGE_MIN_DESIGN, CURRENT_NOW, CURRENT_AVG, CHARGE_FULL, and TEMP). Plus, initialization code for registers is added. Signed-off-by: Donggeun Kim Signed-off-by: MyungJoo Ham Signed-off-by: KyungMin Park Signed-off-by: Anton Vorontsov --- drivers/power/max17042_battery.c | 173 ++++++++++++++++++++------------- include/linux/power/max17042_battery.h | 91 +++++++++++++++++ 2 files changed, 196 insertions(+), 68 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/max17042_battery.c b/drivers/power/max17042_battery.c index 09f7496a6d8c..98bfab35b8e9 100644 --- a/drivers/power/max17042_battery.c +++ b/drivers/power/max17042_battery.c @@ -29,74 +29,6 @@ #include #include -enum max17042_register { - MAX17042_STATUS = 0x00, - MAX17042_VALRT_Th = 0x01, - MAX17042_TALRT_Th = 0x02, - MAX17042_SALRT_Th = 0x03, - MAX17042_AtRate = 0x04, - MAX17042_RepCap = 0x05, - MAX17042_RepSOC = 0x06, - MAX17042_Age = 0x07, - MAX17042_TEMP = 0x08, - MAX17042_VCELL = 0x09, - MAX17042_Current = 0x0A, - MAX17042_AvgCurrent = 0x0B, - MAX17042_Qresidual = 0x0C, - MAX17042_SOC = 0x0D, - MAX17042_AvSOC = 0x0E, - MAX17042_RemCap = 0x0F, - MAX17402_FullCAP = 0x10, - MAX17042_TTE = 0x11, - MAX17042_V_empty = 0x12, - - MAX17042_RSLOW = 0x14, - - MAX17042_AvgTA = 0x16, - MAX17042_Cycles = 0x17, - MAX17042_DesignCap = 0x18, - MAX17042_AvgVCELL = 0x19, - MAX17042_MinMaxTemp = 0x1A, - MAX17042_MinMaxVolt = 0x1B, - MAX17042_MinMaxCurr = 0x1C, - MAX17042_CONFIG = 0x1D, - MAX17042_ICHGTerm = 0x1E, - MAX17042_AvCap = 0x1F, - MAX17042_ManName = 0x20, - MAX17042_DevName = 0x21, - MAX17042_DevChem = 0x22, - - MAX17042_TempNom = 0x24, - MAX17042_TempCold = 0x25, - MAX17042_TempHot = 0x26, - MAX17042_AIN = 0x27, - MAX17042_LearnCFG = 0x28, - MAX17042_SHFTCFG = 0x29, - MAX17042_RelaxCFG = 0x2A, - MAX17042_MiscCFG = 0x2B, - MAX17042_TGAIN = 0x2C, - MAx17042_TOFF = 0x2D, - MAX17042_CGAIN = 0x2E, - MAX17042_COFF = 0x2F, - - MAX17042_Q_empty = 0x33, - MAX17042_T_empty = 0x34, - - MAX17042_RCOMP0 = 0x38, - MAX17042_TempCo = 0x39, - MAX17042_Rx = 0x3A, - MAX17042_T_empty0 = 0x3B, - MAX17042_TaskPeriod = 0x3C, - MAX17042_FSTAT = 0x3D, - - MAX17042_SHDNTIMER = 0x3F, - - MAX17042_VFRemCap = 0x4A, - - MAX17042_QH = 0x4D, - MAX17042_QL = 0x4E, -}; - struct max17042_chip { struct i2c_client *client; struct power_supply battery; @@ -123,10 +55,27 @@ static int max17042_read_reg(struct i2c_client *client, u8 reg) return ret; } +static void max17042_set_reg(struct i2c_client *client, + struct max17042_reg_data *data, int size) +{ + int i; + + for (i = 0; i < size; i++) + max17042_write_reg(client, data[i].addr, data[i].data); +} + static enum power_supply_property max17042_battery_props[] = { + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_CYCLE_COUNT, + POWER_SUPPLY_PROP_VOLTAGE_MAX, + POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN, POWER_SUPPLY_PROP_VOLTAGE_NOW, POWER_SUPPLY_PROP_VOLTAGE_AVG, POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_CHARGE_FULL, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_CURRENT_AVG, }; static int max17042_get_property(struct power_supply *psy, @@ -137,6 +86,30 @@ static int max17042_get_property(struct power_supply *psy, struct max17042_chip, battery); switch (psp) { + case POWER_SUPPLY_PROP_PRESENT: + val->intval = max17042_read_reg(chip->client, + MAX17042_STATUS); + if (val->intval & MAX17042_STATUS_BattAbsent) + val->intval = 0; + else + val->intval = 1; + break; + case POWER_SUPPLY_PROP_CYCLE_COUNT: + val->intval = max17042_read_reg(chip->client, + MAX17042_Cycles); + break; + case POWER_SUPPLY_PROP_VOLTAGE_MAX: + val->intval = max17042_read_reg(chip->client, + MAX17042_MinMaxVolt); + val->intval >>= 8; + val->intval *= 20000; /* Units of LSB = 20mV */ + break; + case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: + val->intval = max17042_read_reg(chip->client, + MAX17042_V_empty); + val->intval >>= 7; + val->intval *= 10000; /* Units of LSB = 10mV */ + break; case POWER_SUPPLY_PROP_VOLTAGE_NOW: val->intval = max17042_read_reg(chip->client, MAX17042_VCELL) * 83; /* 1000 / 12 = 83 */ @@ -149,6 +122,57 @@ static int max17042_get_property(struct power_supply *psy, val->intval = max17042_read_reg(chip->client, MAX17042_SOC) / 256; break; + case POWER_SUPPLY_PROP_CHARGE_FULL: + val->intval = max17042_read_reg(chip->client, + MAX17042_RepSOC); + if ((val->intval / 256) >= MAX17042_BATTERY_FULL) + val->intval = 1; + else if (val->intval >= 0) + val->intval = 0; + break; + case POWER_SUPPLY_PROP_TEMP: + val->intval = max17042_read_reg(chip->client, + MAX17042_TEMP); + /* The value is signed. */ + if (val->intval & 0x8000) { + val->intval = (0x7fff & ~val->intval) + 1; + val->intval *= -1; + } + /* The value is converted into deci-centigrade scale */ + /* Units of LSB = 1 / 256 degree Celsius */ + val->intval = val->intval * 10 / 256; + break; + case POWER_SUPPLY_PROP_CURRENT_NOW: + if (chip->pdata->enable_current_sense) { + val->intval = max17042_read_reg(chip->client, + MAX17042_Current); + if (val->intval & 0x8000) { + /* Negative */ + val->intval = ~val->intval & 0x7fff; + val->intval++; + val->intval *= -1; + } + val->intval >>= 4; + val->intval *= 1000000 * 25 / chip->pdata->r_sns; + } else { + return -EINVAL; + } + break; + case POWER_SUPPLY_PROP_CURRENT_AVG: + if (chip->pdata->enable_current_sense) { + val->intval = max17042_read_reg(chip->client, + MAX17042_AvgCurrent); + if (val->intval & 0x8000) { + /* Negative */ + val->intval = ~val->intval & 0x7fff; + val->intval++; + val->intval *= -1; + } + val->intval *= 1562500 / chip->pdata->r_sns; + } else { + return -EINVAL; + } + break; default: return -EINVAL; } @@ -180,6 +204,11 @@ static int __devinit max17042_probe(struct i2c_client *client, chip->battery.properties = max17042_battery_props; chip->battery.num_properties = ARRAY_SIZE(max17042_battery_props); + /* When current is not measured, + * CURRENT_NOW and CURRENT_AVG properties should be invisible. */ + if (!chip->pdata->enable_current_sense) + chip->battery.num_properties -= 2; + ret = power_supply_register(&client->dev, &chip->battery); if (ret) { dev_err(&client->dev, "failed: power supply register\n"); @@ -187,10 +216,18 @@ static int __devinit max17042_probe(struct i2c_client *client, return ret; } + /* Initialize registers according to values from the platform data */ + if (chip->pdata->init_data) + max17042_set_reg(client, chip->pdata->init_data, + chip->pdata->num_init_data); + if (!chip->pdata->enable_current_sense) { max17042_write_reg(client, MAX17042_CGAIN, 0x0000); max17042_write_reg(client, MAX17042_MiscCFG, 0x0003); max17042_write_reg(client, MAX17042_LearnCFG, 0x0007); + } else { + if (chip->pdata->r_sns == 0) + chip->pdata->r_sns = MAX17042_DEFAULT_SNS_RESISTOR; } return 0; diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h index 7995deb8bfc1..fe99211fb2b8 100644 --- a/include/linux/power/max17042_battery.h +++ b/include/linux/power/max17042_battery.h @@ -23,8 +23,99 @@ #ifndef __MAX17042_BATTERY_H_ #define __MAX17042_BATTERY_H_ +#define MAX17042_STATUS_BattAbsent (1 << 3) +#define MAX17042_BATTERY_FULL (100) +#define MAX17042_DEFAULT_SNS_RESISTOR (10000) + +enum max17042_register { + MAX17042_STATUS = 0x00, + MAX17042_VALRT_Th = 0x01, + MAX17042_TALRT_Th = 0x02, + MAX17042_SALRT_Th = 0x03, + MAX17042_AtRate = 0x04, + MAX17042_RepCap = 0x05, + MAX17042_RepSOC = 0x06, + MAX17042_Age = 0x07, + MAX17042_TEMP = 0x08, + MAX17042_VCELL = 0x09, + MAX17042_Current = 0x0A, + MAX17042_AvgCurrent = 0x0B, + MAX17042_Qresidual = 0x0C, + MAX17042_SOC = 0x0D, + MAX17042_AvSOC = 0x0E, + MAX17042_RemCap = 0x0F, + MAX17402_FullCAP = 0x10, + MAX17042_TTE = 0x11, + MAX17042_V_empty = 0x12, + + MAX17042_RSLOW = 0x14, + + MAX17042_AvgTA = 0x16, + MAX17042_Cycles = 0x17, + MAX17042_DesignCap = 0x18, + MAX17042_AvgVCELL = 0x19, + MAX17042_MinMaxTemp = 0x1A, + MAX17042_MinMaxVolt = 0x1B, + MAX17042_MinMaxCurr = 0x1C, + MAX17042_CONFIG = 0x1D, + MAX17042_ICHGTerm = 0x1E, + MAX17042_AvCap = 0x1F, + MAX17042_ManName = 0x20, + MAX17042_DevName = 0x21, + MAX17042_DevChem = 0x22, + + MAX17042_TempNom = 0x24, + MAX17042_TempCold = 0x25, + MAX17042_TempHot = 0x26, + MAX17042_AIN = 0x27, + MAX17042_LearnCFG = 0x28, + MAX17042_SHFTCFG = 0x29, + MAX17042_RelaxCFG = 0x2A, + MAX17042_MiscCFG = 0x2B, + MAX17042_TGAIN = 0x2C, + MAx17042_TOFF = 0x2D, + MAX17042_CGAIN = 0x2E, + MAX17042_COFF = 0x2F, + + MAX17042_Q_empty = 0x33, + MAX17042_T_empty = 0x34, + + MAX17042_RCOMP0 = 0x38, + MAX17042_TempCo = 0x39, + MAX17042_Rx = 0x3A, + MAX17042_T_empty0 = 0x3B, + MAX17042_TaskPeriod = 0x3C, + MAX17042_FSTAT = 0x3D, + + MAX17042_SHDNTIMER = 0x3F, + + MAX17042_VFRemCap = 0x4A, + + MAX17042_QH = 0x4D, + MAX17042_QL = 0x4E, +}; + +/* + * used for setting a register to a desired value + * addr : address for a register + * data : setting value for the register + */ +struct max17042_reg_data { + u8 addr; + u16 data; +}; + struct max17042_platform_data { + struct max17042_reg_data *init_data; + int num_init_data; /* Number of enties in init_data array */ bool enable_current_sense; + + /* + * R_sns in micro-ohms. + * default 10000 (if r_sns = 0) as it is the recommended value by + * the datasheet although it can be changed by board designers. + */ + unsigned int r_sns; }; #endif /* __MAX17042_BATTERY_H_ */ -- cgit v1.2.3 From 4862fd6047ed02e2726667c54d35f538eecc56aa Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 10 Jul 2011 22:05:08 -0400 Subject: jbd2: remove jbd2_dev_to_name() from jbd2 tracepoints Using function calls in TP_printk causes perf heartburn, so print the MAJOR/MINOR device numbers instead. Signed-off-by: "Theodore Ts'o" --- fs/jbd2/journal.c | 67 --------------------------------------------- include/linux/jbd2.h | 6 ---- include/trace/events/jbd2.h | 36 ++++++++++++------------ 3 files changed, 19 insertions(+), 90 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0dfa5b598e68..f24df13adc4e 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2390,73 +2390,6 @@ static void __exit journal_exit(void) jbd2_journal_destroy_caches(); } -/* - * jbd2_dev_to_name is a utility function used by the jbd2 and ext4 - * tracing infrastructure to map a dev_t to a device name. - * - * The caller should use rcu_read_lock() in order to make sure the - * device name stays valid until its done with it. We use - * rcu_read_lock() as well to make sure we're safe in case the caller - * gets sloppy, and because rcu_read_lock() is cheap and can be safely - * nested. - */ -struct devname_cache { - struct rcu_head rcu; - dev_t device; - char devname[BDEVNAME_SIZE]; -}; -#define CACHE_SIZE_BITS 6 -static struct devname_cache *devcache[1 << CACHE_SIZE_BITS]; -static DEFINE_SPINLOCK(devname_cache_lock); - -static void free_devcache(struct rcu_head *rcu) -{ - kfree(rcu); -} - -const char *jbd2_dev_to_name(dev_t device) -{ - int i = hash_32(device, CACHE_SIZE_BITS); - char *ret; - struct block_device *bd; - static struct devname_cache *new_dev; - - rcu_read_lock(); - if (devcache[i] && devcache[i]->device == device) { - ret = devcache[i]->devname; - rcu_read_unlock(); - return ret; - } - rcu_read_unlock(); - - new_dev = kmalloc(sizeof(struct devname_cache), GFP_KERNEL); - if (!new_dev) - return "NODEV-ALLOCFAILURE"; /* Something non-NULL */ - bd = bdget(device); - spin_lock(&devname_cache_lock); - if (devcache[i]) { - if (devcache[i]->device == device) { - kfree(new_dev); - bdput(bd); - ret = devcache[i]->devname; - spin_unlock(&devname_cache_lock); - return ret; - } - call_rcu(&devcache[i]->rcu, free_devcache); - } - devcache[i] = new_dev; - devcache[i]->device = device; - if (bd) { - bdevname(bd, devcache[i]->devname); - bdput(bd); - } else - __bdevname(device, devcache[i]->devname); - ret = devcache[i]->devname; - spin_unlock(&devname_cache_lock); - return ret; -} -EXPORT_SYMBOL(jbd2_dev_to_name); - MODULE_LICENSE("GPL"); module_init(journal_init); module_exit(journal_exit); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d087c2e7b2aa..38f307b8c334 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1329,12 +1329,6 @@ extern int jbd_blocks_per_page(struct inode *inode); #define BUFFER_TRACE2(bh, bh2, info) do {} while (0) #define JBUFFER_TRACE(jh, info) do {} while (0) -/* - * jbd2_dev_to_name is a utility function used by the jbd2 and ext4 - * tracing infrastructure to map a dev_t to a device name. - */ -extern const char *jbd2_dev_to_name(dev_t device); - #endif /* __KERNEL__ */ #endif /* _LINUX_JBD2_H */ diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index bf16545cc977..75964412ddbb 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -26,8 +26,8 @@ TRACE_EVENT(jbd2_checkpoint, __entry->result = result; ), - TP_printk("dev %s result %d", - jbd2_dev_to_name(__entry->dev), __entry->result) + TP_printk("dev %d,%d result %d", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->result) ); DECLARE_EVENT_CLASS(jbd2_commit, @@ -48,9 +48,9 @@ DECLARE_EVENT_CLASS(jbd2_commit, __entry->transaction = commit_transaction->t_tid; ), - TP_printk("dev %s transaction %d sync %d", - jbd2_dev_to_name(__entry->dev), __entry->transaction, - __entry->sync_commit) + TP_printk("dev %d,%d transaction %d sync %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->transaction, __entry->sync_commit) ); DEFINE_EVENT(jbd2_commit, jbd2_start_commit, @@ -100,9 +100,9 @@ TRACE_EVENT(jbd2_end_commit, __entry->head = journal->j_tail_sequence; ), - TP_printk("dev %s transaction %d sync %d head %d", - jbd2_dev_to_name(__entry->dev), __entry->transaction, - __entry->sync_commit, __entry->head) + TP_printk("dev %d,%d transaction %d sync %d head %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->transaction, __entry->sync_commit, __entry->head) ); TRACE_EVENT(jbd2_submit_inode_data, @@ -120,8 +120,9 @@ TRACE_EVENT(jbd2_submit_inode_data, __entry->ino = inode->i_ino; ), - TP_printk("dev %s ino %lu", - jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino) + TP_printk("dev %d,%d ino %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino) ); TRACE_EVENT(jbd2_run_stats, @@ -156,9 +157,9 @@ TRACE_EVENT(jbd2_run_stats, __entry->blocks_logged = stats->rs_blocks_logged; ), - TP_printk("dev %s tid %lu wait %u running %u locked %u flushing %u " + TP_printk("dev %d,%d tid %lu wait %u running %u locked %u flushing %u " "logging %u handle_count %u blocks %u blocks_logged %u", - jbd2_dev_to_name(__entry->dev), __entry->tid, + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->wait), jiffies_to_msecs(__entry->running), jiffies_to_msecs(__entry->locked), @@ -192,9 +193,9 @@ TRACE_EVENT(jbd2_checkpoint_stats, __entry->dropped = stats->cs_dropped; ), - TP_printk("dev %s tid %lu chp_time %u forced_to_close %u " + TP_printk("dev %d,%d tid %lu chp_time %u forced_to_close %u " "written %u dropped %u", - jbd2_dev_to_name(__entry->dev), __entry->tid, + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->chp_time), __entry->forced_to_close, __entry->written, __entry->dropped) ); @@ -222,9 +223,10 @@ TRACE_EVENT(jbd2_cleanup_journal_tail, __entry->freed = freed; ), - TP_printk("dev %s from %u to %u offset %lu freed %lu", - jbd2_dev_to_name(__entry->dev), __entry->tail_sequence, - __entry->first_tid, __entry->block_nr, __entry->freed) + TP_printk("dev %d,%d from %u to %u offset %lu freed %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->tail_sequence, __entry->first_tid, + __entry->block_nr, __entry->freed) ); #endif /* _TRACE_JBD2_H */ -- cgit v1.2.3 From 1522043bf73ef0e9e61dc512a0f3cdbec1cbf89f Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Wed, 6 Jul 2011 02:54:11 +0000 Subject: sh: move CLKDEV_xxx_ID macro to sh_clk.h Signed-off-by: Kuninori Morimoto Signed-off-by: Paul Mundt --- arch/arm/mach-shmobile/clock-sh7367.c | 3 --- arch/arm/mach-shmobile/clock-sh7372.c | 4 ---- arch/arm/mach-shmobile/clock-sh7377.c | 3 --- arch/arm/mach-shmobile/clock-sh73a0.c | 4 ---- arch/sh/boards/mach-highlander/setup.c | 2 -- arch/sh/kernel/cpu/clock-cpg.c | 2 -- arch/sh/kernel/cpu/sh4/clock-sh4-202.c | 2 -- arch/sh/kernel/cpu/sh4a/clock-sh7343.c | 4 ---- arch/sh/kernel/cpu/sh4a/clock-sh7366.c | 4 ---- arch/sh/kernel/cpu/sh4a/clock-sh7722.c | 4 ---- arch/sh/kernel/cpu/sh4a/clock-sh7723.c | 3 --- arch/sh/kernel/cpu/sh4a/clock-sh7724.c | 4 ---- arch/sh/kernel/cpu/sh4a/clock-sh7757.c | 3 --- arch/sh/kernel/cpu/sh4a/clock-sh7763.c | 2 -- arch/sh/kernel/cpu/sh4a/clock-sh7780.c | 2 -- arch/sh/kernel/cpu/sh4a/clock-sh7785.c | 3 --- arch/sh/kernel/cpu/sh4a/clock-sh7786.c | 3 --- arch/sh/kernel/cpu/sh4a/clock-shx3.c | 3 --- include/linux/sh_clk.h | 4 ++++ 19 files changed, 4 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-shmobile/clock-sh7367.c b/arch/arm/mach-shmobile/clock-sh7367.c index 6b186aefcbd6..5218c34a9cc6 100644 --- a/arch/arm/mach-shmobile/clock-sh7367.c +++ b/arch/arm/mach-shmobile/clock-sh7367.c @@ -259,9 +259,6 @@ static struct clk mstp_clks[MSTP_NR] = { [CMMSTP003] = MSTP(&r_clk, CMMSTPCR0, 3, 0), /* KEYSC */ }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_DEV_ID(_id, _clk) { .dev_id = _id, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("r_clk", &r_clk), diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c index c0800d83971e..a06f78dc0f44 100644 --- a/arch/arm/mach-shmobile/clock-sh7372.c +++ b/arch/arm/mach-shmobile/clock-sh7372.c @@ -561,10 +561,6 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP403] = MSTP(&r_clk, SMSTPCR4, 3, 0), /* KEYSC */ }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_DEV_ID(_id, _clk) { .dev_id = _id, .clk = _clk } -#define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("dv_clki_div2_clk", &sh7372_dv_clki_div2_clk), diff --git a/arch/arm/mach-shmobile/clock-sh7377.c b/arch/arm/mach-shmobile/clock-sh7377.c index 95942466e63f..8cee7b151ae3 100644 --- a/arch/arm/mach-shmobile/clock-sh7377.c +++ b/arch/arm/mach-shmobile/clock-sh7377.c @@ -267,9 +267,6 @@ static struct clk mstp_clks[] = { [MSTP403] = MSTP(&r_clk, SMSTPCR4, 3, 0), /* KEYSC */ }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_DEV_ID(_id, _clk) { .dev_id = _id, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("r_clk", &r_clk), diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c index bcacb1e8cf85..6db2ccabc2bf 100644 --- a/arch/arm/mach-shmobile/clock-sh73a0.c +++ b/arch/arm/mach-shmobile/clock-sh73a0.c @@ -306,10 +306,6 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP403] = MSTP(&r_clk, SMSTPCR4, 3, 0), /* KEYSC */ }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_DEV_ID(_id, _clk) { .dev_id = _id, .clk = _clk } -#define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("r_clk", &r_clk), diff --git a/arch/sh/boards/mach-highlander/setup.c b/arch/sh/boards/mach-highlander/setup.c index 87618c91d178..74b8db1b74a9 100644 --- a/arch/sh/boards/mach-highlander/setup.c +++ b/arch/sh/boards/mach-highlander/setup.c @@ -335,8 +335,6 @@ static struct clk *r7780rp_clocks[] = { &ivdr_clk, }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("ivdr_clk", &ivdr_clk), diff --git a/arch/sh/kernel/cpu/clock-cpg.c b/arch/sh/kernel/cpu/clock-cpg.c index 8f63a264a842..f59b1f30d44b 100644 --- a/arch/sh/kernel/cpu/clock-cpg.c +++ b/arch/sh/kernel/cpu/clock-cpg.c @@ -35,8 +35,6 @@ static struct clk *onchip_clocks[] = { &cpu_clk, }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("master_clk", &master_clk), diff --git a/arch/sh/kernel/cpu/sh4/clock-sh4-202.c b/arch/sh/kernel/cpu/sh4/clock-sh4-202.c index 3f6f8e98635c..f4e262adb39e 100644 --- a/arch/sh/kernel/cpu/sh4/clock-sh4-202.c +++ b/arch/sh/kernel/cpu/sh4/clock-sh4-202.c @@ -147,8 +147,6 @@ static struct clk *sh4202_onchip_clocks[] = { &sh4202_shoc_clk, }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("emi_clk", &sh4202_emi_clk), diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7343.c b/arch/sh/kernel/cpu/sh4a/clock-sh7343.c index 16e151f2d769..70e45bdaadc7 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7343.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7343.c @@ -194,10 +194,6 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP200] = MSTP(&div4_clks[DIV4_B], MSTPCR2, 0, 0), }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_DEV_ID(_id, _clk) { .dev_id = _id, .clk = _clk } -#define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("rclk", &r_clk), diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7366.c b/arch/sh/kernel/cpu/sh4a/clock-sh7366.c index 092abfe8b482..3c3165000c52 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7366.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7366.c @@ -192,10 +192,6 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP200] = MSTP(&div4_clks[DIV4_B], MSTPCR2, 0, 0), }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_DEV_ID(_id, _clk) { .dev_id = _id, .clk = _clk } -#define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("rclk", &r_clk), diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7722.c b/arch/sh/kernel/cpu/sh4a/clock-sh7722.c index d39fcfb1917a..c9a48088ad47 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7722.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7722.c @@ -175,10 +175,6 @@ static struct clk mstp_clks[HWBLK_NR] = { SH_HWBLK_CLK(HWBLK_LCDC, &div4_clks[DIV4_P], 0), }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_DEV_ID(_id, _clk) { .dev_id = _id, .clk = _clk } -#define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("rclk", &r_clk), diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7723.c b/arch/sh/kernel/cpu/sh4a/clock-sh7723.c index 7f708999f647..3cc3827380e3 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7723.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7723.c @@ -200,9 +200,6 @@ static struct clk mstp_clks[] = { SH_HWBLK_CLK(HWBLK_LCDC, &div4_clks[DIV4_B], 0), }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_DEV_ID(_id, _clk) { .dev_id = _id, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("rclk", &r_clk), diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7724.c b/arch/sh/kernel/cpu/sh4a/clock-sh7724.c index 0891876ffd0f..8668f557e0ac 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7724.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7724.c @@ -252,10 +252,6 @@ static struct clk mstp_clks[HWBLK_NR] = { SH_HWBLK_CLK(HWBLK_LCDC, &div4_clks[DIV4_B], 0), }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_DEV_ID(_id, _clk) { .dev_id = _id, .clk = _clk } -#define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("rclk", &r_clk), diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c index 86bf188ce1f7..3b097b09a3ba 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c @@ -101,9 +101,6 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP220] = SH_CLK_MSTP32(&div4_clks[DIV4_P], MSTPCR2, 20, 0), }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("extal", &extal_clk), diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7763.c b/arch/sh/kernel/cpu/sh4a/clock-sh7763.c index 599630fc4d3b..2d4c7fd79c02 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7763.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7763.c @@ -91,8 +91,6 @@ static struct clk *sh7763_onchip_clocks[] = { &sh7763_shyway_clk, }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("shyway_clk", &sh7763_shyway_clk), diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7780.c b/arch/sh/kernel/cpu/sh4a/clock-sh7780.c index 8894926479a6..3b53348fe2fc 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7780.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7780.c @@ -97,8 +97,6 @@ static struct clk *sh7780_onchip_clocks[] = { &sh7780_shyway_clk, }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("shyway_clk", &sh7780_shyway_clk), diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7785.c b/arch/sh/kernel/cpu/sh4a/clock-sh7785.c index 16ad25ce016e..e5b420cc1265 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7785.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7785.c @@ -116,9 +116,6 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP100] = SH_CLK_MSTP32(NULL, MSTPCR1, 0, 0), }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("extal", &extal_clk), diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7786.c b/arch/sh/kernel/cpu/sh4a/clock-sh7786.c index 5a5d209309c8..f6c0c3d5599f 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7786.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7786.c @@ -125,9 +125,6 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP102] = SH_CLK_MSTP32(NULL, MSTPCR1, 2, 0), }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("extal", &extal_clk), diff --git a/arch/sh/kernel/cpu/sh4a/clock-shx3.c b/arch/sh/kernel/cpu/sh4a/clock-shx3.c index a9ba4f1851d1..bf2d00b8b908 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-shx3.c +++ b/arch/sh/kernel/cpu/sh4a/clock-shx3.c @@ -100,9 +100,6 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP104] = SH_CLK_MSTP32(NULL, MSTPCR1, 4, 0), }; -#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } -#define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk } - static struct clk_lookup lookups[] = { /* main clocks */ CLKDEV_CON_ID("extal", &extal_clk), diff --git a/include/linux/sh_clk.h b/include/linux/sh_clk.h index 9a52f72527dc..3ccf18648d0a 100644 --- a/include/linux/sh_clk.h +++ b/include/linux/sh_clk.h @@ -147,4 +147,8 @@ int sh_clk_div4_reparent_register(struct clk *clks, int nr, int sh_clk_div6_register(struct clk *clks, int nr); int sh_clk_div6_reparent_register(struct clk *clks, int nr); +#define CLKDEV_CON_ID(_id, _clk) { .con_id = _id, .clk = _clk } +#define CLKDEV_DEV_ID(_id, _clk) { .dev_id = _id, .clk = _clk } +#define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk } + #endif /* __SH_CLOCK_H */ -- cgit v1.2.3 From eccddd32ced0df8f9130024157bf8d37df860d76 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:20 +0800 Subject: ACPI, APEI, Add APEI bit support in generic _OSC call In APEI firmware first mode, hardware error is reported by hardware to firmware firstly, then firmware reports the error to Linux in a GHES error record via POLL/SCI/IRQ/NMI etc. This may result in some issues if OS has no full APEI support. So some firmware implementation will work in a back-compatible mode by default. Where firmware will only notify OS in old-fashion, without GHES record. For example, for a fatal hardware error, only NMI is signaled, no GHES record. To gain full APEI power on these machines, APEI bit in generic _OSC call can be specified to tell firmware that Linux has full APEI support. This patch adds the APEI bit support in generic _OSC call. Signed-off-by: Huang Ying Reviewed-by: Andi Kleen Reviewed-by: Matthew Garrett Signed-off-by: Len Brown --- drivers/acpi/bus.c | 16 ++++++++++++++-- include/linux/acpi.h | 2 ++ 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index d1e06c182cdb..43ce3b0c4921 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -519,6 +520,7 @@ out_kfree: } EXPORT_SYMBOL(acpi_run_osc); +bool osc_sb_apei_support_acked; static u8 sb_uuid_str[] = "0811B06E-4A27-44F9-8D60-3CBBC22E7B48"; static void acpi_bus_osc_support(void) { @@ -541,11 +543,21 @@ static void acpi_bus_osc_support(void) #if defined(CONFIG_ACPI_PROCESSOR) || defined(CONFIG_ACPI_PROCESSOR_MODULE) capbuf[OSC_SUPPORT_TYPE] |= OSC_SB_PPC_OST_SUPPORT; #endif + +#ifdef CONFIG_ACPI_APEI_GHES + if (!ghes_disable) + capbuf[OSC_SUPPORT_TYPE] |= OSC_SB_APEI_SUPPORT; +#endif if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle))) return; - if (ACPI_SUCCESS(acpi_run_osc(handle, &context))) + if (ACPI_SUCCESS(acpi_run_osc(handle, &context))) { + u32 *capbuf_ret = context.ret.pointer; + if (context.ret.length > OSC_SUPPORT_TYPE) + osc_sb_apei_support_acked = + capbuf_ret[OSC_SUPPORT_TYPE] & OSC_SB_APEI_SUPPORT; kfree(context.ret.pointer); - /* do we need to check the returned cap? Sounds no */ + } + /* do we need to check other returned cap? Sounds no */ } /* -------------------------------------------------------------------------- diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1deb2a73c2da..e19527de6a93 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -280,6 +280,8 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_CPUHP_OST_SUPPORT 8 #define OSC_SB_APEI_SUPPORT 16 +extern bool osc_sb_apei_support_acked; + /* PCI defined _OSC bits */ /* _OSC DW1 Definition (OS Support Fields) */ #define OSC_EXT_PCI_CONFIG_SUPPORT 1 -- cgit v1.2.3 From 3baef940f289f08e4aada1fd481ab9ee3f070144 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 22 Jul 2011 14:04:56 -0700 Subject: ioat: Adding PCI IDs for IOAT devices on SandyBridge platforms Adding to pci_id.h and the device table for ioat. Signed-off-by: Dave Jiang Signed-off-by: Dan Williams --- drivers/dma/ioat/pci.c | 11 +++++++++++ include/linux/pci_ids.h | 10 ++++++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma/ioat/pci.c b/drivers/dma/ioat/pci.c index fab37d1cf48d..5e3a40f79945 100644 --- a/drivers/dma/ioat/pci.c +++ b/drivers/dma/ioat/pci.c @@ -72,6 +72,17 @@ static struct pci_device_id ioat_pci_tbl[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF8) }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF9) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB0) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB1) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB2) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB3) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB4) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB5) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB6) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB7) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB8) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB9) }, + { 0, } }; MODULE_DEVICE_TABLE(pci, ioat_pci_tbl); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index f8910e155566..a8571b36ae97 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2699,6 +2699,16 @@ #define PCI_DEVICE_ID_INTEL_ICH10_5 0x3a60 #define PCI_DEVICE_ID_INTEL_5_3400_SERIES_LPC_MIN 0x3b00 #define PCI_DEVICE_ID_INTEL_5_3400_SERIES_LPC_MAX 0x3b1f +#define PCI_DEVICE_ID_INTEL_IOAT_SNB0 0x3c20 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB1 0x3c21 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB2 0x3c22 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB3 0x3c23 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB4 0x3c24 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB5 0x3c25 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB6 0x3c26 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB7 0x3c27 +#define PCI_DEVICE_ID_INTEL_IOAT_SNB8 0x3c2e +#define PCI_DEVICE_ID_INTEL_IOAT_SNB9 0x3c2f #define PCI_DEVICE_ID_INTEL_IOAT_SNB 0x402f #define PCI_DEVICE_ID_INTEL_5100_16 0x65f0 #define PCI_DEVICE_ID_INTEL_5100_21 0x65f5 -- cgit v1.2.3 From 638c1fd3033c76778e6d9975ad8a4a9cdd5b96d9 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Thu, 21 Jul 2011 16:57:52 -0400 Subject: pstore: Extend API for more flexibility in new backends Some pstore implementations may not have a static context, so extend the API to pass the pstore_info struct to all calls and allow for a context pointer. Signed-off-by: Matthew Garrett Signed-off-by: Tony Luck --- drivers/acpi/apei/erst.c | 18 +++++++++++++----- fs/pstore/inode.c | 10 +++++----- fs/pstore/internal.h | 2 +- fs/pstore/platform.c | 13 +++++++------ include/linux/pstore.h | 8 +++++--- 5 files changed, 31 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index e6cef8e1b534..de3ae92adaa5 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -932,8 +932,10 @@ static int erst_check_table(struct acpi_table_erst *erst_tab) static int erst_open_pstore(struct pstore_info *psi); static int erst_close_pstore(struct pstore_info *psi); static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, - struct timespec *time); -static u64 erst_writer(enum pstore_type_id type, size_t size); + struct timespec *time, struct pstore_info *psi); +static u64 erst_writer(enum pstore_type_id type, size_t size, + struct pstore_info *psi); +static int erst_clearer(u64 id, struct pstore_info *psi); static struct pstore_info erst_info = { .owner = THIS_MODULE, @@ -942,7 +944,7 @@ static struct pstore_info erst_info = { .close = erst_close_pstore, .read = erst_reader, .write = erst_writer, - .erase = erst_clear + .erase = erst_clearer }; #define CPER_CREATOR_PSTORE \ @@ -983,7 +985,7 @@ static int erst_close_pstore(struct pstore_info *psi) } static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, - struct timespec *time) + struct timespec *time, struct pstore_info *psi) { int rc; ssize_t len = 0; @@ -1037,7 +1039,8 @@ out: return (rc < 0) ? rc : (len - sizeof(*rcd)); } -static u64 erst_writer(enum pstore_type_id type, size_t size) +static u64 erst_writer(enum pstore_type_id type, size_t size, + struct pstore_info *psi) { struct cper_pstore_record *rcd = (struct cper_pstore_record *) (erst_info.buf - sizeof(*rcd)); @@ -1080,6 +1083,11 @@ static u64 erst_writer(enum pstore_type_id type, size_t size) return rcd->hdr.record_id; } +static int erst_clearer(u64 id, struct pstore_info *psi) +{ + return erst_clear(id); +} + static int __init erst_init(void) { int rc = 0; diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 977ed2723845..b19884a1ba77 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -40,7 +40,7 @@ struct pstore_private { u64 id; - int (*erase)(u64); + struct pstore_info *psi; ssize_t size; char data[]; }; @@ -73,7 +73,7 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry) { struct pstore_private *p = dentry->d_inode->i_private; - p->erase(p->id); + p->psi->erase(p->id, p->psi); return simple_unlink(dir, dentry); } @@ -175,8 +175,8 @@ int pstore_is_mounted(void) * Set the mtime & ctime to the date that this record was originally stored. */ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, - char *data, size_t size, - struct timespec time, int (*erase)(u64)) + char *data, size_t size, struct timespec time, + struct pstore_info *psi) { struct dentry *root = pstore_sb->s_root; struct dentry *dentry; @@ -193,7 +193,7 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, if (!private) goto fail_alloc; private->id = id; - private->erase = erase; + private->psi = psi; switch (type) { case PSTORE_TYPE_DMESG: diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index 8c9f23eb1645..611c1b3c46fa 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -2,5 +2,5 @@ extern void pstore_set_kmsg_bytes(int); extern void pstore_get_records(void); extern int pstore_mkfile(enum pstore_type_id, char *psname, u64 id, char *data, size_t size, - struct timespec time, int (*erase)(u64)); + struct timespec time, struct pstore_info *psi); extern int pstore_is_mounted(void); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index f2c3ff20ea68..221c04e5e333 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -94,11 +94,12 @@ static void pstore_dump(struct kmsg_dumper *dumper, memcpy(dst, s1 + s1_start, l1_cpy); memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy); - id = psinfo->write(PSTORE_TYPE_DMESG, hsize + l1_cpy + l2_cpy); + id = psinfo->write(PSTORE_TYPE_DMESG, hsize + l1_cpy + l2_cpy, + psinfo); if (reason == KMSG_DUMP_OOPS && pstore_is_mounted()) pstore_mkfile(PSTORE_TYPE_DMESG, psinfo->name, id, psinfo->buf, hsize + l1_cpy + l2_cpy, - CURRENT_TIME, psinfo->erase); + CURRENT_TIME, psinfo); l1 -= l1_cpy; l2 -= l2_cpy; total += l1_cpy + l2_cpy; @@ -166,9 +167,9 @@ void pstore_get_records(void) if (rc) goto out; - while ((size = psi->read(&id, &type, &time)) > 0) { + while ((size = psi->read(&id, &type, &time, psi)) > 0) { if (pstore_mkfile(type, psi->name, id, psi->buf, (size_t)size, - time, psi->erase)) + time, psi)) failed++; } psi->close(psi); @@ -196,10 +197,10 @@ int pstore_write(enum pstore_type_id type, char *buf, size_t size) mutex_lock(&psinfo->buf_mutex); memcpy(psinfo->buf, buf, size); - id = psinfo->write(type, size); + id = psinfo->write(type, size, psinfo); if (pstore_is_mounted()) pstore_mkfile(PSTORE_TYPE_DMESG, psinfo->name, id, psinfo->buf, - size, CURRENT_TIME, psinfo->erase); + size, CURRENT_TIME, psinfo); mutex_unlock(&psinfo->buf_mutex); return 0; diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 2455ef2683f0..b2f1d97f6909 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -38,9 +38,11 @@ struct pstore_info { int (*open)(struct pstore_info *psi); int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, - struct timespec *time); - u64 (*write)(enum pstore_type_id type, size_t size); - int (*erase)(u64 id); + struct timespec *time, struct pstore_info *psi); + u64 (*write)(enum pstore_type_id type, size_t size, + struct pstore_info *psi); + int (*erase)(u64 id, struct pstore_info *psi); + void *data; }; #ifdef CONFIG_PSTORE -- cgit v1.2.3 From 56280682ceeef74b692b3e21d1872049eea7c887 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Thu, 21 Jul 2011 16:57:53 -0400 Subject: pstore: Add extra context for writes and erases EFI only provides small amounts of individual storage, and conventionally puts metadata in the storage variable name. Rather than add a metadata header to the (already limited) variable storage, it's easier for us to modify pstore to pass all the information we need to construct a unique variable name to the appropriate functions. Signed-off-by: Matthew Garrett Signed-off-by: Tony Luck --- drivers/acpi/apei/erst.c | 10 ++++++---- fs/pstore/inode.c | 6 ++++-- fs/pstore/platform.c | 9 +++++---- include/linux/pstore.h | 5 +++-- 4 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index de3ae92adaa5..d842ac4f8cfe 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -933,9 +933,10 @@ static int erst_open_pstore(struct pstore_info *psi); static int erst_close_pstore(struct pstore_info *psi); static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, struct timespec *time, struct pstore_info *psi); -static u64 erst_writer(enum pstore_type_id type, size_t size, +static u64 erst_writer(enum pstore_type_id type, int part, size_t size, struct pstore_info *psi); -static int erst_clearer(u64 id, struct pstore_info *psi); +static int erst_clearer(enum pstore_type_id type, u64 id, + struct pstore_info *psi); static struct pstore_info erst_info = { .owner = THIS_MODULE, @@ -1039,7 +1040,7 @@ out: return (rc < 0) ? rc : (len - sizeof(*rcd)); } -static u64 erst_writer(enum pstore_type_id type, size_t size, +static u64 erst_writer(enum pstore_type_id type, int part, size_t size, struct pstore_info *psi) { struct cper_pstore_record *rcd = (struct cper_pstore_record *) @@ -1083,7 +1084,8 @@ static u64 erst_writer(enum pstore_type_id type, size_t size, return rcd->hdr.record_id; } -static int erst_clearer(u64 id, struct pstore_info *psi) +static int erst_clearer(enum pstore_type_id type, u64 id, + struct pstore_info *psi) { return erst_clear(id); } diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index b19884a1ba77..893b961dcfd8 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -39,8 +39,9 @@ #define PSTORE_NAMELEN 64 struct pstore_private { - u64 id; struct pstore_info *psi; + enum pstore_type_id type; + u64 id; ssize_t size; char data[]; }; @@ -73,7 +74,7 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry) { struct pstore_private *p = dentry->d_inode->i_private; - p->psi->erase(p->id, p->psi); + p->psi->erase(p->type, p->id, p->psi); return simple_unlink(dir, dentry); } @@ -192,6 +193,7 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, private = kmalloc(sizeof *private + size, GFP_KERNEL); if (!private) goto fail_alloc; + private->type = type; private->id = id; private->psi = psi; diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 221c04e5e333..163bb40511e7 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -78,7 +78,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, oopscount++; while (total < kmsg_bytes) { dst = psinfo->buf; - hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part++); + hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part); size = psinfo->bufsize - hsize; dst += hsize; @@ -94,8 +94,8 @@ static void pstore_dump(struct kmsg_dumper *dumper, memcpy(dst, s1 + s1_start, l1_cpy); memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy); - id = psinfo->write(PSTORE_TYPE_DMESG, hsize + l1_cpy + l2_cpy, - psinfo); + id = psinfo->write(PSTORE_TYPE_DMESG, part, + hsize + l1_cpy + l2_cpy, psinfo); if (reason == KMSG_DUMP_OOPS && pstore_is_mounted()) pstore_mkfile(PSTORE_TYPE_DMESG, psinfo->name, id, psinfo->buf, hsize + l1_cpy + l2_cpy, @@ -103,6 +103,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, l1 -= l1_cpy; l2 -= l2_cpy; total += l1_cpy + l2_cpy; + part++; } mutex_unlock(&psinfo->buf_mutex); } @@ -197,7 +198,7 @@ int pstore_write(enum pstore_type_id type, char *buf, size_t size) mutex_lock(&psinfo->buf_mutex); memcpy(psinfo->buf, buf, size); - id = psinfo->write(type, size, psinfo); + id = psinfo->write(type, 0, size, psinfo); if (pstore_is_mounted()) pstore_mkfile(PSTORE_TYPE_DMESG, psinfo->name, id, psinfo->buf, size, CURRENT_TIME, psinfo); diff --git a/include/linux/pstore.h b/include/linux/pstore.h index b2f1d97f6909..12be8f193d09 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -39,9 +39,10 @@ struct pstore_info { int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, struct timespec *time, struct pstore_info *psi); - u64 (*write)(enum pstore_type_id type, size_t size, + u64 (*write)(enum pstore_type_id type, int part, + size_t size, struct pstore_info *psi); + int (*erase)(enum pstore_type_id type, u64 id, struct pstore_info *psi); - int (*erase)(u64 id, struct pstore_info *psi); void *data; }; -- cgit v1.2.3 From b94fdd077eef5e6cab56836bf62695b497946716 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Thu, 21 Jul 2011 16:57:54 -0400 Subject: pstore: Make "part" unsigned We'll never have a negative part, so just make this an unsigned int. Signed-off-by: Matthew Garrett Signed-off-by: Tony Luck --- drivers/acpi/apei/erst.c | 8 ++++---- fs/pstore/platform.c | 3 ++- include/linux/pstore.h | 2 +- 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index d842ac4f8cfe..6053f4780df9 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -933,8 +933,8 @@ static int erst_open_pstore(struct pstore_info *psi); static int erst_close_pstore(struct pstore_info *psi); static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, struct timespec *time, struct pstore_info *psi); -static u64 erst_writer(enum pstore_type_id type, int part, size_t size, - struct pstore_info *psi); +static u64 erst_writer(enum pstore_type_id type, unsigned int part, + size_t size, struct pstore_info *psi); static int erst_clearer(enum pstore_type_id type, u64 id, struct pstore_info *psi); @@ -1040,8 +1040,8 @@ out: return (rc < 0) ? rc : (len - sizeof(*rcd)); } -static u64 erst_writer(enum pstore_type_id type, int part, size_t size, - struct pstore_info *psi) +static u64 erst_writer(enum pstore_type_id type, unsigned int part, + size_t size, struct pstore_info *psi) { struct cper_pstore_record *rcd = (struct cper_pstore_record *) (erst_info.buf - sizeof(*rcd)); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 163bb40511e7..49ff1de2178a 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -67,7 +67,8 @@ static void pstore_dump(struct kmsg_dumper *dumper, unsigned long size, total = 0; char *dst, *why; u64 id; - int hsize, part = 1; + int hsize; + unsigned int part = 1; if (reason < ARRAY_SIZE(reason_str)) why = reason_str[reason]; diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 12be8f193d09..cc03bbf5c4b8 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -39,7 +39,7 @@ struct pstore_info { int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, struct timespec *time, struct pstore_info *psi); - u64 (*write)(enum pstore_type_id type, int part, + u64 (*write)(enum pstore_type_id type, unsigned int part, size_t size, struct pstore_info *psi); int (*erase)(enum pstore_type_id type, u64 id, struct pstore_info *psi); -- cgit v1.2.3 From 5ee9c198a4208d7760275d48e4c4f6c89dcd2ef0 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Thu, 21 Jul 2011 16:57:56 -0400 Subject: efi: Add support for using efivars as a pstore backend EFI provides an area of nonvolatile storage managed by the firmware. We can use this as a pstore backend to maintain copies of oopses, aiding diagnosis. Signed-off-by: Matthew Garrett Signed-off-by: Tony Luck --- drivers/firmware/efivars.c | 191 ++++++++++++++++++++++++++++++++++++++++++++- include/linux/efi.h | 6 ++ 2 files changed, 195 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c index 5f29aafd4462..2bbb22670d2d 100644 --- a/drivers/firmware/efivars.c +++ b/drivers/firmware/efivars.c @@ -78,6 +78,7 @@ #include #include #include +#include #include @@ -89,6 +90,8 @@ MODULE_DESCRIPTION("sysfs interface to EFI Variables"); MODULE_LICENSE("GPL"); MODULE_VERSION(EFIVARS_VERSION); +#define DUMP_NAME_LEN 52 + /* * The maximum size of VariableName + Data = 1024 * Therefore, it's reasonable to save that much @@ -161,18 +164,28 @@ utf8_strsize(efi_char16_t *data, unsigned long maxlength) } static efi_status_t -get_var_data(struct efivars *efivars, struct efi_variable *var) +get_var_data_locked(struct efivars *efivars, struct efi_variable *var) { efi_status_t status; - spin_lock(&efivars->lock); var->DataSize = 1024; status = efivars->ops->get_variable(var->VariableName, &var->VendorGuid, &var->Attributes, &var->DataSize, var->Data); + return status; +} + +static efi_status_t +get_var_data(struct efivars *efivars, struct efi_variable *var) +{ + efi_status_t status; + + spin_lock(&efivars->lock); + status = get_var_data_locked(efivars, var); spin_unlock(&efivars->lock); + if (status != EFI_SUCCESS) { printk(KERN_WARNING "efivars: get_variable() failed 0x%lx!\n", status); @@ -387,12 +400,176 @@ static struct kobj_type efivar_ktype = { .default_attrs = def_attrs, }; +static struct pstore_info efi_pstore_info; + static inline void efivar_unregister(struct efivar_entry *var) { kobject_put(&var->kobj); } +#ifdef CONFIG_PSTORE + +static int efi_pstore_open(struct pstore_info *psi) +{ + struct efivars *efivars = psi->data; + + spin_lock(&efivars->lock); + efivars->walk_entry = list_first_entry(&efivars->list, + struct efivar_entry, list); + return 0; +} + +static int efi_pstore_close(struct pstore_info *psi) +{ + struct efivars *efivars = psi->data; + + spin_unlock(&efivars->lock); + return 0; +} + +static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type, + struct timespec *timespec, struct pstore_info *psi) +{ + efi_guid_t vendor = LINUX_EFI_CRASH_GUID; + struct efivars *efivars = psi->data; + char name[DUMP_NAME_LEN]; + int i; + unsigned int part, size; + unsigned long time; + + while (&efivars->walk_entry->list != &efivars->list) { + if (!efi_guidcmp(efivars->walk_entry->var.VendorGuid, + vendor)) { + for (i = 0; i < DUMP_NAME_LEN; i++) { + name[i] = efivars->walk_entry->var.VariableName[i]; + } + if (sscanf(name, "dump-type%u-%u-%lu", type, &part, &time) == 3) { + *id = part; + timespec->tv_sec = time; + timespec->tv_nsec = 0; + get_var_data_locked(efivars, &efivars->walk_entry->var); + size = efivars->walk_entry->var.DataSize; + memcpy(psi->buf, efivars->walk_entry->var.Data, size); + efivars->walk_entry = list_entry(efivars->walk_entry->list.next, + struct efivar_entry, list); + return size; + } + } + efivars->walk_entry = list_entry(efivars->walk_entry->list.next, + struct efivar_entry, list); + } + return 0; +} + +static u64 efi_pstore_write(enum pstore_type_id type, unsigned int part, + size_t size, struct pstore_info *psi) +{ + char name[DUMP_NAME_LEN]; + char stub_name[DUMP_NAME_LEN]; + efi_char16_t efi_name[DUMP_NAME_LEN]; + efi_guid_t vendor = LINUX_EFI_CRASH_GUID; + struct efivars *efivars = psi->data; + struct efivar_entry *entry, *found = NULL; + int i; + + sprintf(stub_name, "dump-type%u-%u-", type, part); + sprintf(name, "%s%lu", stub_name, get_seconds()); + + spin_lock(&efivars->lock); + + for (i = 0; i < DUMP_NAME_LEN; i++) + efi_name[i] = stub_name[i]; + + /* + * Clean up any entries with the same name + */ + + list_for_each_entry(entry, &efivars->list, list) { + get_var_data_locked(efivars, &entry->var); + + for (i = 0; i < DUMP_NAME_LEN; i++) { + if (efi_name[i] == 0) { + found = entry; + efivars->ops->set_variable(entry->var.VariableName, + &entry->var.VendorGuid, + EFI_VARIABLE_NON_VOLATILE | EFI_VARIABLE_BOOTSERVICE_ACCESS | EFI_VARIABLE_RUNTIME_ACCESS, + 0, NULL); + break; + } else if (efi_name[i] != entry->var.VariableName[i]) { + break; + } + } + } + + if (found) + list_del(&found->list); + + for (i = 0; i < DUMP_NAME_LEN; i++) + efi_name[i] = name[i]; + + efivars->ops->set_variable(efi_name, &vendor, + EFI_VARIABLE_NON_VOLATILE | EFI_VARIABLE_BOOTSERVICE_ACCESS | EFI_VARIABLE_RUNTIME_ACCESS, + size, psi->buf); + + spin_unlock(&efivars->lock); + + if (found) + efivar_unregister(found); + + if (size) + efivar_create_sysfs_entry(efivars, utf8_strsize(efi_name, DUMP_NAME_LEN * 2), + efi_name, &vendor); + + return part; +}; + +static int efi_pstore_erase(enum pstore_type_id type, u64 id, + struct pstore_info *psi) +{ + efi_pstore_write(type, id, 0, psi); + + return 0; +} +#else +static int efi_pstore_open(struct pstore_info *psi) +{ + return 0; +} + +static int efi_pstore_close(struct pstore_info *psi) +{ + return 0; +} + +static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type, + struct timespec *time, struct pstore_info *psi) +{ + return -1; +} + +static u64 efi_pstore_write(enum pstore_type_id type, int part, size_t size, + struct pstore_info *psi) +{ + return 0; +} + +static int efi_pstore_erase(enum pstore_type_id type, u64 id, + struct pstore_info *psi) +{ + return 0; +} +#endif + +static struct pstore_info efi_pstore_info = { + .owner = THIS_MODULE, + .name = "efi", + .open = efi_pstore_open, + .close = efi_pstore_close, + .read = efi_pstore_read, + .write = efi_pstore_write, + .erase = efi_pstore_erase, +}; static ssize_t efivar_create(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, @@ -763,6 +940,16 @@ int register_efivars(struct efivars *efivars, if (error) unregister_efivars(efivars); + efivars->efi_pstore_info = efi_pstore_info; + + efivars->efi_pstore_info.buf = kmalloc(4096, GFP_KERNEL); + if (efivars->efi_pstore_info.buf) { + efivars->efi_pstore_info.bufsize = 1024; + efivars->efi_pstore_info.data = efivars; + mutex_init(&efivars->efi_pstore_info.buf_mutex); + pstore_register(&efivars->efi_pstore_info); + } + out: kfree(variable_name); diff --git a/include/linux/efi.h b/include/linux/efi.h index e376270cd26e..c1f5107338c6 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -211,6 +212,9 @@ typedef efi_status_t efi_set_virtual_address_map_t (unsigned long memory_map_siz #define UV_SYSTEM_TABLE_GUID \ EFI_GUID( 0x3b13a7d4, 0x633e, 0x11dd, 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93 ) +#define LINUX_EFI_CRASH_GUID \ + EFI_GUID( 0xcfc8fc79, 0xbe2e, 0x4ddc, 0x97, 0xf0, 0x9f, 0x98, 0xbf, 0xe2, 0x98, 0xa0 ) + typedef struct { efi_guid_t guid; unsigned long table; @@ -426,6 +430,8 @@ struct efivars { struct kset *kset; struct bin_attribute *new_var, *del_var; const struct efivar_operations *ops; + struct efivar_entry *walk_entry; + struct pstore_info efi_pstore_info; }; int register_efivars(struct efivars *efivars, -- cgit v1.2.3 From b207b4d02beb06059478339bbe4672ba715605d6 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Thu, 21 Jul 2011 17:12:27 +0100 Subject: DMA: PL08x: separately store source/destination slave address Store the source/destination slave address separately into the channel structure. This moves us towards being able to avoid a configuration call each time we use the channel. Acked-by: Linus Walleij Signed-off-by: Russell King Signed-off-by: Vinod Koul --- drivers/dma/amba-pl08x.c | 21 +++++++++------------ include/linux/amba/pl08x.h | 3 ++- 2 files changed, 11 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c index 1c641bfd1826..077ddeefb864 100644 --- a/drivers/dma/amba-pl08x.c +++ b/drivers/dma/amba-pl08x.c @@ -1102,7 +1102,6 @@ static int dma_set_runtime_config(struct dma_chan *chan, struct pl08x_driver_data *pl08x = plchan->host; struct pl08x_channel_data *cd = plchan->cd; enum dma_slave_buswidth addr_width; - dma_addr_t addr; u32 maxburst; u32 cctl = 0; int i; @@ -1113,11 +1112,9 @@ static int dma_set_runtime_config(struct dma_chan *chan, /* Transfer direction */ plchan->runtime_direction = config->direction; if (config->direction == DMA_TO_DEVICE) { - addr = config->dst_addr; addr_width = config->dst_addr_width; maxburst = config->dst_maxburst; } else if (config->direction == DMA_FROM_DEVICE) { - addr = config->src_addr; addr_width = config->src_addr_width; maxburst = config->src_maxburst; } else { @@ -1161,7 +1158,11 @@ static int dma_set_runtime_config(struct dma_chan *chan, cctl |= burst_sizes[i].reg; } - plchan->runtime_addr = addr; + if (plchan->runtime_direction == DMA_FROM_DEVICE) { + plchan->src_addr = config->src_addr; + } else { + plchan->dst_addr = config->dst_addr; + } /* Modify the default channel data to fit PrimeCell request */ cd->cctl = cctl; @@ -1396,19 +1397,13 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg( txd->ccfg |= PL080_FLOW_MEM2PER << PL080_CONFIG_FLOW_CONTROL_SHIFT; txd->cctl |= PL080_CONTROL_SRC_INCR; txd->src_addr = sgl->dma_address; - if (plchan->runtime_addr) - txd->dst_addr = plchan->runtime_addr; - else - txd->dst_addr = plchan->cd->addr; + txd->dst_addr = plchan->dst_addr; src_buses = pl08x->mem_buses; dst_buses = plchan->cd->periph_buses; } else if (direction == DMA_FROM_DEVICE) { txd->ccfg |= PL080_FLOW_PER2MEM << PL080_CONFIG_FLOW_CONTROL_SHIFT; txd->cctl |= PL080_CONTROL_DST_INCR; - if (plchan->runtime_addr) - txd->src_addr = plchan->runtime_addr; - else - txd->src_addr = plchan->cd->addr; + txd->src_addr = plchan->src_addr; txd->dst_addr = sgl->dma_address; src_buses = plchan->cd->periph_buses; dst_buses = pl08x->mem_buses; @@ -1704,6 +1699,8 @@ static int pl08x_dma_init_virtual_channels(struct pl08x_driver_data *pl08x, chan->slave = true; chan->name = pl08x->pd->slave_channels[i].bus_id; chan->cd = &pl08x->pd->slave_channels[i]; + chan->src_addr = chan->cd->addr; + chan->dst_addr = chan->cd->addr; } else { chan->cd = &pl08x->pd->memcpy_channel; chan->name = kasprintf(GFP_KERNEL, "memcpy%d", i); diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 3111385b8ca7..072ab28bbb57 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -173,7 +173,8 @@ struct pl08x_dma_chan { struct tasklet_struct tasklet; char *name; struct pl08x_channel_data *cd; - dma_addr_t runtime_addr; + dma_addr_t src_addr; + dma_addr_t dst_addr; enum dma_data_direction runtime_direction; dma_cookie_t lc; struct list_head pend_list; -- cgit v1.2.3 From f14c426c723634d223344ad820997d92a3e355b6 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Thu, 21 Jul 2011 17:12:47 +0100 Subject: DMA: PL08x: separately store source/destination cctl Store the source/destination cctl values into the channel structure. This moves us towards being able to avoid a configuration call each time we use the channel. Acked-by: Linus Walleij Signed-off-by: Russell King Signed-off-by: Vinod Koul --- drivers/dma/amba-pl08x.c | 30 ++++++++++++++++-------------- include/linux/amba/pl08x.h | 2 ++ 2 files changed, 18 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c index 077ddeefb864..ba617e3f23f8 100644 --- a/drivers/dma/amba-pl08x.c +++ b/drivers/dma/amba-pl08x.c @@ -1095,12 +1095,21 @@ static const struct burst_table burst_sizes[] = { }, }; +static u32 pl08x_cctl(u32 cctl) +{ + cctl &= ~(PL080_CONTROL_SRC_AHB2 | PL080_CONTROL_DST_AHB2 | + PL080_CONTROL_SRC_INCR | PL080_CONTROL_DST_INCR | + PL080_CONTROL_PROT_MASK); + + /* Access the cell in privileged mode, non-bufferable, non-cacheable */ + return cctl | PL080_CONTROL_PROT_SYS; +} + static int dma_set_runtime_config(struct dma_chan *chan, struct dma_slave_config *config) { struct pl08x_dma_chan *plchan = to_pl08x_chan(chan); struct pl08x_driver_data *pl08x = plchan->host; - struct pl08x_channel_data *cd = plchan->cd; enum dma_slave_buswidth addr_width; u32 maxburst; u32 cctl = 0; @@ -1160,13 +1169,12 @@ static int dma_set_runtime_config(struct dma_chan *chan, if (plchan->runtime_direction == DMA_FROM_DEVICE) { plchan->src_addr = config->src_addr; + plchan->src_cctl = pl08x_cctl(cctl); } else { plchan->dst_addr = config->dst_addr; + plchan->dst_cctl = pl08x_cctl(cctl); } - /* Modify the default channel data to fit PrimeCell request */ - cd->cctl = cctl; - dev_dbg(&pl08x->adev->dev, "configured channel %s (%s) for %s, data width %d, " "maxburst %d words, LE, CCTL=0x%08x\n", @@ -1385,24 +1393,16 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg( txd->direction = direction; txd->len = sgl->length; - txd->cctl = plchan->cd->cctl & - ~(PL080_CONTROL_SRC_AHB2 | PL080_CONTROL_DST_AHB2 | - PL080_CONTROL_SRC_INCR | PL080_CONTROL_DST_INCR | - PL080_CONTROL_PROT_MASK); - - /* Access the cell in privileged mode, non-bufferable, non-cacheable */ - txd->cctl |= PL080_CONTROL_PROT_SYS; - if (direction == DMA_TO_DEVICE) { txd->ccfg |= PL080_FLOW_MEM2PER << PL080_CONFIG_FLOW_CONTROL_SHIFT; - txd->cctl |= PL080_CONTROL_SRC_INCR; + txd->cctl = plchan->dst_cctl | PL080_CONTROL_SRC_INCR; txd->src_addr = sgl->dma_address; txd->dst_addr = plchan->dst_addr; src_buses = pl08x->mem_buses; dst_buses = plchan->cd->periph_buses; } else if (direction == DMA_FROM_DEVICE) { txd->ccfg |= PL080_FLOW_PER2MEM << PL080_CONFIG_FLOW_CONTROL_SHIFT; - txd->cctl |= PL080_CONTROL_DST_INCR; + txd->cctl = plchan->src_cctl | PL080_CONTROL_DST_INCR; txd->src_addr = plchan->src_addr; txd->dst_addr = sgl->dma_address; src_buses = plchan->cd->periph_buses; @@ -1701,6 +1701,8 @@ static int pl08x_dma_init_virtual_channels(struct pl08x_driver_data *pl08x, chan->cd = &pl08x->pd->slave_channels[i]; chan->src_addr = chan->cd->addr; chan->dst_addr = chan->cd->addr; + chan->src_cctl = pl08x_cctl(chan->cd->cctl); + chan->dst_cctl = pl08x_cctl(chan->cd->cctl); } else { chan->cd = &pl08x->pd->memcpy_channel; chan->name = kasprintf(GFP_KERNEL, "memcpy%d", i); diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 072ab28bbb57..47cfe31e5c35 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -175,6 +175,8 @@ struct pl08x_dma_chan { struct pl08x_channel_data *cd; dma_addr_t src_addr; dma_addr_t dst_addr; + u32 src_cctl; + u32 dst_cctl; enum dma_data_direction runtime_direction; dma_cookie_t lc; struct list_head pend_list; -- cgit v1.2.3 From fa020e7d046436cb6642b23dc95012a3064d77e2 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Thu, 21 Jul 2011 17:13:07 +0100 Subject: DMA: PL08x: constify plchan->cd and plat->slave_channels We no longer write to the channel data structure, so we can make it const throughout the driver. Acked-by: Linus Walleij Signed-off-by: Russell King Signed-off-by: Vinod Koul --- include/linux/amba/pl08x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 47cfe31e5c35..e6e28f37d8ec 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -172,7 +172,7 @@ struct pl08x_dma_chan { int phychan_hold; struct tasklet_struct tasklet; char *name; - struct pl08x_channel_data *cd; + const struct pl08x_channel_data *cd; dma_addr_t src_addr; dma_addr_t dst_addr; u32 src_cctl; @@ -205,7 +205,7 @@ struct pl08x_dma_chan { * @mem_buses: buses which memory can be accessed from: PL08X_AHB1 | PL08X_AHB2 */ struct pl08x_platform_data { - struct pl08x_channel_data *slave_channels; + const struct pl08x_channel_data *slave_channels; unsigned int num_slave_channels; struct pl08x_channel_data memcpy_channel; int (*get_signal)(struct pl08x_dma_chan *); -- cgit v1.2.3 From 3038bbdf7404ae3948385cbde30df946579d4e3a Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Thu, 28 Jul 2011 16:25:41 +0100 Subject: of/gpio: export of_gpio_simple_xlate Allow GPIO drivers to use of_gpio_simple_xlate. This is useful for the generic GPIO driver for example where gpio_chip is embedded in bgpio_chip and doesn't need of_mm_gpio_chip but has a simple 1:1 GPIO mapping. Cc: Anton Vorontsov Cc: Grant Likely Signed-off-by: Jamie Iles Signed-off-by: Grant Likely --- drivers/of/gpio.c | 5 +++-- include/linux/of_gpio.h | 9 +++++++++ 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/gpio.c b/drivers/of/gpio.c index 3007662ac614..ef0105fa52b1 100644 --- a/drivers/of/gpio.c +++ b/drivers/of/gpio.c @@ -127,8 +127,8 @@ EXPORT_SYMBOL(of_gpio_count); * gpio chips. This function performs only one sanity check: whether gpio * is less than ngpios (that is specified in the gpio_chip). */ -static int of_gpio_simple_xlate(struct gpio_chip *gc, struct device_node *np, - const void *gpio_spec, u32 *flags) +int of_gpio_simple_xlate(struct gpio_chip *gc, struct device_node *np, + const void *gpio_spec, u32 *flags) { const __be32 *gpio = gpio_spec; const u32 n = be32_to_cpup(gpio); @@ -152,6 +152,7 @@ static int of_gpio_simple_xlate(struct gpio_chip *gc, struct device_node *np, return n; } +EXPORT_SYMBOL(of_gpio_simple_xlate); /** * of_mm_gpiochip_add - Add memory mapped GPIO chip (bank) diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index aec8025c786a..52280a2b5e63 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -57,6 +57,8 @@ extern int of_mm_gpiochip_add(struct device_node *np, extern void of_gpiochip_add(struct gpio_chip *gc); extern void of_gpiochip_remove(struct gpio_chip *gc); extern struct gpio_chip *of_node_to_gpiochip(struct device_node *np); +extern int of_gpio_simple_xlate(struct gpio_chip *gc, struct device_node *np, + const void *gpio_spec, u32 *flags); #else /* CONFIG_OF_GPIO */ @@ -72,6 +74,13 @@ static inline unsigned int of_gpio_count(struct device_node *np) return 0; } +static inline int of_gpio_simple_xlate(struct gpio_chip *gc, + struct device_node *np, + const void *gpio_spec, u32 *flags) +{ + return -ENOSYS; +} + static inline void of_gpiochip_add(struct gpio_chip *gc) { } static inline void of_gpiochip_remove(struct gpio_chip *gc) { } -- cgit v1.2.3 From 0c0308066ca53fdf1423895f3a42838b67b3a5a8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 30 Jul 2011 12:45:35 -0400 Subject: NFS: Fix spurious readdir cookie loop messages If the directory contents change, then we have to accept that the file->f_pos value may shrink if we do a 'search-by-cookie'. In that case, we should turn off the loop detection and let the NFS client try to recover. The patch also fixes a second loop detection bug by ensuring that after turning on the ctx->duped flag, we read at least one new cookie into ctx->dir_cookie before attempting to match with ctx->dup_cookie. Reported-by: Petr Vandrovec Cc: stable@kernel.org [2.6.39+] Signed-off-by: Trond Myklebust --- fs/nfs/dir.c | 56 +++++++++++++++++++++++++++++--------------------- include/linux/nfs_fs.h | 3 ++- 2 files changed, 35 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 57f578e2560a..d23108b1e338 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -134,18 +134,19 @@ const struct inode_operations nfs4_dir_inode_operations = { #endif /* CONFIG_NFS_V4 */ -static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct rpc_cred *cred) +static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred) { struct nfs_open_dir_context *ctx; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (ctx != NULL) { ctx->duped = 0; + ctx->attr_gencount = NFS_I(dir)->attr_gencount; ctx->dir_cookie = 0; ctx->dup_cookie = 0; ctx->cred = get_rpccred(cred); - } else - ctx = ERR_PTR(-ENOMEM); - return ctx; + return ctx; + } + return ERR_PTR(-ENOMEM); } static void put_nfs_open_dir_context(struct nfs_open_dir_context *ctx) @@ -173,7 +174,7 @@ nfs_opendir(struct inode *inode, struct file *filp) cred = rpc_lookup_cred(); if (IS_ERR(cred)) return PTR_ERR(cred); - ctx = alloc_nfs_open_dir_context(cred); + ctx = alloc_nfs_open_dir_context(inode, cred); if (IS_ERR(ctx)) { res = PTR_ERR(ctx); goto out; @@ -323,7 +324,6 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri { loff_t diff = desc->file->f_pos - desc->current_index; unsigned int index; - struct nfs_open_dir_context *ctx = desc->file->private_data; if (diff < 0) goto out_eof; @@ -336,7 +336,6 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri index = (unsigned int)diff; *desc->dir_cookie = array->array[index].cookie; desc->cache_entry_index = index; - ctx->duped = 0; return 0; out_eof: desc->eof = 1; @@ -349,14 +348,33 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des int i; loff_t new_pos; int status = -EAGAIN; - struct nfs_open_dir_context *ctx = desc->file->private_data; for (i = 0; i < array->size; i++) { if (array->array[i].cookie == *desc->dir_cookie) { + struct nfs_inode *nfsi = NFS_I(desc->file->f_path.dentry->d_inode); + struct nfs_open_dir_context *ctx = desc->file->private_data; + new_pos = desc->current_index + i; - if (new_pos < desc->file->f_pos) { + if (ctx->attr_gencount != nfsi->attr_gencount + || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))) { + ctx->duped = 0; + ctx->attr_gencount = nfsi->attr_gencount; + } else if (new_pos < desc->file->f_pos) { + if (ctx->duped > 0 + && ctx->dup_cookie == *desc->dir_cookie) { + if (printk_ratelimit()) { + pr_notice("NFS: directory %s/%s contains a readdir loop." + "Please contact your server vendor. " + "Offending cookie: %llu\n", + desc->file->f_dentry->d_parent->d_name.name, + desc->file->f_dentry->d_name.name, + *desc->dir_cookie); + } + status = -ELOOP; + goto out; + } ctx->dup_cookie = *desc->dir_cookie; - ctx->duped = 1; + ctx->duped = -1; } desc->file->f_pos = new_pos; desc->cache_entry_index = i; @@ -368,6 +386,7 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des if (*desc->dir_cookie == array->last_cookie) desc->eof = 1; } +out: return status; } @@ -740,19 +759,6 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent, struct nfs_cache_array *array = NULL; struct nfs_open_dir_context *ctx = file->private_data; - if (ctx->duped != 0 && ctx->dup_cookie == *desc->dir_cookie) { - if (printk_ratelimit()) { - pr_notice("NFS: directory %s/%s contains a readdir loop. " - "Please contact your server vendor. " - "Offending cookie: %llu\n", - file->f_dentry->d_parent->d_name.name, - file->f_dentry->d_name.name, - *desc->dir_cookie); - } - res = -ELOOP; - goto out; - } - array = nfs_readdir_get_array(desc->page); if (IS_ERR(array)) { res = PTR_ERR(array); @@ -774,6 +780,8 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent, *desc->dir_cookie = array->array[i+1].cookie; else *desc->dir_cookie = array->last_cookie; + if (ctx->duped != 0) + ctx->duped = 1; } if (array->eof_index >= 0) desc->eof = 1; @@ -805,6 +813,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent, struct page *page = NULL; int status; struct inode *inode = desc->file->f_path.dentry->d_inode; + struct nfs_open_dir_context *ctx = desc->file->private_data; dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n", (unsigned long long)*desc->dir_cookie); @@ -818,6 +827,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent, desc->page_index = 0; desc->last_cookie = *desc->dir_cookie; desc->page = page; + ctx->duped = 0; status = nfs_readdir_xdr_to_array(desc, page, inode); if (status < 0) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8b579beb6358..b96fb99072ff 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -99,9 +99,10 @@ struct nfs_open_context { struct nfs_open_dir_context { struct rpc_cred *cred; + unsigned long attr_gencount; __u64 dir_cookie; __u64 dup_cookie; - int duped; + signed char duped; }; /* -- cgit v1.2.3 From 1c388919d89ca35741e9c4d3255adf87f76f0c06 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sat, 7 May 2011 20:53:16 +0200 Subject: resources: Add lookup_resource() Add a function to find an existing resource by a resource start address. This allows to implement simple allocators (with a malloc/free-alike API) on top of the resource system. Signed-off-by: Geert Uytterhoeven --- include/linux/ioport.h | 1 + kernel/resource.c | 21 +++++++++++++++++++++ 2 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index e9bb22cba764..63eb429ecbe6 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -132,6 +132,7 @@ extern int allocate_resource(struct resource *root, struct resource *new, resource_size_t, resource_size_t), void *alignf_data); +struct resource *lookup_resource(struct resource *root, resource_size_t start); int adjust_resource(struct resource *res, resource_size_t start, resource_size_t size); resource_size_t resource_alignment(struct resource *res); diff --git a/kernel/resource.c b/kernel/resource.c index 3ff40178dce7..3b3cedc52592 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -553,6 +553,27 @@ int allocate_resource(struct resource *root, struct resource *new, EXPORT_SYMBOL(allocate_resource); +/** + * lookup_resource - find an existing resource by a resource start address + * @root: root resource descriptor + * @start: resource start address + * + * Returns a pointer to the resource if found, NULL otherwise + */ +struct resource *lookup_resource(struct resource *root, resource_size_t start) +{ + struct resource *res; + + read_lock(&resource_lock); + for (res = root->child; res; res = res->sibling) { + if (res->start == start) + break; + } + read_unlock(&resource_lock); + + return res; +} + /* * Insert a resource into the resource tree. If successful, return NULL, * otherwise return the conflicting resource (compare to __request_resource()) -- cgit v1.2.3 From a9bae5666d0510ad69bdb437371c9a3e6b770705 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 30 Jul 2011 20:52:33 -0400 Subject: pnfs: let layoutcommit handle a list of lseg There can be multiple lseg per file, so layoutcommit should be able to handle it. [Needed in v3.0] CC: Stable Tree Signed-off-by: Peng Tao Signed-off-by: Boaz Harrosh Signed-off-by: Jim Rees Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 8 +++++++- fs/nfs/pnfs.c | 32 ++++++++++++++++---------------- fs/nfs/pnfs.h | 2 ++ include/linux/nfs_xdr.h | 2 +- 4 files changed, 26 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 079614deca3f..efa6ae822ca8 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5912,9 +5912,15 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata) static void nfs4_layoutcommit_release(void *calldata) { struct nfs4_layoutcommit_data *data = calldata; + struct pnfs_layout_segment *lseg, *tmp; /* Matched by references in pnfs_set_layoutcommit */ - put_lseg(data->lseg); + list_for_each_entry_safe(lseg, tmp, &data->lseg_list, pls_lc_list) { + list_del_init(&lseg->pls_lc_list); + if (test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, + &lseg->pls_flags)) + put_lseg(lseg); + } put_rpccred(data->cred); kfree(data); } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index ab2cb04f8a28..a7e5f17f7776 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -225,6 +225,7 @@ static void init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg) { INIT_LIST_HEAD(&lseg->pls_list); + INIT_LIST_HEAD(&lseg->pls_lc_list); atomic_set(&lseg->pls_refcount, 1); smp_mb(); set_bit(NFS_LSEG_VALID, &lseg->pls_flags); @@ -1356,16 +1357,17 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages); /* - * Currently there is only one (whole file) write lseg. + * There can be multiple RW segments. */ -static struct pnfs_layout_segment *pnfs_list_write_lseg(struct inode *inode) +static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp) { - struct pnfs_layout_segment *lseg, *rv = NULL; + struct pnfs_layout_segment *lseg; - list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) - if (lseg->pls_range.iomode == IOMODE_RW) - rv = lseg; - return rv; + list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) { + if (lseg->pls_range.iomode == IOMODE_RW && + test_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags)) + list_add(&lseg->pls_lc_list, listp); + } } void @@ -1377,12 +1379,14 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata) spin_lock(&nfsi->vfs_inode.i_lock); if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) { - /* references matched in nfs4_layoutcommit_release */ - get_lseg(wdata->lseg); mark_as_dirty = true; dprintk("%s: Set layoutcommit for inode %lu ", __func__, wdata->inode->i_ino); } + if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &wdata->lseg->pls_flags)) { + /* references matched in nfs4_layoutcommit_release */ + get_lseg(wdata->lseg); + } if (end_pos > nfsi->layout->plh_lwb) nfsi->layout->plh_lwb = end_pos; spin_unlock(&nfsi->vfs_inode.i_lock); @@ -1409,7 +1413,6 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) { struct nfs4_layoutcommit_data *data; struct nfs_inode *nfsi = NFS_I(inode); - struct pnfs_layout_segment *lseg; loff_t end_pos; int status = 0; @@ -1426,17 +1429,15 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) goto out; } + INIT_LIST_HEAD(&data->lseg_list); spin_lock(&inode->i_lock); if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) { spin_unlock(&inode->i_lock); kfree(data); goto out; } - /* - * Currently only one (whole file) write lseg which is referenced - * in pnfs_set_layoutcommit and will be found. - */ - lseg = pnfs_list_write_lseg(inode); + + pnfs_list_write_lseg(inode, &data->lseg_list); end_pos = nfsi->layout->plh_lwb; nfsi->layout->plh_lwb = 0; @@ -1446,7 +1447,6 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) spin_unlock(&inode->i_lock); data->args.inode = inode; - data->lseg = lseg; data->cred = get_rpccred(nfsi->layout->plh_lc_cred); nfs_fattr_init(&data->fattr); data->args.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 1f5cb47e2a2c..b94f874886ca 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -36,10 +36,12 @@ enum { NFS_LSEG_VALID = 0, /* cleared when lseg is recalled/returned */ NFS_LSEG_ROC, /* roc bit received from server */ + NFS_LSEG_LAYOUTCOMMIT, /* layoutcommit bit set for layoutcommit */ }; struct pnfs_layout_segment { struct list_head pls_list; + struct list_head pls_lc_list; struct pnfs_layout_range pls_range; atomic_t pls_refcount; unsigned long pls_flags; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5b115956abac..feb312716c07 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -262,7 +262,7 @@ struct nfs4_layoutcommit_res { struct nfs4_layoutcommit_data { struct rpc_task task; struct nfs_fattr fattr; - struct pnfs_layout_segment *lseg; + struct list_head lseg_list; struct rpc_cred *cred; struct nfs4_layoutcommit_args args; struct nfs4_layoutcommit_res res; -- cgit v1.2.3 From 7f11d8d38d64739e190581e015a2a2730ff54e2a Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Sat, 30 Jul 2011 20:52:35 -0400 Subject: pnfs: GETDEVICELIST The block driver uses GETDEVICELIST Signed-off-by: Andy Adamson [pass struct nfs_server * to getdevicelist] [get machince creds for getdevicelist] [fix getdevicelist decode sizing] Signed-off-by: Benny Halevy Signed-off-by: Benny Halevy Signed-off-by: Jim Rees Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 48 ++++++++++++++++++ fs/nfs/nfs4xdr.c | 131 ++++++++++++++++++++++++++++++++++++++++++++++++ fs/nfs/pnfs.h | 12 +++++ include/linux/nfs4.h | 1 + include/linux/nfs_xdr.h | 11 ++++ 5 files changed, 203 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index efa6ae822ca8..af32d3df0544 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5834,6 +5834,54 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp) return status; } +/* + * Retrieve the list of Data Server devices from the MDS. + */ +static int _nfs4_getdevicelist(struct nfs_server *server, + const struct nfs_fh *fh, + struct pnfs_devicelist *devlist) +{ + struct nfs4_getdevicelist_args args = { + .fh = fh, + .layoutclass = server->pnfs_curr_ld->id, + }; + struct nfs4_getdevicelist_res res = { + .devlist = devlist, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETDEVICELIST], + .rpc_argp = &args, + .rpc_resp = &res, + }; + int status; + + dprintk("--> %s\n", __func__); + status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, + &res.seq_res, 0); + dprintk("<-- %s status=%d\n", __func__, status); + return status; +} + +int nfs4_proc_getdevicelist(struct nfs_server *server, + const struct nfs_fh *fh, + struct pnfs_devicelist *devlist) +{ + struct nfs4_exception exception = { }; + int err; + + do { + err = nfs4_handle_exception(server, + _nfs4_getdevicelist(server, fh, devlist), + &exception); + } while (exception.retry); + + dprintk("%s: err=%d, num_devs=%u\n", __func__, + err, devlist->num_devs); + + return err; +} +EXPORT_SYMBOL_GPL(nfs4_proc_getdevicelist); + static int _nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev) { diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index b851b560a6f8..5f769f8d05b0 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -314,6 +314,17 @@ static int nfs4_stat_to_errno(int); XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) #define encode_reclaim_complete_maxsz (op_encode_hdr_maxsz + 4) #define decode_reclaim_complete_maxsz (op_decode_hdr_maxsz + 4) +#define encode_getdevicelist_maxsz (op_encode_hdr_maxsz + 4 + \ + encode_verifier_maxsz) +#define decode_getdevicelist_maxsz (op_decode_hdr_maxsz + \ + 2 /* nfs_cookie4 gdlr_cookie */ + \ + decode_verifier_maxsz \ + /* verifier4 gdlr_verifier */ + \ + 1 /* gdlr_deviceid_list count */ + \ + XDR_QUADLEN(NFS4_PNFS_GETDEVLIST_MAXNUM * \ + NFS4_DEVICEID4_SIZE) \ + /* gdlr_deviceid_list */ + \ + 1 /* bool gdlr_eof */) #define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + 4 + \ XDR_QUADLEN(NFS4_DEVICEID4_SIZE)) #define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \ @@ -748,6 +759,14 @@ static int nfs4_stat_to_errno(int); #define NFS4_dec_reclaim_complete_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_reclaim_complete_maxsz) +#define NFS4_enc_getdevicelist_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_getdevicelist_maxsz) +#define NFS4_dec_getdevicelist_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_getdevicelist_maxsz) #define NFS4_enc_getdeviceinfo_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz +\ encode_getdeviceinfo_maxsz) @@ -1854,6 +1873,26 @@ static void encode_sequence(struct xdr_stream *xdr, } #ifdef CONFIG_NFS_V4_1 +static void +encode_getdevicelist(struct xdr_stream *xdr, + const struct nfs4_getdevicelist_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + nfs4_verifier dummy = { + .data = "dummmmmy", + }; + + p = reserve_space(xdr, 20); + *p++ = cpu_to_be32(OP_GETDEVICELIST); + *p++ = cpu_to_be32(args->layoutclass); + *p++ = cpu_to_be32(NFS4_PNFS_GETDEVLIST_MAXNUM); + xdr_encode_hyper(p, 0ULL); /* cookie */ + encode_nfs4_verifier(xdr, &dummy); + hdr->nops++; + hdr->replen += decode_getdevicelist_maxsz; +} + static void encode_getdeviceinfo(struct xdr_stream *xdr, const struct nfs4_getdeviceinfo_args *args, @@ -2774,6 +2813,24 @@ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req, encode_nops(&hdr); } +/* + * Encode GETDEVICELIST request + */ +static void nfs4_xdr_enc_getdevicelist(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_getdevicelist_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_getdevicelist(xdr, args, &hdr); + encode_nops(&hdr); +} + /* * Encode GETDEVICEINFO request */ @@ -5268,6 +5325,53 @@ out_overflow: } #if defined(CONFIG_NFS_V4_1) +/* + * TODO: Need to handle case when EOF != true; + */ +static int decode_getdevicelist(struct xdr_stream *xdr, + struct pnfs_devicelist *res) +{ + __be32 *p; + int status, i; + struct nfs_writeverf verftemp; + + status = decode_op_hdr(xdr, OP_GETDEVICELIST); + if (status) + return status; + + p = xdr_inline_decode(xdr, 8 + 8 + 4); + if (unlikely(!p)) + goto out_overflow; + + /* TODO: Skip cookie for now */ + p += 2; + + /* Read verifier */ + p = xdr_decode_opaque_fixed(p, verftemp.verifier, 8); + + res->num_devs = be32_to_cpup(p); + + dprintk("%s: num_dev %d\n", __func__, res->num_devs); + + if (res->num_devs > NFS4_PNFS_GETDEVLIST_MAXNUM) { + printk(KERN_ERR "%s too many result dev_num %u\n", + __func__, res->num_devs); + return -EIO; + } + + p = xdr_inline_decode(xdr, + res->num_devs * NFS4_DEVICEID4_SIZE + 4); + if (unlikely(!p)) + goto out_overflow; + for (i = 0; i < res->num_devs; i++) + p = xdr_decode_opaque_fixed(p, res->dev_id[i].data, + NFS4_DEVICEID4_SIZE); + res->eof = be32_to_cpup(p); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} static int decode_getdeviceinfo(struct xdr_stream *xdr, struct pnfs_device *pdev) @@ -6541,6 +6645,32 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, return status; } +/* + * Decode GETDEVICELIST response + */ +static int nfs4_xdr_dec_getdevicelist(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_getdevicelist_res *res) +{ + struct compound_hdr hdr; + int status; + + dprintk("encoding getdevicelist!\n"); + + status = decode_compound_hdr(xdr, &hdr); + if (status != 0) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status != 0) + goto out; + status = decode_putfh(xdr); + if (status != 0) + goto out; + status = decode_getdevicelist(xdr, res->devlist); +out: + return status; +} + /* * Decode GETDEVINFO response */ @@ -6908,6 +7038,7 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(SECINFO_NO_NAME, enc_secinfo_no_name, dec_secinfo_no_name), PROC(TEST_STATEID, enc_test_stateid, dec_test_stateid), PROC(FREE_STATEID, enc_free_stateid, dec_free_stateid), + PROC(GETDEVICELIST, enc_getdevicelist, dec_getdevicelist), #endif /* CONFIG_NFS_V4_1 */ }; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index b94f874886ca..7074394944a9 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -135,14 +135,26 @@ struct pnfs_device { unsigned int layout_type; unsigned int mincount; struct page **pages; + void *area; unsigned int pgbase; unsigned int pglen; }; +#define NFS4_PNFS_GETDEVLIST_MAXNUM 16 + +struct pnfs_devicelist { + unsigned int eof; + unsigned int num_devs; + struct nfs4_deviceid dev_id[NFS4_PNFS_GETDEVLIST_MAXNUM]; +}; + extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *); extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *); /* nfs4proc.c */ +extern int nfs4_proc_getdevicelist(struct nfs_server *server, + const struct nfs_fh *fh, + struct pnfs_devicelist *devlist); extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *dev); extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp); diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index a3c4bc800dce..76f99e8714f3 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -566,6 +566,7 @@ enum { NFSPROC4_CLNT_SECINFO_NO_NAME, NFSPROC4_CLNT_TEST_STATEID, NFSPROC4_CLNT_FREE_STATEID, + NFSPROC4_CLNT_GETDEVICELIST, }; /* nfs41 types */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index feb312716c07..21f333eae3c8 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -235,6 +235,17 @@ struct nfs4_layoutget { gfp_t gfp_flags; }; +struct nfs4_getdevicelist_args { + const struct nfs_fh *fh; + u32 layoutclass; + struct nfs4_sequence_args seq_args; +}; + +struct nfs4_getdevicelist_res { + struct pnfs_devicelist *devlist; + struct nfs4_sequence_res seq_res; +}; + struct nfs4_getdeviceinfo_args { struct pnfs_device *pdev; struct nfs4_sequence_args seq_args; -- cgit v1.2.3 From dae100c2b1b9463996aab9162f2258145c43f7df Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Sat, 30 Jul 2011 20:52:37 -0400 Subject: pnfs: ask for layout_blksize and save it in nfs_server Block layout needs it to determine IO size. Signed-off-by: Fred Isaman Signed-off-by: Tao Guo Signed-off-by: Benny Halevy Signed-off-by: Benny Halevy Signed-off-by: Jim Rees Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 1 + fs/nfs/nfs4_fs.h | 2 +- fs/nfs/nfs4proc.c | 5 ++- fs/nfs/nfs4xdr.c | 99 +++++++++++++++++++++++++++++++++++++++-------- include/linux/nfs_fs_sb.h | 3 +- include/linux/nfs_xdr.h | 3 +- 6 files changed, 91 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index a9b18483cb24..de00a373f085 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -936,6 +936,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, if (server->wsize > NFS_MAX_FILE_IO_SIZE) server->wsize = NFS_MAX_FILE_IO_SIZE; server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + server->pnfs_blksize = fsinfo->blksize; set_pnfs_layoutdriver(server, mntfh, fsinfo->layouttype); server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 1909ee8be350..1ec1a85fa71c 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -318,7 +318,7 @@ extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[]; extern const u32 nfs4_fattr_bitmap[2]; extern const u32 nfs4_statfs_bitmap[2]; extern const u32 nfs4_pathconf_bitmap[2]; -extern const u32 nfs4_fsinfo_bitmap[2]; +extern const u32 nfs4_fsinfo_bitmap[3]; extern const u32 nfs4_fs_locations_bitmap[2]; /* nfs4renewd.c */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index af32d3df0544..e86de799dd12 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -140,12 +140,13 @@ const u32 nfs4_pathconf_bitmap[2] = { 0 }; -const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE +const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE | FATTR4_WORD0_MAXREAD | FATTR4_WORD0_MAXWRITE | FATTR4_WORD0_LEASE_TIME, FATTR4_WORD1_TIME_DELTA - | FATTR4_WORD1_FS_LAYOUT_TYPES + | FATTR4_WORD1_FS_LAYOUT_TYPES, + FATTR4_WORD2_LAYOUT_BLKSIZE }; const u32 nfs4_fs_locations_bitmap[2] = { diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 5f769f8d05b0..026166993d11 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -113,7 +113,11 @@ static int nfs4_stat_to_errno(int); #define encode_restorefh_maxsz (op_encode_hdr_maxsz) #define decode_restorefh_maxsz (op_decode_hdr_maxsz) #define encode_fsinfo_maxsz (encode_getattr_maxsz) -#define decode_fsinfo_maxsz (op_decode_hdr_maxsz + 15) +/* The 5 accounts for the PNFS attributes, and assumes that at most three + * layout types will be returned. + */ +#define decode_fsinfo_maxsz (op_decode_hdr_maxsz + \ + nfs4_fattr_bitmap_maxsz + 4 + 8 + 5) #define encode_renew_maxsz (op_encode_hdr_maxsz + 3) #define decode_renew_maxsz (op_decode_hdr_maxsz) #define encode_setclientid_maxsz \ @@ -1123,6 +1127,35 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm hdr->replen += decode_getattr_maxsz; } +static void +encode_getattr_three(struct xdr_stream *xdr, + uint32_t bm0, uint32_t bm1, uint32_t bm2, + struct compound_hdr *hdr) +{ + __be32 *p; + + p = reserve_space(xdr, 4); + *p = cpu_to_be32(OP_GETATTR); + if (bm2) { + p = reserve_space(xdr, 16); + *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(bm0); + *p++ = cpu_to_be32(bm1); + *p = cpu_to_be32(bm2); + } else if (bm1) { + p = reserve_space(xdr, 12); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(bm0); + *p = cpu_to_be32(bm1); + } else { + p = reserve_space(xdr, 8); + *p++ = cpu_to_be32(1); + *p = cpu_to_be32(bm0); + } + hdr->nops++; + hdr->replen += decode_getattr_maxsz; +} + static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr) { encode_getattr_two(xdr, bitmask[0] & nfs4_fattr_bitmap[0], @@ -1131,8 +1164,11 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr) { - encode_getattr_two(xdr, bitmask[0] & nfs4_fsinfo_bitmap[0], - bitmask[1] & nfs4_fsinfo_bitmap[1], hdr); + encode_getattr_three(xdr, + bitmask[0] & nfs4_fsinfo_bitmap[0], + bitmask[1] & nfs4_fsinfo_bitmap[1], + bitmask[2] & nfs4_fsinfo_bitmap[2], + hdr); } static void encode_fs_locations(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr) @@ -2643,7 +2679,7 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, struct compound_hdr hdr = { .nops = 0, }; - const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 }; + const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME }; encode_compound_hdr(xdr, req, &hdr); encode_setclientid_confirm(xdr, arg, &hdr); @@ -2787,7 +2823,7 @@ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->la_seq_args), }; - const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 }; + const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME }; encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->la_seq_args, &hdr); @@ -3068,14 +3104,17 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap) goto out_overflow; bmlen = be32_to_cpup(p); - bitmap[0] = bitmap[1] = 0; + bitmap[0] = bitmap[1] = bitmap[2] = 0; p = xdr_inline_decode(xdr, (bmlen << 2)); if (unlikely(!p)) goto out_overflow; if (bmlen > 0) { bitmap[0] = be32_to_cpup(p++); - if (bmlen > 1) - bitmap[1] = be32_to_cpup(p); + if (bmlen > 1) { + bitmap[1] = be32_to_cpup(p++); + if (bmlen > 2) + bitmap[2] = be32_to_cpup(p); + } } return 0; out_overflow: @@ -3107,8 +3146,9 @@ static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint3 return ret; bitmap[0] &= ~FATTR4_WORD0_SUPPORTED_ATTRS; } else - bitmask[0] = bitmask[1] = 0; - dprintk("%s: bitmask=%08x:%08x\n", __func__, bitmask[0], bitmask[1]); + bitmask[0] = bitmask[1] = bitmask[2] = 0; + dprintk("%s: bitmask=%08x:%08x:%08x\n", __func__, + bitmask[0], bitmask[1], bitmask[2]); return 0; } @@ -4162,7 +4202,7 @@ out_overflow: static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res) { __be32 *savep; - uint32_t attrlen, bitmap[2] = {0}; + uint32_t attrlen, bitmap[3] = {0}; int status; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) @@ -4188,7 +4228,7 @@ xdr_error: static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat) { __be32 *savep; - uint32_t attrlen, bitmap[2] = {0}; + uint32_t attrlen, bitmap[3] = {0}; int status; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) @@ -4220,7 +4260,7 @@ xdr_error: static int decode_pathconf(struct xdr_stream *xdr, struct nfs_pathconf *pathconf) { __be32 *savep; - uint32_t attrlen, bitmap[2] = {0}; + uint32_t attrlen, bitmap[3] = {0}; int status; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) @@ -4360,7 +4400,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat { __be32 *savep; uint32_t attrlen, - bitmap[2] = {0}; + bitmap[3] = {0}; int status; status = decode_op_hdr(xdr, OP_GETATTR); @@ -4446,10 +4486,32 @@ static int decode_attr_pnfstype(struct xdr_stream *xdr, uint32_t *bitmap, return status; } +/* + * The prefered block size for layout directed io + */ +static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap, + uint32_t *res) +{ + __be32 *p; + + dprintk("%s: bitmap is %x\n", __func__, bitmap[2]); + *res = 0; + if (bitmap[2] & FATTR4_WORD2_LAYOUT_BLKSIZE) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) { + print_overflow_msg(__func__, xdr); + return -EIO; + } + *res = be32_to_cpup(p); + bitmap[2] &= ~FATTR4_WORD2_LAYOUT_BLKSIZE; + } + return 0; +} + static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) { __be32 *savep; - uint32_t attrlen, bitmap[2]; + uint32_t attrlen, bitmap[3]; int status; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) @@ -4477,6 +4539,9 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype); if (status != 0) goto xdr_error; + status = decode_attr_layout_blksize(xdr, bitmap, &fsinfo->blksize); + if (status) + goto xdr_error; status = verify_attr_len(xdr, savep, attrlen); xdr_error: @@ -4896,7 +4961,7 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, { __be32 *savep; uint32_t attrlen, - bitmap[2] = {0}; + bitmap[3] = {0}; struct kvec *iov = req->rq_rcv_buf.head; int status; @@ -6852,7 +6917,7 @@ out: int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, int plus) { - uint32_t bitmap[2] = {0}; + uint32_t bitmap[3] = {0}; uint32_t len; __be32 *p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 4faeac8f448a..b2ea8b82d2cb 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -132,7 +132,7 @@ struct nfs_server { #endif #ifdef CONFIG_NFS_V4 - u32 attr_bitmask[2];/* V4 bitmask representing the set + u32 attr_bitmask[3];/* V4 bitmask representing the set of attributes supported on this filesystem */ u32 cache_consistency_bitmask[2]; @@ -145,6 +145,7 @@ struct nfs_server { filesystem */ struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */ struct rpc_wait_queue roc_rpcwaitq; + u32 pnfs_blksize; /* layout_blksize attr */ /* the following fields are protected by nfs_client->cl_lock */ struct rb_root state_owners; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 21f333eae3c8..94f27e56df9c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -122,6 +122,7 @@ struct nfs_fsinfo { struct timespec time_delta; /* server time granularity */ __u32 lease_time; /* in seconds */ __u32 layouttype; /* supported pnfs layout driver */ + __u32 blksize; /* preferred pnfs io block size */ }; struct nfs_fsstat { @@ -954,7 +955,7 @@ struct nfs4_server_caps_arg { }; struct nfs4_server_caps_res { - u32 attr_bitmask[2]; + u32 attr_bitmask[3]; u32 acl_bitmask; u32 has_links; u32 has_symlinks; -- cgit v1.2.3 From db29c089094b2e686ebc9ed9f002be4a4f94b1f8 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Sat, 30 Jul 2011 20:52:38 -0400 Subject: pnfs: cleanup_layoutcommit This gives layout driver a chance to cleanup structures they put in at encode_layoutcommit. Signed-off-by: Andy Adamson [fixup layout header pointer for layoutcommit] Signed-off-by: Benny Halevy Signed-off-by: Benny Halevy [rm inode and pnfs_layout_hdr args from cleanup_layoutcommit()] Signed-off-by: Jim Rees Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 1 + fs/nfs/nfs4xdr.c | 1 + fs/nfs/pnfs.c | 8 ++++++++ fs/nfs/pnfs.h | 3 +++ include/linux/nfs_xdr.h | 1 + 5 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e86de799dd12..8c77039e7a81 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5963,6 +5963,7 @@ static void nfs4_layoutcommit_release(void *calldata) struct nfs4_layoutcommit_data *data = calldata; struct pnfs_layout_segment *lseg, *tmp; + pnfs_cleanup_layoutcommit(data); /* Matched by references in pnfs_set_layoutcommit */ list_for_each_entry_safe(lseg, tmp, &data->lseg_list, pls_lc_list) { list_del_init(&lseg->pls_lc_list); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 026166993d11..1dce12f41a4f 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -5599,6 +5599,7 @@ static int decode_layoutcommit(struct xdr_stream *xdr, int status; status = decode_op_hdr(xdr, OP_LAYOUTCOMMIT); + res->status = status; if (status) return status; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 3a47f7ce1e90..e550e8836c37 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1411,6 +1411,14 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata) } EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit); +void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data) +{ + struct nfs_server *nfss = NFS_SERVER(data->args.inode); + + if (nfss->pnfs_curr_ld->cleanup_layoutcommit) + nfss->pnfs_curr_ld->cleanup_layoutcommit(data); +} + /* * For the LAYOUT4_NFSV4_1_FILES layout type, NFS_DATA_SYNC WRITEs and * NFS_UNSTABLE WRITEs with a COMMIT to data servers must store enough diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index bddd8b997e18..606fbde2e757 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -113,6 +113,8 @@ struct pnfs_layoutdriver_type { struct xdr_stream *xdr, const struct nfs4_layoutreturn_args *args); + void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data); + void (*encode_layoutcommit) (struct pnfs_layout_hdr *layoutid, struct xdr_stream *xdr, const struct nfs4_layoutcommit_args *args); @@ -196,6 +198,7 @@ void pnfs_roc_release(struct inode *ino); void pnfs_roc_set_barrier(struct inode *ino, u32 barrier); bool pnfs_roc_drain(struct inode *ino, u32 *barrier); void pnfs_set_layoutcommit(struct nfs_write_data *wdata); +void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data); int pnfs_layoutcommit_inode(struct inode *inode, bool sync); int _pnfs_return_layout(struct inode *); int pnfs_ld_write_done(struct nfs_write_data *); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 94f27e56df9c..569ea5b76fda 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -269,6 +269,7 @@ struct nfs4_layoutcommit_res { struct nfs_fattr *fattr; const struct nfs_server *server; struct nfs4_sequence_res seq_res; + int status; }; struct nfs4_layoutcommit_data { -- cgit v1.2.3 From fe0a9b740881d181e3c96c1f6f6043e252692ffe Mon Sep 17 00:00:00 2001 From: Jim Rees Date: Sat, 30 Jul 2011 20:52:42 -0400 Subject: pnfsblock: add device operations Signed-off-by: Jim Rees Signed-off-by: Fred Isaman Signed-off-by: Benny Halevy Signed-off-by: Benny Halevy [upcall bugfixes] Signed-off-by: Peng Tao Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/Makefile | 2 +- fs/nfs/blocklayout/blocklayout.c | 42 ++++++++ fs/nfs/blocklayout/blocklayout.h | 40 ++++++++ fs/nfs/blocklayout/blocklayoutdev.c | 191 ++++++++++++++++++++++++++++++++++++ fs/nfs/client.c | 2 +- include/linux/nfs.h | 2 + 6 files changed, 277 insertions(+), 2 deletions(-) create mode 100644 fs/nfs/blocklayout/blocklayoutdev.c (limited to 'include/linux') diff --git a/fs/nfs/blocklayout/Makefile b/fs/nfs/blocklayout/Makefile index 5cfadf6ebc90..5bf3409084d2 100644 --- a/fs/nfs/blocklayout/Makefile +++ b/fs/nfs/blocklayout/Makefile @@ -2,4 +2,4 @@ # Makefile for the pNFS block layout driver kernel module # obj-$(CONFIG_PNFS_BLOCK) += blocklayoutdriver.o -blocklayoutdriver-objs := blocklayout.o extents.o +blocklayoutdriver-objs := blocklayout.o extents.o blocklayoutdev.o diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 8dde3723482e..c83878441047 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -31,6 +31,8 @@ */ #include #include +#include +#include #include "blocklayout.h" @@ -40,6 +42,9 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Andy Adamson "); MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver"); +struct dentry *bl_device_pipe; +wait_queue_head_t bl_wq; + static enum pnfs_try_status bl_read_pagelist(struct nfs_read_data *rdata) { @@ -176,13 +181,49 @@ static struct pnfs_layoutdriver_type blocklayout_type = { .pg_write_ops = &bl_pg_write_ops, }; +static const struct rpc_pipe_ops bl_upcall_ops = { + .upcall = bl_pipe_upcall, + .downcall = bl_pipe_downcall, + .destroy_msg = bl_pipe_destroy_msg, +}; + static int __init nfs4blocklayout_init(void) { + struct vfsmount *mnt; + struct path path; int ret; dprintk("%s: NFSv4 Block Layout Driver Registering...\n", __func__); ret = pnfs_register_layoutdriver(&blocklayout_type); + if (ret) + goto out; + + init_waitqueue_head(&bl_wq); + + mnt = rpc_get_mount(); + if (IS_ERR(mnt)) { + ret = PTR_ERR(mnt); + goto out_remove; + } + + ret = vfs_path_lookup(mnt->mnt_root, + mnt, + NFS_PIPE_DIRNAME, 0, &path); + if (ret) + goto out_remove; + + bl_device_pipe = rpc_mkpipe(path.dentry, "blocklayout", NULL, + &bl_upcall_ops, 0); + if (IS_ERR(bl_device_pipe)) { + ret = PTR_ERR(bl_device_pipe); + goto out_remove; + } +out: + return ret; + +out_remove: + pnfs_unregister_layoutdriver(&blocklayout_type); return ret; } @@ -192,6 +233,7 @@ static void __exit nfs4blocklayout_exit(void) __func__); pnfs_unregister_layoutdriver(&blocklayout_type); + rpc_unlink(bl_device_pipe); } MODULE_ALIAS("nfs-layouttype4-3"); diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h index 98e2f60c2143..dd25f1b3fe1e 100644 --- a/fs/nfs/blocklayout/blocklayout.h +++ b/fs/nfs/blocklayout/blocklayout.h @@ -34,8 +34,16 @@ #include #include +#include + #include "../pnfs.h" +struct pnfs_block_dev { + struct list_head bm_node; + struct nfs4_deviceid bm_mdevid; /* associated devid */ + struct block_device *bm_mdev; /* meta device itself */ +}; + enum exstate4 { PNFS_BLOCK_READWRITE_DATA = 0, PNFS_BLOCK_READ_DATA = 1, @@ -88,5 +96,37 @@ static inline struct pnfs_block_layout *BLK_LO2EXT(struct pnfs_layout_hdr *lo) return container_of(lo, struct pnfs_block_layout, bl_layout); } +struct bl_dev_msg { + int status; + uint32_t major, minor; +}; + +struct bl_msg_hdr { + u8 type; + u16 totallen; /* length of entire message, including hdr itself */ +}; + +extern struct dentry *bl_device_pipe; +extern wait_queue_head_t bl_wq; + +#define BL_DEVICE_UMOUNT 0x0 /* Umount--delete devices */ +#define BL_DEVICE_MOUNT 0x1 /* Mount--create devices*/ +#define BL_DEVICE_REQUEST_INIT 0x0 /* Start request */ +#define BL_DEVICE_REQUEST_PROC 0x1 /* User level process succeeds */ +#define BL_DEVICE_REQUEST_ERR 0x2 /* User level process fails */ + +/* blocklayoutdev.c */ +ssize_t bl_pipe_upcall(struct file *, struct rpc_pipe_msg *, + char __user *, size_t); +ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t); +void bl_pipe_destroy_msg(struct rpc_pipe_msg *); +struct block_device *nfs4_blkdev_get(dev_t dev); +int nfs4_blkdev_put(struct block_device *bdev); +struct pnfs_block_dev *nfs4_blk_decode_device(struct nfs_server *server, + struct pnfs_device *dev, + struct list_head *sdlist); +int nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo, + struct nfs4_layoutget_res *lgr, gfp_t gfp_flags); + void bl_put_extent(struct pnfs_block_extent *be); #endif /* FS_NFS_NFS4BLOCKLAYOUT_H */ diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c new file mode 100644 index 000000000000..7e1377fcfdce --- /dev/null +++ b/fs/nfs/blocklayout/blocklayoutdev.c @@ -0,0 +1,191 @@ +/* + * linux/fs/nfs/blocklayout/blocklayoutdev.c + * + * Device operations for the pnfs nfs4 file layout driver. + * + * Copyright (c) 2006 The Regents of the University of Michigan. + * All rights reserved. + * + * Andy Adamson + * Fred Isaman + * + * permission is granted to use, copy, create derivative works and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the university of michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. if + * the above copyright notice or any other identification of the + * university of michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * this software is provided as is, without representation from the + * university of michigan as to its fitness for any purpose, and without + * warranty by the university of michigan of any kind, either express + * or implied, including without limitation the implied warranties of + * merchantability and fitness for a particular purpose. the regents + * of the university of michigan shall not be liable for any damages, + * including special, indirect, incidental, or consequential damages, + * with respect to any claim arising out or in connection with the use + * of the software, even if it has been or is hereafter advised of the + * possibility of such damages. + */ +#include +#include /* __bread */ + +#include +#include +#include + +#include "blocklayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +/* Open a block_device by device number. */ +struct block_device *nfs4_blkdev_get(dev_t dev) +{ + struct block_device *bd; + + dprintk("%s enter\n", __func__); + bd = blkdev_get_by_dev(dev, FMODE_READ, NULL); + if (IS_ERR(bd)) + goto fail; + return bd; +fail: + dprintk("%s failed to open device : %ld\n", + __func__, PTR_ERR(bd)); + return NULL; +} + +/* + * Release the block device + */ +int nfs4_blkdev_put(struct block_device *bdev) +{ + dprintk("%s for device %d:%d\n", __func__, MAJOR(bdev->bd_dev), + MINOR(bdev->bd_dev)); + return blkdev_put(bdev, FMODE_READ); +} + +/* + * Shouldn't there be a rpc_generic_upcall() to do this for us? + */ +ssize_t bl_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg, + char __user *dst, size_t buflen) +{ + char *data = (char *)msg->data + msg->copied; + size_t mlen = min(msg->len - msg->copied, buflen); + unsigned long left; + + left = copy_to_user(dst, data, mlen); + if (left == mlen) { + msg->errno = -EFAULT; + return -EFAULT; + } + + mlen -= left; + msg->copied += mlen; + msg->errno = 0; + return mlen; +} + +static struct bl_dev_msg bl_mount_reply; + +ssize_t bl_pipe_downcall(struct file *filp, const char __user *src, + size_t mlen) +{ + if (mlen != sizeof (struct bl_dev_msg)) + return -EINVAL; + + if (copy_from_user(&bl_mount_reply, src, mlen) != 0) + return -EFAULT; + + wake_up(&bl_wq); + + return mlen; +} + +void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg) +{ + if (msg->errno >= 0) + return; + wake_up(&bl_wq); +} + +/* + * Decodes pnfs_block_deviceaddr4 which is XDR encoded in dev->dev_addr_buf. + */ +struct pnfs_block_dev * +nfs4_blk_decode_device(struct nfs_server *server, + struct pnfs_device *dev, + struct list_head *sdlist) +{ + struct pnfs_block_dev *rv = NULL; + struct block_device *bd = NULL; + struct rpc_pipe_msg msg; + struct bl_msg_hdr bl_msg = { + .type = BL_DEVICE_MOUNT, + .totallen = dev->mincount, + }; + uint8_t *dataptr; + DECLARE_WAITQUEUE(wq, current); + struct bl_dev_msg *reply = &bl_mount_reply; + + dprintk("%s CREATING PIPEFS MESSAGE\n", __func__); + dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data, + dev->mincount); + + memset(&msg, 0, sizeof(msg)); + msg.data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS); + if (!msg.data) { + rv = ERR_PTR(-ENOMEM); + goto out; + } + + memcpy(msg.data, &bl_msg, sizeof(bl_msg)); + dataptr = (uint8_t *) msg.data; + memcpy(&dataptr[sizeof(bl_msg)], dev->area, dev->mincount); + msg.len = sizeof(bl_msg) + dev->mincount; + + dprintk("%s CALLING USERSPACE DAEMON\n", __func__); + add_wait_queue(&bl_wq, &wq); + if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) { + remove_wait_queue(&bl_wq, &wq); + goto out; + } + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); + __set_current_state(TASK_RUNNING); + remove_wait_queue(&bl_wq, &wq); + + if (reply->status != BL_DEVICE_REQUEST_PROC) { + dprintk("%s failed to open device: %d\n", + __func__, reply->status); + rv = ERR_PTR(-EINVAL); + goto out; + } + + bd = nfs4_blkdev_get(MKDEV(reply->major, reply->minor)); + if (IS_ERR(bd)) { + dprintk("%s failed to open device : %ld\n", + __func__, PTR_ERR(bd)); + goto out; + } + + rv = kzalloc(sizeof(*rv), GFP_NOFS); + if (!rv) { + rv = ERR_PTR(-ENOMEM); + goto out; + } + + rv->bm_mdev = bd; + memcpy(&rv->bm_mdevid, &dev->dev_id, sizeof(struct nfs4_deviceid)); + dprintk("%s Created device %s with bd_block_size %u\n", + __func__, + bd->bd_disk->disk_name, + bd->bd_block_size); + +out: + kfree(msg.data); + return rv; +} diff --git a/fs/nfs/client.c b/fs/nfs/client.c index de00a373f085..5833fbbf59b0 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -105,7 +105,7 @@ struct rpc_program nfs_program = { .nrvers = ARRAY_SIZE(nfs_version), .version = nfs_version, .stats = &nfs_rpcstat, - .pipe_dir_name = "/nfs", + .pipe_dir_name = NFS_PIPE_DIRNAME, }; struct rpc_stat nfs_rpcstat = { diff --git a/include/linux/nfs.h b/include/linux/nfs.h index f387919bbc59..8c6ee44914cb 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -29,6 +29,8 @@ #define NFS_MNT_VERSION 1 #define NFS_MNT3_VERSION 3 +#define NFS_PIPE_DIRNAME "/nfs" + /* * NFS stats. The good thing with these values is that NFSv3 errors are * a superset of NFSv2 errors (with the exception of NFSERR_WFLUSH which -- cgit v1.2.3 From 2f9fd182607e7b3bdca35f6ed7f2fae539f7c46b Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Sat, 30 Jul 2011 20:52:46 -0400 Subject: pnfsblock: call and parse getdevicelist Call GETDEVICELIST during mount, then call and parse GETDEVICEINFO for each device returned. [pnfsblock: get rid of deprecated xdr macros] Signed-off-by: Jim Rees [pnfsblock: fix pnfs_deviceid references] Signed-off-by: Fred Isaman [pnfsblock: fix print format warnings for sector_t and size_t] [pnfs-block: #include ] [pnfsblock: no PNFS_NFS_SERVER] Signed-off-by: Benny Halevy [pnfsblock: fix bug determining size of striped volume] [pnfsblock: fix oops when using multiple devices] Signed-off-by: Fred Isaman Signed-off-by: Benny Halevy Signed-off-by: Benny Halevy [pnfsblock: get rid of vmap and deviceid->area structure] Signed-off-by: Peng Tao Signed-off-by: Jim Rees Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/blocklayout.c | 138 +++++++++++++++++++++++++++++++++++- fs/nfs/blocklayout/blocklayout.h | 13 +++- fs/nfs/blocklayout/blocklayoutdev.c | 13 +++- fs/nfs/pnfs.h | 1 - include/linux/nfs_fs_sb.h | 1 + 5 files changed, 158 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index e7bc7a57b3bb..6cd7f4f3acdb 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -157,17 +157,153 @@ bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata) { } +static void free_blk_mountid(struct block_mount_id *mid) +{ + if (mid) { + struct pnfs_block_dev *dev; + spin_lock(&mid->bm_lock); + while (!list_empty(&mid->bm_devlist)) { + dev = list_first_entry(&mid->bm_devlist, + struct pnfs_block_dev, + bm_node); + list_del(&dev->bm_node); + bl_free_block_dev(dev); + } + spin_unlock(&mid->bm_lock); + kfree(mid); + } +} + +/* This is mostly copied from the filelayout's get_device_info function. + * It seems much of this should be at the generic pnfs level. + */ +static struct pnfs_block_dev * +nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh, + struct nfs4_deviceid *d_id) +{ + struct pnfs_device *dev; + struct pnfs_block_dev *rv = NULL; + u32 max_resp_sz; + int max_pages; + struct page **pages = NULL; + int i, rc; + + /* + * Use the session max response size as the basis for setting + * GETDEVICEINFO's maxcount + */ + max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; + max_pages = max_resp_sz >> PAGE_SHIFT; + dprintk("%s max_resp_sz %u max_pages %d\n", + __func__, max_resp_sz, max_pages); + + dev = kmalloc(sizeof(*dev), GFP_NOFS); + if (!dev) { + dprintk("%s kmalloc failed\n", __func__); + return NULL; + } + + pages = kzalloc(max_pages * sizeof(struct page *), GFP_NOFS); + if (pages == NULL) { + kfree(dev); + return NULL; + } + for (i = 0; i < max_pages; i++) { + pages[i] = alloc_page(GFP_NOFS); + if (!pages[i]) + goto out_free; + } + + memcpy(&dev->dev_id, d_id, sizeof(*d_id)); + dev->layout_type = LAYOUT_BLOCK_VOLUME; + dev->pages = pages; + dev->pgbase = 0; + dev->pglen = PAGE_SIZE * max_pages; + dev->mincount = 0; + + dprintk("%s: dev_id: %s\n", __func__, dev->dev_id.data); + rc = nfs4_proc_getdeviceinfo(server, dev); + dprintk("%s getdevice info returns %d\n", __func__, rc); + if (rc) + goto out_free; + + rv = nfs4_blk_decode_device(server, dev); + out_free: + for (i = 0; i < max_pages; i++) + __free_page(pages[i]); + kfree(pages); + kfree(dev); + return rv; +} + static int bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh) { + struct block_mount_id *b_mt_id = NULL; + struct pnfs_devicelist *dlist = NULL; + struct pnfs_block_dev *bdev; + LIST_HEAD(block_disklist); + int status = 0, i; + dprintk("%s enter\n", __func__); - return 0; + + if (server->pnfs_blksize == 0) { + dprintk("%s Server did not return blksize\n", __func__); + return -EINVAL; + } + b_mt_id = kzalloc(sizeof(struct block_mount_id), GFP_NOFS); + if (!b_mt_id) { + status = -ENOMEM; + goto out_error; + } + /* Initialize nfs4 block layout mount id */ + spin_lock_init(&b_mt_id->bm_lock); + INIT_LIST_HEAD(&b_mt_id->bm_devlist); + + dlist = kmalloc(sizeof(struct pnfs_devicelist), GFP_NOFS); + if (!dlist) { + status = -ENOMEM; + goto out_error; + } + dlist->eof = 0; + while (!dlist->eof) { + status = nfs4_proc_getdevicelist(server, fh, dlist); + if (status) + goto out_error; + dprintk("%s GETDEVICELIST numdevs=%i, eof=%i\n", + __func__, dlist->num_devs, dlist->eof); + for (i = 0; i < dlist->num_devs; i++) { + bdev = nfs4_blk_get_deviceinfo(server, fh, + &dlist->dev_id[i]); + if (!bdev) { + status = -ENODEV; + goto out_error; + } + spin_lock(&b_mt_id->bm_lock); + list_add(&bdev->bm_node, &b_mt_id->bm_devlist); + spin_unlock(&b_mt_id->bm_lock); + } + } + dprintk("%s SUCCESS\n", __func__); + server->pnfs_ld_data = b_mt_id; + + out_return: + kfree(dlist); + return status; + + out_error: + free_blk_mountid(b_mt_id); + goto out_return; } static int bl_clear_layoutdriver(struct nfs_server *server) { + struct block_mount_id *b_mt_id = server->pnfs_ld_data; + dprintk("%s enter\n", __func__); + free_blk_mountid(b_mt_id); + dprintk("%s RETURNS\n", __func__); return 0; } diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h index 581d8f47a723..d645880f61a0 100644 --- a/fs/nfs/blocklayout/blocklayout.h +++ b/fs/nfs/blocklayout/blocklayout.h @@ -38,6 +38,11 @@ #include "../pnfs.h" +struct block_mount_id { + spinlock_t bm_lock; /* protects list */ + struct list_head bm_devlist; /* holds pnfs_block_dev */ +}; + struct pnfs_block_dev { struct list_head bm_node; struct nfs4_deviceid bm_mdevid; /* associated devid */ @@ -99,7 +104,10 @@ struct pnfs_block_layout { sector_t bl_blocksize; /* Server blocksize in sectors */ }; -static inline struct pnfs_block_layout *BLK_LO2EXT(struct pnfs_layout_hdr *lo) +#define BLK_ID(lo) ((struct block_mount_id *)(NFS_SERVER(lo->plh_inode)->pnfs_ld_data)) + +static inline struct pnfs_block_layout * +BLK_LO2EXT(struct pnfs_layout_hdr *lo) { return container_of(lo, struct pnfs_block_layout, bl_layout); } @@ -137,8 +145,7 @@ void bl_pipe_destroy_msg(struct rpc_pipe_msg *); struct block_device *nfs4_blkdev_get(dev_t dev); int nfs4_blkdev_put(struct block_device *bdev); struct pnfs_block_dev *nfs4_blk_decode_device(struct nfs_server *server, - struct pnfs_device *dev, - struct list_head *sdlist); + struct pnfs_device *dev); int nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr, gfp_t gfp_flags); diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c index 64da33a40eaf..b23fe601d1c9 100644 --- a/fs/nfs/blocklayout/blocklayoutdev.c +++ b/fs/nfs/blocklayout/blocklayoutdev.c @@ -116,8 +116,7 @@ void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg) */ struct pnfs_block_dev * nfs4_blk_decode_device(struct nfs_server *server, - struct pnfs_device *dev, - struct list_head *sdlist) + struct pnfs_device *dev) { struct pnfs_block_dev *rv = NULL; struct block_device *bd = NULL; @@ -129,6 +128,7 @@ nfs4_blk_decode_device(struct nfs_server *server, uint8_t *dataptr; DECLARE_WAITQUEUE(wq, current); struct bl_dev_msg *reply = &bl_mount_reply; + int offset, len, i; dprintk("%s CREATING PIPEFS MESSAGE\n", __func__); dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data, @@ -143,7 +143,14 @@ nfs4_blk_decode_device(struct nfs_server *server, memcpy(msg.data, &bl_msg, sizeof(bl_msg)); dataptr = (uint8_t *) msg.data; - memcpy(&dataptr[sizeof(bl_msg)], dev->area, dev->mincount); + len = dev->mincount; + offset = sizeof(bl_msg); + for (i = 0; len > 0; i++) { + memcpy(&dataptr[offset], page_address(dev->pages[i]), + len < PAGE_CACHE_SIZE ? len : PAGE_CACHE_SIZE); + len -= PAGE_CACHE_SIZE; + offset += PAGE_CACHE_SIZE; + } msg.len = sizeof(bl_msg) + dev->mincount; dprintk("%s CALLING USERSPACE DAEMON\n", __func__); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 606fbde2e757..e0b5d80a43f6 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -140,7 +140,6 @@ struct pnfs_device { unsigned int layout_type; unsigned int mincount; struct page **pages; - void *area; unsigned int pgbase; unsigned int pglen; }; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index b2ea8b82d2cb..cc03fc1dfb72 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -146,6 +146,7 @@ struct nfs_server { struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */ struct rpc_wait_queue roc_rpcwaitq; u32 pnfs_blksize; /* layout_blksize attr */ + void *pnfs_ld_data; /* per mount point data */ /* the following fields are protected by nfs_client->cl_lock */ struct rb_root state_owners; -- cgit v1.2.3 From ca7a71824ac957b1b9d3322656c05aad38d7275c Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 2 Jun 2011 19:18:47 +0100 Subject: mfd: Fix bus lock interaction for WM831x IRQ set_type() operation The WM831x IRQ set_type() operation is doing a direct register write when called but since set_type() is called with the bus lock held this isn't legal and could cause deadlocks in the IRQ core. Fix this by posting the updates into an array and syncing in the bus_sync_unlock() callback. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- drivers/mfd/wm831x-irq.c | 24 ++++++++++++++++++------ include/linux/mfd/wm831x/core.h | 4 ++++ 2 files changed, 22 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/wm831x-irq.c b/drivers/mfd/wm831x-irq.c index 42b928ec891e..b23d8d5ee96c 100644 --- a/drivers/mfd/wm831x-irq.c +++ b/drivers/mfd/wm831x-irq.c @@ -348,6 +348,15 @@ static void wm831x_irq_sync_unlock(struct irq_data *data) struct wm831x *wm831x = irq_data_get_irq_chip_data(data); int i; + for (i = 0; i < ARRAY_SIZE(wm831x->gpio_update); i++) { + if (wm831x->gpio_update[i]) { + wm831x_set_bits(wm831x, WM831X_GPIO1_CONTROL + i, + WM831X_GPN_INT_MODE | WM831X_GPN_POL, + wm831x->gpio_update[i]); + wm831x->gpio_update[i] = 0; + } + } + for (i = 0; i < ARRAY_SIZE(wm831x->irq_masks_cur); i++) { /* If there's been a change in the mask write it back * to the hardware. */ @@ -387,7 +396,7 @@ static void wm831x_irq_disable(struct irq_data *data) static int wm831x_irq_set_type(struct irq_data *data, unsigned int type) { struct wm831x *wm831x = irq_data_get_irq_chip_data(data); - int val, irq; + int irq; irq = data->irq - wm831x->irq_base; @@ -399,22 +408,25 @@ static int wm831x_irq_set_type(struct irq_data *data, unsigned int type) return -EINVAL; } + /* We set the high bit to flag that we need an update; don't + * do the update here as we can be called with the bus lock + * held. + */ switch (type) { case IRQ_TYPE_EDGE_BOTH: - val = WM831X_GPN_INT_MODE; + wm831x->gpio_update[irq] = 0x10000 | WM831X_GPN_INT_MODE; break; case IRQ_TYPE_EDGE_RISING: - val = WM831X_GPN_POL; + wm831x->gpio_update[irq] = 0x10000 | WM831X_GPN_POL; break; case IRQ_TYPE_EDGE_FALLING: - val = 0; + wm831x->gpio_update[irq] = 0x10000; break; default: return -EINVAL; } - return wm831x_set_bits(wm831x, WM831X_GPIO1_CONTROL + irq, - WM831X_GPN_INT_MODE | WM831X_GPN_POL, val); + return 0; } static struct irq_chip wm831x_irq_chip = { diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 0d515ee1c247..ebead1c401aa 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -237,6 +237,7 @@ struct regulator_dev; #define WM831X_NUM_IRQ_REGS 5 +#define WM831X_NUM_GPIO_REGS 16 enum wm831x_parent { WM8310 = 0x8310, @@ -272,6 +273,9 @@ struct wm831x { int num_gpio; + /* Used by the interrupt controller code to post writes */ + int gpio_update[WM831X_NUM_GPIO_REGS]; + struct mutex auxadc_lock; struct completion auxadc_done; -- cgit v1.2.3 From 266a5e02fe2690637b2318c9fc5c3513937128f4 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 2 Jun 2011 19:18:49 +0100 Subject: mfd: Allow touchscreen to be disabled on wm831x devices Allow platform data to flag the touchscreen as disabled so that if the touch driver is built in we don't end up causing lots of work by spuriously detecting touchscreen activity on systems where it isn't in use. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- drivers/mfd/wm831x-core.c | 27 +++++++++++++++++---------- include/linux/mfd/wm831x/pdata.h | 3 +++ 2 files changed, 20 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/wm831x-core.c b/drivers/mfd/wm831x-core.c index 04994b23bb6b..ff57a1674758 100644 --- a/drivers/mfd/wm831x-core.c +++ b/drivers/mfd/wm831x-core.c @@ -1124,11 +1124,6 @@ static struct mfd_cell wm8311_devs[] = { .num_resources = ARRAY_SIZE(wm831x_status2_resources), .resources = wm831x_status2_resources, }, - { - .name = "wm831x-touch", - .num_resources = ARRAY_SIZE(wm831x_touch_resources), - .resources = wm831x_touch_resources, - }, { .name = "wm831x-watchdog", .num_resources = ARRAY_SIZE(wm831x_wdt_resources), @@ -1285,11 +1280,6 @@ static struct mfd_cell wm8312_devs[] = { .num_resources = ARRAY_SIZE(wm831x_status2_resources), .resources = wm831x_status2_resources, }, - { - .name = "wm831x-touch", - .num_resources = ARRAY_SIZE(wm831x_touch_resources), - .resources = wm831x_touch_resources, - }, { .name = "wm831x-watchdog", .num_resources = ARRAY_SIZE(wm831x_wdt_resources), @@ -1428,6 +1418,15 @@ static struct mfd_cell wm8320_devs[] = { }, }; +static struct mfd_cell touch_devs[] = { + { + .name = "wm831x-touch", + .num_resources = ARRAY_SIZE(wm831x_touch_resources), + .resources = wm831x_touch_resources, + }, +}; + + static struct mfd_cell backlight_devs[] = { { .name = "wm831x-backlight", @@ -1624,12 +1623,20 @@ int wm831x_device_init(struct wm831x *wm831x, unsigned long id, int irq) ret = mfd_add_devices(wm831x->dev, wm831x_num, wm8311_devs, ARRAY_SIZE(wm8311_devs), NULL, wm831x->irq_base); + if (!pdata || !pdata->disable_touch) + mfd_add_devices(wm831x->dev, wm831x_num, + touch_devs, ARRAY_SIZE(touch_devs), + NULL, wm831x->irq_base); break; case WM8312: ret = mfd_add_devices(wm831x->dev, wm831x_num, wm8312_devs, ARRAY_SIZE(wm8312_devs), NULL, wm831x->irq_base); + if (!pdata || !pdata->disable_touch) + mfd_add_devices(wm831x->dev, wm831x_num, + touch_devs, ARRAY_SIZE(touch_devs), + NULL, wm831x->irq_base); break; case WM8320: diff --git a/include/linux/mfd/wm831x/pdata.h b/include/linux/mfd/wm831x/pdata.h index ff42d700293f..0ba24599fe51 100644 --- a/include/linux/mfd/wm831x/pdata.h +++ b/include/linux/mfd/wm831x/pdata.h @@ -120,6 +120,9 @@ struct wm831x_pdata { /** Put the /IRQ line into CMOS mode */ bool irq_cmos; + /** Disable the touchscreen */ + bool disable_touch; + int irq_base; int gpio_base; int gpio_defaults[WM831X_GPIO_NUM]; -- cgit v1.2.3 From 5c05a8d1f0105ada3cb04be5b70686fc6b272619 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 2 Jun 2011 19:18:51 +0100 Subject: mfd: Support dynamic allocation of IRQ range for wm831x Use irq_allocate_desc() to get the IRQ range, which turns into a noop on non-sparse systems. Since all existing users are non-sparse there should be no compatibility issues. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- drivers/mfd/wm831x-irq.c | 18 +++++++++++++----- include/linux/mfd/wm831x/core.h | 2 +- 2 files changed, 14 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/wm831x-irq.c b/drivers/mfd/wm831x-irq.c index b23d8d5ee96c..1808deb8083b 100644 --- a/drivers/mfd/wm831x-irq.c +++ b/drivers/mfd/wm831x-irq.c @@ -527,13 +527,22 @@ int wm831x_irq_init(struct wm831x *wm831x, int irq) 0xffff); } - if (!pdata || !pdata->irq_base) { - dev_err(wm831x->dev, - "No interrupt base specified, no interrupts\n"); + /* Try to dynamically allocate IRQs if no base is specified */ + if (!pdata || !pdata->irq_base) + wm831x->irq_base = -1; + else + wm831x->irq_base = pdata->irq_base; + + wm831x->irq_base = irq_alloc_descs(wm831x->irq_base, 0, + WM831X_NUM_IRQS, 0); + if (wm831x->irq_base < 0) { + dev_warn(wm831x->dev, "Failed to allocate IRQs: %d\n", + wm831x->irq_base); + wm831x->irq_base = 0; return 0; } - if (pdata->irq_cmos) + if (pdata && pdata->irq_cmos) i = 0; else i = WM831X_IRQ_OD; @@ -553,7 +562,6 @@ int wm831x_irq_init(struct wm831x *wm831x, int irq) } wm831x->irq = irq; - wm831x->irq_base = pdata->irq_base; /* Register them with genirq */ for (cur_irq = wm831x->irq_base; diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index ebead1c401aa..9564cf315276 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -262,7 +262,7 @@ struct wm831x { int irq; /* Our chip IRQ */ struct mutex irq_lock; - unsigned int irq_base; + int irq_base; int irq_masks_cur[WM831X_NUM_IRQ_REGS]; /* Currently active value */ int irq_masks_cache[WM831X_NUM_IRQ_REGS]; /* Cached hardware value */ -- cgit v1.2.3 From c1a82780b41e78f31636c49279ce940afe60a453 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 2 Jun 2011 19:18:52 +0100 Subject: mfd: Read wm831x AUXADC conversion results before acknowledging interrupt Ensure that there's no possibility of loosing an AUXADC interrupt by reading the conversion result in the IRQ handler when using interrupts. Otherwise it's possible that under very heavy load a new conversion could be initiated before the acknowledgement for a previous interrupt has happened. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- drivers/mfd/wm831x-core.c | 47 +++++++++++++++++++++++++++-------------- include/linux/mfd/wm831x/core.h | 1 + 2 files changed, 32 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/wm831x-core.c b/drivers/mfd/wm831x-core.c index 58f033b57efe..480abc18f9f3 100644 --- a/drivers/mfd/wm831x-core.c +++ b/drivers/mfd/wm831x-core.c @@ -376,6 +376,16 @@ int wm831x_auxadc_read(struct wm831x *wm831x, enum wm831x_auxadc input) goto disable; } } + + ret = wm831x_reg_read(wm831x, WM831X_AUXADC_DATA); + if (ret < 0) { + dev_err(wm831x->dev, + "Failed to read AUXADC data: %d\n", ret); + goto disable; + } + + wm831x->auxadc_data = ret; + } else { /* If we are using interrupts then wait for the * interrupt to complete. Use an extremely long @@ -390,23 +400,18 @@ int wm831x_auxadc_read(struct wm831x *wm831x, enum wm831x_auxadc input) } } - ret = wm831x_reg_read(wm831x, WM831X_AUXADC_DATA); - if (ret < 0) { - dev_err(wm831x->dev, "Failed to read AUXADC data: %d\n", ret); + src = ((wm831x->auxadc_data & WM831X_AUX_DATA_SRC_MASK) + >> WM831X_AUX_DATA_SRC_SHIFT) - 1; + + if (src == 14) + src = WM831X_AUX_CAL; + + if (src != input) { + dev_err(wm831x->dev, "Data from source %d not %d\n", + src, input); + ret = -EINVAL; } else { - src = ((ret & WM831X_AUX_DATA_SRC_MASK) - >> WM831X_AUX_DATA_SRC_SHIFT) - 1; - - if (src == 14) - src = WM831X_AUX_CAL; - - if (src != input) { - dev_err(wm831x->dev, "Data from source %d not %d\n", - src, input); - ret = -EINVAL; - } else { - ret &= WM831X_AUX_DATA_MASK; - } + ret = wm831x->auxadc_data & WM831X_AUX_DATA_MASK; } disable: @@ -420,6 +425,16 @@ EXPORT_SYMBOL_GPL(wm831x_auxadc_read); static irqreturn_t wm831x_auxadc_irq(int irq, void *irq_data) { struct wm831x *wm831x = irq_data; + int ret; + + ret = wm831x_reg_read(wm831x, WM831X_AUXADC_DATA); + if (ret < 0) { + dev_err(wm831x->dev, + "Failed to read AUXADC data: %d\n", ret); + wm831x->auxadc_data = 0xffff; + } else { + wm831x->auxadc_data = ret; + } complete(&wm831x->auxadc_done); diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 9564cf315276..592e4fd6ab3f 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -278,6 +278,7 @@ struct wm831x { struct mutex auxadc_lock; struct completion auxadc_done; + u16 auxadc_data; /* The WM831x has a security key blocking access to certain * registers. The mutex is taken by the accessors for locking -- cgit v1.2.3 From 78bb3688ea1830672b8095fb6388593f582cd591 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Jun 2011 11:47:28 +0100 Subject: mfd: Support multiple active WM831x AUXADC conversions The WM831x AUXADC hardware can schedule multiple conversions at once, allowing higher performance when more than one source is in use as we can have the hardware start new conversions without having to wait for a register write. Take advantage of this in the interrupt driven case, maintaining a list of callers that are waiting for AUXADC conversions and completing them all simultaneously. The external interface of the AUXADC is not changed so there will be limited use of the feature immediately. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- drivers/mfd/wm831x-auxadc.c | 254 ++++++++++++++++++++++++++++------------ include/linux/mfd/wm831x/core.h | 13 +- 2 files changed, 188 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/wm831x-auxadc.c b/drivers/mfd/wm831x-auxadc.c index 2fc9531b243d..87210954a066 100644 --- a/drivers/mfd/wm831x-auxadc.c +++ b/drivers/mfd/wm831x-auxadc.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -25,19 +26,139 @@ #include #include -/** - * wm831x_auxadc_read: Read a value from the WM831x AUXADC - * - * @wm831x: Device to read from. - * @input: AUXADC input to read. - */ -int wm831x_auxadc_read(struct wm831x *wm831x, enum wm831x_auxadc input) +struct wm831x_auxadc_req { + struct list_head list; + enum wm831x_auxadc input; + int val; + struct completion done; +}; + +static int wm831x_auxadc_read_irq(struct wm831x *wm831x, + enum wm831x_auxadc input) { - int ret, src, irq_masked, timeout; + struct wm831x_auxadc_req *req; + int ret; + bool ena = false; + + req = kzalloc(sizeof(*req), GFP_KERNEL); + if (!req) + return -ENOMEM; + + init_completion(&req->done); + req->input = input; + req->val = -ETIMEDOUT; + + mutex_lock(&wm831x->auxadc_lock); + + /* Enqueue the request */ + list_add(&req->list, &wm831x->auxadc_pending); + + ena = !wm831x->auxadc_active; + + if (ena) { + ret = wm831x_set_bits(wm831x, WM831X_AUXADC_CONTROL, + WM831X_AUX_ENA, WM831X_AUX_ENA); + if (ret != 0) { + dev_err(wm831x->dev, "Failed to enable AUXADC: %d\n", + ret); + goto out; + } + } + + /* Enable the conversion if not already running */ + if (!(wm831x->auxadc_active & (1 << input))) { + ret = wm831x_set_bits(wm831x, WM831X_AUXADC_SOURCE, + 1 << input, 1 << input); + if (ret != 0) { + dev_err(wm831x->dev, + "Failed to set AUXADC source: %d\n", ret); + goto out; + } + + wm831x->auxadc_active |= 1 << input; + } + + /* We convert at the fastest rate possible */ + if (ena) { + ret = wm831x_set_bits(wm831x, WM831X_AUXADC_CONTROL, + WM831X_AUX_CVT_ENA | + WM831X_AUX_RATE_MASK, + WM831X_AUX_CVT_ENA | + WM831X_AUX_RATE_MASK); + if (ret != 0) { + dev_err(wm831x->dev, "Failed to start AUXADC: %d\n", + ret); + goto out; + } + } + + mutex_unlock(&wm831x->auxadc_lock); + + /* Wait for an interrupt */ + wait_for_completion_timeout(&req->done, msecs_to_jiffies(500)); + + mutex_lock(&wm831x->auxadc_lock); + + list_del(&req->list); + ret = req->val; + +out: + mutex_unlock(&wm831x->auxadc_lock); + + kfree(req); + + return ret; +} + +static irqreturn_t wm831x_auxadc_irq(int irq, void *irq_data) +{ + struct wm831x *wm831x = irq_data; + struct wm831x_auxadc_req *req; + int ret, input, val; + + ret = wm831x_reg_read(wm831x, WM831X_AUXADC_DATA); + if (ret < 0) { + dev_err(wm831x->dev, + "Failed to read AUXADC data: %d\n", ret); + return IRQ_NONE; + } + + input = ((ret & WM831X_AUX_DATA_SRC_MASK) + >> WM831X_AUX_DATA_SRC_SHIFT) - 1; + + if (input == 14) + input = WM831X_AUX_CAL; - /* Are we using the interrupt? */ - irq_masked = wm831x_reg_read(wm831x, WM831X_INTERRUPT_STATUS_1_MASK); - irq_masked &= WM831X_AUXADC_DATA_EINT; + val = ret & WM831X_AUX_DATA_MASK; + + mutex_lock(&wm831x->auxadc_lock); + + /* Disable this conversion, we're about to complete all users */ + wm831x_set_bits(wm831x, WM831X_AUXADC_SOURCE, + 1 << input, 0); + wm831x->auxadc_active &= ~(1 << input); + + /* Turn off the entire convertor if idle */ + if (!wm831x->auxadc_active) + wm831x_reg_write(wm831x, WM831X_AUXADC_CONTROL, 0); + + /* Wake up any threads waiting for this request */ + list_for_each_entry(req, &wm831x->auxadc_pending, list) { + if (req->input == input) { + req->val = val; + complete(&req->done); + } + } + + mutex_unlock(&wm831x->auxadc_lock); + + return IRQ_HANDLED; +} + +static int wm831x_auxadc_read_polled(struct wm831x *wm831x, + enum wm831x_auxadc input) +{ + int ret, src, timeout; mutex_lock(&wm831x->auxadc_lock); @@ -57,9 +178,6 @@ int wm831x_auxadc_read(struct wm831x *wm831x, enum wm831x_auxadc input) goto out; } - /* Clear any notification from a very late arriving interrupt */ - try_wait_for_completion(&wm831x->auxadc_done); - ret = wm831x_set_bits(wm831x, WM831X_AUXADC_CONTROL, WM831X_AUX_CVT_ENA, WM831X_AUX_CVT_ENA); if (ret < 0) { @@ -67,59 +185,42 @@ int wm831x_auxadc_read(struct wm831x *wm831x, enum wm831x_auxadc input) goto disable; } - if (irq_masked) { - /* If we're not using interrupts then poll the - * interrupt status register */ - timeout = 5; - while (timeout) { - msleep(1); - - ret = wm831x_reg_read(wm831x, - WM831X_INTERRUPT_STATUS_1); - if (ret < 0) { - dev_err(wm831x->dev, - "ISR 1 read failed: %d\n", ret); - goto disable; - } - - /* Did it complete? */ - if (ret & WM831X_AUXADC_DATA_EINT) { - wm831x_reg_write(wm831x, - WM831X_INTERRUPT_STATUS_1, - WM831X_AUXADC_DATA_EINT); - break; - } else { - dev_err(wm831x->dev, - "AUXADC conversion timeout\n"); - ret = -EBUSY; - goto disable; - } - } + /* If we're not using interrupts then poll the + * interrupt status register */ + timeout = 5; + while (timeout) { + msleep(1); - ret = wm831x_reg_read(wm831x, WM831X_AUXADC_DATA); + ret = wm831x_reg_read(wm831x, + WM831X_INTERRUPT_STATUS_1); if (ret < 0) { dev_err(wm831x->dev, - "Failed to read AUXADC data: %d\n", ret); + "ISR 1 read failed: %d\n", ret); goto disable; } - wm831x->auxadc_data = ret; - - } else { - /* If we are using interrupts then wait for the - * interrupt to complete. Use an extremely long - * timeout to handle situations with heavy load where - * the notification of the interrupt may be delayed by - * threaded IRQ handling. */ - if (!wait_for_completion_timeout(&wm831x->auxadc_done, - msecs_to_jiffies(500))) { - dev_err(wm831x->dev, "Timed out waiting for AUXADC\n"); + /* Did it complete? */ + if (ret & WM831X_AUXADC_DATA_EINT) { + wm831x_reg_write(wm831x, + WM831X_INTERRUPT_STATUS_1, + WM831X_AUXADC_DATA_EINT); + break; + } else { + dev_err(wm831x->dev, + "AUXADC conversion timeout\n"); ret = -EBUSY; goto disable; } } - src = ((wm831x->auxadc_data & WM831X_AUX_DATA_SRC_MASK) + ret = wm831x_reg_read(wm831x, WM831X_AUXADC_DATA); + if (ret < 0) { + dev_err(wm831x->dev, + "Failed to read AUXADC data: %d\n", ret); + goto disable; + } + + src = ((ret & WM831X_AUX_DATA_SRC_MASK) >> WM831X_AUX_DATA_SRC_SHIFT) - 1; if (src == 14) @@ -130,7 +231,7 @@ int wm831x_auxadc_read(struct wm831x *wm831x, enum wm831x_auxadc input) src, input); ret = -EINVAL; } else { - ret = wm831x->auxadc_data & WM831X_AUX_DATA_MASK; + ret &= WM831X_AUX_DATA_MASK; } disable: @@ -139,26 +240,18 @@ out: mutex_unlock(&wm831x->auxadc_lock); return ret; } -EXPORT_SYMBOL_GPL(wm831x_auxadc_read); -static irqreturn_t wm831x_auxadc_irq(int irq, void *irq_data) +/** + * wm831x_auxadc_read: Read a value from the WM831x AUXADC + * + * @wm831x: Device to read from. + * @input: AUXADC input to read. + */ +int wm831x_auxadc_read(struct wm831x *wm831x, enum wm831x_auxadc input) { - struct wm831x *wm831x = irq_data; - int ret; - - ret = wm831x_reg_read(wm831x, WM831X_AUXADC_DATA); - if (ret < 0) { - dev_err(wm831x->dev, - "Failed to read AUXADC data: %d\n", ret); - wm831x->auxadc_data = 0xffff; - } else { - wm831x->auxadc_data = ret; - } - - complete(&wm831x->auxadc_done); - - return IRQ_HANDLED; + return wm831x->auxadc_read(wm831x, input); } +EXPORT_SYMBOL_GPL(wm831x_auxadc_read); /** * wm831x_auxadc_read_uv: Read a voltage from the WM831x AUXADC @@ -185,15 +278,22 @@ void wm831x_auxadc_init(struct wm831x *wm831x) int ret; mutex_init(&wm831x->auxadc_lock); - init_completion(&wm831x->auxadc_done); + INIT_LIST_HEAD(&wm831x->auxadc_pending); + + if (wm831x->irq && wm831x->irq_base) { + wm831x->auxadc_read = wm831x_auxadc_read_irq; - if (wm831x->irq_base) { ret = request_threaded_irq(wm831x->irq_base + WM831X_IRQ_AUXADC_DATA, NULL, wm831x_auxadc_irq, 0, "auxadc", wm831x); - if (ret < 0) + if (ret < 0) { dev_err(wm831x->dev, "AUXADC IRQ request failed: %d\n", ret); + wm831x->auxadc_read = NULL; + } } + + if (!wm831x->auxadc_read) + wm831x->auxadc_read = wm831x_auxadc_read_polled; } diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 592e4fd6ab3f..9fa14cdc1590 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -17,6 +17,7 @@ #include #include +#include /* * Register values. @@ -249,6 +250,12 @@ enum wm831x_parent { WM8326 = 0x8326, }; +struct wm831x; +enum wm831x_auxadc; + +typedef int (*wm831x_auxadc_read_fn)(struct wm831x *wm831x, + enum wm831x_auxadc input); + struct wm831x { struct mutex io_lock; @@ -277,8 +284,9 @@ struct wm831x { int gpio_update[WM831X_NUM_GPIO_REGS]; struct mutex auxadc_lock; - struct completion auxadc_done; - u16 auxadc_data; + struct list_head auxadc_pending; + u16 auxadc_active; + wm831x_auxadc_read_fn auxadc_read; /* The WM831x has a security key blocking access to certain * registers. The mutex is taken by the accessors for locking @@ -305,5 +313,6 @@ void wm831x_device_exit(struct wm831x *wm831x); int wm831x_device_suspend(struct wm831x *wm831x); int wm831x_irq_init(struct wm831x *wm831x, int irq); void wm831x_irq_exit(struct wm831x *wm831x); +void wm831x_auxadc_init(struct wm831x *wm831x); #endif -- cgit v1.2.3 From 36e52873c6393b569f2befcdd1847929211892b8 Mon Sep 17 00:00:00 2001 From: Margarita Olaya Date: Thu, 9 Jun 2011 14:50:00 -0500 Subject: mfd: tps65912: Add new mfd device The tps65912 chip is a power management IC. It contains the following components: - Regulators - GPIO controller The core driver is registered as a platform driver, it provides communication through I2C and SPI interfaces. Signed-off-by: Margarita Olaya Cabrera Acked-by: Samuel Ortiz Acked-by: Liam Girdwood Signed-off-by: Samuel Ortiz --- drivers/mfd/Kconfig | 22 +++ drivers/mfd/Makefile | 4 + drivers/mfd/tps65912-core.c | 164 ++++++++++++++++++++++ drivers/mfd/tps65912-i2c.c | 139 +++++++++++++++++++ drivers/mfd/tps65912-spi.c | 142 +++++++++++++++++++ include/linux/mfd/tps65912.h | 321 +++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 792 insertions(+) create mode 100644 drivers/mfd/tps65912-core.c create mode 100644 drivers/mfd/tps65912-i2c.c create mode 100644 drivers/mfd/tps65912-spi.c create mode 100644 include/linux/mfd/tps65912.h (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 1e2c9f03629b..f94036a4f33d 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -171,6 +171,28 @@ config MFD_TPS6586X This driver can also be built as a module. If so, the module will be called tps6586x. +config MFD_TPS65912 + bool "TPS65912 PMIC" + depends on GPIOLIB + +config MFD_TPS65912_I2C + bool "TPS95612 Power Management chip with I2C" + select MFD_CORE + select MFD_TPS65912 + depends on I2C=y && GPIOLIB + help + If you say yes here you get support for the TPS65912 series of + PM chips with I2C interface. + +config MFD_TPS65912_SPI + bool "TPS65912 Power Management chip with SPI" + select MFD_CORE + select MFD_TPS65912 + depends on SPI_MASTER && GPIOLIB + help + If you say yes here you get support for the TPS65912 series of + PM chips with SPI interface. + config MENELAUS bool "Texas Instruments TWL92330/Menelaus PM chip" depends on I2C=y && ARCH_OMAP2 diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 0889f53c8b02..c9925e5dad99 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -36,6 +36,10 @@ obj-$(CONFIG_MFD_WM8994) += wm8994-core.o wm8994-irq.o obj-$(CONFIG_TPS6105X) += tps6105x.o obj-$(CONFIG_TPS65010) += tps65010.o obj-$(CONFIG_TPS6507X) += tps6507x.o +tps65912-objs := tps65912-core.o +obj-$(CONFIG_MFD_TPS65912) += tps65912.o +obj-$(CONFIG_MFD_TPS65912_I2C) += tps65912-i2c.o +obj-$(CONFIG_MFD_TPS65912_SPI) += tps65912-spi.o obj-$(CONFIG_MENELAUS) += menelaus.o obj-$(CONFIG_TWL4030_CORE) += twl-core.o twl4030-irq.o twl6030-irq.o diff --git a/drivers/mfd/tps65912-core.c b/drivers/mfd/tps65912-core.c new file mode 100644 index 000000000000..10baf7655542 --- /dev/null +++ b/drivers/mfd/tps65912-core.c @@ -0,0 +1,164 @@ +/* + * tps65912-core.c -- TI TPS65912x + * + * Copyright 2011 Texas Instruments Inc. + * + * Author: Margarita Olaya Cabrera + * + * 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 driver is based on wm8350 implementation. + */ + +#include +#include +#include +#include +#include +#include +#include + +static struct mfd_cell tps65912s[] = { + { + .name = "tps65912-pmic", + }, +}; + +int tps65912_set_bits(struct tps65912 *tps65912, u8 reg, u8 mask) +{ + u8 data; + int err; + + mutex_lock(&tps65912->io_mutex); + + err = tps65912->read(tps65912, reg, 1, &data); + if (err) { + dev_err(tps65912->dev, "Read from reg 0x%x failed\n", reg); + goto out; + } + + data |= mask; + err = tps65912->write(tps65912, reg, 1, &data); + if (err) + dev_err(tps65912->dev, "Write to reg 0x%x failed\n", reg); + +out: + mutex_unlock(&tps65912->io_mutex); + return err; +} +EXPORT_SYMBOL_GPL(tps65912_set_bits); + +int tps65912_clear_bits(struct tps65912 *tps65912, u8 reg, u8 mask) +{ + u8 data; + int err; + + mutex_lock(&tps65912->io_mutex); + err = tps65912->read(tps65912, reg, 1, &data); + if (err) { + dev_err(tps65912->dev, "Read from reg 0x%x failed\n", reg); + goto out; + } + + data &= ~mask; + err = tps65912->write(tps65912, reg, 1, &data); + if (err) + dev_err(tps65912->dev, "Write to reg 0x%x failed\n", reg); + +out: + mutex_unlock(&tps65912->io_mutex); + return err; +} +EXPORT_SYMBOL_GPL(tps65912_clear_bits); + +static inline int tps65912_read(struct tps65912 *tps65912, u8 reg) +{ + u8 val; + int err; + + err = tps65912->read(tps65912, reg, 1, &val); + if (err < 0) + return err; + + return val; +} + +static inline int tps65912_write(struct tps65912 *tps65912, u8 reg, u8 val) +{ + return tps65912->write(tps65912, reg, 1, &val); +} + +int tps65912_reg_read(struct tps65912 *tps65912, u8 reg) +{ + int data; + + mutex_lock(&tps65912->io_mutex); + + data = tps65912_read(tps65912, reg); + if (data < 0) + dev_err(tps65912->dev, "Read from reg 0x%x failed\n", reg); + + mutex_unlock(&tps65912->io_mutex); + return data; +} +EXPORT_SYMBOL_GPL(tps65912_reg_read); + +int tps65912_reg_write(struct tps65912 *tps65912, u8 reg, u8 val) +{ + int err; + + mutex_lock(&tps65912->io_mutex); + + err = tps65912_write(tps65912, reg, val); + if (err < 0) + dev_err(tps65912->dev, "Write for reg 0x%x failed\n", reg); + + mutex_unlock(&tps65912->io_mutex); + return err; +} +EXPORT_SYMBOL_GPL(tps65912_reg_write); + +int tps65912_device_init(struct tps65912 *tps65912) +{ + struct tps65912_board *pmic_plat_data = tps65912->dev->platform_data; + int ret, dcdc_avs, value; + + mutex_init(&tps65912->io_mutex); + dev_set_drvdata(tps65912->dev, tps65912); + + dcdc_avs = (pmic_plat_data->is_dcdc1_avs << 0 | + pmic_plat_data->is_dcdc2_avs << 1 | + pmic_plat_data->is_dcdc3_avs << 2 | + pmic_plat_data->is_dcdc4_avs << 3); + if (dcdc_avs) { + tps65912->read(tps65912, TPS65912_I2C_SPI_CFG, 1, &value); + dcdc_avs |= value; + tps65912->write(tps65912, TPS65912_I2C_SPI_CFG, 1, &dcdc_avs); + } + + ret = mfd_add_devices(tps65912->dev, -1, + tps65912s, ARRAY_SIZE(tps65912s), + NULL, 0); + if (ret < 0) + goto err; + + return ret; + +err: + mfd_remove_devices(tps65912->dev); + kfree(tps65912); + return ret; +} + +void tps65912_device_exit(struct tps65912 *tps65912) +{ + mfd_remove_devices(tps65912->dev); + kfree(tps65912); +} + +MODULE_AUTHOR("Margarita Olaya "); +MODULE_DESCRIPTION("TPS65912x chip family multi-function driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/mfd/tps65912-i2c.c b/drivers/mfd/tps65912-i2c.c new file mode 100644 index 000000000000..9ed123aa6624 --- /dev/null +++ b/drivers/mfd/tps65912-i2c.c @@ -0,0 +1,139 @@ +/* + * tps65912-i2c.c -- I2C access for TI TPS65912x PMIC + * + * Copyright 2011 Texas Instruments Inc. + * + * Author: Margarita Olaya Cabrera + * + * 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 driver is based on wm8350 implementation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +static int tps65912_i2c_read(struct tps65912 *tps65912, u8 reg, + int bytes, void *dest) +{ + struct i2c_client *i2c = tps65912->control_data; + struct i2c_msg xfer[2]; + int ret; + + /* Write register */ + xfer[0].addr = i2c->addr; + xfer[0].flags = 0; + xfer[0].len = 1; + xfer[0].buf = ® + + /* Read data */ + xfer[1].addr = i2c->addr; + xfer[1].flags = I2C_M_RD; + xfer[1].len = bytes; + xfer[1].buf = dest; + + ret = i2c_transfer(i2c->adapter, xfer, 2); + if (ret == 2) + ret = 0; + else if (ret >= 0) + ret = -EIO; + return ret; +} + +static int tps65912_i2c_write(struct tps65912 *tps65912, u8 reg, + int bytes, void *src) +{ + struct i2c_client *i2c = tps65912->control_data; + /* we add 1 byte for device register */ + u8 msg[TPS6591X_MAX_REGISTER + 1]; + int ret; + + if (bytes > (TPS6591X_MAX_REGISTER + 1)) + return -EINVAL; + + msg[0] = reg; + memcpy(&msg[1], src, bytes); + + ret = i2c_master_send(i2c, msg, bytes + 1); + if (ret < 0) + return ret; + if (ret != bytes + 1) + return -EIO; + + return 0; +} + +static int tps65912_i2c_probe(struct i2c_client *i2c, + const struct i2c_device_id *id) +{ + struct tps65912 *tps65912; + + tps65912 = kzalloc(sizeof(struct tps65912), GFP_KERNEL); + if (tps65912 == NULL) + return -ENOMEM; + + i2c_set_clientdata(i2c, tps65912); + tps65912->dev = &i2c->dev; + tps65912->control_data = i2c; + tps65912->read = tps65912_i2c_read; + tps65912->write = tps65912_i2c_write; + + return tps65912_device_init(tps65912); +} + +static int tps65912_i2c_remove(struct i2c_client *i2c) +{ + struct tps65912 *tps65912 = i2c_get_clientdata(i2c); + + tps65912_device_exit(tps65912); + + return 0; +} + +static const struct i2c_device_id tps65912_i2c_id[] = { + {"tps65912", 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, tps65912_i2c_id); + +static struct i2c_driver tps65912_i2c_driver = { + .driver = { + .name = "tps65912", + .owner = THIS_MODULE, + }, + .probe = tps65912_i2c_probe, + .remove = tps65912_i2c_remove, + .id_table = tps65912_i2c_id, +}; + +static int __init tps65912_i2c_init(void) +{ + int ret; + + ret = i2c_add_driver(&tps65912_i2c_driver); + if (ret != 0) + pr_err("Failed to register TPS65912 I2C driver: %d\n", ret); + + return ret; +} +/* init early so consumer devices can complete system boot */ +subsys_initcall(tps65912_i2c_init); + +static void __exit tps65912_i2c_exit(void) +{ + i2c_del_driver(&tps65912_i2c_driver); +} +module_exit(tps65912_i2c_exit); + +MODULE_AUTHOR("Margarita Olaya "); +MODULE_DESCRIPTION("TPS6591x chip family multi-function driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/mfd/tps65912-spi.c b/drivers/mfd/tps65912-spi.c new file mode 100644 index 000000000000..6d71e0d25744 --- /dev/null +++ b/drivers/mfd/tps65912-spi.c @@ -0,0 +1,142 @@ +/* + * tps65912-spi.c -- SPI access for TI TPS65912x PMIC + * + * Copyright 2011 Texas Instruments Inc. + * + * Author: Margarita Olaya Cabrera + * + * 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 driver is based on wm8350 implementation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +static int tps65912_spi_write(struct tps65912 *tps65912, u8 addr, + int bytes, void *src) +{ + struct spi_device *spi = tps65912->control_data; + u8 *data = (u8 *) src; + int ret; + /* bit 23 is the read/write bit */ + unsigned long spi_data = 1 << 23 | addr << 15 | *data; + struct spi_transfer xfer; + struct spi_message msg; + u32 tx_buf, rx_buf; + + tx_buf = spi_data; + rx_buf = 0; + + xfer.tx_buf = &tx_buf; + xfer.rx_buf = NULL; + xfer.len = sizeof(unsigned long); + xfer.bits_per_word = 24; + + spi_message_init(&msg); + spi_message_add_tail(&xfer, &msg); + + ret = spi_sync(spi, &msg); + return ret; +} + +static int tps65912_spi_read(struct tps65912 *tps65912, u8 addr, + int bytes, void *dest) +{ + struct spi_device *spi = tps65912->control_data; + /* bit 23 is the read/write bit */ + unsigned long spi_data = 0 << 23 | addr << 15; + struct spi_transfer xfer; + struct spi_message msg; + int ret; + u8 *data = (u8 *) dest; + u32 tx_buf, rx_buf; + + tx_buf = spi_data; + rx_buf = 0; + + xfer.tx_buf = &tx_buf; + xfer.rx_buf = &rx_buf; + xfer.len = sizeof(unsigned long); + xfer.bits_per_word = 24; + + spi_message_init(&msg); + spi_message_add_tail(&xfer, &msg); + + if (spi == NULL) + return 0; + + ret = spi_sync(spi, &msg); + if (ret == 0) + *data = (u8) (rx_buf & 0xFF); + return ret; +} + +static int __devinit tps65912_spi_probe(struct spi_device *spi) +{ + struct tps65912 *tps65912; + + tps65912 = kzalloc(sizeof(struct tps65912), GFP_KERNEL); + if (tps65912 == NULL) + return -ENOMEM; + + tps65912->dev = &spi->dev; + tps65912->control_data = spi; + tps65912->read = tps65912_spi_read; + tps65912->write = tps65912_spi_write; + + spi_set_drvdata(spi, tps65912); + + return tps65912_device_init(tps65912); +} + +static int __devexit tps65912_spi_remove(struct spi_device *spi) +{ + struct tps65912 *tps65912 = spi_get_drvdata(spi); + + tps65912_device_exit(tps65912); + + return 0; +} + +static struct spi_driver tps65912_spi_driver = { + .driver = { + .name = "tps65912", + .bus = &spi_bus_type, + .owner = THIS_MODULE, + }, + .probe = tps65912_spi_probe, + .remove = __devexit_p(tps65912_spi_remove), +}; + +static int __init tps65912_spi_init(void) +{ + int ret; + + ret = spi_register_driver(&tps65912_spi_driver); + if (ret != 0) + pr_err("Failed to register TPS65912 SPI driver: %d\n", ret); + + return 0; +} +/* init early so consumer devices can complete system boot */ +subsys_initcall(tps65912_spi_init); + +static void __exit tps65912_spi_exit(void) +{ + spi_unregister_driver(&tps65912_spi_driver); +} +module_exit(tps65912_spi_exit); + +MODULE_AUTHOR("Margarita Olaya "); +MODULE_DESCRIPTION("SPI support for TPS65912 chip family mfd"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h new file mode 100644 index 000000000000..48d3b53316a9 --- /dev/null +++ b/include/linux/mfd/tps65912.h @@ -0,0 +1,321 @@ +/* + * tps65912.h -- TI TPS6591x + * + * Copyright 2011 Texas Instruments Inc. + * + * Author: Margarita Olaya + * + * 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 __LINUX_MFD_TPS65912_H +#define __LINUX_MFD_TPS65912_H + +/* TPS regulator type list */ +#define REGULATOR_LDO 0 +#define REGULATOR_DCDC 1 + +/* + * List of registers for TPS65912 + */ + +#define TPS65912_DCDC1_CTRL 0x00 +#define TPS65912_DCDC2_CTRL 0x01 +#define TPS65912_DCDC3_CTRL 0x02 +#define TPS65912_DCDC4_CTRL 0x03 +#define TPS65912_DCDC1_OP 0x04 +#define TPS65912_DCDC1_AVS 0x05 +#define TPS65912_DCDC1_LIMIT 0x06 +#define TPS65912_DCDC2_OP 0x07 +#define TPS65912_DCDC2_AVS 0x08 +#define TPS65912_DCDC2_LIMIT 0x09 +#define TPS65912_DCDC3_OP 0x0A +#define TPS65912_DCDC3_AVS 0x0B +#define TPS65912_DCDC3_LIMIT 0x0C +#define TPS65912_DCDC4_OP 0x0D +#define TPS65912_DCDC4_AVS 0x0E +#define TPS65912_DCDC4_LIMIT 0x0F +#define TPS65912_LDO1_OP 0x10 +#define TPS65912_LDO1_AVS 0x11 +#define TPS65912_LDO1_LIMIT 0x12 +#define TPS65912_LDO2_OP 0x13 +#define TPS65912_LDO2_AVS 0x14 +#define TPS65912_LDO2_LIMIT 0x15 +#define TPS65912_LDO3_OP 0x16 +#define TPS65912_LDO3_AVS 0x17 +#define TPS65912_LDO3_LIMIT 0x18 +#define TPS65912_LDO4_OP 0x19 +#define TPS65912_LDO4_AVS 0x1A +#define TPS65912_LDO4_LIMIT 0x1B +#define TPS65912_LDO5 0x1C +#define TPS65912_LDO6 0x1D +#define TPS65912_LDO7 0x1E +#define TPS65912_LDO8 0x1F +#define TPS65912_LDO9 0x20 +#define TPS65912_LDO10 0x21 +#define TPS65912_THRM 0x22 +#define TPS65912_CLK32OUT 0x23 +#define TPS65912_DEVCTRL 0x24 +#define TPS65912_DEVCTRL2 0x25 +#define TPS65912_I2C_SPI_CFG 0x26 +#define TPS65912_KEEP_ON 0x27 +#define TPS65912_KEEP_ON2 0x28 +#define TPS65912_SET_OFF1 0x29 +#define TPS65912_SET_OFF2 0x2A +#define TPS65912_DEF_VOLT 0x2B +#define TPS65912_DEF_VOLT_MAPPING 0x2C +#define TPS65912_DISCHARGE 0x2D +#define TPS65912_DISCHARGE2 0x2E +#define TPS65912_EN1_SET1 0x2F +#define TPS65912_EN1_SET2 0x30 +#define TPS65912_EN2_SET1 0x31 +#define TPS65912_EN2_SET2 0x32 +#define TPS65912_EN3_SET1 0x33 +#define TPS65912_EN3_SET2 0x34 +#define TPS65912_EN4_SET1 0x35 +#define TPS65912_EN4_SET2 0x36 +#define TPS65912_PGOOD 0x37 +#define TPS65912_PGOOD2 0x38 +#define TPS65912_INT_STS 0x39 +#define TPS65912_INT_MSK 0x3A +#define TPS65912_INT_STS2 0x3B +#define TPS65912_INT_MSK2 0x3C +#define TPS65912_INT_STS3 0x3D +#define TPS65912_INT_MSK3 0x3E +#define TPS65912_INT_STS4 0x3F +#define TPS65912_INT_MSK4 0x40 +#define TPS65912_GPIO1 0x41 +#define TPS65912_GPIO2 0x42 +#define TPS65912_GPIO3 0x43 +#define TPS65912_GPIO4 0x44 +#define TPS65912_GPIO5 0x45 +#define TPS65912_VMON 0x46 +#define TPS65912_LEDA_CTRL1 0x47 +#define TPS65912_LEDA_CTRL2 0x48 +#define TPS65912_LEDA_CTRL3 0x49 +#define TPS65912_LEDA_CTRL4 0x4A +#define TPS65912_LEDA_CTRL5 0x4B +#define TPS65912_LEDA_CTRL6 0x4C +#define TPS65912_LEDA_CTRL7 0x4D +#define TPS65912_LEDA_CTRL8 0x4E +#define TPS65912_LEDB_CTRL1 0x4F +#define TPS65912_LEDB_CTRL2 0x50 +#define TPS65912_LEDB_CTRL3 0x51 +#define TPS65912_LEDB_CTRL4 0x52 +#define TPS65912_LEDB_CTRL5 0x53 +#define TPS65912_LEDB_CTRL6 0x54 +#define TPS65912_LEDB_CTRL7 0x55 +#define TPS65912_LEDB_CTRL8 0x56 +#define TPS65912_LEDC_CTRL1 0x57 +#define TPS65912_LEDC_CTRL2 0x58 +#define TPS65912_LEDC_CTRL3 0x59 +#define TPS65912_LEDC_CTRL4 0x5A +#define TPS65912_LEDC_CTRL5 0x5B +#define TPS65912_LEDC_CTRL6 0x5C +#define TPS65912_LEDC_CTRL7 0x5D +#define TPS65912_LEDC_CTRL8 0x5E +#define TPS65912_LED_RAMP_UP_TIME 0x5F +#define TPS65912_LED_RAMP_DOWN_TIME 0x60 +#define TPS65912_LED_SEQ_EN 0x61 +#define TPS65912_LOADSWITCH 0x62 +#define TPS65912_SPARE 0x63 +#define TPS65912_VERNUM 0x64 +#define TPS6591X_MAX_REGISTER 0x64 + +/* IRQ Definitions */ +#define TPS65912_IRQ_PWRHOLD_F 0 +#define TPS65912_IRQ_VMON 1 +#define TPS65912_IRQ_PWRON 2 +#define TPS65912_IRQ_PWRON_LP 3 +#define TPS65912_IRQ_PWRHOLD_R 4 +#define TPS65912_IRQ_HOTDIE 5 +#define TPS65912_IRQ_GPIO1_R 6 +#define TPS65912_IRQ_GPIO1_F 7 +#define TPS65912_IRQ_GPIO2_R 8 +#define TPS65912_IRQ_GPIO2_F 9 +#define TPS65912_IRQ_GPIO3_R 10 +#define TPS65912_IRQ_GPIO3_F 11 +#define TPS65912_IRQ_GPIO4_R 12 +#define TPS65912_IRQ_GPIO4_F 13 +#define TPS65912_IRQ_GPIO5_R 14 +#define TPS65912_IRQ_GPIO5_F 15 +#define TPS65912_IRQ_PGOOD_DCDC1 16 +#define TPS65912_IRQ_PGOOD_DCDC2 17 +#define TPS65912_IRQ_PGOOD_DCDC3 18 +#define TPS65912_IRQ_PGOOD_DCDC4 19 +#define TPS65912_IRQ_PGOOD_LDO1 20 +#define TPS65912_IRQ_PGOOD_LDO2 21 +#define TPS65912_IRQ_PGOOD_LDO3 22 +#define TPS65912_IRQ_PGOOD_LDO4 23 +#define TPS65912_IRQ_PGOOD_LDO5 24 +#define TPS65912_IRQ_PGOOD_LDO6 25 +#define TPS65912_IRQ_PGOOD_LDO7 26 +#define TPS65912_IRQ_PGOOD_LD08 27 +#define TPS65912_IRQ_PGOOD_LDO9 28 +#define TPS65912_IRQ_PGOOD_LDO10 29 + +#define TPS65912_NUM_IRQ 30 + +/* GPIO 1 and 2 Register Definitions */ +#define GPIO_SLEEP_MASK 0x80 +#define GPIO_SLEEP_SHIFT 7 +#define GPIO_DEB_MASK 0x10 +#define GPIO_DEB_SHIFT 4 +#define GPIO_CFG_MASK 0x04 +#define GPIO_CFG_SHIFT 2 +#define GPIO_STS_MASK 0x02 +#define GPIO_STS_SHIFT 1 +#define GPIO_SET_MASK 0x01 +#define GPIO_SET_SHIFT 0 + +/* GPIO 3 Register Definitions */ +#define GPIO3_SLEEP_MASK 0x80 +#define GPIO3_SLEEP_SHIFT 7 +#define GPIO3_SEL_MASK 0x40 +#define GPIO3_SEL_SHIFT 6 +#define GPIO3_ODEN_MASK 0x20 +#define GPIO3_ODEN_SHIFT 5 +#define GPIO3_DEB_MASK 0x10 +#define GPIO3_DEB_SHIFT 4 +#define GPIO3_PDEN_MASK 0x08 +#define GPIO3_PDEN_SHIFT 3 +#define GPIO3_CFG_MASK 0x04 +#define GPIO3_CFG_SHIFT 2 +#define GPIO3_STS_MASK 0x02 +#define GPIO3_STS_SHIFT 1 +#define GPIO3_SET_MASK 0x01 +#define GPIO3_SET_SHIFT 0 + +/* GPIO 4 Register Definitions */ +#define GPIO4_SLEEP_MASK 0x80 +#define GPIO4_SLEEP_SHIFT 7 +#define GPIO4_SEL_MASK 0x40 +#define GPIO4_SEL_SHIFT 6 +#define GPIO4_ODEN_MASK 0x20 +#define GPIO4_ODEN_SHIFT 5 +#define GPIO4_DEB_MASK 0x10 +#define GPIO4_DEB_SHIFT 4 +#define GPIO4_PDEN_MASK 0x08 +#define GPIO4_PDEN_SHIFT 3 +#define GPIO4_CFG_MASK 0x04 +#define GPIO4_CFG_SHIFT 2 +#define GPIO4_STS_MASK 0x02 +#define GPIO4_STS_SHIFT 1 +#define GPIO4_SET_MASK 0x01 +#define GPIO4_SET_SHIFT 0 + +/* Register THERM (0x80) register.RegisterDescription */ +#define THERM_THERM_HD_MASK 0x20 +#define THERM_THERM_HD_SHIFT 5 +#define THERM_THERM_TS_MASK 0x10 +#define THERM_THERM_TS_SHIFT 4 +#define THERM_THERM_HDSEL_MASK 0x0C +#define THERM_THERM_HDSEL_SHIFT 2 +#define THERM_RSVD1_MASK 0x02 +#define THERM_RSVD1_SHIFT 1 +#define THERM_THERM_STATE_MASK 0x01 +#define THERM_THERM_STATE_SHIFT 0 + +/* Register DCDCCTRL1 register.RegisterDescription */ +#define DCDCCTRL_VCON_ENABLE_MASK 0x80 +#define DCDCCTRL_VCON_ENABLE_SHIFT 7 +#define DCDCCTRL_VCON_RANGE1_MASK 0x40 +#define DCDCCTRL_VCON_RANGE1_SHIFT 6 +#define DCDCCTRL_VCON_RANGE0_MASK 0x20 +#define DCDCCTRL_VCON_RANGE0_SHIFT 5 +#define DCDCCTRL_TSTEP2_MASK 0x10 +#define DCDCCTRL_TSTEP2_SHIFT 4 +#define DCDCCTRL_TSTEP1_MASK 0x08 +#define DCDCCTRL_TSTEP1_SHIFT 3 +#define DCDCCTRL_TSTEP0_MASK 0x04 +#define DCDCCTRL_TSTEP0_SHIFT 2 +#define DCDCCTRL_DCDC1_MODE_MASK 0x02 +#define DCDCCTRL_DCDC1_MODE_SHIFT 1 + +/* Register DCDCCTRL2 and DCDCCTRL3 register.RegisterDescription */ +#define DCDCCTRL_TSTEP2_MASK 0x10 +#define DCDCCTRL_TSTEP2_SHIFT 4 +#define DCDCCTRL_TSTEP1_MASK 0x08 +#define DCDCCTRL_TSTEP1_SHIFT 3 +#define DCDCCTRL_TSTEP0_MASK 0x04 +#define DCDCCTRL_TSTEP0_SHIFT 2 +#define DCDCCTRL_DCDC_MODE_MASK 0x02 +#define DCDCCTRL_DCDC_MODE_SHIFT 1 +#define DCDCCTRL_RSVD0_MASK 0x01 +#define DCDCCTRL_RSVD0_SHIFT 0 + +/* Register DCDCCTRL4 register.RegisterDescription */ +#define DCDCCTRL_RAMP_TIME_MASK 0x01 +#define DCDCCTRL_RAMP_TIME_SHIFT 0 + +/* Register DCDCx_AVS */ +#define DCDC_AVS_ENABLE_MASK 0x80 +#define DCDC_AVS_ENABLE_SHIFT 7 +#define DCDC_AVS_ECO_MASK 0x40 +#define DCDC_AVS_ECO_SHIFT 6 + +/* Register DCDCx_LIMIT */ +#define DCDC_LIMIT_RANGE_MASK 0xC0 +#define DCDC_LIMIT_RANGE_SHIFT 6 +#define DCDC_LIMIT_MAX_SEL_MASK 0x3F +#define DCDC_LIMIT_MAX_SEL_SHIFT 0 + +/** + * struct tps65912_board + * Board platform dat may be used to initialize regulators. + */ +struct tps65912_board { + int is_dcdc1_avs; + int is_dcdc2_avs; + int is_dcdc3_avs; + int is_dcdc4_avs; + struct regulator_init_data *tps65912_pmic_init_data; +}; + +/** + * struct tps65912 - tps65912 sub-driver chip access routines + */ + +struct tps65912 { + struct device *dev; + /* for read/write acces */ + struct mutex io_mutex; + + /* For device IO interfaces: I2C or SPI */ + void *control_data; + + int (*read)(struct tps65912 *tps65912, u8 reg, int size, void *dest); + int (*write)(struct tps65912 *tps65912, u8 reg, int size, void *src); + + /* Client devices */ + struct tps65912_pmic *pmic; + + /* GPIO Handling */ + struct gpio_chip gpio; + + /* IRQ Handling */ + struct mutex irq_lock; + int chip_irq; + int irq_base; + int irq_num; + u32 irq_mask; +}; + +struct tps65912_platform_data { + int irq_base; +}; + +unsigned int tps_chip(void); + +int tps65912_set_bits(struct tps65912 *tps65912, u8 reg, u8 mask); +int tps65912_clear_bits(struct tps65912 *tps65912, u8 reg, u8 mask); +int tps65912_reg_read(struct tps65912 *tps65912, u8 reg); +int tps65912_reg_write(struct tps65912 *tps65912, u8 reg, u8 val); +int tps65912_device_init(struct tps65912 *tps65912); +void tps65912_device_exit(struct tps65912 *tps65912); + +#endif /* __LINUX_MFD_TPS65912_H */ -- cgit v1.2.3 From d49a0f3f14a763242b71244019d7881ee06e0658 Mon Sep 17 00:00:00 2001 From: Margarita Olaya Date: Thu, 9 Jun 2011 14:50:13 -0500 Subject: tps65912: irq: add interrupt controller This module controls the interrupt handling for the tps65912. The interrupt sources can be the following: - GPIO - PWRON signal - PWRHOLD signal - Temperature detection Signed-off-by: Margarita Olaya Cabrera Acked-by: Samuel Ortiz Acked-by: Liam Girdwood Signed-off-by: Samuel Ortiz --- drivers/mfd/Makefile | 2 +- drivers/mfd/tps65912-core.c | 13 +++ drivers/mfd/tps65912-irq.c | 224 +++++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/tps65912.h | 5 + 4 files changed, 243 insertions(+), 1 deletion(-) create mode 100644 drivers/mfd/tps65912-irq.c (limited to 'include/linux') diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index c9925e5dad99..1d593b9085b7 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -36,7 +36,7 @@ obj-$(CONFIG_MFD_WM8994) += wm8994-core.o wm8994-irq.o obj-$(CONFIG_TPS6105X) += tps6105x.o obj-$(CONFIG_TPS65010) += tps65010.o obj-$(CONFIG_TPS6507X) += tps6507x.o -tps65912-objs := tps65912-core.o +tps65912-objs := tps65912-core.o tps65912-irq.o obj-$(CONFIG_MFD_TPS65912) += tps65912.o obj-$(CONFIG_MFD_TPS65912_I2C) += tps65912-i2c.o obj-$(CONFIG_MFD_TPS65912_SPI) += tps65912-spi.o diff --git a/drivers/mfd/tps65912-core.c b/drivers/mfd/tps65912-core.c index 10baf7655542..955bc00e4b20 100644 --- a/drivers/mfd/tps65912-core.c +++ b/drivers/mfd/tps65912-core.c @@ -124,8 +124,16 @@ EXPORT_SYMBOL_GPL(tps65912_reg_write); int tps65912_device_init(struct tps65912 *tps65912) { struct tps65912_board *pmic_plat_data = tps65912->dev->platform_data; + struct tps65912_platform_data *init_data; int ret, dcdc_avs, value; + init_data = kzalloc(sizeof(struct tps65912_platform_data), GFP_KERNEL); + if (init_data == NULL) + return -ENOMEM; + + init_data->irq = pmic_plat_data->irq; + init_data->irq_base = pmic_plat_data->irq; + mutex_init(&tps65912->io_mutex); dev_set_drvdata(tps65912->dev, tps65912); @@ -145,9 +153,14 @@ int tps65912_device_init(struct tps65912 *tps65912) if (ret < 0) goto err; + ret = tps65912_irq_init(tps65912, init_data->irq, init_data); + if (ret < 0) + goto err; + return ret; err: + kfree(init_data); mfd_remove_devices(tps65912->dev); kfree(tps65912); return ret; diff --git a/drivers/mfd/tps65912-irq.c b/drivers/mfd/tps65912-irq.c new file mode 100644 index 000000000000..d360a83a2738 --- /dev/null +++ b/drivers/mfd/tps65912-irq.c @@ -0,0 +1,224 @@ +/* + * tps65912-irq.c -- TI TPS6591x + * + * Copyright 2011 Texas Instruments Inc. + * + * Author: Margarita Olaya + * + * 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 driver is based on wm8350 implementation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static inline int irq_to_tps65912_irq(struct tps65912 *tps65912, + int irq) +{ + return irq - tps65912->irq_base; +} + +/* + * This is a threaded IRQ handler so can access I2C/SPI. Since the + * IRQ handler explicitly clears the IRQ it handles the IRQ line + * will be reasserted and the physical IRQ will be handled again if + * another interrupt is asserted while we run - in the normal course + * of events this is a rare occurrence so we save I2C/SPI reads. We're + * also assuming that it's rare to get lots of interrupts firing + * simultaneously so try to minimise I/O. + */ +static irqreturn_t tps65912_irq(int irq, void *irq_data) +{ + struct tps65912 *tps65912 = irq_data; + u32 irq_sts; + u32 irq_mask; + u8 reg; + int i; + + + tps65912->read(tps65912, TPS65912_INT_STS, 1, ®); + irq_sts = reg; + tps65912->read(tps65912, TPS65912_INT_STS2, 1, ®); + irq_sts |= reg << 8; + tps65912->read(tps65912, TPS65912_INT_STS3, 1, ®); + irq_sts |= reg << 16; + tps65912->read(tps65912, TPS65912_INT_STS4, 1, ®); + irq_sts |= reg << 24; + + tps65912->read(tps65912, TPS65912_INT_MSK, 1, ®); + irq_mask = reg; + tps65912->read(tps65912, TPS65912_INT_MSK2, 1, ®); + irq_mask |= reg << 8; + tps65912->read(tps65912, TPS65912_INT_MSK3, 1, ®); + irq_mask |= reg << 16; + tps65912->read(tps65912, TPS65912_INT_MSK4, 1, ®); + irq_mask |= reg << 24; + + irq_sts &= ~irq_mask; + if (!irq_sts) + return IRQ_NONE; + + for (i = 0; i < tps65912->irq_num; i++) { + if (!(irq_sts & (1 << i))) + continue; + + handle_nested_irq(tps65912->irq_base + i); + } + + /* Write the STS register back to clear IRQs we handled */ + reg = irq_sts & 0xFF; + irq_sts >>= 8; + if (reg) + tps65912->write(tps65912, TPS65912_INT_STS, 1, ®); + reg = irq_sts & 0xFF; + irq_sts >>= 8; + if (reg) + tps65912->write(tps65912, TPS65912_INT_STS2, 1, ®); + reg = irq_sts & 0xFF; + irq_sts >>= 8; + if (reg) + tps65912->write(tps65912, TPS65912_INT_STS3, 1, ®); + reg = irq_sts & 0xFF; + if (reg) + tps65912->write(tps65912, TPS65912_INT_STS4, 1, ®); + + return IRQ_HANDLED; +} + +static void tps65912_irq_lock(struct irq_data *data) +{ + struct tps65912 *tps65912 = irq_data_get_irq_chip_data(data); + + mutex_lock(&tps65912->irq_lock); +} + +static void tps65912_irq_sync_unlock(struct irq_data *data) +{ + struct tps65912 *tps65912 = irq_data_get_irq_chip_data(data); + u32 reg_mask; + u8 reg; + + tps65912->read(tps65912, TPS65912_INT_MSK, 1, ®); + reg_mask = reg; + tps65912->read(tps65912, TPS65912_INT_MSK2, 1, ®); + reg_mask |= reg << 8; + tps65912->read(tps65912, TPS65912_INT_MSK3, 1, ®); + reg_mask |= reg << 16; + tps65912->read(tps65912, TPS65912_INT_MSK4, 1, ®); + reg_mask |= reg << 24; + + if (tps65912->irq_mask != reg_mask) { + reg = tps65912->irq_mask & 0xFF; + tps65912->write(tps65912, TPS65912_INT_MSK, 1, ®); + reg = tps65912->irq_mask >> 8 & 0xFF; + tps65912->write(tps65912, TPS65912_INT_MSK2, 1, ®); + reg = tps65912->irq_mask >> 16 & 0xFF; + tps65912->write(tps65912, TPS65912_INT_MSK3, 1, ®); + reg = tps65912->irq_mask >> 24 & 0xFF; + tps65912->write(tps65912, TPS65912_INT_MSK4, 1, ®); + } + + mutex_unlock(&tps65912->irq_lock); +} + +static void tps65912_irq_enable(struct irq_data *data) +{ + struct tps65912 *tps65912 = irq_data_get_irq_chip_data(data); + + tps65912->irq_mask &= ~(1 << irq_to_tps65912_irq(tps65912, data->irq)); +} + +static void tps65912_irq_disable(struct irq_data *data) +{ + struct tps65912 *tps65912 = irq_data_get_irq_chip_data(data); + + tps65912->irq_mask |= (1 << irq_to_tps65912_irq(tps65912, data->irq)); +} + +static struct irq_chip tps65912_irq_chip = { + .name = "tps65912", + .irq_bus_lock = tps65912_irq_lock, + .irq_bus_sync_unlock = tps65912_irq_sync_unlock, + .irq_disable = tps65912_irq_disable, + .irq_enable = tps65912_irq_enable, +}; + +int tps65912_irq_init(struct tps65912 *tps65912, int irq, + struct tps65912_platform_data *pdata) +{ + int ret, cur_irq; + int flags = IRQF_ONESHOT; + u8 reg; + + if (!irq) { + dev_warn(tps65912->dev, "No interrupt support, no core IRQ\n"); + return 0; + } + + if (!pdata || !pdata->irq_base) { + dev_warn(tps65912->dev, "No interrupt support, no IRQ base\n"); + return 0; + } + + /* Clear unattended interrupts */ + tps65912->read(tps65912, TPS65912_INT_STS, 1, ®); + tps65912->write(tps65912, TPS65912_INT_STS, 1, ®); + tps65912->read(tps65912, TPS65912_INT_STS2, 1, ®); + tps65912->write(tps65912, TPS65912_INT_STS2, 1, ®); + tps65912->read(tps65912, TPS65912_INT_STS3, 1, ®); + tps65912->write(tps65912, TPS65912_INT_STS3, 1, ®); + tps65912->read(tps65912, TPS65912_INT_STS4, 1, ®); + tps65912->write(tps65912, TPS65912_INT_STS4, 1, ®); + + /* Mask top level interrupts */ + tps65912->irq_mask = 0xFFFFFFFF; + + mutex_init(&tps65912->irq_lock); + tps65912->chip_irq = irq; + tps65912->irq_base = pdata->irq_base; + + tps65912->irq_num = TPS65912_NUM_IRQ; + + /* Register with genirq */ + for (cur_irq = tps65912->irq_base; + cur_irq < tps65912->irq_num + tps65912->irq_base; + cur_irq++) { + irq_set_chip_data(cur_irq, tps65912); + irq_set_chip_and_handler(cur_irq, &tps65912_irq_chip, + handle_edge_irq); + irq_set_nested_thread(cur_irq, 1); + /* ARM needs us to explicitly flag the IRQ as valid + * and will set them noprobe when we do so. */ +#ifdef CONFIG_ARM + set_irq_flags(cur_irq, IRQF_VALID); +#else + irq_set_noprobe(cur_irq); +#endif + } + + ret = request_threaded_irq(irq, NULL, tps65912_irq, flags, + "tps65912", tps65912); + + irq_set_irq_type(irq, IRQ_TYPE_LEVEL_LOW); + if (ret != 0) + dev_err(tps65912->dev, "Failed to request IRQ: %d\n", ret); + + return ret; +} + +int tps65912_irq_exit(struct tps65912 *tps65912) +{ + free_irq(tps65912->chip_irq, tps65912); + return 0; +} diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h index 48d3b53316a9..be60fb23b583 100644 --- a/include/linux/mfd/tps65912.h +++ b/include/linux/mfd/tps65912.h @@ -273,6 +273,8 @@ struct tps65912_board { int is_dcdc2_avs; int is_dcdc3_avs; int is_dcdc4_avs; + int irq; + int irq_base; struct regulator_init_data *tps65912_pmic_init_data; }; @@ -306,6 +308,7 @@ struct tps65912 { }; struct tps65912_platform_data { + int irq; int irq_base; }; @@ -317,5 +320,7 @@ int tps65912_reg_read(struct tps65912 *tps65912, u8 reg); int tps65912_reg_write(struct tps65912 *tps65912, u8 reg, u8 val); int tps65912_device_init(struct tps65912 *tps65912); void tps65912_device_exit(struct tps65912 *tps65912); +int tps65912_irq_init(struct tps65912 *tps65912, int irq, + struct tps65912_platform_data *pdata); #endif /* __LINUX_MFD_TPS65912_H */ -- cgit v1.2.3 From 668a6cc710ee054af2b059d27bbec746ead0fbca Mon Sep 17 00:00:00 2001 From: Margarita Olaya Date: Thu, 9 Jun 2011 14:50:19 -0500 Subject: tps65912: gpio: add gpio driver TPS65912 has five GPIOs that can be configured for different purposes. Signed-off-by: Margarita Olaya Cabrera Acked-by: Grant Likely Acked-by: Liam Girdwood Signed-off-by: Samuel Ortiz --- drivers/gpio/Kconfig | 6 ++ drivers/gpio/Makefile | 1 + drivers/gpio/gpio-tps65912.c | 156 +++++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/tps65912.h | 1 + 4 files changed, 164 insertions(+) create mode 100644 drivers/gpio/gpio-tps65912.c (limited to 'include/linux') diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 363498697c2c..6778f56a4c64 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -280,6 +280,12 @@ config GPIO_TC3589X This enables support for the GPIOs found on the TC3589X I/O Expander. +config GPIO_TPS65912 + tristate "TI TPS65912 GPIO" + depends on (MFD_TPS65912_I2C || MFD_TPS65912_SPI) + help + This driver supports TPS65912 gpio chip + config GPIO_TWL4030 tristate "TWL4030, TWL5030, and TPS659x0 GPIOs" depends on TWL4030_CORE diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile index 720711251391..4b81d4e1e709 100644 --- a/drivers/gpio/Makefile +++ b/drivers/gpio/Makefile @@ -48,6 +48,7 @@ obj-$(CONFIG_GPIO_TC3589X) += gpio-tc3589x.o obj-$(CONFIG_ARCH_TEGRA) += gpio-tegra.o obj-$(CONFIG_GPIO_TIMBERDALE) += gpio-timberdale.o obj-$(CONFIG_GPIO_TPS65910) += gpio-tps65910.o +obj-$(CONFIG_GPIO_TPS65912) += gpio-tps65912.o obj-$(CONFIG_GPIO_TWL4030) += gpio-twl4030.o obj-$(CONFIG_MACH_U300) += gpio-u300.o obj-$(CONFIG_GPIO_UCB1400) += gpio-ucb1400.o diff --git a/drivers/gpio/gpio-tps65912.c b/drivers/gpio/gpio-tps65912.c new file mode 100644 index 000000000000..79e66c002350 --- /dev/null +++ b/drivers/gpio/gpio-tps65912.c @@ -0,0 +1,156 @@ +/* + * Copyright 2011 Texas Instruments Inc. + * + * Author: Margarita Olaya + * + * 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 driver is based on wm8350 implementation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct tps65912_gpio_data { + struct tps65912 *tps65912; + struct gpio_chip gpio_chip; +}; + +static int tps65912_gpio_get(struct gpio_chip *gc, unsigned offset) +{ + struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + int val; + + val = tps65912_reg_read(tps65912, TPS65912_GPIO1 + offset); + + if (val & GPIO_STS_MASK) + return 1; + + return 0; +} + +static void tps65912_gpio_set(struct gpio_chip *gc, unsigned offset, + int value) +{ + struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + + if (value) + tps65912_set_bits(tps65912, TPS65912_GPIO1 + offset, + GPIO_SET_MASK); + else + tps65912_clear_bits(tps65912, TPS65912_GPIO1 + offset, + GPIO_SET_MASK); +} + +static int tps65912_gpio_output(struct gpio_chip *gc, unsigned offset, + int value) +{ + struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + + /* Set the initial value */ + tps65912_gpio_set(gc, offset, value); + + return tps65912_set_bits(tps65912, TPS65912_GPIO1 + offset, + GPIO_CFG_MASK); +} + +static int tps65912_gpio_input(struct gpio_chip *gc, unsigned offset) +{ + struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + + return tps65912_clear_bits(tps65912, TPS65912_GPIO1 + offset, + GPIO_CFG_MASK); + +} + +static struct gpio_chip template_chip = { + .label = "tps65912", + .owner = THIS_MODULE, + .direction_input = tps65912_gpio_input, + .direction_output = tps65912_gpio_output, + .get = tps65912_gpio_get, + .set = tps65912_gpio_set, + .can_sleep = 1, + .ngpio = 5, + .base = -1, +}; + +static int __devinit tps65912_gpio_probe(struct platform_device *pdev) +{ + struct tps65912 *tps65912 = dev_get_drvdata(pdev->dev.parent); + struct tps65912_board *pdata = tps65912->dev->platform_data; + struct tps65912_gpio_data *tps65912_gpio; + int ret; + + tps65912_gpio = kzalloc(sizeof(*tps65912_gpio), GFP_KERNEL); + if (tps65912_gpio == NULL) + return -ENOMEM; + + tps65912_gpio->tps65912 = tps65912; + tps65912_gpio->gpio_chip = template_chip; + tps65912_gpio->gpio_chip.dev = &pdev->dev; + if (pdata && pdata->gpio_base) + tps65912_gpio->gpio_chip.base = pdata->gpio_base; + + ret = gpiochip_add(&tps65912_gpio->gpio_chip); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to register gpiochip, %d\n", ret); + goto err; + } + + platform_set_drvdata(pdev, tps65912_gpio); + + return ret; + +err: + kfree(tps65912_gpio); + return ret; +} + +static int __devexit tps65912_gpio_remove(struct platform_device *pdev) +{ + struct tps65912_gpio_data *tps65912_gpio = platform_get_drvdata(pdev); + int ret; + + ret = gpiochip_remove(&tps65912_gpio->gpio_chip); + if (ret == 0) + kfree(tps65912_gpio); + + return ret; +} + +static struct platform_driver tps65912_gpio_driver = { + .driver = { + .name = "tps65912-gpio", + .owner = THIS_MODULE, + }, + .probe = tps65912_gpio_probe, + .remove = __devexit_p(tps65912_gpio_remove), +}; + +static int __init tps65912_gpio_init(void) +{ + return platform_driver_register(&tps65912_gpio_driver); +} +subsys_initcall(tps65912_gpio_init); + +static void __exit tps65912_gpio_exit(void) +{ + platform_driver_unregister(&tps65912_gpio_driver); +} +module_exit(tps65912_gpio_exit); + +MODULE_AUTHOR("Margarita Olaya Cabrera "); +MODULE_DESCRIPTION("GPIO interface for TPS65912 PMICs"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:tps65912-gpio"); diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h index be60fb23b583..aaceab402ec5 100644 --- a/include/linux/mfd/tps65912.h +++ b/include/linux/mfd/tps65912.h @@ -275,6 +275,7 @@ struct tps65912_board { int is_dcdc4_avs; int irq; int irq_base; + int gpio_base; struct regulator_init_data *tps65912_pmic_init_data; }; -- cgit v1.2.3 From 0a1b089738cf2165ee8678e2483fce3c40389d4a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 9 Jun 2011 23:57:57 +0200 Subject: mfd: Clean-up ab8500 register file This adds a previously undefined test register and removed a number of double-defined accessory detect registers (they are already defined higher up in the file. Signed-off-by: Linus Walleij Signed-off-by: Samuel Ortiz --- include/linux/mfd/ab8500.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ab8500.h b/include/linux/mfd/ab8500.h index b31843075198..838c6b487cc5 100644 --- a/include/linux/mfd/ab8500.h +++ b/include/linux/mfd/ab8500.h @@ -28,6 +28,7 @@ #define AB8500_INTERRUPT 0xE #define AB8500_RTC 0xF #define AB8500_MISC 0x10 +#define AB8500_DEVELOPMENT 0x11 #define AB8500_DEBUG 0x12 #define AB8500_PROD_TEST 0x13 #define AB8500_OTP_EMUL 0x15 @@ -74,13 +75,6 @@ #define AB8500_INT_ACC_DETECT_21DB_F 37 #define AB8500_INT_ACC_DETECT_21DB_R 38 #define AB8500_INT_GP_SW_ADC_CONV_END 39 -#define AB8500_INT_ACC_DETECT_1DB_F 33 -#define AB8500_INT_ACC_DETECT_1DB_R 34 -#define AB8500_INT_ACC_DETECT_22DB_F 35 -#define AB8500_INT_ACC_DETECT_22DB_R 36 -#define AB8500_INT_ACC_DETECT_21DB_F 37 -#define AB8500_INT_ACC_DETECT_21DB_R 38 -#define AB8500_INT_GP_SW_ADC_CONV_END 39 #define AB8500_INT_GPIO6R 40 #define AB8500_INT_GPIO7R 41 #define AB8500_INT_GPIO8R 42 -- cgit v1.2.3 From ec2328c30bf09fe31e77889090eeb1a965325f53 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 20 Jun 2011 11:47:55 +0100 Subject: mfd: Implement tps65910 IRQ cleanup The tps65910_irq_exit() cleanup function was generating a warning from sparse due to the lack of a prototype. This wasn't causing GCC warnings as the driver wasn't cleaning up its IRQs on exit at all so there was no use of an unprototyped function. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- drivers/mfd/tps65910.c | 1 + include/linux/mfd/tps65910.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c index 2229e66d80db..837f0e6fbf0e 100644 --- a/drivers/mfd/tps65910.c +++ b/drivers/mfd/tps65910.c @@ -187,6 +187,7 @@ static int tps65910_i2c_remove(struct i2c_client *i2c) struct tps65910 *tps65910 = i2c_get_clientdata(i2c); mfd_remove_devices(tps65910->dev); + tps65910_irq_exit(tps65910); kfree(tps65910); return 0; diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h index 73572c65d04f..82b4c8801a4f 100644 --- a/include/linux/mfd/tps65910.h +++ b/include/linux/mfd/tps65910.h @@ -791,6 +791,7 @@ int tps65910_clear_bits(struct tps65910 *tps65910, u8 reg, u8 mask); void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base); int tps65910_irq_init(struct tps65910 *tps65910, int irq, struct tps65910_platform_data *pdata); +int tps65910_irq_exit(struct tps65910 *tps65910); static inline int tps65910_chip_id(struct tps65910 *tps65910) { -- cgit v1.2.3 From c7e1da477293b4b5e0bef3639b3734e28d5d55f7 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 21 Jun 2011 11:12:23 +0100 Subject: mfd: Add WM831x clock control register definitions Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm831x/core.h | 101 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 9fa14cdc1590..8dda8ded5cda 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -235,6 +235,107 @@ #define WM831X_ON_PIN_TO_SHIFT 0 /* ON_PIN_TO - [1:0] */ #define WM831X_ON_PIN_TO_WIDTH 2 /* ON_PIN_TO - [1:0] */ +/* + * R16528 (0x4090) - Clock Control 1 + */ +#define WM831X_CLKOUT_ENA 0x8000 /* CLKOUT_ENA */ +#define WM831X_CLKOUT_ENA_MASK 0x8000 /* CLKOUT_ENA */ +#define WM831X_CLKOUT_ENA_SHIFT 15 /* CLKOUT_ENA */ +#define WM831X_CLKOUT_ENA_WIDTH 1 /* CLKOUT_ENA */ +#define WM831X_CLKOUT_OD 0x2000 /* CLKOUT_OD */ +#define WM831X_CLKOUT_OD_MASK 0x2000 /* CLKOUT_OD */ +#define WM831X_CLKOUT_OD_SHIFT 13 /* CLKOUT_OD */ +#define WM831X_CLKOUT_OD_WIDTH 1 /* CLKOUT_OD */ +#define WM831X_CLKOUT_SLOT_MASK 0x0700 /* CLKOUT_SLOT - [10:8] */ +#define WM831X_CLKOUT_SLOT_SHIFT 8 /* CLKOUT_SLOT - [10:8] */ +#define WM831X_CLKOUT_SLOT_WIDTH 3 /* CLKOUT_SLOT - [10:8] */ +#define WM831X_CLKOUT_SLPSLOT_MASK 0x0070 /* CLKOUT_SLPSLOT - [6:4] */ +#define WM831X_CLKOUT_SLPSLOT_SHIFT 4 /* CLKOUT_SLPSLOT - [6:4] */ +#define WM831X_CLKOUT_SLPSLOT_WIDTH 3 /* CLKOUT_SLPSLOT - [6:4] */ +#define WM831X_CLKOUT_SRC 0x0001 /* CLKOUT_SRC */ +#define WM831X_CLKOUT_SRC_MASK 0x0001 /* CLKOUT_SRC */ +#define WM831X_CLKOUT_SRC_SHIFT 0 /* CLKOUT_SRC */ +#define WM831X_CLKOUT_SRC_WIDTH 1 /* CLKOUT_SRC */ + +/* + * R16529 (0x4091) - Clock Control 2 + */ +#define WM831X_XTAL_INH 0x8000 /* XTAL_INH */ +#define WM831X_XTAL_INH_MASK 0x8000 /* XTAL_INH */ +#define WM831X_XTAL_INH_SHIFT 15 /* XTAL_INH */ +#define WM831X_XTAL_INH_WIDTH 1 /* XTAL_INH */ +#define WM831X_XTAL_ENA 0x2000 /* XTAL_ENA */ +#define WM831X_XTAL_ENA_MASK 0x2000 /* XTAL_ENA */ +#define WM831X_XTAL_ENA_SHIFT 13 /* XTAL_ENA */ +#define WM831X_XTAL_ENA_WIDTH 1 /* XTAL_ENA */ +#define WM831X_XTAL_BKUPENA 0x1000 /* XTAL_BKUPENA */ +#define WM831X_XTAL_BKUPENA_MASK 0x1000 /* XTAL_BKUPENA */ +#define WM831X_XTAL_BKUPENA_SHIFT 12 /* XTAL_BKUPENA */ +#define WM831X_XTAL_BKUPENA_WIDTH 1 /* XTAL_BKUPENA */ +#define WM831X_FLL_AUTO 0x0080 /* FLL_AUTO */ +#define WM831X_FLL_AUTO_MASK 0x0080 /* FLL_AUTO */ +#define WM831X_FLL_AUTO_SHIFT 7 /* FLL_AUTO */ +#define WM831X_FLL_AUTO_WIDTH 1 /* FLL_AUTO */ +#define WM831X_FLL_AUTO_FREQ_MASK 0x0007 /* FLL_AUTO_FREQ - [2:0] */ +#define WM831X_FLL_AUTO_FREQ_SHIFT 0 /* FLL_AUTO_FREQ - [2:0] */ +#define WM831X_FLL_AUTO_FREQ_WIDTH 3 /* FLL_AUTO_FREQ - [2:0] */ + +/* + * R16530 (0x4092) - FLL Control 1 + */ +#define WM831X_FLL_FRAC 0x0004 /* FLL_FRAC */ +#define WM831X_FLL_FRAC_MASK 0x0004 /* FLL_FRAC */ +#define WM831X_FLL_FRAC_SHIFT 2 /* FLL_FRAC */ +#define WM831X_FLL_FRAC_WIDTH 1 /* FLL_FRAC */ +#define WM831X_FLL_OSC_ENA 0x0002 /* FLL_OSC_ENA */ +#define WM831X_FLL_OSC_ENA_MASK 0x0002 /* FLL_OSC_ENA */ +#define WM831X_FLL_OSC_ENA_SHIFT 1 /* FLL_OSC_ENA */ +#define WM831X_FLL_OSC_ENA_WIDTH 1 /* FLL_OSC_ENA */ +#define WM831X_FLL_ENA 0x0001 /* FLL_ENA */ +#define WM831X_FLL_ENA_MASK 0x0001 /* FLL_ENA */ +#define WM831X_FLL_ENA_SHIFT 0 /* FLL_ENA */ +#define WM831X_FLL_ENA_WIDTH 1 /* FLL_ENA */ + +/* + * R16531 (0x4093) - FLL Control 2 + */ +#define WM831X_FLL_OUTDIV_MASK 0x3F00 /* FLL_OUTDIV - [13:8] */ +#define WM831X_FLL_OUTDIV_SHIFT 8 /* FLL_OUTDIV - [13:8] */ +#define WM831X_FLL_OUTDIV_WIDTH 6 /* FLL_OUTDIV - [13:8] */ +#define WM831X_FLL_CTRL_RATE_MASK 0x0070 /* FLL_CTRL_RATE - [6:4] */ +#define WM831X_FLL_CTRL_RATE_SHIFT 4 /* FLL_CTRL_RATE - [6:4] */ +#define WM831X_FLL_CTRL_RATE_WIDTH 3 /* FLL_CTRL_RATE - [6:4] */ +#define WM831X_FLL_FRATIO_MASK 0x0007 /* FLL_FRATIO - [2:0] */ +#define WM831X_FLL_FRATIO_SHIFT 0 /* FLL_FRATIO - [2:0] */ +#define WM831X_FLL_FRATIO_WIDTH 3 /* FLL_FRATIO - [2:0] */ + +/* + * R16532 (0x4094) - FLL Control 3 + */ +#define WM831X_FLL_K_MASK 0xFFFF /* FLL_K - [15:0] */ +#define WM831X_FLL_K_SHIFT 0 /* FLL_K - [15:0] */ +#define WM831X_FLL_K_WIDTH 16 /* FLL_K - [15:0] */ + +/* + * R16533 (0x4095) - FLL Control 4 + */ +#define WM831X_FLL_N_MASK 0x7FE0 /* FLL_N - [14:5] */ +#define WM831X_FLL_N_SHIFT 5 /* FLL_N - [14:5] */ +#define WM831X_FLL_N_WIDTH 10 /* FLL_N - [14:5] */ +#define WM831X_FLL_GAIN_MASK 0x000F /* FLL_GAIN - [3:0] */ +#define WM831X_FLL_GAIN_SHIFT 0 /* FLL_GAIN - [3:0] */ +#define WM831X_FLL_GAIN_WIDTH 4 /* FLL_GAIN - [3:0] */ + +/* + * R16534 (0x4096) - FLL Control 5 + */ +#define WM831X_FLL_CLK_REF_DIV_MASK 0x0018 /* FLL_CLK_REF_DIV - [4:3] */ +#define WM831X_FLL_CLK_REF_DIV_SHIFT 3 /* FLL_CLK_REF_DIV - [4:3] */ +#define WM831X_FLL_CLK_REF_DIV_WIDTH 2 /* FLL_CLK_REF_DIV - [4:3] */ +#define WM831X_FLL_CLK_SRC_MASK 0x0003 /* FLL_CLK_SRC - [1:0] */ +#define WM831X_FLL_CLK_SRC_SHIFT 0 /* FLL_CLK_SRC - [1:0] */ +#define WM831X_FLL_CLK_SRC_WIDTH 2 /* FLL_CLK_SRC - [1:0] */ + struct regulator_dev; #define WM831X_NUM_IRQ_REGS 5 -- cgit v1.2.3 From 4dcaa6b6df354fa44b3072bed3cb13aad7e5fbd4 Mon Sep 17 00:00:00 2001 From: Om Prakash Date: Mon, 27 Jun 2011 09:54:22 +0200 Subject: mfd: Fix missing stmpe kerneldoc Generating kerneldoc for STMPE result in warnings, so fix this by adding missing documentation. Signed-off-by: Om Prakash Reviewed-by: Rabin Vincent Reviewed-by: Jonas Aberg Reviewed-by: Srinidhi Kasagar Signed-off-by: Linus Walleij Signed-off-by: Samuel Ortiz --- drivers/mfd/stmpe.c | 2 +- drivers/mfd/stmpe.h | 1 + include/linux/mfd/stmpe.h | 3 +++ 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c index 7ab7746631d4..2963689cf45c 100644 --- a/drivers/mfd/stmpe.c +++ b/drivers/mfd/stmpe.c @@ -228,7 +228,7 @@ int stmpe_block_write(struct stmpe *stmpe, u8 reg, u8 length, EXPORT_SYMBOL_GPL(stmpe_block_write); /** - * stmpe_set_altfunc: set the alternate function for STMPE pins + * stmpe_set_altfunc()- set the alternate function for STMPE pins * @stmpe: Device to configure * @pins: Bitmask of pins to affect * @block: block to enable alternate functions for diff --git a/drivers/mfd/stmpe.h b/drivers/mfd/stmpe.h index 0dbdc4e8cd77..e4ee38956583 100644 --- a/drivers/mfd/stmpe.h +++ b/drivers/mfd/stmpe.h @@ -42,6 +42,7 @@ struct stmpe_variant_block { * @id_mask: bits valid in CHIPID register for comparison with id_val * @num_gpios: number of GPIOS * @af_bits: number of bits used to specify the alternate function + * @regs: variant specific registers. * @blocks: list of blocks present on this device * @num_blocks: number of blocks present on this device * @num_irqs: number of internal IRQs available on this device diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index e762c270d8d4..be1af7c42e57 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -57,6 +57,7 @@ struct stmpe_variant_info; * @irq_lock: IRQ bus lock * @dev: device, mostly for dev_dbg() * @i2c: i2c client + * @partnum: part number * @variant: the detected STMPE model number * @regs: list of addresses of registers which are at different addresses on * different variants. Indexed by one of STMPE_IDX_*. @@ -121,6 +122,8 @@ struct stmpe_keypad_platform_data { * @norequest_mask: bitmask specifying which GPIOs should _not_ be * requestable due to different usage (e.g. touch, keypad) * STMPE_GPIO_NOREQ_* macros can be used here. + * @setup: board specific setup callback. + * @remove: board specific remove callback */ struct stmpe_gpio_platform_data { int gpio_base; -- cgit v1.2.3 From 09d6292befba8c6319d9471803149573ea6ed170 Mon Sep 17 00:00:00 2001 From: Jin Park Date: Mon, 4 Jul 2011 19:48:12 +0200 Subject: mfd: Add AAT2870 mfd driver Add mfd core driver for AnalogicTech AAT2870. The AAT2870 is communication through I2C and contains backlight and regulator components. Signed-off-by: Jin Park Signed-off-by: Samuel Ortiz --- drivers/mfd/Kconfig | 10 + drivers/mfd/Makefile | 1 + drivers/mfd/aat2870-core.c | 535 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/aat2870.h | 181 +++++++++++++++ 4 files changed, 727 insertions(+) create mode 100644 drivers/mfd/aat2870-core.c create mode 100644 include/linux/mfd/aat2870.h (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index c26136443c05..21574bdf485f 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -760,6 +760,16 @@ config MFD_PM8XXX_IRQ config TPS65911_COMPARATOR tristate +config MFD_AAT2870_CORE + bool "Support for the AnalogicTech AAT2870" + select MFD_CORE + depends on I2C=y && GPIOLIB + help + If you say yes here you get support for the AAT2870. + This driver provides common support for accessing the device, + additional drivers must be enabled in order to use the + functionality of the device. + endif # MFD_SUPPORT menu "Multimedia Capabilities Port drivers" diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index ca1867db3db8..c58020303d18 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -101,3 +101,4 @@ obj-$(CONFIG_MFD_OMAP_USB_HOST) += omap-usb-host.o obj-$(CONFIG_MFD_PM8921_CORE) += pm8921-core.o obj-$(CONFIG_MFD_PM8XXX_IRQ) += pm8xxx-irq.o obj-$(CONFIG_TPS65911_COMPARATOR) += tps65911-comparator.o +obj-$(CONFIG_MFD_AAT2870_CORE) += aat2870-core.o diff --git a/drivers/mfd/aat2870-core.c b/drivers/mfd/aat2870-core.c new file mode 100644 index 000000000000..345dc658ef06 --- /dev/null +++ b/drivers/mfd/aat2870-core.c @@ -0,0 +1,535 @@ +/* + * linux/drivers/mfd/aat2870-core.c + * + * Copyright (c) 2011, NVIDIA Corporation. + * Author: Jin Park + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct aat2870_register aat2870_regs[AAT2870_REG_NUM] = { + /* readable, writeable, value */ + { 0, 1, 0x00 }, /* 0x00 AAT2870_BL_CH_EN */ + { 0, 1, 0x16 }, /* 0x01 AAT2870_BLM */ + { 0, 1, 0x16 }, /* 0x02 AAT2870_BLS */ + { 0, 1, 0x56 }, /* 0x03 AAT2870_BL1 */ + { 0, 1, 0x56 }, /* 0x04 AAT2870_BL2 */ + { 0, 1, 0x56 }, /* 0x05 AAT2870_BL3 */ + { 0, 1, 0x56 }, /* 0x06 AAT2870_BL4 */ + { 0, 1, 0x56 }, /* 0x07 AAT2870_BL5 */ + { 0, 1, 0x56 }, /* 0x08 AAT2870_BL6 */ + { 0, 1, 0x56 }, /* 0x09 AAT2870_BL7 */ + { 0, 1, 0x56 }, /* 0x0A AAT2870_BL8 */ + { 0, 1, 0x00 }, /* 0x0B AAT2870_FLR */ + { 0, 1, 0x03 }, /* 0x0C AAT2870_FM */ + { 0, 1, 0x03 }, /* 0x0D AAT2870_FS */ + { 0, 1, 0x10 }, /* 0x0E AAT2870_ALS_CFG0 */ + { 0, 1, 0x06 }, /* 0x0F AAT2870_ALS_CFG1 */ + { 0, 1, 0x00 }, /* 0x10 AAT2870_ALS_CFG2 */ + { 1, 0, 0x00 }, /* 0x11 AAT2870_AMB */ + { 0, 1, 0x00 }, /* 0x12 AAT2870_ALS0 */ + { 0, 1, 0x00 }, /* 0x13 AAT2870_ALS1 */ + { 0, 1, 0x00 }, /* 0x14 AAT2870_ALS2 */ + { 0, 1, 0x00 }, /* 0x15 AAT2870_ALS3 */ + { 0, 1, 0x00 }, /* 0x16 AAT2870_ALS4 */ + { 0, 1, 0x00 }, /* 0x17 AAT2870_ALS5 */ + { 0, 1, 0x00 }, /* 0x18 AAT2870_ALS6 */ + { 0, 1, 0x00 }, /* 0x19 AAT2870_ALS7 */ + { 0, 1, 0x00 }, /* 0x1A AAT2870_ALS8 */ + { 0, 1, 0x00 }, /* 0x1B AAT2870_ALS9 */ + { 0, 1, 0x00 }, /* 0x1C AAT2870_ALSA */ + { 0, 1, 0x00 }, /* 0x1D AAT2870_ALSB */ + { 0, 1, 0x00 }, /* 0x1E AAT2870_ALSC */ + { 0, 1, 0x00 }, /* 0x1F AAT2870_ALSD */ + { 0, 1, 0x00 }, /* 0x20 AAT2870_ALSE */ + { 0, 1, 0x00 }, /* 0x21 AAT2870_ALSF */ + { 0, 1, 0x00 }, /* 0x22 AAT2870_SUB_SET */ + { 0, 1, 0x00 }, /* 0x23 AAT2870_SUB_CTRL */ + { 0, 1, 0x00 }, /* 0x24 AAT2870_LDO_AB */ + { 0, 1, 0x00 }, /* 0x25 AAT2870_LDO_CD */ + { 0, 1, 0x00 }, /* 0x26 AAT2870_LDO_EN */ +}; + +static struct mfd_cell aat2870_devs[] = { + { + .name = "aat2870-backlight", + .id = AAT2870_ID_BL, + .pdata_size = sizeof(struct aat2870_bl_platform_data), + }, + { + .name = "aat2870-regulator", + .id = AAT2870_ID_LDOA, + .pdata_size = sizeof(struct regulator_init_data), + }, + { + .name = "aat2870-regulator", + .id = AAT2870_ID_LDOB, + .pdata_size = sizeof(struct regulator_init_data), + }, + { + .name = "aat2870-regulator", + .id = AAT2870_ID_LDOC, + .pdata_size = sizeof(struct regulator_init_data), + }, + { + .name = "aat2870-regulator", + .id = AAT2870_ID_LDOD, + .pdata_size = sizeof(struct regulator_init_data), + }, +}; + +static int __aat2870_read(struct aat2870_data *aat2870, u8 addr, u8 *val) +{ + int ret; + + if (addr >= AAT2870_REG_NUM) { + dev_err(aat2870->dev, "Invalid address, 0x%02x\n", addr); + return -EINVAL; + } + + if (!aat2870->reg_cache[addr].readable) { + *val = aat2870->reg_cache[addr].value; + goto out; + } + + ret = i2c_master_send(aat2870->client, &addr, 1); + if (ret < 0) + return ret; + if (ret != 1) + return -EIO; + + ret = i2c_master_recv(aat2870->client, val, 1); + if (ret < 0) + return ret; + if (ret != 1) + return -EIO; + +out: + dev_dbg(aat2870->dev, "read: addr=0x%02x, val=0x%02x\n", addr, *val); + return 0; +} + +static int __aat2870_write(struct aat2870_data *aat2870, u8 addr, u8 val) +{ + u8 msg[2]; + int ret; + + if (addr >= AAT2870_REG_NUM) { + dev_err(aat2870->dev, "Invalid address, 0x%02x\n", addr); + return -EINVAL; + } + + if (!aat2870->reg_cache[addr].writeable) { + dev_err(aat2870->dev, "Address 0x%02x is not writeable\n", + addr); + return -EINVAL; + } + + msg[0] = addr; + msg[1] = val; + ret = i2c_master_send(aat2870->client, msg, 2); + if (ret < 0) + return ret; + if (ret != 2) + return -EIO; + + aat2870->reg_cache[addr].value = val; + + dev_dbg(aat2870->dev, "write: addr=0x%02x, val=0x%02x\n", addr, val); + return 0; +} + +static int aat2870_read(struct aat2870_data *aat2870, u8 addr, u8 *val) +{ + int ret; + + mutex_lock(&aat2870->io_lock); + ret = __aat2870_read(aat2870, addr, val); + mutex_unlock(&aat2870->io_lock); + + return ret; +} + +static int aat2870_write(struct aat2870_data *aat2870, u8 addr, u8 val) +{ + int ret; + + mutex_lock(&aat2870->io_lock); + ret = __aat2870_write(aat2870, addr, val); + mutex_unlock(&aat2870->io_lock); + + return ret; +} + +static int aat2870_update(struct aat2870_data *aat2870, u8 addr, u8 mask, + u8 val) +{ + int change; + u8 old_val, new_val; + int ret; + + mutex_lock(&aat2870->io_lock); + + ret = __aat2870_read(aat2870, addr, &old_val); + if (ret) + goto out_unlock; + + new_val = (old_val & ~mask) | (val & mask); + change = old_val != new_val; + if (change) + ret = __aat2870_write(aat2870, addr, new_val); + +out_unlock: + mutex_unlock(&aat2870->io_lock); + + return ret; +} + +static inline void aat2870_enable(struct aat2870_data *aat2870) +{ + if (aat2870->en_pin >= 0) + gpio_set_value(aat2870->en_pin, 1); + + aat2870->is_enable = 1; +} + +static inline void aat2870_disable(struct aat2870_data *aat2870) +{ + if (aat2870->en_pin >= 0) + gpio_set_value(aat2870->en_pin, 0); + + aat2870->is_enable = 0; +} + +#ifdef CONFIG_DEBUG_FS +static ssize_t aat2870_dump_reg(struct aat2870_data *aat2870, char *buf) +{ + u8 addr, val; + ssize_t count = 0; + int ret; + + count += sprintf(buf, "aat2870 registers\n"); + for (addr = 0; addr < AAT2870_REG_NUM; addr++) { + count += sprintf(buf + count, "0x%02x: ", addr); + if (count >= PAGE_SIZE - 1) + break; + + ret = aat2870->read(aat2870, addr, &val); + if (ret == 0) + count += snprintf(buf + count, PAGE_SIZE - count, + "0x%02x", val); + else + count += snprintf(buf + count, PAGE_SIZE - count, + "", ret); + + if (count >= PAGE_SIZE - 1) + break; + + count += snprintf(buf + count, PAGE_SIZE - count, "\n"); + if (count >= PAGE_SIZE - 1) + break; + } + + /* Truncate count; min() would cause a warning */ + if (count >= PAGE_SIZE) + count = PAGE_SIZE - 1; + + return count; +} + +static int aat2870_reg_open_file(struct inode *inode, struct file *file) +{ + file->private_data = inode->i_private; + + return 0; +} + +static ssize_t aat2870_reg_read_file(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct aat2870_data *aat2870 = file->private_data; + char *buf; + ssize_t ret; + + buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + ret = aat2870_dump_reg(aat2870, buf); + if (ret >= 0) + ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret); + + kfree(buf); + + return ret; +} + +static ssize_t aat2870_reg_write_file(struct file *file, + const char __user *user_buf, size_t count, + loff_t *ppos) +{ + struct aat2870_data *aat2870 = file->private_data; + char buf[32]; + int buf_size; + char *start = buf; + unsigned long addr, val; + int ret; + + buf_size = min(count, (sizeof(buf)-1)); + if (copy_from_user(buf, user_buf, buf_size)) { + dev_err(aat2870->dev, "Failed to copy from user\n"); + return -EFAULT; + } + buf[buf_size] = 0; + + while (*start == ' ') + start++; + + addr = simple_strtoul(start, &start, 16); + if (addr >= AAT2870_REG_NUM) { + dev_err(aat2870->dev, "Invalid address, 0x%lx\n", addr); + return -EINVAL; + } + + while (*start == ' ') + start++; + + if (strict_strtoul(start, 16, &val)) + return -EINVAL; + + ret = aat2870->write(aat2870, (u8)addr, (u8)val); + if (ret) + return ret; + + return buf_size; +} + +static const struct file_operations aat2870_reg_fops = { + .open = aat2870_reg_open_file, + .read = aat2870_reg_read_file, + .write = aat2870_reg_write_file, +}; + +static void aat2870_init_debugfs(struct aat2870_data *aat2870) +{ + aat2870->dentry_root = debugfs_create_dir("aat2870", NULL); + if (!aat2870->dentry_root) { + dev_warn(aat2870->dev, + "Failed to create debugfs root directory\n"); + return; + } + + aat2870->dentry_reg = debugfs_create_file("regs", 0644, + aat2870->dentry_root, + aat2870, &aat2870_reg_fops); + if (!aat2870->dentry_reg) + dev_warn(aat2870->dev, + "Failed to create debugfs register file\n"); +} + +static void aat2870_uninit_debugfs(struct aat2870_data *aat2870) +{ + debugfs_remove_recursive(aat2870->dentry_root); +} +#else +static inline void aat2870_init_debugfs(struct aat2870_data *aat2870) +{ +} + +static inline void aat2870_uninit_debugfs(struct aat2870_data *aat2870) +{ +} +#endif /* CONFIG_DEBUG_FS */ + +static int aat2870_i2c_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct aat2870_platform_data *pdata = client->dev.platform_data; + struct aat2870_data *aat2870; + int i, j; + int ret = 0; + + aat2870 = kzalloc(sizeof(struct aat2870_data), GFP_KERNEL); + if (!aat2870) { + dev_err(&client->dev, + "Failed to allocate memory for aat2870\n"); + ret = -ENOMEM; + goto out; + } + + aat2870->dev = &client->dev; + dev_set_drvdata(aat2870->dev, aat2870); + + aat2870->client = client; + i2c_set_clientdata(client, aat2870); + + aat2870->reg_cache = aat2870_regs; + + if (pdata->en_pin < 0) + aat2870->en_pin = -1; + else + aat2870->en_pin = pdata->en_pin; + + aat2870->init = pdata->init; + aat2870->uninit = pdata->uninit; + aat2870->read = aat2870_read; + aat2870->write = aat2870_write; + aat2870->update = aat2870_update; + + mutex_init(&aat2870->io_lock); + + if (aat2870->init) + aat2870->init(aat2870); + + if (aat2870->en_pin >= 0) { + ret = gpio_request(aat2870->en_pin, "aat2870-en"); + if (ret < 0) { + dev_err(&client->dev, + "Failed to request GPIO %d\n", aat2870->en_pin); + goto out_kfree; + } + gpio_direction_output(aat2870->en_pin, 1); + } + + aat2870_enable(aat2870); + + for (i = 0; i < pdata->num_subdevs; i++) { + for (j = 0; j < ARRAY_SIZE(aat2870_devs); j++) { + if ((pdata->subdevs[i].id == aat2870_devs[j].id) && + !strcmp(pdata->subdevs[i].name, + aat2870_devs[j].name)) { + aat2870_devs[j].platform_data = + pdata->subdevs[i].platform_data; + break; + } + } + } + + ret = mfd_add_devices(aat2870->dev, 0, aat2870_devs, + ARRAY_SIZE(aat2870_devs), NULL, 0); + if (ret != 0) { + dev_err(aat2870->dev, "Failed to add subdev: %d\n", ret); + goto out_disable; + } + + aat2870_init_debugfs(aat2870); + + return 0; + +out_disable: + aat2870_disable(aat2870); + if (aat2870->en_pin >= 0) + gpio_free(aat2870->en_pin); +out_kfree: + kfree(aat2870); +out: + return ret; +} + +static int aat2870_i2c_remove(struct i2c_client *client) +{ + struct aat2870_data *aat2870 = i2c_get_clientdata(client); + + aat2870_uninit_debugfs(aat2870); + + mfd_remove_devices(aat2870->dev); + aat2870_disable(aat2870); + if (aat2870->en_pin >= 0) + gpio_free(aat2870->en_pin); + if (aat2870->uninit) + aat2870->uninit(aat2870); + kfree(aat2870); + + return 0; +} + +#ifdef CONFIG_PM +static int aat2870_i2c_suspend(struct i2c_client *client, pm_message_t state) +{ + struct aat2870_data *aat2870 = i2c_get_clientdata(client); + + aat2870_disable(aat2870); + + return 0; +} + +static int aat2870_i2c_resume(struct i2c_client *client) +{ + struct aat2870_data *aat2870 = i2c_get_clientdata(client); + struct aat2870_register *reg = NULL; + int i; + + aat2870_enable(aat2870); + + /* restore registers */ + for (i = 0; i < AAT2870_REG_NUM; i++) { + reg = &aat2870->reg_cache[i]; + if (reg->writeable) + aat2870->write(aat2870, i, reg->value); + } + + return 0; +} +#else +#define aat2870_i2c_suspend NULL +#define aat2870_i2c_resume NULL +#endif /* CONFIG_PM */ + +static struct i2c_device_id aat2870_i2c_id_table[] = { + { "aat2870", 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, aat2870_i2c_id_table); + +static struct i2c_driver aat2870_i2c_driver = { + .driver = { + .name = "aat2870", + .owner = THIS_MODULE, + }, + .probe = aat2870_i2c_probe, + .remove = aat2870_i2c_remove, + .suspend = aat2870_i2c_suspend, + .resume = aat2870_i2c_resume, + .id_table = aat2870_i2c_id_table, +}; + +static int __init aat2870_init(void) +{ + return i2c_add_driver(&aat2870_i2c_driver); +} +subsys_initcall(aat2870_init); + +static void __exit aat2870_exit(void) +{ + i2c_del_driver(&aat2870_i2c_driver); +} +module_exit(aat2870_exit); + +MODULE_DESCRIPTION("Core support for the AnalogicTech AAT2870"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jin Park "); diff --git a/include/linux/mfd/aat2870.h b/include/linux/mfd/aat2870.h new file mode 100644 index 000000000000..89212df05622 --- /dev/null +++ b/include/linux/mfd/aat2870.h @@ -0,0 +1,181 @@ +/* + * linux/include/linux/mfd/aat2870.h + * + * Copyright (c) 2011, NVIDIA Corporation. + * Author: Jin Park + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + */ + +#ifndef __LINUX_MFD_AAT2870_H +#define __LINUX_MFD_AAT2870_H + +#include +#include + +/* Register offsets */ +#define AAT2870_BL_CH_EN 0x00 +#define AAT2870_BLM 0x01 +#define AAT2870_BLS 0x02 +#define AAT2870_BL1 0x03 +#define AAT2870_BL2 0x04 +#define AAT2870_BL3 0x05 +#define AAT2870_BL4 0x06 +#define AAT2870_BL5 0x07 +#define AAT2870_BL6 0x08 +#define AAT2870_BL7 0x09 +#define AAT2870_BL8 0x0A +#define AAT2870_FLR 0x0B +#define AAT2870_FM 0x0C +#define AAT2870_FS 0x0D +#define AAT2870_ALS_CFG0 0x0E +#define AAT2870_ALS_CFG1 0x0F +#define AAT2870_ALS_CFG2 0x10 +#define AAT2870_AMB 0x11 +#define AAT2870_ALS0 0x12 +#define AAT2870_ALS1 0x13 +#define AAT2870_ALS2 0x14 +#define AAT2870_ALS3 0x15 +#define AAT2870_ALS4 0x16 +#define AAT2870_ALS5 0x17 +#define AAT2870_ALS6 0x18 +#define AAT2870_ALS7 0x19 +#define AAT2870_ALS8 0x1A +#define AAT2870_ALS9 0x1B +#define AAT2870_ALSA 0x1C +#define AAT2870_ALSB 0x1D +#define AAT2870_ALSC 0x1E +#define AAT2870_ALSD 0x1F +#define AAT2870_ALSE 0x20 +#define AAT2870_ALSF 0x21 +#define AAT2870_SUB_SET 0x22 +#define AAT2870_SUB_CTRL 0x23 +#define AAT2870_LDO_AB 0x24 +#define AAT2870_LDO_CD 0x25 +#define AAT2870_LDO_EN 0x26 +#define AAT2870_REG_NUM 0x27 + +/* Device IDs */ +enum aat2870_id { + AAT2870_ID_BL, + AAT2870_ID_LDOA, + AAT2870_ID_LDOB, + AAT2870_ID_LDOC, + AAT2870_ID_LDOD +}; + +/* Backlight channels */ +#define AAT2870_BL_CH1 0x01 +#define AAT2870_BL_CH2 0x02 +#define AAT2870_BL_CH3 0x04 +#define AAT2870_BL_CH4 0x08 +#define AAT2870_BL_CH5 0x10 +#define AAT2870_BL_CH6 0x20 +#define AAT2870_BL_CH7 0x40 +#define AAT2870_BL_CH8 0x80 +#define AAT2870_BL_CH_ALL 0xFF + +/* Backlight current magnitude (mA) */ +enum aat2870_current { + AAT2870_CURRENT_0_45, + AAT2870_CURRENT_0_90, + AAT2870_CURRENT_1_80, + AAT2870_CURRENT_2_70, + AAT2870_CURRENT_3_60, + AAT2870_CURRENT_4_50, + AAT2870_CURRENT_5_40, + AAT2870_CURRENT_6_30, + AAT2870_CURRENT_7_20, + AAT2870_CURRENT_8_10, + AAT2870_CURRENT_9_00, + AAT2870_CURRENT_9_90, + AAT2870_CURRENT_10_8, + AAT2870_CURRENT_11_7, + AAT2870_CURRENT_12_6, + AAT2870_CURRENT_13_5, + AAT2870_CURRENT_14_4, + AAT2870_CURRENT_15_3, + AAT2870_CURRENT_16_2, + AAT2870_CURRENT_17_1, + AAT2870_CURRENT_18_0, + AAT2870_CURRENT_18_9, + AAT2870_CURRENT_19_8, + AAT2870_CURRENT_20_7, + AAT2870_CURRENT_21_6, + AAT2870_CURRENT_22_5, + AAT2870_CURRENT_23_4, + AAT2870_CURRENT_24_3, + AAT2870_CURRENT_25_2, + AAT2870_CURRENT_26_1, + AAT2870_CURRENT_27_0, + AAT2870_CURRENT_27_9 +}; + +struct aat2870_register { + bool readable; + bool writeable; + u8 value; +}; + +struct aat2870_data { + struct device *dev; + struct i2c_client *client; + + struct mutex io_lock; + struct aat2870_register *reg_cache; /* register cache */ + int en_pin; /* enable GPIO pin (if < 0, ignore this value) */ + bool is_enable; + + /* init and uninit for platform specified */ + int (*init)(struct aat2870_data *aat2870); + void (*uninit)(struct aat2870_data *aat2870); + + /* i2c io funcntions */ + int (*read)(struct aat2870_data *aat2870, u8 addr, u8 *val); + int (*write)(struct aat2870_data *aat2870, u8 addr, u8 val); + int (*update)(struct aat2870_data *aat2870, u8 addr, u8 mask, u8 val); + + /* for debugfs */ + struct dentry *dentry_root; + struct dentry *dentry_reg; +}; + +struct aat2870_subdev_info { + int id; + const char *name; + void *platform_data; +}; + +struct aat2870_platform_data { + int en_pin; /* enable GPIO pin (if < 0, ignore this value) */ + + struct aat2870_subdev_info *subdevs; + int num_subdevs; + + /* init and uninit for platform specified */ + int (*init)(struct aat2870_data *aat2870); + void (*uninit)(struct aat2870_data *aat2870); +}; + +struct aat2870_bl_platform_data { + /* backlight channels, default is AAT2870_BL_CH_ALL */ + int channels; + /* backlight current magnitude, default is AAT2870_CURRENT_27_9 */ + int max_current; + /* maximum brightness, default is 255 */ + int max_brightness; +}; + +#endif /* __LINUX_MFD_AAT2870_H */ -- cgit v1.2.3 From a00ed25cce6fe856388f89c7cd40da0eee7666a6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 31 Jul 2011 16:39:04 -0400 Subject: NFS: Re-enable compilation of nfs with !CONFIG_NFS_V4 || !CONFIG_NFS_V4_1 Fix two recently introduced compile problems: Fix a typo in fs/nfs/pnfs.h Move the pnfs_blksize declaration outside the CONFIG_NFS_V4 section in struct nfs_server. Reported-by: Jens Axboe Signed-off-by: Trond Myklebust Signed-off-by: Linus Torvalds --- fs/nfs/pnfs.h | 2 +- include/linux/nfs_fs_sb.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index e0b5d80a43f6..01cbfd54f3cb 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -380,7 +380,7 @@ pnfs_roc_drain(struct inode *ino, u32 *barrier) } static inline void set_pnfs_layoutdriver(struct nfs_server *s, - const struct nfs_fh *mntfh, u32 id); + const struct nfs_fh *mntfh, u32 id) { } diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 82fdfc7987d6..b5479df8378d 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -131,6 +131,7 @@ struct nfs_server { struct fscache_cookie *fscache; /* superblock cookie */ #endif + u32 pnfs_blksize; /* layout_blksize attr */ #ifdef CONFIG_NFS_V4 u32 attr_bitmask[3];/* V4 bitmask representing the set of attributes supported on this @@ -145,7 +146,6 @@ struct nfs_server { filesystem */ struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */ struct rpc_wait_queue roc_rpcwaitq; - u32 pnfs_blksize; /* layout_blksize attr */ void *pnfs_ld_data; /* per mount point data */ /* the following fields are protected by nfs_client->cl_lock */ -- cgit v1.2.3 From f2ee7abf4c40c8e6bffced923a7c01ea2d1f6c97 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 28 Jul 2011 06:41:09 +0200 Subject: vfs: avoid taking inode_hash_lock on pipes and sockets Some inodes (pipes, sockets, ...) are not hashed, no need to take contended inode_hash_lock at dismantle time. nice speedup on SMP machines on socket intensive workloads. Signed-off-by: Eric Dumazet Signed-off-by: Al Viro --- fs/inode.c | 6 +++--- include/linux/fs.h | 9 ++++++++- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index 9dab13ae6ef7..e445be2a18f9 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -399,12 +399,12 @@ void __insert_inode_hash(struct inode *inode, unsigned long hashval) EXPORT_SYMBOL(__insert_inode_hash); /** - * remove_inode_hash - remove an inode from the hash + * __remove_inode_hash - remove an inode from the hash * @inode: inode to unhash * * Remove an inode from the superblock. */ -void remove_inode_hash(struct inode *inode) +void __remove_inode_hash(struct inode *inode) { spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); @@ -412,7 +412,7 @@ void remove_inode_hash(struct inode *inode) spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } -EXPORT_SYMBOL(remove_inode_hash); +EXPORT_SYMBOL(__remove_inode_hash); void end_writeback(struct inode *inode) { diff --git a/include/linux/fs.h b/include/linux/fs.h index f23bcb77260c..786b3b1113cf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2317,11 +2317,18 @@ extern int should_remove_suid(struct dentry *); extern int file_remove_suid(struct file *); extern void __insert_inode_hash(struct inode *, unsigned long hashval); -extern void remove_inode_hash(struct inode *); static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } + +extern void __remove_inode_hash(struct inode *); +static inline void remove_inode_hash(struct inode *inode) +{ + if (!inode_unhashed(inode)) + __remove_inode_hash(inode); +} + extern void inode_sb_list_add(struct inode *inode); #ifdef CONFIG_BLOCK -- cgit v1.2.3 From d3fb612076eebec6f67257db0c7a9666ac7e5892 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jul 2011 18:37:50 -0400 Subject: switch posix_acl_create() to umode_t * so we can pass &inode->i_mode to it Signed-off-by: Al Viro --- fs/9p/acl.c | 4 ++-- fs/9p/acl.h | 4 ++-- fs/9p/vfs_inode_dotl.c | 6 +++--- fs/btrfs/acl.c | 5 +---- fs/ext2/acl.c | 4 +--- fs/ext3/acl.c | 5 +---- fs/ext4/acl.c | 5 +---- fs/generic_acl.c | 7 +++---- fs/gfs2/acl.c | 4 ++-- fs/jffs2/acl.c | 2 +- fs/jffs2/acl.h | 2 +- fs/jffs2/fs.c | 2 +- fs/jffs2/os-linux.h | 2 +- fs/jfs/acl.c | 4 +--- fs/nfs/nfs3acl.c | 2 +- fs/nfs/nfs3proc.c | 6 +++--- fs/ocfs2/acl.c | 2 +- fs/posix_acl.c | 6 +++--- fs/reiserfs/xattr_acl.c | 6 +----- fs/xfs/linux-2.6/xfs_acl.c | 4 ++-- include/linux/nfs_fs.h | 4 ++-- include/linux/posix_acl.h | 2 +- 22 files changed, 35 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/fs/9p/acl.c b/fs/9p/acl.c index e9cb57f07546..ad734e3220cf 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -182,11 +182,11 @@ int v9fs_set_create_acl(struct dentry *dentry, return 0; } -int v9fs_acl_mode(struct inode *dir, mode_t *modep, +int v9fs_acl_mode(struct inode *dir, umode_t *modep, struct posix_acl **dpacl, struct posix_acl **pacl) { int retval = 0; - mode_t mode = *modep; + umode_t mode = *modep; struct posix_acl *acl = NULL; if (!S_ISLNK(mode)) { diff --git a/fs/9p/acl.h b/fs/9p/acl.h index ddb7ae19d971..559556411965 100644 --- a/fs/9p/acl.h +++ b/fs/9p/acl.h @@ -20,7 +20,7 @@ extern struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type); extern int v9fs_acl_chmod(struct dentry *); extern int v9fs_set_create_acl(struct dentry *, struct posix_acl **, struct posix_acl **); -extern int v9fs_acl_mode(struct inode *dir, mode_t *modep, +extern int v9fs_acl_mode(struct inode *dir, umode_t *modep, struct posix_acl **dpacl, struct posix_acl **pacl); #else #define v9fs_iop_get_acl NULL @@ -38,7 +38,7 @@ static inline int v9fs_set_create_acl(struct dentry *dentry, { return 0; } -static inline int v9fs_acl_mode(struct inode *dir, mode_t *modep, +static inline int v9fs_acl_mode(struct inode *dir, umode_t *modep, struct posix_acl **dpacl, struct posix_acl **pacl) { diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 9a26dce5a99f..b6c8ed205192 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -206,7 +206,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int omode, int err = 0; gid_t gid; int flags; - mode_t mode; + umode_t mode; char *name = NULL; struct file *filp; struct p9_qid qid; @@ -348,7 +348,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir, struct p9_fid *fid = NULL, *dfid = NULL; gid_t gid; char *name; - mode_t mode; + umode_t mode; struct inode *inode; struct p9_qid qid; struct dentry *dir_dentry; @@ -751,7 +751,7 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, int omode, int err; gid_t gid; char *name; - mode_t mode; + umode_t mode; struct v9fs_session_info *v9ses; struct p9_fid *fid = NULL, *dfid = NULL; struct inode *inode; diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 65a735d8f6e4..59086142c14d 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -222,19 +222,16 @@ int btrfs_init_acl(struct btrfs_trans_handle *trans, } if (IS_POSIXACL(dir) && acl) { - mode_t mode = inode->i_mode; - if (S_ISDIR(inode->i_mode)) { ret = btrfs_set_acl(trans, inode, acl, ACL_TYPE_DEFAULT); if (ret) goto failed; } - ret = posix_acl_create(&acl, GFP_NOFS, &mode); + ret = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode); if (ret < 0) return ret; - inode->i_mode = mode; if (ret > 0) { /* we need an acl */ ret = btrfs_set_acl(trans, inode, acl, ACL_TYPE_ACCESS); diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 52c053763942..0ce740489ab1 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -253,16 +253,14 @@ ext2_init_acl(struct inode *inode, struct inode *dir) inode->i_mode &= ~current_umask(); } if (test_opt(inode->i_sb, POSIX_ACL) && acl) { - mode_t mode = inode->i_mode; if (S_ISDIR(inode->i_mode)) { error = ext2_set_acl(inode, ACL_TYPE_DEFAULT, acl); if (error) goto cleanup; } - error = posix_acl_create(&acl, GFP_KERNEL, &mode); + error = posix_acl_create(&acl, GFP_KERNEL, &inode->i_mode); if (error < 0) return error; - inode->i_mode = mode; if (error > 0) { /* This is an extended ACL */ error = ext2_set_acl(inode, ACL_TYPE_ACCESS, acl); diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index 6c29bf0df04a..74a3c6486f8f 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -261,19 +261,16 @@ ext3_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) inode->i_mode &= ~current_umask(); } if (test_opt(inode->i_sb, POSIX_ACL) && acl) { - mode_t mode = inode->i_mode; - if (S_ISDIR(inode->i_mode)) { error = ext3_set_acl(handle, inode, ACL_TYPE_DEFAULT, acl); if (error) goto cleanup; } - error = posix_acl_create(&acl, GFP_NOFS, &mode); + error = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode); if (error < 0) return error; - inode->i_mode = mode; if (error > 0) { /* This is an extended ACL */ error = ext3_set_acl(handle, inode, ACL_TYPE_ACCESS, acl); diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index dca2d1ded931..74e469ccdf50 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -259,19 +259,16 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) inode->i_mode &= ~current_umask(); } if (test_opt(inode->i_sb, POSIX_ACL) && acl) { - mode_t mode = inode->i_mode; - if (S_ISDIR(inode->i_mode)) { error = ext4_set_acl(handle, inode, ACL_TYPE_DEFAULT, acl); if (error) goto cleanup; } - error = posix_acl_create(&acl, GFP_NOFS, &mode); + error = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode); if (error < 0) return error; - inode->i_mode = mode; if (error > 0) { /* This is an extended ACL */ error = ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, acl); diff --git a/fs/generic_acl.c b/fs/generic_acl.c index d5e33a077a67..2dd434d6ff29 100644 --- a/fs/generic_acl.c +++ b/fs/generic_acl.c @@ -125,21 +125,20 @@ int generic_acl_init(struct inode *inode, struct inode *dir) { struct posix_acl *acl = NULL; - mode_t mode = inode->i_mode; int error; - inode->i_mode = mode & ~current_umask(); if (!S_ISLNK(inode->i_mode)) acl = get_cached_acl(dir, ACL_TYPE_DEFAULT); if (acl) { if (S_ISDIR(inode->i_mode)) set_cached_acl(inode, ACL_TYPE_DEFAULT, acl); - error = posix_acl_create(&acl, GFP_KERNEL, &mode); + error = posix_acl_create(&acl, GFP_KERNEL, &inode->i_mode); if (error < 0) return error; - inode->i_mode = mode; if (error > 0) set_cached_acl(inode, ACL_TYPE_ACCESS, acl); + } else { + inode->i_mode &= ~current_umask(); } error = 0; diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 884c9af0542f..0ac3c53f928f 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -72,7 +72,7 @@ struct posix_acl *gfs2_get_acl(struct inode *inode, int type) return gfs2_acl_get(GFS2_I(inode), type); } -static int gfs2_set_mode(struct inode *inode, mode_t mode) +static int gfs2_set_mode(struct inode *inode, umode_t mode) { int error = 0; @@ -117,7 +117,7 @@ int gfs2_acl_create(struct gfs2_inode *dip, struct inode *inode) { struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); struct posix_acl *acl; - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; int error = 0; if (!sdp->sd_args.ar_posix_acl) diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 27c511a1cf05..6372a84728d7 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -259,7 +259,7 @@ static int jffs2_set_acl(struct inode *inode, int type, struct posix_acl *acl) return rc; } -int jffs2_init_acl_pre(struct inode *dir_i, struct inode *inode, mode_t *i_mode) +int jffs2_init_acl_pre(struct inode *dir_i, struct inode *inode, umode_t *i_mode) { struct posix_acl *acl; int rc; diff --git a/fs/jffs2/acl.h b/fs/jffs2/acl.h index b3421c78d9f8..9b477246f2a6 100644 --- a/fs/jffs2/acl.h +++ b/fs/jffs2/acl.h @@ -28,7 +28,7 @@ struct jffs2_acl_header { struct posix_acl *jffs2_get_acl(struct inode *inode, int type); extern int jffs2_acl_chmod(struct inode *); -extern int jffs2_init_acl_pre(struct inode *, struct inode *, mode_t *); +extern int jffs2_init_acl_pre(struct inode *, struct inode *, umode_t *); extern int jffs2_init_acl_post(struct inode *); extern const struct xattr_handler jffs2_acl_access_xattr_handler; diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index b81b35ddf4e4..bbcb9755dd2b 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -406,7 +406,7 @@ int jffs2_remount_fs (struct super_block *sb, int *flags, char *data) /* jffs2_new_inode: allocate a new inode and inocache, add it to the hash, fill in the raw_inode while you're at it. */ -struct inode *jffs2_new_inode (struct inode *dir_i, mode_t mode, struct jffs2_raw_inode *ri) +struct inode *jffs2_new_inode (struct inode *dir_i, umode_t mode, struct jffs2_raw_inode *ri) { struct inode *inode; struct super_block *sb = dir_i->i_sb; diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index 526979c607b6..6c1755c59c0f 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -173,7 +173,7 @@ int jffs2_do_setattr (struct inode *, struct iattr *); struct inode *jffs2_iget(struct super_block *, unsigned long); void jffs2_evict_inode (struct inode *); void jffs2_dirty_inode(struct inode *inode, int flags); -struct inode *jffs2_new_inode (struct inode *dir_i, mode_t mode, +struct inode *jffs2_new_inode (struct inode *dir_i, umode_t mode, struct jffs2_raw_inode *ri); int jffs2_statfs (struct dentry *, struct kstatfs *); int jffs2_remount_fs (struct super_block *, int *, char *); diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index b3a32caf2b45..45559dc3ea2f 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -127,16 +127,14 @@ int jfs_init_acl(tid_t tid, struct inode *inode, struct inode *dir) return PTR_ERR(acl); if (acl) { - mode_t mode = inode->i_mode; if (S_ISDIR(inode->i_mode)) { rc = jfs_set_acl(tid, inode, ACL_TYPE_DEFAULT, acl); if (rc) goto cleanup; } - rc = posix_acl_create(&acl, GFP_KERNEL, &mode); + rc = posix_acl_create(&acl, GFP_KERNEL, &inode->i_mode); if (rc < 0) goto cleanup; /* posix_acl_release(NULL) is no-op */ - inode->i_mode = mode; if (rc > 0) rc = jfs_set_acl(tid, inode, ACL_TYPE_ACCESS, acl); cleanup: diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index e49e73107e62..7ef23979896d 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -415,7 +415,7 @@ fail: } int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode, - mode_t mode) + umode_t mode) { struct posix_acl *dfacl, *acl; int error = 0; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 38053d823eb0..85f1690ca08c 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -316,7 +316,7 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, int flags, struct nfs_open_context *ctx) { struct nfs3_createdata *data; - mode_t mode = sattr->ia_mode; + umode_t mode = sattr->ia_mode; int status = -ENOMEM; dprintk("NFS call create %s\n", dentry->d_name.name); @@ -562,7 +562,7 @@ static int nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) { struct nfs3_createdata *data; - int mode = sattr->ia_mode; + umode_t mode = sattr->ia_mode; int status = -ENOMEM; dprintk("NFS call mkdir %s\n", dentry->d_name.name); @@ -681,7 +681,7 @@ nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr, dev_t rdev) { struct nfs3_createdata *data; - mode_t mode = sattr->ia_mode; + umode_t mode = sattr->ia_mode; int status = -ENOMEM; dprintk("NFS call mknod %s %u:%u\n", dentry->d_name.name, diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 783c58d9daf1..fbafc6e36e25 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -351,7 +351,7 @@ int ocfs2_init_acl(handle_t *handle, struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct posix_acl *acl = NULL; int ret = 0, ret2; - mode_t mode; + umode_t mode; if (!S_ISLNK(inode->i_mode)) { if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) { diff --git a/fs/posix_acl.c b/fs/posix_acl.c index d43729a760e2..f0a017edee1e 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -279,11 +279,11 @@ check_perm: * system calls. All permissions that are not granted by the acl are removed. * The permissions in the acl are changed to reflect the mode_p parameter. */ -static int posix_acl_create_masq(struct posix_acl *acl, mode_t *mode_p) +static int posix_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) { struct posix_acl_entry *pa, *pe; struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; - mode_t mode = *mode_p; + umode_t mode = *mode_p; int not_equiv = 0; /* assert(atomic_read(acl->a_refcount) == 1); */ @@ -382,7 +382,7 @@ static int posix_acl_chmod_masq(struct posix_acl *acl, mode_t mode) } int -posix_acl_create(struct posix_acl **acl, gfp_t gfp, mode_t *mode_p) +posix_acl_create(struct posix_acl **acl, gfp_t gfp, umode_t *mode_p) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 7362cf4c946a..89ebc77e0e9a 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -354,8 +354,6 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, return PTR_ERR(acl); if (acl) { - mode_t mode = inode->i_mode; - /* Copy the default ACL to the default ACL of a new directory */ if (S_ISDIR(inode->i_mode)) { err = reiserfs_set_acl(th, inode, ACL_TYPE_DEFAULT, @@ -366,12 +364,10 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, /* Now we reconcile the new ACL and the mode, potentially modifying both */ - err = posix_acl_create(&acl, GFP_NOFS, &mode); + err = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode); if (err < 0) return err; - inode->i_mode = mode; - /* If we need an ACL.. */ if (err > 0) err = reiserfs_set_acl(th, inode, ACL_TYPE_ACCESS, acl); diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c index 44ce51656804..bb85500e0b88 100644 --- a/fs/xfs/linux-2.6/xfs_acl.c +++ b/fs/xfs/linux-2.6/xfs_acl.c @@ -221,7 +221,7 @@ xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) } static int -xfs_set_mode(struct inode *inode, mode_t mode) +xfs_set_mode(struct inode *inode, umode_t mode) { int error = 0; @@ -267,7 +267,7 @@ posix_acl_default_exists(struct inode *inode) int xfs_inherit_acl(struct inode *inode, struct posix_acl *acl) { - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; int error = 0, inherit = 0; if (S_ISDIR(inode->i_mode)) { diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8b579beb6358..dda2ac8a5f7b 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -568,12 +568,12 @@ extern struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type); extern int nfs3_proc_setacl(struct inode *inode, int type, struct posix_acl *acl); extern int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode, - mode_t mode); + umode_t mode); extern void nfs3_forget_cached_acls(struct inode *inode); #else static inline int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode, - mode_t mode) + umode_t mode) { return 0; } diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 9a53b99818e2..bd8d0050d725 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -77,7 +77,7 @@ extern int posix_acl_valid(const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(mode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, mode_t *); -extern int posix_acl_create(struct posix_acl **, gfp_t, mode_t *); +extern int posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int posix_acl_chmod(struct posix_acl **, gfp_t, mode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); -- cgit v1.2.3 From d6952123b53cc8b334df69bba2cd0063b0d88f68 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jul 2011 18:56:36 -0400 Subject: switch posix_acl_equiv_mode() to umode_t * ... so that &inode->i_mode could be passed to it Signed-off-by: Al Viro --- fs/9p/acl.c | 2 +- fs/btrfs/acl.c | 5 +---- fs/ext2/acl.c | 4 +--- fs/ext3/acl.c | 4 +--- fs/ext4/acl.c | 4 +--- fs/generic_acl.c | 6 +----- fs/gfs2/acl.c | 2 +- fs/jffs2/acl.c | 2 +- fs/jfs/xattr.c | 4 +--- fs/ocfs2/acl.c | 2 +- fs/posix_acl.c | 4 ++-- fs/reiserfs/xattr_acl.c | 4 +--- fs/xfs/linux-2.6/xfs_acl.c | 2 +- include/linux/posix_acl.h | 2 +- 14 files changed, 15 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/fs/9p/acl.c b/fs/9p/acl.c index ad734e3220cf..9a1d42630751 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -319,7 +319,7 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; retval = posix_acl_equiv_mode(acl, &mode); if (retval < 0) goto err_out; diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 59086142c14d..4cc5c0164ed6 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -111,7 +111,6 @@ static int btrfs_set_acl(struct btrfs_trans_handle *trans, int ret, size = 0; const char *name; char *value = NULL; - mode_t mode; if (acl) { ret = posix_acl_valid(acl); @@ -122,13 +121,11 @@ static int btrfs_set_acl(struct btrfs_trans_handle *trans, switch (type) { case ACL_TYPE_ACCESS: - mode = inode->i_mode; name = POSIX_ACL_XATTR_ACCESS; if (acl) { - ret = posix_acl_equiv_mode(acl, &mode); + ret = posix_acl_equiv_mode(acl, &inode->i_mode); if (ret < 0) return ret; - inode->i_mode = mode; } ret = 0; break; diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 0ce740489ab1..35d6a3cfd9ff 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -194,12 +194,10 @@ ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl) case ACL_TYPE_ACCESS: name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - mode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); + error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) return error; else { - inode->i_mode = mode; inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); if (error == 0) diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index 74a3c6486f8f..3091f62e55b6 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -199,12 +199,10 @@ ext3_set_acl(handle_t *handle, struct inode *inode, int type, case ACL_TYPE_ACCESS: name_index = EXT3_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - mode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); + error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) return error; else { - inode->i_mode = mode; inode->i_ctime = CURRENT_TIME_SEC; ext3_mark_inode_dirty(handle, inode); if (error == 0) diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 74e469ccdf50..a5c29bb3b835 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -198,12 +198,10 @@ ext4_set_acl(handle_t *handle, struct inode *inode, int type, case ACL_TYPE_ACCESS: name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - mode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); + error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) return error; else { - inode->i_mode = mode; inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); if (error == 0) diff --git a/fs/generic_acl.c b/fs/generic_acl.c index 2dd434d6ff29..d0dddaceac59 100644 --- a/fs/generic_acl.c +++ b/fs/generic_acl.c @@ -82,18 +82,14 @@ generic_acl_set(struct dentry *dentry, const char *name, const void *value, return PTR_ERR(acl); } if (acl) { - mode_t mode; - error = posix_acl_valid(acl); if (error) goto failed; switch (type) { case ACL_TYPE_ACCESS: - mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); + error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) goto failed; - inode->i_mode = mode; inode->i_ctime = CURRENT_TIME; if (error == 0) { posix_acl_release(acl); diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 0ac3c53f928f..34501b64bc47 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -276,7 +276,7 @@ static int gfs2_xattr_system_set(struct dentry *dentry, const char *name, goto out_release; if (type == ACL_TYPE_ACCESS) { - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; error = posix_acl_equiv_mode(acl, &mode); if (error <= 0) { diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 6372a84728d7..926d02068a14 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -227,7 +227,7 @@ static int jffs2_set_acl(struct inode *inode, int type, struct posix_acl *acl) case ACL_TYPE_ACCESS: xprefix = JFFS2_XPREFIX_ACL_ACCESS; if (acl) { - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; rc = posix_acl_equiv_mode(acl, &mode); if (rc < 0) return rc; diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 24838f1eeee5..e87fedef23db 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -693,8 +693,7 @@ static int can_set_system_xattr(struct inode *inode, const char *name, return rc; } if (acl) { - mode_t mode = inode->i_mode; - rc = posix_acl_equiv_mode(acl, &mode); + rc = posix_acl_equiv_mode(acl, &inode->i_mode); posix_acl_release(acl); if (rc < 0) { printk(KERN_ERR @@ -702,7 +701,6 @@ static int can_set_system_xattr(struct inode *inode, const char *name, rc); return rc; } - inode->i_mode = mode; mark_inode_dirty(inode); } /* diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index fbafc6e36e25..a7219075b4de 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -247,7 +247,7 @@ static int ocfs2_set_acl(handle_t *handle, case ACL_TYPE_ACCESS: name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; ret = posix_acl_equiv_mode(acl, &mode); if (ret < 0) return ret; diff --git a/fs/posix_acl.c b/fs/posix_acl.c index f0a017edee1e..3d943be6761c 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -149,10 +149,10 @@ posix_acl_valid(const struct posix_acl *acl) * file mode permission bits, or else 1. Returns -E... on error. */ int -posix_acl_equiv_mode(const struct posix_acl *acl, mode_t *mode_p) +posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p) { const struct posix_acl_entry *pa, *pe; - mode_t mode = 0; + umode_t mode = 0; int not_equiv = 0; FOREACH_ACL_ENTRY(pa, acl, pe) { diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 89ebc77e0e9a..6da0396e5052 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -272,12 +272,10 @@ reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - mode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); + error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) return error; else { - inode->i_mode = mode; if (error == 0) acl = NULL; } diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c index bb85500e0b88..b6c4b3795c4a 100644 --- a/fs/xfs/linux-2.6/xfs_acl.c +++ b/fs/xfs/linux-2.6/xfs_acl.c @@ -381,7 +381,7 @@ xfs_xattr_acl_set(struct dentry *dentry, const char *name, goto out_release; if (type == ACL_TYPE_ACCESS) { - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; error = posix_acl_equiv_mode(acl, &mode); if (error <= 0) { diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index bd8d0050d725..529c32ad58c0 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -76,7 +76,7 @@ extern struct posix_acl *posix_acl_alloc(int, gfp_t); extern int posix_acl_valid(const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(mode_t, gfp_t); -extern int posix_acl_equiv_mode(const struct posix_acl *, mode_t *); +extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int posix_acl_chmod(struct posix_acl **, gfp_t, mode_t); -- cgit v1.2.3 From 3a5fba19b080b365d67866db38e32e6a4a2089e8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jul 2011 19:01:48 -0400 Subject: switch posix_acl_from_mode() to umode_t ... seeing that this is what all callers pass to it anyway. Signed-off-by: Al Viro --- fs/posix_acl.c | 2 +- include/linux/posix_acl.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 3d943be6761c..4e16e8001982 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -188,7 +188,7 @@ posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p) * Create an ACL representing the file mode permission bits of an inode. */ struct posix_acl * -posix_acl_from_mode(mode_t mode, gfp_t flags) +posix_acl_from_mode(umode_t mode, gfp_t flags) { struct posix_acl *acl = posix_acl_alloc(3, flags); if (!acl) diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 529c32ad58c0..16ecfb485d28 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -75,7 +75,7 @@ extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(int, gfp_t); extern int posix_acl_valid(const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); -extern struct posix_acl *posix_acl_from_mode(mode_t, gfp_t); +extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int posix_acl_chmod(struct posix_acl **, gfp_t, mode_t); -- cgit v1.2.3 From 86bc704db0ab7e69230f79bc7d124e063259abc6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jul 2011 19:03:11 -0400 Subject: switch posix_acl_chmod() to umode_t again, that's what all callers pass to it Signed-off-by: Al Viro --- fs/posix_acl.c | 4 ++-- include/linux/posix_acl.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 4e16e8001982..10027b42b7e2 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -336,7 +336,7 @@ static int posix_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) /* * Modify the ACL for the chmod syscall. */ -static int posix_acl_chmod_masq(struct posix_acl *acl, mode_t mode) +static int posix_acl_chmod_masq(struct posix_acl *acl, umode_t mode) { struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; struct posix_acl_entry *pa, *pe; @@ -400,7 +400,7 @@ posix_acl_create(struct posix_acl **acl, gfp_t gfp, umode_t *mode_p) EXPORT_SYMBOL(posix_acl_create); int -posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, mode_t mode) +posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, umode_t mode) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 16ecfb485d28..951bba82d50d 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -78,7 +78,7 @@ extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int posix_acl_create(struct posix_acl **, gfp_t, umode_t *); -extern int posix_acl_chmod(struct posix_acl **, gfp_t, mode_t); +extern int posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); -- cgit v1.2.3 From a6e50b409d3f9e0833e69c3c9cca822e8fa4adbb Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 2 Aug 2011 12:32:04 +0100 Subject: dm snapshot: skip reading origin when overwriting complete chunk If we write a full chunk in the snapshot, skip reading the origin device because the whole chunk will be overwritten anyway. This patch changes the snapshot write logic when a full chunk is written. In this case: 1. allocate the exception 2. dispatch the bio (but don't report the bio completion to device mapper) 3. write the exception record 4. report bio completed Callbacks must be done through the kcopyd thread, because callbacks must not race with each other. So we create two new functions: dm_kcopyd_prepare_callback: allocate a job structure and prepare the callback. (This function must not be called from interrupt context.) dm_kcopyd_do_callback: submit callback. (This function may be called from interrupt context.) Performance test (on snapshots with 4k chunk size): without the patch: non-direct-io sequential write (dd): 17.7MB/s direct-io sequential write (dd): 20.9MB/s non-direct-io random write (mkfs.ext2): 0.44s with the patch: non-direct-io sequential write (dd): 26.5MB/s direct-io sequential write (dd): 33.2MB/s non-direct-io random write (mkfs.ext2): 0.27s Signed-off-by: Mikulas Patocka Signed-off-by: Alasdair G Kergon --- drivers/md/dm-kcopyd.c | 31 ++++++++++++++++++++++++ drivers/md/dm-snap.c | 60 ++++++++++++++++++++++++++++++++++++++++++++--- include/linux/dm-kcopyd.h | 15 ++++++++++++ 3 files changed, 103 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 98725e119324..f82147029636 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -617,6 +617,37 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from, } EXPORT_SYMBOL(dm_kcopyd_copy); +void *dm_kcopyd_prepare_callback(struct dm_kcopyd_client *kc, + dm_kcopyd_notify_fn fn, void *context) +{ + struct kcopyd_job *job; + + job = mempool_alloc(kc->job_pool, GFP_NOIO); + + memset(job, 0, sizeof(struct kcopyd_job)); + job->kc = kc; + job->fn = fn; + job->context = context; + + atomic_inc(&kc->nr_jobs); + + return job; +} +EXPORT_SYMBOL(dm_kcopyd_prepare_callback); + +void dm_kcopyd_do_callback(void *j, int read_err, unsigned long write_err) +{ + struct kcopyd_job *job = j; + struct dm_kcopyd_client *kc = job->kc; + + job->read_err = read_err; + job->write_err = write_err; + + push(&kc->complete_jobs, job); + wake(kc); +} +EXPORT_SYMBOL(dm_kcopyd_do_callback); + /* * Cancels a kcopyd job, eg. someone might be deactivating a * mirror. diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 94dee05dd28e..6f758870fc19 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -170,6 +170,13 @@ struct dm_snap_pending_exception { * kcopyd. */ int started; + + /* + * For writing a complete chunk, bypassing the copy. + */ + struct bio *full_bio; + bio_end_io_t *full_bio_end_io; + void *full_bio_private; }; /* @@ -1369,6 +1376,7 @@ static void pending_complete(struct dm_snap_pending_exception *pe, int success) struct dm_snapshot *s = pe->snap; struct bio *origin_bios = NULL; struct bio *snapshot_bios = NULL; + struct bio *full_bio = NULL; int error = 0; if (!success) { @@ -1408,6 +1416,11 @@ out: dm_remove_exception(&pe->e); snapshot_bios = bio_list_get(&pe->snapshot_bios); origin_bios = bio_list_get(&pe->origin_bios); + full_bio = pe->full_bio; + if (full_bio) { + full_bio->bi_end_io = pe->full_bio_end_io; + full_bio->bi_private = pe->full_bio_private; + } free_pending_exception(pe); increment_pending_exceptions_done_count(); @@ -1415,10 +1428,15 @@ out: up_write(&s->lock); /* Submit any pending write bios */ - if (error) + if (error) { + if (full_bio) + bio_io_error(full_bio); error_bios(snapshot_bios); - else + } else { + if (full_bio) + bio_endio(full_bio, 0); flush_bios(snapshot_bios); + } retry_origin_bios(s, origin_bios); } @@ -1472,6 +1490,32 @@ static void start_copy(struct dm_snap_pending_exception *pe) dm_kcopyd_copy(s->kcopyd_client, &src, 1, &dest, 0, copy_callback, pe); } +static void full_bio_end_io(struct bio *bio, int error) +{ + void *callback_data = bio->bi_private; + + dm_kcopyd_do_callback(callback_data, 0, error ? 1 : 0); +} + +static void start_full_bio(struct dm_snap_pending_exception *pe, + struct bio *bio) +{ + struct dm_snapshot *s = pe->snap; + void *callback_data; + + pe->full_bio = bio; + pe->full_bio_end_io = bio->bi_end_io; + pe->full_bio_private = bio->bi_private; + + callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client, + copy_callback, pe); + + bio->bi_end_io = full_bio_end_io; + bio->bi_private = callback_data; + + generic_make_request(bio); +} + static struct dm_snap_pending_exception * __lookup_pending_exception(struct dm_snapshot *s, chunk_t chunk) { @@ -1507,6 +1551,7 @@ __find_pending_exception(struct dm_snapshot *s, bio_list_init(&pe->origin_bios); bio_list_init(&pe->snapshot_bios); pe->started = 0; + pe->full_bio = NULL; if (s->store->type->prepare_exception(s->store, &pe->e)) { free_pending_exception(pe); @@ -1600,10 +1645,19 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio, } remap_exception(s, &pe->e, bio, chunk); - bio_list_add(&pe->snapshot_bios, bio); r = DM_MAPIO_SUBMITTED; + if (!pe->started && + bio->bi_size == (s->store->chunk_size << SECTOR_SHIFT)) { + pe->started = 1; + up_write(&s->lock); + start_full_bio(pe, bio); + goto out; + } + + bio_list_add(&pe->snapshot_bios, bio); + if (!pe->started) { /* this is protected by snap->lock */ pe->started = 1; diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index 298d587e349b..5e54458e920f 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -42,5 +42,20 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from, unsigned num_dests, struct dm_io_region *dests, unsigned flags, dm_kcopyd_notify_fn fn, void *context); +/* + * Prepare a callback and submit it via the kcopyd thread. + * + * dm_kcopyd_prepare_callback allocates a callback structure and returns it. + * It must not be called from interrupt context. + * The returned value should be passed into dm_kcopyd_do_callback. + * + * dm_kcopyd_do_callback submits the callback. + * It may be called from interrupt context. + * The callback is issued from the kcopyd thread. + */ +void *dm_kcopyd_prepare_callback(struct dm_kcopyd_client *kc, + dm_kcopyd_notify_fn fn, void *context); +void dm_kcopyd_do_callback(void *job, int read_err, unsigned long write_err); + #endif /* __KERNEL__ */ #endif /* _LINUX_DM_KCOPYD_H */ -- cgit v1.2.3 From 498f0103ea13123e007660def9072a0b7dd1c599 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 2 Aug 2011 12:32:04 +0100 Subject: dm table: share target argument parsing functions Move multipath target argument parsing code into dm-table so other targets can share it. Signed-off-by: Mike Snitzer Signed-off-by: Alasdair G Kergon --- drivers/md/dm-crypt.c | 7 +- drivers/md/dm-mpath.c | 152 ++++++++++++------------------------------ drivers/md/dm-table.c | 57 ++++++++++++++++ include/linux/device-mapper.h | 43 ++++++++++++ 4 files changed, 147 insertions(+), 112 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index f5406766ece3..b79e7472a9b3 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -30,7 +30,6 @@ #include #define DM_MSG_PREFIX "crypt" -#define MESG_STR(x) x, sizeof(x) /* * context holding the current state of a multi-part conversion @@ -1770,12 +1769,12 @@ static int crypt_message(struct dm_target *ti, unsigned argc, char **argv) if (argc < 2) goto error; - if (!strnicmp(argv[0], MESG_STR("key"))) { + if (!strcasecmp(argv[0], "key")) { if (!test_bit(DM_CRYPT_SUSPENDED, &cc->flags)) { DMWARN("not suspended during key manipulation."); return -EINVAL; } - if (argc == 3 && !strnicmp(argv[1], MESG_STR("set"))) { + if (argc == 3 && !strcasecmp(argv[1], "set")) { ret = crypt_set_key(cc, argv[2]); if (ret) return ret; @@ -1783,7 +1782,7 @@ static int crypt_message(struct dm_target *ti, unsigned argc, char **argv) ret = cc->iv_gen_ops->init(cc); return ret; } - if (argc == 2 && !strnicmp(argv[1], MESG_STR("wipe"))) { + if (argc == 2 && !strcasecmp(argv[1], "wipe")) { if (cc->iv_gen_ops && cc->iv_gen_ops->wipe) { ret = cc->iv_gen_ops->wipe(cc); if (ret) diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index adf851a081bd..5e0090ef4182 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -22,7 +22,6 @@ #include #define DM_MSG_PREFIX "multipath" -#define MESG_STR(x) x, sizeof(x) #define DM_PG_INIT_DELAY_MSECS 2000 #define DM_PG_INIT_DELAY_DEFAULT ((unsigned) -1) @@ -505,80 +504,29 @@ static void trigger_event(struct work_struct *work) * <#paths> <#per-path selector args> * [ []* ]+ ]+ *---------------------------------------------------------------*/ -struct param { - unsigned min; - unsigned max; - char *error; -}; - -static int read_param(struct param *param, char *str, unsigned *v, char **error) -{ - if (!str || - (sscanf(str, "%u", v) != 1) || - (*v < param->min) || - (*v > param->max)) { - *error = param->error; - return -EINVAL; - } - - return 0; -} - -struct arg_set { - unsigned argc; - char **argv; -}; - -static char *shift(struct arg_set *as) -{ - char *r; - - if (as->argc) { - as->argc--; - r = *as->argv; - as->argv++; - return r; - } - - return NULL; -} - -static void consume(struct arg_set *as, unsigned n) -{ - BUG_ON (as->argc < n); - as->argc -= n; - as->argv += n; -} - -static int parse_path_selector(struct arg_set *as, struct priority_group *pg, +static int parse_path_selector(struct dm_arg_set *as, struct priority_group *pg, struct dm_target *ti) { int r; struct path_selector_type *pst; unsigned ps_argc; - static struct param _params[] = { + static struct dm_arg _args[] = { {0, 1024, "invalid number of path selector args"}, }; - pst = dm_get_path_selector(shift(as)); + pst = dm_get_path_selector(dm_shift_arg(as)); if (!pst) { ti->error = "unknown path selector type"; return -EINVAL; } - r = read_param(_params, shift(as), &ps_argc, &ti->error); + r = dm_read_arg_group(_args, as, &ps_argc, &ti->error); if (r) { dm_put_path_selector(pst); return -EINVAL; } - if (ps_argc > as->argc) { - dm_put_path_selector(pst); - ti->error = "not enough arguments for path selector"; - return -EINVAL; - } - r = pst->create(&pg->ps, ps_argc, as->argv); if (r) { dm_put_path_selector(pst); @@ -587,12 +535,12 @@ static int parse_path_selector(struct arg_set *as, struct priority_group *pg, } pg->ps.type = pst; - consume(as, ps_argc); + dm_consume_args(as, ps_argc); return 0; } -static struct pgpath *parse_path(struct arg_set *as, struct path_selector *ps, +static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps, struct dm_target *ti) { int r; @@ -609,7 +557,7 @@ static struct pgpath *parse_path(struct arg_set *as, struct path_selector *ps, if (!p) return ERR_PTR(-ENOMEM); - r = dm_get_device(ti, shift(as), dm_table_get_mode(ti->table), + r = dm_get_device(ti, dm_shift_arg(as), dm_table_get_mode(ti->table), &p->path.dev); if (r) { ti->error = "error getting device"; @@ -660,16 +608,16 @@ static struct pgpath *parse_path(struct arg_set *as, struct path_selector *ps, return ERR_PTR(r); } -static struct priority_group *parse_priority_group(struct arg_set *as, +static struct priority_group *parse_priority_group(struct dm_arg_set *as, struct multipath *m) { - static struct param _params[] = { + static struct dm_arg _args[] = { {1, 1024, "invalid number of paths"}, {0, 1024, "invalid number of selector args"} }; int r; - unsigned i, nr_selector_args, nr_params; + unsigned i, nr_selector_args, nr_args; struct priority_group *pg; struct dm_target *ti = m->ti; @@ -693,26 +641,26 @@ static struct priority_group *parse_priority_group(struct arg_set *as, /* * read the paths */ - r = read_param(_params, shift(as), &pg->nr_pgpaths, &ti->error); + r = dm_read_arg(_args, as, &pg->nr_pgpaths, &ti->error); if (r) goto bad; - r = read_param(_params + 1, shift(as), &nr_selector_args, &ti->error); + r = dm_read_arg(_args + 1, as, &nr_selector_args, &ti->error); if (r) goto bad; - nr_params = 1 + nr_selector_args; + nr_args = 1 + nr_selector_args; for (i = 0; i < pg->nr_pgpaths; i++) { struct pgpath *pgpath; - struct arg_set path_args; + struct dm_arg_set path_args; - if (as->argc < nr_params) { + if (as->argc < nr_args) { ti->error = "not enough path parameters"; r = -EINVAL; goto bad; } - path_args.argc = nr_params; + path_args.argc = nr_args; path_args.argv = as->argv; pgpath = parse_path(&path_args, &pg->ps, ti); @@ -723,7 +671,7 @@ static struct priority_group *parse_priority_group(struct arg_set *as, pgpath->pg = pg; list_add_tail(&pgpath->list, &pg->pgpaths); - consume(as, nr_params); + dm_consume_args(as, nr_args); } return pg; @@ -733,28 +681,23 @@ static struct priority_group *parse_priority_group(struct arg_set *as, return ERR_PTR(r); } -static int parse_hw_handler(struct arg_set *as, struct multipath *m) +static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m) { unsigned hw_argc; int ret; struct dm_target *ti = m->ti; - static struct param _params[] = { + static struct dm_arg _args[] = { {0, 1024, "invalid number of hardware handler args"}, }; - if (read_param(_params, shift(as), &hw_argc, &ti->error)) + if (dm_read_arg_group(_args, as, &hw_argc, &ti->error)) return -EINVAL; if (!hw_argc) return 0; - if (hw_argc > as->argc) { - ti->error = "not enough arguments for hardware handler"; - return -EINVAL; - } - - m->hw_handler_name = kstrdup(shift(as), GFP_KERNEL); + m->hw_handler_name = kstrdup(dm_shift_arg(as), GFP_KERNEL); request_module("scsi_dh_%s", m->hw_handler_name); if (scsi_dh_handler_exist(m->hw_handler_name) == 0) { ti->error = "unknown hardware handler type"; @@ -778,7 +721,7 @@ static int parse_hw_handler(struct arg_set *as, struct multipath *m) for (i = 0, p+=j+1; i <= hw_argc - 2; i++, p+=j+1) j = sprintf(p, "%s", as->argv[i]); } - consume(as, hw_argc - 1); + dm_consume_args(as, hw_argc - 1); return 0; fail: @@ -787,52 +730,45 @@ fail: return ret; } -static int parse_features(struct arg_set *as, struct multipath *m) +static int parse_features(struct dm_arg_set *as, struct multipath *m) { int r; unsigned argc; struct dm_target *ti = m->ti; - const char *param_name; + const char *arg_name; - static struct param _params[] = { + static struct dm_arg _args[] = { {0, 5, "invalid number of feature args"}, {1, 50, "pg_init_retries must be between 1 and 50"}, {0, 60000, "pg_init_delay_msecs must be between 0 and 60000"}, }; - r = read_param(_params, shift(as), &argc, &ti->error); + r = dm_read_arg_group(_args, as, &argc, &ti->error); if (r) return -EINVAL; if (!argc) return 0; - if (argc > as->argc) { - ti->error = "not enough arguments for features"; - return -EINVAL; - } - do { - param_name = shift(as); + arg_name = dm_shift_arg(as); argc--; - if (!strnicmp(param_name, MESG_STR("queue_if_no_path"))) { + if (!strcasecmp(arg_name, "queue_if_no_path")) { r = queue_if_no_path(m, 1, 0); continue; } - if (!strnicmp(param_name, MESG_STR("pg_init_retries")) && + if (!strcasecmp(arg_name, "pg_init_retries") && (argc >= 1)) { - r = read_param(_params + 1, shift(as), - &m->pg_init_retries, &ti->error); + r = dm_read_arg(_args + 1, as, &m->pg_init_retries, &ti->error); argc--; continue; } - if (!strnicmp(param_name, MESG_STR("pg_init_delay_msecs")) && + if (!strcasecmp(arg_name, "pg_init_delay_msecs") && (argc >= 1)) { - r = read_param(_params + 2, shift(as), - &m->pg_init_delay_msecs, &ti->error); + r = dm_read_arg(_args + 2, as, &m->pg_init_delay_msecs, &ti->error); argc--; continue; } @@ -847,15 +783,15 @@ static int parse_features(struct arg_set *as, struct multipath *m) static int multipath_ctr(struct dm_target *ti, unsigned int argc, char **argv) { - /* target parameters */ - static struct param _params[] = { + /* target arguments */ + static struct dm_arg _args[] = { {0, 1024, "invalid number of priority groups"}, {0, 1024, "invalid initial priority group number"}, }; int r; struct multipath *m; - struct arg_set as; + struct dm_arg_set as; unsigned pg_count = 0; unsigned next_pg_num; @@ -876,11 +812,11 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc, if (r) goto bad; - r = read_param(_params, shift(&as), &m->nr_priority_groups, &ti->error); + r = dm_read_arg(_args, &as, &m->nr_priority_groups, &ti->error); if (r) goto bad; - r = read_param(_params + 1, shift(&as), &next_pg_num, &ti->error); + r = dm_read_arg(_args + 1, &as, &next_pg_num, &ti->error); if (r) goto bad; @@ -1510,10 +1446,10 @@ static int multipath_message(struct dm_target *ti, unsigned argc, char **argv) } if (argc == 1) { - if (!strnicmp(argv[0], MESG_STR("queue_if_no_path"))) { + if (!strcasecmp(argv[0], "queue_if_no_path")) { r = queue_if_no_path(m, 1, 0); goto out; - } else if (!strnicmp(argv[0], MESG_STR("fail_if_no_path"))) { + } else if (!strcasecmp(argv[0], "fail_if_no_path")) { r = queue_if_no_path(m, 0, 0); goto out; } @@ -1524,18 +1460,18 @@ static int multipath_message(struct dm_target *ti, unsigned argc, char **argv) goto out; } - if (!strnicmp(argv[0], MESG_STR("disable_group"))) { + if (!strcasecmp(argv[0], "disable_group")) { r = bypass_pg_num(m, argv[1], 1); goto out; - } else if (!strnicmp(argv[0], MESG_STR("enable_group"))) { + } else if (!strcasecmp(argv[0], "enable_group")) { r = bypass_pg_num(m, argv[1], 0); goto out; - } else if (!strnicmp(argv[0], MESG_STR("switch_group"))) { + } else if (!strcasecmp(argv[0], "switch_group")) { r = switch_pg_num(m, argv[1]); goto out; - } else if (!strnicmp(argv[0], MESG_STR("reinstate_path"))) + } else if (!strcasecmp(argv[0], "reinstate_path")) action = reinstate_path; - else if (!strnicmp(argv[0], MESG_STR("fail_path"))) + else if (!strcasecmp(argv[0], "fail_path")) action = fail_path; else { DMWARN("Unrecognised multipath message received."); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 03516c7f5be1..259ce99302fc 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -797,6 +797,63 @@ int dm_table_add_target(struct dm_table *t, const char *type, return r; } +/* + * Target argument parsing helpers. + */ +static int validate_next_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, + unsigned *value, char **error, unsigned grouped) +{ + const char *arg_str = dm_shift_arg(arg_set); + + if (!arg_str || + (sscanf(arg_str, "%u", value) != 1) || + (*value < arg->min) || + (*value > arg->max) || + (grouped && arg_set->argc < *value)) { + *error = arg->error; + return -EINVAL; + } + + return 0; +} + +int dm_read_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, + unsigned *value, char **error) +{ + return validate_next_arg(arg, arg_set, value, error, 0); +} +EXPORT_SYMBOL(dm_read_arg); + +int dm_read_arg_group(struct dm_arg *arg, struct dm_arg_set *arg_set, + unsigned *value, char **error) +{ + return validate_next_arg(arg, arg_set, value, error, 1); +} +EXPORT_SYMBOL(dm_read_arg_group); + +const char *dm_shift_arg(struct dm_arg_set *as) +{ + char *r; + + if (as->argc) { + as->argc--; + r = *as->argv; + as->argv++; + return r; + } + + return NULL; +} +EXPORT_SYMBOL(dm_shift_arg); + +void dm_consume_args(struct dm_arg_set *as, unsigned num_args) +{ + BUG_ON(as->argc < num_args); + as->argc -= num_args; + as->argv += num_args; +} +EXPORT_SYMBOL(dm_consume_args); + static int dm_table_set_type(struct dm_table *t) { unsigned i; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 4427e0454051..3fa1f3d90ce0 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -208,6 +208,49 @@ struct dm_target_callbacks { int dm_register_target(struct target_type *t); void dm_unregister_target(struct target_type *t); +/* + * Target argument parsing. + */ +struct dm_arg_set { + unsigned argc; + char **argv; +}; + +/* + * The minimum and maximum value of a numeric argument, together with + * the error message to use if the number is found to be outside that range. + */ +struct dm_arg { + unsigned min; + unsigned max; + char *error; +}; + +/* + * Validate the next argument, either returning it as *value or, if invalid, + * returning -EINVAL and setting *error. + */ +int dm_read_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, + unsigned *value, char **error); + +/* + * Process the next argument as the start of a group containing between + * arg->min and arg->max further arguments. Either return the size as + * *num_args or, if invalid, return -EINVAL and set *error. + */ +int dm_read_arg_group(struct dm_arg *arg, struct dm_arg_set *arg_set, + unsigned *num_args, char **error); + +/* + * Return the current argument and shift to the next. + */ +const char *dm_shift_arg(struct dm_arg_set *as); + +/* + * Move through num_args arguments. + */ +void dm_consume_args(struct dm_arg_set *as, unsigned num_args); + /*----------------------------------------------------------------- * Functions for creating and manipulating mapped devices. * Drop the reference with dm_put when you finish with the object. -- cgit v1.2.3 From 0ddf9644cc26e74ed671525e61a17bdbebf18da6 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 2 Aug 2011 12:32:06 +0100 Subject: dm ioctl: fill in device parameters in more ioctls Move parameter filling from find_device to __find_device_hash_cell. This patch causes ioctls using __find_device_hash_cell (DM_DEV_REMOVE_CMD, DM_DEV_SUSPEND_CMD - resume, DM_TABLE_CLEAR_CMD) to return device parameters, bringing them into line with the other ioctls. Signed-off-by: Mikulas Patocka Signed-off-by: Alasdair G Kergon --- drivers/md/dm-ioctl.c | 63 +++++++++++++++++++++++++++--------------------- include/linux/dm-ioctl.h | 4 +-- 2 files changed, 38 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 1622a6bc0bfd..99d38a6925a4 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -719,24 +719,49 @@ static int dev_create(struct dm_ioctl *param, size_t param_size) static struct hash_cell *__find_device_hash_cell(struct dm_ioctl *param) { struct mapped_device *md; - void *mdptr = NULL; + struct hash_cell *hc = NULL; - if (*param->uuid) - return __get_uuid_cell(param->uuid); + if (*param->uuid) { + hc = __get_uuid_cell(param->uuid); + if (!hc) + return NULL; + goto fill_params; + } - if (*param->name) - return __get_name_cell(param->name); + if (*param->name) { + hc = __get_name_cell(param->name); + if (!hc) + return NULL; + goto fill_params; + } md = dm_get_md(huge_decode_dev(param->dev)); if (!md) - goto out; + return NULL; - mdptr = dm_get_mdptr(md); - if (!mdptr) + hc = dm_get_mdptr(md); + if (!hc) { dm_put(md); + return NULL; + } -out: - return mdptr; +fill_params: + /* + * Sneakily write in both the name and the uuid + * while we have the cell. + */ + strlcpy(param->name, hc->name, sizeof(param->name)); + if (hc->uuid) + strlcpy(param->uuid, hc->uuid, sizeof(param->uuid)); + else + param->uuid[0] = '\0'; + + if (hc->new_map) + param->flags |= DM_INACTIVE_PRESENT_FLAG; + else + param->flags &= ~DM_INACTIVE_PRESENT_FLAG; + + return hc; } static struct mapped_device *find_device(struct dm_ioctl *param) @@ -746,24 +771,8 @@ static struct mapped_device *find_device(struct dm_ioctl *param) down_read(&_hash_lock); hc = __find_device_hash_cell(param); - if (hc) { + if (hc) md = hc->md; - - /* - * Sneakily write in both the name and the uuid - * while we have the cell. - */ - strlcpy(param->name, hc->name, sizeof(param->name)); - if (hc->uuid) - strlcpy(param->uuid, hc->uuid, sizeof(param->uuid)); - else - param->uuid[0] = '\0'; - - if (hc->new_map) - param->flags |= DM_INACTIVE_PRESENT_FLAG; - else - param->flags &= ~DM_INACTIVE_PRESENT_FLAG; - } up_read(&_hash_lock); return md; diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index 3708455ee6c3..0cb8eff76bd6 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -267,9 +267,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 20 +#define DM_VERSION_MINOR 21 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2011-02-02)" +#define DM_VERSION_EXTRA "-ioctl (2011-07-06)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From aac285c6cb9622f1cc05ed162604bf5ad2da9a8d Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Tue, 2 Aug 2011 15:45:07 +0100 Subject: of: constify property name parameters for helper functions The helper functions for reading u32 integers, u32 arrays and strings should have the property name as a const pointer. Cc: Grant Likely Signed-off-by: Jamie Iles Signed-off-by: Grant Likely --- drivers/of/base.c | 7 ++++--- include/linux/of.h | 15 +++++++++------ 2 files changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/base.c b/drivers/of/base.c index 02ed36719def..3ff22e32b602 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -610,8 +610,9 @@ EXPORT_SYMBOL(of_find_node_by_phandle); * * The out_value is modified only if a valid u32 value can be decoded. */ -int of_property_read_u32_array(const struct device_node *np, char *propname, - u32 *out_values, size_t sz) +int of_property_read_u32_array(const struct device_node *np, + const char *propname, u32 *out_values, + size_t sz) { struct property *prop = of_find_property(np, propname, NULL); const __be32 *val; @@ -645,7 +646,7 @@ EXPORT_SYMBOL_GPL(of_property_read_u32_array); * * The out_string pointer is modified only if a valid string can be decoded. */ -int of_property_read_string(struct device_node *np, char *propname, +int of_property_read_string(struct device_node *np, const char *propname, const char **out_string) { struct property *prop = of_find_property(np, propname, NULL); diff --git a/include/linux/of.h b/include/linux/of.h index bd716f8908de..0085bb01c041 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -196,12 +196,13 @@ extern struct property *of_find_property(const struct device_node *np, const char *name, int *lenp); extern int of_property_read_u32_array(const struct device_node *np, - char *propname, + const char *propname, u32 *out_values, size_t sz); -extern int of_property_read_string(struct device_node *np, char *propname, - const char **out_string); +extern int of_property_read_string(struct device_node *np, + const char *propname, + const char **out_string); extern int of_device_is_compatible(const struct device_node *device, const char *); extern int of_device_is_available(const struct device_node *device); @@ -242,13 +243,15 @@ static inline bool of_have_populated_dt(void) } static inline int of_property_read_u32_array(const struct device_node *np, - char *propname, u32 *out_values, size_t sz) + const char *propname, + u32 *out_values, size_t sz) { return -ENOSYS; } static inline int of_property_read_string(struct device_node *np, - char *propname, const char **out_string) + const char *propname, + const char **out_string) { return -ENOSYS; } @@ -256,7 +259,7 @@ static inline int of_property_read_string(struct device_node *np, #endif /* CONFIG_OF */ static inline int of_property_read_u32(const struct device_node *np, - char *propname, + const char *propname, u32 *out_value) { return of_property_read_u32_array(np, propname, out_value, 1); -- cgit v1.2.3 From 31f5396ad3bde23c8416e8d23ba425e27f413314 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 28 Jul 2011 13:48:42 -0700 Subject: thermal: make THERMAL_HWMON implementation fully internal THERMAL_HWMON is implemented inside the thermal_sys driver and has no effect on drivers implementing thermal zones, so they shouldn't see anything related to it in . Making the THERMAL_HWMON implementation fully internal has two advantages beyond the cleaner design: * This avoids rebuilding all thermal drivers if the THERMAL_HWMON implementation changes, or if CONFIG_THERMAL_HWMON gets enabled or disabled. * This avoids breaking the thermal kABI in these cases too, which should make distributions happy. The only drawback I can see is slightly higher memory fragmentation, as the number of kzalloc() calls will increase by one per thermal zone. But I doubt it will be a problem in practice, as I've never seen a system with more than two thermal zones. Signed-off-by: Jean Delvare Cc: Rene Herman Acked-by: Guenter Roeck Signed-off-by: Andrew Morton Signed-off-by: Len Brown --- drivers/thermal/thermal_sys.c | 117 +++++++++++++++++++++++++++++++++--------- include/linux/thermal.h | 22 -------- 2 files changed, 92 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c index b6353d61fac5..708f8e92771a 100644 --- a/drivers/thermal/thermal_sys.c +++ b/drivers/thermal/thermal_sys.c @@ -420,6 +420,29 @@ thermal_cooling_device_trip_point_show(struct device *dev, /* hwmon sys I/F */ #include + +/* thermal zone devices with the same type share one hwmon device */ +struct thermal_hwmon_device { + char type[THERMAL_NAME_LENGTH]; + struct device *device; + int count; + struct list_head tz_list; + struct list_head node; +}; + +struct thermal_hwmon_attr { + struct device_attribute attr; + char name[16]; +}; + +/* one temperature input for each thermal zone */ +struct thermal_hwmon_temp { + struct list_head hwmon_node; + struct thermal_zone_device *tz; + struct thermal_hwmon_attr temp_input; /* hwmon sys attr */ + struct thermal_hwmon_attr temp_crit; /* hwmon sys attr */ +}; + static LIST_HEAD(thermal_hwmon_list); static ssize_t @@ -437,9 +460,10 @@ temp_input_show(struct device *dev, struct device_attribute *attr, char *buf) int ret; struct thermal_hwmon_attr *hwmon_attr = container_of(attr, struct thermal_hwmon_attr, attr); - struct thermal_zone_device *tz - = container_of(hwmon_attr, struct thermal_zone_device, + struct thermal_hwmon_temp *temp + = container_of(hwmon_attr, struct thermal_hwmon_temp, temp_input); + struct thermal_zone_device *tz = temp->tz; ret = tz->ops->get_temp(tz, &temperature); @@ -455,9 +479,10 @@ temp_crit_show(struct device *dev, struct device_attribute *attr, { struct thermal_hwmon_attr *hwmon_attr = container_of(attr, struct thermal_hwmon_attr, attr); - struct thermal_zone_device *tz - = container_of(hwmon_attr, struct thermal_zone_device, + struct thermal_hwmon_temp *temp + = container_of(hwmon_attr, struct thermal_hwmon_temp, temp_crit); + struct thermal_zone_device *tz = temp->tz; long temperature; int ret; @@ -485,10 +510,29 @@ thermal_hwmon_lookup_by_type(const struct thermal_zone_device *tz) return NULL; } +/* Find the temperature input matching a given thermal zone */ +static struct thermal_hwmon_temp * +thermal_hwmon_lookup_temp(const struct thermal_hwmon_device *hwmon, + const struct thermal_zone_device *tz) +{ + struct thermal_hwmon_temp *temp; + + mutex_lock(&thermal_list_lock); + list_for_each_entry(temp, &hwmon->tz_list, hwmon_node) + if (temp->tz == tz) { + mutex_unlock(&thermal_list_lock); + return temp; + } + mutex_unlock(&thermal_list_lock); + + return NULL; +} + static int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) { struct thermal_hwmon_device *hwmon; + struct thermal_hwmon_temp *temp; int new_hwmon_device = 1; int result; @@ -515,30 +559,36 @@ thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) goto free_mem; register_sys_interface: - tz->hwmon = hwmon; + temp = kzalloc(sizeof(struct thermal_hwmon_temp), GFP_KERNEL); + if (!temp) { + result = -ENOMEM; + goto unregister_name; + } + + temp->tz = tz; hwmon->count++; - snprintf(tz->temp_input.name, THERMAL_NAME_LENGTH, + snprintf(temp->temp_input.name, THERMAL_NAME_LENGTH, "temp%d_input", hwmon->count); - tz->temp_input.attr.attr.name = tz->temp_input.name; - tz->temp_input.attr.attr.mode = 0444; - tz->temp_input.attr.show = temp_input_show; - sysfs_attr_init(&tz->temp_input.attr.attr); - result = device_create_file(hwmon->device, &tz->temp_input.attr); + temp->temp_input.attr.attr.name = temp->temp_input.name; + temp->temp_input.attr.attr.mode = 0444; + temp->temp_input.attr.show = temp_input_show; + sysfs_attr_init(&temp->temp_input.attr.attr); + result = device_create_file(hwmon->device, &temp->temp_input.attr); if (result) - goto unregister_name; + goto free_temp_mem; if (tz->ops->get_crit_temp) { unsigned long temperature; if (!tz->ops->get_crit_temp(tz, &temperature)) { - snprintf(tz->temp_crit.name, THERMAL_NAME_LENGTH, + snprintf(temp->temp_crit.name, THERMAL_NAME_LENGTH, "temp%d_crit", hwmon->count); - tz->temp_crit.attr.attr.name = tz->temp_crit.name; - tz->temp_crit.attr.attr.mode = 0444; - tz->temp_crit.attr.show = temp_crit_show; - sysfs_attr_init(&tz->temp_crit.attr.attr); + temp->temp_crit.attr.attr.name = temp->temp_crit.name; + temp->temp_crit.attr.attr.mode = 0444; + temp->temp_crit.attr.show = temp_crit_show; + sysfs_attr_init(&temp->temp_crit.attr.attr); result = device_create_file(hwmon->device, - &tz->temp_crit.attr); + &temp->temp_crit.attr); if (result) goto unregister_input; } @@ -547,13 +597,15 @@ thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) mutex_lock(&thermal_list_lock); if (new_hwmon_device) list_add_tail(&hwmon->node, &thermal_hwmon_list); - list_add_tail(&tz->hwmon_node, &hwmon->tz_list); + list_add_tail(&temp->hwmon_node, &hwmon->tz_list); mutex_unlock(&thermal_list_lock); return 0; unregister_input: - device_remove_file(hwmon->device, &tz->temp_input.attr); + device_remove_file(hwmon->device, &temp->temp_input.attr); + free_temp_mem: + kfree(temp); unregister_name: if (new_hwmon_device) { device_remove_file(hwmon->device, &dev_attr_name); @@ -569,15 +621,30 @@ thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) static void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz) { - struct thermal_hwmon_device *hwmon = tz->hwmon; + struct thermal_hwmon_device *hwmon; + struct thermal_hwmon_temp *temp; + + hwmon = thermal_hwmon_lookup_by_type(tz); + if (unlikely(!hwmon)) { + /* Should never happen... */ + dev_dbg(&tz->device, "hwmon device lookup failed!\n"); + return; + } + + temp = thermal_hwmon_lookup_temp(hwmon, tz); + if (unlikely(!temp)) { + /* Should never happen... */ + dev_dbg(&tz->device, "temperature input lookup failed!\n"); + return; + } - tz->hwmon = NULL; - device_remove_file(hwmon->device, &tz->temp_input.attr); + device_remove_file(hwmon->device, &temp->temp_input.attr); if (tz->ops->get_crit_temp) - device_remove_file(hwmon->device, &tz->temp_crit.attr); + device_remove_file(hwmon->device, &temp->temp_crit.attr); mutex_lock(&thermal_list_lock); - list_del(&tz->hwmon_node); + list_del(&temp->hwmon_node); + kfree(temp); if (!list_empty(&hwmon->tz_list)) { mutex_unlock(&thermal_list_lock); return; diff --git a/include/linux/thermal.h b/include/linux/thermal.h index d3ec89fb4122..47b4a27e6e97 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -85,22 +85,6 @@ struct thermal_cooling_device { ((long)t-2732+5)/10 : ((long)t-2732-5)/10) #define CELSIUS_TO_KELVIN(t) ((t)*10+2732) -#if defined(CONFIG_THERMAL_HWMON) -/* thermal zone devices with the same type share one hwmon device */ -struct thermal_hwmon_device { - char type[THERMAL_NAME_LENGTH]; - struct device *device; - int count; - struct list_head tz_list; - struct list_head node; -}; - -struct thermal_hwmon_attr { - struct device_attribute attr; - char name[16]; -}; -#endif - struct thermal_zone_device { int id; char type[THERMAL_NAME_LENGTH]; @@ -120,12 +104,6 @@ struct thermal_zone_device { struct mutex lock; /* protect cooling devices list */ struct list_head node; struct delayed_work poll_queue; -#if defined(CONFIG_THERMAL_HWMON) - struct list_head hwmon_node; - struct thermal_hwmon_device *hwmon; - struct thermal_hwmon_attr temp_input; /* hwmon sys attr */ - struct thermal_hwmon_attr temp_crit; /* hwmon sys attr */ -#endif }; /* Adding event notification support elements */ #define THERMAL_GENL_FAMILY_NAME "thermal_event" -- cgit v1.2.3 From f52e00c668669c9c290e84adf859c76db6d92a5a Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 28 Jul 2011 13:48:43 -0700 Subject: ACPI: remove NID_INVAL b552a8c56db8 ("ACPI: remove NID_INVAL") removed the left over uses of NID_INVAL, but didn't actually remove the definition. Remove it. Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Len Brown --- include/linux/acpi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1deb2a73c2da..2312e850aab8 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -238,7 +238,6 @@ extern int acpi_paddr_to_node(u64 start_addr, u64 size); extern int pnpacpi_disabled; #define PXM_INVAL (-1) -#define NID_INVAL (-1) int acpi_check_resource_conflict(const struct resource *res); -- cgit v1.2.3 From 951c0d660a7c35286e401ca6d6ef38c9d49643c7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 3 Aug 2011 00:47:21 -0400 Subject: get rid of boilerplate switches in posix_acl.h the only potentially subtle thing here: get_cached_acl() is never called with the second argument other than ACL_TYPE_{ACCESS,DEFAULT}. IOW, that return ERR_PTR(-EINVAL) in there might as well be BUG(). Signed-off-by: Al Viro --- include/linux/posix_acl.h | 62 +++++++++++++++-------------------------------- 1 file changed, 20 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 951bba82d50d..a9c2fb29be96 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -84,20 +84,22 @@ extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); #ifdef CONFIG_FS_POSIX_ACL -static inline struct posix_acl *get_cached_acl(struct inode *inode, int type) +static inline struct posix_acl **acl_by_type(struct inode *inode, int type) { - struct posix_acl **p, *acl; switch (type) { case ACL_TYPE_ACCESS: - p = &inode->i_acl; - break; + return &inode->i_acl; case ACL_TYPE_DEFAULT: - p = &inode->i_default_acl; - break; + return &inode->i_default_acl; default: - return ERR_PTR(-EINVAL); + BUG(); } - acl = ACCESS_ONCE(*p); +} + +static inline struct posix_acl *get_cached_acl(struct inode *inode, int type) +{ + struct posix_acl **p = acl_by_type(inode, type); + struct posix_acl *acl = ACCESS_ONCE(*p); if (acl) { spin_lock(&inode->i_lock); acl = *p; @@ -110,18 +112,8 @@ static inline struct posix_acl *get_cached_acl(struct inode *inode, int type) static inline int negative_cached_acl(struct inode *inode, int type) { - struct posix_acl **p, *acl; - switch (type) { - case ACL_TYPE_ACCESS: - p = &inode->i_acl; - break; - case ACL_TYPE_DEFAULT: - p = &inode->i_default_acl; - break; - default: - BUG(); - } - acl = ACCESS_ONCE(*p); + struct posix_acl **p = acl_by_type(inode, type); + struct posix_acl *acl = ACCESS_ONCE(*p); if (acl) return 0; return 1; @@ -131,18 +123,11 @@ static inline void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl) { - struct posix_acl *old = NULL; + struct posix_acl **p = acl_by_type(inode, type); + struct posix_acl *old; spin_lock(&inode->i_lock); - switch (type) { - case ACL_TYPE_ACCESS: - old = inode->i_acl; - inode->i_acl = posix_acl_dup(acl); - break; - case ACL_TYPE_DEFAULT: - old = inode->i_default_acl; - inode->i_default_acl = posix_acl_dup(acl); - break; - } + old = *p; + *p = posix_dup_acl(acl); spin_unlock(&inode->i_lock); if (old != ACL_NOT_CACHED) posix_acl_release(old); @@ -150,18 +135,11 @@ static inline void set_cached_acl(struct inode *inode, static inline void forget_cached_acl(struct inode *inode, int type) { - struct posix_acl *old = NULL; + struct posix_acl **p = acl_by_type(inode, type); + struct posix_acl *old; spin_lock(&inode->i_lock); - switch (type) { - case ACL_TYPE_ACCESS: - old = inode->i_acl; - inode->i_acl = ACL_NOT_CACHED; - break; - case ACL_TYPE_DEFAULT: - old = inode->i_default_acl; - inode->i_default_acl = ACL_NOT_CACHED; - break; - } + old = *p; + *p = ACL_NOT_CACHED; spin_unlock(&inode->i_lock); if (old != ACL_NOT_CACHED) posix_acl_release(old); -- cgit v1.2.3 From 3567866bf26190d1e734c975c907eb06e923ba23 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 2 Aug 2011 21:32:13 -0400 Subject: RCUify freeing acls, let check_acl() go ahead in RCU mode if acl is cached Signed-off-by: Al Viro --- fs/namei.c | 17 ++++++----------- include/linux/posix_acl.h | 18 +++++++++--------- 2 files changed, 15 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index 445fd5da11fa..3d607bd80e09 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -179,19 +179,14 @@ static int check_acl(struct inode *inode, int mask) #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *acl; - /* - * Under RCU walk, we cannot even do a "get_cached_acl()", - * because that involves locking and getting a refcount on - * a cached ACL. - * - * So the only case we handle during RCU walking is the - * case of a cached "no ACL at all", which needs no locks - * or refcounts. - */ if (mask & MAY_NOT_BLOCK) { - if (negative_cached_acl(inode, ACL_TYPE_ACCESS)) + acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS); + if (!acl) return -EAGAIN; - return -ECHILD; + /* no ->get_acl() calls in RCU mode... */ + if (acl == ACL_NOT_CACHED) + return -ECHILD; + return posix_acl_permission(inode, acl, mask); } acl = get_cached_acl(inode, ACL_TYPE_ACCESS); diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index a9c2fb29be96..b7681102a4b9 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -9,6 +9,7 @@ #define __LINUX_POSIX_ACL_H #include +#include #define ACL_UNDEFINED_ID (-1) @@ -38,7 +39,10 @@ struct posix_acl_entry { }; struct posix_acl { - atomic_t a_refcount; + union { + atomic_t a_refcount; + struct rcu_head a_rcu; + }; unsigned int a_count; struct posix_acl_entry a_entries[0]; }; @@ -65,7 +69,7 @@ static inline void posix_acl_release(struct posix_acl *acl) { if (acl && atomic_dec_and_test(&acl->a_refcount)) - kfree(acl); + kfree_rcu(acl, a_rcu); } @@ -110,13 +114,9 @@ static inline struct posix_acl *get_cached_acl(struct inode *inode, int type) return acl; } -static inline int negative_cached_acl(struct inode *inode, int type) +static inline struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type) { - struct posix_acl **p = acl_by_type(inode, type); - struct posix_acl *acl = ACCESS_ONCE(*p); - if (acl) - return 0; - return 1; + return rcu_dereference(*acl_by_type(inode, type)); } static inline void set_cached_acl(struct inode *inode, @@ -127,7 +127,7 @@ static inline void set_cached_acl(struct inode *inode, struct posix_acl *old; spin_lock(&inode->i_lock); old = *p; - *p = posix_dup_acl(acl); + rcu_assign_pointer(*p, posix_acl_dup(acl)); spin_unlock(&inode->i_lock); if (old != ACL_NOT_CACHED) posix_acl_release(old); -- cgit v1.2.3 From 750f463a749e28464151ad26938d11b07b1c43cb Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Wed, 3 Aug 2011 11:28:14 +0100 Subject: dt: add of_alias_scan and of_alias_get_id The patch adds function of_alias_scan to populate a global lookup table with the properties of 'aliases' node and function of_alias_get_id for drivers to find alias id from the lookup table. Signed-off-by: Shawn Guo [grant.likely: add locking and rework parse loop] Signed-off-by: Grant Likely --- drivers/of/base.c | 130 +++++++++++++++++++++++++++++++++++++++++++++++++ drivers/of/fdt.c | 4 +- include/linux/of.h | 8 +++ include/linux/of_fdt.h | 1 - 4 files changed, 141 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/base.c b/drivers/of/base.c index 3ff22e32b602..fb28b5af733b 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -17,14 +17,39 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ +#include #include #include #include #include #include +/** + * struct alias_prop - Alias property in 'aliases' node + * @link: List node to link the structure in aliases_lookup list + * @alias: Alias property name + * @np: Pointer to device_node that the alias stands for + * @id: Index value from end of alias name + * @stem: Alias string without the index + * + * The structure represents one alias property of 'aliases' node as + * an entry in aliases_lookup list. + */ +struct alias_prop { + struct list_head link; + const char *alias; + struct device_node *np; + int id; + char stem[0]; +}; + +static LIST_HEAD(aliases_lookup); + struct device_node *allnodes; struct device_node *of_chosen; +struct device_node *of_aliases; + +static DEFINE_MUTEX(of_aliases_mutex); /* use when traversing tree through the allnext, child, sibling, * or parent members of struct device_node. @@ -988,3 +1013,108 @@ out_unlock: } #endif /* defined(CONFIG_OF_DYNAMIC) */ +static void of_alias_add(struct alias_prop *ap, struct device_node *np, + int id, const char *stem, int stem_len) +{ + ap->id = id; + ap->np = np; + strncpy(ap->stem, stem, stem_len); + ap->stem[stem_len] = 0; + list_add_tail(&ap->link, &aliases_lookup); + pr_debug("adding DT alias:%s: stem=%s id=%i node=%s\n", + ap->alias, ap->stem, ap->id, np ? np->full_name : NULL); +} + +/** + * of_alias_scan() - Scan all properties of 'aliases' node + * + * The function scans all the properties of 'aliases' node and populate + * the global lookup table with the properties. It returns the + * number of alias_prop found, or error code in error case. + */ +__init void of_alias_scan(void) +{ + struct property *pp; + + if (!of_aliases) + return; + + for_each_property(pp, of_aliases->properties) { + const char *start = pp->name; + const char *end = start + strlen(start); + struct device_node *np; + struct alias_prop *ap; + int id, len; + + /* Skip those we do not want to proceed */ + if (!strcmp(pp->name, "name") || + !strcmp(pp->name, "phandle") || + !strcmp(pp->name, "linux,phandle")) + continue; + + np = of_find_node_by_path(pp->value); + if (!np) + continue; + + /* walk alias backwards to extract the id and 'stem' string */ + while (isdigit(*(end-1)) && end > start) + end--; + len = end - start; + id = strlen(end) ? simple_strtoul(end, NULL, 10) : -1; + + /* Allocate an alias_prop with enough space for the stem */ + ap = early_init_dt_alloc_memory_arch(sizeof(*ap) + len + 1, 4); + if (!ap) + continue; + ap->alias = start; + of_alias_add(ap, np, id, start, len); + } +} + +/** + * of_alias_get_id() - Get alias id for the given device_node + * @np: Pointer to the given device_node + * @stem: Alias stem of the given device_node + * + * The function travels the lookup table to get alias id for the given + * device_node and alias stem. It returns the alias id if find it. + * If not, dynamically creates one in the lookup table and returns it, + * or returns error code if fail to create. + */ +int of_alias_get_id(struct device_node *np, const char *stem) +{ + struct alias_prop *app; + int id = 0; + bool found = false; + + mutex_lock(&of_aliases_mutex); + list_for_each_entry(app, &aliases_lookup, link) { + if (strcmp(app->stem, stem) != 0) + continue; + + if (np == app->np) { + found = true; + id = app->id; + break; + } + + if (id <= app->id) + id = app->id + 1; + } + + /* If an id is not found, then allocate a new one */ + if (!found) { + app = kzalloc(sizeof(*app) + strlen(stem) + 1, 4); + if (!app) { + id = -ENODEV; + goto out; + } + of_alias_add(app, np, id, stem, strlen(stem)); + } + + out: + mutex_unlock(&of_aliases_mutex); + + return id; +} +EXPORT_SYMBOL_GPL(of_alias_get_id); diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 65200af29c52..13d6d3a96b31 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -707,10 +707,12 @@ void __init unflatten_device_tree(void) __unflatten_device_tree(initial_boot_params, &allnodes, early_init_dt_alloc_memory_arch); - /* Get pointer to OF "/chosen" node for use everywhere */ + /* Get pointer to "/chosen" and "/aliasas" nodes for use everywhere */ of_chosen = of_find_node_by_path("/chosen"); if (of_chosen == NULL) of_chosen = of_find_node_by_path("/chosen@0"); + of_aliases = of_find_node_by_path("/aliases"); + of_alias_scan(); } #endif /* CONFIG_OF_EARLY_FLATTREE */ diff --git a/include/linux/of.h b/include/linux/of.h index 0085bb01c041..bc3dc6399547 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -68,6 +68,7 @@ struct device_node { /* Pointer for first entry in chain of all nodes. */ extern struct device_node *allnodes; extern struct device_node *of_chosen; +extern struct device_node *of_aliases; extern rwlock_t devtree_lock; static inline bool of_have_populated_dt(void) @@ -209,6 +210,9 @@ extern int of_device_is_available(const struct device_node *device); extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); +#define for_each_property(pp, properties) \ + for (pp = properties; pp != NULL; pp = pp->next) + extern int of_n_addr_cells(struct device_node *np); extern int of_n_size_cells(struct device_node *np); extern const struct of_device_id *of_match_node( @@ -221,6 +225,10 @@ extern int of_parse_phandles_with_args(struct device_node *np, const char *list_name, const char *cells_name, int index, struct device_node **out_node, const void **out_args); +extern void *early_init_dt_alloc_memory_arch(u64 size, u64 align); +extern void of_alias_scan(void); +extern int of_alias_get_id(struct device_node *np, const char *stem); + extern int of_machine_is_compatible(const char *compat); extern int prom_add_property(struct device_node* np, struct property* prop); diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index c84d900fbbb3..b74b74ffe0e7 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -97,7 +97,6 @@ extern void early_init_dt_check_for_initrd(unsigned long node); extern int early_init_dt_scan_memory(unsigned long node, const char *uname, int depth, void *data); extern void early_init_dt_add_memory_arch(u64 base, u64 size); -extern void * early_init_dt_alloc_memory_arch(u64 size, u64 align); extern u64 dt_mem_next_cell(int s, __be32 **cellp); /* -- cgit v1.2.3 From f49f23abf3dd786ddcac1c1e7db3c2013b07413f Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:23 +0800 Subject: lib, Add lock-less NULL terminated single list Cmpxchg is used to implement adding new entry to the list, deleting all entries from the list, deleting first entry of the list and some other operations. Because this is a single list, so the tail can not be accessed in O(1). If there are multiple producers and multiple consumers, llist_add can be used in producers and llist_del_all can be used in consumers. They can work simultaneously without lock. But llist_del_first can not be used here. Because llist_del_first depends on list->first->next does not changed if list->first is not changed during its operation, but llist_del_first, llist_add, llist_add (or llist_del_all, llist_add, llist_add) sequence in another consumer may violate that. If there are multiple producers and one consumer, llist_add can be used in producers and llist_del_all or llist_del_first can be used in the consumer. This can be summarized as follow: | add | del_first | del_all add | - | - | - del_first | | L | L del_all | | | - Where "-" stands for no lock is needed, while "L" stands for lock is needed. The list entries deleted via llist_del_all can be traversed with traversing function such as llist_for_each etc. But the list entries can not be traversed safely before deleted from the list. The order of deleted entries is from the newest to the oldest added one. If you want to traverse from the oldest to the newest, you must reverse the order by yourself before traversing. The basic atomic operation of this list is cmpxchg on long. On architectures that don't have NMI-safe cmpxchg implementation, the list can NOT be used in NMI handler. So code uses the list in NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. Signed-off-by: Huang Ying Reviewed-by: Andi Kleen Reviewed-by: Mathieu Desnoyers Cc: Andrew Morton Signed-off-by: Len Brown --- include/linux/llist.h | 126 ++++++++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig | 3 ++ lib/Makefile | 2 + lib/llist.c | 129 ++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 260 insertions(+) create mode 100644 include/linux/llist.h create mode 100644 lib/llist.c (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h new file mode 100644 index 000000000000..aa0c8b5b3cd0 --- /dev/null +++ b/include/linux/llist.h @@ -0,0 +1,126 @@ +#ifndef LLIST_H +#define LLIST_H +/* + * Lock-less NULL terminated single linked list + * + * If there are multiple producers and multiple consumers, llist_add + * can be used in producers and llist_del_all can be used in + * consumers. They can work simultaneously without lock. But + * llist_del_first can not be used here. Because llist_del_first + * depends on list->first->next does not changed if list->first is not + * changed during its operation, but llist_del_first, llist_add, + * llist_add (or llist_del_all, llist_add, llist_add) sequence in + * another consumer may violate that. + * + * If there are multiple producers and one consumer, llist_add can be + * used in producers and llist_del_all or llist_del_first can be used + * in the consumer. + * + * This can be summarized as follow: + * + * | add | del_first | del_all + * add | - | - | - + * del_first | | L | L + * del_all | | | - + * + * Where "-" stands for no lock is needed, while "L" stands for lock + * is needed. + * + * The list entries deleted via llist_del_all can be traversed with + * traversing function such as llist_for_each etc. But the list + * entries can not be traversed safely before deleted from the list. + * The order of deleted entries is from the newest to the oldest added + * one. If you want to traverse from the oldest to the newest, you + * must reverse the order by yourself before traversing. + * + * The basic atomic operation of this list is cmpxchg on long. On + * architectures that don't have NMI-safe cmpxchg implementation, the + * list can NOT be used in NMI handler. So code uses the list in NMI + * handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. + */ + +struct llist_head { + struct llist_node *first; +}; + +struct llist_node { + struct llist_node *next; +}; + +#define LLIST_HEAD_INIT(name) { NULL } +#define LLIST_HEAD(name) struct llist_head name = LLIST_HEAD_INIT(name) + +/** + * init_llist_head - initialize lock-less list head + * @head: the head for your lock-less list + */ +static inline void init_llist_head(struct llist_head *list) +{ + list->first = NULL; +} + +/** + * llist_entry - get the struct of this entry + * @ptr: the &struct llist_node pointer. + * @type: the type of the struct this is embedded in. + * @member: the name of the llist_node within the struct. + */ +#define llist_entry(ptr, type, member) \ + container_of(ptr, type, member) + +/** + * llist_for_each - iterate over some deleted entries of a lock-less list + * @pos: the &struct llist_node to use as a loop cursor + * @node: the first entry of deleted list entries + * + * In general, some entries of the lock-less list can be traversed + * safely only after being deleted from list, so start with an entry + * instead of list head. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each(pos, node) \ + for ((pos) = (node); pos; (pos) = (pos)->next) + +/** + * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type + * @pos: the type * to use as a loop cursor. + * @node: the fist entry of deleted list entries. + * @member: the name of the llist_node with the struct. + * + * In general, some entries of the lock-less list can be traversed + * safely only after being removed from list, so start with an entry + * instead of list head. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each_entry(pos, node, member) \ + for ((pos) = llist_entry((node), typeof(*(pos)), member); \ + &(pos)->member != NULL; \ + (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) + +/** + * llist_empty - tests whether a lock-less list is empty + * @head: the list to test + * + * Not guaranteed to be accurate or up to date. Just a quick way to + * test whether the list is empty without deleting something from the + * list. + */ +static inline int llist_empty(const struct llist_head *head) +{ + return ACCESS_ONCE(head->first) == NULL; +} + +void llist_add(struct llist_node *new, struct llist_head *head); +void llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, + struct llist_head *head); +struct llist_node *llist_del_first(struct llist_head *head); +struct llist_node *llist_del_all(struct llist_head *head); +#endif /* LLIST_H */ diff --git a/lib/Kconfig b/lib/Kconfig index 830181cc7a83..25c19678a30f 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -262,4 +262,7 @@ config AVERAGE If unsure, say N. +config LLIST + bool + endmenu diff --git a/lib/Makefile b/lib/Makefile index 6b597fdb1898..d770b817202e 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -112,6 +112,8 @@ obj-$(CONFIG_AVERAGE) += average.o obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o +obj-$(CONFIG_LLIST) += llist.o + hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/lib/llist.c b/lib/llist.c new file mode 100644 index 000000000000..da445724fa1f --- /dev/null +++ b/lib/llist.c @@ -0,0 +1,129 @@ +/* + * Lock-less NULL terminated single linked list + * + * The basic atomic operation of this list is cmpxchg on long. On + * architectures that don't have NMI-safe cmpxchg implementation, the + * list can NOT be used in NMI handler. So code uses the list in NMI + * handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. + * + * Copyright 2010,2011 Intel Corp. + * Author: Huang Ying + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation; + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#include +#include +#include +#include + +#include + +/** + * llist_add - add a new entry + * @new: new entry to be added + * @head: the head for your lock-less list + */ +void llist_add(struct llist_node *new, struct llist_head *head) +{ + struct llist_node *entry, *old_entry; + +#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG + BUG_ON(in_nmi()); +#endif + + entry = head->first; + do { + old_entry = entry; + new->next = entry; + cpu_relax(); + } while ((entry = cmpxchg(&head->first, old_entry, new)) != old_entry); +} +EXPORT_SYMBOL_GPL(llist_add); + +/** + * llist_add_batch - add several linked entries in batch + * @new_first: first entry in batch to be added + * @new_last: last entry in batch to be added + * @head: the head for your lock-less list + */ +void llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, + struct llist_head *head) +{ + struct llist_node *entry, *old_entry; + +#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG + BUG_ON(in_nmi()); +#endif + + entry = head->first; + do { + old_entry = entry; + new_last->next = entry; + cpu_relax(); + } while ((entry = cmpxchg(&head->first, old_entry, new_first)) != old_entry); +} +EXPORT_SYMBOL_GPL(llist_add_batch); + +/** + * llist_del_first - delete the first entry of lock-less list + * @head: the head for your lock-less list + * + * If list is empty, return NULL, otherwise, return the first entry + * deleted, this is the newest added one. + * + * Only one llist_del_first user can be used simultaneously with + * multiple llist_add users without lock. Because otherwise + * llist_del_first, llist_add, llist_add (or llist_del_all, llist_add, + * llist_add) sequence in another user may change @head->first->next, + * but keep @head->first. If multiple consumers are needed, please + * use llist_del_all or use lock between consumers. + */ +struct llist_node *llist_del_first(struct llist_head *head) +{ + struct llist_node *entry, *old_entry, *next; + +#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG + BUG_ON(in_nmi()); +#endif + + entry = head->first; + do { + if (entry == NULL) + return NULL; + old_entry = entry; + next = entry->next; + cpu_relax(); + } while ((entry = cmpxchg(&head->first, old_entry, next)) != old_entry); + + return entry; +} +EXPORT_SYMBOL_GPL(llist_del_first); + +/** + * llist_del_all - delete all entries from lock-less list + * @head: the head of lock-less list to delete all entries + * + * If list is empty, return NULL, otherwise, delete all entries and + * return the pointer to the first entry. The order of entries + * deleted is from the newest to the oldest added one. + */ +struct llist_node *llist_del_all(struct llist_head *head) +{ +#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG + BUG_ON(in_nmi()); +#endif + + return xchg(&head->first, NULL); +} +EXPORT_SYMBOL_GPL(llist_del_all); -- cgit v1.2.3 From 7f184275aa306046fe7edcbef3229754f0d97402 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:24 +0800 Subject: lib, Make gen_pool memory allocator lockless This version of the gen_pool memory allocator supports lockless operation. This makes it safe to use in NMI handlers and other special unblockable contexts that could otherwise deadlock on locks. This is implemented by using atomic operations and retries on any conflicts. The disadvantage is that there may be livelocks in extreme cases. For better scalability, one gen_pool allocator can be used for each CPU. The lockless operation only works if there is enough memory available. If new memory is added to the pool a lock has to be still taken. So any user relying on locklessness has to ensure that sufficient memory is preallocated. The basic atomic operation of this allocator is cmpxchg on long. On architectures that don't have NMI-safe cmpxchg implementation, the allocator can NOT be used in NMI handler. So code uses the allocator in NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. Signed-off-by: Huang Ying Reviewed-by: Andi Kleen Reviewed-by: Mathieu Desnoyers Cc: Andrew Morton Signed-off-by: Len Brown --- include/linux/bitmap.h | 1 + include/linux/genalloc.h | 34 +++++- lib/bitmap.c | 2 - lib/genalloc.c | 300 ++++++++++++++++++++++++++++++++++++++--------- 4 files changed, 272 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index dcafe0bf0005..907dd58aa228 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -145,6 +145,7 @@ extern void bitmap_release_region(unsigned long *bitmap, int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order); extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits); +#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG)) #define BITMAP_LAST_WORD_MASK(nbits) \ ( \ ((nbits) % BITS_PER_LONG) ? \ diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 5bbebda78b02..5e98eeb2af3b 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -1,8 +1,26 @@ /* - * Basic general purpose allocator for managing special purpose memory - * not managed by the regular kmalloc/kfree interface. - * Uses for this includes on-device special memory, uncached memory - * etc. + * Basic general purpose allocator for managing special purpose + * memory, for example, memory that is not managed by the regular + * kmalloc/kfree interface. Uses for this includes on-device special + * memory, uncached memory etc. + * + * It is safe to use the allocator in NMI handlers and other special + * unblockable contexts that could otherwise deadlock on locks. This + * is implemented by using atomic operations and retries on any + * conflicts. The disadvantage is that there may be livelocks in + * extreme cases. For better scalability, one allocator can be used + * for each CPU. + * + * The lockless operation only works if there is enough memory + * available. If new memory is added to the pool a lock has to be + * still taken. So any user relying on locklessness has to ensure + * that sufficient memory is preallocated. + * + * The basic atomic operation of this allocator is cmpxchg on long. + * On architectures that don't have NMI-safe cmpxchg implementation, + * the allocator can NOT be used in NMI handler. So code uses the + * allocator in NMI handler should depend on + * CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * This source code is licensed under the GNU General Public License, * Version 2. See the file COPYING for more details. @@ -15,7 +33,7 @@ * General purpose special memory pool descriptor. */ struct gen_pool { - rwlock_t lock; + spinlock_t lock; struct list_head chunks; /* list of chunks in this pool */ int min_alloc_order; /* minimum allocation order */ }; @@ -24,8 +42,8 @@ struct gen_pool { * General purpose special memory pool chunk descriptor. */ struct gen_pool_chunk { - spinlock_t lock; struct list_head next_chunk; /* next chunk in pool */ + atomic_t avail; phys_addr_t phys_addr; /* physical starting address of memory chunk */ unsigned long start_addr; /* starting address of memory chunk */ unsigned long end_addr; /* ending address of memory chunk */ @@ -56,4 +74,8 @@ static inline int gen_pool_add(struct gen_pool *pool, unsigned long addr, extern void gen_pool_destroy(struct gen_pool *); extern unsigned long gen_pool_alloc(struct gen_pool *, size_t); extern void gen_pool_free(struct gen_pool *, unsigned long, size_t); +extern void gen_pool_for_each_chunk(struct gen_pool *, + void (*)(struct gen_pool *, struct gen_pool_chunk *, void *), void *); +extern size_t gen_pool_avail(struct gen_pool *); +extern size_t gen_pool_size(struct gen_pool *); #endif /* __GENALLOC_H__ */ diff --git a/lib/bitmap.c b/lib/bitmap.c index 3f3b68199d74..e3c9e999501e 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -271,8 +271,6 @@ int __bitmap_weight(const unsigned long *bitmap, int bits) } EXPORT_SYMBOL(__bitmap_weight); -#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG)) - void bitmap_set(unsigned long *map, int start, int nr) { unsigned long *p = map + BIT_WORD(start); diff --git a/lib/genalloc.c b/lib/genalloc.c index 577ddf805975..f352cc42f4f8 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -1,8 +1,26 @@ /* - * Basic general purpose allocator for managing special purpose memory - * not managed by the regular kmalloc/kfree interface. - * Uses for this includes on-device special memory, uncached memory - * etc. + * Basic general purpose allocator for managing special purpose + * memory, for example, memory that is not managed by the regular + * kmalloc/kfree interface. Uses for this includes on-device special + * memory, uncached memory etc. + * + * It is safe to use the allocator in NMI handlers and other special + * unblockable contexts that could otherwise deadlock on locks. This + * is implemented by using atomic operations and retries on any + * conflicts. The disadvantage is that there may be livelocks in + * extreme cases. For better scalability, one allocator can be used + * for each CPU. + * + * The lockless operation only works if there is enough memory + * available. If new memory is added to the pool a lock has to be + * still taken. So any user relying on locklessness has to ensure + * that sufficient memory is preallocated. + * + * The basic atomic operation of this allocator is cmpxchg on long. + * On architectures that don't have NMI-safe cmpxchg implementation, + * the allocator can NOT be used in NMI handler. So code uses the + * allocator in NMI handler should depend on + * CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * Copyright 2005 (C) Jes Sorensen * @@ -13,8 +31,109 @@ #include #include #include +#include +#include #include +static int set_bits_ll(unsigned long *addr, unsigned long mask_to_set) +{ + unsigned long val, nval; + + nval = *addr; + do { + val = nval; + if (val & mask_to_set) + return -EBUSY; + cpu_relax(); + } while ((nval = cmpxchg(addr, val, val | mask_to_set)) != val); + + return 0; +} + +static int clear_bits_ll(unsigned long *addr, unsigned long mask_to_clear) +{ + unsigned long val, nval; + + nval = *addr; + do { + val = nval; + if ((val & mask_to_clear) != mask_to_clear) + return -EBUSY; + cpu_relax(); + } while ((nval = cmpxchg(addr, val, val & ~mask_to_clear)) != val); + + return 0; +} + +/* + * bitmap_set_ll - set the specified number of bits at the specified position + * @map: pointer to a bitmap + * @start: a bit position in @map + * @nr: number of bits to set + * + * Set @nr bits start from @start in @map lock-lessly. Several users + * can set/clear the same bitmap simultaneously without lock. If two + * users set the same bit, one user will return remain bits, otherwise + * return 0. + */ +static int bitmap_set_ll(unsigned long *map, int start, int nr) +{ + unsigned long *p = map + BIT_WORD(start); + const int size = start + nr; + int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); + unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start); + + while (nr - bits_to_set >= 0) { + if (set_bits_ll(p, mask_to_set)) + return nr; + nr -= bits_to_set; + bits_to_set = BITS_PER_LONG; + mask_to_set = ~0UL; + p++; + } + if (nr) { + mask_to_set &= BITMAP_LAST_WORD_MASK(size); + if (set_bits_ll(p, mask_to_set)) + return nr; + } + + return 0; +} + +/* + * bitmap_clear_ll - clear the specified number of bits at the specified position + * @map: pointer to a bitmap + * @start: a bit position in @map + * @nr: number of bits to set + * + * Clear @nr bits start from @start in @map lock-lessly. Several users + * can set/clear the same bitmap simultaneously without lock. If two + * users clear the same bit, one user will return remain bits, + * otherwise return 0. + */ +static int bitmap_clear_ll(unsigned long *map, int start, int nr) +{ + unsigned long *p = map + BIT_WORD(start); + const int size = start + nr; + int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); + unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); + + while (nr - bits_to_clear >= 0) { + if (clear_bits_ll(p, mask_to_clear)) + return nr; + nr -= bits_to_clear; + bits_to_clear = BITS_PER_LONG; + mask_to_clear = ~0UL; + p++; + } + if (nr) { + mask_to_clear &= BITMAP_LAST_WORD_MASK(size); + if (clear_bits_ll(p, mask_to_clear)) + return nr; + } + + return 0; +} /** * gen_pool_create - create a new special memory pool @@ -30,7 +149,7 @@ struct gen_pool *gen_pool_create(int min_alloc_order, int nid) pool = kmalloc_node(sizeof(struct gen_pool), GFP_KERNEL, nid); if (pool != NULL) { - rwlock_init(&pool->lock); + spin_lock_init(&pool->lock); INIT_LIST_HEAD(&pool->chunks); pool->min_alloc_order = min_alloc_order; } @@ -63,14 +182,14 @@ int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phy if (unlikely(chunk == NULL)) return -ENOMEM; - spin_lock_init(&chunk->lock); chunk->phys_addr = phys; chunk->start_addr = virt; chunk->end_addr = virt + size; + atomic_set(&chunk->avail, size); - write_lock(&pool->lock); - list_add(&chunk->next_chunk, &pool->chunks); - write_unlock(&pool->lock); + spin_lock(&pool->lock); + list_add_rcu(&chunk->next_chunk, &pool->chunks); + spin_unlock(&pool->lock); return 0; } @@ -85,19 +204,19 @@ EXPORT_SYMBOL(gen_pool_add_virt); */ phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long addr) { - struct list_head *_chunk; struct gen_pool_chunk *chunk; + phys_addr_t paddr = -1; - read_lock(&pool->lock); - list_for_each(_chunk, &pool->chunks) { - chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk); - - if (addr >= chunk->start_addr && addr < chunk->end_addr) - return chunk->phys_addr + addr - chunk->start_addr; + rcu_read_lock(); + list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) { + if (addr >= chunk->start_addr && addr < chunk->end_addr) { + paddr = chunk->phys_addr + (addr - chunk->start_addr); + break; + } } - read_unlock(&pool->lock); + rcu_read_unlock(); - return -1; + return paddr; } EXPORT_SYMBOL(gen_pool_virt_to_phys); @@ -115,7 +234,6 @@ void gen_pool_destroy(struct gen_pool *pool) int order = pool->min_alloc_order; int bit, end_bit; - list_for_each_safe(_chunk, _next_chunk, &pool->chunks) { chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk); list_del(&chunk->next_chunk); @@ -137,44 +255,50 @@ EXPORT_SYMBOL(gen_pool_destroy); * @size: number of bytes to allocate from the pool * * Allocate the requested number of bytes from the specified pool. - * Uses a first-fit algorithm. + * Uses a first-fit algorithm. Can not be used in NMI handler on + * architectures without NMI-safe cmpxchg implementation. */ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size) { - struct list_head *_chunk; struct gen_pool_chunk *chunk; - unsigned long addr, flags; + unsigned long addr = 0; int order = pool->min_alloc_order; - int nbits, start_bit, end_bit; + int nbits, start_bit = 0, end_bit, remain; + +#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG + BUG_ON(in_nmi()); +#endif if (size == 0) return 0; nbits = (size + (1UL << order) - 1) >> order; - - read_lock(&pool->lock); - list_for_each(_chunk, &pool->chunks) { - chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk); + rcu_read_lock(); + list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) { + if (size > atomic_read(&chunk->avail)) + continue; end_bit = (chunk->end_addr - chunk->start_addr) >> order; - - spin_lock_irqsave(&chunk->lock, flags); - start_bit = bitmap_find_next_zero_area(chunk->bits, end_bit, 0, - nbits, 0); - if (start_bit >= end_bit) { - spin_unlock_irqrestore(&chunk->lock, flags); +retry: + start_bit = bitmap_find_next_zero_area(chunk->bits, end_bit, + start_bit, nbits, 0); + if (start_bit >= end_bit) continue; + remain = bitmap_set_ll(chunk->bits, start_bit, nbits); + if (remain) { + remain = bitmap_clear_ll(chunk->bits, start_bit, + nbits - remain); + BUG_ON(remain); + goto retry; } addr = chunk->start_addr + ((unsigned long)start_bit << order); - - bitmap_set(chunk->bits, start_bit, nbits); - spin_unlock_irqrestore(&chunk->lock, flags); - read_unlock(&pool->lock); - return addr; + size = nbits << order; + atomic_sub(size, &chunk->avail); + break; } - read_unlock(&pool->lock); - return 0; + rcu_read_unlock(); + return addr; } EXPORT_SYMBOL(gen_pool_alloc); @@ -184,33 +308,95 @@ EXPORT_SYMBOL(gen_pool_alloc); * @addr: starting address of memory to free back to pool * @size: size in bytes of memory to free * - * Free previously allocated special memory back to the specified pool. + * Free previously allocated special memory back to the specified + * pool. Can not be used in NMI handler on architectures without + * NMI-safe cmpxchg implementation. */ void gen_pool_free(struct gen_pool *pool, unsigned long addr, size_t size) { - struct list_head *_chunk; struct gen_pool_chunk *chunk; - unsigned long flags; int order = pool->min_alloc_order; - int bit, nbits; + int start_bit, nbits, remain; - nbits = (size + (1UL << order) - 1) >> order; - - read_lock(&pool->lock); - list_for_each(_chunk, &pool->chunks) { - chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk); +#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG + BUG_ON(in_nmi()); +#endif + nbits = (size + (1UL << order) - 1) >> order; + rcu_read_lock(); + list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) { if (addr >= chunk->start_addr && addr < chunk->end_addr) { BUG_ON(addr + size > chunk->end_addr); - spin_lock_irqsave(&chunk->lock, flags); - bit = (addr - chunk->start_addr) >> order; - while (nbits--) - __clear_bit(bit++, chunk->bits); - spin_unlock_irqrestore(&chunk->lock, flags); - break; + start_bit = (addr - chunk->start_addr) >> order; + remain = bitmap_clear_ll(chunk->bits, start_bit, nbits); + BUG_ON(remain); + size = nbits << order; + atomic_add(size, &chunk->avail); + rcu_read_unlock(); + return; } } - BUG_ON(nbits > 0); - read_unlock(&pool->lock); + rcu_read_unlock(); + BUG(); } EXPORT_SYMBOL(gen_pool_free); + +/** + * gen_pool_for_each_chunk - call func for every chunk of generic memory pool + * @pool: the generic memory pool + * @func: func to call + * @data: additional data used by @func + * + * Call @func for every chunk of generic memory pool. The @func is + * called with rcu_read_lock held. + */ +void gen_pool_for_each_chunk(struct gen_pool *pool, + void (*func)(struct gen_pool *pool, struct gen_pool_chunk *chunk, void *data), + void *data) +{ + struct gen_pool_chunk *chunk; + + rcu_read_lock(); + list_for_each_entry_rcu(chunk, &(pool)->chunks, next_chunk) + func(pool, chunk, data); + rcu_read_unlock(); +} +EXPORT_SYMBOL(gen_pool_for_each_chunk); + +/** + * gen_pool_avail - get available free space of the pool + * @pool: pool to get available free space + * + * Return available free space of the specified pool. + */ +size_t gen_pool_avail(struct gen_pool *pool) +{ + struct gen_pool_chunk *chunk; + size_t avail = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) + avail += atomic_read(&chunk->avail); + rcu_read_unlock(); + return avail; +} +EXPORT_SYMBOL_GPL(gen_pool_avail); + +/** + * gen_pool_size - get size in bytes of memory managed by the pool + * @pool: pool to get size + * + * Return size in bytes of memory managed by the pool. + */ +size_t gen_pool_size(struct gen_pool *pool) +{ + struct gen_pool_chunk *chunk; + size_t size = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) + size += chunk->end_addr - chunk->start_addr; + rcu_read_unlock(); + return size; +} +EXPORT_SYMBOL_GPL(gen_pool_size); -- cgit v1.2.3 From ea8f5fb8a71fddaf5f3a17100d3247855701f732 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:27 +0800 Subject: HWPoison: add memory_failure_queue() memory_failure() is the entry point for HWPoison memory error recovery. It must be called in process context. But commonly hardware memory errors are notified via MCE or NMI, so some delayed execution mechanism must be used. In MCE handler, a work queue + ring buffer mechanism is used. In addition to MCE, now APEI (ACPI Platform Error Interface) GHES (Generic Hardware Error Source) can be used to report memory errors too. To add support to APEI GHES memory recovery, a mechanism similar to that of MCE is implemented. memory_failure_queue() is the new entry point that can be called in IRQ context. The next step is to make MCE handler uses this interface too. Signed-off-by: Huang Ying Cc: Andi Kleen Cc: Wu Fengguang Cc: Andrew Morton Signed-off-by: Len Brown --- include/linux/mm.h | 1 + mm/memory-failure.c | 92 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 93 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9670f71d7be9..303108eed28c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1633,6 +1633,7 @@ enum mf_flags { }; extern void memory_failure(unsigned long pfn, int trapno); extern int __memory_failure(unsigned long pfn, int trapno, int flags); +extern void memory_failure_queue(unsigned long pfn, int trapno, int flags); extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 740c4f52059c..2b43ba051ac9 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -53,6 +53,7 @@ #include #include #include +#include #include "internal.h" int sysctl_memory_failure_early_kill __read_mostly = 0; @@ -1178,6 +1179,97 @@ void memory_failure(unsigned long pfn, int trapno) __memory_failure(pfn, trapno, 0); } +#define MEMORY_FAILURE_FIFO_ORDER 4 +#define MEMORY_FAILURE_FIFO_SIZE (1 << MEMORY_FAILURE_FIFO_ORDER) + +struct memory_failure_entry { + unsigned long pfn; + int trapno; + int flags; +}; + +struct memory_failure_cpu { + DECLARE_KFIFO(fifo, struct memory_failure_entry, + MEMORY_FAILURE_FIFO_SIZE); + spinlock_t lock; + struct work_struct work; +}; + +static DEFINE_PER_CPU(struct memory_failure_cpu, memory_failure_cpu); + +/** + * memory_failure_queue - Schedule handling memory failure of a page. + * @pfn: Page Number of the corrupted page + * @trapno: Trap number reported in the signal to user space. + * @flags: Flags for memory failure handling + * + * This function is called by the low level hardware error handler + * when it detects hardware memory corruption of a page. It schedules + * the recovering of error page, including dropping pages, killing + * processes etc. + * + * The function is primarily of use for corruptions that + * happen outside the current execution context (e.g. when + * detected by a background scrubber) + * + * Can run in IRQ context. + */ +void memory_failure_queue(unsigned long pfn, int trapno, int flags) +{ + struct memory_failure_cpu *mf_cpu; + unsigned long proc_flags; + struct memory_failure_entry entry = { + .pfn = pfn, + .trapno = trapno, + .flags = flags, + }; + + mf_cpu = &get_cpu_var(memory_failure_cpu); + spin_lock_irqsave(&mf_cpu->lock, proc_flags); + if (kfifo_put(&mf_cpu->fifo, &entry)) + schedule_work_on(smp_processor_id(), &mf_cpu->work); + else + pr_err("Memory failure: buffer overflow when queuing memory failure at 0x%#lx\n", + pfn); + spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + put_cpu_var(memory_failure_cpu); +} +EXPORT_SYMBOL_GPL(memory_failure_queue); + +static void memory_failure_work_func(struct work_struct *work) +{ + struct memory_failure_cpu *mf_cpu; + struct memory_failure_entry entry = { 0, }; + unsigned long proc_flags; + int gotten; + + mf_cpu = &__get_cpu_var(memory_failure_cpu); + for (;;) { + spin_lock_irqsave(&mf_cpu->lock, proc_flags); + gotten = kfifo_get(&mf_cpu->fifo, &entry); + spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + if (!gotten) + break; + __memory_failure(entry.pfn, entry.trapno, entry.flags); + } +} + +static int __init memory_failure_init(void) +{ + struct memory_failure_cpu *mf_cpu; + int cpu; + + for_each_possible_cpu(cpu) { + mf_cpu = &per_cpu(memory_failure_cpu, cpu); + spin_lock_init(&mf_cpu->lock); + INIT_KFIFO(mf_cpu->fifo); + INIT_WORK(&mf_cpu->work, memory_failure_work_func); + } + + return 0; +} +core_initcall(memory_failure_init); + /** * unpoison_memory - Unpoison a previously poisoned page * @pfn: Page number of the to be unpoisoned page -- cgit v1.2.3 From d91ee5863b71e8c90eaf6035bff3078a85e2e7b5 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Fri, 1 Apr 2011 18:28:35 -0400 Subject: cpuidle: replace xen access to x86 pm_idle and default_idle When a Xen Dom0 kernel boots on a hypervisor, it gets access to the raw-hardware ACPI tables. While it parses the idle tables for the hypervisor's beneift, it uses HLT for its own idle. Rather than have xen scribble on pm_idle and access default_idle, have it simply disable_cpuidle() so acpi_idle will not load and architecture default HLT will be used. cc: xen-devel@lists.xensource.com Tested-by: Konrad Rzeszutek Wilk Acked-by: H. Peter Anvin Signed-off-by: Len Brown --- arch/x86/xen/setup.c | 3 ++- drivers/cpuidle/cpuidle.c | 4 ++++ include/linux/cpuidle.h | 2 ++ 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 60aeeb56948f..a9627e2e3295 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -426,7 +427,7 @@ void __init xen_arch_setup(void) #ifdef CONFIG_X86_32 boot_cpu_data.hlt_works_ok = 1; #endif - pm_idle = default_idle; + disable_cpuidle(); boot_option_idle_override = IDLE_HALT; fiddle_vdso(); diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index faae2c357bab..041df0b056b2 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -34,6 +34,10 @@ int cpuidle_disabled(void) { return off; } +void disable_cpuidle(void) +{ + off = 1; +} #if defined(CONFIG_ARCH_HAS_CPU_IDLE_WAIT) static void cpuidle_kick_cpus(void) diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 36719ead50e8..b89f67da919e 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -122,6 +122,7 @@ struct cpuidle_driver { }; #ifdef CONFIG_CPU_IDLE +extern void disable_cpuidle(void); extern int cpuidle_register_driver(struct cpuidle_driver *drv); struct cpuidle_driver *cpuidle_get_driver(void); @@ -135,6 +136,7 @@ extern int cpuidle_enable_device(struct cpuidle_device *dev); extern void cpuidle_disable_device(struct cpuidle_device *dev); #else +static inline void disable_cpuidle(void) { } static inline int cpuidle_register_driver(struct cpuidle_driver *drv) {return -ENODEV; } -- cgit v1.2.3 From a0bfa1373859e9d11dc92561a8667588803e42d8 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Fri, 1 Apr 2011 19:34:59 -0400 Subject: cpuidle: stop depending on pm_idle cpuidle users should call cpuidle_call_idle() directly rather than via (pm_idle)() function pointer. Architecture may choose to continue using (pm_idle)(), but cpuidle need not depend on it: my_arch_cpu_idle() ... if(cpuidle_call_idle()) pm_idle(); cc: Kevin Hilman cc: Paul Mundt cc: x86@kernel.org Acked-by: H. Peter Anvin Signed-off-by: Len Brown --- arch/arm/kernel/process.c | 4 +++- arch/sh/kernel/idle.c | 6 ++++-- arch/x86/kernel/process_32.c | 4 +++- arch/x86/kernel/process_64.c | 4 +++- drivers/cpuidle/cpuidle.c | 38 ++++++++++++++++++-------------------- include/linux/cpuidle.h | 2 ++ 6 files changed, 33 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 5e1e54197227..d7ee0d4c072d 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -196,7 +197,8 @@ void cpu_idle(void) cpu_relax(); } else { stop_critical_timings(); - pm_idle(); + if (cpuidle_call_idle()) + pm_idle(); start_critical_timings(); /* * This will eventually be removed - pm_idle diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 425d604e3a28..9c7099ebfe14 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -16,12 +16,13 @@ #include #include #include +#include #include #include #include #include -void (*pm_idle)(void) = NULL; +static void (*pm_idle)(void); static int hlt_counter; @@ -100,7 +101,8 @@ void cpu_idle(void) local_irq_disable(); /* Don't trace irqs off for idle */ stop_critical_timings(); - pm_idle(); + if (cpuidle_call_idle()) + pm_idle(); /* * Sanity check to ensure that pm_idle() returns * with IRQs enabled diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index a3d0dc59067b..7a3b65107a27 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include @@ -109,7 +110,8 @@ void cpu_idle(void) local_irq_disable(); /* Don't trace irqs off for idle */ stop_critical_timings(); - pm_idle(); + if (cpuidle_idle_call()) + pm_idle(); start_critical_timings(); } tick_nohz_restart_sched_tick(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ca6f7ab8df33..f693e44e1bf6 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -136,7 +137,8 @@ void cpu_idle(void) enter_idle(); /* Don't trace irqs off for idle */ stop_critical_timings(); - pm_idle(); + if (cpuidle_idle_call()) + pm_idle(); start_critical_timings(); /* In many cases the interrupt that ended idle diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 041df0b056b2..d4c542372886 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -25,10 +25,10 @@ DEFINE_PER_CPU(struct cpuidle_device *, cpuidle_devices); DEFINE_MUTEX(cpuidle_lock); LIST_HEAD(cpuidle_detected_devices); -static void (*pm_idle_old)(void); static int enabled_devices; static int off __read_mostly; +static int initialized __read_mostly; int cpuidle_disabled(void) { @@ -56,25 +56,23 @@ static int __cpuidle_register_device(struct cpuidle_device *dev); * cpuidle_idle_call - the main idle loop * * NOTE: no locks or semaphores should be used here + * return non-zero on failure */ -static void cpuidle_idle_call(void) +int cpuidle_idle_call(void) { struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); struct cpuidle_state *target_state; int next_state; + if (off) + return -ENODEV; + + if (!initialized) + return -ENODEV; + /* check if the device is ready */ - if (!dev || !dev->enabled) { - if (pm_idle_old) - pm_idle_old(); - else -#if defined(CONFIG_ARCH_HAS_DEFAULT_IDLE) - default_idle(); -#else - local_irq_enable(); -#endif - return; - } + if (!dev || !dev->enabled) + return -EBUSY; #if 0 /* shows regressions, re-enable for 2.6.29 */ @@ -99,7 +97,7 @@ static void cpuidle_idle_call(void) next_state = cpuidle_curr_governor->select(dev); if (need_resched()) { local_irq_enable(); - return; + return 0; } target_state = &dev->states[next_state]; @@ -124,6 +122,8 @@ static void cpuidle_idle_call(void) /* give the governor an opportunity to reflect on the outcome */ if (cpuidle_curr_governor->reflect) cpuidle_curr_governor->reflect(dev); + + return 0; } /** @@ -131,10 +131,10 @@ static void cpuidle_idle_call(void) */ void cpuidle_install_idle_handler(void) { - if (enabled_devices && (pm_idle != cpuidle_idle_call)) { + if (enabled_devices) { /* Make sure all changes finished before we switch to new idle */ smp_wmb(); - pm_idle = cpuidle_idle_call; + initialized = 1; } } @@ -143,8 +143,8 @@ void cpuidle_install_idle_handler(void) */ void cpuidle_uninstall_idle_handler(void) { - if (enabled_devices && pm_idle_old && (pm_idle != pm_idle_old)) { - pm_idle = pm_idle_old; + if (enabled_devices) { + initialized = 0; cpuidle_kick_cpus(); } } @@ -440,8 +440,6 @@ static int __init cpuidle_init(void) if (cpuidle_disabled()) return -ENODEV; - pm_idle_old = pm_idle; - ret = cpuidle_add_class_sysfs(&cpu_sysdev_class); if (ret) return ret; diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index b89f67da919e..b51629e15cfc 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -123,6 +123,7 @@ struct cpuidle_driver { #ifdef CONFIG_CPU_IDLE extern void disable_cpuidle(void); +extern int cpuidle_idle_call(void); extern int cpuidle_register_driver(struct cpuidle_driver *drv); struct cpuidle_driver *cpuidle_get_driver(void); @@ -137,6 +138,7 @@ extern void cpuidle_disable_device(struct cpuidle_device *dev); #else static inline void disable_cpuidle(void) { } +static inline int cpuidle_idle_call(void) { return -ENODEV; } static inline int cpuidle_register_driver(struct cpuidle_driver *drv) {return -ENODEV; } -- cgit v1.2.3 From dd48c085c1cdf9446f92826f1fd451167fb6c2fd Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Wed, 3 Aug 2011 16:21:01 -0700 Subject: fault-injection: add ability to export fault_attr in arbitrary directory init_fault_attr_dentries() is used to export fault_attr via debugfs. But it can only export it in debugfs root directory. Per Forlin is working on mmc_fail_request which adds support to inject data errors after a completed host transfer in MMC subsystem. The fault_attr for mmc_fail_request should be defined per mmc host and export it in debugfs directory per mmc host like /sys/kernel/debug/mmc0/mmc_fail_request. init_fault_attr_dentries() doesn't help for mmc_fail_request. So this introduces fault_create_debugfs_attr() which is able to create a directory in the arbitrary directory and replace init_fault_attr_dentries(). [akpm@linux-foundation.org: extraneous semicolon, per Randy] Signed-off-by: Akinobu Mita Tested-by: Per Forlin Cc: Jens Axboe Cc: Christoph Lameter Cc: Pekka Enberg Cc: Matt Mackall Cc: Randy Dunlap Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/fault-injection/fault-injection.txt | 3 +-- block/blk-core.c | 6 ++++-- block/blk-timeout.c | 5 ++++- include/linux/fault-inject.h | 18 +++++------------- lib/fault-inject.c | 20 +++++++------------- mm/failslab.c | 14 +++++++------- mm/page_alloc.c | 13 +++++-------- 7 files changed, 33 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/Documentation/fault-injection/fault-injection.txt b/Documentation/fault-injection/fault-injection.txt index 7be15e44d481..82a5d250d75e 100644 --- a/Documentation/fault-injection/fault-injection.txt +++ b/Documentation/fault-injection/fault-injection.txt @@ -143,8 +143,7 @@ o provide a way to configure fault attributes failslab, fail_page_alloc, and fail_make_request use this way. Helper functions: - init_fault_attr_dentries(entries, attr, name); - void cleanup_fault_attr_dentries(entries); + fault_create_debugfs_attr(name, parent, attr); - module parameters diff --git a/block/blk-core.c b/block/blk-core.c index b850bedad229..b627558c461f 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1368,8 +1368,10 @@ static bool should_fail_request(struct hd_struct *part, unsigned int bytes) static int __init fail_make_request_debugfs(void) { - return init_fault_attr_dentries(&fail_make_request, - "fail_make_request"); + struct dentry *dir = fault_create_debugfs_attr("fail_make_request", + NULL, &fail_make_request); + + return IS_ERR(dir) ? PTR_ERR(dir) : 0; } late_initcall(fail_make_request_debugfs); diff --git a/block/blk-timeout.c b/block/blk-timeout.c index 4f0c06c7a338..780354888958 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -28,7 +28,10 @@ int blk_should_fake_timeout(struct request_queue *q) static int __init fail_io_timeout_debugfs(void) { - return init_fault_attr_dentries(&fail_io_timeout, "fail_io_timeout"); + struct dentry *dir = fault_create_debugfs_attr("fail_io_timeout", + NULL, &fail_io_timeout); + + return IS_ERR(dir) ? PTR_ERR(dir) : 0; } late_initcall(fail_io_timeout_debugfs); diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 3ff060ac7810..c6f996f2abb6 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -25,10 +25,6 @@ struct fault_attr { unsigned long reject_end; unsigned long count; - -#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS - struct dentry *dir; -#endif }; #define FAULT_ATTR_INITIALIZER { \ @@ -45,19 +41,15 @@ bool should_fail(struct fault_attr *attr, ssize_t size); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS -int init_fault_attr_dentries(struct fault_attr *attr, const char *name); -void cleanup_fault_attr_dentries(struct fault_attr *attr); +struct dentry *fault_create_debugfs_attr(const char *name, + struct dentry *parent, struct fault_attr *attr); #else /* CONFIG_FAULT_INJECTION_DEBUG_FS */ -static inline int init_fault_attr_dentries(struct fault_attr *attr, - const char *name) -{ - return -ENODEV; -} - -static inline void cleanup_fault_attr_dentries(struct fault_attr *attr) +static inline struct dentry *fault_create_debugfs_attr(const char *name, + struct dentry *parent, struct fault_attr *attr) { + return ERR_PTR(-ENODEV); } #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ diff --git a/lib/fault-inject.c b/lib/fault-inject.c index 2577b121c7c1..f193b7796449 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -197,21 +197,15 @@ static struct dentry *debugfs_create_atomic_t(const char *name, mode_t mode, return debugfs_create_file(name, mode, parent, value, &fops_atomic_t); } -void cleanup_fault_attr_dentries(struct fault_attr *attr) -{ - debugfs_remove_recursive(attr->dir); -} - -int init_fault_attr_dentries(struct fault_attr *attr, const char *name) +struct dentry *fault_create_debugfs_attr(const char *name, + struct dentry *parent, struct fault_attr *attr) { mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; struct dentry *dir; - dir = debugfs_create_dir(name, NULL); + dir = debugfs_create_dir(name, parent); if (!dir) - return -ENOMEM; - - attr->dir = dir; + return ERR_PTR(-ENOMEM); if (!debugfs_create_ul("probability", mode, dir, &attr->probability)) goto fail; @@ -243,11 +237,11 @@ int init_fault_attr_dentries(struct fault_attr *attr, const char *name) #endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */ - return 0; + return dir; fail: - debugfs_remove_recursive(attr->dir); + debugfs_remove_recursive(dir); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ diff --git a/mm/failslab.c b/mm/failslab.c index 1ce58c201dca..0dd7b8fec71c 100644 --- a/mm/failslab.c +++ b/mm/failslab.c @@ -34,23 +34,23 @@ __setup("failslab=", setup_failslab); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init failslab_debugfs_init(void) { + struct dentry *dir; mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; - int err; - err = init_fault_attr_dentries(&failslab.attr, "failslab"); - if (err) - return err; + dir = fault_create_debugfs_attr("failslab", NULL, &failslab.attr); + if (IS_ERR(dir)) + return PTR_ERR(dir); - if (!debugfs_create_bool("ignore-gfp-wait", mode, failslab.attr.dir, + if (!debugfs_create_bool("ignore-gfp-wait", mode, dir, &failslab.ignore_gfp_wait)) goto fail; - if (!debugfs_create_bool("cache-filter", mode, failslab.attr.dir, + if (!debugfs_create_bool("cache-filter", mode, dir, &failslab.cache_filter)) goto fail; return 0; fail: - cleanup_fault_attr_dentries(&failslab.attr); + debugfs_remove_recursive(dir); return -ENOMEM; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1dbcf8888f14..6e8ecb6e021c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1409,14 +1409,11 @@ static int __init fail_page_alloc_debugfs(void) { mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; struct dentry *dir; - int err; - err = init_fault_attr_dentries(&fail_page_alloc.attr, - "fail_page_alloc"); - if (err) - return err; - - dir = fail_page_alloc.attr.dir; + dir = fault_create_debugfs_attr("fail_page_alloc", NULL, + &fail_page_alloc.attr); + if (IS_ERR(dir)) + return PTR_ERR(dir); if (!debugfs_create_bool("ignore-gfp-wait", mode, dir, &fail_page_alloc.ignore_gfp_wait)) @@ -1430,7 +1427,7 @@ static int __init fail_page_alloc_debugfs(void) return 0; fail: - cleanup_fault_attr_dentries(&fail_page_alloc.attr); + debugfs_remove_recursive(dir); return -ENOMEM; } -- cgit v1.2.3 From 88eca0207cf1574328c3ce8c3be537a9317261bb Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 3 Aug 2011 16:21:06 -0700 Subject: ida: simplified functions for id allocation The current hyper-optimized functions are overkill if you simply want to allocate an id for a device. Create versions which use an internal lock. In followup patches, numerous drivers are converted to use this interface. Thanks to Tejun for feedback. Signed-off-by: Rusty Russell Acked-by: Tejun Heo Acked-by: Jonathan Cameron Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 4 ++++ lib/idr.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 71 insertions(+) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 13a801f3d028..255491cf522e 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -146,6 +146,10 @@ void ida_remove(struct ida *ida, int id); void ida_destroy(struct ida *ida); void ida_init(struct ida *ida); +int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end, + gfp_t gfp_mask); +void ida_simple_remove(struct ida *ida, unsigned int id); + void __init idr_init_cache(void); #endif /* __IDR_H__ */ diff --git a/lib/idr.c b/lib/idr.c index e15502e8b21e..db040ce3fa73 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -34,8 +34,10 @@ #include #include #include +#include static struct kmem_cache *idr_layer_cache; +static DEFINE_SPINLOCK(simple_ida_lock); static struct idr_layer *get_from_free_list(struct idr *idp) { @@ -925,6 +927,71 @@ void ida_destroy(struct ida *ida) } EXPORT_SYMBOL(ida_destroy); +/** + * ida_simple_get - get a new id. + * @ida: the (initialized) ida. + * @start: the minimum id (inclusive, < 0x8000000) + * @end: the maximum id (exclusive, < 0x8000000 or 0) + * @gfp_mask: memory allocation flags + * + * Allocates an id in the range start <= id < end, or returns -ENOSPC. + * On memory allocation failure, returns -ENOMEM. + * + * Use ida_simple_remove() to get rid of an id. + */ +int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end, + gfp_t gfp_mask) +{ + int ret, id; + unsigned int max; + + BUG_ON((int)start < 0); + BUG_ON((int)end < 0); + + if (end == 0) + max = 0x80000000; + else { + BUG_ON(end < start); + max = end - 1; + } + +again: + if (!ida_pre_get(ida, gfp_mask)) + return -ENOMEM; + + spin_lock(&simple_ida_lock); + ret = ida_get_new_above(ida, start, &id); + if (!ret) { + if (id > max) { + ida_remove(ida, id); + ret = -ENOSPC; + } else { + ret = id; + } + } + spin_unlock(&simple_ida_lock); + + if (unlikely(ret == -EAGAIN)) + goto again; + + return ret; +} +EXPORT_SYMBOL(ida_simple_get); + +/** + * ida_simple_remove - remove an allocated id. + * @ida: the (initialized) ida. + * @id: the id returned by ida_simple_get. + */ +void ida_simple_remove(struct ida *ida, unsigned int id) +{ + BUG_ON((int)id < 0); + spin_lock(&simple_ida_lock); + ida_remove(ida, id); + spin_unlock(&simple_ida_lock); +} +EXPORT_SYMBOL(ida_simple_remove); + /** * ida_init - initialize ida handle * @ida: ida handle -- cgit v1.2.3 From 3dab1bce8e840606e76f1bad5a009328e2aa35c7 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Aug 2011 16:21:09 -0700 Subject: mm: page_alloc: increase __GFP_BITS_SHIFT to include __GFP_OTHER_NODE __GFP_OTHER_NODE is used for NUMA allocations on behalf of other nodes. It's supposed to be passed through from the page allocator to zone_statistics(), but it never gets there as gfp_allowed_mask is not wide enough and masks out the flag early in the allocation path. The result is an accounting glitch where successful NUMA allocations by-agent are not properly attributed as local. Increase __GFP_BITS_SHIFT so that it includes __GFP_OTHER_NODE. Signed-off-by: Johannes Weiner Acked-by: Andi Kleen Reviewed-by: Minchan Kim Acked-by: Mel Gorman Reviewed-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index cb4089254f01..3a76faf6a3ee 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -92,7 +92,7 @@ struct vm_area_struct; */ #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) -#define __GFP_BITS_SHIFT 23 /* Room for 23 __GFP_FOO bits */ +#define __GFP_BITS_SHIFT 24 /* Room for N __GFP_FOO bits */ #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /* This equals 0, but use constants in case they ever change */ -- cgit v1.2.3 From 5d6f921b42749d1a70441685b7a4f2801e12ebfb Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 3 Aug 2011 16:21:17 -0700 Subject: drivers/video/backlight/aat2870_bl.c: fix setting max_current - Current implementation tests wrong value for setting aat2870_bl->max_current. - In the current implementation, we cannot differentiate between 2 cases: a) if pdata->max_current is not set , or b) pdata->max_current is set to AAT2870_CURRENT_0_45 (which is also 0). Fix it by setting AAT2870_CURRENT_0_45 to be 1 and adjust the equation in aat2870_brightness() accordingly. Signed-off-by: Axel Lin Cc: Richard Purdie Cc: Samuel Ortiz Tested-by: Jin Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/video/backlight/aat2870_bl.c | 4 ++-- include/linux/mfd/aat2870.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/backlight/aat2870_bl.c b/drivers/video/backlight/aat2870_bl.c index f13a3f7e2e8f..331f1ef1dad5 100644 --- a/drivers/video/backlight/aat2870_bl.c +++ b/drivers/video/backlight/aat2870_bl.c @@ -44,7 +44,7 @@ static inline int aat2870_brightness(struct aat2870_bl_driver_data *aat2870_bl, struct backlight_device *bd = aat2870_bl->bd; int val; - val = brightness * aat2870_bl->max_current; + val = brightness * (aat2870_bl->max_current - 1); val /= bd->props.max_brightness; return val; @@ -175,7 +175,7 @@ static int aat2870_bl_probe(struct platform_device *pdev) else aat2870_bl->channels = AAT2870_BL_CH_ALL; - if (pdata->max_brightness > 0) + if (pdata->max_current > 0) aat2870_bl->max_current = pdata->max_current; else aat2870_bl->max_current = AAT2870_CURRENT_27_9; diff --git a/include/linux/mfd/aat2870.h b/include/linux/mfd/aat2870.h index 89212df05622..f7316c29bdec 100644 --- a/include/linux/mfd/aat2870.h +++ b/include/linux/mfd/aat2870.h @@ -89,7 +89,7 @@ enum aat2870_id { /* Backlight current magnitude (mA) */ enum aat2870_current { - AAT2870_CURRENT_0_45, + AAT2870_CURRENT_0_45 = 1, AAT2870_CURRENT_0_90, AAT2870_CURRENT_1_80, AAT2870_CURRENT_2_70, -- cgit v1.2.3 From 6328650bb4d854a7dc1498d1c0048b838b0d340c Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:18 -0700 Subject: radix_tree: exceptional entries and indices A patchset to extend tmpfs to MAX_LFS_FILESIZE by abandoning its peculiar swap vector, instead keeping a file's swap entries in the same radix tree as its struct page pointers: thus saving memory, and simplifying its code and locking. This patch: The radix_tree is used by several subsystems for different purposes. A major use is to store the struct page pointers of a file's pagecache for memory management. But what if mm wanted to store something other than page pointers there too? The low bit of a radix_tree entry is already used to denote an indirect pointer, for internal use, and the unlikely radix_tree_deref_retry() case. Define the next bit as denoting an exceptional entry, and supply inline functions radix_tree_exception() to return non-0 in either unlikely case, and radix_tree_exceptional_entry() to return non-0 in the second case. If a subsystem already uses radix_tree with that bit set, no problem: it does not affect internal workings at all, but is defined for the convenience of those storing well-aligned pointers in the radix_tree. The radix_tree_gang_lookups have an implicit assumption that the caller can deduce the offset of each entry returned e.g. by the page->index of a struct page. But that may not be feasible for some kinds of item to be stored there. radix_tree_gang_lookup_slot() allow for an optional indices argument, output array in which to return those offsets. The same could be added to other radix_tree_gang_lookups, but for now keep it to the only one for which we need it. Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 36 +++++++++++++++++++++++++++++++++--- lib/radix-tree.c | 29 +++++++++++++++++++---------- mm/filemap.c | 4 ++-- 3 files changed, 54 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 23241c2fecce..b7edf8251455 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -39,7 +39,15 @@ * when it is shrunk, before we rcu free the node. See shrink code for * details. */ -#define RADIX_TREE_INDIRECT_PTR 1 +#define RADIX_TREE_INDIRECT_PTR 1 +/* + * A common use of the radix tree is to store pointers to struct pages; + * but shmem/tmpfs needs also to store swap entries in the same tree: + * those are marked as exceptional entries to distinguish them. + * EXCEPTIONAL_ENTRY tests the bit, EXCEPTIONAL_SHIFT shifts content past it. + */ +#define RADIX_TREE_EXCEPTIONAL_ENTRY 2 +#define RADIX_TREE_EXCEPTIONAL_SHIFT 2 #define radix_tree_indirect_to_ptr(ptr) \ radix_tree_indirect_to_ptr((void __force *)(ptr)) @@ -173,6 +181,28 @@ static inline int radix_tree_deref_retry(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_INDIRECT_PTR); } +/** + * radix_tree_exceptional_entry - radix_tree_deref_slot gave exceptional entry? + * @arg: value returned by radix_tree_deref_slot + * Returns: 0 if well-aligned pointer, non-0 if exceptional entry. + */ +static inline int radix_tree_exceptional_entry(void *arg) +{ + /* Not unlikely because radix_tree_exception often tested first */ + return (unsigned long)arg & RADIX_TREE_EXCEPTIONAL_ENTRY; +} + +/** + * radix_tree_exception - radix_tree_deref_slot returned either exception? + * @arg: value returned by radix_tree_deref_slot + * Returns: 0 if well-aligned pointer, non-0 if either kind of exception. + */ +static inline int radix_tree_exception(void *arg) +{ + return unlikely((unsigned long)arg & + (RADIX_TREE_INDIRECT_PTR | RADIX_TREE_EXCEPTIONAL_ENTRY)); +} + /** * radix_tree_replace_slot - replace item in a slot * @pslot: pointer to slot, returned by radix_tree_lookup_slot @@ -194,8 +224,8 @@ void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items); -unsigned int -radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, +unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, + void ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items); unsigned long radix_tree_next_hole(struct radix_tree_root *root, unsigned long index, unsigned long max_scan); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 7ea2e033d715..348eaefbed74 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -823,8 +823,8 @@ unsigned long radix_tree_prev_hole(struct radix_tree_root *root, EXPORT_SYMBOL(radix_tree_prev_hole); static unsigned int -__lookup(struct radix_tree_node *slot, void ***results, unsigned long index, - unsigned int max_items, unsigned long *next_index) +__lookup(struct radix_tree_node *slot, void ***results, unsigned long *indices, + unsigned long index, unsigned int max_items, unsigned long *next_index) { unsigned int nr_found = 0; unsigned int shift, height; @@ -857,12 +857,16 @@ __lookup(struct radix_tree_node *slot, void ***results, unsigned long index, /* Bottom level: grab some items */ for (i = index & RADIX_TREE_MAP_MASK; i < RADIX_TREE_MAP_SIZE; i++) { - index++; if (slot->slots[i]) { - results[nr_found++] = &(slot->slots[i]); - if (nr_found == max_items) + results[nr_found] = &(slot->slots[i]); + if (indices) + indices[nr_found] = index; + if (++nr_found == max_items) { + index++; goto out; + } } + index++; } out: *next_index = index; @@ -918,8 +922,8 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, if (cur_index > max_index) break; - slots_found = __lookup(node, (void ***)results + ret, cur_index, - max_items - ret, &next_index); + slots_found = __lookup(node, (void ***)results + ret, NULL, + cur_index, max_items - ret, &next_index); nr_found = 0; for (i = 0; i < slots_found; i++) { struct radix_tree_node *slot; @@ -944,6 +948,7 @@ EXPORT_SYMBOL(radix_tree_gang_lookup); * radix_tree_gang_lookup_slot - perform multiple slot lookup on radix tree * @root: radix tree root * @results: where the results of the lookup are placed + * @indices: where their indices should be placed (but usually NULL) * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @@ -958,7 +963,8 @@ EXPORT_SYMBOL(radix_tree_gang_lookup); * protection, radix_tree_deref_slot may fail requiring a retry. */ unsigned int -radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, +radix_tree_gang_lookup_slot(struct radix_tree_root *root, + void ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items) { unsigned long max_index; @@ -974,6 +980,8 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, if (first_index > 0) return 0; results[0] = (void **)&root->rnode; + if (indices) + indices[0] = 0; return 1; } node = indirect_to_ptr(node); @@ -987,8 +995,9 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, if (cur_index > max_index) break; - slots_found = __lookup(node, results + ret, cur_index, - max_items - ret, &next_index); + slots_found = __lookup(node, results + ret, + indices ? indices + ret : NULL, + cur_index, max_items - ret, &next_index); ret += slots_found; if (next_index == 0) break; diff --git a/mm/filemap.c b/mm/filemap.c index 867d40222ec7..b83aebfd0a00 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -840,7 +840,7 @@ unsigned find_get_pages(struct address_space *mapping, pgoff_t start, rcu_read_lock(); restart: nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, - (void ***)pages, start, nr_pages); + (void ***)pages, NULL, start, nr_pages); ret = 0; for (i = 0; i < nr_found; i++) { struct page *page; @@ -903,7 +903,7 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, rcu_read_lock(); restart: nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, - (void ***)pages, index, nr_pages); + (void ***)pages, NULL, index, nr_pages); ret = 0; for (i = 0; i < nr_found; i++) { struct page *page; -- cgit v1.2.3 From a2c16d6cb0e478812829ca84aeabd02e36af35eb Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:19 -0700 Subject: mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 23 +++++++++++++++++++++++ mm/filemap.c | 49 +++++++++++++++++++++++++++++++------------------ mm/swapfile.c | 20 ++++++++++++-------- 3 files changed, 66 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index cd42e30b7c6e..2189d3ffc85d 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -1,3 +1,8 @@ +#ifndef _LINUX_SWAPOPS_H +#define _LINUX_SWAPOPS_H + +#include + /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in @@ -76,6 +81,22 @@ static inline pte_t swp_entry_to_pte(swp_entry_t entry) return __swp_entry_to_pte(arch_entry); } +static inline swp_entry_t radix_to_swp_entry(void *arg) +{ + swp_entry_t entry; + + entry.val = (unsigned long)arg >> RADIX_TREE_EXCEPTIONAL_SHIFT; + return entry; +} + +static inline void *swp_to_radix_entry(swp_entry_t entry) +{ + unsigned long value; + + value = entry.val << RADIX_TREE_EXCEPTIONAL_SHIFT; + return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY); +} + #ifdef CONFIG_MIGRATION static inline swp_entry_t make_migration_entry(struct page *page, int write) { @@ -169,3 +190,5 @@ static inline int non_swap_entry(swp_entry_t entry) return 0; } #endif + +#endif /* _LINUX_SWAPOPS_H */ diff --git a/mm/filemap.c b/mm/filemap.c index b83aebfd0a00..76bfb6460f57 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -714,9 +714,12 @@ repeat: page = radix_tree_deref_slot(pagep); if (unlikely(!page)) goto out; - if (radix_tree_deref_retry(page)) + if (radix_tree_exception(page)) { + if (radix_tree_exceptional_entry(page)) + goto out; + /* radix_tree_deref_retry(page) */ goto repeat; - + } if (!page_cache_get_speculative(page)) goto repeat; @@ -753,7 +756,7 @@ struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) repeat: page = find_get_page(mapping, offset); - if (page) { + if (page && !radix_tree_exception(page)) { lock_page(page); /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { @@ -849,11 +852,14 @@ repeat: if (unlikely(!page)) continue; - /* - * This can only trigger when the entry at index 0 moves out - * of or back to the root: none yet gotten, safe to restart. - */ - if (radix_tree_deref_retry(page)) { + if (radix_tree_exception(page)) { + if (radix_tree_exceptional_entry(page)) + continue; + /* + * radix_tree_deref_retry(page): + * can only trigger when entry at index 0 moves out of + * or back to root: none yet gotten, safe to restart. + */ WARN_ON(start | i); goto restart; } @@ -912,12 +918,16 @@ repeat: if (unlikely(!page)) continue; - /* - * This can only trigger when the entry at index 0 moves out - * of or back to the root: none yet gotten, safe to restart. - */ - if (radix_tree_deref_retry(page)) + if (radix_tree_exception(page)) { + if (radix_tree_exceptional_entry(page)) + break; + /* + * radix_tree_deref_retry(page): + * can only trigger when entry at index 0 moves out of + * or back to root: none yet gotten, safe to restart. + */ goto restart; + } if (!page_cache_get_speculative(page)) goto repeat; @@ -977,12 +987,15 @@ repeat: if (unlikely(!page)) continue; - /* - * This can only trigger when the entry at index 0 moves out - * of or back to the root: none yet gotten, safe to restart. - */ - if (radix_tree_deref_retry(page)) + if (radix_tree_exception(page)) { + BUG_ON(radix_tree_exceptional_entry(page)); + /* + * radix_tree_deref_retry(page): + * can only trigger when entry at index 0 moves out of + * or back to root: none yet gotten, safe to restart. + */ goto restart; + } if (!page_cache_get_speculative(page)) goto repeat; diff --git a/mm/swapfile.c b/mm/swapfile.c index 1b8c33907242..17bc224bce68 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1924,20 +1924,24 @@ static unsigned long read_swap_header(struct swap_info_struct *p, /* * Find out how many pages are allowed for a single swap - * device. There are two limiting factors: 1) the number of - * bits for the swap offset in the swp_entry_t type and - * 2) the number of bits in the a swap pte as defined by - * the different architectures. In order to find the - * largest possible bit mask a swap entry with swap type 0 + * device. There are three limiting factors: 1) the number + * of bits for the swap offset in the swp_entry_t type, and + * 2) the number of bits in the swap pte as defined by the + * the different architectures, and 3) the number of free bits + * in an exceptional radix_tree entry. In order to find the + * largest possible bit mask, a swap entry with swap type 0 * and swap offset ~0UL is created, encoded to a swap pte, - * decoded to a swp_entry_t again and finally the swap + * decoded to a swp_entry_t again, and finally the swap * offset is extracted. This will mask all the bits from * the initial ~0UL mask that can't be encoded in either * the swp_entry_t or the architecture definition of a - * swap pte. + * swap pte. Then the same is done for a radix_tree entry. */ maxpages = swp_offset(pte_to_swp_entry( - swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; + swp_entry_to_pte(swp_entry(0, ~0UL)))); + maxpages = swp_offset(radix_to_swp_entry( + swp_to_radix_entry(swp_entry(0, maxpages)))) + 1; + if (maxpages > swap_header->info.last_page) { maxpages = swap_header->info.last_page + 1; /* p->max is an unsigned int: don't overflow it */ -- cgit v1.2.3 From 285b2c4fdd69ea73b4762785d8c6be83b6c074a6 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:20 -0700 Subject: tmpfs: demolish old swap vector support The maximum size of a shmem/tmpfs file has been limited by the maximum size of its triple-indirect swap vector. With 4kB page size, maximum filesize was just over 2TB on a 32-bit kernel, but sadly one eighth of that on a 64-bit kernel. (With 8kB page size, maximum filesize was just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel, MAX_LFS_FILESIZE being then more restrictive than swap vector layout.) It's a shame that tmpfs should be more restrictive than ramfs, and this limitation has now been noticed. Add another level to the swap vector? No, it became obscure and hard to maintain, once I complicated it to make use of highmem pages nine years ago: better choose another way. Surely, if 2.4 had had the radix tree pagecache introduced in 2.5, then tmpfs would never have invented its own peculiar radix tree: we would have fitted swap entries into the common radix tree instead, in much the same way as we fit swap entries into page tables. And why should each file have a separate radix tree for its pages and for its swap entries? The swap entries are required precisely where and when the pages are not. We want to put them together in a single radix tree: which can then avoid much of the locking which was needed to prevent them from being exchanged underneath us. This also avoids the waste of memory devoted to swap vectors, first in the shmem_inode itself, then at least two more pages once a file grew beyond 16 data pages (pages accounted by df and du, but not by memcg). Allocated upfront, to avoid allocation when under swapping pressure, but pure waste when CONFIG_SWAP is not set - I have never spattered around the ifdefs to prevent that, preferring this move to sharing the common radix tree instead. There are three downsides to sharing the radix tree. One, that it binds tmpfs more tightly to the rest of mm, either requiring knowledge of swap entries in radix tree there, or duplication of its code here in shmem.c. I believe that the simplications and memory savings (and probable higher performance, not yet measured) justify that. Two, that on HIGHMEM systems with SWAP enabled, it's the lowmem radix nodes that cannot be freed under memory pressure - whereas before it was the less precious highmem swap vector pages that could not be freed. I'm hoping that 64-bit has now been accessible for long enough, that the highmem argument has grown much less persuasive. Three, that swapoff is slower than it used to be on tmpfs files, since it's using a simple generic mechanism not tailored to it: I find this noticeable, and shall want to improve, but maybe nobody else will notice. So... now remove most of the old swap vector code from shmem.c. But, for the moment, keep the simple i_direct vector of 16 pages, with simple accessors shmem_put_swap() and shmem_get_swap(), as a toy implementation to help mark where swap needs to be handled in subsequent patches. Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 2 - mm/shmem.c | 782 +++++------------------------------------------ 2 files changed, 84 insertions(+), 700 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index aa08fa8fd79b..80b695213fdb 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -17,9 +17,7 @@ struct shmem_inode_info { unsigned long flags; unsigned long alloced; /* data pages alloced to file */ unsigned long swapped; /* subtotal assigned to swap */ - unsigned long next_index; /* highest alloced index + 1 */ struct shared_policy policy; /* NUMA memory alloc policy */ - struct page *i_indirect; /* top indirect blocks page */ union { swp_entry_t i_direct[SHMEM_NR_DIRECT]; /* first blocks */ char inline_symlink[SHMEM_SYMLINK_INLINE_LEN]; diff --git a/mm/shmem.c b/mm/shmem.c index 5cc21f8b4cd3..5574b00ca771 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -66,37 +66,9 @@ static struct vfsmount *shm_mnt; #include #include -/* - * The maximum size of a shmem/tmpfs file is limited by the maximum size of - * its triple-indirect swap vector - see illustration at shmem_swp_entry(). - * - * With 4kB page size, maximum file size is just over 2TB on a 32-bit kernel, - * but one eighth of that on a 64-bit kernel. With 8kB page size, maximum - * file size is just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel, - * MAX_LFS_FILESIZE being then more restrictive than swap vector layout. - * - * We use / and * instead of shifts in the definitions below, so that the swap - * vector can be tested with small even values (e.g. 20) for ENTRIES_PER_PAGE. - */ -#define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long)) -#define ENTRIES_PER_PAGEPAGE ((unsigned long long)ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) - -#define SHMSWP_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1)) -#define SHMSWP_MAX_BYTES (SHMSWP_MAX_INDEX << PAGE_CACHE_SHIFT) - -#define SHMEM_MAX_BYTES min_t(unsigned long long, SHMSWP_MAX_BYTES, MAX_LFS_FILESIZE) -#define SHMEM_MAX_INDEX ((unsigned long)((SHMEM_MAX_BYTES+1) >> PAGE_CACHE_SHIFT)) - #define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) #define VM_ACCT(size) (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT) -/* info->flags needs VM_flags to handle pagein/truncate races efficiently */ -#define SHMEM_PAGEIN VM_READ -#define SHMEM_TRUNCATE VM_WRITE - -/* Definition to limit shmem_truncate's steps between cond_rescheds */ -#define LATENCY_LIMIT 64 - /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 @@ -107,7 +79,7 @@ struct shmem_xattr { char value[0]; }; -/* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */ +/* Flag allocation requirements to shmem_getpage */ enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_CACHE, /* don't exceed i_size, may allocate page */ @@ -137,56 +109,6 @@ static inline int shmem_getpage(struct inode *inode, pgoff_t index, mapping_gfp_mask(inode->i_mapping), fault_type); } -static inline struct page *shmem_dir_alloc(gfp_t gfp_mask) -{ - /* - * The above definition of ENTRIES_PER_PAGE, and the use of - * BLOCKS_PER_PAGE on indirect pages, assume PAGE_CACHE_SIZE: - * might be reconsidered if it ever diverges from PAGE_SIZE. - * - * Mobility flags are masked out as swap vectors cannot move - */ - return alloc_pages((gfp_mask & ~GFP_MOVABLE_MASK) | __GFP_ZERO, - PAGE_CACHE_SHIFT-PAGE_SHIFT); -} - -static inline void shmem_dir_free(struct page *page) -{ - __free_pages(page, PAGE_CACHE_SHIFT-PAGE_SHIFT); -} - -static struct page **shmem_dir_map(struct page *page) -{ - return (struct page **)kmap_atomic(page, KM_USER0); -} - -static inline void shmem_dir_unmap(struct page **dir) -{ - kunmap_atomic(dir, KM_USER0); -} - -static swp_entry_t *shmem_swp_map(struct page *page) -{ - return (swp_entry_t *)kmap_atomic(page, KM_USER1); -} - -static inline void shmem_swp_balance_unmap(void) -{ - /* - * When passing a pointer to an i_direct entry, to code which - * also handles indirect entries and so will shmem_swp_unmap, - * we must arrange for the preempt count to remain in balance. - * What kmap_atomic of a lowmem page does depends on config - * and architecture, so pretend to kmap_atomic some lowmem page. - */ - (void) kmap_atomic(ZERO_PAGE(0), KM_USER1); -} - -static inline void shmem_swp_unmap(swp_entry_t *entry) -{ - kunmap_atomic(entry, KM_USER1); -} - static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) { return sb->s_fs_info; @@ -303,468 +225,56 @@ static void shmem_recalc_inode(struct inode *inode) } } -/** - * shmem_swp_entry - find the swap vector position in the info structure - * @info: info structure for the inode - * @index: index of the page to find - * @page: optional page to add to the structure. Has to be preset to - * all zeros - * - * If there is no space allocated yet it will return NULL when - * page is NULL, else it will use the page for the needed block, - * setting it to NULL on return to indicate that it has been used. - * - * The swap vector is organized the following way: - * - * There are SHMEM_NR_DIRECT entries directly stored in the - * shmem_inode_info structure. So small files do not need an addional - * allocation. - * - * For pages with index > SHMEM_NR_DIRECT there is the pointer - * i_indirect which points to a page which holds in the first half - * doubly indirect blocks, in the second half triple indirect blocks: - * - * For an artificial ENTRIES_PER_PAGE = 4 this would lead to the - * following layout (for SHMEM_NR_DIRECT == 16): - * - * i_indirect -> dir --> 16-19 - * | +-> 20-23 - * | - * +-->dir2 --> 24-27 - * | +-> 28-31 - * | +-> 32-35 - * | +-> 36-39 - * | - * +-->dir3 --> 40-43 - * +-> 44-47 - * +-> 48-51 - * +-> 52-55 - */ -static swp_entry_t *shmem_swp_entry(struct shmem_inode_info *info, unsigned long index, struct page **page) -{ - unsigned long offset; - struct page **dir; - struct page *subdir; - - if (index < SHMEM_NR_DIRECT) { - shmem_swp_balance_unmap(); - return info->i_direct+index; - } - if (!info->i_indirect) { - if (page) { - info->i_indirect = *page; - *page = NULL; - } - return NULL; /* need another page */ - } - - index -= SHMEM_NR_DIRECT; - offset = index % ENTRIES_PER_PAGE; - index /= ENTRIES_PER_PAGE; - dir = shmem_dir_map(info->i_indirect); - - if (index >= ENTRIES_PER_PAGE/2) { - index -= ENTRIES_PER_PAGE/2; - dir += ENTRIES_PER_PAGE/2 + index/ENTRIES_PER_PAGE; - index %= ENTRIES_PER_PAGE; - subdir = *dir; - if (!subdir) { - if (page) { - *dir = *page; - *page = NULL; - } - shmem_dir_unmap(dir); - return NULL; /* need another page */ - } - shmem_dir_unmap(dir); - dir = shmem_dir_map(subdir); - } - - dir += index; - subdir = *dir; - if (!subdir) { - if (!page || !(subdir = *page)) { - shmem_dir_unmap(dir); - return NULL; /* need a page */ - } - *dir = subdir; - *page = NULL; - } - shmem_dir_unmap(dir); - return shmem_swp_map(subdir) + offset; -} - -static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, unsigned long value) +static void shmem_put_swap(struct shmem_inode_info *info, pgoff_t index, + swp_entry_t swap) { - long incdec = value? 1: -1; - - entry->val = value; - info->swapped += incdec; - if ((unsigned long)(entry - info->i_direct) >= SHMEM_NR_DIRECT) { - struct page *page = kmap_atomic_to_page(entry); - set_page_private(page, page_private(page) + incdec); - } -} - -/** - * shmem_swp_alloc - get the position of the swap entry for the page. - * @info: info structure for the inode - * @index: index of the page to find - * @sgp: check and recheck i_size? skip allocation? - * @gfp: gfp mask to use for any page allocation - * - * If the entry does not exist, allocate it. - */ -static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, - unsigned long index, enum sgp_type sgp, gfp_t gfp) -{ - struct inode *inode = &info->vfs_inode; - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); - struct page *page = NULL; - swp_entry_t *entry; - - if (sgp != SGP_WRITE && - ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) - return ERR_PTR(-EINVAL); - - while (!(entry = shmem_swp_entry(info, index, &page))) { - if (sgp == SGP_READ) - return shmem_swp_map(ZERO_PAGE(0)); - /* - * Test used_blocks against 1 less max_blocks, since we have 1 data - * page (and perhaps indirect index pages) yet to allocate: - * a waste to allocate index if we cannot allocate data. - */ - if (sbinfo->max_blocks) { - if (percpu_counter_compare(&sbinfo->used_blocks, - sbinfo->max_blocks - 1) >= 0) - return ERR_PTR(-ENOSPC); - percpu_counter_inc(&sbinfo->used_blocks); - inode->i_blocks += BLOCKS_PER_PAGE; - } - - spin_unlock(&info->lock); - page = shmem_dir_alloc(gfp); - spin_lock(&info->lock); - - if (!page) { - shmem_free_blocks(inode, 1); - return ERR_PTR(-ENOMEM); - } - if (sgp != SGP_WRITE && - ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { - entry = ERR_PTR(-EINVAL); - break; - } - if (info->next_index <= index) - info->next_index = index + 1; - } - if (page) { - /* another task gave its page, or truncated the file */ - shmem_free_blocks(inode, 1); - shmem_dir_free(page); - } - if (info->next_index <= index && !IS_ERR(entry)) - info->next_index = index + 1; - return entry; -} - -/** - * shmem_free_swp - free some swap entries in a directory - * @dir: pointer to the directory - * @edir: pointer after last entry of the directory - * @punch_lock: pointer to spinlock when needed for the holepunch case - */ -static int shmem_free_swp(swp_entry_t *dir, swp_entry_t *edir, - spinlock_t *punch_lock) -{ - spinlock_t *punch_unlock = NULL; - swp_entry_t *ptr; - int freed = 0; - - for (ptr = dir; ptr < edir; ptr++) { - if (ptr->val) { - if (unlikely(punch_lock)) { - punch_unlock = punch_lock; - punch_lock = NULL; - spin_lock(punch_unlock); - if (!ptr->val) - continue; - } - free_swap_and_cache(*ptr); - *ptr = (swp_entry_t){0}; - freed++; - } - } - if (punch_unlock) - spin_unlock(punch_unlock); - return freed; -} - -static int shmem_map_and_free_swp(struct page *subdir, int offset, - int limit, struct page ***dir, spinlock_t *punch_lock) -{ - swp_entry_t *ptr; - int freed = 0; - - ptr = shmem_swp_map(subdir); - for (; offset < limit; offset += LATENCY_LIMIT) { - int size = limit - offset; - if (size > LATENCY_LIMIT) - size = LATENCY_LIMIT; - freed += shmem_free_swp(ptr+offset, ptr+offset+size, - punch_lock); - if (need_resched()) { - shmem_swp_unmap(ptr); - if (*dir) { - shmem_dir_unmap(*dir); - *dir = NULL; - } - cond_resched(); - ptr = shmem_swp_map(subdir); - } - } - shmem_swp_unmap(ptr); - return freed; + if (index < SHMEM_NR_DIRECT) + info->i_direct[index] = swap; } -static void shmem_free_pages(struct list_head *next) +static swp_entry_t shmem_get_swap(struct shmem_inode_info *info, pgoff_t index) { - struct page *page; - int freed = 0; - - do { - page = container_of(next, struct page, lru); - next = next->next; - shmem_dir_free(page); - freed++; - if (freed >= LATENCY_LIMIT) { - cond_resched(); - freed = 0; - } - } while (next); + return (index < SHMEM_NR_DIRECT) ? + info->i_direct[index] : (swp_entry_t){0}; } -void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end) +void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { + struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); - unsigned long idx; - unsigned long size; - unsigned long limit; - unsigned long stage; - unsigned long diroff; - struct page **dir; - struct page *topdir; - struct page *middir; - struct page *subdir; - swp_entry_t *ptr; - LIST_HEAD(pages_to_free); - long nr_pages_to_free = 0; - long nr_swaps_freed = 0; - int offset; - int freed; - int punch_hole; - spinlock_t *needs_lock; - spinlock_t *punch_lock; - unsigned long upper_limit; + pgoff_t start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + pgoff_t end = (lend >> PAGE_CACHE_SHIFT); + pgoff_t index; + swp_entry_t swap; - truncate_inode_pages_range(inode->i_mapping, start, end); + truncate_inode_pages_range(mapping, lstart, lend); - inode->i_ctime = inode->i_mtime = CURRENT_TIME; - idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (idx >= info->next_index) - return; + if (end > SHMEM_NR_DIRECT) + end = SHMEM_NR_DIRECT; spin_lock(&info->lock); - info->flags |= SHMEM_TRUNCATE; - if (likely(end == (loff_t) -1)) { - limit = info->next_index; - upper_limit = SHMEM_MAX_INDEX; - info->next_index = idx; - needs_lock = NULL; - punch_hole = 0; - } else { - if (end + 1 >= inode->i_size) { /* we may free a little more */ - limit = (inode->i_size + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; - upper_limit = SHMEM_MAX_INDEX; - } else { - limit = (end + 1) >> PAGE_CACHE_SHIFT; - upper_limit = limit; - } - needs_lock = &info->lock; - punch_hole = 1; - } - - topdir = info->i_indirect; - if (topdir && idx <= SHMEM_NR_DIRECT && !punch_hole) { - info->i_indirect = NULL; - nr_pages_to_free++; - list_add(&topdir->lru, &pages_to_free); - } - spin_unlock(&info->lock); - - if (info->swapped && idx < SHMEM_NR_DIRECT) { - ptr = info->i_direct; - size = limit; - if (size > SHMEM_NR_DIRECT) - size = SHMEM_NR_DIRECT; - nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size, needs_lock); - } - - /* - * If there are no indirect blocks or we are punching a hole - * below indirect blocks, nothing to be done. - */ - if (!topdir || limit <= SHMEM_NR_DIRECT) - goto done2; - - /* - * The truncation case has already dropped info->lock, and we're safe - * because i_size and next_index have already been lowered, preventing - * access beyond. But in the punch_hole case, we still need to take - * the lock when updating the swap directory, because there might be - * racing accesses by shmem_getpage(SGP_CACHE), shmem_unuse_inode or - * shmem_writepage. However, whenever we find we can remove a whole - * directory page (not at the misaligned start or end of the range), - * we first NULLify its pointer in the level above, and then have no - * need to take the lock when updating its contents: needs_lock and - * punch_lock (either pointing to info->lock or NULL) manage this. - */ - - upper_limit -= SHMEM_NR_DIRECT; - limit -= SHMEM_NR_DIRECT; - idx = (idx > SHMEM_NR_DIRECT)? (idx - SHMEM_NR_DIRECT): 0; - offset = idx % ENTRIES_PER_PAGE; - idx -= offset; - - dir = shmem_dir_map(topdir); - stage = ENTRIES_PER_PAGEPAGE/2; - if (idx < ENTRIES_PER_PAGEPAGE/2) { - middir = topdir; - diroff = idx/ENTRIES_PER_PAGE; - } else { - dir += ENTRIES_PER_PAGE/2; - dir += (idx - ENTRIES_PER_PAGEPAGE/2)/ENTRIES_PER_PAGEPAGE; - while (stage <= idx) - stage += ENTRIES_PER_PAGEPAGE; - middir = *dir; - if (*dir) { - diroff = ((idx - ENTRIES_PER_PAGEPAGE/2) % - ENTRIES_PER_PAGEPAGE) / ENTRIES_PER_PAGE; - if (!diroff && !offset && upper_limit >= stage) { - if (needs_lock) { - spin_lock(needs_lock); - *dir = NULL; - spin_unlock(needs_lock); - needs_lock = NULL; - } else - *dir = NULL; - nr_pages_to_free++; - list_add(&middir->lru, &pages_to_free); - } - shmem_dir_unmap(dir); - dir = shmem_dir_map(middir); - } else { - diroff = 0; - offset = 0; - idx = stage; + for (index = start; index < end; index++) { + swap = shmem_get_swap(info, index); + if (swap.val) { + free_swap_and_cache(swap); + shmem_put_swap(info, index, (swp_entry_t){0}); + info->swapped--; } } - for (; idx < limit; idx += ENTRIES_PER_PAGE, diroff++) { - if (unlikely(idx == stage)) { - shmem_dir_unmap(dir); - dir = shmem_dir_map(topdir) + - ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE; - while (!*dir) { - dir++; - idx += ENTRIES_PER_PAGEPAGE; - if (idx >= limit) - goto done1; - } - stage = idx + ENTRIES_PER_PAGEPAGE; - middir = *dir; - if (punch_hole) - needs_lock = &info->lock; - if (upper_limit >= stage) { - if (needs_lock) { - spin_lock(needs_lock); - *dir = NULL; - spin_unlock(needs_lock); - needs_lock = NULL; - } else - *dir = NULL; - nr_pages_to_free++; - list_add(&middir->lru, &pages_to_free); - } - shmem_dir_unmap(dir); - cond_resched(); - dir = shmem_dir_map(middir); - diroff = 0; - } - punch_lock = needs_lock; - subdir = dir[diroff]; - if (subdir && !offset && upper_limit-idx >= ENTRIES_PER_PAGE) { - if (needs_lock) { - spin_lock(needs_lock); - dir[diroff] = NULL; - spin_unlock(needs_lock); - punch_lock = NULL; - } else - dir[diroff] = NULL; - nr_pages_to_free++; - list_add(&subdir->lru, &pages_to_free); - } - if (subdir && page_private(subdir) /* has swap entries */) { - size = limit - idx; - if (size > ENTRIES_PER_PAGE) - size = ENTRIES_PER_PAGE; - freed = shmem_map_and_free_swp(subdir, - offset, size, &dir, punch_lock); - if (!dir) - dir = shmem_dir_map(middir); - nr_swaps_freed += freed; - if (offset || punch_lock) { - spin_lock(&info->lock); - set_page_private(subdir, - page_private(subdir) - freed); - spin_unlock(&info->lock); - } else - BUG_ON(page_private(subdir) != freed); - } - offset = 0; - } -done1: - shmem_dir_unmap(dir); -done2: - if (inode->i_mapping->nrpages && (info->flags & SHMEM_PAGEIN)) { + if (mapping->nrpages) { + spin_unlock(&info->lock); /* - * Call truncate_inode_pages again: racing shmem_unuse_inode - * may have swizzled a page in from swap since - * truncate_pagecache or generic_delete_inode did it, before we - * lowered next_index. Also, though shmem_getpage checks - * i_size before adding to cache, no recheck after: so fix the - * narrow window there too. + * A page may have meanwhile sneaked in from swap. */ - truncate_inode_pages_range(inode->i_mapping, start, end); + truncate_inode_pages_range(mapping, lstart, lend); + spin_lock(&info->lock); } - spin_lock(&info->lock); - info->flags &= ~SHMEM_TRUNCATE; - info->swapped -= nr_swaps_freed; - if (nr_pages_to_free) - shmem_free_blocks(inode, nr_pages_to_free); shmem_recalc_inode(inode); spin_unlock(&info->lock); - /* - * Empty swap vector directory pages to be freed? - */ - if (!list_empty(&pages_to_free)) { - pages_to_free.prev->next = NULL; - shmem_free_pages(pages_to_free.next); - } + inode->i_ctime = inode->i_mtime = CURRENT_TIME; } EXPORT_SYMBOL_GPL(shmem_truncate_range); @@ -797,19 +307,6 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) if (page) unlock_page(page); } - /* - * Reset SHMEM_PAGEIN flag so that shmem_truncate can - * detect if any pages might have been added to cache - * after truncate_inode_pages. But we needn't bother - * if it's being fully truncated to zero-length: the - * nrpages check is efficient enough in that case. - */ - if (newsize) { - struct shmem_inode_info *info = SHMEM_I(inode); - spin_lock(&info->lock); - info->flags &= ~SHMEM_PAGEIN; - spin_unlock(&info->lock); - } } if (newsize != oldsize) { i_size_write(inode, newsize); @@ -859,106 +356,28 @@ static void shmem_evict_inode(struct inode *inode) end_writeback(inode); } -static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_t *edir) -{ - swp_entry_t *ptr; - - for (ptr = dir; ptr < edir; ptr++) { - if (ptr->val == entry.val) - return ptr - dir; - } - return -1; -} - static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page) { - struct address_space *mapping; + struct address_space *mapping = info->vfs_inode.i_mapping; unsigned long idx; - unsigned long size; - unsigned long limit; - unsigned long stage; - struct page **dir; - struct page *subdir; - swp_entry_t *ptr; - int offset; int error; - idx = 0; - ptr = info->i_direct; - spin_lock(&info->lock); - if (!info->swapped) { - list_del_init(&info->swaplist); - goto lost2; - } - limit = info->next_index; - size = limit; - if (size > SHMEM_NR_DIRECT) - size = SHMEM_NR_DIRECT; - offset = shmem_find_swp(entry, ptr, ptr+size); - if (offset >= 0) { - shmem_swp_balance_unmap(); - goto found; - } - if (!info->i_indirect) - goto lost2; - - dir = shmem_dir_map(info->i_indirect); - stage = SHMEM_NR_DIRECT + ENTRIES_PER_PAGEPAGE/2; - - for (idx = SHMEM_NR_DIRECT; idx < limit; idx += ENTRIES_PER_PAGE, dir++) { - if (unlikely(idx == stage)) { - shmem_dir_unmap(dir-1); - if (cond_resched_lock(&info->lock)) { - /* check it has not been truncated */ - if (limit > info->next_index) { - limit = info->next_index; - if (idx >= limit) - goto lost2; - } - } - dir = shmem_dir_map(info->i_indirect) + - ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE; - while (!*dir) { - dir++; - idx += ENTRIES_PER_PAGEPAGE; - if (idx >= limit) - goto lost1; - } - stage = idx + ENTRIES_PER_PAGEPAGE; - subdir = *dir; - shmem_dir_unmap(dir); - dir = shmem_dir_map(subdir); - } - subdir = *dir; - if (subdir && page_private(subdir)) { - ptr = shmem_swp_map(subdir); - size = limit - idx; - if (size > ENTRIES_PER_PAGE) - size = ENTRIES_PER_PAGE; - offset = shmem_find_swp(entry, ptr, ptr+size); - shmem_swp_unmap(ptr); - if (offset >= 0) { - shmem_dir_unmap(dir); - ptr = shmem_swp_map(subdir); - goto found; - } - } - } -lost1: - shmem_dir_unmap(dir-1); -lost2: - spin_unlock(&info->lock); + for (idx = 0; idx < SHMEM_NR_DIRECT; idx++) + if (shmem_get_swap(info, idx).val == entry.val) + goto found; return 0; found: - idx += offset; - ptr += offset; + spin_lock(&info->lock); + if (shmem_get_swap(info, idx).val != entry.val) { + spin_unlock(&info->lock); + return 0; + } /* * Move _head_ to start search for next from here. * But be careful: shmem_evict_inode checks list_empty without taking * mutex, and there's an instant in list_move_tail when info->swaplist - * would appear empty, if it were the only one on shmem_swaplist. We - * could avoid doing it if inode NULL; or use this minor optimization. + * would appear empty, if it were the only one on shmem_swaplist. */ if (shmem_swaplist.next != &info->swaplist) list_move_tail(&shmem_swaplist, &info->swaplist); @@ -968,19 +387,17 @@ found: * but also to hold up shmem_evict_inode(): so inode cannot be freed * beneath us (pagelock doesn't help until the page is in pagecache). */ - mapping = info->vfs_inode.i_mapping; error = add_to_page_cache_locked(page, mapping, idx, GFP_NOWAIT); /* which does mem_cgroup_uncharge_cache_page on error */ if (error != -ENOMEM) { delete_from_swap_cache(page); set_page_dirty(page); - info->flags |= SHMEM_PAGEIN; - shmem_swp_set(info, ptr, 0); + shmem_put_swap(info, idx, (swp_entry_t){0}); + info->swapped--; swap_free(entry); error = 1; /* not an error, but entry was found */ } - shmem_swp_unmap(ptr); spin_unlock(&info->lock); return error; } @@ -1017,7 +434,14 @@ int shmem_unuse(swp_entry_t entry, struct page *page) mutex_lock(&shmem_swaplist_mutex); list_for_each_safe(p, next, &shmem_swaplist) { info = list_entry(p, struct shmem_inode_info, swaplist); - found = shmem_unuse_inode(info, entry, page); + if (!info->swapped) { + spin_lock(&info->lock); + if (!info->swapped) + list_del_init(&info->swaplist); + spin_unlock(&info->lock); + } + if (info->swapped) + found = shmem_unuse_inode(info, entry, page); cond_resched(); if (found) break; @@ -1041,7 +465,7 @@ out: static int shmem_writepage(struct page *page, struct writeback_control *wbc) { struct shmem_inode_info *info; - swp_entry_t *entry, swap; + swp_entry_t swap, oswap; struct address_space *mapping; unsigned long index; struct inode *inode; @@ -1067,6 +491,15 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ goto redirty; } + + /* + * Just for this patch, we have a toy implementation, + * which can swap out only the first SHMEM_NR_DIRECT pages: + * for simple demonstration of where we need to think about swap. + */ + if (index >= SHMEM_NR_DIRECT) + goto redirty; + swap = get_swap_page(); if (!swap.val) goto redirty; @@ -1087,22 +520,19 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) spin_lock(&info->lock); mutex_unlock(&shmem_swaplist_mutex); - if (index >= info->next_index) { - BUG_ON(!(info->flags & SHMEM_TRUNCATE)); - goto unlock; - } - entry = shmem_swp_entry(info, index, NULL); - if (entry->val) { + oswap = shmem_get_swap(info, index); + if (oswap.val) { WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ - free_swap_and_cache(*entry); - shmem_swp_set(info, entry, 0); + free_swap_and_cache(oswap); + shmem_put_swap(info, index, (swp_entry_t){0}); + info->swapped--; } shmem_recalc_inode(inode); if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { delete_from_page_cache(page); - shmem_swp_set(info, entry, swap.val); - shmem_swp_unmap(entry); + shmem_put_swap(info, index, swap); + info->swapped++; swap_shmem_alloc(swap); spin_unlock(&info->lock); BUG_ON(page_mapped(page)); @@ -1110,13 +540,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) return 0; } - shmem_swp_unmap(entry); -unlock: spin_unlock(&info->lock); - /* - * add_to_swap_cache() doesn't return -EEXIST, so we can safely - * clear SWAP_HAS_CACHE flag. - */ swapcache_free(swap, NULL); redirty: set_page_dirty(page); @@ -1230,12 +654,10 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t idx, struct shmem_sb_info *sbinfo; struct page *page; struct page *prealloc_page = NULL; - swp_entry_t *entry; swp_entry_t swap; int error; - int ret; - if (idx >= SHMEM_MAX_INDEX) + if (idx > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT)) return -EFBIG; repeat: page = find_lock_page(mapping, idx); @@ -1272,37 +694,22 @@ repeat: spin_lock(&info->lock); shmem_recalc_inode(inode); - entry = shmem_swp_alloc(info, idx, sgp, gfp); - if (IS_ERR(entry)) { - spin_unlock(&info->lock); - error = PTR_ERR(entry); - goto out; - } - swap = *entry; - + swap = shmem_get_swap(info, idx); if (swap.val) { /* Look it up and read it in.. */ page = lookup_swap_cache(swap); if (!page) { - shmem_swp_unmap(entry); spin_unlock(&info->lock); /* here we actually do the io */ if (fault_type) *fault_type |= VM_FAULT_MAJOR; page = shmem_swapin(swap, gfp, info, idx); if (!page) { - spin_lock(&info->lock); - entry = shmem_swp_alloc(info, idx, sgp, gfp); - if (IS_ERR(entry)) - error = PTR_ERR(entry); - else { - if (entry->val == swap.val) - error = -ENOMEM; - shmem_swp_unmap(entry); - } - spin_unlock(&info->lock); - if (error) + swp_entry_t nswap = shmem_get_swap(info, idx); + if (nswap.val == swap.val) { + error = -ENOMEM; goto out; + } goto repeat; } wait_on_page_locked(page); @@ -1312,14 +719,12 @@ repeat: /* We have to do this with page locked to prevent races */ if (!trylock_page(page)) { - shmem_swp_unmap(entry); spin_unlock(&info->lock); wait_on_page_locked(page); page_cache_release(page); goto repeat; } if (PageWriteback(page)) { - shmem_swp_unmap(entry); spin_unlock(&info->lock); wait_on_page_writeback(page); unlock_page(page); @@ -1327,7 +732,6 @@ repeat: goto repeat; } if (!PageUptodate(page)) { - shmem_swp_unmap(entry); spin_unlock(&info->lock); unlock_page(page); page_cache_release(page); @@ -1338,7 +742,6 @@ repeat: error = add_to_page_cache_locked(page, mapping, idx, GFP_NOWAIT); if (error) { - shmem_swp_unmap(entry); spin_unlock(&info->lock); if (error == -ENOMEM) { /* @@ -1358,16 +761,14 @@ repeat: goto repeat; } - info->flags |= SHMEM_PAGEIN; - shmem_swp_set(info, entry, 0); - shmem_swp_unmap(entry); delete_from_swap_cache(page); + shmem_put_swap(info, idx, (swp_entry_t){0}); + info->swapped--; spin_unlock(&info->lock); set_page_dirty(page); swap_free(swap); } else if (sgp == SGP_READ) { - shmem_swp_unmap(entry); page = find_get_page(mapping, idx); if (page && !trylock_page(page)) { spin_unlock(&info->lock); @@ -1378,7 +779,6 @@ repeat: spin_unlock(&info->lock); } else if (prealloc_page) { - shmem_swp_unmap(entry); sbinfo = SHMEM_SB(inode->i_sb); if (sbinfo->max_blocks) { if (percpu_counter_compare(&sbinfo->used_blocks, @@ -1393,34 +793,24 @@ repeat: page = prealloc_page; prealloc_page = NULL; - entry = shmem_swp_alloc(info, idx, sgp, gfp); - if (IS_ERR(entry)) - error = PTR_ERR(entry); - else { - swap = *entry; - shmem_swp_unmap(entry); - } - ret = error || swap.val; - if (ret) + swap = shmem_get_swap(info, idx); + if (swap.val) mem_cgroup_uncharge_cache_page(page); else - ret = add_to_page_cache_lru(page, mapping, + error = add_to_page_cache_lru(page, mapping, idx, GFP_NOWAIT); /* * At add_to_page_cache_lru() failure, * uncharge will be done automatically. */ - if (ret) { + if (swap.val || error) { shmem_unacct_blocks(info->flags, 1); shmem_free_blocks(inode, 1); spin_unlock(&info->lock); page_cache_release(page); - if (error) - goto out; goto repeat; } - info->flags |= SHMEM_PAGEIN; info->alloced++; spin_unlock(&info->lock); clear_highpage(page); @@ -2627,7 +2017,7 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent) goto failed; sbinfo->free_inodes = sbinfo->max_inodes; - sb->s_maxbytes = SHMEM_MAX_BYTES; + sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = PAGE_CACHE_SIZE; sb->s_blocksize_bits = PAGE_CACHE_SHIFT; sb->s_magic = TMPFS_MAGIC; @@ -2863,7 +2253,7 @@ out4: void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, struct page **pagep, swp_entry_t *ent) { - swp_entry_t entry = { .val = 0 }, *ptr; + swp_entry_t entry = { .val = 0 }; struct page *page = NULL; struct shmem_inode_info *info = SHMEM_I(inode); @@ -2871,16 +2261,13 @@ void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, goto out; spin_lock(&info->lock); - ptr = shmem_swp_entry(info, pgoff, NULL); #ifdef CONFIG_SWAP - if (ptr && ptr->val) { - entry.val = ptr->val; + entry = shmem_get_swap(info, pgoff); + if (entry.val) page = find_get_page(&swapper_space, entry.val); - } else + else #endif page = find_get_page(inode->i_mapping, pgoff); - if (ptr) - shmem_swp_unmap(ptr); spin_unlock(&info->lock); out: *pagep = page; @@ -2963,7 +2350,6 @@ out: #define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev) #define shmem_acct_size(flags, size) 0 #define shmem_unacct_size(flags, size) do {} while (0) -#define SHMEM_MAX_BYTES MAX_LFS_FILESIZE #endif /* CONFIG_SHMEM */ @@ -2987,7 +2373,7 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags if (IS_ERR(shm_mnt)) return (void *)shm_mnt; - if (size < 0 || size > SHMEM_MAX_BYTES) + if (size < 0 || size > MAX_LFS_FILESIZE) return ERR_PTR(-EINVAL); if (shmem_acct_size(flags, size)) -- cgit v1.2.3 From 41ffe5d5ceef7f7ff2ff18e320d88ca6d629efaf Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:21 -0700 Subject: tmpfs: miscellaneous trivial cleanups While it's at its least, make a number of boring nitpicky cleanups to shmem.c, mostly for consistency of variable naming. Things like "swap" instead of "entry", "pgoff_t index" instead of "unsigned long idx". And since everything else here is prefixed "shmem_", better change init_tmpfs() to shmem_init(). Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 2 +- init/main.c | 2 +- mm/shmem.c | 216 +++++++++++++++++++++++------------------------ 3 files changed, 109 insertions(+), 111 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 80b695213fdb..3f05795dcf7b 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -47,7 +47,7 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) /* * Functions in mm/shmem.c called directly from elsewhere: */ -extern int init_tmpfs(void); +extern int shmem_init(void); extern int shmem_fill_super(struct super_block *sb, void *data, int silent); extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); diff --git a/init/main.c b/init/main.c index d7211faed2ad..1952d37e4ecb 100644 --- a/init/main.c +++ b/init/main.c @@ -715,7 +715,7 @@ static void __init do_basic_setup(void) { cpuset_init_smp(); usermodehelper_init(); - init_tmpfs(); + shmem_init(); driver_init(); init_irq_proc(); do_ctors(); diff --git a/mm/shmem.c b/mm/shmem.c index 5574b00ca771..24e95ac16053 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -28,7 +28,6 @@ #include #include #include -#include #include static struct vfsmount *shm_mnt; @@ -51,6 +50,7 @@ static struct vfsmount *shm_mnt; #include #include #include +#include #include #include #include @@ -63,7 +63,6 @@ static struct vfsmount *shm_mnt; #include #include -#include #include #define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) @@ -201,7 +200,7 @@ static void shmem_free_inode(struct super_block *sb) } /** - * shmem_recalc_inode - recalculate the size of an inode + * shmem_recalc_inode - recalculate the block usage of an inode * @inode: inode to recalc * * We have to calculate the free blocks since the mm can drop @@ -356,19 +355,20 @@ static void shmem_evict_inode(struct inode *inode) end_writeback(inode); } -static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page) +static int shmem_unuse_inode(struct shmem_inode_info *info, + swp_entry_t swap, struct page *page) { struct address_space *mapping = info->vfs_inode.i_mapping; - unsigned long idx; + pgoff_t index; int error; - for (idx = 0; idx < SHMEM_NR_DIRECT; idx++) - if (shmem_get_swap(info, idx).val == entry.val) + for (index = 0; index < SHMEM_NR_DIRECT; index++) + if (shmem_get_swap(info, index).val == swap.val) goto found; return 0; found: spin_lock(&info->lock); - if (shmem_get_swap(info, idx).val != entry.val) { + if (shmem_get_swap(info, index).val != swap.val) { spin_unlock(&info->lock); return 0; } @@ -387,15 +387,15 @@ found: * but also to hold up shmem_evict_inode(): so inode cannot be freed * beneath us (pagelock doesn't help until the page is in pagecache). */ - error = add_to_page_cache_locked(page, mapping, idx, GFP_NOWAIT); + error = add_to_page_cache_locked(page, mapping, index, GFP_NOWAIT); /* which does mem_cgroup_uncharge_cache_page on error */ if (error != -ENOMEM) { delete_from_swap_cache(page); set_page_dirty(page); - shmem_put_swap(info, idx, (swp_entry_t){0}); + shmem_put_swap(info, index, (swp_entry_t){0}); info->swapped--; - swap_free(entry); + swap_free(swap); error = 1; /* not an error, but entry was found */ } spin_unlock(&info->lock); @@ -405,9 +405,9 @@ found: /* * shmem_unuse() search for an eventually swapped out shmem page. */ -int shmem_unuse(swp_entry_t entry, struct page *page) +int shmem_unuse(swp_entry_t swap, struct page *page) { - struct list_head *p, *next; + struct list_head *this, *next; struct shmem_inode_info *info; int found = 0; int error; @@ -432,8 +432,8 @@ int shmem_unuse(swp_entry_t entry, struct page *page) radix_tree_preload_end(); mutex_lock(&shmem_swaplist_mutex); - list_for_each_safe(p, next, &shmem_swaplist) { - info = list_entry(p, struct shmem_inode_info, swaplist); + list_for_each_safe(this, next, &shmem_swaplist) { + info = list_entry(this, struct shmem_inode_info, swaplist); if (!info->swapped) { spin_lock(&info->lock); if (!info->swapped) @@ -441,7 +441,7 @@ int shmem_unuse(swp_entry_t entry, struct page *page) spin_unlock(&info->lock); } if (info->swapped) - found = shmem_unuse_inode(info, entry, page); + found = shmem_unuse_inode(info, swap, page); cond_resched(); if (found) break; @@ -467,7 +467,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) struct shmem_inode_info *info; swp_entry_t swap, oswap; struct address_space *mapping; - unsigned long index; + pgoff_t index; struct inode *inode; BUG_ON(!PageLocked(page)); @@ -577,35 +577,33 @@ static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) } #endif /* CONFIG_TMPFS */ -static struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp, - struct shmem_inode_info *info, unsigned long idx) +static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) { struct mempolicy mpol, *spol; struct vm_area_struct pvma; - struct page *page; spol = mpol_cond_copy(&mpol, - mpol_shared_policy_lookup(&info->policy, idx)); + mpol_shared_policy_lookup(&info->policy, index)); /* Create a pseudo vma that just contains the policy */ pvma.vm_start = 0; - pvma.vm_pgoff = idx; + pvma.vm_pgoff = index; pvma.vm_ops = NULL; pvma.vm_policy = spol; - page = swapin_readahead(entry, gfp, &pvma, 0); - return page; + return swapin_readahead(swap, gfp, &pvma, 0); } static struct page *shmem_alloc_page(gfp_t gfp, - struct shmem_inode_info *info, unsigned long idx) + struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; /* Create a pseudo vma that just contains the policy */ pvma.vm_start = 0; - pvma.vm_pgoff = idx; + pvma.vm_pgoff = index; pvma.vm_ops = NULL; - pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx); + pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index); /* * alloc_page_vma() will drop the shared policy reference @@ -614,19 +612,19 @@ static struct page *shmem_alloc_page(gfp_t gfp, } #else /* !CONFIG_NUMA */ #ifdef CONFIG_TMPFS -static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *p) +static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { } #endif /* CONFIG_TMPFS */ -static inline struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp, - struct shmem_inode_info *info, unsigned long idx) +static inline struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) { - return swapin_readahead(entry, gfp, NULL, 0); + return swapin_readahead(swap, gfp, NULL, 0); } static inline struct page *shmem_alloc_page(gfp_t gfp, - struct shmem_inode_info *info, unsigned long idx) + struct shmem_inode_info *info, pgoff_t index) { return alloc_page(gfp); } @@ -646,7 +644,7 @@ static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache */ -static int shmem_getpage_gfp(struct inode *inode, pgoff_t idx, +static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type) { struct address_space *mapping = inode->i_mapping; @@ -657,10 +655,10 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t idx, swp_entry_t swap; int error; - if (idx > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT)) + if (index > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT)) return -EFBIG; repeat: - page = find_lock_page(mapping, idx); + page = find_lock_page(mapping, index); if (page) { /* * Once we can get the page lock, it must be uptodate: @@ -681,7 +679,7 @@ repeat: radix_tree_preload_end(); if (sgp != SGP_READ && !prealloc_page) { - prealloc_page = shmem_alloc_page(gfp, info, idx); + prealloc_page = shmem_alloc_page(gfp, info, index); if (prealloc_page) { SetPageSwapBacked(prealloc_page); if (mem_cgroup_cache_charge(prealloc_page, @@ -694,7 +692,7 @@ repeat: spin_lock(&info->lock); shmem_recalc_inode(inode); - swap = shmem_get_swap(info, idx); + swap = shmem_get_swap(info, index); if (swap.val) { /* Look it up and read it in.. */ page = lookup_swap_cache(swap); @@ -703,9 +701,9 @@ repeat: /* here we actually do the io */ if (fault_type) *fault_type |= VM_FAULT_MAJOR; - page = shmem_swapin(swap, gfp, info, idx); + page = shmem_swapin(swap, gfp, info, index); if (!page) { - swp_entry_t nswap = shmem_get_swap(info, idx); + swp_entry_t nswap = shmem_get_swap(info, index); if (nswap.val == swap.val) { error = -ENOMEM; goto out; @@ -740,7 +738,7 @@ repeat: } error = add_to_page_cache_locked(page, mapping, - idx, GFP_NOWAIT); + index, GFP_NOWAIT); if (error) { spin_unlock(&info->lock); if (error == -ENOMEM) { @@ -762,14 +760,14 @@ repeat: } delete_from_swap_cache(page); - shmem_put_swap(info, idx, (swp_entry_t){0}); + shmem_put_swap(info, index, (swp_entry_t){0}); info->swapped--; spin_unlock(&info->lock); set_page_dirty(page); swap_free(swap); } else if (sgp == SGP_READ) { - page = find_get_page(mapping, idx); + page = find_get_page(mapping, index); if (page && !trylock_page(page)) { spin_unlock(&info->lock); wait_on_page_locked(page); @@ -793,12 +791,12 @@ repeat: page = prealloc_page; prealloc_page = NULL; - swap = shmem_get_swap(info, idx); + swap = shmem_get_swap(info, index); if (swap.val) mem_cgroup_uncharge_cache_page(page); else error = add_to_page_cache_lru(page, mapping, - idx, GFP_NOWAIT); + index, GFP_NOWAIT); /* * At add_to_page_cache_lru() failure, * uncharge will be done automatically. @@ -841,7 +839,7 @@ nospace: * but must also avoid reporting a spurious ENOSPC while working on a * full tmpfs. */ - page = find_get_page(mapping, idx); + page = find_get_page(mapping, index); spin_unlock(&info->lock); if (page) { page_cache_release(page); @@ -872,20 +870,20 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } #ifdef CONFIG_NUMA -static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new) +static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) { - struct inode *i = vma->vm_file->f_path.dentry->d_inode; - return mpol_set_shared_policy(&SHMEM_I(i)->policy, vma, new); + struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + return mpol_set_shared_policy(&SHMEM_I(inode)->policy, vma, mpol); } static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, unsigned long addr) { - struct inode *i = vma->vm_file->f_path.dentry->d_inode; - unsigned long idx; + struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + pgoff_t index; - idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - return mpol_shared_policy_lookup(&SHMEM_I(i)->policy, idx); + index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + return mpol_shared_policy_lookup(&SHMEM_I(inode)->policy, index); } #endif @@ -1016,7 +1014,8 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ { struct inode *inode = filp->f_path.dentry->d_inode; struct address_space *mapping = inode->i_mapping; - unsigned long index, offset; + pgoff_t index; + unsigned long offset; enum sgp_type sgp = SGP_READ; /* @@ -1032,7 +1031,8 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ for (;;) { struct page *page = NULL; - unsigned long end_index, nr, ret; + pgoff_t end_index; + unsigned long nr, ret; loff_t i_size = i_size_read(inode); end_index = i_size >> PAGE_CACHE_SHIFT; @@ -1270,8 +1270,9 @@ static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_namelen = NAME_MAX; if (sbinfo->max_blocks) { buf->f_blocks = sbinfo->max_blocks; - buf->f_bavail = buf->f_bfree = - sbinfo->max_blocks - percpu_counter_sum(&sbinfo->used_blocks); + buf->f_bavail = + buf->f_bfree = sbinfo->max_blocks - + percpu_counter_sum(&sbinfo->used_blocks); } if (sbinfo->max_inodes) { buf->f_files = sbinfo->max_inodes; @@ -1480,8 +1481,8 @@ static void *shmem_follow_link_inline(struct dentry *dentry, struct nameidata *n static void *shmem_follow_link(struct dentry *dentry, struct nameidata *nd) { struct page *page = NULL; - int res = shmem_getpage(dentry->d_inode, 0, &page, SGP_READ, NULL); - nd_set_link(nd, res ? ERR_PTR(res) : kmap(page)); + int error = shmem_getpage(dentry->d_inode, 0, &page, SGP_READ, NULL); + nd_set_link(nd, error ? ERR_PTR(error) : kmap(page)); if (page) unlock_page(page); return page; @@ -1592,7 +1593,6 @@ out: return err; } - static const struct xattr_handler *shmem_xattr_handlers[] = { #ifdef CONFIG_TMPFS_POSIX_ACL &generic_acl_access_handler, @@ -2052,14 +2052,14 @@ static struct kmem_cache *shmem_inode_cachep; static struct inode *shmem_alloc_inode(struct super_block *sb) { - struct shmem_inode_info *p; - p = (struct shmem_inode_info *)kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL); - if (!p) + struct shmem_inode_info *info; + info = kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL); + if (!info) return NULL; - return &p->vfs_inode; + return &info->vfs_inode; } -static void shmem_i_callback(struct rcu_head *head) +static void shmem_destroy_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); INIT_LIST_HEAD(&inode->i_dentry); @@ -2072,25 +2072,24 @@ static void shmem_destroy_inode(struct inode *inode) /* only struct inode is valid if it's an inline symlink */ mpol_free_shared_policy(&SHMEM_I(inode)->policy); } - call_rcu(&inode->i_rcu, shmem_i_callback); + call_rcu(&inode->i_rcu, shmem_destroy_callback); } -static void init_once(void *foo) +static void shmem_init_inode(void *foo) { - struct shmem_inode_info *p = (struct shmem_inode_info *) foo; - - inode_init_once(&p->vfs_inode); + struct shmem_inode_info *info = foo; + inode_init_once(&info->vfs_inode); } -static int init_inodecache(void) +static int shmem_init_inodecache(void) { shmem_inode_cachep = kmem_cache_create("shmem_inode_cache", sizeof(struct shmem_inode_info), - 0, SLAB_PANIC, init_once); + 0, SLAB_PANIC, shmem_init_inode); return 0; } -static void destroy_inodecache(void) +static void shmem_destroy_inodecache(void) { kmem_cache_destroy(shmem_inode_cachep); } @@ -2187,21 +2186,20 @@ static const struct vm_operations_struct shmem_vm_ops = { #endif }; - static struct dentry *shmem_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { return mount_nodev(fs_type, flags, data, shmem_fill_super); } -static struct file_system_type tmpfs_fs_type = { +static struct file_system_type shmem_fs_type = { .owner = THIS_MODULE, .name = "tmpfs", .mount = shmem_mount, .kill_sb = kill_litter_super, }; -int __init init_tmpfs(void) +int __init shmem_init(void) { int error; @@ -2209,18 +2207,18 @@ int __init init_tmpfs(void) if (error) goto out4; - error = init_inodecache(); + error = shmem_init_inodecache(); if (error) goto out3; - error = register_filesystem(&tmpfs_fs_type); + error = register_filesystem(&shmem_fs_type); if (error) { printk(KERN_ERR "Could not register tmpfs\n"); goto out2; } - shm_mnt = vfs_kern_mount(&tmpfs_fs_type, MS_NOUSER, - tmpfs_fs_type.name, NULL); + shm_mnt = vfs_kern_mount(&shmem_fs_type, MS_NOUSER, + shmem_fs_type.name, NULL); if (IS_ERR(shm_mnt)) { error = PTR_ERR(shm_mnt); printk(KERN_ERR "Could not kern_mount tmpfs\n"); @@ -2229,9 +2227,9 @@ int __init init_tmpfs(void) return 0; out1: - unregister_filesystem(&tmpfs_fs_type); + unregister_filesystem(&shmem_fs_type); out2: - destroy_inodecache(); + shmem_destroy_inodecache(); out3: bdi_destroy(&shmem_backing_dev_info); out4: @@ -2241,37 +2239,37 @@ out4: #ifdef CONFIG_CGROUP_MEM_RES_CTLR /** - * mem_cgroup_get_shmem_target - find a page or entry assigned to the shmem file + * mem_cgroup_get_shmem_target - find page or swap assigned to the shmem file * @inode: the inode to be searched - * @pgoff: the offset to be searched + * @index: the page offset to be searched * @pagep: the pointer for the found page to be stored - * @ent: the pointer for the found swap entry to be stored + * @swapp: the pointer for the found swap entry to be stored * * If a page is found, refcount of it is incremented. Callers should handle * these refcount. */ -void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, - struct page **pagep, swp_entry_t *ent) +void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t index, + struct page **pagep, swp_entry_t *swapp) { - swp_entry_t entry = { .val = 0 }; - struct page *page = NULL; struct shmem_inode_info *info = SHMEM_I(inode); + struct page *page = NULL; + swp_entry_t swap = {0}; - if ((pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode)) + if ((index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) goto out; spin_lock(&info->lock); #ifdef CONFIG_SWAP - entry = shmem_get_swap(info, pgoff); - if (entry.val) - page = find_get_page(&swapper_space, entry.val); + swap = shmem_get_swap(info, index); + if (swap.val) + page = find_get_page(&swapper_space, swap.val); else #endif - page = find_get_page(inode->i_mapping, pgoff); + page = find_get_page(inode->i_mapping, index); spin_unlock(&info->lock); out: *pagep = page; - *ent = entry; + *swapp = swap; } #endif @@ -2288,23 +2286,23 @@ out: #include -static struct file_system_type tmpfs_fs_type = { +static struct file_system_type shmem_fs_type = { .name = "tmpfs", .mount = ramfs_mount, .kill_sb = kill_litter_super, }; -int __init init_tmpfs(void) +int __init shmem_init(void) { - BUG_ON(register_filesystem(&tmpfs_fs_type) != 0); + BUG_ON(register_filesystem(&shmem_fs_type) != 0); - shm_mnt = kern_mount(&tmpfs_fs_type); + shm_mnt = kern_mount(&shmem_fs_type); BUG_ON(IS_ERR(shm_mnt)); return 0; } -int shmem_unuse(swp_entry_t entry, struct page *page) +int shmem_unuse(swp_entry_t swap, struct page *page) { return 0; } @@ -2314,34 +2312,34 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) return 0; } -void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end) +void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { - truncate_inode_pages_range(inode->i_mapping, start, end); + truncate_inode_pages_range(inode->i_mapping, lstart, lend); } EXPORT_SYMBOL_GPL(shmem_truncate_range); #ifdef CONFIG_CGROUP_MEM_RES_CTLR /** - * mem_cgroup_get_shmem_target - find a page or entry assigned to the shmem file + * mem_cgroup_get_shmem_target - find page or swap assigned to the shmem file * @inode: the inode to be searched - * @pgoff: the offset to be searched + * @index: the page offset to be searched * @pagep: the pointer for the found page to be stored - * @ent: the pointer for the found swap entry to be stored + * @swapp: the pointer for the found swap entry to be stored * * If a page is found, refcount of it is incremented. Callers should handle * these refcount. */ -void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, - struct page **pagep, swp_entry_t *ent) +void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t index, + struct page **pagep, swp_entry_t *swapp) { struct page *page = NULL; - if ((pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode)) + if ((index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) goto out; - page = find_get_page(inode->i_mapping, pgoff); + page = find_get_page(inode->i_mapping, index); out: *pagep = page; - *ent = (swp_entry_t){ .val = 0 }; + *swapp = (swp_entry_t){0}; } #endif -- cgit v1.2.3 From aa3b189551ad8e5cc1d9c663735c131650238278 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:24 -0700 Subject: tmpfs: convert mem_cgroup shmem to radix-swap Remove mem_cgroup_shmem_charge_fallback(): it was only required when we had to move swappage to filecache with GFP_NOWAIT. Remove the GFP_NOWAIT special case from mem_cgroup_cache_charge(), by moving its call out from shmem_add_to_page_cache() to two of thats three callers. But leave it doing mem_cgroup_uncharge_cache_page() on error: although asymmetrical, it's easier for all 3 callers to handle. These two changes would also be appropriate if anyone were to start using shmem_read_mapping_page_gfp() with GFP_NOWAIT. Remove mem_cgroup_get_shmem_target(): mc_handle_file_pte() can test radix_tree_exceptional_entry() to get what it needs for itself. Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 8 ----- include/linux/shmem_fs.h | 2 -- mm/memcontrol.c | 66 +++++------------------------------- mm/shmem.c | 83 ++++++---------------------------------------- 4 files changed, 20 insertions(+), 139 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b96600786913..3b535db00a94 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -86,8 +86,6 @@ extern void mem_cgroup_uncharge_end(void); extern void mem_cgroup_uncharge_page(struct page *page); extern void mem_cgroup_uncharge_cache_page(struct page *page); -extern int mem_cgroup_shmem_charge_fallback(struct page *page, - struct mm_struct *mm, gfp_t gfp_mask); extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask); int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem); @@ -225,12 +223,6 @@ static inline void mem_cgroup_uncharge_cache_page(struct page *page) { } -static inline int mem_cgroup_shmem_charge_fallback(struct page *page, - struct mm_struct *mm, gfp_t gfp_mask) -{ - return 0; -} - static inline void mem_cgroup_add_lru_list(struct page *page, int lru) { } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 3f05795dcf7b..0c8e952df594 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -57,8 +57,6 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); extern int shmem_unuse(swp_entry_t entry, struct page *page); -extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, - struct page **pagep, swp_entry_t *ent); static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5f84d2351ddb..f4ec4e7ca4cd 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -35,7 +35,6 @@ #include #include #include -#include #include #include #include @@ -2873,30 +2872,6 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, return 0; if (PageCompound(page)) return 0; - /* - * Corner case handling. This is called from add_to_page_cache() - * in usual. But some FS (shmem) precharges this page before calling it - * and call add_to_page_cache() with GFP_NOWAIT. - * - * For GFP_NOWAIT case, the page may be pre-charged before calling - * add_to_page_cache(). (See shmem.c) check it here and avoid to call - * charge twice. (It works but has to pay a bit larger cost.) - * And when the page is SwapCache, it should take swap information - * into account. This is under lock_page() now. - */ - if (!(gfp_mask & __GFP_WAIT)) { - struct page_cgroup *pc; - - pc = lookup_page_cgroup(page); - if (!pc) - return 0; - lock_page_cgroup(pc); - if (PageCgroupUsed(pc)) { - unlock_page_cgroup(pc); - return 0; - } - unlock_page_cgroup(pc); - } if (unlikely(!mm)) mm = &init_mm; @@ -3486,31 +3461,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem, cgroup_release_and_wakeup_rmdir(&mem->css); } -/* - * A call to try to shrink memory usage on charge failure at shmem's swapin. - * Calling hierarchical_reclaim is not enough because we should update - * last_oom_jiffies to prevent pagefault_out_of_memory from invoking global OOM. - * Moreover considering hierarchy, we should reclaim from the mem_over_limit, - * not from the memcg which this page would be charged to. - * try_charge_swapin does all of these works properly. - */ -int mem_cgroup_shmem_charge_fallback(struct page *page, - struct mm_struct *mm, - gfp_t gfp_mask) -{ - struct mem_cgroup *mem; - int ret; - - if (mem_cgroup_disabled()) - return 0; - - ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem); - if (!ret) - mem_cgroup_cancel_charge_swapin(mem); /* it does !mem check */ - - return ret; -} - #ifdef CONFIG_DEBUG_VM static struct page_cgroup *lookup_page_cgroup_used(struct page *page) { @@ -5330,15 +5280,17 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, pgoff = pte_to_pgoff(ptent); /* page is moved even if it's not RSS of this task(page-faulted). */ - if (!mapping_cap_swap_backed(mapping)) { /* normal file */ - page = find_get_page(mapping, pgoff); - } else { /* shmem/tmpfs file. we should take account of swap too. */ - swp_entry_t ent; - mem_cgroup_get_shmem_target(inode, pgoff, &page, &ent); + page = find_get_page(mapping, pgoff); + +#ifdef CONFIG_SWAP + /* shmem/tmpfs may report page out on swap: account for that too. */ + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swap = radix_to_swp_entry(page); if (do_swap_account) - entry->val = ent.val; + *entry = swap; + page = find_get_page(&swapper_space, swap.val); } - +#endif return page; } diff --git a/mm/shmem.c b/mm/shmem.c index 92f01d7cc150..13ef2d7e912d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -262,15 +262,11 @@ static int shmem_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp, void *expected) { - int error; + int error = 0; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(!PageSwapBacked(page)); - error = mem_cgroup_cache_charge(page, current->mm, - gfp & GFP_RECLAIM_MASK); - if (error) - goto out; if (!expected) error = radix_tree_preload(gfp & GFP_RECLAIM_MASK); if (!error) { @@ -300,7 +296,6 @@ static int shmem_add_to_page_cache(struct page *page, } if (error) mem_cgroup_uncharge_cache_page(page); -out: return error; } @@ -660,7 +655,6 @@ int shmem_unuse(swp_entry_t swap, struct page *page) * Charge page using GFP_KERNEL while we can wait, before taking * the shmem_swaplist_mutex which might hold up shmem_writepage(). * Charged back to the user (not to caller) when swap account is used. - * shmem_add_to_page_cache() will be called with GFP_NOWAIT. */ error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); if (error) @@ -954,8 +948,11 @@ repeat: goto failed; } - error = shmem_add_to_page_cache(page, mapping, index, - gfp, swp_to_radix_entry(swap)); + error = mem_cgroup_cache_charge(page, current->mm, + gfp & GFP_RECLAIM_MASK); + if (!error) + error = shmem_add_to_page_cache(page, mapping, index, + gfp, swp_to_radix_entry(swap)); if (error) goto failed; @@ -990,8 +987,11 @@ repeat: SetPageSwapBacked(page); __set_page_locked(page); - error = shmem_add_to_page_cache(page, mapping, index, - gfp, NULL); + error = mem_cgroup_cache_charge(page, current->mm, + gfp & GFP_RECLAIM_MASK); + if (!error) + error = shmem_add_to_page_cache(page, mapping, index, + gfp, NULL); if (error) goto decused; lru_cache_add_anon(page); @@ -2442,42 +2442,6 @@ out4: return error; } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR -/** - * mem_cgroup_get_shmem_target - find page or swap assigned to the shmem file - * @inode: the inode to be searched - * @index: the page offset to be searched - * @pagep: the pointer for the found page to be stored - * @swapp: the pointer for the found swap entry to be stored - * - * If a page is found, refcount of it is incremented. Callers should handle - * these refcount. - */ -void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t index, - struct page **pagep, swp_entry_t *swapp) -{ - struct shmem_inode_info *info = SHMEM_I(inode); - struct page *page = NULL; - swp_entry_t swap = {0}; - - if ((index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) - goto out; - - spin_lock(&info->lock); -#ifdef CONFIG_SWAP - swap = shmem_get_swap(info, index); - if (swap.val) - page = find_get_page(&swapper_space, swap.val); - else -#endif - page = find_get_page(inode->i_mapping, index); - spin_unlock(&info->lock); -out: - *pagep = page; - *swapp = swap; -} -#endif - #else /* !CONFIG_SHMEM */ /* @@ -2523,31 +2487,6 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) } EXPORT_SYMBOL_GPL(shmem_truncate_range); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR -/** - * mem_cgroup_get_shmem_target - find page or swap assigned to the shmem file - * @inode: the inode to be searched - * @index: the page offset to be searched - * @pagep: the pointer for the found page to be stored - * @swapp: the pointer for the found swap entry to be stored - * - * If a page is found, refcount of it is incremented. Callers should handle - * these refcount. - */ -void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t index, - struct page **pagep, swp_entry_t *swapp) -{ - struct page *page = NULL; - - if ((index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) - goto out; - page = find_get_page(inode->i_mapping, index); -out: - *pagep = page; - *swapp = (swp_entry_t){0}; -} -#endif - #define shmem_vm_ops generic_file_vm_ops #define shmem_file_operations ramfs_file_operations #define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev) -- cgit v1.2.3 From 69f07ec938712b58755add82dd3d0b35f01317cc Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:26 -0700 Subject: tmpfs: use kmemdup for short symlinks But we've not yet removed the old swp_entry_t i_direct[16] from shmem_inode_info. That's because it was still being shared with the inline symlink. Remove it now (saving 64 or 128 bytes from shmem inode size), and use kmemdup() for short symlinks, say, those up to 128 bytes. I wonder why mpol_free_shared_policy() is done in shmem_destroy_inode() rather than shmem_evict_inode(), where we usually do such freeing? I guess it doesn't matter, and I'm not into NUMA mpol testing right now. Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Reviewed-by: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 11 +++-------- mm/shmem.c | 31 ++++++++++++++++++------------- 2 files changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 0c8e952df594..9291ac3cc627 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -8,20 +8,15 @@ /* inode in-kernel data */ -#define SHMEM_NR_DIRECT 16 - -#define SHMEM_SYMLINK_INLINE_LEN (SHMEM_NR_DIRECT * sizeof(swp_entry_t)) - struct shmem_inode_info { spinlock_t lock; unsigned long flags; unsigned long alloced; /* data pages alloced to file */ - unsigned long swapped; /* subtotal assigned to swap */ - struct shared_policy policy; /* NUMA memory alloc policy */ union { - swp_entry_t i_direct[SHMEM_NR_DIRECT]; /* first blocks */ - char inline_symlink[SHMEM_SYMLINK_INLINE_LEN]; + unsigned long swapped; /* subtotal assigned to swap */ + char *symlink; /* unswappable short symlink */ }; + struct shared_policy policy; /* NUMA memory alloc policy */ struct list_head swaplist; /* chain of maybes on swap */ struct list_head xattr_list; /* list of shmem_xattr */ struct inode vfs_inode; diff --git a/mm/shmem.c b/mm/shmem.c index 0f094a258526..3a5be0feb6af 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -73,6 +73,9 @@ static struct vfsmount *shm_mnt; /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 +/* Symlink up to this size is kmalloc'ed instead of using a swappable page */ +#define SHORT_SYMLINK_LEN 128 + struct shmem_xattr { struct list_head list; /* anchored by shmem_inode_info->xattr_list */ char *name; /* xattr name */ @@ -585,7 +588,8 @@ static void shmem_evict_inode(struct inode *inode) list_del_init(&info->swaplist); mutex_unlock(&shmem_swaplist_mutex); } - } + } else + kfree(info->symlink); list_for_each_entry_safe(xattr, nxattr, &info->xattr_list, list) { kfree(xattr->name); @@ -1173,7 +1177,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; -static const struct inode_operations shmem_symlink_inline_operations; +static const struct inode_operations shmem_short_symlink_operations; static int shmem_write_begin(struct file *file, struct address_space *mapping, @@ -1638,10 +1642,13 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s info = SHMEM_I(inode); inode->i_size = len-1; - if (len <= SHMEM_SYMLINK_INLINE_LEN) { - /* do it inline */ - memcpy(info->inline_symlink, symname, len); - inode->i_op = &shmem_symlink_inline_operations; + if (len <= SHORT_SYMLINK_LEN) { + info->symlink = kmemdup(symname, len, GFP_KERNEL); + if (!info->symlink) { + iput(inode); + return -ENOMEM; + } + inode->i_op = &shmem_short_symlink_operations; } else { error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL); if (error) { @@ -1664,9 +1671,9 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s return 0; } -static void *shmem_follow_link_inline(struct dentry *dentry, struct nameidata *nd) +static void *shmem_follow_short_symlink(struct dentry *dentry, struct nameidata *nd) { - nd_set_link(nd, SHMEM_I(dentry->d_inode)->inline_symlink); + nd_set_link(nd, SHMEM_I(dentry->d_inode)->symlink); return NULL; } @@ -1914,9 +1921,9 @@ static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size) } #endif /* CONFIG_TMPFS_XATTR */ -static const struct inode_operations shmem_symlink_inline_operations = { +static const struct inode_operations shmem_short_symlink_operations = { .readlink = generic_readlink, - .follow_link = shmem_follow_link_inline, + .follow_link = shmem_follow_short_symlink, #ifdef CONFIG_TMPFS_XATTR .setxattr = shmem_setxattr, .getxattr = shmem_getxattr, @@ -2259,10 +2266,8 @@ static void shmem_destroy_callback(struct rcu_head *head) static void shmem_destroy_inode(struct inode *inode) { - if ((inode->i_mode & S_IFMT) == S_IFREG) { - /* only struct inode is valid if it's an inline symlink */ + if ((inode->i_mode & S_IFMT) == S_IFREG) mpol_free_shared_policy(&SHMEM_I(inode)->policy); - } call_rcu(&inode->i_rcu, shmem_destroy_callback); } -- cgit v1.2.3 From e504f3fdd63d486d45b18009e5a65f2e329acb0a Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 3 Aug 2011 16:21:27 -0700 Subject: tmpfs radix_tree: locate_item to speed up swapoff We have already acknowledged that swapoff of a tmpfs file is slower than it was before conversion to the generic radix_tree: a little slower there will be acceptable, if the hotter paths are faster. But it was a shock to find swapoff of a 500MB file 20 times slower on my laptop, taking 10 minutes; and at that rate it significantly slows down my testing. Now, most of that turned out to be overhead from PROVE_LOCKING and PROVE_RCU: without those it was only 4 times slower than before; and more realistic tests on other machines don't fare as badly. I've tried a number of things to improve it, including tagging the swap entries, then doing lookup by tag: I'd expected that to halve the time, but in practice it's erratic, and often counter-productive. The only change I've so far found to make a consistent improvement, is to short-circuit the way we go back and forth, gang lookup packing entries into the array supplied, then shmem scanning that array for the target entry. Scanning in place doubles the speed, so it's now only twice as slow as before (or three times slower when the PROVEs are on). So, add radix_tree_locate_item() as an expedient, once-off, single-caller hack to do the lookup directly in place. #ifdef it on CONFIG_SHMEM and CONFIG_SWAP, as much to document its limited applicability as save space in other configurations. And, sadly, #include sched.h for cond_resched(). Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 1 + lib/radix-tree.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++ mm/shmem.c | 38 +------------------ 3 files changed, 94 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index b7edf8251455..9d4539c52e53 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -252,6 +252,7 @@ unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root, unsigned long nr_to_tag, unsigned int fromtag, unsigned int totag); int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag); +unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item); static inline void radix_tree_preload_end(void) { diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 348eaefbed74..a2f9da59c197 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1203,6 +1203,98 @@ radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results, } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); +#if defined(CONFIG_SHMEM) && defined(CONFIG_SWAP) +#include /* for cond_resched() */ + +/* + * This linear search is at present only useful to shmem_unuse_inode(). + */ +static unsigned long __locate(struct radix_tree_node *slot, void *item, + unsigned long index, unsigned long *found_index) +{ + unsigned int shift, height; + unsigned long i; + + height = slot->height; + shift = (height-1) * RADIX_TREE_MAP_SHIFT; + + for ( ; height > 1; height--) { + i = (index >> shift) & RADIX_TREE_MAP_MASK; + for (;;) { + if (slot->slots[i] != NULL) + break; + index &= ~((1UL << shift) - 1); + index += 1UL << shift; + if (index == 0) + goto out; /* 32-bit wraparound */ + i++; + if (i == RADIX_TREE_MAP_SIZE) + goto out; + } + + shift -= RADIX_TREE_MAP_SHIFT; + slot = rcu_dereference_raw(slot->slots[i]); + if (slot == NULL) + goto out; + } + + /* Bottom level: check items */ + for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { + if (slot->slots[i] == item) { + *found_index = index + i; + index = 0; + goto out; + } + } + index += RADIX_TREE_MAP_SIZE; +out: + return index; +} + +/** + * radix_tree_locate_item - search through radix tree for item + * @root: radix tree root + * @item: item to be found + * + * Returns index where item was found, or -1 if not found. + * Caller must hold no lock (since this time-consuming function needs + * to be preemptible), and must check afterwards if item is still there. + */ +unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item) +{ + struct radix_tree_node *node; + unsigned long max_index; + unsigned long cur_index = 0; + unsigned long found_index = -1; + + do { + rcu_read_lock(); + node = rcu_dereference_raw(root->rnode); + if (!radix_tree_is_indirect_ptr(node)) { + rcu_read_unlock(); + if (node == item) + found_index = 0; + break; + } + + node = indirect_to_ptr(node); + max_index = radix_tree_maxindex(node->height); + if (cur_index > max_index) + break; + + cur_index = __locate(node, item, cur_index, &found_index); + rcu_read_unlock(); + cond_resched(); + } while (cur_index != 0 && cur_index <= max_index); + + return found_index; +} +#else +unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item) +{ + return -1; +} +#endif /* CONFIG_SHMEM && CONFIG_SWAP */ /** * radix_tree_shrink - shrink height of a radix tree to minimal diff --git a/mm/shmem.c b/mm/shmem.c index 3a5be0feb6af..1c702f6f1241 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -356,42 +356,6 @@ export: return ret; } -/* - * Lockless lookup of swap entry in radix tree, avoiding refcount on pages. - */ -static pgoff_t shmem_find_swap(struct address_space *mapping, void *radswap) -{ - void **slots[PAGEVEC_SIZE]; - pgoff_t indices[PAGEVEC_SIZE]; - unsigned int nr_found; - -restart: - nr_found = 1; - indices[0] = -1; - while (nr_found) { - pgoff_t index = indices[nr_found - 1] + 1; - unsigned int i; - - rcu_read_lock(); - nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, - slots, indices, index, PAGEVEC_SIZE); - for (i = 0; i < nr_found; i++) { - void *item = radix_tree_deref_slot(slots[i]); - if (radix_tree_deref_retry(item)) { - rcu_read_unlock(); - goto restart; - } - if (item == radswap) { - rcu_read_unlock(); - return indices[i]; - } - } - rcu_read_unlock(); - cond_resched(); - } - return -1; -} - /* * Remove swap entry from radix tree, free the swap and its page cache. */ @@ -612,7 +576,7 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, int error; radswap = swp_to_radix_entry(swap); - index = shmem_find_swap(mapping, radswap); + index = radix_tree_locate_item(&mapping->page_tree, radswap); if (index == -1) return 0; -- cgit v1.2.3 From fe55c1844a1c106e9d9d3dd27cbfcf8caeb9e77e Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 4 Aug 2011 10:27:32 +0100 Subject: Revert "dt: add of_alias_scan and of_alias_get_id" This reverts commit 750f463a749e28464151ad26938d11b07b1c43cb. of_alias_* still needs work to be generalized for 'promtree' dt platforms, and to no implicitly create entries for available ids. Signed-off-by: Grant Likely --- drivers/of/base.c | 130 ------------------------------------------------- drivers/of/fdt.c | 4 +- include/linux/of.h | 8 --- include/linux/of_fdt.h | 1 + 4 files changed, 2 insertions(+), 141 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/base.c b/drivers/of/base.c index fb28b5af733b..3ff22e32b602 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -17,39 +17,14 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#include #include #include #include #include #include -/** - * struct alias_prop - Alias property in 'aliases' node - * @link: List node to link the structure in aliases_lookup list - * @alias: Alias property name - * @np: Pointer to device_node that the alias stands for - * @id: Index value from end of alias name - * @stem: Alias string without the index - * - * The structure represents one alias property of 'aliases' node as - * an entry in aliases_lookup list. - */ -struct alias_prop { - struct list_head link; - const char *alias; - struct device_node *np; - int id; - char stem[0]; -}; - -static LIST_HEAD(aliases_lookup); - struct device_node *allnodes; struct device_node *of_chosen; -struct device_node *of_aliases; - -static DEFINE_MUTEX(of_aliases_mutex); /* use when traversing tree through the allnext, child, sibling, * or parent members of struct device_node. @@ -1013,108 +988,3 @@ out_unlock: } #endif /* defined(CONFIG_OF_DYNAMIC) */ -static void of_alias_add(struct alias_prop *ap, struct device_node *np, - int id, const char *stem, int stem_len) -{ - ap->id = id; - ap->np = np; - strncpy(ap->stem, stem, stem_len); - ap->stem[stem_len] = 0; - list_add_tail(&ap->link, &aliases_lookup); - pr_debug("adding DT alias:%s: stem=%s id=%i node=%s\n", - ap->alias, ap->stem, ap->id, np ? np->full_name : NULL); -} - -/** - * of_alias_scan() - Scan all properties of 'aliases' node - * - * The function scans all the properties of 'aliases' node and populate - * the global lookup table with the properties. It returns the - * number of alias_prop found, or error code in error case. - */ -__init void of_alias_scan(void) -{ - struct property *pp; - - if (!of_aliases) - return; - - for_each_property(pp, of_aliases->properties) { - const char *start = pp->name; - const char *end = start + strlen(start); - struct device_node *np; - struct alias_prop *ap; - int id, len; - - /* Skip those we do not want to proceed */ - if (!strcmp(pp->name, "name") || - !strcmp(pp->name, "phandle") || - !strcmp(pp->name, "linux,phandle")) - continue; - - np = of_find_node_by_path(pp->value); - if (!np) - continue; - - /* walk alias backwards to extract the id and 'stem' string */ - while (isdigit(*(end-1)) && end > start) - end--; - len = end - start; - id = strlen(end) ? simple_strtoul(end, NULL, 10) : -1; - - /* Allocate an alias_prop with enough space for the stem */ - ap = early_init_dt_alloc_memory_arch(sizeof(*ap) + len + 1, 4); - if (!ap) - continue; - ap->alias = start; - of_alias_add(ap, np, id, start, len); - } -} - -/** - * of_alias_get_id() - Get alias id for the given device_node - * @np: Pointer to the given device_node - * @stem: Alias stem of the given device_node - * - * The function travels the lookup table to get alias id for the given - * device_node and alias stem. It returns the alias id if find it. - * If not, dynamically creates one in the lookup table and returns it, - * or returns error code if fail to create. - */ -int of_alias_get_id(struct device_node *np, const char *stem) -{ - struct alias_prop *app; - int id = 0; - bool found = false; - - mutex_lock(&of_aliases_mutex); - list_for_each_entry(app, &aliases_lookup, link) { - if (strcmp(app->stem, stem) != 0) - continue; - - if (np == app->np) { - found = true; - id = app->id; - break; - } - - if (id <= app->id) - id = app->id + 1; - } - - /* If an id is not found, then allocate a new one */ - if (!found) { - app = kzalloc(sizeof(*app) + strlen(stem) + 1, 4); - if (!app) { - id = -ENODEV; - goto out; - } - of_alias_add(app, np, id, stem, strlen(stem)); - } - - out: - mutex_unlock(&of_aliases_mutex); - - return id; -} -EXPORT_SYMBOL_GPL(of_alias_get_id); diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 13d6d3a96b31..65200af29c52 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -707,12 +707,10 @@ void __init unflatten_device_tree(void) __unflatten_device_tree(initial_boot_params, &allnodes, early_init_dt_alloc_memory_arch); - /* Get pointer to "/chosen" and "/aliasas" nodes for use everywhere */ + /* Get pointer to OF "/chosen" node for use everywhere */ of_chosen = of_find_node_by_path("/chosen"); if (of_chosen == NULL) of_chosen = of_find_node_by_path("/chosen@0"); - of_aliases = of_find_node_by_path("/aliases"); - of_alias_scan(); } #endif /* CONFIG_OF_EARLY_FLATTREE */ diff --git a/include/linux/of.h b/include/linux/of.h index bc3dc6399547..0085bb01c041 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -68,7 +68,6 @@ struct device_node { /* Pointer for first entry in chain of all nodes. */ extern struct device_node *allnodes; extern struct device_node *of_chosen; -extern struct device_node *of_aliases; extern rwlock_t devtree_lock; static inline bool of_have_populated_dt(void) @@ -210,9 +209,6 @@ extern int of_device_is_available(const struct device_node *device); extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); -#define for_each_property(pp, properties) \ - for (pp = properties; pp != NULL; pp = pp->next) - extern int of_n_addr_cells(struct device_node *np); extern int of_n_size_cells(struct device_node *np); extern const struct of_device_id *of_match_node( @@ -225,10 +221,6 @@ extern int of_parse_phandles_with_args(struct device_node *np, const char *list_name, const char *cells_name, int index, struct device_node **out_node, const void **out_args); -extern void *early_init_dt_alloc_memory_arch(u64 size, u64 align); -extern void of_alias_scan(void); -extern int of_alias_get_id(struct device_node *np, const char *stem); - extern int of_machine_is_compatible(const char *compat); extern int prom_add_property(struct device_node* np, struct property* prop); diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index b74b74ffe0e7..c84d900fbbb3 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -97,6 +97,7 @@ extern void early_init_dt_check_for_initrd(unsigned long node); extern int early_init_dt_scan_memory(unsigned long node, const char *uname, int depth, void *data); extern void early_init_dt_add_memory_arch(u64 base, u64 size); +extern void * early_init_dt_alloc_memory_arch(u64 size, u64 align); extern u64 dt_mem_next_cell(int s, __be32 **cellp); /* -- cgit v1.2.3 From 655b16128482fd12808f77a6799eea5419c93709 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Sun, 29 May 2011 10:57:47 +0300 Subject: nfs_xdr: Move nfs4_string definition out of #ifdef CONFIG_NFS_V4 exofs file system wants to use pnfs_osd_xdr.h file instead of redefining pnfs-objects types in it's private "pnfs.h" headr. Before we do the switch we must make sure pnfs_osd_xdr.h is compilable also under NFS versions smaller than 4.1. Since now it is needed regardless of version, by the exofs code. nfs4_string is not the only nfs4 type out in the global scope. Ack-by: Trond Myklebust Signed-off-by: Boaz Harrosh --- include/linux/nfs_xdr.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 00848d86ffb2..d9f5e8d6ca84 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -759,6 +759,11 @@ struct nfs3_getaclres { struct posix_acl * acl_default; }; +struct nfs4_string { + unsigned int len; + char *data; +}; + #ifdef CONFIG_NFS_V4 typedef u64 clientid4; @@ -949,11 +954,6 @@ struct nfs4_server_caps_res { struct nfs4_sequence_res seq_res; }; -struct nfs4_string { - unsigned int len; - char *data; -}; - #define NFS4_PATHNAME_MAXCOMPONENTS 512 struct nfs4_pathname { unsigned int ncomponents; -- cgit v1.2.3 From 33009557bd9397c446a59e4cc91059a8e84c046b Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 24 May 2011 15:16:43 -0400 Subject: Add KEY_MICMUTE and enable it on Lenovo X220 I suspect that this works on T410. Signed-off-by: Andy Lutomirski Signed-off-by: Matthew Garrett --- drivers/platform/x86/thinkpad_acpi.c | 11 ++++++++++- include/linux/input.h | 2 ++ 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 26c5b117df22..7bd829f247eb 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -3185,9 +3185,18 @@ static int __init hotkey_init(struct ibm_init_struct *iibm) KEY_VENDOR, /* 0x17: Thinkpad/AccessIBM/Lenovo */ + /* (assignments unknown, please report if found) */ + KEY_UNKNOWN, KEY_UNKNOWN, + + /* + * The mic mute button only sends 0x1a. It does not + * automatically mute the mic or change the mute light. + */ + KEY_MICMUTE, /* 0x1a: Mic mute (since ?400 or so) */ + /* (assignments unknown, please report if found) */ KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, - KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, + KEY_UNKNOWN, }, }; diff --git a/include/linux/input.h b/include/linux/input.h index 068784e17972..a637e7814334 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -438,6 +438,8 @@ struct input_keymap_entry { #define KEY_WIMAX 246 #define KEY_RFKILL 247 /* Key that controls all radios */ +#define KEY_MICMUTE 248 /* Mute / unmute the microphone */ + /* Code 255 is reserved for special needs of AT keyboard driver */ #define BTN_MISC 0x100 -- cgit v1.2.3 From 1eb19a12bd2214cdcad5273d472b062a4ba97fa1 Mon Sep 17 00:00:00 2001 From: Mandeep Singh Baines Date: Fri, 5 Aug 2011 18:46:27 -0700 Subject: lib/sha1: use the git implementation of SHA-1 For ChromiumOS, we use SHA-1 to verify the integrity of the root filesystem. The speed of the kernel sha-1 implementation has a major impact on our boot performance. To improve boot performance, we investigated using the heavily optimized sha-1 implementation used in git. With the git sha-1 implementation, we see a 11.7% improvement in boot time. 10 reboots, remove slowest/fastest. Before: Mean: 6.58 seconds Stdev: 0.14 After (with git sha-1, this patch): Mean: 5.89 seconds Stdev: 0.07 The other cool thing about the git SHA-1 implementation is that it only needs 64 bytes of stack for the workspace while the original kernel implementation needed 320 bytes. Signed-off-by: Mandeep Singh Baines Cc: Ramsay Jones Cc: Nicolas Pitre Cc: Herbert Xu Cc: David S. Miller Cc: linux-crypto@vger.kernel.org Signed-off-by: Linus Torvalds --- include/linux/cryptohash.h | 2 +- lib/sha1.c | 212 +++++++++++++++++++++++++++++++++------------ 2 files changed, 159 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h index ec78a4bbe1d5..f9452185b019 100644 --- a/include/linux/cryptohash.h +++ b/include/linux/cryptohash.h @@ -3,7 +3,7 @@ #define SHA_DIGEST_WORDS 5 #define SHA_MESSAGE_BYTES (512 /*bits*/ / 8) -#define SHA_WORKSPACE_WORDS 80 +#define SHA_WORKSPACE_WORDS 16 void sha_init(__u32 *buf); void sha_transform(__u32 *digest, const char *data, __u32 *W); diff --git a/lib/sha1.c b/lib/sha1.c index 4c45fd50e913..f33271dd00cb 100644 --- a/lib/sha1.c +++ b/lib/sha1.c @@ -1,31 +1,72 @@ /* - * SHA transform algorithm, originally taken from code written by - * Peter Gutmann, and placed in the public domain. + * SHA1 routine optimized to do word accesses rather than byte accesses, + * and to avoid unnecessary copies into the context array. + * + * This was based on the git SHA1 implementation. */ #include #include -#include +#include +#include -/* The SHA f()-functions. */ +/* + * If you have 32 registers or more, the compiler can (and should) + * try to change the array[] accesses into registers. However, on + * machines with less than ~25 registers, that won't really work, + * and at least gcc will make an unholy mess of it. + * + * So to avoid that mess which just slows things down, we force + * the stores to memory to actually happen (we might be better off + * with a 'W(t)=(val);asm("":"+m" (W(t))' there instead, as + * suggested by Artur Skawina - that will also make gcc unable to + * try to do the silly "optimize away loads" part because it won't + * see what the value will be). + * + * Ben Herrenschmidt reports that on PPC, the C version comes close + * to the optimized asm with this (ie on PPC you don't want that + * 'volatile', since there are lots of registers). + * + * On ARM we get the best code generation by forcing a full memory barrier + * between each SHA_ROUND, otherwise gcc happily get wild with spilling and + * the stack frame size simply explode and performance goes down the drain. + */ -#define f1(x,y,z) (z ^ (x & (y ^ z))) /* x ? y : z */ -#define f2(x,y,z) (x ^ y ^ z) /* XOR */ -#define f3(x,y,z) ((x & y) + (z & (x ^ y))) /* majority */ +#ifdef CONFIG_X86 + #define setW(x, val) (*(volatile __u32 *)&W(x) = (val)) +#elif defined(CONFIG_ARM) + #define setW(x, val) do { W(x) = (val); __asm__("":::"memory"); } while (0) +#else + #define setW(x, val) (W(x) = (val)) +#endif -/* The SHA Mysterious Constants */ +/* This "rolls" over the 512-bit array */ +#define W(x) (array[(x)&15]) -#define K1 0x5A827999L /* Rounds 0-19: sqrt(2) * 2^30 */ -#define K2 0x6ED9EBA1L /* Rounds 20-39: sqrt(3) * 2^30 */ -#define K3 0x8F1BBCDCL /* Rounds 40-59: sqrt(5) * 2^30 */ -#define K4 0xCA62C1D6L /* Rounds 60-79: sqrt(10) * 2^30 */ +/* + * Where do we get the source from? The first 16 iterations get it from + * the input data, the next mix it from the 512-bit array. + */ +#define SHA_SRC(t) get_unaligned_be32((__u32 *)data + t) +#define SHA_MIX(t) rol32(W(t+13) ^ W(t+8) ^ W(t+2) ^ W(t), 1) + +#define SHA_ROUND(t, input, fn, constant, A, B, C, D, E) do { \ + __u32 TEMP = input(t); setW(t, TEMP); \ + E += TEMP + rol32(A,5) + (fn) + (constant); \ + B = ror32(B, 2); } while (0) + +#define T_0_15(t, A, B, C, D, E) SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E ) +#define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E ) +#define T_20_39(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0x6ed9eba1, A, B, C, D, E ) +#define T_40_59(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, ((B&C)+(D&(B^C))) , 0x8f1bbcdc, A, B, C, D, E ) +#define T_60_79(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0xca62c1d6, A, B, C, D, E ) /** * sha_transform - single block SHA1 transform * * @digest: 160 bit digest to update * @data: 512 bits of data to hash - * @W: 80 words of workspace (see note) + * @array: 16 words of workspace (see note) * * This function generates a SHA1 digest for a single 512-bit block. * Be warned, it does not handle padding and message digest, do not @@ -36,47 +77,111 @@ * to clear the workspace. This is left to the caller to avoid * unnecessary clears between chained hashing operations. */ -void sha_transform(__u32 *digest, const char *in, __u32 *W) +void sha_transform(__u32 *digest, const char *data, __u32 *array) { - __u32 a, b, c, d, e, t, i; - - for (i = 0; i < 16; i++) - W[i] = be32_to_cpu(((const __be32 *)in)[i]); - - for (i = 0; i < 64; i++) - W[i+16] = rol32(W[i+13] ^ W[i+8] ^ W[i+2] ^ W[i], 1); - - a = digest[0]; - b = digest[1]; - c = digest[2]; - d = digest[3]; - e = digest[4]; - - for (i = 0; i < 20; i++) { - t = f1(b, c, d) + K1 + rol32(a, 5) + e + W[i]; - e = d; d = c; c = rol32(b, 30); b = a; a = t; - } - - for (; i < 40; i ++) { - t = f2(b, c, d) + K2 + rol32(a, 5) + e + W[i]; - e = d; d = c; c = rol32(b, 30); b = a; a = t; - } - - for (; i < 60; i ++) { - t = f3(b, c, d) + K3 + rol32(a, 5) + e + W[i]; - e = d; d = c; c = rol32(b, 30); b = a; a = t; - } - - for (; i < 80; i ++) { - t = f2(b, c, d) + K4 + rol32(a, 5) + e + W[i]; - e = d; d = c; c = rol32(b, 30); b = a; a = t; - } - - digest[0] += a; - digest[1] += b; - digest[2] += c; - digest[3] += d; - digest[4] += e; + __u32 A, B, C, D, E; + + A = digest[0]; + B = digest[1]; + C = digest[2]; + D = digest[3]; + E = digest[4]; + + /* Round 1 - iterations 0-16 take their input from 'data' */ + T_0_15( 0, A, B, C, D, E); + T_0_15( 1, E, A, B, C, D); + T_0_15( 2, D, E, A, B, C); + T_0_15( 3, C, D, E, A, B); + T_0_15( 4, B, C, D, E, A); + T_0_15( 5, A, B, C, D, E); + T_0_15( 6, E, A, B, C, D); + T_0_15( 7, D, E, A, B, C); + T_0_15( 8, C, D, E, A, B); + T_0_15( 9, B, C, D, E, A); + T_0_15(10, A, B, C, D, E); + T_0_15(11, E, A, B, C, D); + T_0_15(12, D, E, A, B, C); + T_0_15(13, C, D, E, A, B); + T_0_15(14, B, C, D, E, A); + T_0_15(15, A, B, C, D, E); + + /* Round 1 - tail. Input from 512-bit mixing array */ + T_16_19(16, E, A, B, C, D); + T_16_19(17, D, E, A, B, C); + T_16_19(18, C, D, E, A, B); + T_16_19(19, B, C, D, E, A); + + /* Round 2 */ + T_20_39(20, A, B, C, D, E); + T_20_39(21, E, A, B, C, D); + T_20_39(22, D, E, A, B, C); + T_20_39(23, C, D, E, A, B); + T_20_39(24, B, C, D, E, A); + T_20_39(25, A, B, C, D, E); + T_20_39(26, E, A, B, C, D); + T_20_39(27, D, E, A, B, C); + T_20_39(28, C, D, E, A, B); + T_20_39(29, B, C, D, E, A); + T_20_39(30, A, B, C, D, E); + T_20_39(31, E, A, B, C, D); + T_20_39(32, D, E, A, B, C); + T_20_39(33, C, D, E, A, B); + T_20_39(34, B, C, D, E, A); + T_20_39(35, A, B, C, D, E); + T_20_39(36, E, A, B, C, D); + T_20_39(37, D, E, A, B, C); + T_20_39(38, C, D, E, A, B); + T_20_39(39, B, C, D, E, A); + + /* Round 3 */ + T_40_59(40, A, B, C, D, E); + T_40_59(41, E, A, B, C, D); + T_40_59(42, D, E, A, B, C); + T_40_59(43, C, D, E, A, B); + T_40_59(44, B, C, D, E, A); + T_40_59(45, A, B, C, D, E); + T_40_59(46, E, A, B, C, D); + T_40_59(47, D, E, A, B, C); + T_40_59(48, C, D, E, A, B); + T_40_59(49, B, C, D, E, A); + T_40_59(50, A, B, C, D, E); + T_40_59(51, E, A, B, C, D); + T_40_59(52, D, E, A, B, C); + T_40_59(53, C, D, E, A, B); + T_40_59(54, B, C, D, E, A); + T_40_59(55, A, B, C, D, E); + T_40_59(56, E, A, B, C, D); + T_40_59(57, D, E, A, B, C); + T_40_59(58, C, D, E, A, B); + T_40_59(59, B, C, D, E, A); + + /* Round 4 */ + T_60_79(60, A, B, C, D, E); + T_60_79(61, E, A, B, C, D); + T_60_79(62, D, E, A, B, C); + T_60_79(63, C, D, E, A, B); + T_60_79(64, B, C, D, E, A); + T_60_79(65, A, B, C, D, E); + T_60_79(66, E, A, B, C, D); + T_60_79(67, D, E, A, B, C); + T_60_79(68, C, D, E, A, B); + T_60_79(69, B, C, D, E, A); + T_60_79(70, A, B, C, D, E); + T_60_79(71, E, A, B, C, D); + T_60_79(72, D, E, A, B, C); + T_60_79(73, C, D, E, A, B); + T_60_79(74, B, C, D, E, A); + T_60_79(75, A, B, C, D, E); + T_60_79(76, E, A, B, C, D); + T_60_79(77, D, E, A, B, C); + T_60_79(78, C, D, E, A, B); + T_60_79(79, B, C, D, E, A); + + digest[0] += A; + digest[1] += B; + digest[2] += C; + digest[3] += D; + digest[4] += E; } EXPORT_SYMBOL(sha_transform); @@ -92,4 +197,3 @@ void sha_init(__u32 *buf) buf[3] = 0x10325476; buf[4] = 0xc3d2e1f0; } - -- cgit v1.2.3 From bc0b96b54a21246e377122d54569eef71cec535f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 3 Aug 2011 19:45:10 -0700 Subject: crypto: Move md5_transform to lib/md5.c We are going to use this for TCP/IP sequence number and fragment ID generation. Signed-off-by: David S. Miller --- crypto/md5.c | 92 +------------------------------------------- include/linux/cryptohash.h | 5 +++ lib/Makefile | 2 +- lib/md5.c | 95 ++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 102 insertions(+), 92 deletions(-) create mode 100644 lib/md5.c (limited to 'include/linux') diff --git a/crypto/md5.c b/crypto/md5.c index 30efc7dad891..7febeaab923b 100644 --- a/crypto/md5.c +++ b/crypto/md5.c @@ -21,99 +21,9 @@ #include #include #include +#include #include -#define F1(x, y, z) (z ^ (x & (y ^ z))) -#define F2(x, y, z) F1(z, x, y) -#define F3(x, y, z) (x ^ y ^ z) -#define F4(x, y, z) (y ^ (x | ~z)) - -#define MD5STEP(f, w, x, y, z, in, s) \ - (w += f(x, y, z) + in, w = (w<>(32-s)) + x) - -static void md5_transform(u32 *hash, u32 const *in) -{ - u32 a, b, c, d; - - a = hash[0]; - b = hash[1]; - c = hash[2]; - d = hash[3]; - - MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7); - MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12); - MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17); - MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22); - MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7); - MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12); - MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17); - MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22); - MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7); - MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12); - MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17); - MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22); - MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7); - MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12); - MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17); - MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22); - - MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5); - MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9); - MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14); - MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20); - MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5); - MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9); - MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14); - MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20); - MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5); - MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9); - MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14); - MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20); - MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5); - MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9); - MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14); - MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20); - - MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4); - MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11); - MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16); - MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23); - MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4); - MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11); - MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16); - MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23); - MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4); - MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11); - MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16); - MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23); - MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4); - MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11); - MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16); - MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23); - - MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6); - MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10); - MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15); - MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21); - MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6); - MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10); - MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15); - MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21); - MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6); - MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10); - MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15); - MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21); - MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6); - MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10); - MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15); - MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21); - - hash[0] += a; - hash[1] += b; - hash[2] += c; - hash[3] += d; -} - /* XXX: this stuff can be optimized */ static inline void le32_to_cpu_array(u32 *buf, unsigned int words) { diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h index ec78a4bbe1d5..d2984fbebbc0 100644 --- a/include/linux/cryptohash.h +++ b/include/linux/cryptohash.h @@ -8,6 +8,11 @@ void sha_init(__u32 *buf); void sha_transform(__u32 *digest, const char *data, __u32 *W); +#define MD5_DIGEST_WORDS 4 +#define MD5_MESSAGE_BYTES 64 + +void md5_transform(__u32 *hash, __u32 const *in); + __u32 half_md4_transform(__u32 buf[4], __u32 const in[8]); #endif diff --git a/lib/Makefile b/lib/Makefile index 6457af4a7caf..d5d175c8a6ca 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -10,7 +10,7 @@ endif lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o dump_stack.o timerqueue.o\ idr.o int_sqrt.o extable.o prio_tree.o \ - sha1.o irq_regs.o reciprocal_div.o argv_split.o \ + sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \ proportions.o prio_heap.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o find_next_bit.o diff --git a/lib/md5.c b/lib/md5.c new file mode 100644 index 000000000000..c777180e1f2f --- /dev/null +++ b/lib/md5.c @@ -0,0 +1,95 @@ +#include +#include +#include + +#define F1(x, y, z) (z ^ (x & (y ^ z))) +#define F2(x, y, z) F1(z, x, y) +#define F3(x, y, z) (x ^ y ^ z) +#define F4(x, y, z) (y ^ (x | ~z)) + +#define MD5STEP(f, w, x, y, z, in, s) \ + (w += f(x, y, z) + in, w = (w<>(32-s)) + x) + +void md5_transform(__u32 *hash, __u32 const *in) +{ + u32 a, b, c, d; + + a = hash[0]; + b = hash[1]; + c = hash[2]; + d = hash[3]; + + MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7); + MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12); + MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17); + MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22); + MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7); + MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12); + MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17); + MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22); + MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7); + MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12); + MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17); + MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22); + MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7); + MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12); + MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17); + MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22); + + MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5); + MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9); + MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14); + MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20); + MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5); + MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9); + MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14); + MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20); + MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5); + MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9); + MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14); + MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20); + MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5); + MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9); + MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14); + MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20); + + MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4); + MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11); + MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16); + MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23); + MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4); + MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11); + MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16); + MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23); + MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4); + MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11); + MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16); + MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23); + MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4); + MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11); + MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16); + MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23); + + MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6); + MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10); + MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15); + MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21); + MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6); + MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10); + MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15); + MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21); + MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6); + MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10); + MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15); + MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21); + MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6); + MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10); + MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15); + MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21); + + hash[0] += a; + hash[1] += b; + hash[2] += c; + hash[3] += d; +} +EXPORT_SYMBOL(md5_transform); -- cgit v1.2.3 From 6e5714eaf77d79ae1c8b47e3e040ff5411b717ec Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 3 Aug 2011 20:50:44 -0700 Subject: net: Compute protocol sequence numbers and fragment IDs using MD5. Computers have become a lot faster since we compromised on the partial MD4 hash which we use currently for performance reasons. MD5 is a much safer choice, and is inline with both RFC1948 and other ISS generators (OpenBSD, Solaris, etc.) Furthermore, only having 24-bits of the sequence number be truly unpredictable is a very serious limitation. So the periodic regeneration and 8-bit counter have been removed. We compute and use a full 32-bit sequence number. For ipv6, DCCP was found to use a 32-bit truncated initial sequence number (it needs 43-bits) and that is fixed here as well. Reported-by: Dan Kaminsky Tested-by: Willy Tarreau Signed-off-by: David S. Miller --- drivers/char/random.c | 349 +------------------------------ include/linux/random.h | 12 -- include/net/secure_seq.h | 20 ++ net/core/Makefile | 2 +- net/core/secure_seq.c | 184 ++++++++++++++++ net/dccp/ipv4.c | 1 + net/dccp/ipv6.c | 9 +- net/ipv4/inet_hashtables.c | 1 + net/ipv4/inetpeer.c | 1 + net/ipv4/netfilter/nf_nat_proto_common.c | 1 + net/ipv4/route.c | 1 + net/ipv4/tcp_ipv4.c | 1 + net/ipv6/inet6_hashtables.c | 1 + net/ipv6/tcp_ipv6.c | 1 + 14 files changed, 223 insertions(+), 361 deletions(-) create mode 100644 include/net/secure_seq.h create mode 100644 net/core/secure_seq.c (limited to 'include/linux') diff --git a/drivers/char/random.c b/drivers/char/random.c index 729281961f22..c35a785005b0 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1300,345 +1300,14 @@ ctl_table random_table[] = { }; #endif /* CONFIG_SYSCTL */ -/******************************************************************** - * - * Random functions for networking - * - ********************************************************************/ - -/* - * TCP initial sequence number picking. This uses the random number - * generator to pick an initial secret value. This value is hashed - * along with the TCP endpoint information to provide a unique - * starting point for each pair of TCP endpoints. This defeats - * attacks which rely on guessing the initial TCP sequence number. - * This algorithm was suggested by Steve Bellovin. - * - * Using a very strong hash was taking an appreciable amount of the total - * TCP connection establishment time, so this is a weaker hash, - * compensated for by changing the secret periodically. - */ - -/* F, G and H are basic MD4 functions: selection, majority, parity */ -#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z)))) -#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z))) -#define H(x, y, z) ((x) ^ (y) ^ (z)) - -/* - * The generic round function. The application is so specific that - * we don't bother protecting all the arguments with parens, as is generally - * good macro practice, in favor of extra legibility. - * Rotation is separate from addition to prevent recomputation - */ -#define ROUND(f, a, b, c, d, x, s) \ - (a += f(b, c, d) + x, a = (a << s) | (a >> (32 - s))) -#define K1 0 -#define K2 013240474631UL -#define K3 015666365641UL - -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) - -static __u32 twothirdsMD4Transform(__u32 const buf[4], __u32 const in[12]) -{ - __u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3]; - - /* Round 1 */ - ROUND(F, a, b, c, d, in[ 0] + K1, 3); - ROUND(F, d, a, b, c, in[ 1] + K1, 7); - ROUND(F, c, d, a, b, in[ 2] + K1, 11); - ROUND(F, b, c, d, a, in[ 3] + K1, 19); - ROUND(F, a, b, c, d, in[ 4] + K1, 3); - ROUND(F, d, a, b, c, in[ 5] + K1, 7); - ROUND(F, c, d, a, b, in[ 6] + K1, 11); - ROUND(F, b, c, d, a, in[ 7] + K1, 19); - ROUND(F, a, b, c, d, in[ 8] + K1, 3); - ROUND(F, d, a, b, c, in[ 9] + K1, 7); - ROUND(F, c, d, a, b, in[10] + K1, 11); - ROUND(F, b, c, d, a, in[11] + K1, 19); - - /* Round 2 */ - ROUND(G, a, b, c, d, in[ 1] + K2, 3); - ROUND(G, d, a, b, c, in[ 3] + K2, 5); - ROUND(G, c, d, a, b, in[ 5] + K2, 9); - ROUND(G, b, c, d, a, in[ 7] + K2, 13); - ROUND(G, a, b, c, d, in[ 9] + K2, 3); - ROUND(G, d, a, b, c, in[11] + K2, 5); - ROUND(G, c, d, a, b, in[ 0] + K2, 9); - ROUND(G, b, c, d, a, in[ 2] + K2, 13); - ROUND(G, a, b, c, d, in[ 4] + K2, 3); - ROUND(G, d, a, b, c, in[ 6] + K2, 5); - ROUND(G, c, d, a, b, in[ 8] + K2, 9); - ROUND(G, b, c, d, a, in[10] + K2, 13); - - /* Round 3 */ - ROUND(H, a, b, c, d, in[ 3] + K3, 3); - ROUND(H, d, a, b, c, in[ 7] + K3, 9); - ROUND(H, c, d, a, b, in[11] + K3, 11); - ROUND(H, b, c, d, a, in[ 2] + K3, 15); - ROUND(H, a, b, c, d, in[ 6] + K3, 3); - ROUND(H, d, a, b, c, in[10] + K3, 9); - ROUND(H, c, d, a, b, in[ 1] + K3, 11); - ROUND(H, b, c, d, a, in[ 5] + K3, 15); - ROUND(H, a, b, c, d, in[ 9] + K3, 3); - ROUND(H, d, a, b, c, in[ 0] + K3, 9); - ROUND(H, c, d, a, b, in[ 4] + K3, 11); - ROUND(H, b, c, d, a, in[ 8] + K3, 15); - - return buf[1] + b; /* "most hashed" word */ - /* Alternative: return sum of all words? */ -} -#endif - -#undef ROUND -#undef F -#undef G -#undef H -#undef K1 -#undef K2 -#undef K3 - -/* This should not be decreased so low that ISNs wrap too fast. */ -#define REKEY_INTERVAL (300 * HZ) -/* - * Bit layout of the tcp sequence numbers (before adding current time): - * bit 24-31: increased after every key exchange - * bit 0-23: hash(source,dest) - * - * The implementation is similar to the algorithm described - * in the Appendix of RFC 1185, except that - * - it uses a 1 MHz clock instead of a 250 kHz clock - * - it performs a rekey every 5 minutes, which is equivalent - * to a (source,dest) tulple dependent forward jump of the - * clock by 0..2^(HASH_BITS+1) - * - * Thus the average ISN wraparound time is 68 minutes instead of - * 4.55 hours. - * - * SMP cleanup and lock avoidance with poor man's RCU. - * Manfred Spraul - * - */ -#define COUNT_BITS 8 -#define COUNT_MASK ((1 << COUNT_BITS) - 1) -#define HASH_BITS 24 -#define HASH_MASK ((1 << HASH_BITS) - 1) +static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned; -static struct keydata { - __u32 count; /* already shifted to the final position */ - __u32 secret[12]; -} ____cacheline_aligned ip_keydata[2]; - -static unsigned int ip_cnt; - -static void rekey_seq_generator(struct work_struct *work); - -static DECLARE_DELAYED_WORK(rekey_work, rekey_seq_generator); - -/* - * Lock avoidance: - * The ISN generation runs lockless - it's just a hash over random data. - * State changes happen every 5 minutes when the random key is replaced. - * Synchronization is performed by having two copies of the hash function - * state and rekey_seq_generator always updates the inactive copy. - * The copy is then activated by updating ip_cnt. - * The implementation breaks down if someone blocks the thread - * that processes SYN requests for more than 5 minutes. Should never - * happen, and even if that happens only a not perfectly compliant - * ISN is generated, nothing fatal. - */ -static void rekey_seq_generator(struct work_struct *work) +static int __init random_int_secret_init(void) { - struct keydata *keyptr = &ip_keydata[1 ^ (ip_cnt & 1)]; - - get_random_bytes(keyptr->secret, sizeof(keyptr->secret)); - keyptr->count = (ip_cnt & COUNT_MASK) << HASH_BITS; - smp_wmb(); - ip_cnt++; - schedule_delayed_work(&rekey_work, - round_jiffies_relative(REKEY_INTERVAL)); -} - -static inline struct keydata *get_keyptr(void) -{ - struct keydata *keyptr = &ip_keydata[ip_cnt & 1]; - - smp_rmb(); - - return keyptr; -} - -static __init int seqgen_init(void) -{ - rekey_seq_generator(NULL); + get_random_bytes(random_int_secret, sizeof(random_int_secret)); return 0; } -late_initcall(seqgen_init); - -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -__u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr, - __be16 sport, __be16 dport) -{ - __u32 seq; - __u32 hash[12]; - struct keydata *keyptr = get_keyptr(); - - /* The procedure is the same as for IPv4, but addresses are longer. - * Thus we must use twothirdsMD4Transform. - */ - - memcpy(hash, saddr, 16); - hash[4] = ((__force u16)sport << 16) + (__force u16)dport; - memcpy(&hash[5], keyptr->secret, sizeof(__u32) * 7); - - seq = twothirdsMD4Transform((const __u32 *)daddr, hash) & HASH_MASK; - seq += keyptr->count; - - seq += ktime_to_ns(ktime_get_real()); - - return seq; -} -EXPORT_SYMBOL(secure_tcpv6_sequence_number); -#endif - -/* The code below is shamelessly stolen from secure_tcp_sequence_number(). - * All blames to Andrey V. Savochkin . - */ -__u32 secure_ip_id(__be32 daddr) -{ - struct keydata *keyptr; - __u32 hash[4]; - - keyptr = get_keyptr(); - - /* - * Pick a unique starting offset for each IP destination. - * The dest ip address is placed in the starting vector, - * which is then hashed with random data. - */ - hash[0] = (__force __u32)daddr; - hash[1] = keyptr->secret[9]; - hash[2] = keyptr->secret[10]; - hash[3] = keyptr->secret[11]; - - return half_md4_transform(hash, keyptr->secret); -} - -__u32 secure_ipv6_id(const __be32 daddr[4]) -{ - const struct keydata *keyptr; - __u32 hash[4]; - - keyptr = get_keyptr(); - - hash[0] = (__force __u32)daddr[0]; - hash[1] = (__force __u32)daddr[1]; - hash[2] = (__force __u32)daddr[2]; - hash[3] = (__force __u32)daddr[3]; - - return half_md4_transform(hash, keyptr->secret); -} - -#ifdef CONFIG_INET - -__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport) -{ - __u32 seq; - __u32 hash[4]; - struct keydata *keyptr = get_keyptr(); - - /* - * Pick a unique starting offset for each TCP connection endpoints - * (saddr, daddr, sport, dport). - * Note that the words are placed into the starting vector, which is - * then mixed with a partial MD4 over random data. - */ - hash[0] = (__force u32)saddr; - hash[1] = (__force u32)daddr; - hash[2] = ((__force u16)sport << 16) + (__force u16)dport; - hash[3] = keyptr->secret[11]; - - seq = half_md4_transform(hash, keyptr->secret) & HASH_MASK; - seq += keyptr->count; - /* - * As close as possible to RFC 793, which - * suggests using a 250 kHz clock. - * Further reading shows this assumes 2 Mb/s networks. - * For 10 Mb/s Ethernet, a 1 MHz clock is appropriate. - * For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but - * we also need to limit the resolution so that the u32 seq - * overlaps less than one time per MSL (2 minutes). - * Choosing a clock of 64 ns period is OK. (period of 274 s) - */ - seq += ktime_to_ns(ktime_get_real()) >> 6; - - return seq; -} - -/* Generate secure starting point for ephemeral IPV4 transport port search */ -u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) -{ - struct keydata *keyptr = get_keyptr(); - u32 hash[4]; - - /* - * Pick a unique starting offset for each ephemeral port search - * (saddr, daddr, dport) and 48bits of random data. - */ - hash[0] = (__force u32)saddr; - hash[1] = (__force u32)daddr; - hash[2] = (__force u32)dport ^ keyptr->secret[10]; - hash[3] = keyptr->secret[11]; - - return half_md4_transform(hash, keyptr->secret); -} -EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); - -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, - __be16 dport) -{ - struct keydata *keyptr = get_keyptr(); - u32 hash[12]; - - memcpy(hash, saddr, 16); - hash[4] = (__force u32)dport; - memcpy(&hash[5], keyptr->secret, sizeof(__u32) * 7); - - return twothirdsMD4Transform((const __u32 *)daddr, hash); -} -#endif - -#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE) -/* Similar to secure_tcp_sequence_number but generate a 48 bit value - * bit's 32-47 increase every key exchange - * 0-31 hash(source, dest) - */ -u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport) -{ - u64 seq; - __u32 hash[4]; - struct keydata *keyptr = get_keyptr(); - - hash[0] = (__force u32)saddr; - hash[1] = (__force u32)daddr; - hash[2] = ((__force u16)sport << 16) + (__force u16)dport; - hash[3] = keyptr->secret[11]; - - seq = half_md4_transform(hash, keyptr->secret); - seq |= ((u64)keyptr->count) << (32 - HASH_BITS); - - seq += ktime_to_ns(ktime_get_real()); - seq &= (1ull << 48) - 1; - - return seq; -} -EXPORT_SYMBOL(secure_dccp_sequence_number); -#endif - -#endif /* CONFIG_INET */ - +late_initcall(random_int_secret_init); /* * Get a random word for internal kernel use only. Similar to urandom but @@ -1646,17 +1315,15 @@ EXPORT_SYMBOL(secure_dccp_sequence_number); * value is not cryptographically secure but for several uses the cost of * depleting entropy is too high */ -DEFINE_PER_CPU(__u32 [4], get_random_int_hash); +DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash); unsigned int get_random_int(void) { - struct keydata *keyptr; __u32 *hash = get_cpu_var(get_random_int_hash); - int ret; + unsigned int ret; - keyptr = get_keyptr(); hash[0] += current->pid + jiffies + get_cycles(); - - ret = half_md4_transform(hash, keyptr->secret); + md5_transform(hash, random_int_secret); + ret = hash[0]; put_cpu_var(get_random_int_hash); return ret; diff --git a/include/linux/random.h b/include/linux/random.h index ce29a040c8dc..d13059f3ea32 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -57,18 +57,6 @@ extern void add_interrupt_randomness(int irq); extern void get_random_bytes(void *buf, int nbytes); void generate_random_uuid(unsigned char uuid_out[16]); -extern __u32 secure_ip_id(__be32 daddr); -extern __u32 secure_ipv6_id(const __be32 daddr[4]); -extern u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); -extern u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, - __be16 dport); -extern __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport); -extern __u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr, - __be16 sport, __be16 dport); -extern u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport); - #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; #endif diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h new file mode 100644 index 000000000000..d97f6892c019 --- /dev/null +++ b/include/net/secure_seq.h @@ -0,0 +1,20 @@ +#ifndef _NET_SECURE_SEQ +#define _NET_SECURE_SEQ + +#include + +extern __u32 secure_ip_id(__be32 daddr); +extern __u32 secure_ipv6_id(const __be32 daddr[4]); +extern u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); +extern u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, + __be16 dport); +extern __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport); +extern __u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr, + __be16 sport, __be16 dport); +extern u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport); +extern u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, + __be16 sport, __be16 dport); + +#endif /* _NET_SECURE_SEQ */ diff --git a/net/core/Makefile b/net/core/Makefile index 8a04dd22cf77..0d357b1c4e57 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -3,7 +3,7 @@ # obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ - gen_stats.o gen_estimator.o net_namespace.o + gen_stats.o gen_estimator.o net_namespace.o secure_seq.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c new file mode 100644 index 000000000000..45329d7c9dd9 --- /dev/null +++ b/net/core/secure_seq.c @@ -0,0 +1,184 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned; + +static int __init net_secret_init(void) +{ + get_random_bytes(net_secret, sizeof(net_secret)); + return 0; +} +late_initcall(net_secret_init); + +static u32 seq_scale(u32 seq) +{ + /* + * As close as possible to RFC 793, which + * suggests using a 250 kHz clock. + * Further reading shows this assumes 2 Mb/s networks. + * For 10 Mb/s Ethernet, a 1 MHz clock is appropriate. + * For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but + * we also need to limit the resolution so that the u32 seq + * overlaps less than one time per MSL (2 minutes). + * Choosing a clock of 64 ns period is OK. (period of 274 s) + */ + return seq + (ktime_to_ns(ktime_get_real()) >> 6); +} + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +__u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr, + __be16 sport, __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u32 i; + + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + daddr[i]; + secret[4] = net_secret[4] + + (((__force u16)sport << 16) + (__force u16)dport); + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + return seq_scale(hash[0]); +} +EXPORT_SYMBOL(secure_tcpv6_sequence_number); + +u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, + __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u32 i; + + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + (__force u32) daddr[i]; + secret[4] = net_secret[4] + (__force u32)dport; + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + return hash[0]; +} +#endif + +#ifdef CONFIG_INET +__u32 secure_ip_id(__be32 daddr) +{ + u32 hash[MD5_DIGEST_WORDS]; + + hash[0] = (__force __u32) daddr; + hash[1] = net_secret[13]; + hash[2] = net_secret[14]; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return hash[0]; +} + +__u32 secure_ipv6_id(const __be32 daddr[4]) +{ + __u32 hash[4]; + + memcpy(hash, daddr, 16); + md5_transform(hash, net_secret); + + return hash[0]; +} + +__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = ((__force u16)sport << 16) + (__force u16)dport; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return seq_scale(hash[0]); +} + +u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = (__force u32)dport ^ net_secret[14]; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return hash[0]; +} +EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); +#endif + +#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE) +u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + u64 seq; + + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = ((__force u16)sport << 16) + (__force u16)dport; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + seq = hash[0] | (((u64)hash[1]) << 32); + seq += ktime_to_ns(ktime_get_real()); + seq &= (1ull << 48) - 1; + + return seq; +} +EXPORT_SYMBOL(secure_dccp_sequence_number); + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, + __be16 sport, __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u64 seq; + u32 i; + + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + daddr[i]; + secret[4] = net_secret[4] + + (((__force u16)sport << 16) + (__force u16)dport); + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + seq = hash[0] | (((u64)hash[1]) << 32); + seq += ktime_to_ns(ktime_get_real()); + seq &= (1ull << 48) - 1; + + return seq; +} +EXPORT_SYMBOL(secure_dccpv6_sequence_number); +#endif +#endif diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8c36adfd1919..332639b56f4d 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -26,6 +26,7 @@ #include #include #include +#include #include "ackvec.h" #include "ccid.h" diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 8dc4348774a5..b74f76117dcf 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -29,6 +29,7 @@ #include #include #include +#include #include "dccp.h" #include "ipv6.h" @@ -69,13 +70,7 @@ static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb) dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &np->daddr); } -static inline __u32 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, - __be16 sport, __be16 dport ) -{ - return secure_tcpv6_sequence_number(saddr, daddr, sport, dport); -} - -static inline __u32 dccp_v6_init_sequence(struct sk_buff *skb) +static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb) { return secure_dccpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 3c0369a3a663..984ec656b03b 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -21,6 +21,7 @@ #include #include +#include #include /* diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e38213817d0a..86f13c67ea85 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -19,6 +19,7 @@ #include #include #include +#include /* * Theory of operations. diff --git a/net/ipv4/netfilter/nf_nat_proto_common.c b/net/ipv4/netfilter/nf_nat_proto_common.c index 3e61faf23a9a..f52d41ea0690 100644 --- a/net/ipv4/netfilter/nf_nat_proto_common.c +++ b/net/ipv4/netfilter/nf_nat_proto_common.c @@ -12,6 +12,7 @@ #include #include +#include #include #include #include diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6afc4eb50591..e3dec1c9f09d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -109,6 +109,7 @@ #include #endif #include +#include #define RT_FL_TOS(oldflp4) \ ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 955b8e65b69e..1c12b8ec849d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -72,6 +72,7 @@ #include #include #include +#include #include #include diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b53197233709..73f1a00a96af 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -20,6 +20,7 @@ #include #include #include +#include #include int __inet6_hash(struct sock *sk, struct inet_timewait_sock *tw) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 78aa53492b3e..d1fb63f4aeb7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -61,6 +61,7 @@ #include #include #include +#include #include -- cgit v1.2.3 From 830c0f0edca67403d361fe976a25b17356c11f19 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 6 Aug 2011 22:41:50 -0700 Subject: vfs: renumber DCACHE_xyz flags, remove some stale ones Gcc tends to generate better code with small integers, including the DCACHE_xyz flag tests - so move the common ones to be first in the list. Also just remove the unused DCACHE_INOTIFY_PARENT_WATCHED and DCACHE_AUTOFS_PENDING values, their users no longer exists in the source tree. And add a "unlikely()" to the DCACHE_OP_COMPARE test, since we want the common case to be a nice straight-line fall-through. Signed-off-by: Linus Torvalds --- fs/dcache.c | 2 +- include/linux/dcache.h | 30 +++++++++++++----------------- 2 files changed, 14 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/fs/dcache.c b/fs/dcache.c index c83cae19161e..a88948b8bd17 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1729,7 +1729,7 @@ seqretry: */ if (read_seqcount_retry(&dentry->d_seq, *seq)) goto seqretry; - if (parent->d_flags & DCACHE_OP_COMPARE) { + if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) { if (parent->d_op->d_compare(parent, *inode, dentry, i, tlen, tname, name)) diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d37d2a793099..62157c03caf7 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -180,12 +180,12 @@ struct dentry_operations { */ /* d_flags entries */ -#define DCACHE_AUTOFS_PENDING 0x0001 /* autofs: "under construction" */ -#define DCACHE_NFSFS_RENAMED 0x0002 - /* this dentry has been "silly renamed" and has to be deleted on the last - * dput() */ +#define DCACHE_OP_HASH 0x0001 +#define DCACHE_OP_COMPARE 0x0002 +#define DCACHE_OP_REVALIDATE 0x0004 +#define DCACHE_OP_DELETE 0x0008 -#define DCACHE_DISCONNECTED 0x0004 +#define DCACHE_DISCONNECTED 0x0010 /* This dentry is possibly not currently connected to the dcache tree, in * which case its parent will either be itself, or will have this flag as * well. nfsd will not use a dentry with this bit set, but will first @@ -196,22 +196,18 @@ struct dentry_operations { * dentry into place and return that dentry rather than the passed one, * typically using d_splice_alias. */ -#define DCACHE_REFERENCED 0x0008 /* Recently used, don't discard. */ -#define DCACHE_RCUACCESS 0x0010 /* Entry has ever been RCU-visible */ -#define DCACHE_INOTIFY_PARENT_WATCHED 0x0020 - /* Parent inode is watched by inotify */ - -#define DCACHE_COOKIE 0x0040 /* For use by dcookie subsystem */ -#define DCACHE_FSNOTIFY_PARENT_WATCHED 0x0080 - /* Parent inode is watched by some fsnotify listener */ +#define DCACHE_REFERENCED 0x0020 /* Recently used, don't discard. */ +#define DCACHE_RCUACCESS 0x0040 /* Entry has ever been RCU-visible */ #define DCACHE_CANT_MOUNT 0x0100 #define DCACHE_GENOCIDE 0x0200 -#define DCACHE_OP_HASH 0x1000 -#define DCACHE_OP_COMPARE 0x2000 -#define DCACHE_OP_REVALIDATE 0x4000 -#define DCACHE_OP_DELETE 0x8000 +#define DCACHE_NFSFS_RENAMED 0x1000 + /* this dentry has been "silly renamed" and has to be deleted on the last + * dput() */ +#define DCACHE_COOKIE 0x2000 /* For use by dcookie subsystem */ +#define DCACHE_FSNOTIFY_PARENT_WATCHED 0x4000 + /* Parent inode is watched by some fsnotify listener */ #define DCACHE_MOUNTED 0x10000 /* is a mountpoint */ #define DCACHE_NEED_AUTOMOUNT 0x20000 /* handle automount on this dir */ -- cgit v1.2.3 From 3ddcd0569cd68f00f3beae9a7959b72918bb91f4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 6 Aug 2011 22:45:50 -0700 Subject: vfs: optimize inode cache access patterns The inode structure layout is largely random, and some of the vfs paths really do care. The path lookup in particular is already quite D$ intensive, and profiles show that accessing the 'inode->i_op->xyz' fields is quite costly. We already optimized the dcache to not unnecessarily load the d_op structure for members that are often NULL using the DCACHE_OP_xyz bits in dentry->d_flags, and this does something very similar for the inode ops that are used during pathname lookup. It also re-orders the fields so that the fields accessed by 'stat' are together at the beginning of the inode structure, and roughly in the order accessed. The effect of this seems to be in the 1-2% range for an empty kernel "make -j" run (which is fairly kernel-intensive, mostly in filename lookup), so it's visible. The numbers are fairly noisy, though, and likely depend a lot on exact microarchitecture. So there's more tuning to be done. Signed-off-by: Linus Torvalds --- fs/inode.c | 1 + fs/namei.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++------- fs/stat.c | 4 +-- include/linux/fs.h | 59 ++++++++++++++++++++++++++---------------- 4 files changed, 106 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index 5aab80dc008c..73920d555c88 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -143,6 +143,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_op = &empty_iops; inode->i_fop = &empty_fops; inode->i_nlink = 1; + inode->i_opflags = 0; inode->i_uid = 0; inode->i_gid = 0; atomic_set(&inode->i_writecount, 0); diff --git a/fs/namei.c b/fs/namei.c index 3d607bd80e09..4a98bf154d88 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -308,6 +308,26 @@ int generic_permission(struct inode *inode, int mask) return -EACCES; } +/* + * We _really_ want to just do "generic_permission()" without + * even looking at the inode->i_op values. So we keep a cache + * flag in inode->i_opflags, that says "this has not special + * permission function, use the fast case". + */ +static inline int do_inode_permission(struct inode *inode, int mask) +{ + if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { + if (likely(inode->i_op->permission)) + return inode->i_op->permission(inode, mask); + + /* This gets set once for the inode lifetime */ + spin_lock(&inode->i_lock); + inode->i_opflags |= IOP_FASTPERM; + spin_unlock(&inode->i_lock); + } + return generic_permission(inode, mask); +} + /** * inode_permission - check for access rights to a given inode * @inode: inode to check permission on @@ -322,7 +342,7 @@ int inode_permission(struct inode *inode, int mask) { int retval; - if (mask & MAY_WRITE) { + if (unlikely(mask & MAY_WRITE)) { umode_t mode = inode->i_mode; /* @@ -339,11 +359,7 @@ int inode_permission(struct inode *inode, int mask) return -EACCES; } - if (inode->i_op->permission) - retval = inode->i_op->permission(inode, mask); - else - retval = generic_permission(inode, mask); - + retval = do_inode_permission(inode, mask); if (retval) return retval; @@ -1245,6 +1261,26 @@ static void terminate_walk(struct nameidata *nd) } } +/* + * Do we need to follow links? We _really_ want to be able + * to do this check without having to look at inode->i_op, + * so we keep a cache of "no, this doesn't need follow_link" + * for the common case. + */ +static inline int do_follow_link(struct inode *inode, int follow) +{ + if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { + if (likely(inode->i_op->follow_link)) + return follow; + + /* This gets set once for the inode lifetime */ + spin_lock(&inode->i_lock); + inode->i_opflags |= IOP_NOFOLLOW; + spin_unlock(&inode->i_lock); + } + return 0; +} + static inline int walk_component(struct nameidata *nd, struct path *path, struct qstr *name, int type, int follow) { @@ -1267,7 +1303,7 @@ static inline int walk_component(struct nameidata *nd, struct path *path, terminate_walk(nd); return -ENOENT; } - if (unlikely(inode->i_op->follow_link) && follow) { + if (do_follow_link(inode, follow)) { if (nd->flags & LOOKUP_RCU) { if (unlikely(unlazy_walk(nd, path->dentry))) { terminate_walk(nd); @@ -1319,6 +1355,26 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd) return res; } +/* + * We really don't want to look at inode->i_op->lookup + * when we don't have to. So we keep a cache bit in + * the inode ->i_opflags field that says "yes, we can + * do lookup on this inode". + */ +static inline int can_lookup(struct inode *inode) +{ + if (likely(inode->i_opflags & IOP_LOOKUP)) + return 1; + if (likely(!inode->i_op->lookup)) + return 0; + + /* We do this once for the lifetime of the inode */ + spin_lock(&inode->i_lock); + inode->i_opflags |= IOP_LOOKUP; + spin_unlock(&inode->i_lock); + return 1; +} + /* * Name resolution. * This is the basic name resolution function, turning a pathname into @@ -1398,10 +1454,10 @@ static int link_path_walk(const char *name, struct nameidata *nd) if (err) return err; } + if (can_lookup(nd->inode)) + continue; err = -ENOTDIR; - if (!nd->inode->i_op->lookup) - break; - continue; + break; /* here ends the main loop */ last_component: diff --git a/fs/stat.c b/fs/stat.c index 961039121cb8..ba5316ffac61 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -27,12 +27,12 @@ void generic_fillattr(struct inode *inode, struct kstat *stat) stat->uid = inode->i_uid; stat->gid = inode->i_gid; stat->rdev = inode->i_rdev; + stat->size = i_size_read(inode); stat->atime = inode->i_atime; stat->mtime = inode->i_mtime; stat->ctime = inode->i_ctime; - stat->size = i_size_read(inode); - stat->blocks = inode->i_blocks; stat->blksize = (1 << inode->i_blkbits); + stat->blocks = inode->i_blocks; } EXPORT_SYMBOL(generic_fillattr); diff --git a/include/linux/fs.h b/include/linux/fs.h index 786b3b1113cf..178cdb4f1d4a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -738,22 +738,54 @@ static inline int mapping_writably_mapped(struct address_space *mapping) struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) +#define IOP_FASTPERM 0x0001 +#define IOP_LOOKUP 0x0002 +#define IOP_NOFOLLOW 0x0004 + +/* + * Keep mostly read-only and often accessed (especially for + * the RCU path lookup and 'stat' data) fields at the beginning + * of the 'struct inode' + */ struct inode { - /* RCU path lookup touches following: */ umode_t i_mode; + unsigned short i_opflags; uid_t i_uid; gid_t i_gid; + unsigned int i_flags; + +#ifdef CONFIG_FS_POSIX_ACL + struct posix_acl *i_acl; + struct posix_acl *i_default_acl; +#endif + const struct inode_operations *i_op; struct super_block *i_sb; + struct address_space *i_mapping; - spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ - unsigned int i_flags; - unsigned long i_state; #ifdef CONFIG_SECURITY void *i_security; #endif - struct mutex i_mutex; + /* Stat data, not accessed from path walking */ + unsigned long i_ino; + unsigned int i_nlink; + dev_t i_rdev; + loff_t i_size; + struct timespec i_atime; + struct timespec i_mtime; + struct timespec i_ctime; + unsigned int i_blkbits; + blkcnt_t i_blocks; + +#ifdef __NEED_I_SIZE_ORDERED + seqcount_t i_size_seqcount; +#endif + + /* Misc */ + unsigned long i_state; + spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ + struct mutex i_mutex; unsigned long dirtied_when; /* jiffies of first dirtying */ @@ -765,25 +797,12 @@ struct inode { struct list_head i_dentry; struct rcu_head i_rcu; }; - unsigned long i_ino; atomic_t i_count; - unsigned int i_nlink; - dev_t i_rdev; - unsigned int i_blkbits; u64 i_version; - loff_t i_size; -#ifdef __NEED_I_SIZE_ORDERED - seqcount_t i_size_seqcount; -#endif - struct timespec i_atime; - struct timespec i_mtime; - struct timespec i_ctime; - blkcnt_t i_blocks; unsigned short i_bytes; atomic_t i_dio_count; const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ struct file_lock *i_flock; - struct address_space *i_mapping; struct address_space i_data; #ifdef CONFIG_QUOTA struct dquot *i_dquot[MAXQUOTAS]; @@ -806,10 +825,6 @@ struct inode { atomic_t i_readcount; /* struct files open RO */ #endif atomic_t i_writecount; -#ifdef CONFIG_FS_POSIX_ACL - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; -#endif void *i_private; /* fs or device private pointer */ }; -- cgit v1.2.3 From 3295514841c2112d94451ba5deaf54f5afb78ea9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 7 Aug 2011 18:55:11 +0100 Subject: fix rcu annotations noise in cred.h task->cred is declared as __rcu, and access to other tasks' ->cred is, indeed, protected. Access to current->cred does not need rcu_dereference() at all, since only the task itself can change its ->cred. sparse, of course, has no way of knowing that... Add force-cast in current_cred(), make current_fsuid() et.al. use it. Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/cred.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cred.h b/include/linux/cred.h index 48e82af1159b..98f46efbe2d2 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -265,10 +265,11 @@ static inline void put_cred(const struct cred *_cred) /** * current_cred - Access the current task's subjective credentials * - * Access the subjective credentials of the current task. + * Access the subjective credentials of the current task. RCU-safe, + * since nobody else can modify it. */ #define current_cred() \ - (current->cred) + (*(__force struct cred **)¤t->cred) /** * __task_cred - Access a task's objective credentials @@ -307,7 +308,7 @@ static inline void put_cred(const struct cred *_cred) ({ \ struct user_struct *__u; \ struct cred *__cred; \ - __cred = (struct cred *) current_cred(); \ + __cred = current_cred(); \ __u = get_uid(__cred->user); \ __u; \ }) @@ -322,7 +323,7 @@ static inline void put_cred(const struct cred *_cred) ({ \ struct group_info *__groups; \ struct cred *__cred; \ - __cred = (struct cred *) current_cred(); \ + __cred = current_cred(); \ __groups = get_group_info(__cred->group_info); \ __groups; \ }) @@ -341,7 +342,7 @@ static inline void put_cred(const struct cred *_cred) #define current_cred_xxx(xxx) \ ({ \ - current->cred->xxx; \ + current_cred()->xxx; \ }) #define current_uid() (current_cred_xxx(uid)) -- cgit v1.2.3