From f84dbb912f344270f31d5cce974f12908a47798d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 10 Jul 2008 14:48:54 -0700 Subject: genirq: enable polling for disabled screaming irqs When we disable a screaming irq we never see it again. If the irq line is shared or if the driver half works this is a real pain. So periodically poll the handlers for screaming interrupts. I use a timer instead of the classic irq poll technique of working off the timer interrupt because when we use the local apic timers note_interrupt is never called (bug?). Further on a system with dynamic ticks the timer interrupt might not even fire unless there is a timer telling it it needs to. I forced this case on my test system with an e1000 nic and my ssh session remained responsive despite the interrupt handler only being called every 10th of a second. Signed-off-by: Eric W. Biederman Signed-off-by: Ingo Molnar diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index c66d3f1..19fe9d6 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -12,83 +12,117 @@ #include #include #include +#include static int irqfixup __read_mostly; +#define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10) +static void poll_spurious_irqs(unsigned long dummy); +static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs, 0, 0); + /* * Recovery handler for misrouted interrupts. */ -static int misrouted_irq(int irq) +static int try_one_irq(int irq, struct irq_desc *desc) { - int i; + struct irqaction *action; int ok = 0; int work = 0; /* Did we do work for a real IRQ */ - for (i = 1; i < NR_IRQS; i++) { - struct irq_desc *desc = irq_desc + i; - struct irqaction *action; - - if (i == irq) /* Already tried */ - continue; - - spin_lock(&desc->lock); - /* Already running on another processor */ - if (desc->status & IRQ_INPROGRESS) { - /* - * Already running: If it is shared get the other - * CPU to go looking for our mystery interrupt too - */ - if (desc->action && (desc->action->flags & IRQF_SHARED)) - desc->status |= IRQ_PENDING; - spin_unlock(&desc->lock); - continue; - } - /* Honour the normal IRQ locking */ - desc->status |= IRQ_INPROGRESS; - action = desc->action; + spin_lock(&desc->lock); + /* Already running on another processor */ + if (desc->status & IRQ_INPROGRESS) { + /* + * Already running: If it is shared get the other + * CPU to go looking for our mystery interrupt too + */ + if (desc->action && (desc->action->flags & IRQF_SHARED)) + desc->status |= IRQ_PENDING; spin_unlock(&desc->lock); + return ok; + } + /* Honour the normal IRQ locking */ + desc->status |= IRQ_INPROGRESS; + action = desc->action; + spin_unlock(&desc->lock); - while (action) { - /* Only shared IRQ handlers are safe to call */ - if (action->flags & IRQF_SHARED) { - if (action->handler(i, action->dev_id) == - IRQ_HANDLED) - ok = 1; - } - action = action->next; + while (action) { + /* Only shared IRQ handlers are safe to call */ + if (action->flags & IRQF_SHARED) { + if (action->handler(irq, action->dev_id) == + IRQ_HANDLED) + ok = 1; } - local_irq_disable(); - /* Now clean up the flags */ - spin_lock(&desc->lock); - action = desc->action; + action = action->next; + } + local_irq_disable(); + /* Now clean up the flags */ + spin_lock(&desc->lock); + action = desc->action; + /* + * While we were looking for a fixup someone queued a real + * IRQ clashing with our walk: + */ + while ((desc->status & IRQ_PENDING) && action) { /* - * While we were looking for a fixup someone queued a real - * IRQ clashing with our walk: - */ - while ((desc->status & IRQ_PENDING) && action) { - /* - * Perform real IRQ processing for the IRQ we deferred - */ - work = 1; - spin_unlock(&desc->lock); - handle_IRQ_event(i, action); - spin_lock(&desc->lock); - desc->status &= ~IRQ_PENDING; - } - desc->status &= ~IRQ_INPROGRESS; - /* - * If we did actual work for the real IRQ line we must let the - * IRQ controller clean up too + * Perform real IRQ processing for the IRQ we deferred */ - if (work && desc->chip && desc->chip->end) - desc->chip->end(i); + work = 1; spin_unlock(&desc->lock); + handle_IRQ_event(irq, action); + spin_lock(&desc->lock); + desc->status &= ~IRQ_PENDING; + } + desc->status &= ~IRQ_INPROGRESS; + /* + * If we did actual work for the real IRQ line we must let the + * IRQ controller clean up too + */ + if (work && desc->chip && desc->chip->end) + desc->chip->end(irq); + spin_unlock(&desc->lock); + + return ok; +} + +static int misrouted_irq(int irq) +{ + int i; + int ok = 0; + + for (i = 1; i < NR_IRQS; i++) { + struct irq_desc *desc = irq_desc + i; + + if (i == irq) /* Already tried */ + continue; + + if (try_one_irq(i, desc)) + ok = 1; } /* So the caller can adjust the irq error counts */ return ok; } +static void poll_spurious_irqs(unsigned long dummy) +{ + int i; + for (i = 1; i < NR_IRQS; i++) { + struct irq_desc *desc = irq_desc + i; + unsigned int status; + + /* Racy but it doesn't matter */ + status = desc->status; + barrier(); + if (!(status & IRQ_SPURIOUS_DISABLED)) + continue; + + try_one_irq(i, desc); + } + + mod_timer(&poll_spurious_irq_timer, jiffies + POLL_SPURIOUS_IRQ_INTERVAL); +} + /* * If 99,900 of the previous 100,000 interrupts have not been handled * then assume that the IRQ is stuck in some manner. Drop a diagnostic @@ -212,6 +246,8 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc, desc->status |= IRQ_DISABLED | IRQ_SPURIOUS_DISABLED; desc->depth++; desc->chip->disable(irq); + + mod_timer(&poll_spurious_irq_timer, jiffies + POLL_SPURIOUS_IRQ_INTERVAL); } desc->irqs_unhandled = 0; } -- cgit v0.10.2 From 8d00a6c8f6b08e7167bc03bf955cdc7e47c5132e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 22 Jul 2008 08:39:57 +0200 Subject: genirq: remove last NO_IDLE_HZ leftovers Signed-off-by: Thomas Gleixner diff --git a/include/linux/irq.h b/include/linux/irq.h index 8ccb462..f3047df 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -197,10 +197,6 @@ extern int setup_irq(unsigned int irq, struct irqaction *new); #ifdef CONFIG_GENERIC_HARDIRQS -#ifndef handle_dynamic_tick -# define handle_dynamic_tick(a) do { } while (0) -#endif - #ifdef CONFIG_SMP #if defined(CONFIG_GENERIC_PENDING_IRQ) || defined(CONFIG_IRQBALANCE) diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 5fa6198..f4c8a03 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -131,8 +131,6 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) irqreturn_t ret, retval = IRQ_NONE; unsigned int status = 0; - handle_dynamic_tick(action); - if (!(action->flags & IRQF_DISABLED)) local_irq_enable_in_hardirq(); -- cgit v0.10.2 From 34a82443b79dcda4304b229d555586296da40c16 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 30 Jul 2008 12:35:05 -0700 Subject: [MTD] dataflash OTP support Now that we can tell when we have one of the newer DataFlash chips, optionally expose the 128 bytes of OTP memory they provide. Tested on at45db642 revision B and D chips. Switch mtdchar over to a generic HAVE_MTD_OTP flag instead of adding another #ifdef for each type of chip whose driver has OTP support. Signed-off-by: David Brownell Cc: Bryan Wu Cc: Michael Hennerich Signed-off-by: Andrew Morton Signed-off-by: David Woodhouse diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig index 14f11f8..a90d50c 100644 --- a/drivers/mtd/Kconfig +++ b/drivers/mtd/Kconfig @@ -172,6 +172,11 @@ config MTD_CHAR memory chips, and also use ioctl() to obtain information about the device, or to erase parts of it. +config HAVE_MTD_OTP + bool + help + Enable access to OTP regions using MTD_CHAR. + config MTD_BLKDEVS tristate "Common interface to block layer for MTD 'translation layers'" depends on BLOCK diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig index 479d32b..4c35e5d 100644 --- a/drivers/mtd/chips/Kconfig +++ b/drivers/mtd/chips/Kconfig @@ -154,6 +154,7 @@ config MTD_CFI_I8 config MTD_OTP bool "Protection Registers aka one-time programmable (OTP) bits" depends on MTD_CFI_ADV_OPTIONS + select HAVE_MTD_OTP default n help This enables support for reading, writing and locking so called diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index 9c613f0..88f4df0 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -59,6 +59,17 @@ config MTD_DATAFLASH Sometimes DataFlash chips are packaged inside MMC-format cards; at this writing, the MMC stack won't handle those. +config MTD_DATAFLASH_OTP + bool "DataFlash OTP support (Security Register)" + depends on MTD_DATAFLASH + select HAVE_MTD_OTP + help + Newer DataFlash chips (revisions C and D) support 128 bytes of + one-time-programmable (OTP) data. The first half may be written + (once) with up to 64 bytes of data, such as a serial number or + other key product data. The second half is programmed with a + unique-to-each-chip bit pattern at the factory. + config MTD_M25P80 tristate "Support most SPI Flash chips (AT26DF, M25P, W25X, ...)" depends on SPI_MASTER && EXPERIMENTAL diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c index 8bd0dea..17c9b20 100644 --- a/drivers/mtd/devices/mtd_dataflash.c +++ b/drivers/mtd/devices/mtd_dataflash.c @@ -80,7 +80,8 @@ */ #define OP_READ_ID 0x9F #define OP_READ_SECURITY 0x77 -#define OP_WRITE_SECURITY 0x9A /* OTP bits */ +#define OP_WRITE_SECURITY_REVC 0x9A +#define OP_WRITE_SECURITY 0x9B /* revision D */ struct dataflash { @@ -451,16 +452,192 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len, /* ......................................................................... */ +#ifdef CONFIG_MTD_DATAFLASH_OTP + +static int dataflash_get_otp_info(struct mtd_info *mtd, + struct otp_info *info, size_t len) +{ + /* Report both blocks as identical: bytes 0..64, locked. + * Unless the user block changed from all-ones, we can't + * tell whether it's still writable; so we assume it isn't. + */ + info->start = 0; + info->length = 64; + info->locked = 1; + return sizeof(*info); +} + +static ssize_t otp_read(struct spi_device *spi, unsigned base, + uint8_t *buf, loff_t off, size_t len) +{ + struct spi_message m; + size_t l; + uint8_t *scratch; + struct spi_transfer t; + int status; + + if (off > 64) + return -EINVAL; + + if ((off + len) > 64) + len = 64 - off; + if (len == 0) + return len; + + spi_message_init(&m); + + l = 4 + base + off + len; + scratch = kzalloc(l, GFP_KERNEL); + if (!scratch) + return -ENOMEM; + + /* OUT: OP_READ_SECURITY, 3 don't-care bytes, zeroes + * IN: ignore 4 bytes, data bytes 0..N (max 127) + */ + scratch[0] = OP_READ_SECURITY; + + memset(&t, 0, sizeof t); + t.tx_buf = scratch; + t.rx_buf = scratch; + t.len = l; + spi_message_add_tail(&t, &m); + + dataflash_waitready(spi); + + status = spi_sync(spi, &m); + if (status >= 0) { + memcpy(buf, scratch + 4 + base + off, len); + status = len; + } + + kfree(scratch); + return status; +} + +static int dataflash_read_fact_otp(struct mtd_info *mtd, + loff_t from, size_t len, size_t *retlen, u_char *buf) +{ + struct dataflash *priv = (struct dataflash *)mtd->priv; + int status; + + /* 64 bytes, from 0..63 ... start at 64 on-chip */ + mutex_lock(&priv->lock); + status = otp_read(priv->spi, 64, buf, from, len); + mutex_unlock(&priv->lock); + + if (status < 0) + return status; + *retlen = status; + return 0; +} + +static int dataflash_read_user_otp(struct mtd_info *mtd, + loff_t from, size_t len, size_t *retlen, u_char *buf) +{ + struct dataflash *priv = (struct dataflash *)mtd->priv; + int status; + + /* 64 bytes, from 0..63 ... start at 0 on-chip */ + mutex_lock(&priv->lock); + status = otp_read(priv->spi, 0, buf, from, len); + mutex_unlock(&priv->lock); + + if (status < 0) + return status; + *retlen = status; + return 0; +} + +static int dataflash_write_user_otp(struct mtd_info *mtd, + loff_t from, size_t len, size_t *retlen, u_char *buf) +{ + struct spi_message m; + const size_t l = 4 + 64; + uint8_t *scratch; + struct spi_transfer t; + struct dataflash *priv = (struct dataflash *)mtd->priv; + int status; + + if (len > 64) + return -EINVAL; + + /* Strictly speaking, we *could* truncate the write ... but + * let's not do that for the only write that's ever possible. + */ + if ((from + len) > 64) + return -EINVAL; + + /* OUT: OP_WRITE_SECURITY, 3 zeroes, 64 data-or-zero bytes + * IN: ignore all + */ + scratch = kzalloc(l, GFP_KERNEL); + if (!scratch) + return -ENOMEM; + scratch[0] = OP_WRITE_SECURITY; + memcpy(scratch + 4 + from, buf, len); + + spi_message_init(&m); + + memset(&t, 0, sizeof t); + t.tx_buf = scratch; + t.len = l; + spi_message_add_tail(&t, &m); + + /* Write the OTP bits, if they've not yet been written. + * This modifies SRAM buffer1. + */ + mutex_lock(&priv->lock); + dataflash_waitready(priv->spi); + status = spi_sync(priv->spi, &m); + mutex_unlock(&priv->lock); + + kfree(scratch); + + if (status >= 0) { + status = 0; + *retlen = len; + } + return status; +} + +static char *otp_setup(struct mtd_info *device, char revision) +{ + device->get_fact_prot_info = dataflash_get_otp_info; + device->read_fact_prot_reg = dataflash_read_fact_otp; + device->get_user_prot_info = dataflash_get_otp_info; + device->read_user_prot_reg = dataflash_read_user_otp; + + /* rev c parts (at45db321c and at45db1281 only!) use a + * different write procedure; not (yet?) implemented. + */ + if (revision > 'c') + device->write_user_prot_reg = dataflash_write_user_otp; + + return ", OTP"; +} + +#else + +static char *otp_setup(struct mtd_info *device) +{ + return " (OTP)"; +} + +#endif + +/* ......................................................................... */ + /* * Register DataFlash device with MTD subsystem. */ static int __devinit -add_dataflash(struct spi_device *spi, char *name, - int nr_pages, int pagesize, int pageoffset) +add_dataflash_otp(struct spi_device *spi, char *name, + int nr_pages, int pagesize, int pageoffset, char revision) { struct dataflash *priv; struct mtd_info *device; struct flash_platform_data *pdata = spi->dev.platform_data; + char *otp_tag = ""; priv = kzalloc(sizeof *priv, GFP_KERNEL); if (!priv) @@ -489,8 +666,12 @@ add_dataflash(struct spi_device *spi, char *name, device->write = dataflash_write; device->priv = priv; - dev_info(&spi->dev, "%s (%d KBytes) pagesize %d bytes\n", - name, DIV_ROUND_UP(device->size, 1024), pagesize); + if (revision >= 'c') + otp_tag = otp_setup(device, revision); + + dev_info(&spi->dev, "%s (%d KBytes) pagesize %d bytes%s\n", + name, DIV_ROUND_UP(device->size, 1024), + pagesize, otp_tag); dev_set_drvdata(&spi->dev, priv); if (mtd_has_partitions()) { @@ -519,6 +700,14 @@ add_dataflash(struct spi_device *spi, char *name, return add_mtd_device(device) == 1 ? -ENODEV : 0; } +static inline int __devinit +add_dataflash(struct spi_device *spi, char *name, + int nr_pages, int pagesize, int pageoffset) +{ + return add_dataflash_otp(spi, name, nr_pages, pagesize, + pageoffset, 0); +} + struct flash_info { char *name; @@ -664,13 +853,16 @@ static int __devinit dataflash_probe(struct spi_device *spi) * Try to detect dataflash by JEDEC ID. * If it succeeds we know we have either a C or D part. * D will support power of 2 pagesize option. + * Both support the security register, though with different + * write procedures. */ info = jedec_probe(spi); if (IS_ERR(info)) return PTR_ERR(info); if (info != NULL) - return add_dataflash(spi, info->name, info->nr_pages, - info->pagesize, info->pageoffset); + return add_dataflash_otp(spi, info->name, info->nr_pages, + info->pagesize, info->pageoffset, + (info->flags & SUP_POW2PS) ? 'd' : 'c'); /* * Older chips support only legacy commands, identifing diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c index d2f3318..13cc67a 100644 --- a/drivers/mtd/mtdchar.c +++ b/drivers/mtd/mtdchar.c @@ -350,7 +350,7 @@ static void mtdchar_erase_callback (struct erase_info *instr) wake_up((wait_queue_head_t *)instr->priv); } -#if defined(CONFIG_MTD_OTP) || defined(CONFIG_MTD_ONENAND_OTP) +#ifdef CONFIG_HAVE_MTD_OTP static int otp_select_filemode(struct mtd_file_info *mfi, int mode) { struct mtd_info *mtd = mfi->mtd; @@ -663,7 +663,7 @@ static int mtd_ioctl(struct inode *inode, struct file *file, break; } -#if defined(CONFIG_MTD_OTP) || defined(CONFIG_MTD_ONENAND_OTP) +#ifdef CONFIG_HAVE_MTD_OTP case OTPSELECT: { int mode; diff --git a/drivers/mtd/onenand/Kconfig b/drivers/mtd/onenand/Kconfig index cb41cbc..b94a61b 100644 --- a/drivers/mtd/onenand/Kconfig +++ b/drivers/mtd/onenand/Kconfig @@ -29,6 +29,7 @@ config MTD_ONENAND_GENERIC config MTD_ONENAND_OTP bool "OneNAND OTP Support" + select HAVE_MTD_OTP help One Block of the NAND Flash Array memory is reserved as a One-Time Programmable Block memory area. -- cgit v0.10.2 From feb2f55db45919aa80731f8877b60cab454b7b94 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 1 Aug 2008 11:53:29 +0300 Subject: [MTD] [OneNAND] Add defines for HF and sync write Signed-off-by: Adrian Hunter Signed-off-by: David Woodhouse diff --git a/include/linux/mtd/onenand_regs.h b/include/linux/mtd/onenand_regs.h index d1b310c..0c6bbe2 100644 --- a/include/linux/mtd/onenand_regs.h +++ b/include/linux/mtd/onenand_regs.h @@ -152,6 +152,8 @@ #define ONENAND_SYS_CFG1_INT (1 << 6) #define ONENAND_SYS_CFG1_IOBE (1 << 5) #define ONENAND_SYS_CFG1_RDY_CONF (1 << 4) +#define ONENAND_SYS_CFG1_HF (1 << 2) +#define ONENAND_SYS_CFG1_SYNC_WRITE (1 << 1) /* * Controller Status Register F240h (R) -- cgit v0.10.2 From c4308d1076830a72e05eb3e5f58b9ed851229399 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Fri, 1 Aug 2008 11:44:20 -0500 Subject: [MTD] remove code associated with !CONFIG_PPC_MERGE Now that arch/ppc is gone we don't need CONFIG_PPC_MERGE anymore remove the dead code associated with !CONFIG_PPC_MERGE. The mtd maps should be using the OF based mechanism. Signed-off-by: Kumar Gala Acked-by: Josh Boyer Signed-off-by: David Woodhouse diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig index df8e00b..db667b1 100644 --- a/drivers/mtd/maps/Kconfig +++ b/drivers/mtd/maps/Kconfig @@ -332,30 +332,6 @@ config MTD_CFI_FLAGADM Mapping for the Flaga digital module. If you don't have one, ignore this setting. -config MTD_WALNUT - tristate "Flash device mapped on IBM 405GP Walnut" - depends on MTD_JEDECPROBE && WALNUT && !PPC_MERGE - help - This enables access routines for the flash chips on the IBM 405GP - Walnut board. If you have one of these boards and would like to - use the flash chips on it, say 'Y'. - -config MTD_EBONY - tristate "Flash devices mapped on IBM 440GP Ebony" - depends on MTD_JEDECPROBE && EBONY && !PPC_MERGE - help - This enables access routines for the flash chips on the IBM 440GP - Ebony board. If you have one of these boards and would like to - use the flash chips on it, say 'Y'. - -config MTD_OCOTEA - tristate "Flash devices mapped on IBM 440GX Ocotea" - depends on MTD_CFI && OCOTEA && !PPC_MERGE - help - This enables access routines for the flash chips on the IBM 440GX - Ocotea board. If you have one of these boards and would like to - use the flash chips on it, say 'Y'. - config MTD_REDWOOD tristate "CFI Flash devices mapped on IBM Redwood" depends on MTD_CFI && ( REDWOOD_4 || REDWOOD_5 || REDWOOD_6 ) diff --git a/drivers/mtd/maps/Makefile b/drivers/mtd/maps/Makefile index 6cda6df..b258250 100644 --- a/drivers/mtd/maps/Makefile +++ b/drivers/mtd/maps/Makefile @@ -50,9 +50,6 @@ obj-$(CONFIG_MTD_REDWOOD) += redwood.o obj-$(CONFIG_MTD_UCLINUX) += uclinux.o obj-$(CONFIG_MTD_NETtel) += nettel.o obj-$(CONFIG_MTD_SCB2_FLASH) += scb2_flash.o -obj-$(CONFIG_MTD_EBONY) += ebony.o -obj-$(CONFIG_MTD_OCOTEA) += ocotea.o -obj-$(CONFIG_MTD_WALNUT) += walnut.o obj-$(CONFIG_MTD_H720X) += h720x-flash.o obj-$(CONFIG_MTD_SBC8240) += sbc8240.o obj-$(CONFIG_MTD_NOR_TOTO) += omap-toto-flash.o diff --git a/drivers/mtd/maps/ebony.c b/drivers/mtd/maps/ebony.c deleted file mode 100644 index d92b7c7..0000000 --- a/drivers/mtd/maps/ebony.c +++ /dev/null @@ -1,163 +0,0 @@ -/* - * Mapping for Ebony user flash - * - * Matt Porter - * - * Copyright 2002-2004 MontaVista Software Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static struct mtd_info *flash; - -static struct map_info ebony_small_map = { - .name = "Ebony small flash", - .size = EBONY_SMALL_FLASH_SIZE, - .bankwidth = 1, -}; - -static struct map_info ebony_large_map = { - .name = "Ebony large flash", - .size = EBONY_LARGE_FLASH_SIZE, - .bankwidth = 1, -}; - -static struct mtd_partition ebony_small_partitions[] = { - { - .name = "OpenBIOS", - .offset = 0x0, - .size = 0x80000, - } -}; - -static struct mtd_partition ebony_large_partitions[] = { - { - .name = "fs", - .offset = 0, - .size = 0x380000, - }, - { - .name = "firmware", - .offset = 0x380000, - .size = 0x80000, - } -}; - -int __init init_ebony(void) -{ - u8 fpga0_reg; - u8 __iomem *fpga0_adr; - unsigned long long small_flash_base, large_flash_base; - - fpga0_adr = ioremap64(EBONY_FPGA_ADDR, 16); - if (!fpga0_adr) - return -ENOMEM; - - fpga0_reg = readb(fpga0_adr); - iounmap(fpga0_adr); - - if (EBONY_BOOT_SMALL_FLASH(fpga0_reg) && - !EBONY_FLASH_SEL(fpga0_reg)) - small_flash_base = EBONY_SMALL_FLASH_HIGH2; - else if (EBONY_BOOT_SMALL_FLASH(fpga0_reg) && - EBONY_FLASH_SEL(fpga0_reg)) - small_flash_base = EBONY_SMALL_FLASH_HIGH1; - else if (!EBONY_BOOT_SMALL_FLASH(fpga0_reg) && - !EBONY_FLASH_SEL(fpga0_reg)) - small_flash_base = EBONY_SMALL_FLASH_LOW2; - else - small_flash_base = EBONY_SMALL_FLASH_LOW1; - - if (EBONY_BOOT_SMALL_FLASH(fpga0_reg) && - !EBONY_ONBRD_FLASH_EN(fpga0_reg)) - large_flash_base = EBONY_LARGE_FLASH_LOW; - else - large_flash_base = EBONY_LARGE_FLASH_HIGH; - - ebony_small_map.phys = small_flash_base; - ebony_small_map.virt = ioremap64(small_flash_base, - ebony_small_map.size); - - if (!ebony_small_map.virt) { - printk("Failed to ioremap flash\n"); - return -EIO; - } - - simple_map_init(&ebony_small_map); - - flash = do_map_probe("jedec_probe", &ebony_small_map); - if (flash) { - flash->owner = THIS_MODULE; - add_mtd_partitions(flash, ebony_small_partitions, - ARRAY_SIZE(ebony_small_partitions)); - } else { - printk("map probe failed for flash\n"); - iounmap(ebony_small_map.virt); - return -ENXIO; - } - - ebony_large_map.phys = large_flash_base; - ebony_large_map.virt = ioremap64(large_flash_base, - ebony_large_map.size); - - if (!ebony_large_map.virt) { - printk("Failed to ioremap flash\n"); - iounmap(ebony_small_map.virt); - return -EIO; - } - - simple_map_init(&ebony_large_map); - - flash = do_map_probe("jedec_probe", &ebony_large_map); - if (flash) { - flash->owner = THIS_MODULE; - add_mtd_partitions(flash, ebony_large_partitions, - ARRAY_SIZE(ebony_large_partitions)); - } else { - printk("map probe failed for flash\n"); - iounmap(ebony_small_map.virt); - iounmap(ebony_large_map.virt); - return -ENXIO; - } - - return 0; -} - -static void __exit cleanup_ebony(void) -{ - if (flash) { - del_mtd_partitions(flash); - map_destroy(flash); - } - - if (ebony_small_map.virt) { - iounmap(ebony_small_map.virt); - ebony_small_map.virt = NULL; - } - - if (ebony_large_map.virt) { - iounmap(ebony_large_map.virt); - ebony_large_map.virt = NULL; - } -} - -module_init(init_ebony); -module_exit(cleanup_ebony); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Matt Porter "); -MODULE_DESCRIPTION("MTD map and partitions for IBM 440GP Ebony boards"); diff --git a/drivers/mtd/maps/ocotea.c b/drivers/mtd/maps/ocotea.c deleted file mode 100644 index 5522eac..0000000 --- a/drivers/mtd/maps/ocotea.c +++ /dev/null @@ -1,154 +0,0 @@ -/* - * Mapping for Ocotea user flash - * - * Matt Porter - * - * Copyright 2002-2004 MontaVista Software Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static struct mtd_info *flash; - -static struct map_info ocotea_small_map = { - .name = "Ocotea small flash", - .size = OCOTEA_SMALL_FLASH_SIZE, - .buswidth = 1, -}; - -static struct map_info ocotea_large_map = { - .name = "Ocotea large flash", - .size = OCOTEA_LARGE_FLASH_SIZE, - .buswidth = 1, -}; - -static struct mtd_partition ocotea_small_partitions[] = { - { - .name = "pibs", - .offset = 0x0, - .size = 0x100000, - } -}; - -static struct mtd_partition ocotea_large_partitions[] = { - { - .name = "fs", - .offset = 0, - .size = 0x300000, - }, - { - .name = "firmware", - .offset = 0x300000, - .size = 0x100000, - } -}; - -int __init init_ocotea(void) -{ - u8 fpga0_reg; - u8 *fpga0_adr; - unsigned long long small_flash_base, large_flash_base; - - fpga0_adr = ioremap64(OCOTEA_FPGA_ADDR, 16); - if (!fpga0_adr) - return -ENOMEM; - - fpga0_reg = readb((unsigned long)fpga0_adr); - iounmap(fpga0_adr); - - if (OCOTEA_BOOT_LARGE_FLASH(fpga0_reg)) { - small_flash_base = OCOTEA_SMALL_FLASH_HIGH; - large_flash_base = OCOTEA_LARGE_FLASH_LOW; - } - else { - small_flash_base = OCOTEA_SMALL_FLASH_LOW; - large_flash_base = OCOTEA_LARGE_FLASH_HIGH; - } - - ocotea_small_map.phys = small_flash_base; - ocotea_small_map.virt = ioremap64(small_flash_base, - ocotea_small_map.size); - - if (!ocotea_small_map.virt) { - printk("Failed to ioremap flash\n"); - return -EIO; - } - - simple_map_init(&ocotea_small_map); - - flash = do_map_probe("map_rom", &ocotea_small_map); - if (flash) { - flash->owner = THIS_MODULE; - add_mtd_partitions(flash, ocotea_small_partitions, - ARRAY_SIZE(ocotea_small_partitions)); - } else { - printk("map probe failed for flash\n"); - iounmap(ocotea_small_map.virt); - return -ENXIO; - } - - ocotea_large_map.phys = large_flash_base; - ocotea_large_map.virt = ioremap64(large_flash_base, - ocotea_large_map.size); - - if (!ocotea_large_map.virt) { - printk("Failed to ioremap flash\n"); - iounmap(ocotea_small_map.virt); - return -EIO; - } - - simple_map_init(&ocotea_large_map); - - flash = do_map_probe("cfi_probe", &ocotea_large_map); - if (flash) { - flash->owner = THIS_MODULE; - add_mtd_partitions(flash, ocotea_large_partitions, - ARRAY_SIZE(ocotea_large_partitions)); - } else { - printk("map probe failed for flash\n"); - iounmap(ocotea_small_map.virt); - iounmap(ocotea_large_map.virt); - return -ENXIO; - } - - return 0; -} - -static void __exit cleanup_ocotea(void) -{ - if (flash) { - del_mtd_partitions(flash); - map_destroy(flash); - } - - if (ocotea_small_map.virt) { - iounmap((void *)ocotea_small_map.virt); - ocotea_small_map.virt = 0; - } - - if (ocotea_large_map.virt) { - iounmap((void *)ocotea_large_map.virt); - ocotea_large_map.virt = 0; - } -} - -module_init(init_ocotea); -module_exit(cleanup_ocotea); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Matt Porter "); -MODULE_DESCRIPTION("MTD map and partitions for IBM 440GX Ocotea boards"); diff --git a/drivers/mtd/maps/walnut.c b/drivers/mtd/maps/walnut.c deleted file mode 100644 index e243476..0000000 --- a/drivers/mtd/maps/walnut.c +++ /dev/null @@ -1,122 +0,0 @@ -/* - * Mapping for Walnut flash - * (used ebony.c as a "framework") - * - * Heikki Lindholm - * - * - * 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. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* these should be in platforms/4xx/walnut.h ? */ -#define WALNUT_FLASH_ONBD_N(x) (x & 0x02) -#define WALNUT_FLASH_SRAM_SEL(x) (x & 0x01) -#define WALNUT_FLASH_LOW 0xFFF00000 -#define WALNUT_FLASH_HIGH 0xFFF80000 -#define WALNUT_FLASH_SIZE 0x80000 - -static struct mtd_info *flash; - -static struct map_info walnut_map = { - .name = "Walnut flash", - .size = WALNUT_FLASH_SIZE, - .bankwidth = 1, -}; - -/* Actually, OpenBIOS is the last 128 KiB of the flash - better - * partitioning could be made */ -static struct mtd_partition walnut_partitions[] = { - { - .name = "OpenBIOS", - .offset = 0x0, - .size = WALNUT_FLASH_SIZE, - /*.mask_flags = MTD_WRITEABLE, */ /* force read-only */ - } -}; - -int __init init_walnut(void) -{ - u8 fpga_brds1; - void *fpga_brds1_adr; - void *fpga_status_adr; - unsigned long flash_base; - - /* this should already be mapped (platform/4xx/walnut.c) */ - fpga_status_adr = ioremap(WALNUT_FPGA_BASE, 8); - if (!fpga_status_adr) - return -ENOMEM; - - fpga_brds1_adr = fpga_status_adr+5; - fpga_brds1 = readb(fpga_brds1_adr); - /* iounmap(fpga_status_adr); */ - - if (WALNUT_FLASH_ONBD_N(fpga_brds1)) { - printk("The on-board flash is disabled (U79 sw 5)!"); - iounmap(fpga_status_adr); - return -EIO; - } - if (WALNUT_FLASH_SRAM_SEL(fpga_brds1)) - flash_base = WALNUT_FLASH_LOW; - else - flash_base = WALNUT_FLASH_HIGH; - - walnut_map.phys = flash_base; - walnut_map.virt = - (void __iomem *)ioremap(flash_base, walnut_map.size); - - if (!walnut_map.virt) { - printk("Failed to ioremap flash.\n"); - iounmap(fpga_status_adr); - return -EIO; - } - - simple_map_init(&walnut_map); - - flash = do_map_probe("jedec_probe", &walnut_map); - if (flash) { - flash->owner = THIS_MODULE; - add_mtd_partitions(flash, walnut_partitions, - ARRAY_SIZE(walnut_partitions)); - } else { - printk("map probe failed for flash\n"); - iounmap(fpga_status_adr); - return -ENXIO; - } - - iounmap(fpga_status_adr); - return 0; -} - -static void __exit cleanup_walnut(void) -{ - if (flash) { - del_mtd_partitions(flash); - map_destroy(flash); - } - - if (walnut_map.virt) { - iounmap((void *)walnut_map.virt); - walnut_map.virt = 0; - } -} - -module_init(init_walnut); -module_exit(cleanup_walnut); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Heikki Lindholm "); -MODULE_DESCRIPTION("MTD map and partitions for IBM 405GP Walnut boards"); -- cgit v0.10.2 From c8872b069c536976b81bccfc95dda945594bc504 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 2 Aug 2008 17:14:21 +0200 Subject: [MTD] Use DIV_ROUND_UP The kernel.h macro DIV_ROUND_UP performs the computation (((n) + (d) - 1) / (d)) but is perhaps more readable. Signed-off-by: Julia Lawall Signed-off-by: David Woodhouse diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c index 5f1b472..d49cbe2 100644 --- a/drivers/mtd/chips/cfi_cmdset_0001.c +++ b/drivers/mtd/chips/cfi_cmdset_0001.c @@ -1640,7 +1640,7 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip, /* Figure out the number of words to write */ word_gap = (-adr & (map_bankwidth(map)-1)); - words = (len - word_gap + map_bankwidth(map) - 1) / map_bankwidth(map); + words = DIV_ROUND_UP(len - word_gap, map_bankwidth(map)); if (!word_gap) { words--; } else { diff --git a/drivers/mtd/chips/gen_probe.c b/drivers/mtd/chips/gen_probe.c index f061885..e2dc964 100644 --- a/drivers/mtd/chips/gen_probe.c +++ b/drivers/mtd/chips/gen_probe.c @@ -111,7 +111,7 @@ static struct cfi_private *genprobe_ident_chips(struct map_info *map, struct chi max_chips = 1; } - mapsize = sizeof(long) * ( (max_chips + BITS_PER_LONG-1) / BITS_PER_LONG ); + mapsize = sizeof(long) * DIV_ROUND_UP(max_chips, BITS_PER_LONG); chip_map = kzalloc(mapsize, GFP_KERNEL); if (!chip_map) { printk(KERN_WARNING "%s: kmalloc failed for CFI chip map\n", map->name); diff --git a/drivers/mtd/ssfdc.c b/drivers/mtd/ssfdc.c index a5f3d60..33a5d6e 100644 --- a/drivers/mtd/ssfdc.c +++ b/drivers/mtd/ssfdc.c @@ -321,8 +321,7 @@ static void ssfdcr_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd) DEBUG(MTD_DEBUG_LEVEL1, "SSFDC_RO: cis_block=%d,erase_size=%d,map_len=%d,n_zones=%d\n", ssfdc->cis_block, ssfdc->erase_size, ssfdc->map_len, - (ssfdc->map_len + MAX_PHYS_BLK_PER_ZONE - 1) / - MAX_PHYS_BLK_PER_ZONE); + DIV_ROUND_UP(ssfdc->map_len, MAX_PHYS_BLK_PER_ZONE)); /* Set geometry */ ssfdc->heads = 16; -- cgit v0.10.2 From 16e00b609aed439453d57b954b449f647466e0d7 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 4 Aug 2008 11:25:23 +0100 Subject: [MTD] Remove references to TI 'toto' platform. This was a reference board for which support never got merged upstream. Kill it off, at rmk's suggestion. Signed-off-by: David Woodhouse diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig index db667b1..3ae76ec 100644 --- a/drivers/mtd/maps/Kconfig +++ b/drivers/mtd/maps/Kconfig @@ -434,13 +434,6 @@ config MTD_CEIVA PhotoMax Digital Picture Frame. If you have such a device, say 'Y'. -config MTD_NOR_TOTO - tristate "NOR Flash device on TOTO board" - depends on ARCH_OMAP && OMAP_TOTO - help - This enables access to the NOR flash on the Texas Instruments - TOTO board. - config MTD_H720X tristate "Hynix evaluation board mappings" depends on MTD_CFI && ( ARCH_H7201 || ARCH_H7202 ) diff --git a/drivers/mtd/maps/Makefile b/drivers/mtd/maps/Makefile index b258250..6d9ba35 100644 --- a/drivers/mtd/maps/Makefile +++ b/drivers/mtd/maps/Makefile @@ -52,7 +52,6 @@ obj-$(CONFIG_MTD_NETtel) += nettel.o obj-$(CONFIG_MTD_SCB2_FLASH) += scb2_flash.o obj-$(CONFIG_MTD_H720X) += h720x-flash.o obj-$(CONFIG_MTD_SBC8240) += sbc8240.o -obj-$(CONFIG_MTD_NOR_TOTO) += omap-toto-flash.o obj-$(CONFIG_MTD_IXP4XX) += ixp4xx.o obj-$(CONFIG_MTD_IXP2000) += ixp2000.o obj-$(CONFIG_MTD_WRSBC8260) += wr_sbc82xx_flash.o diff --git a/drivers/mtd/maps/omap-toto-flash.c b/drivers/mtd/maps/omap-toto-flash.c deleted file mode 100644 index 0a60ebb..0000000 --- a/drivers/mtd/maps/omap-toto-flash.c +++ /dev/null @@ -1,133 +0,0 @@ -/* - * NOR Flash memory access on TI Toto board - * - * jzhang@ti.com (C) 2003 Texas Instruments. - * - * (C) 2002 MontVista Software, Inc. - */ - -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -#include -#include - - -#ifndef CONFIG_ARCH_OMAP -#error This is for OMAP architecture only -#endif - -//these lines need be moved to a hardware header file -#define OMAP_TOTO_FLASH_BASE 0xd8000000 -#define OMAP_TOTO_FLASH_SIZE 0x80000 - -static struct map_info omap_toto_map_flash = { - .name = "OMAP Toto flash", - .bankwidth = 2, - .virt = (void __iomem *)OMAP_TOTO_FLASH_BASE, -}; - - -static struct mtd_partition toto_flash_partitions[] = { - { - .name = "BootLoader", - .size = 0x00040000, /* hopefully u-boot will stay 128k + 128*/ - .offset = 0, - .mask_flags = MTD_WRITEABLE, /* force read-only */ - }, { - .name = "ReservedSpace", - .size = 0x00030000, - .offset = MTDPART_OFS_APPEND, - //mask_flags: MTD_WRITEABLE, /* force read-only */ - }, { - .name = "EnvArea", /* bottom 64KiB for env vars */ - .size = MTDPART_SIZ_FULL, - .offset = MTDPART_OFS_APPEND, - } -}; - -static struct mtd_partition *parsed_parts; - -static struct mtd_info *flash_mtd; - -static int __init init_flash (void) -{ - - struct mtd_partition *parts; - int nb_parts = 0; - int parsed_nr_parts = 0; - const char *part_type; - - /* - * Static partition definition selection - */ - part_type = "static"; - - parts = toto_flash_partitions; - nb_parts = ARRAY_SIZE(toto_flash_partitions); - omap_toto_map_flash.size = OMAP_TOTO_FLASH_SIZE; - omap_toto_map_flash.phys = virt_to_phys(OMAP_TOTO_FLASH_BASE); - - simple_map_init(&omap_toto_map_flash); - /* - * Now let's probe for the actual flash. Do it here since - * specific machine settings might have been set above. - */ - printk(KERN_NOTICE "OMAP toto flash: probing %d-bit flash bus\n", - omap_toto_map_flash.bankwidth*8); - flash_mtd = do_map_probe("jedec_probe", &omap_toto_map_flash); - if (!flash_mtd) - return -ENXIO; - - if (parsed_nr_parts > 0) { - parts = parsed_parts; - nb_parts = parsed_nr_parts; - } - - if (nb_parts == 0) { - printk(KERN_NOTICE "OMAP toto flash: no partition info available," - "registering whole flash at once\n"); - if (add_mtd_device(flash_mtd)){ - return -ENXIO; - } - } else { - printk(KERN_NOTICE "Using %s partition definition\n", - part_type); - return add_mtd_partitions(flash_mtd, parts, nb_parts); - } - return 0; -} - -int __init omap_toto_mtd_init(void) -{ - int status; - - if (status = init_flash()) { - printk(KERN_ERR "OMAP Toto Flash: unable to init map for toto flash\n"); - } - return status; -} - -static void __exit omap_toto_mtd_cleanup(void) -{ - if (flash_mtd) { - del_mtd_partitions(flash_mtd); - map_destroy(flash_mtd); - kfree(parsed_parts); - } -} - -module_init(omap_toto_mtd_init); -module_exit(omap_toto_mtd_cleanup); - -MODULE_AUTHOR("Jian Zhang"); -MODULE_DESCRIPTION("OMAP Toto board map driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index 02f9cc3..572c842 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -68,12 +68,6 @@ config MTD_NAND_AMS_DELTA help Support for NAND flash on Amstrad E3 (Delta). -config MTD_NAND_TOTO - tristate "NAND Flash device on TOTO board" - depends on ARCH_OMAP && BROKEN - help - Support for NAND flash on Texas Instruments Toto platform. - config MTD_NAND_TS7250 tristate "NAND Flash device on TS-7250 board" depends on MACH_TS72XX diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile index d772581..b55e4c6 100644 --- a/drivers/mtd/nand/Makefile +++ b/drivers/mtd/nand/Makefile @@ -8,7 +8,6 @@ obj-$(CONFIG_MTD_NAND_IDS) += nand_ids.o obj-$(CONFIG_MTD_NAND_CAFE) += cafe_nand.o obj-$(CONFIG_MTD_NAND_SPIA) += spia.o obj-$(CONFIG_MTD_NAND_AMS_DELTA) += ams-delta.o -obj-$(CONFIG_MTD_NAND_TOTO) += toto.o obj-$(CONFIG_MTD_NAND_AUTCPU12) += autcpu12.o obj-$(CONFIG_MTD_NAND_EDB7312) += edb7312.o obj-$(CONFIG_MTD_NAND_AU1550) += au1550nd.o diff --git a/drivers/mtd/nand/toto.c b/drivers/mtd/nand/toto.c deleted file mode 100644 index bbf492e..0000000 --- a/drivers/mtd/nand/toto.c +++ /dev/null @@ -1,206 +0,0 @@ -/* - * drivers/mtd/nand/toto.c - * - * Copyright (c) 2003 Texas Instruments - * - * Derived from drivers/mtd/autcpu12.c - * - * Copyright (c) 2002 Thomas Gleixner - * - * 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. - * - * Overview: - * This is a device driver for the NAND flash device found on the - * TI fido board. It supports 32MiB and 64MiB cards - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define CONFIG_NAND_WORKAROUND 1 - -/* - * MTD structure for TOTO board - */ -static struct mtd_info *toto_mtd = NULL; - -static unsigned long toto_io_base = OMAP_FLASH_1_BASE; - -/* - * Define partitions for flash devices - */ - -static struct mtd_partition partition_info64M[] = { - { .name = "toto kernel partition 1", - .offset = 0, - .size = 2 * SZ_1M }, - { .name = "toto file sys partition 2", - .offset = 2 * SZ_1M, - .size = 14 * SZ_1M }, - { .name = "toto user partition 3", - .offset = 16 * SZ_1M, - .size = 16 * SZ_1M }, - { .name = "toto devboard extra partition 4", - .offset = 32 * SZ_1M, - .size = 32 * SZ_1M }, -}; - -static struct mtd_partition partition_info32M[] = { - { .name = "toto kernel partition 1", - .offset = 0, - .size = 2 * SZ_1M }, - { .name = "toto file sys partition 2", - .offset = 2 * SZ_1M, - .size = 14 * SZ_1M }, - { .name = "toto user partition 3", - .offset = 16 * SZ_1M, - .size = 16 * SZ_1M }, -}; - -#define NUM_PARTITIONS32M 3 -#define NUM_PARTITIONS64M 4 - -/* - * hardware specific access to control-lines - * - * ctrl: - * NAND_NCE: bit 0 -> bit 14 (0x4000) - * NAND_CLE: bit 1 -> bit 12 (0x1000) - * NAND_ALE: bit 2 -> bit 1 (0x0002) - */ -static void toto_hwcontrol(struct mtd_info *mtd, int cmd, - unsigned int ctrl) -{ - struct nand_chip *chip = mtd->priv; - - if (ctrl & NAND_CTRL_CHANGE) { - unsigned long bits; - - /* hopefully enough time for tc make proceding write to clear */ - udelay(1); - - bits = (~ctrl & NAND_NCE) << 14; - bits |= (ctrl & NAND_CLE) << 12; - bits |= (ctrl & NAND_ALE) >> 1; - -#warning Wild guess as gpiosetout() is nowhere defined in the kernel source - tglx - gpiosetout(0x5002, bits); - -#ifdef CONFIG_NAND_WORKAROUND - /* "some" dev boards busted, blue wired to rts2 :( */ - rts2setout(2, (ctrl & NAND_CLE) << 1); -#endif - /* allow time to ensure gpio state to over take memory write */ - udelay(1); - } - - if (cmd != NAND_CMD_NONE) - writeb(cmd, chip->IO_ADDR_W); -} - -/* - * Main initialization routine - */ -static int __init toto_init(void) -{ - struct nand_chip *this; - int err = 0; - - /* Allocate memory for MTD device structure and private data */ - toto_mtd = kmalloc(sizeof(struct mtd_info) + sizeof(struct nand_chip), GFP_KERNEL); - if (!toto_mtd) { - printk(KERN_WARNING "Unable to allocate toto NAND MTD device structure.\n"); - err = -ENOMEM; - goto out; - } - - /* Get pointer to private data */ - this = (struct nand_chip *)(&toto_mtd[1]); - - /* Initialize structures */ - memset(toto_mtd, 0, sizeof(struct mtd_info)); - memset(this, 0, sizeof(struct nand_chip)); - - /* Link the private data with the MTD structure */ - toto_mtd->priv = this; - toto_mtd->owner = THIS_MODULE; - - /* Set address of NAND IO lines */ - this->IO_ADDR_R = toto_io_base; - this->IO_ADDR_W = toto_io_base; - this->cmd_ctrl = toto_hwcontrol; - this->dev_ready = NULL; - /* 25 us command delay time */ - this->chip_delay = 30; - this->ecc.mode = NAND_ECC_SOFT; - - /* Scan to find existance of the device */ - if (nand_scan(toto_mtd, 1)) { - err = -ENXIO; - goto out_mtd; - } - - /* Register the partitions */ - switch (toto_mtd->size) { - case SZ_64M: - add_mtd_partitions(toto_mtd, partition_info64M, NUM_PARTITIONS64M); - break; - case SZ_32M: - add_mtd_partitions(toto_mtd, partition_info32M, NUM_PARTITIONS32M); - break; - default:{ - printk(KERN_WARNING "Unsupported Nand device\n"); - err = -ENXIO; - goto out_buf; - } - } - - gpioreserve(NAND_MASK); /* claim our gpios */ - archflashwp(0, 0); /* open up flash for writing */ - - goto out; - - out_mtd: - kfree(toto_mtd); - out: - return err; -} - -module_init(toto_init); - -/* - * Clean up routine - */ -static void __exit toto_cleanup(void) -{ - /* Release resources, unregister device */ - nand_release(toto_mtd); - - /* Free the MTD device structure */ - kfree(toto_mtd); - - /* stop flash writes */ - archflashwp(0, 1); - - /* release gpios to system */ - gpiorelease(NAND_MASK); -} - -module_exit(toto_cleanup); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Richard Woodruff "); -MODULE_DESCRIPTION("Glue layer for NAND flash on toto board"); -- cgit v0.10.2 From a0e7229edbfef9495e73bc8baea2131a7e69e365 Mon Sep 17 00:00:00 2001 From: "George G. Davis" Date: Mon, 4 Aug 2008 19:43:25 -0400 Subject: [MTD] [NOR] Add "Spansion" to MTD_CFI_AMDSTD kconfig menu description This long overdue trivial change to the MTD_CFI_AMDSTD kconfig menu description is intended to help clarify that this option also supports Spansion flash devices. Signed-off-by: George G. Davis Signed-off-by: David Woodhouse diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig index 4c35e5d..9401bfe 100644 --- a/drivers/mtd/chips/Kconfig +++ b/drivers/mtd/chips/Kconfig @@ -188,7 +188,7 @@ config MTD_CFI_INTELEXT StrataFlash and other parts. config MTD_CFI_AMDSTD - tristate "Support for AMD/Fujitsu flash chips" + tristate "Support for AMD/Fujitsu/Spansion flash chips" depends on MTD_GEN_PROBE select MTD_CFI_UTIL help -- cgit v0.10.2 From 2e489e077a6ad118c4f247faedf330117b107cce Mon Sep 17 00:00:00 2001 From: Alexey Korolev Date: Tue, 5 Aug 2008 16:39:42 +0100 Subject: [MTD] [NOR] Add qry_mode_on()/qry_omde_off() to deal with odd chips There are some CFI chips which require non standard procedures to get into QRY mode. The possible way to support them would be trying different modes till QRY will be read. This patch introduce two new functions qry_mode_on qry_mode_off. qry_mode_on tries different commands in order switch chip into QRY mode. So if we have one more "odd" chip - we just could add several lines to qry_mode_on. Also using these functions remove unnecessary code duplicaton in porbe procedure. Currently there are two "odd" cases 1. Some old intel chips which require 0xFF before 0x98 2. ST M29DW chip which requires 0x98 to be sent at 0x555 (according to CFI should be 0x55) This patch is partialy based on the patch from Uwe (see "[PATCH 2/4] [RFC][MTD] cfi_probe: remove Intel chip workaround" thread ) Signed-off-by: Alexey Korolev Signed-off-by: Alexander Belyakov Signed-off-by: David Woodhouse diff --git a/drivers/mtd/chips/cfi_probe.c b/drivers/mtd/chips/cfi_probe.c index c418e92..e706be2 100644 --- a/drivers/mtd/chips/cfi_probe.c +++ b/drivers/mtd/chips/cfi_probe.c @@ -44,17 +44,14 @@ do { \ #define xip_enable(base, map, cfi) \ do { \ - cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); \ - cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL); \ + qry_mode_off(base, map, cfi); \ xip_allowed(base, map); \ } while (0) #define xip_disable_qry(base, map, cfi) \ do { \ xip_disable(); \ - cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); \ - cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL); \ - cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL); \ + qry_mode_on(base, map, cfi); \ } while (0) #else @@ -70,32 +67,6 @@ do { \ in: interleave,type,mode ret: table index, <0 for error */ -static int __xipram qry_present(struct map_info *map, __u32 base, - struct cfi_private *cfi) -{ - int osf = cfi->interleave * cfi->device_type; // scale factor - map_word val[3]; - map_word qry[3]; - - qry[0] = cfi_build_cmd('Q', map, cfi); - qry[1] = cfi_build_cmd('R', map, cfi); - qry[2] = cfi_build_cmd('Y', map, cfi); - - val[0] = map_read(map, base + osf*0x10); - val[1] = map_read(map, base + osf*0x11); - val[2] = map_read(map, base + osf*0x12); - - if (!map_word_equal(map, qry[0], val[0])) - return 0; - - if (!map_word_equal(map, qry[1], val[1])) - return 0; - - if (!map_word_equal(map, qry[2], val[2])) - return 0; - - return 1; // "QRY" found -} static int __xipram cfi_probe_chip(struct map_info *map, __u32 base, unsigned long *chip_map, struct cfi_private *cfi) @@ -116,11 +87,7 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base, } xip_disable(); - cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); - cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL); - cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL); - - if (!qry_present(map,base,cfi)) { + if (!qry_mode_on(base, map, cfi)) { xip_enable(base, map, cfi); return 0; } @@ -144,8 +111,7 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base, if (qry_present(map, start, cfi)) { /* Eep. This chip also had the QRY marker. * Is it an alias for the new one? */ - cfi_send_gen_cmd(0xF0, 0, start, map, cfi, cfi->device_type, NULL); - cfi_send_gen_cmd(0xFF, 0, start, map, cfi, cfi->device_type, NULL); + qry_mode_off(start, map, cfi); /* If the QRY marker goes away, it's an alias */ if (!qry_present(map, start, cfi)) { @@ -158,8 +124,7 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base, * unfortunate. Stick the new chip in read mode * too and if it's the same, assume it's an alias. */ /* FIXME: Use other modes to do a proper check */ - cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); - cfi_send_gen_cmd(0xFF, 0, start, map, cfi, cfi->device_type, NULL); + qry_mode_off(base, map, cfi); if (qry_present(map, base, cfi)) { xip_allowed(base, map); @@ -176,8 +141,7 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base, cfi->numchips++; /* Put it back into Read Mode */ - cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); - cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL); + qry_mode_off(base, map, cfi); xip_allowed(base, map); printk(KERN_INFO "%s: Found %d x%d devices at 0x%x in %d-bit bank\n", @@ -237,9 +201,7 @@ static int __xipram cfi_chip_setup(struct map_info *map, cfi_read_query(map, base + 0xf * ofs_factor); /* Put it back into Read Mode */ - cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); - /* ... even if it's an Intel chip */ - cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL); + qry_mode_off(base, map, cfi); xip_allowed(base, map); /* Do any necessary byteswapping */ diff --git a/drivers/mtd/chips/cfi_util.c b/drivers/mtd/chips/cfi_util.c index 0ee4570..8d75536 100644 --- a/drivers/mtd/chips/cfi_util.c +++ b/drivers/mtd/chips/cfi_util.c @@ -24,6 +24,62 @@ #include #include +int __xipram qry_present(struct map_info *map, __u32 base, + struct cfi_private *cfi) +{ + int osf = cfi->interleave * cfi->device_type; /* scale factor */ + map_word val[3]; + map_word qry[3]; + + qry[0] = cfi_build_cmd('Q', map, cfi); + qry[1] = cfi_build_cmd('R', map, cfi); + qry[2] = cfi_build_cmd('Y', map, cfi); + + val[0] = map_read(map, base + osf*0x10); + val[1] = map_read(map, base + osf*0x11); + val[2] = map_read(map, base + osf*0x12); + + if (!map_word_equal(map, qry[0], val[0])) + return 0; + + if (!map_word_equal(map, qry[1], val[1])) + return 0; + + if (!map_word_equal(map, qry[2], val[2])) + return 0; + + return 1; /* "QRY" found */ +} + +int __xipram qry_mode_on(uint32_t base, struct map_info *map, + struct cfi_private *cfi) +{ + cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); + cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL); + if (qry_present(map, base, cfi)) + return 1; + /* QRY not found probably we deal with some odd CFI chips */ + /* Some revisions of some old Intel chips? */ + cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); + cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL); + cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL); + if (qry_present(map, base, cfi)) + return 1; + /* ST M29DW chips */ + cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); + cfi_send_gen_cmd(0x98, 0x555, base, map, cfi, cfi->device_type, NULL); + if (qry_present(map, base, cfi)) + return 1; + /* QRY not found */ + return 0; +} +void __xipram qry_mode_off(uint32_t base, struct map_info *map, + struct cfi_private *cfi) +{ + cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); + cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL); +} + struct cfi_extquery * __xipram cfi_read_pri(struct map_info *map, __u16 adr, __u16 size, const char* name) { @@ -48,8 +104,7 @@ __xipram cfi_read_pri(struct map_info *map, __u16 adr, __u16 size, const char* n #endif /* Switch it into Query Mode */ - cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL); - + qry_mode_on(base, map, cfi); /* Read in the Extended Query Table */ for (i=0; idevice_type, NULL); - cfi_send_gen_cmd(0xff, 0, base, map, cfi, cfi->device_type, NULL); + qry_mode_off(base, map, cfi); #ifdef CONFIG_MTD_XIP (void) map_read(map, base); diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index d6fb115..3058917 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -12,6 +12,7 @@ #include #include #include +#include #ifdef CONFIG_MTD_CFI_I1 #define cfi_interleave(cfi) 1 @@ -430,7 +431,6 @@ static inline uint32_t cfi_send_gen_cmd(u_char cmd, uint32_t cmd_addr, uint32_t { map_word val; uint32_t addr = base + cfi_build_cmd_addr(cmd_addr, cfi_interleave(cfi), type); - val = cfi_build_cmd(cmd, map, cfi); if (prev_val) @@ -483,6 +483,13 @@ static inline void cfi_udelay(int us) } } +int __xipram qry_present(struct map_info *map, __u32 base, + struct cfi_private *cfi); +int __xipram qry_mode_on(uint32_t base, struct map_info *map, + struct cfi_private *cfi); +void __xipram qry_mode_off(uint32_t base, struct map_info *map, + struct cfi_private *cfi); + struct cfi_extquery *cfi_read_pri(struct map_info *map, uint16_t adr, uint16_t size, const char* name); struct cfi_fixup { -- cgit v0.10.2 From e93cafe45fd74935e0aca2b79e533f0e3ed9640f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Anders=20Grafstr=C3=B6m?= Date: Tue, 5 Aug 2008 18:37:41 +0200 Subject: [MTD] [NOR] cfi_cmdset_0001: Timeouts for erase, write and unlock operations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Timeouts are currently given by the typical operation time times 8. It works in the general well-behaved case but not when an erase block is failing. For erase operations, it seems that a failing erase block will keep the device state machine in erasing state until the vendor specified maximum timeout period has passed. By this time the driver would have long since timed out, left erasing state and attempted further operations which all fail. This patch implements timeouts using values from the CFI Query structure when available. The patch also sets a longer timeout for locking operations. The current value used for locking/unlocking given by 1000000/HZ microseconds is too short for devices like J3 and J5 Strataflash which have a typical clear lock-bits time of 0.5 seconds. Signed-off-by: Anders Grafström Signed-off-by: David Woodhouse diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c index d49cbe2..5157e3c 100644 --- a/drivers/mtd/chips/cfi_cmdset_0001.c +++ b/drivers/mtd/chips/cfi_cmdset_0001.c @@ -478,6 +478,28 @@ struct mtd_info *cfi_cmdset_0001(struct map_info *map, int primary) else cfi->chips[i].erase_time = 2000000; + if (cfi->cfiq->WordWriteTimeoutTyp && + cfi->cfiq->WordWriteTimeoutMax) + cfi->chips[i].word_write_time_max = + 1<<(cfi->cfiq->WordWriteTimeoutTyp + + cfi->cfiq->WordWriteTimeoutMax); + else + cfi->chips[i].word_write_time_max = 50000 * 8; + + if (cfi->cfiq->BufWriteTimeoutTyp && + cfi->cfiq->BufWriteTimeoutMax) + cfi->chips[i].buffer_write_time_max = + 1<<(cfi->cfiq->BufWriteTimeoutTyp + + cfi->cfiq->BufWriteTimeoutMax); + + if (cfi->cfiq->BlockEraseTimeoutTyp && + cfi->cfiq->BlockEraseTimeoutMax) + cfi->chips[i].erase_time_max = + 1000<<(cfi->cfiq->BlockEraseTimeoutTyp + + cfi->cfiq->BlockEraseTimeoutMax); + else + cfi->chips[i].erase_time_max = 2000000 * 8; + cfi->chips[i].ref_point_counter = 0; init_waitqueue_head(&(cfi->chips[i].wq)); } @@ -1012,7 +1034,7 @@ static void __xipram xip_enable(struct map_info *map, struct flchip *chip, static int __xipram xip_wait_for_operation( struct map_info *map, struct flchip *chip, - unsigned long adr, unsigned int chip_op_time ) + unsigned long adr, unsigned int chip_op_time_max) { struct cfi_private *cfi = map->fldrv_priv; struct cfi_pri_intelext *cfip = cfi->cmdset_priv; @@ -1021,7 +1043,7 @@ static int __xipram xip_wait_for_operation( flstate_t oldstate, newstate; start = xip_currtime(); - usec = chip_op_time * 8; + usec = chip_op_time_max; if (usec == 0) usec = 500000; done = 0; @@ -1131,8 +1153,8 @@ static int __xipram xip_wait_for_operation( #define XIP_INVAL_CACHED_RANGE(map, from, size) \ INVALIDATE_CACHED_RANGE(map, from, size) -#define INVAL_CACHE_AND_WAIT(map, chip, cmd_adr, inval_adr, inval_len, usec) \ - xip_wait_for_operation(map, chip, cmd_adr, usec) +#define INVAL_CACHE_AND_WAIT(map, chip, cmd_adr, inval_adr, inval_len, usec, usec_max) \ + xip_wait_for_operation(map, chip, cmd_adr, usec_max) #else @@ -1144,7 +1166,7 @@ static int __xipram xip_wait_for_operation( static int inval_cache_and_wait_for_operation( struct map_info *map, struct flchip *chip, unsigned long cmd_adr, unsigned long inval_adr, int inval_len, - unsigned int chip_op_time) + unsigned int chip_op_time, unsigned int chip_op_time_max) { struct cfi_private *cfi = map->fldrv_priv; map_word status, status_OK = CMD(0x80); @@ -1156,8 +1178,7 @@ static int inval_cache_and_wait_for_operation( INVALIDATE_CACHED_RANGE(map, inval_adr, inval_len); spin_lock(chip->mutex); - /* set our timeout to 8 times the expected delay */ - timeo = chip_op_time * 8; + timeo = chip_op_time_max; if (!timeo) timeo = 500000; reset_timeo = timeo; @@ -1217,8 +1238,8 @@ static int inval_cache_and_wait_for_operation( #endif -#define WAIT_TIMEOUT(map, chip, adr, udelay) \ - INVAL_CACHE_AND_WAIT(map, chip, adr, 0, 0, udelay); +#define WAIT_TIMEOUT(map, chip, adr, udelay, udelay_max) \ + INVAL_CACHE_AND_WAIT(map, chip, adr, 0, 0, udelay, udelay_max); static int do_point_onechip (struct map_info *map, struct flchip *chip, loff_t adr, size_t len) @@ -1452,7 +1473,8 @@ static int __xipram do_write_oneword(struct map_info *map, struct flchip *chip, ret = INVAL_CACHE_AND_WAIT(map, chip, adr, adr, map_bankwidth(map), - chip->word_write_time); + chip->word_write_time, + chip->word_write_time_max); if (ret) { xip_enable(map, chip, adr); printk(KERN_ERR "%s: word write error (status timeout)\n", map->name); @@ -1623,7 +1645,7 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip, chip->state = FL_WRITING_TO_BUFFER; map_write(map, write_cmd, cmd_adr); - ret = WAIT_TIMEOUT(map, chip, cmd_adr, 0); + ret = WAIT_TIMEOUT(map, chip, cmd_adr, 0, 0); if (ret) { /* Argh. Not ready for write to buffer */ map_word Xstatus = map_read(map, cmd_adr); @@ -1692,7 +1714,8 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip, ret = INVAL_CACHE_AND_WAIT(map, chip, cmd_adr, initial_adr, initial_len, - chip->buffer_write_time); + chip->buffer_write_time, + chip->buffer_write_time_max); if (ret) { map_write(map, CMD(0x70), cmd_adr); chip->state = FL_STATUS; @@ -1827,7 +1850,8 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip, ret = INVAL_CACHE_AND_WAIT(map, chip, adr, adr, len, - chip->erase_time); + chip->erase_time, + chip->erase_time_max); if (ret) { map_write(map, CMD(0x70), adr); chip->state = FL_STATUS; @@ -2006,7 +2030,7 @@ static int __xipram do_xxlock_oneblock(struct map_info *map, struct flchip *chip */ udelay = (!extp || !(extp->FeatureSupport & (1 << 5))) ? 1000000/HZ : 0; - ret = WAIT_TIMEOUT(map, chip, adr, udelay); + ret = WAIT_TIMEOUT(map, chip, adr, udelay, udelay * 100); if (ret) { map_write(map, CMD(0x70), adr); chip->state = FL_STATUS; diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h index 08dd131..d4f38c5 100644 --- a/include/linux/mtd/flashchip.h +++ b/include/linux/mtd/flashchip.h @@ -73,6 +73,10 @@ struct flchip { int buffer_write_time; int erase_time; + int word_write_time_max; + int buffer_write_time_max; + int erase_time_max; + void *priv; }; -- cgit v0.10.2 From cf93ae02600e2c752bf2570085e7970a1c0f2b94 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 6 Aug 2008 13:12:04 -0700 Subject: [MTD] Compile fix for dataflash OTP support > > linux-next-20080805/drivers/mtd/devices/mtd_dataflash.c: In function 'add_dataflash_otp': > > linux-next-20080805/drivers/mtd/devices/mtd_dataflash.c:670: error: too many arguments to function 'otp_setup' Whoops, sorry ... I see what was going on. My bad. Signed-off-by: David Brownell Signed-off-by: David Woodhouse diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c index 17c9b20..9016127 100644 --- a/drivers/mtd/devices/mtd_dataflash.c +++ b/drivers/mtd/devices/mtd_dataflash.c @@ -618,7 +618,7 @@ static char *otp_setup(struct mtd_info *device, char revision) #else -static char *otp_setup(struct mtd_info *device) +static char *otp_setup(struct mtd_info *device, char revision) { return " (OTP)"; } -- cgit v0.10.2 From 8c64038e4c077b2b37c6b27d0c40c77a3ddfaeef Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 6 Aug 2008 21:55:14 -0700 Subject: [MTD] make dataflash write-verify be optional This adds a WRITE_VERIFY Kconfig option to the DataFlash driver, closely mirroring the similar NAND and ONENAND options, giving an option to disable some code that's currently always enabled. Removing this step probably saves a millisecond or so per page when writing data, which will add up quickly since these pages are small (the largest is 1 KiB). It doesn't seem to add a lot in terms of reliability, and wouldn't detect errors which crop up when transferring data to the on-chip SRAM buffer. Signed-off-by: David Brownell Acked-by: Haavard Skinnemoen Acked-by: Andrew Victor Signed-off-by: David Woodhouse diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index 88f4df0..6fde0a2 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -59,6 +59,16 @@ config MTD_DATAFLASH Sometimes DataFlash chips are packaged inside MMC-format cards; at this writing, the MMC stack won't handle those. +config MTD_DATAFLASH_WRITE_VERIFY + bool "Verify DataFlash page writes" + depends on MTD_DATAFLASH + help + This adds an extra check when data is written to the flash. + It may help if you are verifying chip setup (timings etc) on + your board. There is a rare possibility that even though the + device thinks the write was successful, a bit could have been + flipped accidentally due to device wear or something else. + config MTD_DATAFLASH_OTP bool "DataFlash OTP support (Security Register)" depends on MTD_DATAFLASH diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c index 9016127..6dd9aff 100644 --- a/drivers/mtd/devices/mtd_dataflash.c +++ b/drivers/mtd/devices/mtd_dataflash.c @@ -30,12 +30,10 @@ * doesn't (yet) use these for any kind of i/o overlap or prefetching. * * Sometimes DataFlash is packaged in MMC-format cards, although the - * MMC stack can't use SPI (yet), or distinguish between MMC and DataFlash + * MMC stack can't (yet?) distinguish between MMC and DataFlash * protocols during enumeration. */ -#define CONFIG_DATAFLASH_WRITE_VERIFY - /* reads can bypass the buffers */ #define OP_READ_CONTINUOUS 0xE8 #define OP_READ_PAGE 0xD2 @@ -403,7 +401,7 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len, (void) dataflash_waitready(priv->spi); -#ifdef CONFIG_DATAFLASH_WRITE_VERIFY +#ifdef CONFIG_MTD_DATAFLASH_VERIFY_WRITE /* (3) Compare to Buffer1 */ addr = pageaddr << priv->page_offset; @@ -432,7 +430,7 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len, } else status = 0; -#endif /* CONFIG_DATAFLASH_WRITE_VERIFY */ +#endif /* CONFIG_MTD_DATAFLASH_VERIFY_WRITE */ remaining = remaining - writelen; pageaddr++; -- cgit v0.10.2 From c314dfdc358847eef0fc07ec8682e1acc8cadd00 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 7 Aug 2008 11:55:07 +0100 Subject: [MTD] [NOR] Rename and export new cfi_qry_*() functions They need to be exported, so let's give them less generic-sounding names while we're at it. Original export patch, along with the suggestion about the nomenclature, from Stephen Rothwell. Signed-off-by: David Woodhouse diff --git a/drivers/mtd/chips/cfi_probe.c b/drivers/mtd/chips/cfi_probe.c index e706be2..e63e674 100644 --- a/drivers/mtd/chips/cfi_probe.c +++ b/drivers/mtd/chips/cfi_probe.c @@ -44,14 +44,14 @@ do { \ #define xip_enable(base, map, cfi) \ do { \ - qry_mode_off(base, map, cfi); \ + cfi_qry_mode_off(base, map, cfi); \ xip_allowed(base, map); \ } while (0) #define xip_disable_qry(base, map, cfi) \ do { \ xip_disable(); \ - qry_mode_on(base, map, cfi); \ + cfi_qry_mode_on(base, map, cfi); \ } while (0) #else @@ -87,7 +87,7 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base, } xip_disable(); - if (!qry_mode_on(base, map, cfi)) { + if (!cfi_qry_mode_on(base, map, cfi)) { xip_enable(base, map, cfi); return 0; } @@ -108,13 +108,13 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base, start = i << cfi->chipshift; /* This chip should be in read mode if it's one we've already touched. */ - if (qry_present(map, start, cfi)) { + if (cfi_qry_present(map, start, cfi)) { /* Eep. This chip also had the QRY marker. * Is it an alias for the new one? */ - qry_mode_off(start, map, cfi); + cfi_qry_mode_off(start, map, cfi); /* If the QRY marker goes away, it's an alias */ - if (!qry_present(map, start, cfi)) { + if (!cfi_qry_present(map, start, cfi)) { xip_allowed(base, map); printk(KERN_DEBUG "%s: Found an alias at 0x%x for the chip at 0x%lx\n", map->name, base, start); @@ -124,9 +124,9 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base, * unfortunate. Stick the new chip in read mode * too and if it's the same, assume it's an alias. */ /* FIXME: Use other modes to do a proper check */ - qry_mode_off(base, map, cfi); + cfi_qry_mode_off(base, map, cfi); - if (qry_present(map, base, cfi)) { + if (cfi_qry_present(map, base, cfi)) { xip_allowed(base, map); printk(KERN_DEBUG "%s: Found an alias at 0x%x for the chip at 0x%lx\n", map->name, base, start); @@ -141,7 +141,7 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base, cfi->numchips++; /* Put it back into Read Mode */ - qry_mode_off(base, map, cfi); + cfi_qry_mode_off(base, map, cfi); xip_allowed(base, map); printk(KERN_INFO "%s: Found %d x%d devices at 0x%x in %d-bit bank\n", @@ -201,7 +201,7 @@ static int __xipram cfi_chip_setup(struct map_info *map, cfi_read_query(map, base + 0xf * ofs_factor); /* Put it back into Read Mode */ - qry_mode_off(base, map, cfi); + cfi_qry_mode_off(base, map, cfi); xip_allowed(base, map); /* Do any necessary byteswapping */ diff --git a/drivers/mtd/chips/cfi_util.c b/drivers/mtd/chips/cfi_util.c index 8d75536..34d40e2 100644 --- a/drivers/mtd/chips/cfi_util.c +++ b/drivers/mtd/chips/cfi_util.c @@ -24,8 +24,8 @@ #include #include -int __xipram qry_present(struct map_info *map, __u32 base, - struct cfi_private *cfi) +int __xipram cfi_qry_present(struct map_info *map, __u32 base, + struct cfi_private *cfi) { int osf = cfi->interleave * cfi->device_type; /* scale factor */ map_word val[3]; @@ -50,35 +50,39 @@ int __xipram qry_present(struct map_info *map, __u32 base, return 1; /* "QRY" found */ } +EXPORT_SYMBOL_GPL(cfi_qry_present); -int __xipram qry_mode_on(uint32_t base, struct map_info *map, - struct cfi_private *cfi) +int __xipram cfi_qry_mode_on(uint32_t base, struct map_info *map, + struct cfi_private *cfi) { cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL); - if (qry_present(map, base, cfi)) + if (cfi_qry_present(map, base, cfi)) return 1; /* QRY not found probably we deal with some odd CFI chips */ /* Some revisions of some old Intel chips? */ cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL); cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL); - if (qry_present(map, base, cfi)) + if (cfi_qry_present(map, base, cfi)) return 1; /* ST M29DW chips */ cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); cfi_send_gen_cmd(0x98, 0x555, base, map, cfi, cfi->device_type, NULL); - if (qry_present(map, base, cfi)) + if (cfi_qry_present(map, base, cfi)) return 1; /* QRY not found */ return 0; } -void __xipram qry_mode_off(uint32_t base, struct map_info *map, - struct cfi_private *cfi) +EXPORT_SYMBOL_GPL(cfi_qry_mode_on); + +void __xipram cfi_qry_mode_off(uint32_t base, struct map_info *map, + struct cfi_private *cfi) { cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL); } +EXPORT_SYMBOL_GPL(cfi_qry_mode_off); struct cfi_extquery * __xipram cfi_read_pri(struct map_info *map, __u16 adr, __u16 size, const char* name) @@ -104,7 +108,7 @@ __xipram cfi_read_pri(struct map_info *map, __u16 adr, __u16 size, const char* n #endif /* Switch it into Query Mode */ - qry_mode_on(base, map, cfi); + cfi_qry_mode_on(base, map, cfi); /* Read in the Extended Query Table */ for (i=0; i Date: Sun, 10 Aug 2008 18:46:50 +0800 Subject: [MTD] [NAND] drivers/mtd/nand/nandsim.c: remove duplicated #include Removed duplicated include in drivers/mtd/nand/nandsim.c. Signed-off-by: Huang Weiyi Signed-off-by: David Woodhouse diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c index 556e813..ae7c577 100644 --- a/drivers/mtd/nand/nandsim.c +++ b/drivers/mtd/nand/nandsim.c @@ -38,7 +38,6 @@ #include #include #include -#include /* Default simulator parameters values */ #if !defined(CONFIG_NANDSIM_FIRST_ID_BYTE) || \ -- cgit v0.10.2 From faff37508a104e9ec5285d5adecaab7e8dde472a Mon Sep 17 00:00:00 2001 From: Chen Gong Date: Mon, 11 Aug 2008 16:59:13 +0800 Subject: [MTD] m25p80.c erase enhance This patch adds an erase_block command to enhance erase operation Signed-off-by: Chen Gong Signed-off-by: David Woodhouse diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c index b35c333..8fbd1b5 100644 --- a/drivers/mtd/devices/m25p80.c +++ b/drivers/mtd/devices/m25p80.c @@ -39,6 +39,7 @@ #define OPCODE_PP 0x02 /* Page program (up to 256 bytes) */ #define OPCODE_BE_4K 0x20 /* Erase 4KiB block */ #define OPCODE_BE_32K 0x52 /* Erase 32KiB block */ +#define OPCODE_BE 0xc7 /* Erase whole flash block */ #define OPCODE_SE 0xd8 /* Sector erase (usually 64KiB) */ #define OPCODE_RDID 0x9f /* Read JEDEC ID */ @@ -161,6 +162,31 @@ static int wait_till_ready(struct m25p *flash) return 1; } +/* + * Erase the whole flash memory + * + * Returns 0 if successful, non-zero otherwise. + */ +static int erase_block(struct m25p *flash) +{ + DEBUG(MTD_DEBUG_LEVEL3, "%s: %s %dKiB\n", + flash->spi->dev.bus_id, __func__, + flash->mtd.size / 1024); + + /* Wait until finished previous write command. */ + if (wait_till_ready(flash)) + return 1; + + /* Send write enable, then erase commands. */ + write_enable(flash); + + /* Set up command buffer. */ + flash->command[0] = OPCODE_BE; + + spi_write(flash->spi, flash->command, 1); + + return 0; +} /* * Erase one sector of flash memory at offset ``offset'' which is any @@ -229,15 +255,21 @@ static int m25p80_erase(struct mtd_info *mtd, struct erase_info *instr) */ /* now erase those sectors */ - while (len) { - if (erase_sector(flash, addr)) { - instr->state = MTD_ERASE_FAILED; - mutex_unlock(&flash->lock); - return -EIO; - } + if (len == flash->mtd.size && erase_block(flash)) { + instr->state = MTD_ERASE_FAILED; + mutex_unlock(&flash->lock); + return -EIO; + } else { + while (len) { + if (erase_sector(flash, addr)) { + instr->state = MTD_ERASE_FAILED; + mutex_unlock(&flash->lock); + return -EIO; + } - addr += mtd->erasesize; - len -= mtd->erasesize; + addr += mtd->erasesize; + len -= mtd->erasesize; + } } mutex_unlock(&flash->lock); -- cgit v0.10.2 From 75d0ee2202b5740e94e913d8a52f91c6557c4c81 Mon Sep 17 00:00:00 2001 From: Chen Gong Date: Mon, 11 Aug 2008 16:59:14 +0800 Subject: [MTD] m25p80.c code cleanup code cleanup for m25p80.c Signed-off-by: Chen Gong Signed-off-by: David Woodhouse diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c index 8fbd1b5..b2b58c1 100644 --- a/drivers/mtd/devices/m25p80.c +++ b/drivers/mtd/devices/m25p80.c @@ -134,7 +134,7 @@ static inline int write_enable(struct m25p *flash) { u8 code = OPCODE_WREN; - return spi_write_then_read(flash->spi, &code, 1, NULL, 0); + return spi_write(flash->spi, &code, 1); } -- cgit v0.10.2 From d0e8c47c58575b9131e786edb488fd029eba443e Mon Sep 17 00:00:00 2001 From: Chen Gong Date: Mon, 11 Aug 2008 16:59:15 +0800 Subject: [MTD] m25p80.c extended jedec support - add extended device information support - add s25sl128 device support Signed-off-by: Chen Gong Signed-off-by: David Woodhouse diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c index b2b58c1..4d3ae08 100644 --- a/drivers/mtd/devices/m25p80.c +++ b/drivers/mtd/devices/m25p80.c @@ -469,6 +469,7 @@ struct flash_info { * then a two byte device id. */ u32 jedec_id; + u16 ext_id; /* The size listed here is what works with OPCODE_SE, which isn't * necessarily called a "sector" by the vendor. @@ -488,57 +489,59 @@ struct flash_info { static struct flash_info __devinitdata m25p_data [] = { /* Atmel -- some are (confusingly) marketed as "DataFlash" */ - { "at25fs010", 0x1f6601, 32 * 1024, 4, SECT_4K, }, - { "at25fs040", 0x1f6604, 64 * 1024, 8, SECT_4K, }, + { "at25fs010", 0x1f6601, 0, 32 * 1024, 4, SECT_4K, }, + { "at25fs040", 0x1f6604, 0, 64 * 1024, 8, SECT_4K, }, - { "at25df041a", 0x1f4401, 64 * 1024, 8, SECT_4K, }, - { "at25df641", 0x1f4800, 64 * 1024, 128, SECT_4K, }, + { "at25df041a", 0x1f4401, 0, 64 * 1024, 8, SECT_4K, }, + { "at25df641", 0x1f4800, 0, 64 * 1024, 128, SECT_4K, }, - { "at26f004", 0x1f0400, 64 * 1024, 8, SECT_4K, }, - { "at26df081a", 0x1f4501, 64 * 1024, 16, SECT_4K, }, - { "at26df161a", 0x1f4601, 64 * 1024, 32, SECT_4K, }, - { "at26df321", 0x1f4701, 64 * 1024, 64, SECT_4K, }, + { "at26f004", 0x1f0400, 0, 64 * 1024, 8, SECT_4K, }, + { "at26df081a", 0x1f4501, 0, 64 * 1024, 16, SECT_4K, }, + { "at26df161a", 0x1f4601, 0, 64 * 1024, 32, SECT_4K, }, + { "at26df321", 0x1f4701, 0, 64 * 1024, 64, SECT_4K, }, /* Spansion -- single (large) sector size only, at least * for the chips listed here (without boot sectors). */ - { "s25sl004a", 0x010212, 64 * 1024, 8, }, - { "s25sl008a", 0x010213, 64 * 1024, 16, }, - { "s25sl016a", 0x010214, 64 * 1024, 32, }, - { "s25sl032a", 0x010215, 64 * 1024, 64, }, - { "s25sl064a", 0x010216, 64 * 1024, 128, }, + { "s25sl004a", 0x010212, 0, 64 * 1024, 8, }, + { "s25sl008a", 0x010213, 0, 64 * 1024, 16, }, + { "s25sl016a", 0x010214, 0, 64 * 1024, 32, }, + { "s25sl032a", 0x010215, 0, 64 * 1024, 64, }, + { "s25sl064a", 0x010216, 0, 64 * 1024, 128, }, + { "s25sl12800", 0x012018, 0x0300, 256 * 1024, 64, }, + { "s25sl12801", 0x012018, 0x0301, 64 * 1024, 256, }, /* SST -- large erase sizes are "overlays", "sectors" are 4K */ - { "sst25vf040b", 0xbf258d, 64 * 1024, 8, SECT_4K, }, - { "sst25vf080b", 0xbf258e, 64 * 1024, 16, SECT_4K, }, - { "sst25vf016b", 0xbf2541, 64 * 1024, 32, SECT_4K, }, - { "sst25vf032b", 0xbf254a, 64 * 1024, 64, SECT_4K, }, + { "sst25vf040b", 0xbf258d, 0, 64 * 1024, 8, SECT_4K, }, + { "sst25vf080b", 0xbf258e, 0, 64 * 1024, 16, SECT_4K, }, + { "sst25vf016b", 0xbf2541, 0, 64 * 1024, 32, SECT_4K, }, + { "sst25vf032b", 0xbf254a, 0, 64 * 1024, 64, SECT_4K, }, /* ST Microelectronics -- newer production may have feature updates */ - { "m25p05", 0x202010, 32 * 1024, 2, }, - { "m25p10", 0x202011, 32 * 1024, 4, }, - { "m25p20", 0x202012, 64 * 1024, 4, }, - { "m25p40", 0x202013, 64 * 1024, 8, }, - { "m25p80", 0, 64 * 1024, 16, }, - { "m25p16", 0x202015, 64 * 1024, 32, }, - { "m25p32", 0x202016, 64 * 1024, 64, }, - { "m25p64", 0x202017, 64 * 1024, 128, }, - { "m25p128", 0x202018, 256 * 1024, 64, }, - - { "m45pe80", 0x204014, 64 * 1024, 16, }, - { "m45pe16", 0x204015, 64 * 1024, 32, }, - - { "m25pe80", 0x208014, 64 * 1024, 16, }, - { "m25pe16", 0x208015, 64 * 1024, 32, SECT_4K, }, + { "m25p05", 0x202010, 0, 32 * 1024, 2, }, + { "m25p10", 0x202011, 0, 32 * 1024, 4, }, + { "m25p20", 0x202012, 0, 64 * 1024, 4, }, + { "m25p40", 0x202013, 0, 64 * 1024, 8, }, + { "m25p80", 0, 0, 64 * 1024, 16, }, + { "m25p16", 0x202015, 0, 64 * 1024, 32, }, + { "m25p32", 0x202016, 0, 64 * 1024, 64, }, + { "m25p64", 0x202017, 0, 64 * 1024, 128, }, + { "m25p128", 0x202018, 0, 256 * 1024, 64, }, + + { "m45pe80", 0x204014, 0, 64 * 1024, 16, }, + { "m45pe16", 0x204015, 0, 64 * 1024, 32, }, + + { "m25pe80", 0x208014, 0, 64 * 1024, 16, }, + { "m25pe16", 0x208015, 0, 64 * 1024, 32, SECT_4K, }, /* Winbond -- w25x "blocks" are 64K, "sectors" are 4KiB */ - { "w25x10", 0xef3011, 64 * 1024, 2, SECT_4K, }, - { "w25x20", 0xef3012, 64 * 1024, 4, SECT_4K, }, - { "w25x40", 0xef3013, 64 * 1024, 8, SECT_4K, }, - { "w25x80", 0xef3014, 64 * 1024, 16, SECT_4K, }, - { "w25x16", 0xef3015, 64 * 1024, 32, SECT_4K, }, - { "w25x32", 0xef3016, 64 * 1024, 64, SECT_4K, }, - { "w25x64", 0xef3017, 64 * 1024, 128, SECT_4K, }, + { "w25x10", 0xef3011, 0, 64 * 1024, 2, SECT_4K, }, + { "w25x20", 0xef3012, 0, 64 * 1024, 4, SECT_4K, }, + { "w25x40", 0xef3013, 0, 64 * 1024, 8, SECT_4K, }, + { "w25x80", 0xef3014, 0, 64 * 1024, 16, SECT_4K, }, + { "w25x16", 0xef3015, 0, 64 * 1024, 32, SECT_4K, }, + { "w25x32", 0xef3016, 0, 64 * 1024, 64, SECT_4K, }, + { "w25x64", 0xef3017, 0, 64 * 1024, 128, SECT_4K, }, }; static struct flash_info *__devinit jedec_probe(struct spi_device *spi) @@ -547,6 +550,7 @@ static struct flash_info *__devinit jedec_probe(struct spi_device *spi) u8 code = OPCODE_RDID; u8 id[3]; u32 jedec; + u16 ext_jedec; struct flash_info *info; /* JEDEC also defines an optional "extended device information" @@ -565,10 +569,14 @@ static struct flash_info *__devinit jedec_probe(struct spi_device *spi) jedec = jedec << 8; jedec |= id[2]; + ext_jedec = id[3] << 8 | id[4]; + for (tmp = 0, info = m25p_data; tmp < ARRAY_SIZE(m25p_data); tmp++, info++) { if (info->jedec_id == jedec) + if (ext_jedec != 0 && info->ext_id != ext_jedec) + continue; return info; } dev_err(&spi->dev, "unrecognized JEDEC id %06x\n", jedec); -- cgit v0.10.2 From bb0eb217c980d50c45f3e793b4dcc70ab9ee820d Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 12 Aug 2008 12:40:50 +0300 Subject: [MTD] Define and use MTD_FAIL_ADDR_UNKNOWN instead of 0xffffffff Signed-off-by: Adrian Hunter Signed-off-by: David Woodhouse diff --git a/drivers/mtd/mtdconcat.c b/drivers/mtd/mtdconcat.c index 2972a5e..789842d 100644 --- a/drivers/mtd/mtdconcat.c +++ b/drivers/mtd/mtdconcat.c @@ -444,7 +444,7 @@ static int concat_erase(struct mtd_info *mtd, struct erase_info *instr) return -EINVAL; } - instr->fail_addr = 0xffffffff; + instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN; /* make a local copy of instr to avoid modifying the caller's struct */ erase = kmalloc(sizeof (struct erase_info), GFP_KERNEL); @@ -493,7 +493,7 @@ static int concat_erase(struct mtd_info *mtd, struct erase_info *instr) /* sanity check: should never happen since * block alignment has been checked above */ BUG_ON(err == -EINVAL); - if (erase->fail_addr != 0xffffffff) + if (erase->fail_addr != MTD_FAIL_ADDR_UNKNOWN) instr->fail_addr = erase->fail_addr + offset; break; } diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index edb90b5..8e77e36 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -214,7 +214,7 @@ static int part_erase(struct mtd_info *mtd, struct erase_info *instr) instr->addr += part->offset; ret = part->master->erase(part->master, instr); if (ret) { - if (instr->fail_addr != 0xffffffff) + if (instr->fail_addr != MTD_FAIL_ADDR_UNKNOWN) instr->fail_addr -= part->offset; instr->addr -= part->offset; } @@ -226,7 +226,7 @@ void mtd_erase_callback(struct erase_info *instr) if (instr->mtd->erase == part_erase) { struct mtd_part *part = PART(instr->mtd); - if (instr->fail_addr != 0xffffffff) + if (instr->fail_addr != MTD_FAIL_ADDR_UNKNOWN) instr->fail_addr -= part->offset; instr->addr -= part->offset; } diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index d1129ba..5822805 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -2042,7 +2042,7 @@ int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr, return -EINVAL; } - instr->fail_addr = 0xffffffff; + instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN; /* Grab the lock and see if the device is available */ nand_get_device(chip, mtd, FL_ERASING); diff --git a/drivers/mtd/onenand/onenand_base.c b/drivers/mtd/onenand/onenand_base.c index 926cf3a..90ed319 100644 --- a/drivers/mtd/onenand/onenand_base.c +++ b/drivers/mtd/onenand/onenand_base.c @@ -1794,7 +1794,7 @@ static int onenand_erase(struct mtd_info *mtd, struct erase_info *instr) return -EINVAL; } - instr->fail_addr = 0xffffffff; + instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN; /* Grab the lock and see if the device is available */ onenand_get_device(mtd, FL_ERASING); diff --git a/fs/jffs2/erase.c b/fs/jffs2/erase.c index dddb2a6..259461b 100644 --- a/fs/jffs2/erase.c +++ b/fs/jffs2/erase.c @@ -68,7 +68,7 @@ static void jffs2_erase_block(struct jffs2_sb_info *c, instr->len = c->sector_size; instr->callback = jffs2_erase_callback; instr->priv = (unsigned long)(&instr[1]); - instr->fail_addr = 0xffffffff; + instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN; ((struct erase_priv_struct *)instr->priv)->jeb = jeb; ((struct erase_priv_struct *)instr->priv)->c = c; @@ -175,7 +175,7 @@ static void jffs2_erase_failed(struct jffs2_sb_info *c, struct jffs2_eraseblock { /* For NAND, if the failure did not occur at the device level for a specific physical page, don't bother updating the bad block table. */ - if (jffs2_cleanmarker_oob(c) && (bad_offset != 0xffffffff)) { + if (jffs2_cleanmarker_oob(c) && (bad_offset != MTD_FAIL_ADDR_UNKNOWN)) { /* We had a device-level failure to erase. Let's see if we've failed too many times. */ if (!jffs2_write_nand_badblock(c, jeb, bad_offset)) { diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 9226365..eae26bb 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -25,8 +25,10 @@ #define MTD_ERASE_DONE 0x08 #define MTD_ERASE_FAILED 0x10 +#define MTD_FAIL_ADDR_UNKNOWN 0xffffffff + /* If the erase fails, fail_addr might indicate exactly which block failed. If - fail_addr = 0xffffffff, the failure was not at the device level or was not + fail_addr = MTD_FAIL_ADDR_UNKNOWN, the failure was not at the device level or was not specific to any particular block. */ struct erase_info { struct mtd_info *mtd; -- cgit v0.10.2 From 36cd4fb5d277f34fe9e4db0deac2d4efd7dff735 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 6 Aug 2008 10:08:46 +0300 Subject: [MTD] [OneNAND] Add OMAP2 / OMAP3 OneNAND driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This driver had resided in the OMAP tree but is now to be in MTD. Original authors were: Jarkko Lavinen and Juha Yrjölä IRQ and DMA support written by Timo Teras Signed-off-by: Adrian Hunter Signed-off-by: David Woodhouse diff --git a/drivers/mtd/onenand/Kconfig b/drivers/mtd/onenand/Kconfig index b94a61b..79fa79e 100644 --- a/drivers/mtd/onenand/Kconfig +++ b/drivers/mtd/onenand/Kconfig @@ -27,6 +27,13 @@ config MTD_ONENAND_GENERIC help Support for OneNAND flash via platform device driver. +config MTD_ONENAND_OMAP2 + tristate "OneNAND on OMAP2/OMAP3 support" + depends on MTD_ONENAND && (ARCH_OMAP2 || ARCH_OMAP3) + help + Support for a OneNAND flash device connected to an OMAP2/OMAP3 CPU + via the GPMC memory controller. + config MTD_ONENAND_OTP bool "OneNAND OTP Support" select HAVE_MTD_OTP diff --git a/drivers/mtd/onenand/Makefile b/drivers/mtd/onenand/Makefile index 4d2eacf..64b6cc6 100644 --- a/drivers/mtd/onenand/Makefile +++ b/drivers/mtd/onenand/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_MTD_ONENAND) += onenand.o # Board specific. obj-$(CONFIG_MTD_ONENAND_GENERIC) += generic.o +obj-$(CONFIG_MTD_ONENAND_OMAP2) += omap2.o # Simulator obj-$(CONFIG_MTD_ONENAND_SIM) += onenand_sim.o diff --git a/drivers/mtd/onenand/omap2.c b/drivers/mtd/onenand/omap2.c new file mode 100644 index 0000000..40153ac --- /dev/null +++ b/drivers/mtd/onenand/omap2.c @@ -0,0 +1,777 @@ +/* + * linux/drivers/mtd/onenand/omap2.c + * + * OneNAND driver for OMAP2 / OMAP3 + * + * Copyright © 2005-2006 Nokia Corporation + * + * Author: Jarkko Lavinen and Juha Yrjölä + * IRQ and DMA support written by Timo Teras + * + * 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; see the file COPYING. If not, write to the Free Software + * Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include + +#define DRIVER_NAME "omap2-onenand" + +#define ONENAND_IO_SIZE SZ_128K +#define ONENAND_BUFRAM_SIZE (1024 * 5) + +struct omap2_onenand { + struct platform_device *pdev; + int gpmc_cs; + unsigned long phys_base; + int gpio_irq; + struct mtd_info mtd; + struct mtd_partition *parts; + struct onenand_chip onenand; + struct completion irq_done; + struct completion dma_done; + int dma_channel; + int freq; + int (*setup)(void __iomem *base, int freq); +}; + +static void omap2_onenand_dma_cb(int lch, u16 ch_status, void *data) +{ + struct omap2_onenand *c = data; + + complete(&c->dma_done); +} + +static irqreturn_t omap2_onenand_interrupt(int irq, void *dev_id) +{ + struct omap2_onenand *c = dev_id; + + complete(&c->irq_done); + + return IRQ_HANDLED; +} + +static inline unsigned short read_reg(struct omap2_onenand *c, int reg) +{ + return readw(c->onenand.base + reg); +} + +static inline void write_reg(struct omap2_onenand *c, unsigned short value, + int reg) +{ + writew(value, c->onenand.base + reg); +} + +static void wait_err(char *msg, int state, unsigned int ctrl, unsigned int intr) +{ + printk(KERN_ERR "onenand_wait: %s! state %d ctrl 0x%04x intr 0x%04x\n", + msg, state, ctrl, intr); +} + +static void wait_warn(char *msg, int state, unsigned int ctrl, + unsigned int intr) +{ + printk(KERN_WARNING "onenand_wait: %s! state %d ctrl 0x%04x " + "intr 0x%04x\n", msg, state, ctrl, intr); +} + +static int omap2_onenand_wait(struct mtd_info *mtd, int state) +{ + struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd); + unsigned int intr = 0; + unsigned int ctrl; + unsigned long timeout; + u32 syscfg; + + if (state == FL_RESETING) { + int i; + + for (i = 0; i < 20; i++) { + udelay(1); + intr = read_reg(c, ONENAND_REG_INTERRUPT); + if (intr & ONENAND_INT_MASTER) + break; + } + ctrl = read_reg(c, ONENAND_REG_CTRL_STATUS); + if (ctrl & ONENAND_CTRL_ERROR) { + wait_err("controller error", state, ctrl, intr); + return -EIO; + } + if (!(intr & ONENAND_INT_RESET)) { + wait_err("timeout", state, ctrl, intr); + return -EIO; + } + return 0; + } + + if (state != FL_READING) { + int result; + + /* Turn interrupts on */ + syscfg = read_reg(c, ONENAND_REG_SYS_CFG1); + syscfg |= ONENAND_SYS_CFG1_IOBE; + write_reg(c, syscfg, ONENAND_REG_SYS_CFG1); + + INIT_COMPLETION(c->irq_done); + if (c->gpio_irq) { + result = omap_get_gpio_datain(c->gpio_irq); + if (result == -1) { + ctrl = read_reg(c, ONENAND_REG_CTRL_STATUS); + intr = read_reg(c, ONENAND_REG_INTERRUPT); + wait_err("gpio error", state, ctrl, intr); + return -EIO; + } + } else + result = 0; + if (result == 0) { + int retry_cnt = 0; +retry: + result = wait_for_completion_timeout(&c->irq_done, + msecs_to_jiffies(20)); + if (result == 0) { + /* Timeout after 20ms */ + ctrl = read_reg(c, ONENAND_REG_CTRL_STATUS); + if (ctrl & ONENAND_CTRL_ONGO) { + /* + * The operation seems to be still going + * so give it some more time. + */ + retry_cnt += 1; + if (retry_cnt < 3) + goto retry; + intr = read_reg(c, + ONENAND_REG_INTERRUPT); + wait_err("timeout", state, ctrl, intr); + return -EIO; + } + intr = read_reg(c, ONENAND_REG_INTERRUPT); + if ((intr & ONENAND_INT_MASTER) == 0) + wait_warn("timeout", state, ctrl, intr); + } + } + } else { + /* Turn interrupts off */ + syscfg = read_reg(c, ONENAND_REG_SYS_CFG1); + syscfg &= ~ONENAND_SYS_CFG1_IOBE; + write_reg(c, syscfg, ONENAND_REG_SYS_CFG1); + + timeout = jiffies + msecs_to_jiffies(20); + while (time_before(jiffies, timeout)) { + intr = read_reg(c, ONENAND_REG_INTERRUPT); + if (intr & ONENAND_INT_MASTER) + break; + } + } + + intr = read_reg(c, ONENAND_REG_INTERRUPT); + ctrl = read_reg(c, ONENAND_REG_CTRL_STATUS); + + if (intr & ONENAND_INT_READ) { + int ecc = read_reg(c, ONENAND_REG_ECC_STATUS); + + if (ecc) { + unsigned int addr1, addr8; + + addr1 = read_reg(c, ONENAND_REG_START_ADDRESS1); + addr8 = read_reg(c, ONENAND_REG_START_ADDRESS8); + if (ecc & ONENAND_ECC_2BIT_ALL) { + printk(KERN_ERR "onenand_wait: ECC error = " + "0x%04x, addr1 %#x, addr8 %#x\n", + ecc, addr1, addr8); + mtd->ecc_stats.failed++; + return -EBADMSG; + } else if (ecc & ONENAND_ECC_1BIT_ALL) { + printk(KERN_NOTICE "onenand_wait: correctable " + "ECC error = 0x%04x, addr1 %#x, " + "addr8 %#x\n", ecc, addr1, addr8); + mtd->ecc_stats.corrected++; + } + } + } else if (state == FL_READING) { + wait_err("timeout", state, ctrl, intr); + return -EIO; + } + + if (ctrl & ONENAND_CTRL_ERROR) { + wait_err("controller error", state, ctrl, intr); + if (ctrl & ONENAND_CTRL_LOCK) + printk(KERN_ERR "onenand_wait: " + "Device is write protected!!!\n"); + return -EIO; + } + + if (ctrl & 0xFE9F) + wait_warn("unexpected controller status", state, ctrl, intr); + + return 0; +} + +static inline int omap2_onenand_bufferram_offset(struct mtd_info *mtd, int area) +{ + struct onenand_chip *this = mtd->priv; + + if (ONENAND_CURRENT_BUFFERRAM(this)) { + if (area == ONENAND_DATARAM) + return mtd->writesize; + if (area == ONENAND_SPARERAM) + return mtd->oobsize; + } + + return 0; +} + +#if defined(CONFIG_ARCH_OMAP3) || defined(MULTI_OMAP2) + +static int omap3_onenand_read_bufferram(struct mtd_info *mtd, int area, + unsigned char *buffer, int offset, + size_t count) +{ + struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd); + struct onenand_chip *this = mtd->priv; + dma_addr_t dma_src, dma_dst; + int bram_offset; + unsigned long timeout; + void *buf = (void *)buffer; + size_t xtra; + volatile unsigned *done; + + bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset; + if (bram_offset & 3 || (size_t)buf & 3 || count < 384) + goto out_copy; + + if (buf >= high_memory) { + struct page *p1; + + if (((size_t)buf & PAGE_MASK) != + ((size_t)(buf + count - 1) & PAGE_MASK)) + goto out_copy; + p1 = vmalloc_to_page(buf); + if (!p1) + goto out_copy; + buf = page_address(p1) + ((size_t)buf & ~PAGE_MASK); + } + + xtra = count & 3; + if (xtra) { + count -= xtra; + memcpy(buf + count, this->base + bram_offset + count, xtra); + } + + dma_src = c->phys_base + bram_offset; + dma_dst = dma_map_single(&c->pdev->dev, buf, count, DMA_FROM_DEVICE); + if (dma_mapping_error(&c->pdev->dev, dma_dst)) { + dev_err(&c->pdev->dev, + "Couldn't DMA map a %d byte buffer\n", + count); + goto out_copy; + } + + omap_set_dma_transfer_params(c->dma_channel, OMAP_DMA_DATA_TYPE_S32, + count >> 2, 1, 0, 0, 0); + omap_set_dma_src_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC, + dma_src, 0, 0); + omap_set_dma_dest_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC, + dma_dst, 0, 0); + + INIT_COMPLETION(c->dma_done); + omap_start_dma(c->dma_channel); + + timeout = jiffies + msecs_to_jiffies(20); + done = &c->dma_done.done; + while (time_before(jiffies, timeout)) + if (*done) + break; + + dma_unmap_single(&c->pdev->dev, dma_dst, count, DMA_FROM_DEVICE); + + if (!*done) { + dev_err(&c->pdev->dev, "timeout waiting for DMA\n"); + goto out_copy; + } + + return 0; + +out_copy: + memcpy(buf, this->base + bram_offset, count); + return 0; +} + +static int omap3_onenand_write_bufferram(struct mtd_info *mtd, int area, + const unsigned char *buffer, + int offset, size_t count) +{ + struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd); + struct onenand_chip *this = mtd->priv; + dma_addr_t dma_src, dma_dst; + int bram_offset; + unsigned long timeout; + void *buf = (void *)buffer; + volatile unsigned *done; + + bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset; + if (bram_offset & 3 || (size_t)buf & 3 || count < 384) + goto out_copy; + + /* panic_write() may be in an interrupt context */ + if (in_interrupt()) + goto out_copy; + + if (buf >= high_memory) { + struct page *p1; + + if (((size_t)buf & PAGE_MASK) != + ((size_t)(buf + count - 1) & PAGE_MASK)) + goto out_copy; + p1 = vmalloc_to_page(buf); + if (!p1) + goto out_copy; + buf = page_address(p1) + ((size_t)buf & ~PAGE_MASK); + } + + dma_src = dma_map_single(&c->pdev->dev, buf, count, DMA_TO_DEVICE); + dma_dst = c->phys_base + bram_offset; + if (dma_mapping_error(&c->pdev->dev, dma_dst)) { + dev_err(&c->pdev->dev, + "Couldn't DMA map a %d byte buffer\n", + count); + return -1; + } + + omap_set_dma_transfer_params(c->dma_channel, OMAP_DMA_DATA_TYPE_S32, + count >> 2, 1, 0, 0, 0); + omap_set_dma_src_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC, + dma_src, 0, 0); + omap_set_dma_dest_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC, + dma_dst, 0, 0); + + INIT_COMPLETION(c->dma_done); + omap_start_dma(c->dma_channel); + + timeout = jiffies + msecs_to_jiffies(20); + done = &c->dma_done.done; + while (time_before(jiffies, timeout)) + if (*done) + break; + + dma_unmap_single(&c->pdev->dev, dma_dst, count, DMA_TO_DEVICE); + + if (!*done) { + dev_err(&c->pdev->dev, "timeout waiting for DMA\n"); + goto out_copy; + } + + return 0; + +out_copy: + memcpy(this->base + bram_offset, buf, count); + return 0; +} + +#else + +int omap3_onenand_read_bufferram(struct mtd_info *mtd, int area, + unsigned char *buffer, int offset, + size_t count); + +int omap3_onenand_write_bufferram(struct mtd_info *mtd, int area, + const unsigned char *buffer, + int offset, size_t count); + +#endif + +#if defined(CONFIG_ARCH_OMAP2) || defined(MULTI_OMAP2) + +static int omap2_onenand_read_bufferram(struct mtd_info *mtd, int area, + unsigned char *buffer, int offset, + size_t count) +{ + struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd); + struct onenand_chip *this = mtd->priv; + dma_addr_t dma_src, dma_dst; + int bram_offset; + + bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset; + /* DMA is not used. Revisit PM requirements before enabling it. */ + if (1 || (c->dma_channel < 0) || + ((void *) buffer >= (void *) high_memory) || (bram_offset & 3) || + (((unsigned int) buffer) & 3) || (count < 1024) || (count & 3)) { + memcpy(buffer, (__force void *)(this->base + bram_offset), + count); + return 0; + } + + dma_src = c->phys_base + bram_offset; + dma_dst = dma_map_single(&c->pdev->dev, buffer, count, + DMA_FROM_DEVICE); + if (dma_mapping_error(&c->pdev->dev, dma_dst)) { + dev_err(&c->pdev->dev, + "Couldn't DMA map a %d byte buffer\n", + count); + return -1; + } + + omap_set_dma_transfer_params(c->dma_channel, OMAP_DMA_DATA_TYPE_S32, + count / 4, 1, 0, 0, 0); + omap_set_dma_src_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC, + dma_src, 0, 0); + omap_set_dma_dest_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC, + dma_dst, 0, 0); + + INIT_COMPLETION(c->dma_done); + omap_start_dma(c->dma_channel); + wait_for_completion(&c->dma_done); + + dma_unmap_single(&c->pdev->dev, dma_dst, count, DMA_FROM_DEVICE); + + return 0; +} + +static int omap2_onenand_write_bufferram(struct mtd_info *mtd, int area, + const unsigned char *buffer, + int offset, size_t count) +{ + struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd); + struct onenand_chip *this = mtd->priv; + dma_addr_t dma_src, dma_dst; + int bram_offset; + + bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset; + /* DMA is not used. Revisit PM requirements before enabling it. */ + if (1 || (c->dma_channel < 0) || + ((void *) buffer >= (void *) high_memory) || (bram_offset & 3) || + (((unsigned int) buffer) & 3) || (count < 1024) || (count & 3)) { + memcpy((__force void *)(this->base + bram_offset), buffer, + count); + return 0; + } + + dma_src = dma_map_single(&c->pdev->dev, (void *) buffer, count, + DMA_TO_DEVICE); + dma_dst = c->phys_base + bram_offset; + if (dma_mapping_error(&c->pdev->dev, dma_dst)) { + dev_err(&c->pdev->dev, + "Couldn't DMA map a %d byte buffer\n", + count); + return -1; + } + + omap_set_dma_transfer_params(c->dma_channel, OMAP_DMA_DATA_TYPE_S16, + count / 2, 1, 0, 0, 0); + omap_set_dma_src_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC, + dma_src, 0, 0); + omap_set_dma_dest_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC, + dma_dst, 0, 0); + + INIT_COMPLETION(c->dma_done); + omap_start_dma(c->dma_channel); + wait_for_completion(&c->dma_done); + + dma_unmap_single(&c->pdev->dev, dma_dst, count, DMA_TO_DEVICE); + + return 0; +} + +#else + +int omap2_onenand_read_bufferram(struct mtd_info *mtd, int area, + unsigned char *buffer, int offset, + size_t count); + +int omap2_onenand_write_bufferram(struct mtd_info *mtd, int area, + const unsigned char *buffer, + int offset, size_t count); + +#endif + +static struct platform_driver omap2_onenand_driver; + +static int __adjust_timing(struct device *dev, void *data) +{ + int ret = 0; + struct omap2_onenand *c; + + c = dev_get_drvdata(dev); + + BUG_ON(c->setup == NULL); + + /* DMA is not in use so this is all that is needed */ + /* Revisit for OMAP3! */ + ret = c->setup(c->onenand.base, c->freq); + + return ret; +} + +int omap2_onenand_rephase(void) +{ + return driver_for_each_device(&omap2_onenand_driver.driver, NULL, + NULL, __adjust_timing); +} + +static void __devexit omap2_onenand_shutdown(struct platform_device *pdev) +{ + struct omap2_onenand *c = dev_get_drvdata(&pdev->dev); + + /* With certain content in the buffer RAM, the OMAP boot ROM code + * can recognize the flash chip incorrectly. Zero it out before + * soft reset. + */ + memset((__force void *)c->onenand.base, 0, ONENAND_BUFRAM_SIZE); +} + +static int __devinit omap2_onenand_probe(struct platform_device *pdev) +{ + struct omap_onenand_platform_data *pdata; + struct omap2_onenand *c; + int r; + + pdata = pdev->dev.platform_data; + if (pdata == NULL) { + dev_err(&pdev->dev, "platform data missing\n"); + return -ENODEV; + } + + c = kzalloc(sizeof(struct omap2_onenand), GFP_KERNEL); + if (!c) + return -ENOMEM; + + init_completion(&c->irq_done); + init_completion(&c->dma_done); + c->gpmc_cs = pdata->cs; + c->gpio_irq = pdata->gpio_irq; + c->dma_channel = pdata->dma_channel; + if (c->dma_channel < 0) { + /* if -1, don't use DMA */ + c->gpio_irq = 0; + } + + r = gpmc_cs_request(c->gpmc_cs, ONENAND_IO_SIZE, &c->phys_base); + if (r < 0) { + dev_err(&pdev->dev, "Cannot request GPMC CS\n"); + goto err_kfree; + } + + if (request_mem_region(c->phys_base, ONENAND_IO_SIZE, + pdev->dev.driver->name) == NULL) { + dev_err(&pdev->dev, "Cannot reserve memory region at 0x%08lx, " + "size: 0x%x\n", c->phys_base, ONENAND_IO_SIZE); + r = -EBUSY; + goto err_free_cs; + } + c->onenand.base = ioremap(c->phys_base, ONENAND_IO_SIZE); + if (c->onenand.base == NULL) { + r = -ENOMEM; + goto err_release_mem_region; + } + + if (pdata->onenand_setup != NULL) { + r = pdata->onenand_setup(c->onenand.base, c->freq); + if (r < 0) { + dev_err(&pdev->dev, "Onenand platform setup failed: " + "%d\n", r); + goto err_iounmap; + } + c->setup = pdata->onenand_setup; + } + + if (c->gpio_irq) { + if ((r = omap_request_gpio(c->gpio_irq)) < 0) { + dev_err(&pdev->dev, "Failed to request GPIO%d for " + "OneNAND\n", c->gpio_irq); + goto err_iounmap; + } + omap_set_gpio_direction(c->gpio_irq, 1); + + if ((r = request_irq(OMAP_GPIO_IRQ(c->gpio_irq), + omap2_onenand_interrupt, IRQF_TRIGGER_RISING, + pdev->dev.driver->name, c)) < 0) + goto err_release_gpio; + } + + if (c->dma_channel >= 0) { + r = omap_request_dma(0, pdev->dev.driver->name, + omap2_onenand_dma_cb, (void *) c, + &c->dma_channel); + if (r == 0) { + omap_set_dma_write_mode(c->dma_channel, + OMAP_DMA_WRITE_NON_POSTED); + omap_set_dma_src_data_pack(c->dma_channel, 1); + omap_set_dma_src_burst_mode(c->dma_channel, + OMAP_DMA_DATA_BURST_8); + omap_set_dma_dest_data_pack(c->dma_channel, 1); + omap_set_dma_dest_burst_mode(c->dma_channel, + OMAP_DMA_DATA_BURST_8); + } else { + dev_info(&pdev->dev, + "failed to allocate DMA for OneNAND, " + "using PIO instead\n"); + c->dma_channel = -1; + } + } + + dev_info(&pdev->dev, "initializing on CS%d, phys base 0x%08lx, virtual " + "base %p\n", c->gpmc_cs, c->phys_base, + c->onenand.base); + + c->pdev = pdev; + c->mtd.name = pdev->dev.bus_id; + c->mtd.priv = &c->onenand; + c->mtd.owner = THIS_MODULE; + + if (c->dma_channel >= 0) { + struct onenand_chip *this = &c->onenand; + + this->wait = omap2_onenand_wait; + if (cpu_is_omap34xx()) { + this->read_bufferram = omap3_onenand_read_bufferram; + this->write_bufferram = omap3_onenand_write_bufferram; + } else { + this->read_bufferram = omap2_onenand_read_bufferram; + this->write_bufferram = omap2_onenand_write_bufferram; + } + } + + if ((r = onenand_scan(&c->mtd, 1)) < 0) + goto err_release_dma; + + switch ((c->onenand.version_id >> 4) & 0xf) { + case 0: + c->freq = 40; + break; + case 1: + c->freq = 54; + break; + case 2: + c->freq = 66; + break; + case 3: + c->freq = 83; + break; + } + +#ifdef CONFIG_MTD_PARTITIONS + if (pdata->parts != NULL) + r = add_mtd_partitions(&c->mtd, pdata->parts, + pdata->nr_parts); + else +#endif + r = add_mtd_device(&c->mtd); + if (r < 0) + goto err_release_onenand; + + platform_set_drvdata(pdev, c); + + return 0; + +err_release_onenand: + onenand_release(&c->mtd); +err_release_dma: + if (c->dma_channel != -1) + omap_free_dma(c->dma_channel); + if (c->gpio_irq) + free_irq(OMAP_GPIO_IRQ(c->gpio_irq), c); +err_release_gpio: + if (c->gpio_irq) + omap_free_gpio(c->gpio_irq); +err_iounmap: + iounmap(c->onenand.base); +err_release_mem_region: + release_mem_region(c->phys_base, ONENAND_IO_SIZE); +err_free_cs: + gpmc_cs_free(c->gpmc_cs); +err_kfree: + kfree(c); + + return r; +} + +static int __devexit omap2_onenand_remove(struct platform_device *pdev) +{ + struct omap2_onenand *c = dev_get_drvdata(&pdev->dev); + + BUG_ON(c == NULL); + +#ifdef CONFIG_MTD_PARTITIONS + if (c->parts) + del_mtd_partitions(&c->mtd); + else + del_mtd_device(&c->mtd); +#else + del_mtd_device(&c->mtd); +#endif + + onenand_release(&c->mtd); + if (c->dma_channel != -1) + omap_free_dma(c->dma_channel); + omap2_onenand_shutdown(pdev); + platform_set_drvdata(pdev, NULL); + if (c->gpio_irq) { + free_irq(OMAP_GPIO_IRQ(c->gpio_irq), c); + omap_free_gpio(c->gpio_irq); + } + iounmap(c->onenand.base); + release_mem_region(c->phys_base, ONENAND_IO_SIZE); + kfree(c); + + return 0; +} + +static struct platform_driver omap2_onenand_driver = { + .probe = omap2_onenand_probe, + .remove = omap2_onenand_remove, + .shutdown = omap2_onenand_shutdown, + .driver = { + .name = DRIVER_NAME, + .owner = THIS_MODULE, + }, +}; + +static int __init omap2_onenand_init(void) +{ + printk(KERN_INFO "OneNAND driver initializing\n"); + return platform_driver_register(&omap2_onenand_driver); +} + +static void __exit omap2_onenand_exit(void) +{ + platform_driver_unregister(&omap2_onenand_driver); +} + +module_init(omap2_onenand_init); +module_exit(omap2_onenand_exit); + +MODULE_ALIAS(DRIVER_NAME); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jarkko Lavinen "); +MODULE_DESCRIPTION("Glue layer for OneNAND flash on OMAP2 / OMAP3"); diff --git a/include/asm-arm/arch-omap/onenand.h b/include/asm-arm/arch-omap/onenand.h index 6c959d0ce..e302371 100644 --- a/include/asm-arm/arch-omap/onenand.h +++ b/include/asm-arm/arch-omap/onenand.h @@ -16,6 +16,11 @@ struct omap_onenand_platform_data { int gpio_irq; struct mtd_partition *parts; int nr_parts; - int (*onenand_setup)(void __iomem *); + int (*onenand_setup)(void __iomem *, int freq); int dma_channel; }; + +int omap2_onenand_rephase(void); + +#define ONENAND_MAX_PARTITIONS 8 + -- cgit v0.10.2 From bde86fec7c822b6009d3cfefc20b76b8d34716af Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 14 Aug 2008 11:57:45 +0300 Subject: [JFFS2] Correct symlink name too long error code Signed-off-by: Adrian Hunter Signed-off-by: David Woodhouse diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index cd219ef..b1aaae8 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -311,7 +311,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char /* FIXME: If you care. We'd need to use frags for the target if it grows much more than this */ if (targetlen > 254) - return -EINVAL; + return -ENAMETOOLONG; ri = jffs2_alloc_raw_inode(); -- cgit v0.10.2 From 782b7a367d81da005d93b28cb00f9ae086773c24 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 14 Aug 2008 14:00:12 +0300 Subject: [MTD] [OneNAND] OMAP3: add delay for GPIO On OMAP3, the driver was occasionally not seeing the GPIO interrupt. Adding a small delay of one register read eliminates the problem. Signed-off-by: Adrian Hunter Signed-off-by: David Woodhouse diff --git a/drivers/mtd/onenand/omap2.c b/drivers/mtd/onenand/omap2.c index 40153ac..34b4253 100644 --- a/drivers/mtd/onenand/omap2.c +++ b/drivers/mtd/onenand/omap2.c @@ -141,8 +141,13 @@ static int omap2_onenand_wait(struct mtd_info *mtd, int state) /* Turn interrupts on */ syscfg = read_reg(c, ONENAND_REG_SYS_CFG1); - syscfg |= ONENAND_SYS_CFG1_IOBE; - write_reg(c, syscfg, ONENAND_REG_SYS_CFG1); + if (!(syscfg & ONENAND_SYS_CFG1_IOBE)) { + syscfg |= ONENAND_SYS_CFG1_IOBE; + write_reg(c, syscfg, ONENAND_REG_SYS_CFG1); + if (cpu_is_omap34xx()) + /* Add a delay to let GPIO settle */ + syscfg = read_reg(c, ONENAND_REG_SYS_CFG1); + } INIT_COMPLETION(c->irq_done); if (c->gpio_irq) { -- cgit v0.10.2 From e6cf5df1838c28bb060ac45b5585e48e71bbc740 Mon Sep 17 00:00:00 2001 From: frans Date: Fri, 15 Aug 2008 23:14:31 +0200 Subject: [MTD] [NAND] nand_ecc.c: rewrite for improved performance This patch improves the performance of the ecc generation code by a factor of 18 on an INTEL D920 CPU, a factor of 7 on MIPS and a factor of 5 on ARM (NSLU2) Signed-off-by: Frans Meulenbroeks Signed-off-by: David Woodhouse diff --git a/Documentation/mtd/nand_ecc.txt b/Documentation/mtd/nand_ecc.txt new file mode 100644 index 0000000..bdf93b7 --- /dev/null +++ b/Documentation/mtd/nand_ecc.txt @@ -0,0 +1,714 @@ +Introduction +============ + +Having looked at the linux mtd/nand driver and more specific at nand_ecc.c +I felt there was room for optimisation. I bashed the code for a few hours +performing tricks like table lookup removing superfluous code etc. +After that the speed was increased by 35-40%. +Still I was not too happy as I felt there was additional room for improvement. + +Bad! I was hooked. +I decided to annotate my steps in this file. Perhaps it is useful to someone +or someone learns something from it. + + +The problem +=========== + +NAND flash (at least SLC one) typically has sectors of 256 bytes. +However NAND flash is not extremely reliable so some error detection +(and sometimes correction) is needed. + +This is done by means of a Hamming code. I'll try to explain it in +laymans terms (and apologies to all the pro's in the field in case I do +not use the right terminology, my coding theory class was almost 30 +years ago, and I must admit it was not one of my favourites). + +As I said before the ecc calculation is performed on sectors of 256 +bytes. This is done by calculating several parity bits over the rows and +columns. The parity used is even parity which means that the parity bit = 1 +if the data over which the parity is calculated is 1 and the parity bit = 0 +if the data over which the parity is calculated is 0. So the total +number of bits over the data over which the parity is calculated + the +parity bit is even. (see wikipedia if you can't follow this). +Parity is often calculated by means of an exclusive or operation, +sometimes also referred to as xor. In C the operator for xor is ^ + +Back to ecc. +Let's give a small figure: + +byte 0: bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0 rp0 rp2 rp4 ... rp14 +byte 1: bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0 rp1 rp2 rp4 ... rp14 +byte 2: bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0 rp0 rp3 rp4 ... rp14 +byte 3: bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0 rp1 rp3 rp4 ... rp14 +byte 4: bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0 rp0 rp2 rp5 ... rp14 +.... +byte 254: bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0 rp0 rp3 rp5 ... rp15 +byte 255: bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0 rp1 rp3 rp5 ... rp15 + cp1 cp0 cp1 cp0 cp1 cp0 cp1 cp0 + cp3 cp3 cp2 cp2 cp3 cp3 cp2 cp2 + cp5 cp5 cp5 cp5 cp4 cp4 cp4 cp4 + +This figure represents a sector of 256 bytes. +cp is my abbreviaton for column parity, rp for row parity. + +Let's start to explain column parity. +cp0 is the parity that belongs to all bit0, bit2, bit4, bit6. +so the sum of all bit0, bit2, bit4 and bit6 values + cp0 itself is even. +Similarly cp1 is the sum of all bit1, bit3, bit5 and bit7. +cp2 is the parity over bit0, bit1, bit4 and bit5 +cp3 is the parity over bit2, bit3, bit6 and bit7. +cp4 is the parity over bit0, bit1, bit2 and bit3. +cp5 is the parity over bit4, bit5, bit6 and bit7. +Note that each of cp0 .. cp5 is exactly one bit. + +Row parity actually works almost the same. +rp0 is the parity of all even bytes (0, 2, 4, 6, ... 252, 254) +rp1 is the parity of all odd bytes (1, 3, 5, 7, ..., 253, 255) +rp2 is the parity of all bytes 0, 1, 4, 5, 8, 9, ... +(so handle two bytes, then skip 2 bytes). +rp3 is covers the half rp2 does not cover (bytes 2, 3, 6, 7, 10, 11, ...) +for rp4 the rule is cover 4 bytes, skip 4 bytes, cover 4 bytes, skip 4 etc. +so rp4 calculates parity over bytes 0, 1, 2, 3, 8, 9, 10, 11, 16, ...) +and rp5 covers the other half, so bytes 4, 5, 6, 7, 12, 13, 14, 15, 20, .. +The story now becomes quite boring. I guess you get the idea. +rp6 covers 8 bytes then skips 8 etc +rp7 skips 8 bytes then covers 8 etc +rp8 covers 16 bytes then skips 16 etc +rp9 skips 16 bytes then covers 16 etc +rp10 covers 32 bytes then skips 32 etc +rp11 skips 32 bytes then covers 32 etc +rp12 covers 64 bytes then skips 64 etc +rp13 skips 64 bytes then covers 64 etc +rp14 covers 128 bytes then skips 128 +rp15 skips 128 bytes then covers 128 + +In the end the parity bits are grouped together in three bytes as +follows: +ECC Bit 7 Bit 6 Bit 5 Bit 4 Bit 3 Bit 2 Bit 1 Bit 0 +ECC 0 rp07 rp06 rp05 rp04 rp03 rp02 rp01 rp00 +ECC 1 rp15 rp14 rp13 rp12 rp11 rp10 rp09 rp08 +ECC 2 cp5 cp4 cp3 cp2 cp1 cp0 1 1 + +I detected after writing this that ST application note AN1823 +(http://www.st.com/stonline/books/pdf/docs/10123.pdf) gives a much +nicer picture.(but they use line parity as term where I use row parity) +Oh well, I'm graphically challenged, so suffer with me for a moment :-) +And I could not reuse the ST picture anyway for copyright reasons. + + +Attempt 0 +========= + +Implementing the parity calculation is pretty simple. +In C pseudocode: +for (i = 0; i < 256; i++) +{ + if (i & 0x01) + rp1 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp1; + else + rp0 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp1; + if (i & 0x02) + rp3 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp3; + else + rp2 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp2; + if (i & 0x04) + rp5 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp5; + else + rp4 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp4; + if (i & 0x08) + rp7 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp7; + else + rp6 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp6; + if (i & 0x10) + rp9 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp9; + else + rp8 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp8; + if (i & 0x20) + rp11 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp11; + else + rp10 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp10; + if (i & 0x40) + rp13 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp13; + else + rp12 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp12; + if (i & 0x80) + rp15 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp15; + else + rp14 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp14; + cp0 = bit6 ^ bit4 ^ bit2 ^ bit0 ^ cp0; + cp1 = bit7 ^ bit5 ^ bit3 ^ bit1 ^ cp1; + cp2 = bit5 ^ bit4 ^ bit1 ^ bit0 ^ cp2; + cp3 = bit7 ^ bit6 ^ bit3 ^ bit2 ^ cp3 + cp4 = bit3 ^ bit2 ^ bit1 ^ bit0 ^ cp4 + cp5 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ cp5 +} + + +Analysis 0 +========== + +C does have bitwise operators but not really operators to do the above +efficiently (and most hardware has no such instructions either). +Therefore without implementing this it was clear that the code above was +not going to bring me a Nobel prize :-) + +Fortunately the exclusive or operation is commutative, so we can combine +the values in any order. So instead of calculating all the bits +individually, let us try to rearrange things. +For the column parity this is easy. We can just xor the bytes and in the +end filter out the relevant bits. This is pretty nice as it will bring +all cp calculation out of the if loop. + +Similarly we can first xor the bytes for the various rows. +This leads to: + + +Attempt 1 +========= + +const char parity[256] = { + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0 +}; + +void ecc1(const unsigned char *buf, unsigned char *code) +{ + int i; + const unsigned char *bp = buf; + unsigned char cur; + unsigned char rp0, rp1, rp2, rp3, rp4, rp5, rp6, rp7; + unsigned char rp8, rp9, rp10, rp11, rp12, rp13, rp14, rp15; + unsigned char par; + + par = 0; + rp0 = 0; rp1 = 0; rp2 = 0; rp3 = 0; + rp4 = 0; rp5 = 0; rp6 = 0; rp7 = 0; + rp8 = 0; rp9 = 0; rp10 = 0; rp11 = 0; + rp12 = 0; rp13 = 0; rp14 = 0; rp15 = 0; + + for (i = 0; i < 256; i++) + { + cur = *bp++; + par ^= cur; + if (i & 0x01) rp1 ^= cur; else rp0 ^= cur; + if (i & 0x02) rp3 ^= cur; else rp2 ^= cur; + if (i & 0x04) rp5 ^= cur; else rp4 ^= cur; + if (i & 0x08) rp7 ^= cur; else rp6 ^= cur; + if (i & 0x10) rp9 ^= cur; else rp8 ^= cur; + if (i & 0x20) rp11 ^= cur; else rp10 ^= cur; + if (i & 0x40) rp13 ^= cur; else rp12 ^= cur; + if (i & 0x80) rp15 ^= cur; else rp14 ^= cur; + } + code[0] = + (parity[rp7] << 7) | + (parity[rp6] << 6) | + (parity[rp5] << 5) | + (parity[rp4] << 4) | + (parity[rp3] << 3) | + (parity[rp2] << 2) | + (parity[rp1] << 1) | + (parity[rp0]); + code[1] = + (parity[rp15] << 7) | + (parity[rp14] << 6) | + (parity[rp13] << 5) | + (parity[rp12] << 4) | + (parity[rp11] << 3) | + (parity[rp10] << 2) | + (parity[rp9] << 1) | + (parity[rp8]); + code[2] = + (parity[par & 0xf0] << 7) | + (parity[par & 0x0f] << 6) | + (parity[par & 0xcc] << 5) | + (parity[par & 0x33] << 4) | + (parity[par & 0xaa] << 3) | + (parity[par & 0x55] << 2); + code[0] = ~code[0]; + code[1] = ~code[1]; + code[2] = ~code[2]; +} + +Still pretty straightforward. The last three invert statements are there to +give a checksum of 0xff 0xff 0xff for an empty flash. In an empty flash +all data is 0xff, so the checksum then matches. + +I also introduced the parity lookup. I expected this to be the fastest +way to calculate the parity, but I will investigate alternatives later +on. + + +Analysis 1 +========== + +The code works, but is not terribly efficient. On my system it took +almost 4 times as much time as the linux driver code. But hey, if it was +*that* easy this would have been done long before. +No pain. no gain. + +Fortunately there is plenty of room for improvement. + +In step 1 we moved from bit-wise calculation to byte-wise calculation. +However in C we can also use the unsigned long data type and virtually +every modern microprocessor supports 32 bit operations, so why not try +to write our code in such a way that we process data in 32 bit chunks. + +Of course this means some modification as the row parity is byte by +byte. A quick analysis: +for the column parity we use the par variable. When extending to 32 bits +we can in the end easily calculate p0 and p1 from it. +(because par now consists of 4 bytes, contributing to rp1, rp0, rp1, rp0 +respectively) +also rp2 and rp3 can be easily retrieved from par as rp3 covers the +first two bytes and rp2 the last two bytes. + +Note that of course now the loop is executed only 64 times (256/4). +And note that care must taken wrt byte ordering. The way bytes are +ordered in a long is machine dependent, and might affect us. +Anyway, if there is an issue: this code is developed on x86 (to be +precise: a DELL PC with a D920 Intel CPU) + +And of course the performance might depend on alignment, but I expect +that the I/O buffers in the nand driver are aligned properly (and +otherwise that should be fixed to get maximum performance). + +Let's give it a try... + + +Attempt 2 +========= + +extern const char parity[256]; + +void ecc2(const unsigned char *buf, unsigned char *code) +{ + int i; + const unsigned long *bp = (unsigned long *)buf; + unsigned long cur; + unsigned long rp0, rp1, rp2, rp3, rp4, rp5, rp6, rp7; + unsigned long rp8, rp9, rp10, rp11, rp12, rp13, rp14, rp15; + unsigned long par; + + par = 0; + rp0 = 0; rp1 = 0; rp2 = 0; rp3 = 0; + rp4 = 0; rp5 = 0; rp6 = 0; rp7 = 0; + rp8 = 0; rp9 = 0; rp10 = 0; rp11 = 0; + rp12 = 0; rp13 = 0; rp14 = 0; rp15 = 0; + + for (i = 0; i < 64; i++) + { + cur = *bp++; + par ^= cur; + if (i & 0x01) rp5 ^= cur; else rp4 ^= cur; + if (i & 0x02) rp7 ^= cur; else rp6 ^= cur; + if (i & 0x04) rp9 ^= cur; else rp8 ^= cur; + if (i & 0x08) rp11 ^= cur; else rp10 ^= cur; + if (i & 0x10) rp13 ^= cur; else rp12 ^= cur; + if (i & 0x20) rp15 ^= cur; else rp14 ^= cur; + } + /* + we need to adapt the code generation for the fact that rp vars are now + long; also the column parity calculation needs to be changed. + we'll bring rp4 to 15 back to single byte entities by shifting and + xoring + */ + rp4 ^= (rp4 >> 16); rp4 ^= (rp4 >> 8); rp4 &= 0xff; + rp5 ^= (rp5 >> 16); rp5 ^= (rp5 >> 8); rp5 &= 0xff; + rp6 ^= (rp6 >> 16); rp6 ^= (rp6 >> 8); rp6 &= 0xff; + rp7 ^= (rp7 >> 16); rp7 ^= (rp7 >> 8); rp7 &= 0xff; + rp8 ^= (rp8 >> 16); rp8 ^= (rp8 >> 8); rp8 &= 0xff; + rp9 ^= (rp9 >> 16); rp9 ^= (rp9 >> 8); rp9 &= 0xff; + rp10 ^= (rp10 >> 16); rp10 ^= (rp10 >> 8); rp10 &= 0xff; + rp11 ^= (rp11 >> 16); rp11 ^= (rp11 >> 8); rp11 &= 0xff; + rp12 ^= (rp12 >> 16); rp12 ^= (rp12 >> 8); rp12 &= 0xff; + rp13 ^= (rp13 >> 16); rp13 ^= (rp13 >> 8); rp13 &= 0xff; + rp14 ^= (rp14 >> 16); rp14 ^= (rp14 >> 8); rp14 &= 0xff; + rp15 ^= (rp15 >> 16); rp15 ^= (rp15 >> 8); rp15 &= 0xff; + rp3 = (par >> 16); rp3 ^= (rp3 >> 8); rp3 &= 0xff; + rp2 = par & 0xffff; rp2 ^= (rp2 >> 8); rp2 &= 0xff; + par ^= (par >> 16); + rp1 = (par >> 8); rp1 &= 0xff; + rp0 = (par & 0xff); + par ^= (par >> 8); par &= 0xff; + + code[0] = + (parity[rp7] << 7) | + (parity[rp6] << 6) | + (parity[rp5] << 5) | + (parity[rp4] << 4) | + (parity[rp3] << 3) | + (parity[rp2] << 2) | + (parity[rp1] << 1) | + (parity[rp0]); + code[1] = + (parity[rp15] << 7) | + (parity[rp14] << 6) | + (parity[rp13] << 5) | + (parity[rp12] << 4) | + (parity[rp11] << 3) | + (parity[rp10] << 2) | + (parity[rp9] << 1) | + (parity[rp8]); + code[2] = + (parity[par & 0xf0] << 7) | + (parity[par & 0x0f] << 6) | + (parity[par & 0xcc] << 5) | + (parity[par & 0x33] << 4) | + (parity[par & 0xaa] << 3) | + (parity[par & 0x55] << 2); + code[0] = ~code[0]; + code[1] = ~code[1]; + code[2] = ~code[2]; +} + +The parity array is not shown any more. Note also that for these +examples I kinda deviated from my regular programming style by allowing +multiple statements on a line, not using { } in then and else blocks +with only a single statement and by using operators like ^= + + +Analysis 2 +========== + +The code (of course) works, and hurray: we are a little bit faster than +the linux driver code (about 15%). But wait, don't cheer too quickly. +THere is more to be gained. +If we look at e.g. rp14 and rp15 we see that we either xor our data with +rp14 or with rp15. However we also have par which goes over all data. +This means there is no need to calculate rp14 as it can be calculated from +rp15 through rp14 = par ^ rp15; +(or if desired we can avoid calculating rp15 and calculate it from +rp14). That is why some places refer to inverse parity. +Of course the same thing holds for rp4/5, rp6/7, rp8/9, rp10/11 and rp12/13. +Effectively this means we can eliminate the else clause from the if +statements. Also we can optimise the calculation in the end a little bit +by going from long to byte first. Actually we can even avoid the table +lookups + +Attempt 3 +========= + +Odd replaced: + if (i & 0x01) rp5 ^= cur; else rp4 ^= cur; + if (i & 0x02) rp7 ^= cur; else rp6 ^= cur; + if (i & 0x04) rp9 ^= cur; else rp8 ^= cur; + if (i & 0x08) rp11 ^= cur; else rp10 ^= cur; + if (i & 0x10) rp13 ^= cur; else rp12 ^= cur; + if (i & 0x20) rp15 ^= cur; else rp14 ^= cur; +with + if (i & 0x01) rp5 ^= cur; + if (i & 0x02) rp7 ^= cur; + if (i & 0x04) rp9 ^= cur; + if (i & 0x08) rp11 ^= cur; + if (i & 0x10) rp13 ^= cur; + if (i & 0x20) rp15 ^= cur; + + and outside the loop added: + rp4 = par ^ rp5; + rp6 = par ^ rp7; + rp8 = par ^ rp9; + rp10 = par ^ rp11; + rp12 = par ^ rp13; + rp14 = par ^ rp15; + +And after that the code takes about 30% more time, although the number of +statements is reduced. This is also reflected in the assembly code. + + +Analysis 3 +========== + +Very weird. Guess it has to do with caching or instruction parallellism +or so. I also tried on an eeePC (Celeron, clocked at 900 Mhz). Interesting +observation was that this one is only 30% slower (according to time) +executing the code as my 3Ghz D920 processor. + +Well, it was expected not to be easy so maybe instead move to a +different track: let's move back to the code from attempt2 and do some +loop unrolling. This will eliminate a few if statements. I'll try +different amounts of unrolling to see what works best. + + +Attempt 4 +========= + +Unrolled the loop 1, 2, 3 and 4 times. +For 4 the code starts with: + + for (i = 0; i < 4; i++) + { + cur = *bp++; + par ^= cur; + rp4 ^= cur; + rp6 ^= cur; + rp8 ^= cur; + rp10 ^= cur; + if (i & 0x1) rp13 ^= cur; else rp12 ^= cur; + if (i & 0x2) rp15 ^= cur; else rp14 ^= cur; + cur = *bp++; + par ^= cur; + rp5 ^= cur; + rp6 ^= cur; + ... + + +Analysis 4 +========== + +Unrolling once gains about 15% +Unrolling twice keeps the gain at about 15% +Unrolling three times gives a gain of 30% compared to attempt 2. +Unrolling four times gives a marginal improvement compared to unrolling +three times. + +I decided to proceed with a four time unrolled loop anyway. It was my gut +feeling that in the next steps I would obtain additional gain from it. + +The next step was triggered by the fact that par contains the xor of all +bytes and rp4 and rp5 each contain the xor of half of the bytes. +So in effect par = rp4 ^ rp5. But as xor is commutative we can also say +that rp5 = par ^ rp4. So no need to keep both rp4 and rp5 around. We can +eliminate rp5 (or rp4, but I already foresaw another optimisation). +The same holds for rp6/7, rp8/9, rp10/11 rp12/13 and rp14/15. + + +Attempt 5 +========= + +Effectively so all odd digit rp assignments in the loop were removed. +This included the else clause of the if statements. +Of course after the loop we need to correct things by adding code like: + rp5 = par ^ rp4; +Also the initial assignments (rp5 = 0; etc) could be removed. +Along the line I also removed the initialisation of rp0/1/2/3. + + +Analysis 5 +========== + +Measurements showed this was a good move. The run-time roughly halved +compared with attempt 4 with 4 times unrolled, and we only require 1/3rd +of the processor time compared to the current code in the linux kernel. + +However, still I thought there was more. I didn't like all the if +statements. Why not keep a running parity and only keep the last if +statement. Time for yet another version! + + +Attempt 6 +========= + +THe code within the for loop was changed to: + + for (i = 0; i < 4; i++) + { + cur = *bp++; tmppar = cur; rp4 ^= cur; + cur = *bp++; tmppar ^= cur; rp6 ^= tmppar; + cur = *bp++; tmppar ^= cur; rp4 ^= cur; + cur = *bp++; tmppar ^= cur; rp8 ^= tmppar; + + cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur; + cur = *bp++; tmppar ^= cur; rp6 ^= cur; + cur = *bp++; tmppar ^= cur; rp4 ^= cur; + cur = *bp++; tmppar ^= cur; rp10 ^= tmppar; + + cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur; rp8 ^= cur; + cur = *bp++; tmppar ^= cur; rp6 ^= cur; rp8 ^= cur; + cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp8 ^= cur; + cur = *bp++; tmppar ^= cur; rp8 ^= cur; + + cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur; + cur = *bp++; tmppar ^= cur; rp6 ^= cur; + cur = *bp++; tmppar ^= cur; rp4 ^= cur; + cur = *bp++; tmppar ^= cur; + + par ^= tmppar; + if ((i & 0x1) == 0) rp12 ^= tmppar; + if ((i & 0x2) == 0) rp14 ^= tmppar; + } + +As you can see tmppar is used to accumulate the parity within a for +iteration. In the last 3 statements is is added to par and, if needed, +to rp12 and rp14. + +While making the changes I also found that I could exploit that tmppar +contains the running parity for this iteration. So instead of having: +rp4 ^= cur; rp6 = cur; +I removed the rp6 = cur; statement and did rp6 ^= tmppar; on next +statement. A similar change was done for rp8 and rp10 + + +Analysis 6 +========== + +Measuring this code again showed big gain. When executing the original +linux code 1 million times, this took about 1 second on my system. +(using time to measure the performance). After this iteration I was back +to 0.075 sec. Actually I had to decide to start measuring over 10 +million interations in order not to loose too much accuracy. This one +definitely seemed to be the jackpot! + +There is a little bit more room for improvement though. There are three +places with statements: +rp4 ^= cur; rp6 ^= cur; +It seems more efficient to also maintain a variable rp4_6 in the while +loop; This eliminates 3 statements per loop. Of course after the loop we +need to correct by adding: + rp4 ^= rp4_6; + rp6 ^= rp4_6 +Furthermore there are 4 sequential assingments to rp8. This can be +encoded slightly more efficient by saving tmppar before those 4 lines +and later do rp8 = rp8 ^ tmppar ^ notrp8; +(where notrp8 is the value of rp8 before those 4 lines). +Again a use of the commutative property of xor. +Time for a new test! + + +Attempt 7 +========= + +The new code now looks like: + + for (i = 0; i < 4; i++) + { + cur = *bp++; tmppar = cur; rp4 ^= cur; + cur = *bp++; tmppar ^= cur; rp6 ^= tmppar; + cur = *bp++; tmppar ^= cur; rp4 ^= cur; + cur = *bp++; tmppar ^= cur; rp8 ^= tmppar; + + cur = *bp++; tmppar ^= cur; rp4_6 ^= cur; + cur = *bp++; tmppar ^= cur; rp6 ^= cur; + cur = *bp++; tmppar ^= cur; rp4 ^= cur; + cur = *bp++; tmppar ^= cur; rp10 ^= tmppar; + + notrp8 = tmppar; + cur = *bp++; tmppar ^= cur; rp4_6 ^= cur; + cur = *bp++; tmppar ^= cur; rp6 ^= cur; + cur = *bp++; tmppar ^= cur; rp4 ^= cur; + cur = *bp++; tmppar ^= cur; + rp8 = rp8 ^ tmppar ^ notrp8; + + cur = *bp++; tmppar ^= cur; rp4_6 ^= cur; + cur = *bp++; tmppar ^= cur; rp6 ^= cur; + cur = *bp++; tmppar ^= cur; rp4 ^= cur; + cur = *bp++; tmppar ^= cur; + + par ^= tmppar; + if ((i & 0x1) == 0) rp12 ^= tmppar; + if ((i & 0x2) == 0) rp14 ^= tmppar; + } + rp4 ^= rp4_6; + rp6 ^= rp4_6; + + +Not a big change, but every penny counts :-) + + +Analysis 7 +========== + +Acutally this made things worse. Not very much, but I don't want to move +into the wrong direction. Maybe something to investigate later. Could +have to do with caching again. + +Guess that is what there is to win within the loop. Maybe unrolling one +more time will help. I'll keep the optimisations from 7 for now. + + +Attempt 8 +========= + +Unrolled the loop one more time. + + +Analysis 8 +========== + +This makes things worse. Let's stick with attempt 6 and continue from there. +Although it seems that the code within the loop cannot be optimised +further there is still room to optimize the generation of the ecc codes. +We can simply calcualate the total parity. If this is 0 then rp4 = rp5 +etc. If the parity is 1, then rp4 = !rp5; +But if rp4 = rp5 we do not need rp5 etc. We can just write the even bits +in the result byte and then do something like + code[0] |= (code[0] << 1); +Lets test this. + + +Attempt 9 +========= + +Changed the code but again this slightly degrades performance. Tried all +kind of other things, like having dedicated parity arrays to avoid the +shift after parity[rp7] << 7; No gain. +Change the lookup using the parity array by using shift operators (e.g. +replace parity[rp7] << 7 with: +rp7 ^= (rp7 << 4); +rp7 ^= (rp7 << 2); +rp7 ^= (rp7 << 1); +rp7 &= 0x80; +No gain. + +The only marginal change was inverting the parity bits, so we can remove +the last three invert statements. + +Ah well, pity this does not deliver more. Then again 10 million +iterations using the linux driver code takes between 13 and 13.5 +seconds, whereas my code now takes about 0.73 seconds for those 10 +million iterations. So basically I've improved the performance by a +factor 18 on my system. Not that bad. Of course on different hardware +you will get different results. No warranties! + +But of course there is no such thing as a free lunch. The codesize almost +tripled (from 562 bytes to 1434 bytes). Then again, it is not that much. + + +Correcting errors +================= + +For correcting errors I again used the ST application note as a starter, +but I also peeked at the existing code. +The algorithm itself is pretty straightforward. Just xor the given and +the calculated ecc. If all bytes are 0 there is no problem. If 11 bits +are 1 we have one correctable bit error. If there is 1 bit 1, we have an +error in the given ecc code. +It proved to be fastest to do some table lookups. Performance gain +introduced by this is about a factor 2 on my system when a repair had to +be done, and 1% or so if no repair had to be done. +Code size increased from 330 bytes to 686 bytes for this function. +(gcc 4.2, -O3) + + +Conclusion +========== + +The gain when calculating the ecc is tremendous. Om my development hardware +a speedup of a factor of 18 for ecc calculation was achieved. On a test on an +embedded system with a MIPS core a factor 7 was obtained. +On a test with a Linksys NSLU2 (ARMv5TE processor) the speedup was a factor +5 (big endian mode, gcc 4.1.2, -O3) +For correction not much gain could be obtained (as bitflips are rare). Then +again there are also much less cycles spent there. + +It seems there is not much more gain possible in this, at least when +programmed in C. Of course it might be possible to squeeze something more +out of it with an assembler program, but due to pipeline behaviour etc +this is very tricky (at least for intel hw). + +Author: Frans Meulenbroeks +Copyright (C) 2008 Koninklijke Philips Electronics NV. diff --git a/drivers/mtd/nand/nand_ecc.c b/drivers/mtd/nand/nand_ecc.c index 918a806..7129da5 100644 --- a/drivers/mtd/nand/nand_ecc.c +++ b/drivers/mtd/nand/nand_ecc.c @@ -1,13 +1,18 @@ /* - * This file contains an ECC algorithm from Toshiba that detects and - * corrects 1 bit errors in a 256 byte block of data. + * This file contains an ECC algorithm that detects and corrects 1 bit + * errors in a 256 byte block of data. * * drivers/mtd/nand/nand_ecc.c * - * Copyright (C) 2000-2004 Steven J. Hill (sjhill@realitydiluted.com) - * Toshiba America Electronics Components, Inc. + * Copyright (C) 2008 Koninklijke Philips Electronics NV. + * Author: Frans Meulenbroeks * - * Copyright (C) 2006 Thomas Gleixner + * Completely replaces the previous ECC implementation which was written by: + * Steven J. Hill (sjhill@realitydiluted.com) + * Thomas Gleixner (tglx@linutronix.de) + * + * Information on how this algorithm works and how it was developed + * can be found in Documentation/nand/ecc.txt * * This file is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -23,174 +28,417 @@ * with this file; if not, write to the Free Software Foundation, Inc., * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. * - * As a special exception, if other files instantiate templates or use - * macros or inline functions from these files, or you compile these - * files and link them with other works to produce a work based on these - * files, these files do not by themselves cause the resulting work to be - * covered by the GNU General Public License. However the source code for - * these files must still be made available in accordance with section (3) - * of the GNU General Public License. - * - * This exception does not invalidate any other reasons why a work based on - * this file might be covered by the GNU General Public License. */ +/* + * The STANDALONE macro is useful when running the code outside the kernel + * e.g. when running the code in a testbed or a benchmark program. + * When STANDALONE is used, the module related macros are commented out + * as well as the linux include files. + * Instead a private definition of mtd_into is given to satisfy the compiler + * (the code does not use mtd_info, so the code does not care) + */ +#ifndef STANDALONE #include #include #include #include +#else +typedef uint32_t unsigned long +struct mtd_info { + int dummy; +}; +#define EXPORT_SYMBOL(x) /* x */ + +#define MODULE_LICENSE(x) /* x */ +#define MODULE_AUTHOR(x) /* x */ +#define MODULE_DESCRIPTION(x) /* x */ +#endif + +/* + * invparity is a 256 byte table that contains the odd parity + * for each byte. So if the number of bits in a byte is even, + * the array element is 1, and when the number of bits is odd + * the array eleemnt is 0. + */ +static const char invparity[256] = { + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, + 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1 +}; /* - * Pre-calculated 256-way 1 byte column parity + * bitsperbyte contains the number of bits per byte + * this is only used for testing and repairing parity + * (a precalculated value slightly improves performance) */ -static const u_char nand_ecc_precalc_table[] = { - 0x00, 0x55, 0x56, 0x03, 0x59, 0x0c, 0x0f, 0x5a, 0x5a, 0x0f, 0x0c, 0x59, 0x03, 0x56, 0x55, 0x00, - 0x65, 0x30, 0x33, 0x66, 0x3c, 0x69, 0x6a, 0x3f, 0x3f, 0x6a, 0x69, 0x3c, 0x66, 0x33, 0x30, 0x65, - 0x66, 0x33, 0x30, 0x65, 0x3f, 0x6a, 0x69, 0x3c, 0x3c, 0x69, 0x6a, 0x3f, 0x65, 0x30, 0x33, 0x66, - 0x03, 0x56, 0x55, 0x00, 0x5a, 0x0f, 0x0c, 0x59, 0x59, 0x0c, 0x0f, 0x5a, 0x00, 0x55, 0x56, 0x03, - 0x69, 0x3c, 0x3f, 0x6a, 0x30, 0x65, 0x66, 0x33, 0x33, 0x66, 0x65, 0x30, 0x6a, 0x3f, 0x3c, 0x69, - 0x0c, 0x59, 0x5a, 0x0f, 0x55, 0x00, 0x03, 0x56, 0x56, 0x03, 0x00, 0x55, 0x0f, 0x5a, 0x59, 0x0c, - 0x0f, 0x5a, 0x59, 0x0c, 0x56, 0x03, 0x00, 0x55, 0x55, 0x00, 0x03, 0x56, 0x0c, 0x59, 0x5a, 0x0f, - 0x6a, 0x3f, 0x3c, 0x69, 0x33, 0x66, 0x65, 0x30, 0x30, 0x65, 0x66, 0x33, 0x69, 0x3c, 0x3f, 0x6a, - 0x6a, 0x3f, 0x3c, 0x69, 0x33, 0x66, 0x65, 0x30, 0x30, 0x65, 0x66, 0x33, 0x69, 0x3c, 0x3f, 0x6a, - 0x0f, 0x5a, 0x59, 0x0c, 0x56, 0x03, 0x00, 0x55, 0x55, 0x00, 0x03, 0x56, 0x0c, 0x59, 0x5a, 0x0f, - 0x0c, 0x59, 0x5a, 0x0f, 0x55, 0x00, 0x03, 0x56, 0x56, 0x03, 0x00, 0x55, 0x0f, 0x5a, 0x59, 0x0c, - 0x69, 0x3c, 0x3f, 0x6a, 0x30, 0x65, 0x66, 0x33, 0x33, 0x66, 0x65, 0x30, 0x6a, 0x3f, 0x3c, 0x69, - 0x03, 0x56, 0x55, 0x00, 0x5a, 0x0f, 0x0c, 0x59, 0x59, 0x0c, 0x0f, 0x5a, 0x00, 0x55, 0x56, 0x03, - 0x66, 0x33, 0x30, 0x65, 0x3f, 0x6a, 0x69, 0x3c, 0x3c, 0x69, 0x6a, 0x3f, 0x65, 0x30, 0x33, 0x66, - 0x65, 0x30, 0x33, 0x66, 0x3c, 0x69, 0x6a, 0x3f, 0x3f, 0x6a, 0x69, 0x3c, 0x66, 0x33, 0x30, 0x65, - 0x00, 0x55, 0x56, 0x03, 0x59, 0x0c, 0x0f, 0x5a, 0x5a, 0x0f, 0x0c, 0x59, 0x03, 0x56, 0x55, 0x00 +static const char bitsperbyte[256] = { + 0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4, + 1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5, + 1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5, + 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, + 1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5, + 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, + 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, + 3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7, + 1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5, + 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, + 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, + 3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7, + 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, + 3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7, + 3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7, + 4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8, +}; + +/* + * addressbits is a lookup table to filter out the bits from the xor-ed + * ecc data that identify the faulty location. + * this is only used for repairing parity + * see the comments in nand_correct_data for more details + */ +static const char addressbits[256] = { + 0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01, + 0x02, 0x02, 0x03, 0x03, 0x02, 0x02, 0x03, 0x03, + 0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01, + 0x02, 0x02, 0x03, 0x03, 0x02, 0x02, 0x03, 0x03, + 0x04, 0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x05, + 0x06, 0x06, 0x07, 0x07, 0x06, 0x06, 0x07, 0x07, + 0x04, 0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x05, + 0x06, 0x06, 0x07, 0x07, 0x06, 0x06, 0x07, 0x07, + 0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01, + 0x02, 0x02, 0x03, 0x03, 0x02, 0x02, 0x03, 0x03, + 0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01, + 0x02, 0x02, 0x03, 0x03, 0x02, 0x02, 0x03, 0x03, + 0x04, 0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x05, + 0x06, 0x06, 0x07, 0x07, 0x06, 0x06, 0x07, 0x07, + 0x04, 0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x05, + 0x06, 0x06, 0x07, 0x07, 0x06, 0x06, 0x07, 0x07, + 0x08, 0x08, 0x09, 0x09, 0x08, 0x08, 0x09, 0x09, + 0x0a, 0x0a, 0x0b, 0x0b, 0x0a, 0x0a, 0x0b, 0x0b, + 0x08, 0x08, 0x09, 0x09, 0x08, 0x08, 0x09, 0x09, + 0x0a, 0x0a, 0x0b, 0x0b, 0x0a, 0x0a, 0x0b, 0x0b, + 0x0c, 0x0c, 0x0d, 0x0d, 0x0c, 0x0c, 0x0d, 0x0d, + 0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f, + 0x0c, 0x0c, 0x0d, 0x0d, 0x0c, 0x0c, 0x0d, 0x0d, + 0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f, + 0x08, 0x08, 0x09, 0x09, 0x08, 0x08, 0x09, 0x09, + 0x0a, 0x0a, 0x0b, 0x0b, 0x0a, 0x0a, 0x0b, 0x0b, + 0x08, 0x08, 0x09, 0x09, 0x08, 0x08, 0x09, 0x09, + 0x0a, 0x0a, 0x0b, 0x0b, 0x0a, 0x0a, 0x0b, 0x0b, + 0x0c, 0x0c, 0x0d, 0x0d, 0x0c, 0x0c, 0x0d, 0x0d, + 0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f, + 0x0c, 0x0c, 0x0d, 0x0d, 0x0c, 0x0c, 0x0d, 0x0d, + 0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f }; /** * nand_calculate_ecc - [NAND Interface] Calculate 3-byte ECC for 256-byte block - * @mtd: MTD block structure + * @mtd: MTD block structure (unused) * @dat: raw data * @ecc_code: buffer for ECC */ -int nand_calculate_ecc(struct mtd_info *mtd, const u_char *dat, - u_char *ecc_code) +int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf, + unsigned char *code) { - uint8_t idx, reg1, reg2, reg3, tmp1, tmp2; int i; + const uint32_t *bp = (uint32_t *)buf; + uint32_t cur; /* current value in buffer */ + /* rp0..rp15 are the various accumulated parities (per byte) */ + uint32_t rp0, rp1, rp2, rp3, rp4, rp5, rp6, rp7; + uint32_t rp8, rp9, rp10, rp11, rp12, rp13, rp14, rp15; + uint32_t par; /* the cumulative parity for all data */ + uint32_t tmppar; /* the cumulative parity for this iteration; + for rp12 and rp14 at the end of the loop */ + + par = 0; + rp4 = 0; + rp6 = 0; + rp8 = 0; + rp10 = 0; + rp12 = 0; + rp14 = 0; + + /* + * The loop is unrolled a number of times; + * This avoids if statements to decide on which rp value to update + * Also we process the data by longwords. + * Note: passing unaligned data might give a performance penalty. + * It is assumed that the buffers are aligned. + * tmppar is the cumulative sum of this iteration. + * needed for calculating rp12, rp14 and par + * also used as a performance improvement for rp6, rp8 and rp10 + */ + for (i = 0; i < 4; i++) { + cur = *bp++; + tmppar = cur; + rp4 ^= cur; + cur = *bp++; + tmppar ^= cur; + rp6 ^= tmppar; + cur = *bp++; + tmppar ^= cur; + rp4 ^= cur; + cur = *bp++; + tmppar ^= cur; + rp8 ^= tmppar; - /* Initialize variables */ - reg1 = reg2 = reg3 = 0; + cur = *bp++; + tmppar ^= cur; + rp4 ^= cur; + rp6 ^= cur; + cur = *bp++; + tmppar ^= cur; + rp6 ^= cur; + cur = *bp++; + tmppar ^= cur; + rp4 ^= cur; + cur = *bp++; + tmppar ^= cur; + rp10 ^= tmppar; - /* Build up column parity */ - for(i = 0; i < 256; i++) { - /* Get CP0 - CP5 from table */ - idx = nand_ecc_precalc_table[*dat++]; - reg1 ^= (idx & 0x3f); + cur = *bp++; + tmppar ^= cur; + rp4 ^= cur; + rp6 ^= cur; + rp8 ^= cur; + cur = *bp++; + tmppar ^= cur; + rp6 ^= cur; + rp8 ^= cur; + cur = *bp++; + tmppar ^= cur; + rp4 ^= cur; + rp8 ^= cur; + cur = *bp++; + tmppar ^= cur; + rp8 ^= cur; - /* All bit XOR = 1 ? */ - if (idx & 0x40) { - reg3 ^= (uint8_t) i; - reg2 ^= ~((uint8_t) i); - } + cur = *bp++; + tmppar ^= cur; + rp4 ^= cur; + rp6 ^= cur; + cur = *bp++; + tmppar ^= cur; + rp6 ^= cur; + cur = *bp++; + tmppar ^= cur; + rp4 ^= cur; + cur = *bp++; + tmppar ^= cur; + + par ^= tmppar; + if ((i & 0x1) == 0) + rp12 ^= tmppar; + if ((i & 0x2) == 0) + rp14 ^= tmppar; } - /* Create non-inverted ECC code from line parity */ - tmp1 = (reg3 & 0x80) >> 0; /* B7 -> B7 */ - tmp1 |= (reg2 & 0x80) >> 1; /* B7 -> B6 */ - tmp1 |= (reg3 & 0x40) >> 1; /* B6 -> B5 */ - tmp1 |= (reg2 & 0x40) >> 2; /* B6 -> B4 */ - tmp1 |= (reg3 & 0x20) >> 2; /* B5 -> B3 */ - tmp1 |= (reg2 & 0x20) >> 3; /* B5 -> B2 */ - tmp1 |= (reg3 & 0x10) >> 3; /* B4 -> B1 */ - tmp1 |= (reg2 & 0x10) >> 4; /* B4 -> B0 */ - - tmp2 = (reg3 & 0x08) << 4; /* B3 -> B7 */ - tmp2 |= (reg2 & 0x08) << 3; /* B3 -> B6 */ - tmp2 |= (reg3 & 0x04) << 3; /* B2 -> B5 */ - tmp2 |= (reg2 & 0x04) << 2; /* B2 -> B4 */ - tmp2 |= (reg3 & 0x02) << 2; /* B1 -> B3 */ - tmp2 |= (reg2 & 0x02) << 1; /* B1 -> B2 */ - tmp2 |= (reg3 & 0x01) << 1; /* B0 -> B1 */ - tmp2 |= (reg2 & 0x01) << 0; /* B7 -> B0 */ - - /* Calculate final ECC code */ + /* + * handle the fact that we use longword operations + * we'll bring rp4..rp14 back to single byte entities by shifting and + * xoring first fold the upper and lower 16 bits, + * then the upper and lower 8 bits. + */ + rp4 ^= (rp4 >> 16); + rp4 ^= (rp4 >> 8); + rp4 &= 0xff; + rp6 ^= (rp6 >> 16); + rp6 ^= (rp6 >> 8); + rp6 &= 0xff; + rp8 ^= (rp8 >> 16); + rp8 ^= (rp8 >> 8); + rp8 &= 0xff; + rp10 ^= (rp10 >> 16); + rp10 ^= (rp10 >> 8); + rp10 &= 0xff; + rp12 ^= (rp12 >> 16); + rp12 ^= (rp12 >> 8); + rp12 &= 0xff; + rp14 ^= (rp14 >> 16); + rp14 ^= (rp14 >> 8); + rp14 &= 0xff; + + /* + * we also need to calculate the row parity for rp0..rp3 + * This is present in par, because par is now + * rp3 rp3 rp2 rp2 + * as well as + * rp1 rp0 rp1 rp0 + * First calculate rp2 and rp3 + * (and yes: rp2 = (par ^ rp3) & 0xff; but doing that did not + * give a performance improvement) + */ + rp3 = (par >> 16); + rp3 ^= (rp3 >> 8); + rp3 &= 0xff; + rp2 = par & 0xffff; + rp2 ^= (rp2 >> 8); + rp2 &= 0xff; + + /* reduce par to 16 bits then calculate rp1 and rp0 */ + par ^= (par >> 16); + rp1 = (par >> 8) & 0xff; + rp0 = (par & 0xff); + + /* finally reduce par to 8 bits */ + par ^= (par >> 8); + par &= 0xff; + + /* + * and calculate rp5..rp15 + * note that par = rp4 ^ rp5 and due to the commutative property + * of the ^ operator we can say: + * rp5 = (par ^ rp4); + * The & 0xff seems superfluous, but benchmarking learned that + * leaving it out gives slightly worse results. No idea why, probably + * it has to do with the way the pipeline in pentium is organized. + */ + rp5 = (par ^ rp4) & 0xff; + rp7 = (par ^ rp6) & 0xff; + rp9 = (par ^ rp8) & 0xff; + rp11 = (par ^ rp10) & 0xff; + rp13 = (par ^ rp12) & 0xff; + rp15 = (par ^ rp14) & 0xff; + + /* + * Finally calculate the ecc bits. + * Again here it might seem that there are performance optimisations + * possible, but benchmarks showed that on the system this is developed + * the code below is the fastest + */ #ifdef CONFIG_MTD_NAND_ECC_SMC - ecc_code[0] = ~tmp2; - ecc_code[1] = ~tmp1; + code[0] = + (invparity[rp7] << 7) | + (invparity[rp6] << 6) | + (invparity[rp5] << 5) | + (invparity[rp4] << 4) | + (invparity[rp3] << 3) | + (invparity[rp2] << 2) | + (invparity[rp1] << 1) | + (invparity[rp0]); + code[1] = + (invparity[rp15] << 7) | + (invparity[rp14] << 6) | + (invparity[rp13] << 5) | + (invparity[rp12] << 4) | + (invparity[rp11] << 3) | + (invparity[rp10] << 2) | + (invparity[rp9] << 1) | + (invparity[rp8]); #else - ecc_code[0] = ~tmp1; - ecc_code[1] = ~tmp2; + code[1] = + (invparity[rp7] << 7) | + (invparity[rp6] << 6) | + (invparity[rp5] << 5) | + (invparity[rp4] << 4) | + (invparity[rp3] << 3) | + (invparity[rp2] << 2) | + (invparity[rp1] << 1) | + (invparity[rp0]); + code[0] = + (invparity[rp15] << 7) | + (invparity[rp14] << 6) | + (invparity[rp13] << 5) | + (invparity[rp12] << 4) | + (invparity[rp11] << 3) | + (invparity[rp10] << 2) | + (invparity[rp9] << 1) | + (invparity[rp8]); #endif - ecc_code[2] = ((~reg1) << 2) | 0x03; - + code[2] = + (invparity[par & 0xf0] << 7) | + (invparity[par & 0x0f] << 6) | + (invparity[par & 0xcc] << 5) | + (invparity[par & 0x33] << 4) | + (invparity[par & 0xaa] << 3) | + (invparity[par & 0x55] << 2) | + 3; return 0; } EXPORT_SYMBOL(nand_calculate_ecc); -static inline int countbits(uint32_t byte) -{ - int res = 0; - - for (;byte; byte >>= 1) - res += byte & 0x01; - return res; -} - /** * nand_correct_data - [NAND Interface] Detect and correct bit error(s) - * @mtd: MTD block structure + * @mtd: MTD block structure (unused) * @dat: raw data read from the chip * @read_ecc: ECC from the chip * @calc_ecc: the ECC calculated from raw data * * Detect and correct a 1 bit error for 256 byte block */ -int nand_correct_data(struct mtd_info *mtd, u_char *dat, - u_char *read_ecc, u_char *calc_ecc) +int nand_correct_data(struct mtd_info *mtd, unsigned char *buf, + unsigned char *read_ecc, unsigned char *calc_ecc) { - uint8_t s0, s1, s2; + int nr_bits; + unsigned char b0, b1, b2; + unsigned char byte_addr, bit_addr; + /* + * b0 to b2 indicate which bit is faulty (if any) + * we might need the xor result more than once, + * so keep them in a local var + */ #ifdef CONFIG_MTD_NAND_ECC_SMC - s0 = calc_ecc[0] ^ read_ecc[0]; - s1 = calc_ecc[1] ^ read_ecc[1]; - s2 = calc_ecc[2] ^ read_ecc[2]; + b0 = read_ecc[0] ^ calc_ecc[0]; + b1 = read_ecc[1] ^ calc_ecc[1]; #else - s1 = calc_ecc[0] ^ read_ecc[0]; - s0 = calc_ecc[1] ^ read_ecc[1]; - s2 = calc_ecc[2] ^ read_ecc[2]; + b0 = read_ecc[1] ^ calc_ecc[1]; + b1 = read_ecc[0] ^ calc_ecc[0]; #endif - if ((s0 | s1 | s2) == 0) - return 0; - - /* Check for a single bit error */ - if( ((s0 ^ (s0 >> 1)) & 0x55) == 0x55 && - ((s1 ^ (s1 >> 1)) & 0x55) == 0x55 && - ((s2 ^ (s2 >> 1)) & 0x54) == 0x54) { - - uint32_t byteoffs, bitnum; + b2 = read_ecc[2] ^ calc_ecc[2]; - byteoffs = (s1 << 0) & 0x80; - byteoffs |= (s1 << 1) & 0x40; - byteoffs |= (s1 << 2) & 0x20; - byteoffs |= (s1 << 3) & 0x10; + /* check if there are any bitfaults */ - byteoffs |= (s0 >> 4) & 0x08; - byteoffs |= (s0 >> 3) & 0x04; - byteoffs |= (s0 >> 2) & 0x02; - byteoffs |= (s0 >> 1) & 0x01; + /* count nr of bits; use table lookup, faster than calculating it */ + nr_bits = bitsperbyte[b0] + bitsperbyte[b1] + bitsperbyte[b2]; - bitnum = (s2 >> 5) & 0x04; - bitnum |= (s2 >> 4) & 0x02; - bitnum |= (s2 >> 3) & 0x01; - - dat[byteoffs] ^= (1 << bitnum); - - return 1; + /* repeated if statements are slightly more efficient than switch ... */ + /* ordered in order of likelihood */ + if (nr_bits == 0) + return (0); /* no error */ + if (nr_bits == 11) { /* correctable error */ + /* + * rp15/13/11/9/7/5/3/1 indicate which byte is the faulty byte + * cp 5/3/1 indicate the faulty bit. + * A lookup table (called addressbits) is used to filter + * the bits from the byte they are in. + * A marginal optimisation is possible by having three + * different lookup tables. + * One as we have now (for b0), one for b2 + * (that would avoid the >> 1), and one for b1 (with all values + * << 4). However it was felt that introducing two more tables + * hardly justify the gain. + * + * The b2 shift is there to get rid of the lowest two bits. + * We could also do addressbits[b2] >> 1 but for the + * performace it does not make any difference + */ + byte_addr = (addressbits[b1] << 4) + addressbits[b0]; + bit_addr = addressbits[b2 >> 2]; + /* flip the bit */ + buf[byte_addr] ^= (1 << bit_addr); + return (1); } - - if(countbits(s0 | ((uint32_t)s1 << 8) | ((uint32_t)s2 <<16)) == 1) - return 1; - - return -EBADMSG; + if (nr_bits == 1) + return (1); /* error in ecc data; no action needed */ + return -1; } EXPORT_SYMBOL(nand_correct_data); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Steven J. Hill "); +MODULE_AUTHOR("Frans Meulenbroeks "); MODULE_DESCRIPTION("Generic NAND ECC support"); -- cgit v0.10.2 From ccbcd6cba5ef6e071deb072188ad044921f6b91e Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 16 Aug 2008 11:01:31 +0100 Subject: [MTD] [NAND] Minor cleanup of nand_ecc.c Make the standalone stuff a little cleaner, fix some checkpatch warnings. Signed-off-by: David Woodhouse diff --git a/drivers/mtd/nand/nand_ecc.c b/drivers/mtd/nand/nand_ecc.c index 7129da5..a8e8413 100644 --- a/drivers/mtd/nand/nand_ecc.c +++ b/drivers/mtd/nand/nand_ecc.c @@ -4,15 +4,15 @@ * * drivers/mtd/nand/nand_ecc.c * - * Copyright (C) 2008 Koninklijke Philips Electronics NV. - * Author: Frans Meulenbroeks + * Copyright © 2008 Koninklijke Philips Electronics NV. + * Author: Frans Meulenbroeks * * Completely replaces the previous ECC implementation which was written by: * Steven J. Hill (sjhill@realitydiluted.com) * Thomas Gleixner (tglx@linutronix.de) * * Information on how this algorithm works and how it was developed - * can be found in Documentation/nand/ecc.txt + * can be found in Documentation/mtd/nand_ecc.txt * * This file is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -35,7 +35,7 @@ * e.g. when running the code in a testbed or a benchmark program. * When STANDALONE is used, the module related macros are commented out * as well as the linux include files. - * Instead a private definition of mtd_into is given to satisfy the compiler + * Instead a private definition of mtd_info is given to satisfy the compiler * (the code does not use mtd_info, so the code does not care) */ #ifndef STANDALONE @@ -44,10 +44,8 @@ #include #include #else -typedef uint32_t unsigned long -struct mtd_info { - int dummy; -}; +#include +struct mtd_info; #define EXPORT_SYMBOL(x) /* x */ #define MODULE_LICENSE(x) /* x */ @@ -409,7 +407,7 @@ int nand_correct_data(struct mtd_info *mtd, unsigned char *buf, /* repeated if statements are slightly more efficient than switch ... */ /* ordered in order of likelihood */ if (nr_bits == 0) - return (0); /* no error */ + return 0; /* no error */ if (nr_bits == 11) { /* correctable error */ /* * rp15/13/11/9/7/5/3/1 indicate which byte is the faulty byte @@ -431,10 +429,10 @@ int nand_correct_data(struct mtd_info *mtd, unsigned char *buf, bit_addr = addressbits[b2 >> 2]; /* flip the bit */ buf[byte_addr] ^= (1 << bit_addr); - return (1); + return 1; } if (nr_bits == 1) - return (1); /* error in ecc data; no action needed */ + return 1; /* error in ecc data; no action needed */ return -1; } EXPORT_SYMBOL(nand_correct_data); -- cgit v0.10.2 From 8ee991dd343df57910ff6947696afada9f02bf7e Mon Sep 17 00:00:00 2001 From: Huang Weiyi Date: Sun, 17 Aug 2008 07:50:44 +0800 Subject: [MTD] removed unused #include The drivers below do not use LINUX_VERSION_CODE nor KERNEL_VERSION. drivers/mtd/maps/amd76xrom.c drivers/mtd/maps/ck804xrom.c drivers/mtd/maps/esb2rom.c This patch removes the said #include . Signed-off-by: Huang Weiyi Signed-off-by: David Woodhouse diff --git a/drivers/mtd/maps/amd76xrom.c b/drivers/mtd/maps/amd76xrom.c index 948b86f3..d1eec7d 100644 --- a/drivers/mtd/maps/amd76xrom.c +++ b/drivers/mtd/maps/amd76xrom.c @@ -6,7 +6,6 @@ #include #include -#include #include #include #include diff --git a/drivers/mtd/maps/ck804xrom.c b/drivers/mtd/maps/ck804xrom.c index effaf7c..1a6feb4 100644 --- a/drivers/mtd/maps/ck804xrom.c +++ b/drivers/mtd/maps/ck804xrom.c @@ -9,7 +9,6 @@ #include #include -#include #include #include #include diff --git a/drivers/mtd/maps/esb2rom.c b/drivers/mtd/maps/esb2rom.c index aa64a47..bbbcdd4 100644 --- a/drivers/mtd/maps/esb2rom.c +++ b/drivers/mtd/maps/esb2rom.c @@ -12,7 +12,6 @@ #include #include -#include #include #include #include -- cgit v0.10.2 From 75caf6b5acc6b895df9bdd36db631220e1096e9f Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 18 Aug 2008 16:23:53 +0100 Subject: [JFFS2] Fill in f_fsid field in jffs2_statfs() Signed-off-by: David Woodhouse diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 086c438..89e9b73 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -207,6 +207,8 @@ int jffs2_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_files = 0; buf->f_ffree = 0; buf->f_namelen = JFFS2_MAX_NAME_LEN; + buf->f_fsid.val[0] = JFFS2_SUPER_MAGIC; + buf->f_fsid.val[1] = c->mtd->index; spin_lock(&c->erase_completion_lock); avail = c->dirty_size + c->free_size; -- cgit v0.10.2 From 1077be58ad7baadd86e47e8b4f6209fa5b6364a5 Mon Sep 17 00:00:00 2001 From: frans Date: Wed, 20 Aug 2008 21:11:50 +0200 Subject: [MTD] [NAND] nand_ecc.c: fix big endian, strengthen test, add printk This patch for nand_ecc.c fixes three issues - fix code so it also works on big endian architectures - added a printk in case of an uncorrectable ecc error - strengthen the test for correctable errors (decreasing the chance that multiple bit faults by accident will be seen as correctable) Note: the big endian code is only tested in a testbed (running on big endian hardware) as I cannot rebuild and test a big endian kernel at the moment. However the only thing that can go wrong is if does not give __BIG_ENDIAN in that case. In my eyes very unlikely. Signed-off-by: Frans Meulenbroeks Signed-off-by: David Woodhouse diff --git a/drivers/mtd/nand/nand_ecc.c b/drivers/mtd/nand/nand_ecc.c index a8e8413..d99e569 100644 --- a/drivers/mtd/nand/nand_ecc.c +++ b/drivers/mtd/nand/nand_ecc.c @@ -43,6 +43,7 @@ #include #include #include +#include #else #include struct mtd_info; @@ -51,6 +52,9 @@ struct mtd_info; #define MODULE_LICENSE(x) /* x */ #define MODULE_AUTHOR(x) /* x */ #define MODULE_DESCRIPTION(x) /* x */ + +#define printk printf +#define KERN_ERR "" #endif /* @@ -273,24 +277,38 @@ int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf, /* * we also need to calculate the row parity for rp0..rp3 * This is present in par, because par is now - * rp3 rp3 rp2 rp2 + * rp3 rp3 rp2 rp2 in little endian and + * rp2 rp2 rp3 rp3 in big endian * as well as - * rp1 rp0 rp1 rp0 + * rp1 rp0 rp1 rp0 in little endian and + * rp0 rp1 rp0 rp1 in big endian * First calculate rp2 and rp3 - * (and yes: rp2 = (par ^ rp3) & 0xff; but doing that did not - * give a performance improvement) */ +#ifdef __BIG_ENDIAN + rp2 = (par >> 16); + rp2 ^= (rp2 >> 8); + rp2 &= 0xff; + rp3 = par & 0xffff; + rp3 ^= (rp3 >> 8); + rp3 &= 0xff; +#else rp3 = (par >> 16); rp3 ^= (rp3 >> 8); rp3 &= 0xff; rp2 = par & 0xffff; rp2 ^= (rp2 >> 8); rp2 &= 0xff; +#endif /* reduce par to 16 bits then calculate rp1 and rp0 */ par ^= (par >> 16); +#ifdef __BIG_ENDIAN + rp0 = (par >> 8) & 0xff; + rp1 = (par & 0xff); +#else rp1 = (par >> 8) & 0xff; rp0 = (par & 0xff); +#endif /* finally reduce par to 8 bits */ par ^= (par >> 8); @@ -381,7 +399,6 @@ EXPORT_SYMBOL(nand_calculate_ecc); int nand_correct_data(struct mtd_info *mtd, unsigned char *buf, unsigned char *read_ecc, unsigned char *calc_ecc) { - int nr_bits; unsigned char b0, b1, b2; unsigned char byte_addr, bit_addr; @@ -401,14 +418,15 @@ int nand_correct_data(struct mtd_info *mtd, unsigned char *buf, /* check if there are any bitfaults */ - /* count nr of bits; use table lookup, faster than calculating it */ - nr_bits = bitsperbyte[b0] + bitsperbyte[b1] + bitsperbyte[b2]; - /* repeated if statements are slightly more efficient than switch ... */ /* ordered in order of likelihood */ - if (nr_bits == 0) + + if ((b0 | b1 | b2) == 0) return 0; /* no error */ - if (nr_bits == 11) { /* correctable error */ + + if ((((b0 ^ (b0 >> 1)) & 0x55) == 0x55) && + (((b1 ^ (b1 >> 1)) & 0x55) == 0x55) && + (((b2 ^ (b2 >> 1)) & 0x54) == 0x54)) { /* single bit error */ /* * rp15/13/11/9/7/5/3/1 indicate which byte is the faulty byte * cp 5/3/1 indicate the faulty bit. @@ -430,9 +448,13 @@ int nand_correct_data(struct mtd_info *mtd, unsigned char *buf, /* flip the bit */ buf[byte_addr] ^= (1 << bit_addr); return 1; + } - if (nr_bits == 1) + /* count nr of bits; use table lookup, faster than calculating it */ + if ((bitsperbyte[b0] + bitsperbyte[b1] + bitsperbyte[b2]) == 1) return 1; /* error in ecc data; no action needed */ + + printk(KERN_ERR "uncorrectable error : "); return -1; } EXPORT_SYMBOL(nand_correct_data); -- cgit v0.10.2 From 17c1d2be28e485c0c8b09661db39d5bf2605069d Mon Sep 17 00:00:00 2001 From: Alexey Korolev Date: Wed, 20 Aug 2008 22:32:08 +0100 Subject: [MTD] [NAND] Fix missing kernel-doc [Reported by Randy Dunlap] Signed-off-by: Alexey Korolev Signed-off-by: David Woodhouse diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 5822805..d303db3 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -801,9 +801,9 @@ static int nand_read_page_swecc(struct mtd_info *mtd, struct nand_chip *chip, * nand_read_subpage - [REPLACABLE] software ecc based sub-page read function * @mtd: mtd info structure * @chip: nand chip info structure - * @dataofs offset of requested data within the page - * @readlen data length - * @buf: buffer to store read data + * @data_offs: offset of requested data within the page + * @readlen: data length + * @bufpoi: buffer to store read data */ static int nand_read_subpage(struct mtd_info *mtd, struct nand_chip *chip, uint32_t data_offs, uint32_t readlen, uint8_t *bufpoi) { diff --git a/drivers/mtd/nand/nand_ecc.c b/drivers/mtd/nand/nand_ecc.c index d99e569..fd19787 100644 --- a/drivers/mtd/nand/nand_ecc.c +++ b/drivers/mtd/nand/nand_ecc.c @@ -150,8 +150,8 @@ static const char addressbits[256] = { /** * nand_calculate_ecc - [NAND Interface] Calculate 3-byte ECC for 256-byte block * @mtd: MTD block structure (unused) - * @dat: raw data - * @ecc_code: buffer for ECC + * @buf: input buffer with raw data + * @code: output buffer with ECC */ int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf, unsigned char *code) @@ -390,7 +390,7 @@ EXPORT_SYMBOL(nand_calculate_ecc); /** * nand_correct_data - [NAND Interface] Detect and correct bit error(s) * @mtd: MTD block structure (unused) - * @dat: raw data read from the chip + * @buf: raw data read from the chip * @read_ecc: ECC from the chip * @calc_ecc: the ECC calculated from raw data * diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 81774e5..733d3f3 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -248,6 +248,7 @@ struct nand_hw_control { * @read_page_raw: function to read a raw page without ECC * @write_page_raw: function to write a raw page without ECC * @read_page: function to read a page according to the ecc generator requirements + * @read_subpage: function to read parts of the page covered by ECC. * @write_page: function to write a page according to the ecc generator requirements * @read_oob: function to read chip OOB data * @write_oob: function to write chip OOB data -- cgit v0.10.2 From ee974e01e5ef2914036f08c8e41d1a3fa8bfc9d9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Aug 2008 16:37:26 -0700 Subject: clocksource: check range Check that the value being passed to parse_pmtmr() does not exceed the limits of pmtmr_ioport. Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c index 5ca1d80..3df3384 100644 --- a/drivers/clocksource/acpi_pm.c +++ b/drivers/clocksource/acpi_pm.c @@ -226,9 +226,12 @@ static int __init parse_pmtmr(char *arg) if (strict_strtoul(arg, 16, &base)) return -EINVAL; - +#ifdef CONFIG_X86_64 + if (base > UINT_MAX) + return -ERANGE; +#endif printk(KERN_INFO "PMTMR IOPort override: 0x%04x -> 0x%04lx\n", - (unsigned int)pmtmr_ioport, base); + pmtmr_ioport, base); pmtmr_ioport = base; return 1; -- cgit v0.10.2 From 1aa5dfb751d275ae7117d3b73ac423b4a46f2a73 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 20 Aug 2008 16:37:28 -0700 Subject: clocksource: keep track of original clocksource frequency The clocksource frequency is represented by clocksource->mult/2^(clocksource->shift). Currently, when NTP makes adjustments to the clock frequency, they are made directly to the mult value. This has the drawback that once changed, we cannot know what the orignal mult value was, or how much adjustment has been applied. This property causes problems in calculating proper ntp intervals when switching back and forth between clocksources. This patch separates the current mult value into a mult and mult_orig pair. The mult_orig value stays constant, while the ntp clocksource adjustments are done only to the mult value. This allows for correct ntp interval calculation and additionally lays the groundwork for a new notion of time, what I'm calling the monotonic-raw time, which is introduced in a following patch. Signed-off-by: John Stultz Signed-off-by: Roman Zippel Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 55e434f..f0a7fb9 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -45,7 +45,8 @@ struct clocksource; * @read: returns a cycle value * @mask: bitmask for two's complement * subtraction of non 64 bit counters - * @mult: cycle to nanosecond multiplier + * @mult: cycle to nanosecond multiplier (adjusted by NTP) + * @mult_orig: cycle to nanosecond multiplier (unadjusted by NTP) * @shift: cycle to nanosecond divisor (power of two) * @flags: flags describing special properties * @vread: vsyscall based read @@ -63,6 +64,7 @@ struct clocksource { cycle_t (*read)(void); cycle_t mask; u32 mult; + u32 mult_orig; u32 shift; unsigned long flags; cycle_t (*vread)(void); @@ -201,16 +203,17 @@ static inline void clocksource_calculate_interval(struct clocksource *c, { u64 tmp; - /* XXX - All of this could use a whole lot of optimization */ + /* Do the ns -> cycle conversion first, using original mult */ tmp = length_nsec; tmp <<= c->shift; - tmp += c->mult/2; - do_div(tmp, c->mult); + tmp += c->mult_orig/2; + do_div(tmp, c->mult_orig); c->cycle_interval = (cycle_t)tmp; if (c->cycle_interval == 0) c->cycle_interval = 1; + /* Go back from cycles -> shifted ns, this time use ntp adjused mult */ c->xtime_interval = (u64)c->cycle_interval * c->mult; } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 093d4ac..9ed2eec 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -325,6 +325,9 @@ int clocksource_register(struct clocksource *c) unsigned long flags; int ret; + /* save mult_orig on registration */ + c->mult_orig = c->mult; + spin_lock_irqsave(&clocksource_lock, flags); ret = clocksource_enqueue(c); if (!ret) diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 4c256fd..1ca9955 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -61,6 +61,7 @@ struct clocksource clocksource_jiffies = { .read = jiffies_read, .mask = 0xffffffff, /*32bits*/ .mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */ + .mult_orig = NSEC_PER_JIFFY << JIFFIES_SHIFT, .shift = JIFFIES_SHIFT, }; -- cgit v0.10.2 From 9a055117d3d9cb562f83f8d4cd88772761f4cab0 Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Wed, 20 Aug 2008 16:37:28 -0700 Subject: clocksource: introduce clocksource_forward_now() To keep the raw monotonic patch simple first introduce clocksource_forward_now(), which takes care of the offset since the last update_wall_time() call and adds it to the clock, so there is no need anymore to deal with it explicitly at various places, which need to make significant changes to the clock. This is also gets rid of the timekeeping_suspend_nsecs, instead of waiting until resume, the value is accumulated during suspend. In the end there is only a single user of __get_nsec_offset() left, so I integrated it back to getnstimeofday(). Signed-off-by: Roman Zippel Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e91c29f..83d3555 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -58,27 +58,23 @@ struct clocksource *clock; #ifdef CONFIG_GENERIC_TIME /** - * __get_nsec_offset - Returns nanoseconds since last call to periodic_hook + * clocksource_forward_now - update clock to the current time * - * private function, must hold xtime_lock lock when being - * called. Returns the number of nanoseconds since the - * last call to update_wall_time() (adjusted by NTP scaling) + * Forward the current clock to update its state since the last call to + * update_wall_time(). This is useful before significant clock changes, + * as it avoids having to deal with this time offset explicitly. */ -static inline s64 __get_nsec_offset(void) +static void clocksource_forward_now(void) { cycle_t cycle_now, cycle_delta; - s64 ns_offset; + s64 nsec; - /* read clocksource: */ cycle_now = clocksource_read(clock); - - /* calculate the delta since the last update_wall_time: */ cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + clock->cycle_last = cycle_now; - /* convert to nanoseconds: */ - ns_offset = cyc2ns(clock, cycle_delta); - - return ns_offset; + nsec = cyc2ns(clock, cycle_delta); + timespec_add_ns(&xtime, nsec); } /** @@ -89,6 +85,7 @@ static inline s64 __get_nsec_offset(void) */ void getnstimeofday(struct timespec *ts) { + cycle_t cycle_now, cycle_delta; unsigned long seq; s64 nsecs; @@ -96,7 +93,15 @@ void getnstimeofday(struct timespec *ts) seq = read_seqbegin(&xtime_lock); *ts = xtime; - nsecs = __get_nsec_offset(); + + /* read clocksource: */ + cycle_now = clocksource_read(clock); + + /* calculate the delta since the last update_wall_time: */ + cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + + /* convert to nanoseconds: */ + nsecs = cyc2ns(clock, cycle_delta); } while (read_seqretry(&xtime_lock, seq)); @@ -129,22 +134,22 @@ EXPORT_SYMBOL(do_gettimeofday); */ int do_settimeofday(struct timespec *tv) { + struct timespec ts_delta; unsigned long flags; - time_t wtm_sec, sec = tv->tv_sec; - long wtm_nsec, nsec = tv->tv_nsec; if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) return -EINVAL; write_seqlock_irqsave(&xtime_lock, flags); - nsec -= __get_nsec_offset(); + clocksource_forward_now(); + + ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec; + ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec; + wall_to_monotonic = timespec_sub(wall_to_monotonic, ts_delta); - wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); - wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); + xtime = *tv; - set_normalized_timespec(&xtime, sec, nsec); - set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); update_xtime_cache(0); clock->error = 0; @@ -170,22 +175,17 @@ EXPORT_SYMBOL(do_settimeofday); static void change_clocksource(void) { struct clocksource *new; - cycle_t now; - u64 nsec; new = clocksource_get_next(); if (clock == new) return; - new->cycle_last = 0; - now = clocksource_read(new); - nsec = __get_nsec_offset(); - timespec_add_ns(&xtime, nsec); + clocksource_forward_now(); clock = new; - clock->cycle_last = now; - + clock->cycle_last = 0; + clock->cycle_last = clocksource_read(new); clock->error = 0; clock->xtime_nsec = 0; clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH); @@ -200,8 +200,8 @@ static void change_clocksource(void) */ } #else +static inline void clocksource_forward_now(void) { } static inline void change_clocksource(void) { } -static inline s64 __get_nsec_offset(void) { return 0; } #endif /** @@ -265,8 +265,6 @@ void __init timekeeping_init(void) static int timekeeping_suspended; /* time in seconds when suspend began */ static unsigned long timekeeping_suspend_time; -/* xtime offset when we went into suspend */ -static s64 timekeeping_suspend_nsecs; /** * timekeeping_resume - Resumes the generic timekeeping subsystem. @@ -292,8 +290,6 @@ static int timekeeping_resume(struct sys_device *dev) wall_to_monotonic.tv_sec -= sleep_length; total_sleep_time += sleep_length; } - /* Make sure that we have the correct xtime reference */ - timespec_add_ns(&xtime, timekeeping_suspend_nsecs); update_xtime_cache(0); /* re-base the last cycle value */ clock->cycle_last = 0; @@ -319,8 +315,7 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state) timekeeping_suspend_time = read_persistent_clock(); write_seqlock_irqsave(&xtime_lock, flags); - /* Get the current xtime offset */ - timekeeping_suspend_nsecs = __get_nsec_offset(); + clocksource_forward_now(); timekeeping_suspended = 1; write_sequnlock_irqrestore(&xtime_lock, flags); @@ -461,10 +456,10 @@ void update_wall_time(void) */ while (offset >= clock->cycle_interval) { /* accumulate one interval */ - clock->xtime_nsec += clock->xtime_interval; - clock->cycle_last += clock->cycle_interval; offset -= clock->cycle_interval; + clock->cycle_last += clock->cycle_interval; + clock->xtime_nsec += clock->xtime_interval; if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) { clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift; xtime.tv_sec++; -- cgit v0.10.2 From 2d42244ae71d6c7b0884b5664cf2eda30fb2ae68 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 20 Aug 2008 16:37:30 -0700 Subject: clocksource: introduce CLOCK_MONOTONIC_RAW In talking with Josip Loncaric, and his work on clock synchronization (see btime.sf.net), he mentioned that for really close synchronization, it is useful to have access to "hardware time", that is a notion of time that is not in any way adjusted by the clock slewing done to keep close time sync. Part of the issue is if we are using the kernel's ntp adjusted representation of time in order to measure how we should correct time, we can run into what Paul McKenney aptly described as "Painting a road using the lines we're painting as the guide". I had been thinking of a similar problem, and was trying to come up with a way to give users access to a purely hardware based time representation that avoided users having to know the underlying frequency and mask values needed to deal with the wide variety of possible underlying hardware counters. My solution is to introduce CLOCK_MONOTONIC_RAW. This exposes a nanosecond based time value, that increments starting at bootup and has no frequency adjustments made to it what so ever. The time is accessed from userspace via the posix_clock_gettime() syscall, passing CLOCK_MONOTONIC_RAW as the clock_id. Signed-off-by: John Stultz Signed-off-by: Roman Zippel Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index f0a7fb9..f88d32f 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -79,6 +79,7 @@ struct clocksource { /* timekeeping specific data, ignore */ cycle_t cycle_interval; u64 xtime_interval; + u32 raw_interval; /* * Second part is written at each timer interrupt * Keep it in a different cache line to dirty no @@ -87,6 +88,7 @@ struct clocksource { cycle_t cycle_last ____cacheline_aligned_in_smp; u64 xtime_nsec; s64 error; + struct timespec raw_time; #ifdef CONFIG_CLOCKSOURCE_WATCHDOG /* Watchdog related data, used by the framework */ @@ -215,6 +217,7 @@ static inline void clocksource_calculate_interval(struct clocksource *c, /* Go back from cycles -> shifted ns, this time use ntp adjused mult */ c->xtime_interval = (u64)c->cycle_interval * c->mult; + c->raw_interval = ((u64)c->cycle_interval * c->mult_orig) >> c->shift; } diff --git a/include/linux/time.h b/include/linux/time.h index e15206a..205f974 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -117,6 +117,7 @@ extern int do_setitimer(int which, struct itimerval *value, extern unsigned int alarm_setitimer(unsigned int seconds); extern int do_getitimer(int which, struct itimerval *value); extern void getnstimeofday(struct timespec *tv); +extern void getrawmonotonic(struct timespec *ts); extern void getboottime(struct timespec *ts); extern void monotonic_to_bootbased(struct timespec *ts); @@ -214,6 +215,7 @@ struct itimerval { #define CLOCK_MONOTONIC 1 #define CLOCK_PROCESS_CPUTIME_ID 2 #define CLOCK_THREAD_CPUTIME_ID 3 +#define CLOCK_MONOTONIC_RAW 4 /* * The IDs of various hardware clocks: diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index e36d579..d3c66b5 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -223,6 +223,15 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp) } /* + * Get monotonic time for posix timers + */ +static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp) +{ + getrawmonotonic(tp); + return 0; +} + +/* * Initialize everything, well, just everything in Posix clocks/timers ;) */ static __init int init_posix_timers(void) @@ -235,9 +244,15 @@ static __init int init_posix_timers(void) .clock_get = posix_ktime_get_ts, .clock_set = do_posix_clock_nosettime, }; + struct k_clock clock_monotonic_raw = { + .clock_getres = hrtimer_get_res, + .clock_get = posix_get_monotonic_raw, + .clock_set = do_posix_clock_nosettime, + }; register_posix_clock(CLOCK_REALTIME, &clock_realtime); register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic); + register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw); posix_timers_cache = kmem_cache_create("posix_timers_cache", sizeof (struct k_itimer), 0, SLAB_PANIC, diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 83d3555..5099c95 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -75,6 +75,9 @@ static void clocksource_forward_now(void) nsec = cyc2ns(clock, cycle_delta); timespec_add_ns(&xtime, nsec); + + nsec = ((s64)cycle_delta * clock->mult_orig) >> clock->shift; + clock->raw_time.tv_nsec += nsec; } /** @@ -183,6 +186,8 @@ static void change_clocksource(void) clocksource_forward_now(); + new->raw_time = clock->raw_time; + clock = new; clock->cycle_last = 0; clock->cycle_last = clocksource_read(new); @@ -205,6 +210,39 @@ static inline void change_clocksource(void) { } #endif /** + * getrawmonotonic - Returns the raw monotonic time in a timespec + * @ts: pointer to the timespec to be set + * + * Returns the raw monotonic time (completely un-modified by ntp) + */ +void getrawmonotonic(struct timespec *ts) +{ + unsigned long seq; + s64 nsecs; + cycle_t cycle_now, cycle_delta; + + do { + seq = read_seqbegin(&xtime_lock); + + /* read clocksource: */ + cycle_now = clocksource_read(clock); + + /* calculate the delta since the last update_wall_time: */ + cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + + /* convert to nanoseconds: */ + nsecs = ((s64)cycle_delta * clock->mult_orig) >> clock->shift; + + *ts = clock->raw_time; + + } while (read_seqretry(&xtime_lock, seq)); + + timespec_add_ns(ts, nsecs); +} +EXPORT_SYMBOL(getrawmonotonic); + + +/** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) @@ -466,6 +504,12 @@ void update_wall_time(void) second_overflow(); } + clock->raw_time.tv_nsec += clock->raw_interval; + if (clock->raw_time.tv_nsec >= NSEC_PER_SEC) { + clock->raw_time.tv_nsec -= NSEC_PER_SEC; + clock->raw_time.tv_sec++; + } + /* accumulate error between NTP and clock interval */ clock->error += tick_length; clock->error -= clock->xtime_interval << (NTP_SCALE_SHIFT - clock->shift); -- cgit v0.10.2 From d82f0b0f6f1a0a25afc288fb7135b1601fe6df18 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 20 Aug 2008 16:46:04 -0700 Subject: migrate_timers: add comment, use spinlock_irq() Add the comment to explain why the double lock in migrate_timers() can't deadlock. Change the code to use spinlock_irq() instead of local_irq_disable() + spin_lock(). Signed-off-by: Oleg Nesterov Acked-by: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index b8e4dce..03ea137 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1620,9 +1620,11 @@ static void migrate_hrtimers(int cpu) new_base = &get_cpu_var(hrtimer_bases); tick_cancel_sched_timer(cpu); - - local_irq_disable(); - spin_lock(&new_base->lock); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. + */ + spin_lock_irq(&new_base->lock); spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { @@ -1631,8 +1633,7 @@ static void migrate_hrtimers(int cpu) } spin_unlock(&old_base->lock); - spin_unlock(&new_base->lock); - local_irq_enable(); + spin_unlock_irq(&new_base->lock); put_cpu_var(hrtimer_bases); } #endif /* CONFIG_HOTPLUG_CPU */ diff --git a/kernel/timer.c b/kernel/timer.c index 03bc7f1..e8019cc 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1435,9 +1435,11 @@ static void __cpuinit migrate_timers(int cpu) BUG_ON(cpu_online(cpu)); old_base = per_cpu(tvec_bases, cpu); new_base = get_cpu_var(tvec_bases); - - local_irq_disable(); - spin_lock(&new_base->lock); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. + */ + spin_lock_irq(&new_base->lock); spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); BUG_ON(old_base->running_timer); @@ -1452,8 +1454,7 @@ static void __cpuinit migrate_timers(int cpu) } spin_unlock(&old_base->lock); - spin_unlock(&new_base->lock); - local_irq_enable(); + spin_unlock_irq(&new_base->lock); put_cpu_var(tvec_bases); } #endif /* CONFIG_HOTPLUG_CPU */ -- cgit v0.10.2 From 916c7a855174e3b53d182b97a26b2e27a29726a1 Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Wed, 20 Aug 2008 16:46:08 -0700 Subject: ntp: fix ADJ_OFFSET_SS_READ bug and do_adjtimex() cleanup Thanks to the review by Michael Kerrisk a bug in the recent ADJ_OFFSET_SS_READ option was discovered, where the ntp time_offset was inadvertently set by it. This fixes this by making the adjtime code more separate from the ntp_adjtime code (both of which really want to be separate syscalls). Signed-off-by: Roman Zippel Signed-off-by: Andrew Morton Acked-by: John Stultz Signed-off-by: Ingo Molnar diff --git a/include/linux/timex.h b/include/linux/timex.h index fc6035d..c00bcdd 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -141,8 +141,15 @@ struct timex { #define ADJ_MICRO 0x1000 /* select microsecond resolution */ #define ADJ_NANO 0x2000 /* select nanosecond resolution */ #define ADJ_TICK 0x4000 /* tick value */ + +#ifdef __KERNEL__ +#define ADJ_ADJTIME 0x8000 /* switch between adjtime/adjtimex modes */ +#define ADJ_OFFSET_SINGLESHOT 0x0001 /* old-fashioned adjtime */ +#define ADJ_OFFSET_READONLY 0x2000 /* read-only adjtime */ +#else #define ADJ_OFFSET_SINGLESHOT 0x8001 /* old-fashioned adjtime */ -#define ADJ_OFFSET_SS_READ 0xa001 /* read-only adjtime */ +#define ADJ_OFFSET_SS_READ 0xa001 /* read-only adjtime */ +#endif /* xntp 3.4 compatibility names */ #define MOD_OFFSET ADJ_OFFSET diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 5125ddd..c6921aa1 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -277,38 +277,50 @@ static inline void notify_cmos_timer(void) { } int do_adjtimex(struct timex *txc) { struct timespec ts; - long save_adjust, sec; int result; - /* In order to modify anything, you gotta be super-user! */ - if (txc->modes && !capable(CAP_SYS_TIME)) - return -EPERM; - - /* Now we validate the data before disabling interrupts */ - - if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) { + /* Validate the data before disabling interrupts */ + if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ - if (txc->modes & ~ADJ_OFFSET_SS_READ) + if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; + if (!(txc->modes & ADJ_OFFSET_READONLY) && + !capable(CAP_SYS_TIME)) + return -EPERM; + } else { + /* In order to modify anything, you gotta be super-user! */ + if (txc->modes && !capable(CAP_SYS_TIME)) + return -EPERM; + + /* if the quartz is off by more than 10% something is VERY wrong! */ + if (txc->modes & ADJ_TICK && + (txc->tick < 900000/USER_HZ || + txc->tick > 1100000/USER_HZ)) + return -EINVAL; + + if (txc->modes & ADJ_STATUS && time_state != TIME_OK) + hrtimer_cancel(&leap_timer); } - /* if the quartz is off by more than 10% something is VERY wrong ! */ - if (txc->modes & ADJ_TICK) - if (txc->tick < 900000/USER_HZ || - txc->tick > 1100000/USER_HZ) - return -EINVAL; - - if (time_state != TIME_OK && txc->modes & ADJ_STATUS) - hrtimer_cancel(&leap_timer); getnstimeofday(&ts); write_seqlock_irq(&xtime_lock); - /* Save for later - semantics of adjtime is to return old value */ - save_adjust = time_adjust; - /* If there are input parameters, then process them */ + if (txc->modes & ADJ_ADJTIME) { + long save_adjust = time_adjust; + + if (!(txc->modes & ADJ_OFFSET_READONLY)) { + /* adjtime() is independent from ntp_adjtime() */ + time_adjust = txc->offset; + ntp_update_frequency(); + } + txc->offset = save_adjust; + goto adj_done; + } if (txc->modes) { + long sec; + if (txc->modes & ADJ_STATUS) { if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { @@ -375,13 +387,8 @@ int do_adjtimex(struct timex *txc) if (txc->modes & ADJ_TAI && txc->constant > 0) time_tai = txc->constant; - if (txc->modes & ADJ_OFFSET) { - if (txc->modes == ADJ_OFFSET_SINGLESHOT) - /* adjtime() is independent from ntp_adjtime() */ - time_adjust = txc->offset; - else - ntp_update_offset(txc->offset); - } + if (txc->modes & ADJ_OFFSET) + ntp_update_offset(txc->offset); if (txc->modes & ADJ_TICK) tick_usec = txc->tick; @@ -389,19 +396,16 @@ int do_adjtimex(struct timex *txc) ntp_update_frequency(); } + txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, + NTP_SCALE_SHIFT); + if (!(time_status & STA_NANO)) + txc->offset /= NSEC_PER_USEC; + +adj_done: result = time_state; /* mostly `TIME_OK' */ if (time_status & (STA_UNSYNC|STA_CLOCKERR)) result = TIME_ERROR; - if ((txc->modes == ADJ_OFFSET_SINGLESHOT) || - (txc->modes == ADJ_OFFSET_SS_READ)) - txc->offset = save_adjust; - else { - txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, - NTP_SCALE_SHIFT); - if (!(time_status & STA_NANO)) - txc->offset /= NSEC_PER_USEC; - } txc->freq = shift_right((s32)(time_freq >> PPM_SCALE_INV_SHIFT) * (s64)PPM_SCALE_INV, NTP_SCALE_SHIFT); -- cgit v0.10.2 From 377bf1e4ac2d894791733270604594c7c851ef83 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Thu, 21 Aug 2008 22:58:28 +0400 Subject: genirq: fix irq_desc->depth handling with DEBUG_SHIRQ When DEBUG_SHIRQ is selected, a spurious IRQ is issued before the setup_irq() initializes the desc->depth. An IRQ handler may call disable_irq_nosync(), but then setup_irq() will overwrite desc->depth, and upon enable_irq() we'll catch this WARN: ------------[ cut here ]------------ Badness at kernel/irq/manage.c:180 NIP: c0061ab8 LR: c0061f10 CTR: 00000000 REGS: cf83be50 TRAP: 0700 Not tainted (2.6.27-rc3-23450-g74919b0) MSR: 00021032 CR: 22042022 XER: 20000000 TASK = cf829100[5] 'events/0' THREAD: cf83a000 GPR00: c0061f10 cf83bf00 cf829100 c038e674 00000016 00000000 cf83bef8 00000038 GPR08: c0298910 00000000 c0310d28 cf83a000 00000c9c 1001a1a8 0fffe000 00800000 GPR16: ffffffff 00000000 007fff00 00000000 007ffeb0 c03320a0 c031095c c0310924 GPR24: cf8292ec cf807190 cf83a000 00009032 c038e6a4 c038e674 cf99b1cc c038e674 NIP [c0061ab8] __enable_irq+0x20/0x80 LR [c0061f10] enable_irq+0x50/0x70 Call Trace: [cf83bf00] [c038e674] irq_desc+0x630/0x9000 (unreliable) [cf83bf10] [c0061f10] enable_irq+0x50/0x70 [cf83bf30] [c01abe94] phy_change+0x68/0x108 [cf83bf50] [c0046394] run_workqueue+0xc4/0x16c [cf83bf90] [c0046834] worker_thread+0x74/0xd4 [cf83bfd0] [c004ab7c] kthread+0x48/0x84 [cf83bff0] [c00135e0] kernel_thread+0x44/0x60 Instruction dump: 4e800020 3d20c031 38a94214 4bffffcc 9421fff0 7c0802a6 93e1000c 7c7f1b78 90010014 8123001c 2f890000 409e001c <0fe00000> 80010014 83e1000c 38210010 That trace corresponds to this line: WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); The patch fixes the problem by moving the SHIRQ code below the setup_irq(). Unfortunately we can't easily move the SHIRQ code inside the setup_irq(), since it grabs a spinlock, so to prvent a 'real' IRQ from interfere us we should disable that IRQ. p.s. The driver in question is drivers/net/phy/phy.c. Signed-off-by: Anton Vorontsov Cc: David Woodhouse Signed-off-by: Ingo Molnar diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 77a51be..ae1b684 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -596,26 +596,29 @@ int request_irq(unsigned int irq, irq_handler_t handler, action->next = NULL; action->dev_id = dev_id; + retval = setup_irq(irq, action); + if (retval) + kfree(action); + #ifdef CONFIG_DEBUG_SHIRQ if (irqflags & IRQF_SHARED) { /* * It's a shared IRQ -- the driver ought to be prepared for it * to happen immediately, so let's make sure.... - * We do this before actually registering it, to make sure that - * a 'real' IRQ doesn't run in parallel with our fake + * We disable the irq to make sure that a 'real' IRQ doesn't + * run in parallel with our fake. */ unsigned long flags; + disable_irq(irq); local_irq_save(flags); + handler(irq, dev_id); + local_irq_restore(flags); + enable_irq(irq); } #endif - - retval = setup_irq(irq, action); - if (retval) - kfree(action); - return retval; } EXPORT_SYMBOL(request_irq); -- cgit v0.10.2 From dffc8d66544563fe00f176f230d5d8a5b45847bb Mon Sep 17 00:00:00 2001 From: Huang Weiyi Date: Sat, 23 Aug 2008 13:56:21 +0800 Subject: [MTD] [NAND] au1550nd.c: remove unused #include It doesn't use LINUX_VERSION_CODE nor KERNEL_VERSION. This patch removes the said #include . Signed-off-by: Huang Weiyi Signed-off-by: David Woodhouse diff --git a/drivers/mtd/nand/au1550nd.c b/drivers/mtd/nand/au1550nd.c index 761946e..92c334f 100644 --- a/drivers/mtd/nand/au1550nd.c +++ b/drivers/mtd/nand/au1550nd.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include -- cgit v0.10.2 From d68156cfad0fe09201dd049fff167a8a881427ad Mon Sep 17 00:00:00 2001 From: "Singh, Vimal" Date: Sat, 23 Aug 2008 18:18:34 +0200 Subject: [MTD] [NAND] nand_ecc.c: adding support for 512 byte ecc Support 512 byte ECC calculation [FM: updated two comments] Signed-off-by: Vimal Singh Signed-off-by: Frans Meulenbroeks Signed-off-by: David Woodhouse diff --git a/drivers/mtd/nand/nand_ecc.c b/drivers/mtd/nand/nand_ecc.c index fd19787..868147a 100644 --- a/drivers/mtd/nand/nand_ecc.c +++ b/drivers/mtd/nand/nand_ecc.c @@ -42,6 +42,8 @@ #include #include #include +#include +#include #include #include #else @@ -148,8 +150,9 @@ static const char addressbits[256] = { }; /** - * nand_calculate_ecc - [NAND Interface] Calculate 3-byte ECC for 256-byte block - * @mtd: MTD block structure (unused) + * nand_calculate_ecc - [NAND Interface] Calculate 3-byte ECC for 256/512-byte + * block + * @mtd: MTD block structure * @buf: input buffer with raw data * @code: output buffer with ECC */ @@ -158,13 +161,18 @@ int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf, { int i; const uint32_t *bp = (uint32_t *)buf; + /* 256 or 512 bytes/ecc */ + const uint32_t eccsize_mult = + (((struct nand_chip *)mtd->priv)->ecc.size) >> 8; uint32_t cur; /* current value in buffer */ - /* rp0..rp15 are the various accumulated parities (per byte) */ + /* rp0..rp15..rp17 are the various accumulated parities (per byte) */ uint32_t rp0, rp1, rp2, rp3, rp4, rp5, rp6, rp7; - uint32_t rp8, rp9, rp10, rp11, rp12, rp13, rp14, rp15; + uint32_t rp8, rp9, rp10, rp11, rp12, rp13, rp14, rp15, rp16; + uint32_t uninitialized_var(rp17); /* to make compiler happy */ uint32_t par; /* the cumulative parity for all data */ uint32_t tmppar; /* the cumulative parity for this iteration; - for rp12 and rp14 at the end of the loop */ + for rp12, rp14 and rp16 at the end of the + loop */ par = 0; rp4 = 0; @@ -173,6 +181,7 @@ int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf, rp10 = 0; rp12 = 0; rp14 = 0; + rp16 = 0; /* * The loop is unrolled a number of times; @@ -181,10 +190,10 @@ int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf, * Note: passing unaligned data might give a performance penalty. * It is assumed that the buffers are aligned. * tmppar is the cumulative sum of this iteration. - * needed for calculating rp12, rp14 and par + * needed for calculating rp12, rp14, rp16 and par * also used as a performance improvement for rp6, rp8 and rp10 */ - for (i = 0; i < 4; i++) { + for (i = 0; i < eccsize_mult << 2; i++) { cur = *bp++; tmppar = cur; rp4 ^= cur; @@ -247,12 +256,14 @@ int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf, rp12 ^= tmppar; if ((i & 0x2) == 0) rp14 ^= tmppar; + if (eccsize_mult == 2 && (i & 0x4) == 0) + rp16 ^= tmppar; } /* * handle the fact that we use longword operations - * we'll bring rp4..rp14 back to single byte entities by shifting and - * xoring first fold the upper and lower 16 bits, + * we'll bring rp4..rp14..rp16 back to single byte entities by + * shifting and xoring first fold the upper and lower 16 bits, * then the upper and lower 8 bits. */ rp4 ^= (rp4 >> 16); @@ -273,6 +284,11 @@ int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf, rp14 ^= (rp14 >> 16); rp14 ^= (rp14 >> 8); rp14 &= 0xff; + if (eccsize_mult == 2) { + rp16 ^= (rp16 >> 16); + rp16 ^= (rp16 >> 8); + rp16 &= 0xff; + } /* * we also need to calculate the row parity for rp0..rp3 @@ -315,7 +331,7 @@ int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf, par &= 0xff; /* - * and calculate rp5..rp15 + * and calculate rp5..rp15..rp17 * note that par = rp4 ^ rp5 and due to the commutative property * of the ^ operator we can say: * rp5 = (par ^ rp4); @@ -329,6 +345,8 @@ int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf, rp11 = (par ^ rp10) & 0xff; rp13 = (par ^ rp12) & 0xff; rp15 = (par ^ rp14) & 0xff; + if (eccsize_mult == 2) + rp17 = (par ^ rp16) & 0xff; /* * Finally calculate the ecc bits. @@ -375,32 +393,46 @@ int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf, (invparity[rp9] << 1) | (invparity[rp8]); #endif - code[2] = - (invparity[par & 0xf0] << 7) | - (invparity[par & 0x0f] << 6) | - (invparity[par & 0xcc] << 5) | - (invparity[par & 0x33] << 4) | - (invparity[par & 0xaa] << 3) | - (invparity[par & 0x55] << 2) | - 3; + if (eccsize_mult == 1) + code[2] = + (invparity[par & 0xf0] << 7) | + (invparity[par & 0x0f] << 6) | + (invparity[par & 0xcc] << 5) | + (invparity[par & 0x33] << 4) | + (invparity[par & 0xaa] << 3) | + (invparity[par & 0x55] << 2) | + 3; + else + code[2] = + (invparity[par & 0xf0] << 7) | + (invparity[par & 0x0f] << 6) | + (invparity[par & 0xcc] << 5) | + (invparity[par & 0x33] << 4) | + (invparity[par & 0xaa] << 3) | + (invparity[par & 0x55] << 2) | + (invparity[rp17] << 1) | + (invparity[rp16] << 0); return 0; } EXPORT_SYMBOL(nand_calculate_ecc); /** * nand_correct_data - [NAND Interface] Detect and correct bit error(s) - * @mtd: MTD block structure (unused) + * @mtd: MTD block structure * @buf: raw data read from the chip * @read_ecc: ECC from the chip * @calc_ecc: the ECC calculated from raw data * - * Detect and correct a 1 bit error for 256 byte block + * Detect and correct a 1 bit error for 256/512 byte block */ int nand_correct_data(struct mtd_info *mtd, unsigned char *buf, unsigned char *read_ecc, unsigned char *calc_ecc) { unsigned char b0, b1, b2; unsigned char byte_addr, bit_addr; + /* 256 or 512 bytes/ecc */ + const uint32_t eccsize_mult = + (((struct nand_chip *)mtd->priv)->ecc.size) >> 8; /* * b0 to b2 indicate which bit is faulty (if any) @@ -426,10 +458,12 @@ int nand_correct_data(struct mtd_info *mtd, unsigned char *buf, if ((((b0 ^ (b0 >> 1)) & 0x55) == 0x55) && (((b1 ^ (b1 >> 1)) & 0x55) == 0x55) && - (((b2 ^ (b2 >> 1)) & 0x54) == 0x54)) { /* single bit error */ + ((eccsize_mult == 1 && ((b2 ^ (b2 >> 1)) & 0x54) == 0x54) || + (eccsize_mult == 2 && ((b2 ^ (b2 >> 1)) & 0x55) == 0x55))) { + /* single bit error */ /* - * rp15/13/11/9/7/5/3/1 indicate which byte is the faulty byte - * cp 5/3/1 indicate the faulty bit. + * rp17/rp15/13/11/9/7/5/3/1 indicate which byte is the faulty + * byte, cp 5/3/1 indicate the faulty bit. * A lookup table (called addressbits) is used to filter * the bits from the byte they are in. * A marginal optimisation is possible by having three @@ -443,7 +477,11 @@ int nand_correct_data(struct mtd_info *mtd, unsigned char *buf, * We could also do addressbits[b2] >> 1 but for the * performace it does not make any difference */ - byte_addr = (addressbits[b1] << 4) + addressbits[b0]; + if (eccsize_mult == 1) + byte_addr = (addressbits[b1] << 4) + addressbits[b0]; + else + byte_addr = (addressbits[b2 & 0x3] << 8) + + (addressbits[b1] << 4) + addressbits[b0]; bit_addr = addressbits[b2 >> 2]; /* flip the bit */ buf[byte_addr] ^= (1 << bit_addr); -- cgit v0.10.2 From e82374fd1a804e197fc2a54c3930e70c5d300abc Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Mon, 11 Aug 2008 22:22:27 +0200 Subject: pda_power: Check and handle return value of set_irq_wake The recent change in commit 2db873211ba47ef704c301f9ecf4a33413a0b649 forces the calls enable_irq_wake() and disable_irq_wake() to be balanced. But if in pda_power_suspend() the call to enable_irq_wake() fails (because attached gpio cannot wake up the CPU), the corresponding disable_irq_wake will WARN(). Fix it by storing success/failure of enable_irq_wake(). Signed-off-by: Robert Jarzmik Signed-off-by: Anton Vorontsov diff --git a/drivers/power/pda_power.c b/drivers/power/pda_power.c index 0471ec7..d30bb76 100644 --- a/drivers/power/pda_power.c +++ b/drivers/power/pda_power.c @@ -334,13 +334,16 @@ static int pda_power_remove(struct platform_device *pdev) } #ifdef CONFIG_PM +static int ac_wakeup_enabled; +static int usb_wakeup_enabled; + static int pda_power_suspend(struct platform_device *pdev, pm_message_t state) { if (device_may_wakeup(&pdev->dev)) { if (ac_irq) - enable_irq_wake(ac_irq->start); + ac_wakeup_enabled = !enable_irq_wake(ac_irq->start); if (usb_irq) - enable_irq_wake(usb_irq->start); + usb_wakeup_enabled = !enable_irq_wake(usb_irq->start); } return 0; @@ -349,9 +352,9 @@ static int pda_power_suspend(struct platform_device *pdev, pm_message_t state) static int pda_power_resume(struct platform_device *pdev) { if (device_may_wakeup(&pdev->dev)) { - if (usb_irq) + if (usb_irq && usb_wakeup_enabled) disable_irq_wake(usb_irq->start); - if (ac_irq) + if (ac_irq && ac_wakeup_enabled) disable_irq_wake(ac_irq->start); } -- cgit v0.10.2 From 942ed161944b3476639916cf544e6975b29c985a Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Tue, 26 Aug 2008 21:09:59 +0100 Subject: power_supply: Add function to return system-wide power state Certain drivers benefit from knowing whether the system is on ac or battery, for instance when determining which backlight registers to read. This adds a simple call to determine whether there's an online power supply other than any batteries. Signed-off-by: Matthew Garrett Signed-off-by: Anton Vorontsov diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c index cb1ccb4..f44f5b6 100644 --- a/drivers/power/power_supply_core.c +++ b/drivers/power/power_supply_core.c @@ -87,6 +87,30 @@ int power_supply_am_i_supplied(struct power_supply *psy) return error; } +static int __power_supply_is_system_supplied(struct device *dev, void *data) +{ + union power_supply_propval ret = {0,}; + struct power_supply *psy = dev_get_drvdata(dev); + + if (psy->type != POWER_SUPPLY_TYPE_BATTERY) { + if (psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &ret)) + return 0; + if (ret.intval) + return ret.intval; + } + return 0; +} + +int power_supply_is_system_supplied(void) +{ + int error; + + error = class_for_each_device(power_supply_class, NULL, NULL, + __power_supply_is_system_supplied); + + return error; +} + int power_supply_register(struct device *parent, struct power_supply *psy) { int rc = 0; @@ -148,6 +172,7 @@ static void __exit power_supply_class_exit(void) EXPORT_SYMBOL_GPL(power_supply_changed); EXPORT_SYMBOL_GPL(power_supply_am_i_supplied); +EXPORT_SYMBOL_GPL(power_supply_is_system_supplied); EXPORT_SYMBOL_GPL(power_supply_register); EXPORT_SYMBOL_GPL(power_supply_unregister); diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index ea96ead..f9348cb 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -165,6 +165,12 @@ struct power_supply_info { extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); +#if defined(CONFIG_POWER_SUPPLY) || defined(CONFIG_POWER_SUPPLY_MODULE) +extern int power_supply_is_system_supplied(void); +#else +static inline int power_supply_is_system_supplied(void) { return -ENOSYS; } +#endif + extern int power_supply_register(struct device *parent, struct power_supply *psy); extern void power_supply_unregister(struct power_supply *psy); -- cgit v0.10.2 From b996ad0e9fb15ca4acc60bcd0380912117a45d13 Mon Sep 17 00:00:00 2001 From: Rodolfo Giometti Date: Wed, 20 Aug 2008 16:52:58 -0700 Subject: power_supply: Support for Texas Instruments BQ27200 battery managers These battery managers came in two different packages: one for I2C busses (BQ27200) and one for HDQ busses (BQ27000). This driver currently supports only the I2C chip version but the code is designed in order to easily allow the HDQ chip version integration. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: make things static, use kasprintf()] Signed-off-by: Rodolfo Giometti Cc: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Anton Vorontsov diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig index 9ce5585..b2bd104 100644 --- a/drivers/power/Kconfig +++ b/drivers/power/Kconfig @@ -62,4 +62,10 @@ config BATTERY_PALMTX help Say Y to enable support for the battery in Palm T|X. +config BATTERY_BQ27x00 + tristate "BQ27200 battery driver" + depends on I2C + help + Say Y here to enable support for batteries with BQ27200(I2C) chip. + endif # POWER_SUPPLY diff --git a/drivers/power/Makefile b/drivers/power/Makefile index 4706bf8..6cb301b 100644 --- a/drivers/power/Makefile +++ b/drivers/power/Makefile @@ -22,3 +22,4 @@ obj-$(CONFIG_BATTERY_PMU) += pmu_battery.o obj-$(CONFIG_BATTERY_OLPC) += olpc_battery.o obj-$(CONFIG_BATTERY_TOSA) += tosa_battery.o obj-$(CONFIG_BATTERY_PALMTX) += palmtx_battery.o +obj-$(CONFIG_BATTERY_BQ27x00) += bq27x00_battery.o diff --git a/drivers/power/bq27x00_battery.c b/drivers/power/bq27x00_battery.c new file mode 100644 index 0000000..62d4948 --- /dev/null +++ b/drivers/power/bq27x00_battery.c @@ -0,0 +1,382 @@ +/* + * BQ27x00 battery driver + * + * Copyright (C) 2008 Rodolfo Giometti + * Copyright (C) 2008 Eurotech S.p.A. + * + * Based on a previous work by Copyright (C) 2008 Texas Instruments, Inc. + * + * This package 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 PACKAGE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR + * IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED + * WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE. + * + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define DRIVER_VERSION "1.0.0" + +#define BQ27x00_REG_TEMP 0x06 +#define BQ27x00_REG_VOLT 0x08 +#define BQ27x00_REG_RSOC 0x0B /* Relative State-of-Charge */ +#define BQ27x00_REG_AI 0x14 +#define BQ27x00_REG_FLAGS 0x0A +#define HIGH_BYTE(A) ((A) << 8) + +/* If the system has several batteries we need a different name for each + * of them... + */ +static DEFINE_IDR(battery_id); +static DEFINE_MUTEX(battery_mutex); + +struct bq27x00_device_info; +struct bq27x00_access_methods { + int (*read)(u8 reg, int *rt_value, int b_single, + struct bq27x00_device_info *di); +}; + +struct bq27x00_device_info { + struct device *dev; + int id; + int voltage_uV; + int current_uA; + int temp_C; + int charge_rsoc; + struct bq27x00_access_methods *bus; + struct power_supply bat; + + struct i2c_client *client; +}; + +static enum power_supply_property bq27x00_battery_props[] = { + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_TEMP, +}; + +/* + * Common code for BQ27x00 devices + */ + +static int bq27x00_read(u8 reg, int *rt_value, int b_single, + struct bq27x00_device_info *di) +{ + int ret; + + ret = di->bus->read(reg, rt_value, b_single, di); + *rt_value = be16_to_cpu(*rt_value); + + return ret; +} + +/* + * Return the battery temperature in Celcius degrees + * Or < 0 if something fails. + */ +static int bq27x00_battery_temperature(struct bq27x00_device_info *di) +{ + int ret; + int temp = 0; + + ret = bq27x00_read(BQ27x00_REG_TEMP, &temp, 0, di); + if (ret) { + dev_err(di->dev, "error reading temperature\n"); + return ret; + } + + return (temp >> 2) - 273; +} + +/* + * Return the battery Voltage in milivolts + * Or < 0 if something fails. + */ +static int bq27x00_battery_voltage(struct bq27x00_device_info *di) +{ + int ret; + int volt = 0; + + ret = bq27x00_read(BQ27x00_REG_VOLT, &volt, 0, di); + if (ret) { + dev_err(di->dev, "error reading voltage\n"); + return ret; + } + + return volt; +} + +/* + * Return the battery average current + * Note that current can be negative signed as well + * Or 0 if something fails. + */ +static int bq27x00_battery_current(struct bq27x00_device_info *di) +{ + int ret; + int curr = 0; + int flags = 0; + + ret = bq27x00_read(BQ27x00_REG_AI, &curr, 0, di); + if (ret) { + dev_err(di->dev, "error reading current\n"); + return 0; + } + ret = bq27x00_read(BQ27x00_REG_FLAGS, &flags, 0, di); + if (ret < 0) { + dev_err(di->dev, "error reading flags\n"); + return 0; + } + if ((flags & (1 << 7)) != 0) { + dev_dbg(di->dev, "negative current!\n"); + return -curr; + } + return curr; +} + +/* + * Return the battery Relative State-of-Charge + * Or < 0 if something fails. + */ +static int bq27x00_battery_rsoc(struct bq27x00_device_info *di) +{ + int ret; + int rsoc = 0; + + ret = bq27x00_read(BQ27x00_REG_RSOC, &rsoc, 1, di); + if (ret) { + dev_err(di->dev, "error reading relative State-of-Charge\n"); + return ret; + } + + return rsoc >> 8; +} + +#define to_bq27x00_device_info(x) container_of((x), \ + struct bq27x00_device_info, bat); + +static int bq27x00_battery_get_property(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) +{ + struct bq27x00_device_info *di = to_bq27x00_device_info(psy); + + switch (psp) { + case POWER_SUPPLY_PROP_VOLTAGE_NOW: + case POWER_SUPPLY_PROP_PRESENT: + val->intval = bq27x00_battery_voltage(di); + if (psp == POWER_SUPPLY_PROP_PRESENT) + val->intval = val->intval <= 0 ? 0 : 1; + break; + case POWER_SUPPLY_PROP_CURRENT_NOW: + val->intval = bq27x00_battery_current(di); + break; + case POWER_SUPPLY_PROP_CAPACITY: + val->intval = bq27x00_battery_rsoc(di); + break; + case POWER_SUPPLY_PROP_TEMP: + val->intval = bq27x00_battery_temperature(di); + break; + default: + return -EINVAL; + } + + return 0; +} + +static void bq27x00_powersupply_init(struct bq27x00_device_info *di) +{ + di->bat.type = POWER_SUPPLY_TYPE_BATTERY; + di->bat.properties = bq27x00_battery_props; + di->bat.num_properties = ARRAY_SIZE(bq27x00_battery_props); + di->bat.get_property = bq27x00_battery_get_property; + di->bat.external_power_changed = NULL; +} + +/* + * BQ27200 specific code + */ + +static int bq27200_read(u8 reg, int *rt_value, int b_single, + struct bq27x00_device_info *di) +{ + struct i2c_client *client = di->client; + struct i2c_msg msg[1]; + unsigned char data[2]; + int err; + + if (!client->adapter) + return -ENODEV; + + msg->addr = client->addr; + msg->flags = 0; + msg->len = 1; + msg->buf = data; + + data[0] = reg; + err = i2c_transfer(client->adapter, msg, 1); + + if (err >= 0) { + if (!b_single) + msg->len = 2; + else + msg->len = 1; + + msg->flags = I2C_M_RD; + err = i2c_transfer(client->adapter, msg, 1); + if (err >= 0) { + if (!b_single) + *rt_value = data[1] | HIGH_BYTE(data[0]); + else + *rt_value = data[0]; + + return 0; + } + } + return err; +} + +static int bq27200_battery_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + char *name; + struct bq27x00_device_info *di; + struct bq27x00_access_methods *bus; + int num; + int retval = 0; + + /* Get new ID for the new battery device */ + retval = idr_pre_get(&battery_id, GFP_KERNEL); + if (retval == 0) + return -ENOMEM; + mutex_lock(&battery_mutex); + retval = idr_get_new(&battery_id, client, &num); + mutex_unlock(&battery_mutex); + if (retval < 0) + return retval; + + name = kasprintf(GFP_KERNEL, "bq27200-%d", num); + if (!name) { + dev_err(&client->dev, "failed to allocate device name\n"); + retval = -ENOMEM; + goto batt_failed_1; + } + + di = kzalloc(sizeof(*di), GFP_KERNEL); + if (!di) { + dev_err(&client->dev, "failed to allocate device info data\n"); + retval = -ENOMEM; + goto batt_failed_2; + } + di->id = num; + + bus = kzalloc(sizeof(*bus), GFP_KERNEL); + if (!bus) { + dev_err(&client->dev, "failed to allocate access method " + "data\n"); + retval = -ENOMEM; + goto batt_failed_3; + } + + i2c_set_clientdata(client, di); + di->dev = &client->dev; + di->bat.name = name; + bus->read = &bq27200_read; + di->bus = bus; + di->client = client; + + bq27x00_powersupply_init(di); + + retval = power_supply_register(&client->dev, &di->bat); + if (retval) { + dev_err(&client->dev, "failed to register battery\n"); + goto batt_failed_4; + } + + dev_info(&client->dev, "support ver. %s enabled\n", DRIVER_VERSION); + + return 0; + +batt_failed_4: + kfree(bus); +batt_failed_3: + kfree(di); +batt_failed_2: + kfree(name); +batt_failed_1: + mutex_lock(&battery_mutex); + idr_remove(&battery_id, num); + mutex_unlock(&battery_mutex); + + return retval; +} + +static int bq27200_battery_remove(struct i2c_client *client) +{ + struct bq27x00_device_info *di = i2c_get_clientdata(client); + + power_supply_unregister(&di->bat); + + kfree(di->bat.name); + + mutex_lock(&battery_mutex); + idr_remove(&battery_id, di->id); + mutex_unlock(&battery_mutex); + + kfree(di); + + return 0; +} + +/* + * Module stuff + */ + +static const struct i2c_device_id bq27200_id[] = { + { "bq27200", 0 }, + {}, +}; + +static struct i2c_driver bq27200_battery_driver = { + .driver = { + .name = "bq27200-battery", + }, + .probe = bq27200_battery_probe, + .remove = bq27200_battery_remove, + .id_table = bq27200_id, +}; + +static int __init bq27x00_battery_init(void) +{ + int ret; + + ret = i2c_add_driver(&bq27200_battery_driver); + if (ret) + printk(KERN_ERR "Unable to register BQ27200 driver\n"); + + return ret; +} +module_init(bq27x00_battery_init); + +static void __exit bq27x00_battery_exit(void) +{ + i2c_del_driver(&bq27200_battery_driver); +} +module_exit(bq27x00_battery_exit); + +MODULE_AUTHOR("Rodolfo Giometti "); +MODULE_DESCRIPTION("BQ27x00 battery monitor driver"); +MODULE_LICENSE("GPL"); -- cgit v0.10.2 From 31db6e9ea1dbdcf66b8227b4f7035dee1b1dd8c0 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 29 Aug 2008 07:19:50 +0400 Subject: [JFFS2] Move JFFS2 config options out of fs/Kconfig Signed-off-by: Alexey Dobriyan Signed-off-by: David Woodhouse diff --git a/fs/Kconfig b/fs/Kconfig index d387358..5831f9c 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -1136,195 +1136,7 @@ config EFS_FS To compile the EFS file system support as a module, choose M here: the module will be called efs. -config JFFS2_FS - tristate "Journalling Flash File System v2 (JFFS2) support" - select CRC32 - depends on MTD - help - JFFS2 is the second generation of the Journalling Flash File System - for use on diskless embedded devices. It provides improved wear - levelling, compression and support for hard links. You cannot use - this on normal block devices, only on 'MTD' devices. - - Further information on the design and implementation of JFFS2 is - available at . - -config JFFS2_FS_DEBUG - int "JFFS2 debugging verbosity (0 = quiet, 2 = noisy)" - depends on JFFS2_FS - default "0" - help - This controls the amount of debugging messages produced by the JFFS2 - code. Set it to zero for use in production systems. For evaluation, - testing and debugging, it's advisable to set it to one. This will - enable a few assertions and will print debugging messages at the - KERN_DEBUG loglevel, where they won't normally be visible. Level 2 - is unlikely to be useful - it enables extra debugging in certain - areas which at one point needed debugging, but when the bugs were - located and fixed, the detailed messages were relegated to level 2. - - If reporting bugs, please try to have available a full dump of the - messages at debug level 1 while the misbehaviour was occurring. - -config JFFS2_FS_WRITEBUFFER - bool "JFFS2 write-buffering support" - depends on JFFS2_FS - default y - help - This enables the write-buffering support in JFFS2. - - This functionality is required to support JFFS2 on the following - types of flash devices: - - NAND flash - - NOR flash with transparent ECC - - DataFlash - -config JFFS2_FS_WBUF_VERIFY - bool "Verify JFFS2 write-buffer reads" - depends on JFFS2_FS_WRITEBUFFER - default n - help - This causes JFFS2 to read back every page written through the - write-buffer, and check for errors. - -config JFFS2_SUMMARY - bool "JFFS2 summary support (EXPERIMENTAL)" - depends on JFFS2_FS && EXPERIMENTAL - default n - help - This feature makes it possible to use summary information - for faster filesystem mount. - - The summary information can be inserted into a filesystem image - by the utility 'sumtool'. - - If unsure, say 'N'. - -config JFFS2_FS_XATTR - bool "JFFS2 XATTR support (EXPERIMENTAL)" - depends on JFFS2_FS && EXPERIMENTAL - default n - help - Extended attributes are name:value pairs associated with inodes by - the kernel or by users (see the attr(5) manual page, or visit - for details). - - If unsure, say N. - -config JFFS2_FS_POSIX_ACL - bool "JFFS2 POSIX Access Control Lists" - depends on JFFS2_FS_XATTR - default y - select FS_POSIX_ACL - help - Posix Access Control Lists (ACLs) support permissions for users and - groups beyond the owner/group/world scheme. - - To learn more about Access Control Lists, visit the Posix ACLs for - Linux website . - - If you don't know what Access Control Lists are, say N - -config JFFS2_FS_SECURITY - bool "JFFS2 Security Labels" - depends on JFFS2_FS_XATTR - default y - help - Security labels support alternative access control models - implemented by security modules like SELinux. This option - enables an extended attribute handler for file security - labels in the jffs2 filesystem. - - If you are not using a security module that requires using - extended attributes for file security labels, say N. - -config JFFS2_COMPRESSION_OPTIONS - bool "Advanced compression options for JFFS2" - depends on JFFS2_FS - default n - help - Enabling this option allows you to explicitly choose which - compression modules, if any, are enabled in JFFS2. Removing - compressors can mean you cannot read existing file systems, - and enabling experimental compressors can mean that you - write a file system which cannot be read by a standard kernel. - - If unsure, you should _definitely_ say 'N'. - -config JFFS2_ZLIB - bool "JFFS2 ZLIB compression support" if JFFS2_COMPRESSION_OPTIONS - select ZLIB_INFLATE - select ZLIB_DEFLATE - depends on JFFS2_FS - default y - help - Zlib is designed to be a free, general-purpose, legally unencumbered, - lossless data-compression library for use on virtually any computer - hardware and operating system. See for - further information. - - Say 'Y' if unsure. - -config JFFS2_LZO - bool "JFFS2 LZO compression support" if JFFS2_COMPRESSION_OPTIONS - select LZO_COMPRESS - select LZO_DECOMPRESS - depends on JFFS2_FS - default n - help - minilzo-based compression. Generally works better than Zlib. - - This feature was added in July, 2007. Say 'N' if you need - compatibility with older bootloaders or kernels. - -config JFFS2_RTIME - bool "JFFS2 RTIME compression support" if JFFS2_COMPRESSION_OPTIONS - depends on JFFS2_FS - default y - help - Rtime does manage to recompress already-compressed data. Say 'Y' if unsure. - -config JFFS2_RUBIN - bool "JFFS2 RUBIN compression support" if JFFS2_COMPRESSION_OPTIONS - depends on JFFS2_FS - default n - help - RUBINMIPS and DYNRUBIN compressors. Say 'N' if unsure. - -choice - prompt "JFFS2 default compression mode" if JFFS2_COMPRESSION_OPTIONS - default JFFS2_CMODE_PRIORITY - depends on JFFS2_FS - help - You can set here the default compression mode of JFFS2 from - the available compression modes. Don't touch if unsure. - -config JFFS2_CMODE_NONE - bool "no compression" - help - Uses no compression. - -config JFFS2_CMODE_PRIORITY - bool "priority" - help - Tries the compressors in a predefined order and chooses the first - successful one. - -config JFFS2_CMODE_SIZE - bool "size (EXPERIMENTAL)" - help - Tries all compressors and chooses the one which has the smallest - result. - -config JFFS2_CMODE_FAVOURLZO - bool "Favour LZO" - help - Tries all compressors and chooses the one which has the smallest - result but gives some preference to LZO (which has faster - decompression) at the expense of size. - -endchoice - +source "fs/jffs2/Kconfig" # UBIFS File system configuration source "fs/ubifs/Kconfig" diff --git a/fs/jffs2/Kconfig b/fs/jffs2/Kconfig new file mode 100644 index 0000000..6ae169c --- /dev/null +++ b/fs/jffs2/Kconfig @@ -0,0 +1,188 @@ +config JFFS2_FS + tristate "Journalling Flash File System v2 (JFFS2) support" + select CRC32 + depends on MTD + help + JFFS2 is the second generation of the Journalling Flash File System + for use on diskless embedded devices. It provides improved wear + levelling, compression and support for hard links. You cannot use + this on normal block devices, only on 'MTD' devices. + + Further information on the design and implementation of JFFS2 is + available at . + +config JFFS2_FS_DEBUG + int "JFFS2 debugging verbosity (0 = quiet, 2 = noisy)" + depends on JFFS2_FS + default "0" + help + This controls the amount of debugging messages produced by the JFFS2 + code. Set it to zero for use in production systems. For evaluation, + testing and debugging, it's advisable to set it to one. This will + enable a few assertions and will print debugging messages at the + KERN_DEBUG loglevel, where they won't normally be visible. Level 2 + is unlikely to be useful - it enables extra debugging in certain + areas which at one point needed debugging, but when the bugs were + located and fixed, the detailed messages were relegated to level 2. + + If reporting bugs, please try to have available a full dump of the + messages at debug level 1 while the misbehaviour was occurring. + +config JFFS2_FS_WRITEBUFFER + bool "JFFS2 write-buffering support" + depends on JFFS2_FS + default y + help + This enables the write-buffering support in JFFS2. + + This functionality is required to support JFFS2 on the following + types of flash devices: + - NAND flash + - NOR flash with transparent ECC + - DataFlash + +config JFFS2_FS_WBUF_VERIFY + bool "Verify JFFS2 write-buffer reads" + depends on JFFS2_FS_WRITEBUFFER + default n + help + This causes JFFS2 to read back every page written through the + write-buffer, and check for errors. + +config JFFS2_SUMMARY + bool "JFFS2 summary support (EXPERIMENTAL)" + depends on JFFS2_FS && EXPERIMENTAL + default n + help + This feature makes it possible to use summary information + for faster filesystem mount. + + The summary information can be inserted into a filesystem image + by the utility 'sumtool'. + + If unsure, say 'N'. + +config JFFS2_FS_XATTR + bool "JFFS2 XATTR support (EXPERIMENTAL)" + depends on JFFS2_FS && EXPERIMENTAL + default n + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page, or visit + for details). + + If unsure, say N. + +config JFFS2_FS_POSIX_ACL + bool "JFFS2 POSIX Access Control Lists" + depends on JFFS2_FS_XATTR + default y + select FS_POSIX_ACL + help + Posix Access Control Lists (ACLs) support permissions for users and + groups beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the Posix ACLs for + Linux website . + + If you don't know what Access Control Lists are, say N + +config JFFS2_FS_SECURITY + bool "JFFS2 Security Labels" + depends on JFFS2_FS_XATTR + default y + help + Security labels support alternative access control models + implemented by security modules like SELinux. This option + enables an extended attribute handler for file security + labels in the jffs2 filesystem. + + If you are not using a security module that requires using + extended attributes for file security labels, say N. + +config JFFS2_COMPRESSION_OPTIONS + bool "Advanced compression options for JFFS2" + depends on JFFS2_FS + default n + help + Enabling this option allows you to explicitly choose which + compression modules, if any, are enabled in JFFS2. Removing + compressors can mean you cannot read existing file systems, + and enabling experimental compressors can mean that you + write a file system which cannot be read by a standard kernel. + + If unsure, you should _definitely_ say 'N'. + +config JFFS2_ZLIB + bool "JFFS2 ZLIB compression support" if JFFS2_COMPRESSION_OPTIONS + select ZLIB_INFLATE + select ZLIB_DEFLATE + depends on JFFS2_FS + default y + help + Zlib is designed to be a free, general-purpose, legally unencumbered, + lossless data-compression library for use on virtually any computer + hardware and operating system. See for + further information. + + Say 'Y' if unsure. + +config JFFS2_LZO + bool "JFFS2 LZO compression support" if JFFS2_COMPRESSION_OPTIONS + select LZO_COMPRESS + select LZO_DECOMPRESS + depends on JFFS2_FS + default n + help + minilzo-based compression. Generally works better than Zlib. + + This feature was added in July, 2007. Say 'N' if you need + compatibility with older bootloaders or kernels. + +config JFFS2_RTIME + bool "JFFS2 RTIME compression support" if JFFS2_COMPRESSION_OPTIONS + depends on JFFS2_FS + default y + help + Rtime does manage to recompress already-compressed data. Say 'Y' if unsure. + +config JFFS2_RUBIN + bool "JFFS2 RUBIN compression support" if JFFS2_COMPRESSION_OPTIONS + depends on JFFS2_FS + default n + help + RUBINMIPS and DYNRUBIN compressors. Say 'N' if unsure. + +choice + prompt "JFFS2 default compression mode" if JFFS2_COMPRESSION_OPTIONS + default JFFS2_CMODE_PRIORITY + depends on JFFS2_FS + help + You can set here the default compression mode of JFFS2 from + the available compression modes. Don't touch if unsure. + +config JFFS2_CMODE_NONE + bool "no compression" + help + Uses no compression. + +config JFFS2_CMODE_PRIORITY + bool "priority" + help + Tries the compressors in a predefined order and chooses the first + successful one. + +config JFFS2_CMODE_SIZE + bool "size (EXPERIMENTAL)" + help + Tries all compressors and chooses the one which has the smallest + result. + +config JFFS2_CMODE_FAVOURLZO + bool "Favour LZO" + help + Tries all compressors and chooses the one which has the smallest + result but gives some preference to LZO (which has faster + decompression) at the expense of size. + +endchoice -- cgit v0.10.2 From 3fc678a0e63138f56109ea31850f19b2e29c45b8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 27 Aug 2008 14:48:32 +0100 Subject: CRED: Wrap task credential accesses in the JFFS2 filesystem Wrap access to task credentials so that they can be separated more easily from the task_struct during the introduction of COW creds. Change most current->(|e|s|fs)[ug]id to current_(|e|s|fs)[ug]id(). Change some task->e?[ug]id to task_e?[ug]id(). In some places it makes more sense to use RCU directly rather than a convenient wrapper; these will be addressed by later patches. Signed-off-by: David Howells Reviewed-by: James Morris Acked-by: Serge Hallyn Signed-off-by: David Woodhouse diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 89e9b73..249305d 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -442,14 +442,14 @@ struct inode *jffs2_new_inode (struct inode *dir_i, int mode, struct jffs2_raw_i memset(ri, 0, sizeof(*ri)); /* Set OS-specific defaults for new inodes */ - ri->uid = cpu_to_je16(current->fsuid); + ri->uid = cpu_to_je16(current_fsuid()); if (dir_i->i_mode & S_ISGID) { ri->gid = cpu_to_je16(dir_i->i_gid); if (S_ISDIR(mode)) mode |= S_ISGID; } else { - ri->gid = cpu_to_je16(current->fsgid); + ri->gid = cpu_to_je16(current_fsgid()); } /* POSIX ACLs have to be processed now, at least partly. -- cgit v0.10.2 From 4262bd2981307258b31e15f1a526d2b3884e77b5 Mon Sep 17 00:00:00 2001 From: Semun Lee Date: Mon, 1 Sep 2008 11:49:27 +0100 Subject: [MTD] [NAND] pxa3xx_nand_flash: Add definition of STM2GbX16 NAND flashes Signed-off-by: Semun Lee Acked-by: Eric Miao Signed-off-by: David Woodhouse diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index a64ad15..0cd213c 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -291,10 +291,33 @@ static struct pxa3xx_nand_flash micron1GbX16 = { .chip_id = 0xb12c, }; +static struct pxa3xx_nand_timing stm2GbX16_timing = { + .tCH = 10, + .tCS = 35, + .tWH = 15, + .tWP = 25, + .tRH = 15, + .tRP = 25, + .tR = 25000, + .tWHR = 60, + .tAR = 10, +}; + +static struct pxa3xx_nand_flash stm2GbX16 = { + .timing = &stm2GbX16_timing, + .page_per_block = 64, + .page_size = 2048, + .flash_width = 16, + .dfc_width = 16, + .num_blocks = 2048, + .chip_id = 0xba20, +}; + static struct pxa3xx_nand_flash *builtin_flash_types[] = { &samsung512MbX16, µn1GbX8, µn1GbX16, + &stm2GbX16, }; #define NDTR0_tCH(c) (min((c), 7) << 19) -- cgit v0.10.2 From 5e706469a0518ec640a122aa5da22035e2af003a Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 1 Sep 2008 12:21:05 +0100 Subject: [MTD] [NOR] Select MTD_CFI_UTIL when MTD_CFI probe routine is enabled It requires cfi_qry_mode_on(), which is in cfi_util.c Reported by Russell King Signed-off-by: David Woodhouse diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig index 9401bfe..9408099 100644 --- a/drivers/mtd/chips/Kconfig +++ b/drivers/mtd/chips/Kconfig @@ -6,6 +6,7 @@ menu "RAM/ROM/Flash chip drivers" config MTD_CFI tristate "Detect flash chips by Common Flash Interface (CFI) probe" select MTD_GEN_PROBE + select MTD_CFI_UTIL help The Common Flash Interface specification was developed by Intel, AMD and other flash manufactures that provides a universal method -- cgit v0.10.2 From 43035338ad772b6a4097b2ac530b75390bee87c1 Mon Sep 17 00:00:00 2001 From: Enrico Scholz Date: Fri, 29 Aug 2008 12:57:28 +0200 Subject: [MTD] [NAND] pxa3xx_nand: moved nand definitions into shared platform header This patch moves the exported datastructures from the pxa3xx_nand.c driver into the header. This is a plain movement without any modification of the attributes. This is the first one of a set of patches which: * allows to specify used NAND flash in the platform code and allows to turn off the old way to specify NAND characteristics in the driver. This way did not worked well as these characteristics depend on the platform and can not be derived from NAND id alone. E.g. some NAND chips share the same ID (e.g. K9K8G08U0A and K9NBG08U5A) but have different timings (which are written in the common driver currently and must be modified there). * adds 'const' annotations at various places Further patches will be sent to the mtd-list. Signed-off-by: Enrico Scholz Signed-off-by: David Woodhouse diff --git a/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h b/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h index eb4b190..0dc50d8 100644 --- a/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h +++ b/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h @@ -4,6 +4,50 @@ #include #include +struct pxa3xx_nand_timing { + unsigned int tCH; /* Enable signal hold time */ + unsigned int tCS; /* Enable signal setup time */ + unsigned int tWH; /* ND_nWE high duration */ + unsigned int tWP; /* ND_nWE pulse time */ + unsigned int tRH; /* ND_nRE high duration */ + unsigned int tRP; /* ND_nRE pulse width */ + unsigned int tR; /* ND_nWE high to ND_nRE low for read */ + unsigned int tWHR; /* ND_nWE high to ND_nRE low for status read */ + unsigned int tAR; /* ND_ALE low to ND_nRE low delay */ +}; + +struct pxa3xx_nand_cmdset { + uint16_t read1; + uint16_t read2; + uint16_t program; + uint16_t read_status; + uint16_t read_id; + uint16_t erase; + uint16_t reset; + uint16_t lock; + uint16_t unlock; + uint16_t lock_status; +}; + +struct pxa3xx_nand_flash { + struct pxa3xx_nand_timing *timing; /* NAND Flash timing */ + struct pxa3xx_nand_cmdset *cmdset; + + uint32_t page_per_block;/* Pages per block (PG_PER_BLK) */ + uint32_t page_size; /* Page size in bytes (PAGE_SZ) */ + uint32_t flash_width; /* Width of Flash memory (DWIDTH_M) */ + uint32_t dfc_width; /* Width of flash controller(DWIDTH_C) */ + uint32_t num_blocks; /* Number of physical blocks in Flash */ + uint32_t chip_id; + + /* NOTE: these are automatically calculated, do not define */ + size_t oob_size; + size_t read_id_bytes; + + unsigned int col_addr_cycles; + unsigned int row_addr_cycles; +}; + struct pxa3xx_nand_platform_data { /* the data flash bus is shared between the Static Memory diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index 0cd213c..203e8ef 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -115,50 +115,6 @@ enum { STATE_PIO_WRITING, }; -struct pxa3xx_nand_timing { - unsigned int tCH; /* Enable signal hold time */ - unsigned int tCS; /* Enable signal setup time */ - unsigned int tWH; /* ND_nWE high duration */ - unsigned int tWP; /* ND_nWE pulse time */ - unsigned int tRH; /* ND_nRE high duration */ - unsigned int tRP; /* ND_nRE pulse width */ - unsigned int tR; /* ND_nWE high to ND_nRE low for read */ - unsigned int tWHR; /* ND_nWE high to ND_nRE low for status read */ - unsigned int tAR; /* ND_ALE low to ND_nRE low delay */ -}; - -struct pxa3xx_nand_cmdset { - uint16_t read1; - uint16_t read2; - uint16_t program; - uint16_t read_status; - uint16_t read_id; - uint16_t erase; - uint16_t reset; - uint16_t lock; - uint16_t unlock; - uint16_t lock_status; -}; - -struct pxa3xx_nand_flash { - struct pxa3xx_nand_timing *timing; /* NAND Flash timing */ - struct pxa3xx_nand_cmdset *cmdset; - - uint32_t page_per_block;/* Pages per block (PG_PER_BLK) */ - uint32_t page_size; /* Page size in bytes (PAGE_SZ) */ - uint32_t flash_width; /* Width of Flash memory (DWIDTH_M) */ - uint32_t dfc_width; /* Width of flash controller(DWIDTH_C) */ - uint32_t num_blocks; /* Number of physical blocks in Flash */ - uint32_t chip_id; - - /* NOTE: these are automatically calculated, do not define */ - size_t oob_size; - size_t read_id_bytes; - - unsigned int col_addr_cycles; - unsigned int row_addr_cycles; -}; - struct pxa3xx_nand_info { struct nand_chip nand_chip; -- cgit v0.10.2 From c8ac3f818e1183eab8d08a41b01b6078c5df4b43 Mon Sep 17 00:00:00 2001 From: Enrico Scholz Date: Fri, 29 Aug 2008 12:59:48 +0200 Subject: [MTD] [NAND] pxa3xx_nand: allow to define flash types in the platform data This patch adds 'flash' and 'num_flash' attributes to the platform data. There was added code in the driver to iterate across these attributes in the detect-flash routine. This is done similarly to the existing method which uses a 'builtin_flash_types' field. Signed-off-by: Enrico Scholz Signed-off-by: David Woodhouse diff --git a/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h b/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h index 0dc50d8..6ac9aea 100644 --- a/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h +++ b/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h @@ -58,6 +58,9 @@ struct pxa3xx_nand_platform_data { struct mtd_partition *parts; unsigned int nr_parts; + + struct pxa3xx_nand_flash * const flash; + size_t num_flash; }; extern void pxa3xx_set_nand_info(struct pxa3xx_nand_platform_data *info); diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index 203e8ef..1906aba 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -911,12 +911,26 @@ static int pxa3xx_nand_config_flash(struct pxa3xx_nand_info *info, return 0; } -static int pxa3xx_nand_detect_flash(struct pxa3xx_nand_info *info) +static int pxa3xx_nand_detect_flash(struct pxa3xx_nand_info *info, + const struct pxa3xx_nand_platform_data *pdata) { struct pxa3xx_nand_flash *f; uint32_t id; int i; + for (i = 0; inum_flash; ++i) { + f = pdata->flash + i; + + if (pxa3xx_nand_config_flash(info, f)) + continue; + + if (__readid(info, &id)) + continue; + + if (id == f->chip_id) + return 0; + } + for (i = 0; i < ARRAY_SIZE(builtin_flash_types); i++) { f = builtin_flash_types[i]; @@ -1114,7 +1128,7 @@ static int pxa3xx_nand_probe(struct platform_device *pdev) goto fail_free_buf; } - ret = pxa3xx_nand_detect_flash(info); + ret = pxa3xx_nand_detect_flash(info, pdata); if (ret) { dev_err(&pdev->dev, "failed to detect flash\n"); ret = -ENODEV; -- cgit v0.10.2 From 80ebf20f34c30760cfba7b5e0a418241181d2cd9 Mon Sep 17 00:00:00 2001 From: Enrico Scholz Date: Fri, 29 Aug 2008 12:59:49 +0200 Subject: [MTD] [NAND] pxa3xx_nand: allow to disable builtin flash-type table This patch adds a MTD_NAND_PXA3xx_BUILTIN configuration variables which allows to disable usage of builtin flash-type table. Not enabling this option saves some space in the generated driver. Signed-off-by: Enrico Scholz Signed-off-by: David Woodhouse diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index 8eb2b06..6eebe852 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -334,6 +334,13 @@ config MTD_NAND_PXA3xx This enables the driver for the NAND flash device found on PXA3xx processors +config MTD_NAND_PXA3xx_BUILTIN + bool "Use builtin definitions for some NAND chips (deprecated)" + depends on MTD_NAND_PXA3xx + help + This enables builtin definitions for some NAND chips. This + is deprecated in favor of platform specific data. + config MTD_NAND_CM_X270 tristate "Support for NAND Flash on CM-X270 modules" depends on MTD_NAND && MACH_ARMCORE diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index 1906aba..e492804 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -164,6 +164,7 @@ static int use_dma = 1; module_param(use_dma, bool, 0444); MODULE_PARM_DESC(use_dma, "enable DMA for data transfering to/from NAND HW"); +#ifdef CONFIG_MTD_NAND_PXA3xx_BUILTIN static struct pxa3xx_nand_cmdset smallpage_cmdset = { .read1 = 0x0000, .read2 = 0x0050, @@ -275,6 +276,7 @@ static struct pxa3xx_nand_flash *builtin_flash_types[] = { µn1GbX16, &stm2GbX16, }; +#endif /* CONFIG_MTD_NAND_PXA3xx_BUILTIN */ #define NDTR0_tCH(c) (min((c), 7) << 19) #define NDTR0_tCS(c) (min((c), 7) << 16) @@ -931,6 +933,7 @@ static int pxa3xx_nand_detect_flash(struct pxa3xx_nand_info *info, return 0; } +#ifdef CONFIG_MTD_NAND_PXA3xx_BUILTIN for (i = 0; i < ARRAY_SIZE(builtin_flash_types); i++) { f = builtin_flash_types[i]; @@ -944,6 +947,7 @@ static int pxa3xx_nand_detect_flash(struct pxa3xx_nand_info *info, if (id == f->chip_id) return 0; } +#endif return -ENODEV; } -- cgit v0.10.2 From 7dad482ed0648a40e403d1ed44e0ea92248632f1 Mon Sep 17 00:00:00 2001 From: Enrico Scholz Date: Fri, 29 Aug 2008 12:59:50 +0200 Subject: [MTD] [NAND] pxa3xx_nand: added some 'const' annotations to the exported API This patch marks some attributes as 'const' which are set only once and never be modified by the driver. There are some changes in parameter list and variable declarations too which mark them as 'const'. Signed-off-by: Enrico Scholz Signed-off-by: David Woodhouse diff --git a/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h b/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h index 6ac9aea..cfcb2e2 100644 --- a/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h +++ b/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h @@ -30,8 +30,8 @@ struct pxa3xx_nand_cmdset { }; struct pxa3xx_nand_flash { - struct pxa3xx_nand_timing *timing; /* NAND Flash timing */ - struct pxa3xx_nand_cmdset *cmdset; + const struct pxa3xx_nand_timing *timing; /* NAND Flash timing */ + const struct pxa3xx_nand_cmdset *cmdset; uint32_t page_per_block;/* Pages per block (PG_PER_BLK) */ uint32_t page_size; /* Page size in bytes (PAGE_SZ) */ @@ -56,8 +56,8 @@ struct pxa3xx_nand_platform_data { */ int enable_arbiter; - struct mtd_partition *parts; - unsigned int nr_parts; + const struct mtd_partition *parts; + unsigned int nr_parts; struct pxa3xx_nand_flash * const flash; size_t num_flash; diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index e492804..af17405 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -293,7 +293,7 @@ static struct pxa3xx_nand_flash *builtin_flash_types[] = { #define ns2cycle(ns, clk) (int)(((ns) * (clk / 1000000) / 1000) + 1) static void pxa3xx_nand_set_timing(struct pxa3xx_nand_info *info, - struct pxa3xx_nand_timing *t) + const struct pxa3xx_nand_timing *t) { unsigned long nand_clk = clk_get_rate(info->clk); uint32_t ndtr0, ndtr1; @@ -336,7 +336,7 @@ static int prepare_read_prog_cmd(struct pxa3xx_nand_info *info, uint16_t cmd, int column, int page_addr) { struct pxa3xx_nand_flash *f = info->flash_info; - struct pxa3xx_nand_cmdset *cmdset = f->cmdset; + const struct pxa3xx_nand_cmdset *cmdset = f->cmdset; /* calculate data size */ switch (f->page_size) { @@ -387,7 +387,7 @@ static int prepare_erase_cmd(struct pxa3xx_nand_info *info, static int prepare_other_cmd(struct pxa3xx_nand_info *info, uint16_t cmd) { - struct pxa3xx_nand_cmdset *cmdset = info->flash_info->cmdset; + const struct pxa3xx_nand_cmdset *cmdset = info->flash_info->cmdset; info->ndcb0 = cmd | ((cmd & 0xff00) ? NDCB0_DBC : 0); info->ndcb1 = 0; @@ -623,7 +623,7 @@ static void pxa3xx_nand_cmdfunc(struct mtd_info *mtd, unsigned command, { struct pxa3xx_nand_info *info = mtd->priv; struct pxa3xx_nand_flash *flash_info = info->flash_info; - struct pxa3xx_nand_cmdset *cmdset = flash_info->cmdset; + const struct pxa3xx_nand_cmdset *cmdset = flash_info->cmdset; int ret; info->use_dma = (use_dma) ? 1 : 0; @@ -843,7 +843,7 @@ static int pxa3xx_nand_ecc_correct(struct mtd_info *mtd, static int __readid(struct pxa3xx_nand_info *info, uint32_t *id) { struct pxa3xx_nand_flash *f = info->flash_info; - struct pxa3xx_nand_cmdset *cmdset = f->cmdset; + const struct pxa3xx_nand_cmdset *cmdset = f->cmdset; uint32_t ndcr; uint8_t id_buff[8]; -- cgit v0.10.2 From c8c17c888d936c58ceb28b084a6272d67e10ea28 Mon Sep 17 00:00:00 2001 From: Enrico Scholz Date: Fri, 29 Aug 2008 12:59:51 +0200 Subject: [MTD] [NAND] pxa3xx_nand: moved some helper variables out from platform data This patch moves some attributes out from the platform data into the dynamically created nand device. This results into a cleaner interface and allows to use constant pxa3xx_nand_flash definitions. Signed-off-by: Enrico Scholz Signed-off-by: David Woodhouse diff --git a/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h b/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h index cfcb2e2..eb35fca 100644 --- a/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h +++ b/arch/arm/mach-pxa/include/mach/pxa3xx_nand.h @@ -39,13 +39,6 @@ struct pxa3xx_nand_flash { uint32_t dfc_width; /* Width of flash controller(DWIDTH_C) */ uint32_t num_blocks; /* Number of physical blocks in Flash */ uint32_t chip_id; - - /* NOTE: these are automatically calculated, do not define */ - size_t oob_size; - size_t read_id_bytes; - - unsigned int col_addr_cycles; - unsigned int row_addr_cycles; }; struct pxa3xx_nand_platform_data { @@ -59,7 +52,7 @@ struct pxa3xx_nand_platform_data { const struct mtd_partition *parts; unsigned int nr_parts; - struct pxa3xx_nand_flash * const flash; + const struct pxa3xx_nand_flash * flash; size_t num_flash; }; diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index af17405..bc37f55 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -119,7 +119,7 @@ struct pxa3xx_nand_info { struct nand_chip nand_chip; struct platform_device *pdev; - struct pxa3xx_nand_flash *flash_info; + const struct pxa3xx_nand_flash *flash_info; struct clk *clk; void __iomem *mmio_base; @@ -158,6 +158,13 @@ struct pxa3xx_nand_info { uint32_t ndcb0; uint32_t ndcb1; uint32_t ndcb2; + + /* calculated from pxa3xx_nand_flash data */ + size_t oob_size; + size_t read_id_bytes; + + unsigned int col_addr_cycles; + unsigned int row_addr_cycles; }; static int use_dma = 1; @@ -335,7 +342,7 @@ static int wait_for_event(struct pxa3xx_nand_info *info, uint32_t event) static int prepare_read_prog_cmd(struct pxa3xx_nand_info *info, uint16_t cmd, int column, int page_addr) { - struct pxa3xx_nand_flash *f = info->flash_info; + const struct pxa3xx_nand_flash *f = info->flash_info; const struct pxa3xx_nand_cmdset *cmdset = f->cmdset; /* calculate data size */ @@ -354,14 +361,14 @@ static int prepare_read_prog_cmd(struct pxa3xx_nand_info *info, info->ndcb0 = cmd | ((cmd & 0xff00) ? NDCB0_DBC : 0); info->ndcb1 = 0; info->ndcb2 = 0; - info->ndcb0 |= NDCB0_ADDR_CYC(f->row_addr_cycles + f->col_addr_cycles); + info->ndcb0 |= NDCB0_ADDR_CYC(info->row_addr_cycles + info->col_addr_cycles); - if (f->col_addr_cycles == 2) { + if (info->col_addr_cycles == 2) { /* large block, 2 cycles for column address * row address starts from 3rd cycle */ info->ndcb1 |= (page_addr << 16) | (column & 0xffff); - if (f->row_addr_cycles == 3) + if (info->row_addr_cycles == 3) info->ndcb2 = (page_addr >> 16) & 0xff; } else /* small block, 1 cycles for column address @@ -622,7 +629,7 @@ static void pxa3xx_nand_cmdfunc(struct mtd_info *mtd, unsigned command, int column, int page_addr) { struct pxa3xx_nand_info *info = mtd->priv; - struct pxa3xx_nand_flash *flash_info = info->flash_info; + const struct pxa3xx_nand_flash *flash_info = info->flash_info; const struct pxa3xx_nand_cmdset *cmdset = flash_info->cmdset; int ret; @@ -701,7 +708,7 @@ static void pxa3xx_nand_cmdfunc(struct mtd_info *mtd, unsigned command, info->use_dma = 0; /* force PIO read */ info->buf_start = 0; info->buf_count = (command == NAND_CMD_READID) ? - flash_info->read_id_bytes : 1; + info->read_id_bytes : 1; if (prepare_other_cmd(info, (command == NAND_CMD_READID) ? cmdset->read_id : cmdset->read_status)) @@ -842,7 +849,7 @@ static int pxa3xx_nand_ecc_correct(struct mtd_info *mtd, static int __readid(struct pxa3xx_nand_info *info, uint32_t *id) { - struct pxa3xx_nand_flash *f = info->flash_info; + const struct pxa3xx_nand_flash *f = info->flash_info; const struct pxa3xx_nand_cmdset *cmdset = f->cmdset; uint32_t ndcr; uint8_t id_buff[8]; @@ -872,7 +879,7 @@ fail_timeout: } static int pxa3xx_nand_config_flash(struct pxa3xx_nand_info *info, - struct pxa3xx_nand_flash *f) + const struct pxa3xx_nand_flash *f) { struct platform_device *pdev = info->pdev; struct pxa3xx_nand_platform_data *pdata = pdev->dev.platform_data; @@ -885,25 +892,25 @@ static int pxa3xx_nand_config_flash(struct pxa3xx_nand_info *info, return -EINVAL; /* calculate flash information */ - f->oob_size = (f->page_size == 2048) ? 64 : 16; - f->read_id_bytes = (f->page_size == 2048) ? 4 : 2; + info->oob_size = (f->page_size == 2048) ? 64 : 16; + info->read_id_bytes = (f->page_size == 2048) ? 4 : 2; /* calculate addressing information */ - f->col_addr_cycles = (f->page_size == 2048) ? 2 : 1; + info->col_addr_cycles = (f->page_size == 2048) ? 2 : 1; if (f->num_blocks * f->page_per_block > 65536) - f->row_addr_cycles = 3; + info->row_addr_cycles = 3; else - f->row_addr_cycles = 2; + info->row_addr_cycles = 2; ndcr |= (pdata->enable_arbiter) ? NDCR_ND_ARB_EN : 0; - ndcr |= (f->col_addr_cycles == 2) ? NDCR_RA_START : 0; + ndcr |= (info->col_addr_cycles == 2) ? NDCR_RA_START : 0; ndcr |= (f->page_per_block == 64) ? NDCR_PG_PER_BLK : 0; ndcr |= (f->page_size == 2048) ? NDCR_PAGE_SZ : 0; ndcr |= (f->flash_width == 16) ? NDCR_DWIDTH_M : 0; ndcr |= (f->dfc_width == 16) ? NDCR_DWIDTH_C : 0; - ndcr |= NDCR_RD_ID_CNT(f->read_id_bytes); + ndcr |= NDCR_RD_ID_CNT(info->read_id_bytes); ndcr |= NDCR_SPARE_EN; /* enable spare by default */ info->reg_ndcr = ndcr; @@ -916,7 +923,7 @@ static int pxa3xx_nand_config_flash(struct pxa3xx_nand_info *info, static int pxa3xx_nand_detect_flash(struct pxa3xx_nand_info *info, const struct pxa3xx_nand_platform_data *pdata) { - struct pxa3xx_nand_flash *f; + const struct pxa3xx_nand_flash *f; uint32_t id; int i; @@ -1011,7 +1018,7 @@ static struct nand_ecclayout hw_largepage_ecclayout = { static void pxa3xx_nand_init_mtd(struct mtd_info *mtd, struct pxa3xx_nand_info *info) { - struct pxa3xx_nand_flash *f = info->flash_info; + const struct pxa3xx_nand_flash *f = info->flash_info; struct nand_chip *this = &info->nand_chip; this->options = (f->flash_width == 16) ? NAND_BUSWIDTH_16: 0; -- cgit v0.10.2 From 2675e9447bb5c861dbd29c5fe55b7ce2ad3ff0f5 Mon Sep 17 00:00:00 2001 From: Enrico Scholz Date: Fri, 29 Aug 2008 12:59:52 +0200 Subject: [MTD] [NAND] pxa3xx_nand: added warning which tells id of detected NAND Minor patch to help debugging of NAND detection. Signed-off-by: Enrico Scholz Signed-off-by: David Woodhouse diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index bc37f55..c0fa9c9 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -924,7 +924,7 @@ static int pxa3xx_nand_detect_flash(struct pxa3xx_nand_info *info, const struct pxa3xx_nand_platform_data *pdata) { const struct pxa3xx_nand_flash *f; - uint32_t id; + uint32_t id = -1; int i; for (i = 0; inum_flash; ++i) { @@ -956,6 +956,9 @@ static int pxa3xx_nand_detect_flash(struct pxa3xx_nand_info *info, } #endif + dev_warn(&info->pdev->dev, + "failed to detect configured nand flash; found %04x instead of\n", + id); return -ENODEV; } -- cgit v0.10.2 From 34f6e15786293e8d6ed05f9c19ed784ff15d2702 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Tue, 2 Sep 2008 17:16:59 +0200 Subject: [MTD] [NAND] Freescale i.MX2 NAND driver This patch adds support for the integrated NAND flash controller of the i.MX2 and i.MX3 family. It is tested on MX27 but should work on MX3 aswell. Signed-off-by: Sascha Hauer Acked-by: Juergen Beisert Signed-off-by: David Woodhouse diff --git a/arch/arm/plat-mxc/include/mach/mxc_nand.h b/arch/arm/plat-mxc/include/mach/mxc_nand.h new file mode 100644 index 0000000..2b972df --- /dev/null +++ b/arch/arm/plat-mxc/include/mach/mxc_nand.h @@ -0,0 +1,27 @@ +/* + * Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved. + * Copyright 2008 Sascha Hauer, kernel@pengutronix.de + * + * 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., 51 Franklin Street, Fifth Floor, Boston, + * MA 02110-1301, USA. + */ + +#ifndef __ASM_ARCH_NAND_H +#define __ASM_ARCH_NAND_H + +struct mxc_nand_platform_data { + int width; /* data bus width in bytes */ + int hw_ecc; /* 0 if supress hardware ECC */ +}; +#endif /* __ASM_ARCH_NAND_H */ diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index 6eebe852..7153854 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -407,4 +407,11 @@ config MTD_NAND_FSL_UPM Enables support for NAND Flash chips wired onto Freescale PowerPC processor localbus with User-Programmable Machine support. +config MTD_NAND_MXC + tristate "MXC NAND support" + depends on ARCH_MX2 + help + This enables the driver for the NAND flash controller on the + MXC processors. + endif # MTD_NAND diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile index 8540c46..e0fee04 100644 --- a/drivers/mtd/nand/Makefile +++ b/drivers/mtd/nand/Makefile @@ -33,5 +33,6 @@ obj-$(CONFIG_MTD_NAND_PASEMI) += pasemi_nand.o obj-$(CONFIG_MTD_NAND_ORION) += orion_nand.o obj-$(CONFIG_MTD_NAND_FSL_ELBC) += fsl_elbc_nand.o obj-$(CONFIG_MTD_NAND_FSL_UPM) += fsl_upm.o +obj-$(CONFIG_MTD_NAND_MXC) += mxc_nand.o nand-objs := nand_base.o nand_bbt.o diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c new file mode 100644 index 0000000..21fd4f1 --- /dev/null +++ b/drivers/mtd/nand/mxc_nand.c @@ -0,0 +1,1077 @@ +/* + * Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved. + * Copyright 2008 Sascha Hauer, kernel@pengutronix.de + * + * 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., 51 Franklin Street, Fifth Floor, Boston, + * MA 02110-1301, USA. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define DRIVER_NAME "mxc_nand" + +/* Addresses for NFC registers */ +#define NFC_BUF_SIZE 0xE00 +#define NFC_BUF_ADDR 0xE04 +#define NFC_FLASH_ADDR 0xE06 +#define NFC_FLASH_CMD 0xE08 +#define NFC_CONFIG 0xE0A +#define NFC_ECC_STATUS_RESULT 0xE0C +#define NFC_RSLTMAIN_AREA 0xE0E +#define NFC_RSLTSPARE_AREA 0xE10 +#define NFC_WRPROT 0xE12 +#define NFC_UNLOCKSTART_BLKADDR 0xE14 +#define NFC_UNLOCKEND_BLKADDR 0xE16 +#define NFC_NF_WRPRST 0xE18 +#define NFC_CONFIG1 0xE1A +#define NFC_CONFIG2 0xE1C + +/* Addresses for NFC RAM BUFFER Main area 0 */ +#define MAIN_AREA0 0x000 +#define MAIN_AREA1 0x200 +#define MAIN_AREA2 0x400 +#define MAIN_AREA3 0x600 + +/* Addresses for NFC SPARE BUFFER Spare area 0 */ +#define SPARE_AREA0 0x800 +#define SPARE_AREA1 0x810 +#define SPARE_AREA2 0x820 +#define SPARE_AREA3 0x830 + +/* Set INT to 0, FCMD to 1, rest to 0 in NFC_CONFIG2 Register + * for Command operation */ +#define NFC_CMD 0x1 + +/* Set INT to 0, FADD to 1, rest to 0 in NFC_CONFIG2 Register + * for Address operation */ +#define NFC_ADDR 0x2 + +/* Set INT to 0, FDI to 1, rest to 0 in NFC_CONFIG2 Register + * for Input operation */ +#define NFC_INPUT 0x4 + +/* Set INT to 0, FDO to 001, rest to 0 in NFC_CONFIG2 Register + * for Data Output operation */ +#define NFC_OUTPUT 0x8 + +/* Set INT to 0, FD0 to 010, rest to 0 in NFC_CONFIG2 Register + * for Read ID operation */ +#define NFC_ID 0x10 + +/* Set INT to 0, FDO to 100, rest to 0 in NFC_CONFIG2 Register + * for Read Status operation */ +#define NFC_STATUS 0x20 + +/* Set INT to 1, rest to 0 in NFC_CONFIG2 Register for Read + * Status operation */ +#define NFC_INT 0x8000 + +#define NFC_SP_EN (1 << 2) +#define NFC_ECC_EN (1 << 3) +#define NFC_INT_MSK (1 << 4) +#define NFC_BIG (1 << 5) +#define NFC_RST (1 << 6) +#define NFC_CE (1 << 7) +#define NFC_ONE_CYCLE (1 << 8) + +struct mxc_nand_host { + struct mtd_info mtd; + struct nand_chip nand; + struct mtd_partition *parts; + struct device *dev; + + void __iomem *regs; + int spare_only; + int status_request; + int pagesize_2k; + uint16_t col_addr; + struct clk *clk; + int clk_act; + int irq; + + wait_queue_head_t irq_waitq; +}; + +/* Define delays in microsec for NAND device operations */ +#define TROP_US_DELAY 2000 +/* Macros to get byte and bit positions of ECC */ +#define COLPOS(x) ((x) >> 3) +#define BITPOS(x) ((x) & 0xf) + +/* Define single bit Error positions in Main & Spare area */ +#define MAIN_SINGLEBIT_ERROR 0x4 +#define SPARE_SINGLEBIT_ERROR 0x1 + +/* OOB placement block for use with hardware ecc generation */ +static struct nand_ecclayout nand_hw_eccoob_8 = { + .eccbytes = 5, + .eccpos = {6, 7, 8, 9, 10}, + .oobfree = {{0, 5}, {11, 5}, } +}; + +static struct nand_ecclayout nand_hw_eccoob_16 = { + .eccbytes = 5, + .eccpos = {6, 7, 8, 9, 10}, + .oobfree = {{0, 6}, {12, 4}, } +}; + +#ifdef CONFIG_MTD_PARTITIONS +static const char *part_probes[] = { "RedBoot", "cmdlinepart", NULL }; +#endif + +static irqreturn_t mxc_nfc_irq(int irq, void *dev_id) +{ + struct mxc_nand_host *host = dev_id; + + uint16_t tmp; + + tmp = readw(host->regs + NFC_CONFIG1); + tmp |= NFC_INT_MSK; /* Disable interrupt */ + writew(tmp, host->regs + NFC_CONFIG1); + + wake_up(&host->irq_waitq); + + return IRQ_HANDLED; +} + +/* This function polls the NANDFC to wait for the basic operation to + * complete by checking the INT bit of config2 register. + */ +static void wait_op_done(struct mxc_nand_host *host, int max_retries, + uint16_t param, int useirq) +{ + uint32_t tmp; + + if (useirq) { + if ((readw(host->regs + NFC_CONFIG2) & NFC_INT) == 0) { + + tmp = readw(host->regs + NFC_CONFIG1); + tmp &= ~NFC_INT_MSK; /* Enable interrupt */ + writew(tmp, host->regs + NFC_CONFIG1); + + wait_event(host->irq_waitq, + readw(host->regs + NFC_CONFIG2) & NFC_INT); + + tmp = readw(host->regs + NFC_CONFIG2); + tmp &= ~NFC_INT; + writew(tmp, host->regs + NFC_CONFIG2); + } + } else { + while (max_retries-- > 0) { + if (readw(host->regs + NFC_CONFIG2) & NFC_INT) { + tmp = readw(host->regs + NFC_CONFIG2); + tmp &= ~NFC_INT; + writew(tmp, host->regs + NFC_CONFIG2); + break; + } + udelay(1); + } + if (max_retries <= 0) + DEBUG(MTD_DEBUG_LEVEL0, "%s(%d): INT not set\n", + __func__, param); + } +} + +/* This function issues the specified command to the NAND device and + * waits for completion. */ +static void send_cmd(struct mxc_nand_host *host, uint16_t cmd, int useirq) +{ + DEBUG(MTD_DEBUG_LEVEL3, "send_cmd(host, 0x%x, %d)\n", cmd, useirq); + + writew(cmd, host->regs + NFC_FLASH_CMD); + writew(NFC_CMD, host->regs + NFC_CONFIG2); + + /* Wait for operation to complete */ + wait_op_done(host, TROP_US_DELAY, cmd, useirq); +} + +/* This function sends an address (or partial address) to the + * NAND device. The address is used to select the source/destination for + * a NAND command. */ +static void send_addr(struct mxc_nand_host *host, uint16_t addr, int islast) +{ + DEBUG(MTD_DEBUG_LEVEL3, "send_addr(host, 0x%x %d)\n", addr, islast); + + writew(addr, host->regs + NFC_FLASH_ADDR); + writew(NFC_ADDR, host->regs + NFC_CONFIG2); + + /* Wait for operation to complete */ + wait_op_done(host, TROP_US_DELAY, addr, islast); +} + +/* This function requests the NANDFC to initate the transfer + * of data currently in the NANDFC RAM buffer to the NAND device. */ +static void send_prog_page(struct mxc_nand_host *host, uint8_t buf_id, + int spare_only) +{ + DEBUG(MTD_DEBUG_LEVEL3, "send_prog_page (%d)\n", spare_only); + + /* NANDFC buffer 0 is used for page read/write */ + writew(buf_id, host->regs + NFC_BUF_ADDR); + + /* Configure spare or page+spare access */ + if (!host->pagesize_2k) { + uint16_t config1 = readw(host->regs + NFC_CONFIG1); + if (spare_only) + config1 |= NFC_SP_EN; + else + config1 &= ~(NFC_SP_EN); + writew(config1, host->regs + NFC_CONFIG1); + } + + writew(NFC_INPUT, host->regs + NFC_CONFIG2); + + /* Wait for operation to complete */ + wait_op_done(host, TROP_US_DELAY, spare_only, true); +} + +/* Requests NANDFC to initated the transfer of data from the + * NAND device into in the NANDFC ram buffer. */ +static void send_read_page(struct mxc_nand_host *host, uint8_t buf_id, + int spare_only) +{ + DEBUG(MTD_DEBUG_LEVEL3, "send_read_page (%d)\n", spare_only); + + /* NANDFC buffer 0 is used for page read/write */ + writew(buf_id, host->regs + NFC_BUF_ADDR); + + /* Configure spare or page+spare access */ + if (!host->pagesize_2k) { + uint32_t config1 = readw(host->regs + NFC_CONFIG1); + if (spare_only) + config1 |= NFC_SP_EN; + else + config1 &= ~NFC_SP_EN; + writew(config1, host->regs + NFC_CONFIG1); + } + + writew(NFC_OUTPUT, host->regs + NFC_CONFIG2); + + /* Wait for operation to complete */ + wait_op_done(host, TROP_US_DELAY, spare_only, true); +} + +/* Request the NANDFC to perform a read of the NAND device ID. */ +static void send_read_id(struct mxc_nand_host *host) +{ + struct nand_chip *this = &host->nand; + uint16_t tmp; + + /* NANDFC buffer 0 is used for device ID output */ + writew(0x0, host->regs + NFC_BUF_ADDR); + + /* Read ID into main buffer */ + tmp = readw(host->regs + NFC_CONFIG1); + tmp &= ~NFC_SP_EN; + writew(tmp, host->regs + NFC_CONFIG1); + + writew(NFC_ID, host->regs + NFC_CONFIG2); + + /* Wait for operation to complete */ + wait_op_done(host, TROP_US_DELAY, 0, true); + + if (this->options & NAND_BUSWIDTH_16) { + void __iomem *main_buf = host->regs + MAIN_AREA0; + /* compress the ID info */ + writeb(readb(main_buf + 2), main_buf + 1); + writeb(readb(main_buf + 4), main_buf + 2); + writeb(readb(main_buf + 6), main_buf + 3); + writeb(readb(main_buf + 8), main_buf + 4); + writeb(readb(main_buf + 10), main_buf + 5); + } +} + +/* This function requests the NANDFC to perform a read of the + * NAND device status and returns the current status. */ +static uint16_t get_dev_status(struct mxc_nand_host *host) +{ + void __iomem *main_buf = host->regs + MAIN_AREA1; + uint32_t store; + uint16_t ret, tmp; + /* Issue status request to NAND device */ + + /* store the main area1 first word, later do recovery */ + store = readl(main_buf); + /* NANDFC buffer 1 is used for device status to prevent + * corruption of read/write buffer on status requests. */ + writew(1, host->regs + NFC_BUF_ADDR); + + /* Read status into main buffer */ + tmp = readw(host->regs + NFC_CONFIG1); + tmp &= ~NFC_SP_EN; + writew(tmp, host->regs + NFC_CONFIG1); + + writew(NFC_STATUS, host->regs + NFC_CONFIG2); + + /* Wait for operation to complete */ + wait_op_done(host, TROP_US_DELAY, 0, true); + + /* Status is placed in first word of main buffer */ + /* get status, then recovery area 1 data */ + ret = readw(main_buf); + writel(store, main_buf); + + return ret; +} + +/* This functions is used by upper layer to checks if device is ready */ +static int mxc_nand_dev_ready(struct mtd_info *mtd) +{ + /* + * NFC handles R/B internally. Therefore, this function + * always returns status as ready. + */ + return 1; +} + +static void mxc_nand_enable_hwecc(struct mtd_info *mtd, int mode) +{ + /* + * If HW ECC is enabled, we turn it on during init. There is + * no need to enable again here. + */ +} + +static int mxc_nand_correct_data(struct mtd_info *mtd, u_char *dat, + u_char *read_ecc, u_char *calc_ecc) +{ + struct nand_chip *nand_chip = mtd->priv; + struct mxc_nand_host *host = nand_chip->priv; + + /* + * 1-Bit errors are automatically corrected in HW. No need for + * additional correction. 2-Bit errors cannot be corrected by + * HW ECC, so we need to return failure + */ + uint16_t ecc_status = readw(host->regs + NFC_ECC_STATUS_RESULT); + + if (((ecc_status & 0x3) == 2) || ((ecc_status >> 2) == 2)) { + DEBUG(MTD_DEBUG_LEVEL0, + "MXC_NAND: HWECC uncorrectable 2-bit ECC error\n"); + return -1; + } + + return 0; +} + +static int mxc_nand_calculate_ecc(struct mtd_info *mtd, const u_char *dat, + u_char *ecc_code) +{ + return 0; +} + +static u_char mxc_nand_read_byte(struct mtd_info *mtd) +{ + struct nand_chip *nand_chip = mtd->priv; + struct mxc_nand_host *host = nand_chip->priv; + uint8_t ret = 0; + uint16_t col, rd_word; + uint16_t __iomem *main_buf = host->regs + MAIN_AREA0; + uint16_t __iomem *spare_buf = host->regs + SPARE_AREA0; + + /* Check for status request */ + if (host->status_request) + return get_dev_status(host) & 0xFF; + + /* Get column for 16-bit access */ + col = host->col_addr >> 1; + + /* If we are accessing the spare region */ + if (host->spare_only) + rd_word = readw(&spare_buf[col]); + else + rd_word = readw(&main_buf[col]); + + /* Pick upper/lower byte of word from RAM buffer */ + if (host->col_addr & 0x1) + ret = (rd_word >> 8) & 0xFF; + else + ret = rd_word & 0xFF; + + /* Update saved column address */ + host->col_addr++; + + return ret; +} + +static uint16_t mxc_nand_read_word(struct mtd_info *mtd) +{ + struct nand_chip *nand_chip = mtd->priv; + struct mxc_nand_host *host = nand_chip->priv; + uint16_t col, rd_word, ret; + uint16_t __iomem *p; + + DEBUG(MTD_DEBUG_LEVEL3, + "mxc_nand_read_word(col = %d)\n", host->col_addr); + + col = host->col_addr; + /* Adjust saved column address */ + if (col < mtd->writesize && host->spare_only) + col += mtd->writesize; + + if (col < mtd->writesize) + p = (host->regs + MAIN_AREA0) + (col >> 1); + else + p = (host->regs + SPARE_AREA0) + ((col - mtd->writesize) >> 1); + + if (col & 1) { + rd_word = readw(p); + ret = (rd_word >> 8) & 0xff; + rd_word = readw(&p[1]); + ret |= (rd_word << 8) & 0xff00; + + } else + ret = readw(p); + + /* Update saved column address */ + host->col_addr = col + 2; + + return ret; +} + +/* Write data of length len to buffer buf. The data to be + * written on NAND Flash is first copied to RAMbuffer. After the Data Input + * Operation by the NFC, the data is written to NAND Flash */ +static void mxc_nand_write_buf(struct mtd_info *mtd, + const u_char *buf, int len) +{ + struct nand_chip *nand_chip = mtd->priv; + struct mxc_nand_host *host = nand_chip->priv; + int n, col, i = 0; + + DEBUG(MTD_DEBUG_LEVEL3, + "mxc_nand_write_buf(col = %d, len = %d)\n", host->col_addr, + len); + + col = host->col_addr; + + /* Adjust saved column address */ + if (col < mtd->writesize && host->spare_only) + col += mtd->writesize; + + n = mtd->writesize + mtd->oobsize - col; + n = min(len, n); + + DEBUG(MTD_DEBUG_LEVEL3, + "%s:%d: col = %d, n = %d\n", __func__, __LINE__, col, n); + + while (n) { + void __iomem *p; + + if (col < mtd->writesize) + p = host->regs + MAIN_AREA0 + (col & ~3); + else + p = host->regs + SPARE_AREA0 - + mtd->writesize + (col & ~3); + + DEBUG(MTD_DEBUG_LEVEL3, "%s:%d: p = %p\n", __func__, + __LINE__, p); + + if (((col | (int)&buf[i]) & 3) || n < 16) { + uint32_t data = 0; + + if (col & 3 || n < 4) + data = readl(p); + + switch (col & 3) { + case 0: + if (n) { + data = (data & 0xffffff00) | + (buf[i++] << 0); + n--; + col++; + } + case 1: + if (n) { + data = (data & 0xffff00ff) | + (buf[i++] << 8); + n--; + col++; + } + case 2: + if (n) { + data = (data & 0xff00ffff) | + (buf[i++] << 16); + n--; + col++; + } + case 3: + if (n) { + data = (data & 0x00ffffff) | + (buf[i++] << 24); + n--; + col++; + } + } + + writel(data, p); + } else { + int m = mtd->writesize - col; + + if (col >= mtd->writesize) + m += mtd->oobsize; + + m = min(n, m) & ~3; + + DEBUG(MTD_DEBUG_LEVEL3, + "%s:%d: n = %d, m = %d, i = %d, col = %d\n", + __func__, __LINE__, n, m, i, col); + + memcpy(p, &buf[i], m); + col += m; + i += m; + n -= m; + } + } + /* Update saved column address */ + host->col_addr = col; +} + +/* Read the data buffer from the NAND Flash. To read the data from NAND + * Flash first the data output cycle is initiated by the NFC, which copies + * the data to RAMbuffer. This data of length len is then copied to buffer buf. + */ +static void mxc_nand_read_buf(struct mtd_info *mtd, u_char *buf, int len) +{ + struct nand_chip *nand_chip = mtd->priv; + struct mxc_nand_host *host = nand_chip->priv; + int n, col, i = 0; + + DEBUG(MTD_DEBUG_LEVEL3, + "mxc_nand_read_buf(col = %d, len = %d)\n", host->col_addr, len); + + col = host->col_addr; + + /* Adjust saved column address */ + if (col < mtd->writesize && host->spare_only) + col += mtd->writesize; + + n = mtd->writesize + mtd->oobsize - col; + n = min(len, n); + + while (n) { + void __iomem *p; + + if (col < mtd->writesize) + p = host->regs + MAIN_AREA0 + (col & ~3); + else + p = host->regs + SPARE_AREA0 - + mtd->writesize + (col & ~3); + + if (((col | (int)&buf[i]) & 3) || n < 16) { + uint32_t data; + + data = readl(p); + switch (col & 3) { + case 0: + if (n) { + buf[i++] = (uint8_t) (data); + n--; + col++; + } + case 1: + if (n) { + buf[i++] = (uint8_t) (data >> 8); + n--; + col++; + } + case 2: + if (n) { + buf[i++] = (uint8_t) (data >> 16); + n--; + col++; + } + case 3: + if (n) { + buf[i++] = (uint8_t) (data >> 24); + n--; + col++; + } + } + } else { + int m = mtd->writesize - col; + + if (col >= mtd->writesize) + m += mtd->oobsize; + + m = min(n, m) & ~3; + memcpy(&buf[i], p, m); + col += m; + i += m; + n -= m; + } + } + /* Update saved column address */ + host->col_addr = col; + +} + +/* Used by the upper layer to verify the data in NAND Flash + * with the data in the buf. */ +static int mxc_nand_verify_buf(struct mtd_info *mtd, + const u_char *buf, int len) +{ + return -EFAULT; +} + +/* This function is used by upper layer for select and + * deselect of the NAND chip */ +static void mxc_nand_select_chip(struct mtd_info *mtd, int chip) +{ + struct nand_chip *nand_chip = mtd->priv; + struct mxc_nand_host *host = nand_chip->priv; + +#ifdef CONFIG_MTD_NAND_MXC_FORCE_CE + if (chip > 0) { + DEBUG(MTD_DEBUG_LEVEL0, + "ERROR: Illegal chip select (chip = %d)\n", chip); + return; + } + + if (chip == -1) { + writew(readw(host->regs + NFC_CONFIG1) & ~NFC_CE, + host->regs + NFC_CONFIG1); + return; + } + + writew(readw(host->regs + NFC_CONFIG1) | NFC_CE, + host->regs + NFC_CONFIG1); +#endif + + switch (chip) { + case -1: + /* Disable the NFC clock */ + if (host->clk_act) { + clk_disable(host->clk); + host->clk_act = 0; + } + break; + case 0: + /* Enable the NFC clock */ + if (!host->clk_act) { + clk_enable(host->clk); + host->clk_act = 1; + } + break; + + default: + break; + } +} + +/* Used by the upper layer to write command to NAND Flash for + * different operations to be carried out on NAND Flash */ +static void mxc_nand_command(struct mtd_info *mtd, unsigned command, + int column, int page_addr) +{ + struct nand_chip *nand_chip = mtd->priv; + struct mxc_nand_host *host = nand_chip->priv; + int useirq = true; + + DEBUG(MTD_DEBUG_LEVEL3, + "mxc_nand_command (cmd = 0x%x, col = 0x%x, page = 0x%x)\n", + command, column, page_addr); + + /* Reset command state information */ + host->status_request = false; + + /* Command pre-processing step */ + switch (command) { + + case NAND_CMD_STATUS: + host->col_addr = 0; + host->status_request = true; + break; + + case NAND_CMD_READ0: + host->col_addr = column; + host->spare_only = false; + useirq = false; + break; + + case NAND_CMD_READOOB: + host->col_addr = column; + host->spare_only = true; + useirq = false; + if (host->pagesize_2k) + command = NAND_CMD_READ0; /* only READ0 is valid */ + break; + + case NAND_CMD_SEQIN: + if (column >= mtd->writesize) { + /* + * FIXME: before send SEQIN command for write OOB, + * We must read one page out. + * For K9F1GXX has no READ1 command to set current HW + * pointer to spare area, we must write the whole page + * including OOB together. + */ + if (host->pagesize_2k) + /* call ourself to read a page */ + mxc_nand_command(mtd, NAND_CMD_READ0, 0, + page_addr); + + host->col_addr = column - mtd->writesize; + host->spare_only = true; + + /* Set program pointer to spare region */ + if (!host->pagesize_2k) + send_cmd(host, NAND_CMD_READOOB, false); + } else { + host->spare_only = false; + host->col_addr = column; + + /* Set program pointer to page start */ + if (!host->pagesize_2k) + send_cmd(host, NAND_CMD_READ0, false); + } + useirq = false; + break; + + case NAND_CMD_PAGEPROG: + send_prog_page(host, 0, host->spare_only); + + if (host->pagesize_2k) { + /* data in 4 areas datas */ + send_prog_page(host, 1, host->spare_only); + send_prog_page(host, 2, host->spare_only); + send_prog_page(host, 3, host->spare_only); + } + + break; + + case NAND_CMD_ERASE1: + useirq = false; + break; + } + + /* Write out the command to the device. */ + send_cmd(host, command, useirq); + + /* Write out column address, if necessary */ + if (column != -1) { + /* + * MXC NANDFC can only perform full page+spare or + * spare-only read/write. When the upper layers + * layers perform a read/write buf operation, + * we will used the saved column adress to index into + * the full page. + */ + send_addr(host, 0, page_addr == -1); + if (host->pagesize_2k) + /* another col addr cycle for 2k page */ + send_addr(host, 0, false); + } + + /* Write out page address, if necessary */ + if (page_addr != -1) { + /* paddr_0 - p_addr_7 */ + send_addr(host, (page_addr & 0xff), false); + + if (host->pagesize_2k) { + send_addr(host, (page_addr >> 8) & 0xFF, false); + if (mtd->size >= 0x40000000) + send_addr(host, (page_addr >> 16) & 0xff, true); + } else { + /* One more address cycle for higher density devices */ + if (mtd->size >= 0x4000000) { + /* paddr_8 - paddr_15 */ + send_addr(host, (page_addr >> 8) & 0xff, false); + send_addr(host, (page_addr >> 16) & 0xff, true); + } else + /* paddr_8 - paddr_15 */ + send_addr(host, (page_addr >> 8) & 0xff, true); + } + } + + /* Command post-processing step */ + switch (command) { + + case NAND_CMD_RESET: + break; + + case NAND_CMD_READOOB: + case NAND_CMD_READ0: + if (host->pagesize_2k) { + /* send read confirm command */ + send_cmd(host, NAND_CMD_READSTART, true); + /* read for each AREA */ + send_read_page(host, 0, host->spare_only); + send_read_page(host, 1, host->spare_only); + send_read_page(host, 2, host->spare_only); + send_read_page(host, 3, host->spare_only); + } else + send_read_page(host, 0, host->spare_only); + break; + + case NAND_CMD_READID: + send_read_id(host); + break; + + case NAND_CMD_PAGEPROG: + break; + + case NAND_CMD_STATUS: + break; + + case NAND_CMD_ERASE2: + break; + } +} + +static int __init mxcnd_probe(struct platform_device *pdev) +{ + struct nand_chip *this; + struct mtd_info *mtd; + struct mxc_nand_platform_data *pdata = pdev->dev.platform_data; + struct mxc_nand_host *host; + struct resource *res; + uint16_t tmp; + int err = 0, nr_parts = 0; + + /* Allocate memory for MTD device structure and private data */ + host = kzalloc(sizeof(struct mxc_nand_host), GFP_KERNEL); + if (!host) + return -ENOMEM; + + host->dev = &pdev->dev; + /* structures must be linked */ + this = &host->nand; + mtd = &host->mtd; + mtd->priv = this; + mtd->owner = THIS_MODULE; + + /* 50 us command delay time */ + this->chip_delay = 5; + + this->priv = host; + this->dev_ready = mxc_nand_dev_ready; + this->cmdfunc = mxc_nand_command; + this->select_chip = mxc_nand_select_chip; + this->read_byte = mxc_nand_read_byte; + this->read_word = mxc_nand_read_word; + this->write_buf = mxc_nand_write_buf; + this->read_buf = mxc_nand_read_buf; + this->verify_buf = mxc_nand_verify_buf; + + host->clk = clk_get(&pdev->dev, "nfc_clk"); + if (IS_ERR(host->clk)) + goto eclk; + + clk_enable(host->clk); + host->clk_act = 1; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + err = -ENODEV; + goto eres; + } + + host->regs = ioremap(res->start, res->end - res->start + 1); + if (!host->regs) { + err = -EIO; + goto eres; + } + + tmp = readw(host->regs + NFC_CONFIG1); + tmp |= NFC_INT_MSK; + writew(tmp, host->regs + NFC_CONFIG1); + + init_waitqueue_head(&host->irq_waitq); + + host->irq = platform_get_irq(pdev, 0); + + err = request_irq(host->irq, mxc_nfc_irq, 0, "mxc_nd", host); + if (err) + goto eirq; + + if (pdata->hw_ecc) { + this->ecc.calculate = mxc_nand_calculate_ecc; + this->ecc.hwctl = mxc_nand_enable_hwecc; + this->ecc.correct = mxc_nand_correct_data; + this->ecc.mode = NAND_ECC_HW; + this->ecc.size = 512; + this->ecc.bytes = 3; + this->ecc.layout = &nand_hw_eccoob_8; + tmp = readw(host->regs + NFC_CONFIG1); + tmp |= NFC_ECC_EN; + writew(tmp, host->regs + NFC_CONFIG1); + } else { + this->ecc.size = 512; + this->ecc.bytes = 3; + this->ecc.layout = &nand_hw_eccoob_8; + this->ecc.mode = NAND_ECC_SOFT; + tmp = readw(host->regs + NFC_CONFIG1); + tmp &= ~NFC_ECC_EN; + writew(tmp, host->regs + NFC_CONFIG1); + } + + /* Reset NAND */ + this->cmdfunc(mtd, NAND_CMD_RESET, -1, -1); + + /* preset operation */ + /* Unlock the internal RAM Buffer */ + writew(0x2, host->regs + NFC_CONFIG); + + /* Blocks to be unlocked */ + writew(0x0, host->regs + NFC_UNLOCKSTART_BLKADDR); + writew(0x4000, host->regs + NFC_UNLOCKEND_BLKADDR); + + /* Unlock Block Command for given address range */ + writew(0x4, host->regs + NFC_WRPROT); + + /* NAND bus width determines access funtions used by upper layer */ + if (pdata->width == 2) { + this->options |= NAND_BUSWIDTH_16; + this->ecc.layout = &nand_hw_eccoob_16; + } + + host->pagesize_2k = 0; + + /* Scan to find existence of the device */ + if (nand_scan(mtd, 1)) { + DEBUG(MTD_DEBUG_LEVEL0, + "MXC_ND: Unable to find any NAND device.\n"); + err = -ENXIO; + goto escan; + } + + /* Register the partitions */ +#ifdef CONFIG_MTD_PARTITIONS + nr_parts = + parse_mtd_partitions(mtd, part_probes, &host->parts, 0); + if (nr_parts > 0) + add_mtd_partitions(mtd, host->parts, nr_parts); + else +#endif + { + pr_info("Registering %s as whole device\n", mtd->name); + add_mtd_device(mtd); + } + + platform_set_drvdata(pdev, host); + + return 0; + +escan: + free_irq(host->irq, NULL); +eirq: + iounmap(host->regs); +eres: + clk_put(host->clk); +eclk: + kfree(host); + + return err; +} + +static int __devexit mxcnd_remove(struct platform_device *pdev) +{ + struct mxc_nand_host *host = platform_get_drvdata(pdev); + + clk_put(host->clk); + + platform_set_drvdata(pdev, NULL); + + nand_release(&host->mtd); + free_irq(host->irq, NULL); + iounmap(host->regs); + kfree(host); + + return 0; +} + +#ifdef CONFIG_PM +static int mxcnd_suspend(struct platform_device *pdev, pm_message_t state) +{ + struct mtd_info *info = platform_get_drvdata(pdev); + int ret = 0; + + DEBUG(MTD_DEBUG_LEVEL0, "MXC_ND : NAND suspend\n"); + if (info) + ret = info->suspend(info); + + /* Disable the NFC clock */ + clk_disable(nfc_clk); /* FIXME */ + + return ret; +} + +static int mxcnd_resume(struct platform_device *pdev) +{ + struct mtd_info *info = platform_get_drvdata(pdev); + int ret = 0; + + DEBUG(MTD_DEBUG_LEVEL0, "MXC_ND : NAND resume\n"); + /* Enable the NFC clock */ + clk_enable(nfc_clk); /* FIXME */ + + if (info) + info->resume(info); + + return ret; +} + +#else +# define mxcnd_suspend NULL +# define mxcnd_resume NULL +#endif /* CONFIG_PM */ + +static struct platform_driver mxcnd_driver = { + .driver = { + .name = DRIVER_NAME, + }, + .remove = __exit_p(mxcnd_remove), + .suspend = mxcnd_suspend, + .resume = mxcnd_resume, +}; + +static int __init mxc_nd_init(void) +{ + /* Register the device driver structure. */ + pr_info("MXC MTD nand Driver\n"); + if (platform_driver_probe(&mxcnd_driver, mxcnd_probe) != 0) { + printk(KERN_ERR "Driver register failed for mxcnd_driver\n"); + return -ENODEV; + } + return 0; +} + +static void __exit mxc_nd_cleanup(void) +{ + /* Unregister the device structure */ + platform_driver_unregister(&mxcnd_driver); +} + +module_init(mxc_nd_init); +module_exit(mxc_nd_cleanup); + +MODULE_AUTHOR("Freescale Semiconductor, Inc."); +MODULE_DESCRIPTION("MXC NAND MTD driver"); +MODULE_LICENSE("GPL"); -- cgit v0.10.2 From 7d200e88cbdff5334d23d3af8d444eb9cc041962 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Sun, 31 Aug 2008 19:32:13 +0300 Subject: UBI: remove BKL We do not need BKL in UBI because we serialize things properly. Signed-off-by: Artem Bityutskiy diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c index 03c759b..b30a0b8 100644 --- a/drivers/mtd/ubi/cdev.c +++ b/drivers/mtd/ubi/cdev.c @@ -104,12 +104,9 @@ static int vol_cdev_open(struct inode *inode, struct file *file) struct ubi_volume_desc *desc; int vol_id = iminor(inode) - 1, mode, ubi_num; - lock_kernel(); ubi_num = ubi_major2num(imajor(inode)); - if (ubi_num < 0) { - unlock_kernel(); + if (ubi_num < 0) return ubi_num; - } if (file->f_mode & FMODE_WRITE) mode = UBI_READWRITE; @@ -119,7 +116,6 @@ static int vol_cdev_open(struct inode *inode, struct file *file) dbg_gen("open volume %d, mode %d", vol_id, mode); desc = ubi_open_volume(ubi_num, vol_id, mode); - unlock_kernel(); if (IS_ERR(desc)) return PTR_ERR(desc); -- cgit v0.10.2 From 7e6e178ab1548c8d894a77593e757acf4510b8ba Mon Sep 17 00:00:00 2001 From: Pawel MOLL Date: Mon, 1 Sep 2008 10:12:11 +0100 Subject: genirq: irq_chip->startup() usage in setup_irq and set_irq_chained handler This patch clarifies usage of irq_chip->startup() callback: 1. The "if (startup) startup(); else enabled();" code in setup_irq() is unnecessary, as startup() falls back to enabled() via default callbacks, set by irq_chip_set_defaults(). 2. When using set_irq_chained_handler() the startup() was never called, which is not good at all... Fixed. And again - when startup() is not defined the call will fall back to enable() than to unmask() via default callbacks. Signed-off-by: Pawel Moll Acked-by: Benjamin Herrenschmidt Signed-off-by: Ingo Molnar diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 964964b..240c64d 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -587,7 +587,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, desc->status &= ~IRQ_DISABLED; desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE; desc->depth = 0; - desc->chip->unmask(irq); + desc->chip->startup(irq); } spin_unlock_irqrestore(&desc->lock, flags); } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index ae1b684..9aa3e7b 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -397,10 +397,7 @@ int setup_irq(unsigned int irq, struct irqaction *new) if (!(desc->status & IRQ_NOAUTOEN)) { desc->depth = 0; desc->status &= ~IRQ_DISABLED; - if (desc->chip->startup) - desc->chip->startup(irq); - else - desc->chip->enable(irq); + desc->chip->startup(irq); } else /* Undo nested disables: */ desc->depth = 1; -- cgit v0.10.2 From 742fd1bcfb475c702c9b1dd6afc79c08f8dbf7dd Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Thu, 7 Aug 2008 17:36:12 +0900 Subject: sh: Provide movli.l/movco.l-based bitops. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/bitops-llsc.h b/arch/sh/include/asm/bitops-llsc.h new file mode 100644 index 0000000..43b8e1a --- /dev/null +++ b/arch/sh/include/asm/bitops-llsc.h @@ -0,0 +1,144 @@ +#ifndef __ASM_SH_BITOPS_LLSC_H +#define __ASM_SH_BITOPS_LLSC_H + +static inline void set_bit(int nr, volatile void * addr) +{ + int mask; + volatile unsigned int *a = addr; + unsigned long tmp; + + a += nr >> 5; + mask = 1 << (nr & 0x1f); + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%1, %0 ! set_bit \n\t" + "or %3, %0 \n\t" + "movco.l %0, @%1 \n\t" + "bf 1b \n\t" + : "=&z" (tmp), "=r" (a) + : "1" (a), "r" (mask) + : "t", "memory" + ); +} + +static inline void clear_bit(int nr, volatile void * addr) +{ + int mask; + volatile unsigned int *a = addr; + unsigned long tmp; + + a += nr >> 5; + mask = 1 << (nr & 0x1f); + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%1, %0 ! clear_bit \n\t" + "and %3, %0 \n\t" + "movco.l %0, @%1 \n\t" + "bf 1b \n\t" + : "=&z" (tmp), "=r" (a) + : "1" (a), "r" (~mask) + : "t", "memory" + ); +} + +static inline void change_bit(int nr, volatile void * addr) +{ + int mask; + volatile unsigned int *a = addr; + unsigned long tmp; + + a += nr >> 5; + mask = 1 << (nr & 0x1f); + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%1, %0 ! change_bit \n\t" + "xor %3, %0 \n\t" + "movco.l %0, @%1 \n\t" + "bf 1b \n\t" + : "=&z" (tmp), "=r" (a) + : "1" (a), "r" (mask) + : "t", "memory" + ); +} + +static inline int test_and_set_bit(int nr, volatile void * addr) +{ + int mask, retval; + volatile unsigned int *a = addr; + unsigned long tmp; + + a += nr >> 5; + mask = 1 << (nr & 0x1f); + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%1, %0 ! test_and_set_bit \n\t" + "mov %0, %2 \n\t" + "or %4, %0 \n\t" + "movco.l %0, @%1 \n\t" + "bf 1b \n\t" + "and %4, %2 \n\t" + : "=&z" (tmp), "=r" (a), "=&r" (retval) + : "1" (a), "r" (mask) + : "t", "memory" + ); + + return retval != 0; +} + +static inline int test_and_clear_bit(int nr, volatile void * addr) +{ + int mask, retval; + volatile unsigned int *a = addr; + unsigned long tmp; + + a += nr >> 5; + mask = 1 << (nr & 0x1f); + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%1, %0 ! test_and_clear_bit \n\t" + "mov %0, %2 \n\t" + "and %5, %0 \n\t" + "movco.l %0, @%1 \n\t" + "bf 1b \n\t" + "and %4, %2 \n\t" + "synco \n\t" + : "=&z" (tmp), "=r" (a), "=&r" (retval) + : "1" (a), "r" (mask), "r" (~mask) + : "t", "memory" + ); + + return retval != 0; +} + +static inline int test_and_change_bit(int nr, volatile void * addr) +{ + int mask, retval; + volatile unsigned int *a = addr; + unsigned long tmp; + + a += nr >> 5; + mask = 1 << (nr & 0x1f); + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%1, %0 ! test_and_change_bit \n\t" + "mov %0, %2 \n\t" + "xor %4, %0 \n\t" + "movco.l %0, @%1 \n\t" + "bf 1b \n\t" + "and %4, %2 \n\t" + "synco \n\t" + : "=&z" (tmp), "=r" (a), "=&r" (retval) + : "1" (a), "r" (mask) + : "t", "memory" + ); + + return retval != 0; +} + +#endif /* __ASM_SH_BITOPS_LLSC_H */ diff --git a/arch/sh/include/asm/bitops.h b/arch/sh/include/asm/bitops.h index d7d382f..367930d 100644 --- a/arch/sh/include/asm/bitops.h +++ b/arch/sh/include/asm/bitops.h @@ -13,6 +13,8 @@ #ifdef CONFIG_GUSA_RB #include +#elif defined(CONFIG_CPU_SH4A) +#include #else #include #endif -- cgit v0.10.2 From ee43a8442bd7a5d611f11958e6f8c8953d26f907 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Thu, 7 Aug 2008 18:01:43 +0900 Subject: sh: Provide movli.l/movco.l-based cmpxchg. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/cmpxchg-llsc.h b/arch/sh/include/asm/cmpxchg-llsc.h new file mode 100644 index 0000000..aee3bf2 --- /dev/null +++ b/arch/sh/include/asm/cmpxchg-llsc.h @@ -0,0 +1,71 @@ +#ifndef __ASM_SH_CMPXCHG_LLSC_H +#define __ASM_SH_CMPXCHG_LLSC_H + +static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val) +{ + unsigned long retval; + unsigned long tmp; + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%1, %0 ! xchg_u32 \n\t" + "mov %0, %2 \n\t" + "mov %4, %0 \n\t" + "movco.l %0, @%1 \n\t" + "bf 1b \n\t" + "synco \n\t" + : "=&z"(tmp), "=r" (m), "=&r" (retval) + : "1" (m), "r" (val) + : "t", "memory" + ); + + return retval; +} + +static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val) +{ + unsigned long retval; + unsigned long tmp; + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%1, %0 ! xchg_u8 \n\t" + "mov %0, %2 \n\t" + "mov %4, %0 \n\t" + "movco.l %0, @%1 \n\t" + "bf 1b \n\t" + "synco \n\t" + : "=&z"(tmp), "=r" (m), "=&r" (retval) + : "1" (m), "r" (val & 0xff) + : "t", "memory" + ); + + return retval; +} + +static inline unsigned long +__cmpxchg_u32(volatile int *m, unsigned long old, unsigned long new) +{ + unsigned long retval; + unsigned long tmp; + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%1, %0 ! __cmpxchg_u32 \n\t" + "mov %0, %2 \n\t" + "cmp/eq %2, %4 \n\t" + "bf 2f \n\t" + "mov %5, %0 \n\t" + "2: \n\t" + "movco.l %0, @%1 \n\t" + "bf 1b \n\t" + "synco \n\t" + : "=&z" (tmp), "=r" (m), "=&r" (retval) + : "1" (m), "r" (old), "r" (new) + : "t", "memory" + ); + + return retval; +} + +#endif /* __ASM_SH_CMPXCHG_LLSC_H */ diff --git a/arch/sh/include/asm/system.h b/arch/sh/include/asm/system.h index 056d68c..fbac113 100644 --- a/arch/sh/include/asm/system.h +++ b/arch/sh/include/asm/system.h @@ -70,6 +70,8 @@ #ifdef CONFIG_GUSA_RB #include +#elif defined(CONFIG_CPU_SH4A) +#include #else #include #endif -- cgit v0.10.2 From 04ec080dcaad7d3c6d0b40b599c8e63da618f784 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 6 Aug 2008 17:29:14 +0900 Subject: sh: Kill off unused defines from asm/smp.h. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h index 593343c..e2b79e6 100644 --- a/arch/sh/include/asm/smp.h +++ b/arch/sh/include/asm/smp.h @@ -21,11 +21,6 @@ extern int __cpu_number_map[NR_CPUS]; extern int __cpu_logical_map[NR_CPUS]; #define cpu_logical_map(cpu) __cpu_logical_map[cpu] -/* I've no idea what the real meaning of this is */ -#define PROC_CHANGE_PENALTY 20 - -#define NO_PROC_ID (-1) - #define SMP_MSG_FUNCTION 0 #define SMP_MSG_RESCHEDULE 1 #define SMP_MSG_FUNCTION_SINGLE 2 -- cgit v0.10.2 From 173a44dd1f406e9aa6fcf46c83b7c972d10ec930 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 6 Aug 2008 18:02:48 +0900 Subject: sh: smp: Provide a generic IPI handler. This provides a generic smp_message_recv() routine (based on the PPC one), that IPI IRQs can wrap in to. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h index e2b79e6..1292c6d 100644 --- a/arch/sh/include/asm/smp.h +++ b/arch/sh/include/asm/smp.h @@ -26,6 +26,7 @@ extern int __cpu_logical_map[NR_CPUS]; #define SMP_MSG_FUNCTION_SINGLE 2 #define SMP_MSG_NR 3 +void smp_message_recv(unsigned int msg); void plat_smp_setup(void); void plat_prepare_cpus(unsigned int max_cpus); int plat_smp_processor_id(void); diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index 60c5084..ebfdd36 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -3,7 +3,7 @@ * * SMP support for the SuperH processors. * - * Copyright (C) 2002 - 2007 Paul Mundt + * Copyright (C) 2002 - 2008 Paul Mundt * Copyright (C) 2006 - 2007 Akio Idehara * * This file is subject to the terms and conditions of the GNU General Public @@ -184,6 +184,24 @@ void arch_send_call_function_single_ipi(int cpu) plat_send_ipi(cpu, SMP_MSG_FUNCTION_SINGLE); } +void smp_message_recv(unsigned int msg) +{ + switch (msg) { + case SMP_MSG_FUNCTION: + generic_smp_call_function_interrupt(); + break; + case SMP_MSG_RESCHEDULE: + break; + case SMP_MSG_FUNCTION_SINGLE: + generic_smp_call_function_single_interrupt(); + break; + default: + printk(KERN_WARNING "SMP %d: %s(): unknown IPI %d\n", + smp_processor_id(), __func__, msg); + break; + } +} + /* Not really SMP stuff ... */ int setup_profiling_timer(unsigned int multiplier) { -- cgit v0.10.2 From c7936b9abcf5e043e73f183a37e81787f6178dd0 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 6 Aug 2008 18:05:09 +0900 Subject: sh: smp: Hook in to the generic IPI handler for SH-X3 SMP. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h index 1292c6d..5ebe0d0 100644 --- a/arch/sh/include/asm/smp.h +++ b/arch/sh/include/asm/smp.h @@ -32,8 +32,6 @@ void plat_prepare_cpus(unsigned int max_cpus); int plat_smp_processor_id(void); void plat_start_cpu(unsigned int cpu, unsigned long entry_point); void plat_send_ipi(unsigned int cpu, unsigned int message); -int plat_register_ipi_handler(unsigned int message, - void (*handler)(void *), void *arg); extern void arch_send_call_function_single_ipi(int cpu); extern void arch_send_call_function_ipi(cpumask_t mask); diff --git a/arch/sh/kernel/cpu/sh4a/smp-shx3.c b/arch/sh/kernel/cpu/sh4a/smp-shx3.c index e5e0684..edb4da0 100644 --- a/arch/sh/kernel/cpu/sh4a/smp-shx3.c +++ b/arch/sh/kernel/cpu/sh4a/smp-shx3.c @@ -1,7 +1,7 @@ /* * SH-X3 SMP * - * Copyright (C) 2007 Paul Mundt + * Copyright (C) 2007 - 2008 Paul Mundt * Copyright (C) 2007 Magnus Damm * * This file is subject to the terms and conditions of the GNU General Public @@ -14,6 +14,22 @@ #include #include +static irqreturn_t ipi_interrupt_handler(int irq, void *arg) +{ + unsigned int message = (unsigned int)(long)arg; + unsigned int cpu = hard_smp_processor_id(); + unsigned int offs = 4 * cpu; + unsigned int x; + + x = ctrl_inl(0xfe410070 + offs); /* C0INITICI..CnINTICI */ + x &= (1 << (message << 2)); + ctrl_outl(x, 0xfe410080 + offs); /* C0INTICICLR..CnINTICICLR */ + + smp_message_recv(message); + + return IRQ_HANDLED; +} + void __init plat_smp_setup(void) { unsigned int cpu = 0; @@ -40,6 +56,13 @@ void __init plat_smp_setup(void) void __init plat_prepare_cpus(unsigned int max_cpus) { + int i; + + BUILD_BUG_ON(SMP_MSG_NR >= 8); + + for (i = 0; i < SMP_MSG_NR; i++) + request_irq(104 + i, ipi_interrupt_handler, IRQF_DISABLED, + "IPI", (void *)(long)i); } #define STBCR_REG(phys_id) (0xfe400004 | (phys_id << 12)) @@ -75,46 +98,6 @@ void plat_send_ipi(unsigned int cpu, unsigned int message) unsigned long addr = 0xfe410070 + (cpu * 4); BUG_ON(cpu >= 4); - BUG_ON(message >= SMP_MSG_NR); ctrl_outl(1 << (message << 2), addr); /* C0INTICI..CnINTICI */ } - -struct ipi_data { - void (*handler)(void *); - void *arg; - unsigned int message; -}; - -static irqreturn_t ipi_interrupt_handler(int irq, void *arg) -{ - struct ipi_data *id = arg; - unsigned int cpu = hard_smp_processor_id(); - unsigned int offs = 4 * cpu; - unsigned int x; - - x = ctrl_inl(0xfe410070 + offs); /* C0INITICI..CnINTICI */ - x &= (1 << (id->message << 2)); - ctrl_outl(x, 0xfe410080 + offs); /* C0INTICICLR..CnINTICICLR */ - - id->handler(id->arg); - - return IRQ_HANDLED; -} - -static struct ipi_data ipi_handlers[SMP_MSG_NR]; - -int plat_register_ipi_handler(unsigned int message, - void (*handler)(void *), void *arg) -{ - struct ipi_data *id = &ipi_handlers[message]; - - BUG_ON(SMP_MSG_NR >= 8); - BUG_ON(message >= SMP_MSG_NR); - - id->handler = handler; - id->arg = arg; - id->message = message; - - return request_irq(104 + message, ipi_interrupt_handler, 0, "IPI", id); -} -- cgit v0.10.2 From 6f52707e6882eb3bc6920c3f59beb05d23d68354 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 6 Aug 2008 18:21:03 +0900 Subject: sh: smp: Hook up a timer IPI stub. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h index 5ebe0d0..9d22cda 100644 --- a/arch/sh/include/asm/smp.h +++ b/arch/sh/include/asm/smp.h @@ -21,19 +21,26 @@ extern int __cpu_number_map[NR_CPUS]; extern int __cpu_logical_map[NR_CPUS]; #define cpu_logical_map(cpu) __cpu_logical_map[cpu] -#define SMP_MSG_FUNCTION 0 -#define SMP_MSG_RESCHEDULE 1 -#define SMP_MSG_FUNCTION_SINGLE 2 -#define SMP_MSG_NR 3 +enum { + SMP_MSG_FUNCTION, + SMP_MSG_RESCHEDULE, + SMP_MSG_FUNCTION_SINGLE, + SMP_MSG_TIMER, + + SMP_MSG_NR, /* must be last */ +}; void smp_message_recv(unsigned int msg); +void smp_timer_broadcast(cpumask_t mask); + void plat_smp_setup(void); void plat_prepare_cpus(unsigned int max_cpus); int plat_smp_processor_id(void); void plat_start_cpu(unsigned int cpu, unsigned long entry_point); void plat_send_ipi(unsigned int cpu, unsigned int message); -extern void arch_send_call_function_single_ipi(int cpu); -extern void arch_send_call_function_ipi(cpumask_t mask); + +void arch_send_call_function_single_ipi(int cpu); +void arch_send_call_function_ipi(cpumask_t mask); #else diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index ebfdd36..9cb3734 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -184,6 +184,21 @@ void arch_send_call_function_single_ipi(int cpu) plat_send_ipi(cpu, SMP_MSG_FUNCTION_SINGLE); } +void smp_timer_broadcast(cpumask_t mask) +{ + int cpu; + + for_each_cpu_mask(cpu, mask) + plat_send_ipi(cpu, SMP_MSG_TIMER); +} + +static void ipi_timer(void) +{ + irq_enter(); + /* XXX ... */ + irq_exit(); +} + void smp_message_recv(unsigned int msg) { switch (msg) { @@ -195,6 +210,9 @@ void smp_message_recv(unsigned int msg) case SMP_MSG_FUNCTION_SINGLE: generic_smp_call_function_single_interrupt(); break; + case SMP_MSG_TIMER: + ipi_timer(); + break; default: printk(KERN_WARNING "SMP %d: %s(): unknown IPI %d\n", smp_processor_id(), __func__, msg); -- cgit v0.10.2 From 8c24594deab89a484879bee270e948f0a556ed75 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 6 Aug 2008 18:37:07 +0900 Subject: sh: generic clockevent broadcast support. This hooks up GENERIC_CLOCKEVENTS_BROADCAST and a dummy local timer, which we call in to from the timer IPI when no other local timer is provided. Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 5131d50..399664c 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -66,6 +66,9 @@ config GENERIC_TIME config GENERIC_CLOCKEVENTS def_bool n +config GENERIC_CLOCKEVENTS_BROADCAST + bool + config GENERIC_LOCKBREAK def_bool y depends on SMP && PREEMPT @@ -323,6 +326,7 @@ config CPU_SUBTYPE_SHX3 select ARCH_SPARSEMEM_ENABLE select SYS_SUPPORTS_NUMA select SYS_SUPPORTS_SMP + select GENERIC_CLOCKEVENTS_BROADCAST # SH4AL-DSP Processor Support diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h index 9d22cda..85b660c 100644 --- a/arch/sh/include/asm/smp.h +++ b/arch/sh/include/asm/smp.h @@ -33,6 +33,9 @@ enum { void smp_message_recv(unsigned int msg); void smp_timer_broadcast(cpumask_t mask); +void local_timer_interrupt(void); +void local_timer_setup(unsigned int cpu); + void plat_smp_setup(void); void plat_prepare_cpus(unsigned int max_cpus); int plat_smp_processor_id(void); diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index 9cb3734..c55d314 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -84,9 +84,12 @@ asmlinkage void __cpuinit start_secondary(void) local_irq_enable(); + cpu = smp_processor_id(); + + /* Enable local timers */ + local_timer_setup(cpu); calibrate_delay(); - cpu = smp_processor_id(); smp_store_cpu_info(cpu); cpu_set(cpu, cpu_online_map); @@ -195,7 +198,7 @@ void smp_timer_broadcast(cpumask_t mask) static void ipi_timer(void) { irq_enter(); - /* XXX ... */ + local_timer_interrupt(); irq_exit(); } diff --git a/arch/sh/kernel/time_32.c b/arch/sh/kernel/time_32.c index 0758b5e..decee0a 100644 --- a/arch/sh/kernel/time_32.c +++ b/arch/sh/kernel/time_32.c @@ -1,9 +1,9 @@ /* - * arch/sh/kernel/time.c + * arch/sh/kernel/time_32.c * * Copyright (C) 1999 Tetsuya Okada & Niibe Yutaka * Copyright (C) 2000 Philipp Rumpf - * Copyright (C) 2002 - 2007 Paul Mundt + * Copyright (C) 2002 - 2008 Paul Mundt * Copyright (C) 2002 M. R. Brown * * Some code taken from i386 version. @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -260,6 +261,10 @@ void __init time_init(void) sys_timer = get_sys_timer(); printk(KERN_INFO "Using %s for system timer\n", sys_timer->name); +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST + local_timer_setup(smp_processor_id()); +#endif + if (sys_timer->ops->read) clocksource_sh.read = sys_timer->ops->read; diff --git a/arch/sh/kernel/timers/Makefile b/arch/sh/kernel/timers/Makefile index bcf244f..0b7f857 100644 --- a/arch/sh/kernel/timers/Makefile +++ b/arch/sh/kernel/timers/Makefile @@ -8,3 +8,4 @@ obj-$(CONFIG_SH_TMU) += timer-tmu.o obj-$(CONFIG_SH_MTU2) += timer-mtu2.o obj-$(CONFIG_SH_CMT) += timer-cmt.o +obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += timer-broadcast.o diff --git a/arch/sh/kernel/timers/timer-broadcast.c b/arch/sh/kernel/timers/timer-broadcast.c new file mode 100644 index 0000000..c231763 --- /dev/null +++ b/arch/sh/kernel/timers/timer-broadcast.c @@ -0,0 +1,57 @@ +/* + * Dummy local timer + * + * Copyright (C) 2008 Paul Mundt + * + * cloned from: + * + * linux/arch/arm/mach-realview/localtimer.c + * + * Copyright (C) 2002 ARM Ltd. + * All Rights Reserved + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_PER_CPU(struct clock_event_device, local_clockevent); + +/* + * Used on SMP for either the local timer or SMP_MSG_TIMER + */ +void local_timer_interrupt(void) +{ + struct clock_event_device *clk = &__get_cpu_var(local_clockevent); + + clk->event_handler(clk); +} + +static void dummy_timer_set_mode(enum clock_event_mode mode, + struct clock_event_device *clk) +{ +} + +void __cpuinit local_timer_setup(unsigned int cpu) +{ + struct clock_event_device *clk = &per_cpu(local_clockevent, cpu); + + clk->name = "dummy_timer"; + clk->features = CLOCK_EVT_FEAT_DUMMY; + clk->rating = 200; + clk->mult = 1; + clk->set_mode = dummy_timer_set_mode; + clk->broadcast = smp_timer_broadcast; + clk->cpumask = cpumask_of_cpu(cpu); + + clockevents_register_device(clk); +} -- cgit v0.10.2 From 71f0bdcab69ab36b1e939d36063aaf6c4a164ed3 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 6 Aug 2008 18:39:32 +0900 Subject: sh: smp: shove a cpu_relax() in the plat_start_cpu() busy loop. Without this, certain versions of GCC will happily optimize the entire loop out. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/cpu/sh4a/smp-shx3.c b/arch/sh/kernel/cpu/sh4a/smp-shx3.c index edb4da0..b8869aa 100644 --- a/arch/sh/kernel/cpu/sh4a/smp-shx3.c +++ b/arch/sh/kernel/cpu/sh4a/smp-shx3.c @@ -82,7 +82,7 @@ void plat_start_cpu(unsigned int cpu, unsigned long entry_point) ctrl_outl(STBCR_MSTP, STBCR_REG(cpu)); while (!(ctrl_inl(STBCR_REG(cpu)) & STBCR_MSTP)) - ; + cpu_relax(); /* Start up secondary processor by sending a reset */ ctrl_outl(STBCR_AP_VAL, STBCR_REG(cpu)); -- cgit v0.10.2 From 53c01d2dc38cd3cfaf5591ec5c6c9c4e437cfec2 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 8 Aug 2008 01:18:48 +0900 Subject: sh: Early dummy clockevent registration on boot CPU. The dummy timer needs to be registered on the boot CPU before the system timer clockevent is registered, or broadcasting doesn't work as advertized. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/time_32.c b/arch/sh/kernel/time_32.c index decee0a..e2f74cc 100644 --- a/arch/sh/kernel/time_32.c +++ b/arch/sh/kernel/time_32.c @@ -254,6 +254,10 @@ void __init time_init(void) set_normalized_timespec(&wall_to_monotonic, -xtime.tv_sec, -xtime.tv_nsec); +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST + local_timer_setup(smp_processor_id()); +#endif + /* * Find the timer to use as the system timer, it will be * initialized for us. @@ -261,9 +265,6 @@ void __init time_init(void) sys_timer = get_sys_timer(); printk(KERN_INFO "Using %s for system timer\n", sys_timer->name); -#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST - local_timer_setup(smp_processor_id()); -#endif if (sys_timer->ops->read) clocksource_sh.read = sys_timer->ops->read; -- cgit v0.10.2 From 7d96169cb769f459dd6730b06fa3a88cb0c9297d Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 8 Aug 2008 01:23:34 +0900 Subject: sh: Display CPU information in show_regs(). Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 3326a45..7326313 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -111,15 +111,21 @@ void show_regs(struct pt_regs * regs) { printk("\n"); printk("Pid : %d, Comm: %20s\n", task_pid_nr(current), current->comm); + printk("CPU : %d %s (%s %.*s)\n", + smp_processor_id(), print_tainted(), init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + print_symbol("PC is at %s\n", instruction_pointer(regs)); + print_symbol("PR is at %s\n", regs->pr); + printk("PC : %08lx SP : %08lx SR : %08lx ", regs->pc, regs->regs[15], regs->sr); #ifdef CONFIG_MMU - printk("TEA : %08x ", ctrl_inl(MMU_TEA)); + printk("TEA : %08x\n", ctrl_inl(MMU_TEA)); #else - printk(" "); + printk("\n"); #endif - printk("%s\n", print_tainted()); printk("R0 : %08lx R1 : %08lx R2 : %08lx R3 : %08lx\n", regs->regs[0],regs->regs[1], -- cgit v0.10.2 From fa43972fab24a3c050e880a7831f9378c6cebc0b Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Thu, 4 Sep 2008 18:53:58 +0900 Subject: sh: fixup many sparse errors. Signed-off-by: Paul Mundt diff --git a/arch/sh/boot/compressed/misc_32.c b/arch/sh/boot/compressed/misc_32.c index f386997..efdba6b 100644 --- a/arch/sh/boot/compressed/misc_32.c +++ b/arch/sh/boot/compressed/misc_32.c @@ -191,7 +191,7 @@ long* stack_start = &user_stack[STACK_SIZE]; void decompress_kernel(void) { - output_data = 0; + output_data = NULL; output_ptr = PHYSADDR((unsigned long)&_text+PAGE_SIZE); #ifdef CONFIG_29BIT output_ptr |= P2SEG; diff --git a/arch/sh/include/asm/clock.h b/arch/sh/include/asm/clock.h index 720dfab..f9c8858 100644 --- a/arch/sh/include/asm/clock.h +++ b/arch/sh/include/asm/clock.h @@ -39,6 +39,7 @@ struct clk { /* Should be defined by processor-specific code */ void arch_init_clk_ops(struct clk_ops **, int type); +int __init arch_clk_init(void); /* arch/sh/kernel/cpu/clock.c */ int clk_init(void); diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index a4fbf0c..e49cfee 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -194,6 +194,8 @@ __BUILD_MEMORY_STRING(w, u16) #define IO_SPACE_LIMIT 0xffffffff +extern unsigned long generic_io_base; + /* * This function provides a method for the generic case where a board-specific * ioport_map simply needs to return the port + some arbitrary port base. @@ -203,8 +205,6 @@ __BUILD_MEMORY_STRING(w, u16) */ static inline void __set_io_port_base(unsigned long pbase) { - extern unsigned long generic_io_base; - generic_io_base = pbase; } diff --git a/arch/sh/include/asm/irq.h b/arch/sh/include/asm/irq.h index 6195a53..d319baa 100644 --- a/arch/sh/include/asm/irq.h +++ b/arch/sh/include/asm/irq.h @@ -41,6 +41,9 @@ static inline int generic_irq_demux(int irq) #define irq_canonicalize(irq) (irq) #define irq_demux(irq) sh_mv.mv_irq_demux(irq) +void init_IRQ(void); +asmlinkage int do_IRQ(unsigned int irq, struct pt_regs *regs); + #ifdef CONFIG_IRQSTACKS extern void irq_ctx_init(int cpu); extern void irq_ctx_exit(int cpu); diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h index 15d9f92..58e2be5 100644 --- a/arch/sh/include/asm/processor.h +++ b/arch/sh/include/asm/processor.h @@ -45,9 +45,13 @@ enum cpu_type { /* Forward decl */ struct sh_cpuinfo; +struct seq_operations; + +extern struct pt_regs fake_swapper_regs; /* arch/sh/kernel/setup.c */ const char *get_cpu_subtype(struct sh_cpuinfo *c); +extern const struct seq_operations cpuinfo_op; #ifdef CONFIG_VSYSCALL int vsyscall_init(void); diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index 0dadd75..41d2321 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -10,6 +10,7 @@ #ifdef __KERNEL__ #include +#include #include #include #include @@ -44,6 +45,8 @@ extern struct sh_cpuinfo cpu_data[]; #define current_cpu_data cpu_data[smp_processor_id()] #define raw_current_cpu_data cpu_data[raw_smp_processor_id()] +asmlinkage void __init sh_cpu_init(void); + /* * User space process size: 2GB. * diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h index 770d516..16609bc 100644 --- a/arch/sh/include/asm/processor_64.h +++ b/arch/sh/include/asm/processor_64.h @@ -169,8 +169,6 @@ struct thread_struct { #define INIT_MMAP \ { &init_mm, 0, 0, NULL, PAGE_SHARED, VM_READ | VM_WRITE | VM_EXEC, 1, NULL, NULL } -extern struct pt_regs fake_swapper_regs; - #define INIT_THREAD { \ .sp = sizeof(init_stack) + \ (long) &init_stack, \ diff --git a/arch/sh/include/asm/rtc.h b/arch/sh/include/asm/rtc.h index 1813f42..f7b010d 100644 --- a/arch/sh/include/asm/rtc.h +++ b/arch/sh/include/asm/rtc.h @@ -1,6 +1,7 @@ #ifndef _ASM_RTC_H #define _ASM_RTC_H +void time_init(void); extern void (*board_time_init)(void); extern void (*rtc_sh_get_time)(struct timespec *); extern int (*rtc_sh_set_time)(const time_t); diff --git a/arch/sh/include/asm/setup.h b/arch/sh/include/asm/setup.h index 55a2bd3..554f865 100644 --- a/arch/sh/include/asm/setup.h +++ b/arch/sh/include/asm/setup.h @@ -1,6 +1,8 @@ #ifndef _SH_SETUP_H #define _SH_SETUP_H +#include + #define COMMAND_LINE_SIZE 256 #ifdef __KERNEL__ diff --git a/arch/sh/include/asm/syscalls.h b/arch/sh/include/asm/syscalls.h new file mode 100644 index 0000000..c1e2b8d --- /dev/null +++ b/arch/sh/include/asm/syscalls.h @@ -0,0 +1,25 @@ +#ifndef __ASM_SH_SYSCALLS_H +#define __ASM_SH_SYSCALLS_H + +#ifdef __KERNEL__ + +struct old_utsname; + +asmlinkage int old_mmap(unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flags, + int fd, unsigned long off); +asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff); +asmlinkage int sys_ipc(uint call, int first, int second, + int third, void __user *ptr, long fifth); +asmlinkage int sys_uname(struct old_utsname __user *name); + +#ifdef CONFIG_SUPERH32 +# include "syscalls_32.h" +#else +# include "syscalls_64.h" +#endif + +#endif /* __KERNEL__ */ +#endif /* __ASM_SH_SYSCALLS_H */ diff --git a/arch/sh/include/asm/syscalls_32.h b/arch/sh/include/asm/syscalls_32.h new file mode 100644 index 0000000..104c5e6 --- /dev/null +++ b/arch/sh/include/asm/syscalls_32.h @@ -0,0 +1,56 @@ +#ifndef __ASM_SH_SYSCALLS_32_H +#define __ASM_SH_SYSCALLS_32_H + +#ifdef __KERNEL__ + +#include +#include +#include + +struct pt_regs; + +asmlinkage int sys_fork(unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs __regs); +asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp, + unsigned long parent_tidptr, + unsigned long child_tidptr, + struct pt_regs __regs); +asmlinkage int sys_vfork(unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs __regs); +asmlinkage int sys_execve(char __user *ufilename, char __user * __user *uargv, + char __user * __user *uenvp, unsigned long r7, + struct pt_regs __regs); +asmlinkage int sys_sigsuspend(old_sigset_t mask, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs __regs); +asmlinkage int sys_sigaction(int sig, const struct old_sigaction __user *act, + struct old_sigaction __user *oact); +asmlinkage int sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, + unsigned long r6, unsigned long r7, + struct pt_regs __regs); +asmlinkage int sys_sigreturn(unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs __regs); +asmlinkage int sys_rt_sigreturn(unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs __regs); +asmlinkage int sys_pipe(unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs __regs); +asmlinkage ssize_t sys_pread_wrapper(unsigned int fd, char __user *buf, + size_t count, long dummy, loff_t pos); +asmlinkage ssize_t sys_pwrite_wrapper(unsigned int fd, const char __user *buf, + size_t count, long dummy, loff_t pos); +asmlinkage int sys_fadvise64_64_wrapper(int fd, u32 offset0, u32 offset1, + u32 len0, u32 len1, int advice); + +/* Misc syscall related bits */ +asmlinkage long do_syscall_trace_enter(struct pt_regs *regs); +asmlinkage void do_syscall_trace_leave(struct pt_regs *regs); +asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int save_r0, + unsigned long thread_info_flags); + +#endif /* __KERNEL__ */ +#endif /* __ASM_SH_SYSCALLS_32_H */ diff --git a/arch/sh/include/asm/syscalls_64.h b/arch/sh/include/asm/syscalls_64.h new file mode 100644 index 0000000..751fd88 --- /dev/null +++ b/arch/sh/include/asm/syscalls_64.h @@ -0,0 +1,34 @@ +#ifndef __ASM_SH_SYSCALLS_64_H +#define __ASM_SH_SYSCALLS_64_H + +#ifdef __KERNEL__ + +#include +#include +#include + +struct pt_regs; + +asmlinkage int sys_fork(unsigned long r2, unsigned long r3, + unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs *pregs); +asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp, + unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs *pregs); +asmlinkage int sys_vfork(unsigned long r2, unsigned long r3, + unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs *pregs); +asmlinkage int sys_execve(char *ufilename, char **uargv, + char **uenvp, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs *pregs); + +/* Misc syscall related bits */ +asmlinkage long long do_syscall_trace_enter(struct pt_regs *regs); +asmlinkage void do_syscall_trace_leave(struct pt_regs *regs); + +#endif /* __KERNEL__ */ +#endif /* __ASM_SH_SYSCALLS_64_H */ diff --git a/arch/sh/include/asm/system.h b/arch/sh/include/asm/system.h index fbac113..6160fe4 100644 --- a/arch/sh/include/asm/system.h +++ b/arch/sh/include/asm/system.h @@ -127,6 +127,8 @@ static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old, }) extern void die(const char *str, struct pt_regs *regs, long err) __attribute__ ((noreturn)); +void free_initmem(void); +void free_initrd_mem(unsigned long start, unsigned long end); extern void *set_exception_table_vec(unsigned int vec, void *handler); @@ -179,8 +181,8 @@ BUILD_TRAP_HANDLER(fpu_state_restore); #define arch_align_stack(x) (x) struct mem_access { - unsigned long (*from)(void *dst, const void *src, unsigned long cnt); - unsigned long (*to)(void *dst, const void *src, unsigned long cnt); + unsigned long (*from)(void *dst, const void __user *src, unsigned long cnt); + unsigned long (*to)(void __user *dst, const void *src, unsigned long cnt); }; #ifdef CONFIG_SUPERH32 diff --git a/arch/sh/include/asm/system_32.h b/arch/sh/include/asm/system_32.h index f11bcf0..16509ed 100644 --- a/arch/sh/include/asm/system_32.h +++ b/arch/sh/include/asm/system_32.h @@ -99,4 +99,20 @@ do { \ int handle_unaligned_access(opcode_t instruction, struct pt_regs *regs, struct mem_access *ma); +asmlinkage void do_address_error(struct pt_regs *regs, + unsigned long writeaccess, + unsigned long address); +asmlinkage void do_divide_error(unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs __regs); +asmlinkage void do_reserved_inst(unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs __regs); +asmlinkage void do_illegal_slot_inst(unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs __regs); +asmlinkage void do_exception_error(unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, + struct pt_regs __regs); + #endif /* __ASM_SH_SYSTEM_32_H */ diff --git a/arch/sh/kernel/cpu/clock.c b/arch/sh/kernel/cpu/clock.c index f5eb56e..b7e46d5 100644 --- a/arch/sh/kernel/cpu/clock.c +++ b/arch/sh/kernel/cpu/clock.c @@ -294,9 +294,10 @@ arch_init_clk_ops(struct clk_ops **ops, int type) { } -void __init __attribute__ ((weak)) +int __init __attribute__ ((weak)) arch_clk_init(void) { + return 0; } static int show_clocks(char *buf, char **start, off_t off, @@ -331,7 +332,7 @@ int __init clk_init(void) ret |= clk_register(clk); } - arch_clk_init(); + ret |= arch_clk_init(); /* Kick the child clocks.. */ propagate_rate(&master_clk); diff --git a/arch/sh/kernel/io_generic.c b/arch/sh/kernel/io_generic.c index db76944..f1b214d 100644 --- a/arch/sh/kernel/io_generic.c +++ b/arch/sh/kernel/io_generic.c @@ -81,7 +81,7 @@ void generic_insb(unsigned long port, void *dst, unsigned long count) volatile u8 *port_addr; u8 *buf = dst; - port_addr = (volatile u8 *)__ioport_map(port, 1); + port_addr = (volatile u8 __force *)__ioport_map(port, 1); while (count--) *buf++ = *port_addr; } @@ -91,7 +91,7 @@ void generic_insw(unsigned long port, void *dst, unsigned long count) volatile u16 *port_addr; u16 *buf = dst; - port_addr = (volatile u16 *)__ioport_map(port, 2); + port_addr = (volatile u16 __force *)__ioport_map(port, 2); while (count--) *buf++ = *port_addr; @@ -103,7 +103,7 @@ void generic_insl(unsigned long port, void *dst, unsigned long count) volatile u32 *port_addr; u32 *buf = dst; - port_addr = (volatile u32 *)__ioport_map(port, 4); + port_addr = (volatile u32 __force *)__ioport_map(port, 4); while (count--) *buf++ = *port_addr; diff --git a/arch/sh/kernel/machvec.c b/arch/sh/kernel/machvec.c index 129b2cf..8bfdd27 100644 --- a/arch/sh/kernel/machvec.c +++ b/arch/sh/kernel/machvec.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 7326313..914e543 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -26,6 +26,7 @@ #include #include #include +#include static int hlt_counter; int ubc_usercnt = 0; diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c index b9dbd2d..d0dddc4 100644 --- a/arch/sh/kernel/process_64.c +++ b/arch/sh/kernel/process_64.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c index 035cb30..84bf342 100644 --- a/arch/sh/kernel/ptrace_32.c +++ b/arch/sh/kernel/ptrace_32.c @@ -27,6 +27,7 @@ #include #include #include +#include /* * does not yet catch signals sent when the child dies. @@ -105,6 +106,7 @@ void ptrace_disable(struct task_struct *child) long arch_ptrace(struct task_struct *child, long request, long addr, long data) { struct user * dummy = NULL; + unsigned long __user *datap = (unsigned long __user *)data; int ret; switch (request) { @@ -133,7 +135,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) tmp = !!tsk_used_math(child); else tmp = 0; - ret = put_user(tmp, (unsigned long __user *)data); + ret = put_user(tmp, datap); break; } @@ -202,7 +204,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } ret = 0; - if (put_user(tmp, (unsigned long *) data)) { + if (put_user(tmp, datap)) { ret = -EFAULT; break; } diff --git a/arch/sh/kernel/ptrace_64.c b/arch/sh/kernel/ptrace_64.c index 9c64248..e15b099 100644 --- a/arch/sh/kernel/ptrace_64.c +++ b/arch/sh/kernel/ptrace_64.c @@ -35,6 +35,7 @@ #include #include #include +#include #include /* This mask defines the bits of the SR which the user is not allowed to diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index de83205..6d0899e 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c index 51689d2..345de2f 100644 --- a/arch/sh/kernel/signal_32.c +++ b/arch/sh/kernel/signal_32.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) @@ -247,7 +248,6 @@ asmlinkage int sys_rt_sigreturn(unsigned long r4, unsigned long r5, struct pt_regs *regs = RELOC_HIDE(&__regs, 0); struct rt_sigframe __user *frame = (struct rt_sigframe __user *)regs->regs[15]; sigset_t set; - stack_t st; int r0; if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) @@ -265,11 +265,9 @@ asmlinkage int sys_rt_sigreturn(unsigned long r4, unsigned long r5, if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &r0)) goto badframe; - if (__copy_from_user(&st, &frame->uc.uc_stack, sizeof(st))) + if (do_sigaltstack(&frame->uc.uc_stack, NULL, + regs->regs[15]) == -EFAULT) goto badframe; - /* It is more difficult to avoid calling this function than to - call it and ignore errors. */ - do_sigaltstack((const stack_t __user *)&st, NULL, (unsigned long)frame); return r0; @@ -429,7 +427,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, /* Create the ucontext. */ err |= __put_user(0, &frame->uc.uc_flags); - err |= __put_user(0, &frame->uc.uc_link); + err |= __put_user(NULL, &frame->uc.uc_link); err |= __put_user((void *)current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); err |= __put_user(sas_ss_flags(regs->regs[15]), diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c index 9061b86..0dfb889 100644 --- a/arch/sh/kernel/sys_sh.c +++ b/arch/sh/kernel/sys_sh.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -186,7 +187,7 @@ asmlinkage int sys_ipc(uint call, int first, int second, union semun fourth; if (!ptr) return -EINVAL; - if (get_user(fourth.__pad, (void * __user *) ptr)) + if (get_user(fourth.__pad, (void __user * __user *) ptr)) return -EFAULT; return sys_semctl (first, second, third, fourth); } @@ -261,13 +262,13 @@ asmlinkage int sys_ipc(uint call, int first, int second, return -EINVAL; } -asmlinkage int sys_uname(struct old_utsname * name) +asmlinkage int sys_uname(struct old_utsname __user *name) { int err; if (!name) return -EFAULT; down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof (*name)); + err = copy_to_user(name, utsname(), sizeof(*name)); up_read(&uts_sem); return err?-EFAULT:0; } diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c index f0aa5c3..dbba1e1 100644 --- a/arch/sh/kernel/sys_sh32.c +++ b/arch/sh/kernel/sys_sh32.c @@ -16,6 +16,7 @@ #include #include #include +#include /* * sys_pipe() is the normal C calling standard for creating @@ -37,13 +38,13 @@ asmlinkage int sys_pipe(unsigned long r4, unsigned long r5, return error; } -asmlinkage ssize_t sys_pread_wrapper(unsigned int fd, char * buf, +asmlinkage ssize_t sys_pread_wrapper(unsigned int fd, char __user *buf, size_t count, long dummy, loff_t pos) { return sys_pread64(fd, buf, count, pos); } -asmlinkage ssize_t sys_pwrite_wrapper(unsigned int fd, const char * buf, +asmlinkage ssize_t sys_pwrite_wrapper(unsigned int fd, const char __user *buf, size_t count, long dummy, loff_t pos) { return sys_pwrite64(fd, buf, count, pos); diff --git a/arch/sh/kernel/time_32.c b/arch/sh/kernel/time_32.c index e2f74cc..23ca711 100644 --- a/arch/sh/kernel/time_32.c +++ b/arch/sh/kernel/time_32.c @@ -16,6 +16,7 @@ #include #include #include +#include /* for rtc_lock */ #include #include #include diff --git a/arch/sh/kernel/timers/timer-cmt.c b/arch/sh/kernel/timers/timer-cmt.c index d20c8c3..c127293 100644 --- a/arch/sh/kernel/timers/timer-cmt.c +++ b/arch/sh/kernel/timers/timer-cmt.c @@ -174,7 +174,7 @@ static int cmt_timer_init(void) return 0; } -struct sys_timer_ops cmt_timer_ops = { +static struct sys_timer_ops cmt_timer_ops = { .init = cmt_timer_init, .start = cmt_timer_start, .stop = cmt_timer_stop, diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c index 511a942..4901f67 100644 --- a/arch/sh/kernel/traps_32.c +++ b/arch/sh/kernel/traps_32.c @@ -192,6 +192,7 @@ static int handle_unaligned_ins(opcode_t instruction, struct pt_regs *regs, int ret, index, count; unsigned long *rm, *rn; unsigned char *src, *dst; + unsigned char __user *srcu, *dstu; index = (instruction>>8)&15; /* 0x0F00 */ rn = ®s->regs[index]; @@ -206,28 +207,28 @@ static int handle_unaligned_ins(opcode_t instruction, struct pt_regs *regs, case 0: /* mov.[bwl] to/from memory via r0+rn */ if (instruction & 8) { /* from memory */ - src = (unsigned char*) *rm; - src += regs->regs[0]; - dst = (unsigned char*) rn; - *(unsigned long*)dst = 0; + srcu = (unsigned char __user *)*rm; + srcu += regs->regs[0]; + dst = (unsigned char *)rn; + *(unsigned long *)dst = 0; #if !defined(__LITTLE_ENDIAN__) dst += 4-count; #endif - if (ma->from(dst, src, count)) + if (ma->from(dst, srcu, count)) goto fetch_fault; sign_extend(count, dst); } else { /* to memory */ - src = (unsigned char*) rm; + src = (unsigned char *)rm; #if !defined(__LITTLE_ENDIAN__) src += 4-count; #endif - dst = (unsigned char*) *rn; - dst += regs->regs[0]; + dstu = (unsigned char __user *)*rn; + dstu += regs->regs[0]; - if (ma->to(dst, src, count)) + if (ma->to(dstu, src, count)) goto fetch_fault; } ret = 0; @@ -235,10 +236,10 @@ static int handle_unaligned_ins(opcode_t instruction, struct pt_regs *regs, case 1: /* mov.l Rm,@(disp,Rn) */ src = (unsigned char*) rm; - dst = (unsigned char*) *rn; - dst += (instruction&0x000F)<<2; + dstu = (unsigned char __user *)*rn; + dstu += (instruction&0x000F)<<2; - if (ma->to(dst, src, 4)) + if (ma->to(dstu, src, 4)) goto fetch_fault; ret = 0; break; @@ -247,28 +248,28 @@ static int handle_unaligned_ins(opcode_t instruction, struct pt_regs *regs, if (instruction & 4) *rn -= count; src = (unsigned char*) rm; - dst = (unsigned char*) *rn; + dstu = (unsigned char __user *)*rn; #if !defined(__LITTLE_ENDIAN__) src += 4-count; #endif - if (ma->to(dst, src, count)) + if (ma->to(dstu, src, count)) goto fetch_fault; ret = 0; break; case 5: /* mov.l @(disp,Rm),Rn */ - src = (unsigned char*) *rm; - src += (instruction&0x000F)<<2; - dst = (unsigned char*) rn; - *(unsigned long*)dst = 0; + srcu = (unsigned char __user *)*rm; + srcu += (instruction & 0x000F) << 2; + dst = (unsigned char *)rn; + *(unsigned long *)dst = 0; - if (ma->from(dst, src, 4)) + if (ma->from(dst, srcu, 4)) goto fetch_fault; ret = 0; break; case 6: /* mov.[bwl] from memory, possibly with post-increment */ - src = (unsigned char*) *rm; + srcu = (unsigned char __user *)*rm; if (instruction & 4) *rm += count; dst = (unsigned char*) rn; @@ -277,7 +278,7 @@ static int handle_unaligned_ins(opcode_t instruction, struct pt_regs *regs, #if !defined(__LITTLE_ENDIAN__) dst += 4-count; #endif - if (ma->from(dst, src, count)) + if (ma->from(dst, srcu, count)) goto fetch_fault; sign_extend(count, dst); ret = 0; @@ -286,28 +287,28 @@ static int handle_unaligned_ins(opcode_t instruction, struct pt_regs *regs, case 8: switch ((instruction&0xFF00)>>8) { case 0x81: /* mov.w R0,@(disp,Rn) */ - src = (unsigned char*) ®s->regs[0]; + src = (unsigned char *) ®s->regs[0]; #if !defined(__LITTLE_ENDIAN__) src += 2; #endif - dst = (unsigned char*) *rm; /* called Rn in the spec */ - dst += (instruction&0x000F)<<1; + dstu = (unsigned char __user *)*rm; /* called Rn in the spec */ + dstu += (instruction & 0x000F) << 1; - if (ma->to(dst, src, 2)) + if (ma->to(dstu, src, 2)) goto fetch_fault; ret = 0; break; case 0x85: /* mov.w @(disp,Rm),R0 */ - src = (unsigned char*) *rm; - src += (instruction&0x000F)<<1; - dst = (unsigned char*) ®s->regs[0]; - *(unsigned long*)dst = 0; + srcu = (unsigned char __user *)*rm; + srcu += (instruction & 0x000F) << 1; + dst = (unsigned char *) ®s->regs[0]; + *(unsigned long *)dst = 0; #if !defined(__LITTLE_ENDIAN__) dst += 2; #endif - if (ma->from(dst, src, 2)) + if (ma->from(dst, srcu, 2)) goto fetch_fault; sign_extend(2, dst); ret = 0; @@ -333,7 +334,8 @@ static inline int handle_delayslot(struct pt_regs *regs, struct mem_access *ma) { opcode_t instruction; - void *addr = (void *)(regs->pc + instruction_size(old_instruction)); + void __user *addr = (void __user *)(regs->pc + + instruction_size(old_instruction)); if (copy_from_user(&instruction, addr, sizeof(instruction))) { /* the instruction-fetch faulted */ @@ -559,7 +561,7 @@ asmlinkage void do_address_error(struct pt_regs *regs, } set_fs(USER_DS); - if (copy_from_user(&instruction, (void *)(regs->pc), + if (copy_from_user(&instruction, (void __user *)(regs->pc), sizeof(instruction))) { /* Argh. Fault on the instruction itself. This should never happen non-SMP @@ -589,7 +591,7 @@ uspace_segv: die("unaligned program counter", regs, error_code); set_fs(KERNEL_DS); - if (copy_from_user(&instruction, (void *)(regs->pc), + if (copy_from_user(&instruction, (void __user *)(regs->pc), sizeof(instruction))) { /* Argh. Fault on the instruction itself. This should never happen non-SMP diff --git a/arch/sh/lib/div64-generic.c b/arch/sh/lib/div64-generic.c index 4bef3b5..60e76aa 100644 --- a/arch/sh/lib/div64-generic.c +++ b/arch/sh/lib/div64-generic.c @@ -3,6 +3,7 @@ */ #include +#include extern uint64_t __xdiv64_32(u64 n, u32 d); diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c index 64b8f7f..7619a0f 100644 --- a/arch/sh/mm/consistent.c +++ b/arch/sh/mm/consistent.c @@ -44,7 +44,7 @@ void *dma_alloc_coherent(struct device *dev, size_t size, */ dma_cache_sync(dev, ret, size, DMA_BIDIRECTIONAL); - ret_nocache = ioremap_nocache(virt_to_phys(ret), size); + ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size); if (!ret_nocache) { free_pages((unsigned long)ret, order); return NULL; diff --git a/arch/sh/mm/pg-nommu.c b/arch/sh/mm/pg-nommu.c index 677dd57..91ed4e6 100644 --- a/arch/sh/mm/pg-nommu.c +++ b/arch/sh/mm/pg-nommu.c @@ -13,6 +13,7 @@ #include #include #include +#include void copy_page(void *to, void *from) { diff --git a/arch/sh/mm/tlb-nommu.c b/arch/sh/mm/tlb-nommu.c index 15111bc..71c742b 100644 --- a/arch/sh/mm/tlb-nommu.c +++ b/arch/sh/mm/tlb-nommu.c @@ -10,6 +10,7 @@ #include #include #include +#include /* * Nothing too terribly exciting here .. diff --git a/drivers/serial/sh-sci.c b/drivers/serial/sh-sci.c index 3df2aae..f5aebc9 100644 --- a/drivers/serial/sh-sci.c +++ b/drivers/serial/sh-sci.c @@ -1113,7 +1113,7 @@ static const char *sci_type(struct uart_port *port) case PORT_IRDA: return "irda"; } - return 0; + return NULL; } static void sci_release_port(struct uart_port *port) -- cgit v0.10.2 From 5840263ecb95e55a2d248fc740644a2c9171a61c Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 5 Sep 2008 15:36:39 +0900 Subject: sh: Don't enable clockevents broadcasting on UP SH-X3 builds. Fixes up compile errors with missing timer definitions. It's pointless to have this enabled anyways if CONFIG_SMP=n. Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 399664c..af2b174 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -326,7 +326,7 @@ config CPU_SUBTYPE_SHX3 select ARCH_SPARSEMEM_ENABLE select SYS_SUPPORTS_NUMA select SYS_SUPPORTS_SMP - select GENERIC_CLOCKEVENTS_BROADCAST + select GENERIC_CLOCKEVENTS_BROADCAST if SMP # SH4AL-DSP Processor Support -- cgit v0.10.2 From 3159e7d62ad13f71ef3fe029c145594d8caa580d Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 5 Sep 2008 15:39:12 +0900 Subject: sh: Add support for memory hot-remove. Signed-off-by: Paul Mundt diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index 8a03926..f8e6dc5 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -134,6 +134,10 @@ config ARCH_ENABLE_MEMORY_HOTPLUG def_bool y depends on SPARSEMEM +config ARCH_ENABLE_MEMORY_HOTREMOVE + def_bool y + depends on SPARSEMEM + config ARCH_MEMORY_PROBE def_bool y depends on MEMORY_HOTPLUG diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index b75a7ac..d4681a5 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -292,4 +292,21 @@ int memory_add_physaddr_to_nid(u64 addr) } EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif + +#ifdef CONFIG_MEMORY_HOTREMOVE +int remove_memory(u64 start, u64 size) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long end_pfn = start_pfn + (size >> PAGE_SHIFT); + int ret; + + ret = offline_pages(start_pfn, end_pfn, 120 * HZ); + if (unlikely(ret)) + printk("%s: Failed, offline_pages() == %d\n", __func__, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(remove_memory); #endif + +#endif /* CONFIG_MEMORY_HOTPLUG */ -- cgit v0.10.2 From c6feb6142cb85228e73497a309f475a0d7279318 Mon Sep 17 00:00:00 2001 From: Stuart Menefy Date: Fri, 5 Sep 2008 16:06:42 +0900 Subject: sh: early cached_to_uncached initialization. statically initialise the cached_to_uncached offset, so that we can use it immediatly. Signed-off-by: Stuart Menefy Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/system_32.h b/arch/sh/include/asm/system_32.h index 16509ed..f7f1056 100644 --- a/arch/sh/include/asm/system_32.h +++ b/arch/sh/include/asm/system_32.h @@ -58,7 +58,8 @@ do { \ last = __last; \ } while (0) -#define __uses_jump_to_uncached __attribute__ ((__section__ (".uncached.text"))) +#define __uses_jump_to_uncached \ + noinline __attribute__ ((__section__ (".uncached.text"))) /* * Jump to uncached area. diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index d4681a5..f1a4942 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -23,7 +23,19 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); pgd_t swapper_pg_dir[PTRS_PER_PGD]; -unsigned long cached_to_uncached = 0; + +#ifdef CONFIG_SUPERH32 +/* + * Handle trivial transitions between cached and uncached + * segments, making use of the 1:1 mapping relationship in + * 512MB lowmem. + * + * This is the offset of the uncached section from its cached alias. + * Default value only valid in 29 bit mode, in 32bit mode will be + * overridden in pmb_init. + */ +unsigned long cached_to_uncached = P2SEG - P1SEG; +#endif #ifdef CONFIG_MMU static void set_pte_phys(unsigned long addr, unsigned long phys, pgprot_t prot) @@ -58,9 +70,7 @@ static void set_pte_phys(unsigned long addr, unsigned long phys, pgprot_t prot) } set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, prot)); - - if (cached_to_uncached) - flush_tlb_one(get_asid(), addr); + flush_tlb_one(get_asid(), addr); } /* @@ -165,15 +175,6 @@ void __init paging_init(void) #ifdef CONFIG_SUPERH32 /* Set up the uncached fixmap */ set_fixmap_nocache(FIX_UNCACHED, __pa(&__uncached_start)); - -#ifdef CONFIG_29BIT - /* - * Handle trivial transitions between cached and uncached - * segments, making use of the 1:1 mapping relationship in - * 512MB lowmem. - */ - cached_to_uncached = P2SEG - P1SEG; -#endif #endif } -- cgit v0.10.2 From 28d6e52cf7e881834d2dab370afa20b6223f726c Mon Sep 17 00:00:00 2001 From: Stuart Menefy Date: Fri, 5 Sep 2008 16:14:17 +0900 Subject: sh: Fix up broken 32-bit initrd support. Signed-off-by: Stuart Menefy Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index 6d0899e..fc7171a 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -249,17 +249,18 @@ void __init setup_bootmem_allocator(unsigned long free_pfn) ROOT_DEV = Root_RAM0; if (LOADER_TYPE && INITRD_START) { - if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) { - reserve_bootmem(INITRD_START + __MEMORY_START, - INITRD_SIZE, BOOTMEM_DEFAULT); - initrd_start = INITRD_START + PAGE_OFFSET + - __MEMORY_START; + unsigned long initrd_start_phys = INITRD_START + __MEMORY_START; + + if (initrd_start_phys + INITRD_SIZE <= PFN_PHYS(max_low_pfn)) { + reserve_bootmem(initrd_start_phys, INITRD_SIZE, + BOOTMEM_DEFAULT); + initrd_start = (unsigned long)__va(initrd_start_phys); initrd_end = initrd_start + INITRD_SIZE; } else { printk("initrd extends beyond end of memory " - "(0x%08lx > 0x%08lx)\ndisabling initrd\n", - INITRD_START + INITRD_SIZE, - max_low_pfn << PAGE_SHIFT); + "(0x%08lx > 0x%08lx)\ndisabling initrd\n", + initrd_start_phys + INITRD_SIZE, + PFN_PHYS(max_low_pfn)); initrd_start = 0; } } -- cgit v0.10.2 From 96e14e54a6abd5a4bcd75e33962f87bef145d1f6 Mon Sep 17 00:00:00 2001 From: Stuart Menefy Date: Fri, 5 Sep 2008 16:17:15 +0900 Subject: sh: vmalloc pgtable sync fix. This fixes a problem in the code which copies the vmalloc portion of the kernel's page table into the current user space page table. The addition of the four level page table code breaks on folded page tables, because the pud level is always present (although folded). This updates the code to use the same style of updates for the pud as is used for the pgd level. Signed-off-by: Stuart Menefy Signed-off-by: Paul Mundt diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c index 0c776fd..e8efda9 100644 --- a/arch/sh/mm/fault_32.c +++ b/arch/sh/mm/fault_32.c @@ -61,7 +61,6 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, pgd = get_TTB() + offset; pgd_k = swapper_pg_dir + offset; - /* This will never happen with the folded page table. */ if (!pgd_present(*pgd)) { if (!pgd_present(*pgd_k)) goto bad_area_nosemaphore; @@ -71,9 +70,13 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, pud = pud_offset(pgd, address); pud_k = pud_offset(pgd_k, address); - if (pud_present(*pud) || !pud_present(*pud_k)) - goto bad_area_nosemaphore; - set_pud(pud, *pud_k); + + if (!pud_present(*pud)) { + if (!pud_present(*pud_k)) + goto bad_area_nosemaphore; + set_pud(pud, *pud_k); + return; + } pmd = pmd_offset(pud, address); pmd_k = pmd_offset(pud_k, address); -- cgit v0.10.2 From 664718a34348a9ef6f966c3977e8df927a378134 Mon Sep 17 00:00:00 2001 From: Chris Smith Date: Fri, 5 Sep 2008 16:24:13 +0900 Subject: sh: Fix uImage load address in 32-bit mode. Fix "make uImage" load and entry addresses in 32-bit mode. Signed-off-by: Chris Smith Signed-off-by: Paul Mundt diff --git a/arch/sh/boot/Makefile b/arch/sh/boot/Makefile index 5b54965..c16ccd4 100644 --- a/arch/sh/boot/Makefile +++ b/arch/sh/boot/Makefile @@ -33,10 +33,16 @@ $(obj)/zImage: $(obj)/compressed/vmlinux FORCE $(obj)/compressed/vmlinux: FORCE $(Q)$(MAKE) $(build)=$(obj)/compressed $@ +ifeq ($(CONFIG_32BIT),y) +KERNEL_LOAD := $(shell /bin/bash -c 'printf "0x%08x" \ + $$[$(CONFIG_PAGE_OFFSET) + \ + $(CONFIG_ZERO_PAGE_OFFSET)]') +else KERNEL_LOAD := $(shell /bin/bash -c 'printf "0x%08x" \ $$[$(CONFIG_PAGE_OFFSET) + \ $(CONFIG_MEMORY_START) + \ $(CONFIG_ZERO_PAGE_OFFSET)]') +endif KERNEL_ENTRY := $(shell /bin/bash -c 'printf "0x%08x" \ $$[$(CONFIG_PAGE_OFFSET) + \ -- cgit v0.10.2 From f040ddaf4cfd28f25ea9d6a42d3c734d5c3f6798 Mon Sep 17 00:00:00 2001 From: Stuart Menefy Date: Fri, 5 Sep 2008 16:29:40 +0900 Subject: sh: Fix an unusual memory initialisation error. This fixes a problems with the set up of Linux memory: - When reserving memory at boot time, the code previously reserved the bottom page of memory, and then from one page up to the end of the bootmap. This had the desired effect, but was strictly speaking wrong, as the one page was actually whatever CONFIG_ZERO_PAGE_OFFSET had been set to. Signed-off-by: Stuart Menefy Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index fc7171a..fc098c8 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -233,15 +233,17 @@ void __init setup_bootmem_allocator(unsigned long free_pfn) * case of us accidentally initializing the bootmem allocator with * an invalid RAM area. */ - reserve_bootmem(__MEMORY_START+PAGE_SIZE, - (PFN_PHYS(free_pfn)+bootmap_size+PAGE_SIZE-1)-__MEMORY_START, - BOOTMEM_DEFAULT); + reserve_bootmem(__MEMORY_START + CONFIG_ZERO_PAGE_OFFSET, + (PFN_PHYS(free_pfn) + bootmap_size + PAGE_SIZE - 1) - + (__MEMORY_START + CONFIG_ZERO_PAGE_OFFSET), + BOOTMEM_DEFAULT); /* * reserve physical page 0 - it's a special BIOS page on many boxes, * enabling clean reboots, SMP operation, laptop functions. */ - reserve_bootmem(__MEMORY_START, PAGE_SIZE, BOOTMEM_DEFAULT); + reserve_bootmem(__MEMORY_START, CONFIG_ZERO_PAGE_OFFSET, + BOOTMEM_DEFAULT); sparse_memory_present_with_active_regions(0); -- cgit v0.10.2 From b6ad1e8c3f76fcc5dee506d5e79e752d296ff745 Mon Sep 17 00:00:00 2001 From: Carl Shaw Date: Fri, 5 Sep 2008 16:36:19 +0900 Subject: sh: Subnormal double to float conversion This patch adds support for the SH4 to convert a subnormal double into a float by catching the FPE and implementing the FCNVDS instruction in software. Signed-off-by: Carl Shaw Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/cpu/sh4/fpu.c b/arch/sh/kernel/cpu/sh4/fpu.c index 2d452f6..2780917 100644 --- a/arch/sh/kernel/cpu/sh4/fpu.c +++ b/arch/sh/kernel/cpu/sh4/fpu.c @@ -36,7 +36,7 @@ extern unsigned long int float32_add(unsigned long int a, unsigned long int b); extern unsigned long long float64_sub(unsigned long long a, unsigned long long b); extern unsigned long int float32_sub(unsigned long int a, unsigned long int b); - +extern unsigned long int float64_to_float32(unsigned long long a); static unsigned int fpu_exception_flags; /* @@ -417,6 +417,29 @@ static int ieee_fpe_handler(struct pt_regs *regs) regs->pc = nextpc; return 1; + } else if ((finsn & 0xf0bd) == 0xf0bd) { + /* fcnvds - double to single precision convert */ + struct task_struct *tsk = current; + int m; + unsigned int hx; + + m = (finsn >> 9) & 0x7; + hx = tsk->thread.fpu.hard.fp_regs[m]; + + if ((tsk->thread.fpu.hard.fpscr & FPSCR_CAUSE_ERROR) + && ((hx & 0x7fffffff) < 0x00100000)) { + /* subnormal double to float conversion */ + long long llx; + + llx = ((long long)tsk->thread.fpu.hard.fp_regs[m] << 32) + | tsk->thread.fpu.hard.fp_regs[m + 1]; + + tsk->thread.fpu.hard.fpul = float64_to_float32(llx); + } else + return 0; + + regs->pc = nextpc; + return 1; } return 0; diff --git a/arch/sh/kernel/cpu/sh4/softfloat.c b/arch/sh/kernel/cpu/sh4/softfloat.c index 828cb57..2b747f3 100644 --- a/arch/sh/kernel/cpu/sh4/softfloat.c +++ b/arch/sh/kernel/cpu/sh4/softfloat.c @@ -85,6 +85,7 @@ float64 float64_div(float64 a, float64 b); float32 float32_div(float32 a, float32 b); float32 float32_mul(float32 a, float32 b); float64 float64_mul(float64 a, float64 b); +float32 float64_to_float32(float64 a); inline void add128(bits64 a0, bits64 a1, bits64 b0, bits64 b1, bits64 * z0Ptr, bits64 * z1Ptr); inline void sub128(bits64 a0, bits64 a1, bits64 b0, bits64 b1, bits64 * z0Ptr, @@ -890,3 +891,31 @@ float64 float64_mul(float64 a, float64 b) } return roundAndPackFloat64(zSign, zExp, zSig0); } + +/* + * ------------------------------------------------------------------------------- + * Returns the result of converting the double-precision floating-point value + * `a' to the single-precision floating-point format. The conversion is + * performed according to the IEC/IEEE Standard for Binary Floating-point + * Arithmetic. + * ------------------------------------------------------------------------------- + * */ +float32 float64_to_float32(float64 a) +{ + flag aSign; + int16 aExp; + bits64 aSig; + bits32 zSig; + + aSig = extractFloat64Frac( a ); + aExp = extractFloat64Exp( a ); + aSign = extractFloat64Sign( a ); + + shift64RightJamming( aSig, 22, &aSig ); + zSig = aSig; + if ( aExp || zSig ) { + zSig |= 0x40000000; + aExp -= 0x381; + } + return roundAndPackFloat32(aSign, aExp, zSig); +} -- cgit v0.10.2 From 61c66387e640abc0e0aa11519bc48ff9bb50580a Mon Sep 17 00:00:00 2001 From: Francesco Virlinzi Date: Fri, 5 Sep 2008 16:40:22 +0900 Subject: sh: fix the TMU code to allow a fully running NO_HZ system This patch fixes the TMU code to allow NO_HZ to work on sh Signed-off-by: Francesco Virlinzi Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/timers/timer-tmu.c b/arch/sh/kernel/timers/timer-tmu.c index 1ca9ad4..aaaf90d 100644 --- a/arch/sh/kernel/timers/timer-tmu.c +++ b/arch/sh/kernel/timers/timer-tmu.c @@ -28,43 +28,90 @@ #define TMU_TOCR_INIT 0x00 #define TMU_TCR_INIT 0x0020 -static int tmu_timer_start(void) +#define TMU0 (0) +#define TMU1 (1) + +static inline void _tmu_start(int tmu_num) { - ctrl_outb(ctrl_inb(TMU_012_TSTR) | 0x3, TMU_012_TSTR); - return 0; + ctrl_outb(ctrl_inb(TMU_012_TSTR) | (0x1<mode == CLOCK_EVT_MODE_PERIODIC); + _tmu_set_irq(TMU0,1); return 0; } @@ -96,12 +143,8 @@ static struct clock_event_device tmu0_clockevent = { static irqreturn_t tmu_timer_interrupt(int irq, void *dummy) { struct clock_event_device *evt = &tmu0_clockevent; - unsigned long timer_status; - - /* Clear UNF bit */ - timer_status = ctrl_inw(TMU0_TCR); - timer_status &= ~0x100; - ctrl_outw(timer_status, TMU0_TCR); + _tmu_clear_status(TMU0); + _tmu_set_irq(TMU0,tmu0_clockevent.mode != CLOCK_EVT_MODE_ONESHOT); evt->event_handler(evt); @@ -109,56 +152,73 @@ static irqreturn_t tmu_timer_interrupt(int irq, void *dummy) } static struct irqaction tmu0_irq = { - .name = "periodic timer", + .name = "periodic/oneshot timer", .handler = tmu_timer_interrupt, .flags = IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL, .mask = CPU_MASK_NONE, }; -static void tmu0_clk_init(struct clk *clk) +static void __init tmu_clk_init(struct clk *clk) { - u8 divisor = TMU_TCR_INIT & 0x7; - ctrl_outw(TMU_TCR_INIT, TMU0_TCR); - clk->rate = clk->parent->rate / (4 << (divisor << 1)); + u8 divisor = TMU_TCR_INIT & 0x7; + int tmu_num = clk->name[3]-'0'; + ctrl_outw(TMU_TCR_INIT, TMU0_TCR+(tmu_num*0xC)); + clk->rate = clk_get_rate(clk->parent) / (4 << (divisor << 1)); } -static void tmu0_clk_recalc(struct clk *clk) +static void tmu_clk_recalc(struct clk *clk) { - u8 divisor = ctrl_inw(TMU0_TCR) & 0x7; - clk->rate = clk->parent->rate / (4 << (divisor << 1)); -} + int tmu_num = clk->name[3]-'0'; + unsigned long prev_rate = clk_get_rate(clk); + unsigned long flags; + u8 divisor = ctrl_inw(TMU0_TCR+tmu_num*0xC) & 0x7; + clk->rate = clk_get_rate(clk->parent) / (4 << (divisor << 1)); -static struct clk_ops tmu0_clk_ops = { - .init = tmu0_clk_init, - .recalc = tmu0_clk_recalc, -}; + if(prev_rate==clk_get_rate(clk)) + return; -static struct clk tmu0_clk = { - .name = "tmu0_clk", - .ops = &tmu0_clk_ops, -}; + if(tmu_num) + return; /* No more work on TMU1 */ -static void tmu1_clk_init(struct clk *clk) -{ - u8 divisor = TMU_TCR_INIT & 0x7; - ctrl_outw(divisor, TMU1_TCR); - clk->rate = clk->parent->rate / (4 << (divisor << 1)); -} + local_irq_save(flags); + tmus_are_scaled = (prev_rate > clk->rate); -static void tmu1_clk_recalc(struct clk *clk) -{ - u8 divisor = ctrl_inw(TMU1_TCR) & 0x7; - clk->rate = clk->parent->rate / (4 << (divisor << 1)); + _tmu_stop(TMU0); + + tmu0_clockevent.mult = div_sc(clk->rate, NSEC_PER_SEC, + tmu0_clockevent.shift); + tmu0_clockevent.max_delta_ns = + clockevent_delta2ns(-1, &tmu0_clockevent); + tmu0_clockevent.min_delta_ns = + clockevent_delta2ns(1, &tmu0_clockevent); + + if (tmus_are_scaled) + tmu_latest_interval[TMU0] >>= 1; + else + tmu_latest_interval[TMU0] <<= 1; + + tmu_timer_set_interval(TMU0, + tmu_latest_interval[TMU0], + tmu0_clockevent.mode == CLOCK_EVT_MODE_PERIODIC); + + _tmu_start(TMU0); + + local_irq_restore(flags); } -static struct clk_ops tmu1_clk_ops = { - .init = tmu1_clk_init, - .recalc = tmu1_clk_recalc, +static struct clk_ops tmu_clk_ops = { + .init = tmu_clk_init, + .recalc = tmu_clk_recalc, +}; + +static struct clk tmu0_clk = { + .name = "tmu0_clk", + .ops = &tmu_clk_ops, }; static struct clk tmu1_clk = { .name = "tmu1_clk", - .ops = &tmu1_clk_ops, + .ops = &tmu_clk_ops, }; static int tmu_timer_init(void) @@ -189,11 +249,12 @@ static int tmu_timer_init(void) frequency = clk_get_rate(&tmu0_clk); interval = (frequency + HZ / 2) / HZ; - sh_hpt_frequency = clk_get_rate(&tmu1_clk); - ctrl_outl(~0, TMU1_TCNT); - ctrl_outl(~0, TMU1_TCOR); + tmu_timer_set_interval(TMU0,interval, 1); + tmu_timer_set_interval(TMU1,~0,1); - tmu0_timer_set_interval(interval, 1); + _tmu_start(TMU1); + + sh_hpt_frequency = clk_get_rate(&tmu1_clk); tmu0_clockevent.mult = div_sc(frequency, NSEC_PER_SEC, tmu0_clockevent.shift); -- cgit v0.10.2 From b6c20e4290a1ef92bcef5ec9dd8e5c7d036153aa Mon Sep 17 00:00:00 2001 From: Marek Skuczynski Date: Fri, 5 Sep 2008 16:42:58 +0900 Subject: sh: remove unnecessary memset after alloc_bootmem_low_pages Because alloc_bootmem functions return the allocated memory always zeroed, an additional call of memset on allocated memory is unnecessary. Signed-off-by: Marek Skuczynski Signed-off-by: Carl Shaw Signed-off-by: Paul Mundt diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index f1a4942..31211bf 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -123,7 +123,6 @@ void __init page_table_range_init(unsigned long start, unsigned long end, if (!pmd_present(*pmd)) { pte_t *pte_table; pte_table = (pte_t *)alloc_bootmem_low_pages(PAGE_SIZE); - memset(pte_table, 0, PAGE_SIZE); pmd_populate_kernel(&init_mm, pmd, pte_table); } -- cgit v0.10.2 From d39f5450146ff39f66cfde9d5184420627d0ac51 Mon Sep 17 00:00:00 2001 From: Chris Smith Date: Fri, 5 Sep 2008 17:15:39 +0900 Subject: sh: Add kprobes support. Initial support for kprobes/kretprobes for 32-bit SH platforms. [ General cleanup and some rework for the kretprobe hash lock. -- PFM ] Signed-off-by: Chris Smith Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index af2b174..334917a 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -20,6 +20,8 @@ config SUPERH config SUPERH32 def_bool !SUPERH64 + select HAVE_KPROBES + select HAVE_KRETPROBES config SUPERH64 def_bool y if CPU_SH5 diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h new file mode 100644 index 0000000..70fc629 --- /dev/null +++ b/arch/sh/include/asm/kprobes.h @@ -0,0 +1,59 @@ +#ifndef __ASM_SH_KPROBES_H +#define __ASM_SH_KPROBES_H + +#ifdef CONFIG_KPROBES + +#include +#include + +struct pt_regs; + +typedef u16 kprobe_opcode_t; +#define BREAKPOINT_INSTRUCTION 0xc3ff + +#define MAX_INSN_SIZE 16 +#define MAX_STACK_SIZE 64 +#define MIN_STACK_SIZE(ADDR) (((MAX_STACK_SIZE) < \ + (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR))) \ + ? (MAX_STACK_SIZE) \ + : (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR))) + +#define regs_return_value(regs) ((regs)->regs[0]) +#define flush_insn_slot(p) do { } while (0) +#define kretprobe_blacklist_size 0 + +struct kprobe; + +void arch_remove_kprobe(struct kprobe *); +void kretprobe_trampoline(void); +void jprobe_return_end(void); + +/* Architecture specific copy of original instruction*/ +struct arch_specific_insn { + /* copy of the original instruction */ + kprobe_opcode_t insn[MAX_INSN_SIZE]; +}; + +struct prev_kprobe { + struct kprobe *kp; + unsigned long status; +}; + +/* per-cpu kprobe control block */ +struct kprobe_ctlblk { + unsigned long kprobe_status; + unsigned long jprobe_saved_r15; + struct pt_regs jprobe_saved_regs; + kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE]; + struct prev_kprobe prev_kprobe; +}; + +extern int kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data); +extern int kprobe_handle_illslot(unsigned long pc); +#else + +#define kprobe_handle_illslot(pc) (-1) + +#endif /* CONFIG_KPROBES */ +#endif /* __ASM_SH_KPROBES_H */ diff --git a/arch/sh/kernel/Makefile_32 b/arch/sh/kernel/Makefile_32 index 0e6905f..12e617b 100644 --- a/arch/sh/kernel/Makefile_32 +++ b/arch/sh/kernel/Makefile_32 @@ -23,5 +23,6 @@ obj-$(CONFIG_PM) += pm.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_ELF_CORE) += dump_task.o obj-$(CONFIG_IO_TRAPPED) += io_trapped.o +obj-$(CONFIG_KPROBES) += kprobes.o EXTRA_CFLAGS += -Werror diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c new file mode 100644 index 0000000..c4f4a09 --- /dev/null +++ b/arch/sh/kernel/kprobes.c @@ -0,0 +1,568 @@ +/* + * Kernel probes (kprobes) for SuperH + * + * Copyright (C) 2007 Chris Smith + * Copyright (C) 2006 Lineo Solutions, Inc. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ +#include +#include +#include +#include +#include +#include +#include + +DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +static struct kprobe saved_current_opcode; +static struct kprobe saved_next_opcode; +static struct kprobe saved_next_opcode2; + +#define OPCODE_JMP(x) (((x) & 0xF0FF) == 0x402b) +#define OPCODE_JSR(x) (((x) & 0xF0FF) == 0x400b) +#define OPCODE_BRA(x) (((x) & 0xF000) == 0xa000) +#define OPCODE_BRAF(x) (((x) & 0xF0FF) == 0x0023) +#define OPCODE_BSR(x) (((x) & 0xF000) == 0xb000) +#define OPCODE_BSRF(x) (((x) & 0xF0FF) == 0x0003) + +#define OPCODE_BF_S(x) (((x) & 0xFF00) == 0x8f00) +#define OPCODE_BT_S(x) (((x) & 0xFF00) == 0x8d00) + +#define OPCODE_BF(x) (((x) & 0xFF00) == 0x8b00) +#define OPCODE_BT(x) (((x) & 0xFF00) == 0x8900) + +#define OPCODE_RTS(x) (((x) & 0x000F) == 0x000b) +#define OPCODE_RTE(x) (((x) & 0xFFFF) == 0x002b) + +int __kprobes arch_prepare_kprobe(struct kprobe *p) +{ + kprobe_opcode_t opcode = *(kprobe_opcode_t *) (p->addr); + + if (OPCODE_RTE(opcode)) + return -EFAULT; /* Bad breakpoint */ + + p->opcode = opcode; + + return 0; +} + +void __kprobes arch_copy_kprobe(struct kprobe *p) +{ + memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + p->opcode = *p->addr; +} + +void __kprobes arch_arm_kprobe(struct kprobe *p) +{ + *p->addr = BREAKPOINT_INSTRUCTION; + flush_icache_range((unsigned long)p->addr, + (unsigned long)p->addr + sizeof(kprobe_opcode_t)); +} + +void __kprobes arch_disarm_kprobe(struct kprobe *p) +{ + *p->addr = p->opcode; + flush_icache_range((unsigned long)p->addr, + (unsigned long)p->addr + sizeof(kprobe_opcode_t)); +} + +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + if (*p->addr == BREAKPOINT_INSTRUCTION) + return 1; + + return 0; +} + +/** + * If an illegal slot instruction exception occurs for an address + * containing a kprobe, remove the probe. + * + * Returns 0 if the exception was handled successfully, 1 otherwise. + */ +int __kprobes kprobe_handle_illslot(unsigned long pc) +{ + struct kprobe *p = get_kprobe((kprobe_opcode_t *) pc + 1); + + if (p != NULL) { + printk("Warning: removing kprobe from delay slot: 0x%.8x\n", + (unsigned int)pc + 2); + unregister_kprobe(p); + return 0; + } + + return 1; +} + +void __kprobes arch_remove_kprobe(struct kprobe *p) +{ + if (saved_next_opcode.addr != 0x0) { + arch_disarm_kprobe(p); + arch_disarm_kprobe(&saved_next_opcode); + saved_next_opcode.addr = 0x0; + saved_next_opcode.opcode = 0x0; + + if (saved_next_opcode2.addr != 0x0) { + arch_disarm_kprobe(&saved_next_opcode2); + saved_next_opcode2.addr = 0x0; + saved_next_opcode2.opcode = 0x0; + } + } +} + +static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + kcb->prev_kprobe.kp = kprobe_running(); + kcb->prev_kprobe.status = kcb->kprobe_status; +} + +static inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + kcb->kprobe_status = kcb->prev_kprobe.status; +} + +static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + __get_cpu_var(current_kprobe) = p; +} + +/* + * Singlestep is implemented by disabling the current kprobe and setting one + * on the next instruction, following branches. Two probes are set if the + * branch is conditional. + */ +static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t *addr = NULL; + saved_current_opcode.addr = (kprobe_opcode_t *) (regs->pc); + addr = saved_current_opcode.addr; + + if (p != NULL) { + arch_disarm_kprobe(p); + + if (OPCODE_JSR(p->opcode) || OPCODE_JMP(p->opcode)) { + unsigned int reg_nr = ((p->opcode >> 8) & 0x000F); + saved_next_opcode.addr = + (kprobe_opcode_t *) regs->regs[reg_nr]; + } else if (OPCODE_BRA(p->opcode) || OPCODE_BSR(p->opcode)) { + unsigned long disp = (p->opcode & 0x0FFF); + saved_next_opcode.addr = + (kprobe_opcode_t *) (regs->pc + 4 + disp * 2); + + } else if (OPCODE_BRAF(p->opcode) || OPCODE_BSRF(p->opcode)) { + unsigned int reg_nr = ((p->opcode >> 8) & 0x000F); + saved_next_opcode.addr = + (kprobe_opcode_t *) (regs->pc + 4 + + regs->regs[reg_nr]); + + } else if (OPCODE_RTS(p->opcode)) { + saved_next_opcode.addr = (kprobe_opcode_t *) regs->pr; + + } else if (OPCODE_BF(p->opcode) || OPCODE_BT(p->opcode)) { + unsigned long disp = (p->opcode & 0x00FF); + /* case 1 */ + saved_next_opcode.addr = p->addr + 1; + /* case 2 */ + saved_next_opcode2.addr = + (kprobe_opcode_t *) (regs->pc + 4 + disp * 2); + saved_next_opcode2.opcode = *(saved_next_opcode2.addr); + arch_arm_kprobe(&saved_next_opcode2); + + } else if (OPCODE_BF_S(p->opcode) || OPCODE_BT_S(p->opcode)) { + unsigned long disp = (p->opcode & 0x00FF); + /* case 1 */ + saved_next_opcode.addr = p->addr + 2; + /* case 2 */ + saved_next_opcode2.addr = + (kprobe_opcode_t *) (regs->pc + 4 + disp * 2); + saved_next_opcode2.opcode = *(saved_next_opcode2.addr); + arch_arm_kprobe(&saved_next_opcode2); + + } else { + saved_next_opcode.addr = p->addr + 1; + } + + saved_next_opcode.opcode = *(saved_next_opcode.addr); + arch_arm_kprobe(&saved_next_opcode); + } +} + +/* Called with kretprobe_lock held */ +void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + ri->ret_addr = (kprobe_opcode_t *) regs->pr; + + /* Replace the return addr with trampoline addr */ + regs->pr = (unsigned long)kretprobe_trampoline; +} + +static int __kprobes kprobe_handler(struct pt_regs *regs) +{ + struct kprobe *p; + int ret = 0; + kprobe_opcode_t *addr = NULL; + struct kprobe_ctlblk *kcb; + + /* + * We don't want to be preempted for the entire + * duration of kprobe processing + */ + preempt_disable(); + kcb = get_kprobe_ctlblk(); + + addr = (kprobe_opcode_t *) (regs->pc); + + /* Check we're not actually recursing */ + if (kprobe_running()) { + p = get_kprobe(addr); + if (p) { + if (kcb->kprobe_status == KPROBE_HIT_SS && + *p->ainsn.insn == BREAKPOINT_INSTRUCTION) { + goto no_kprobe; + } + /* We have reentered the kprobe_handler(), since + * another probe was hit while within the handler. + * We here save the original kprobes variables and + * just single step on the instruction of the new probe + * without calling any user handlers. + */ + save_previous_kprobe(kcb); + set_current_kprobe(p, regs, kcb); + kprobes_inc_nmissed_count(p); + prepare_singlestep(p, regs); + kcb->kprobe_status = KPROBE_REENTER; + return 1; + } else { + p = __get_cpu_var(current_kprobe); + if (p->break_handler && p->break_handler(p, regs)) { + goto ss_probe; + } + } + goto no_kprobe; + } + + p = get_kprobe(addr); + if (!p) { + /* Not one of ours: let kernel handle it */ + goto no_kprobe; + } + + set_current_kprobe(p, regs, kcb); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + if (p->pre_handler && p->pre_handler(p, regs)) + /* handler has already set things up, so skip ss setup */ + return 1; + + ss_probe: + prepare_singlestep(p, regs); + kcb->kprobe_status = KPROBE_HIT_SS; + return 1; + + no_kprobe: + preempt_enable_no_resched(); + return ret; +} + +/* + * For function-return probes, init_kprobes() establishes a probepoint + * here. When a retprobed function returns, this probe is hit and + * trampoline_probe_handler() runs, calling the kretprobe's handler. + */ +void kretprobe_trampoline_holder(void) +{ + asm volatile ("kretprobe_trampoline: \n" "nop\n"); +} + +/* + * Called when we hit the probe point at kretprobe_trampoline + */ +int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kretprobe_instance *ri = NULL; + struct hlist_head *head, empty_rp; + struct hlist_node *node, *tmp; + unsigned long flags, orig_ret_address = 0; + unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; + + INIT_HLIST_HEAD(&empty_rp); + kretprobe_hash_lock(current, &head, &flags); + + /* + * It is possible to have multiple instances associated with a given + * task either because an multiple functions in the call path + * have a return probe installed on them, and/or more then one return + * return probe was registered for a target function. + * + * We can handle this because: + * - instances are always inserted at the head of the list + * - when multiple return probes are registered for the same + * function, the first instance's ret_addr will point to the + * real return address, and all the rest will point to + * kretprobe_trampoline + */ + hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; + + if (ri->rp && ri->rp->handler) { + __get_cpu_var(current_kprobe) = &ri->rp->kp; + ri->rp->handler(ri, regs); + __get_cpu_var(current_kprobe) = NULL; + } + + orig_ret_address = (unsigned long)ri->ret_addr; + recycle_rp_inst(ri, &empty_rp); + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; + } + + kretprobe_assert(ri, orig_ret_address, trampoline_address); + + regs->pc = orig_ret_address; + kretprobe_hash_unlock(current, &flags); + + preempt_enable_no_resched(); + + hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } + + return orig_ret_address; +} + +static inline int post_kprobe_handler(struct pt_regs *regs) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + kprobe_opcode_t *addr = NULL; + struct kprobe *p = NULL; + + if (!cur) + return 0; + + if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + cur->post_handler(cur, regs, 0); + } + + if (saved_next_opcode.addr != 0x0) { + arch_disarm_kprobe(&saved_next_opcode); + saved_next_opcode.addr = 0x0; + saved_next_opcode.opcode = 0x0; + + addr = saved_current_opcode.addr; + saved_current_opcode.addr = 0x0; + + p = get_kprobe(addr); + arch_arm_kprobe(p); + + if (saved_next_opcode2.addr != 0x0) { + arch_disarm_kprobe(&saved_next_opcode2); + saved_next_opcode2.addr = 0x0; + saved_next_opcode2.opcode = 0x0; + } + } + + /*Restore back the original saved kprobes variables and continue. */ + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); + goto out; + } + reset_current_kprobe(); + + out: + preempt_enable_no_resched(); + + return 1; +} + +static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + const struct exception_table_entry *entry; + + switch (kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe, point the pc back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->pc = (unsigned long)cur->addr; + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else + reset_current_kprobe(); + preempt_enable_no_resched(); + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accounting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(cur); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) + return 1; + + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ + if ((entry = search_exception_tables(regs->pc)) != NULL) { + regs->pc = entry->fixup; + return 1; + } + + /* + * fixup_exception() could not handle it, + * Let do_page_fault() fix it. + */ + break; + default: + break; + } + return 0; +} + +/* + * Wrapper routine to for handling exceptions. + */ +int __kprobes kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct kprobe *p = NULL; + struct die_args *args = (struct die_args *)data; + int ret = NOTIFY_DONE; + kprobe_opcode_t *addr = NULL; + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + addr = (kprobe_opcode_t *) (args->regs->pc); + if (val == DIE_TRAP) { + if (!kprobe_running()) { + if (kprobe_handler(args->regs)) { + ret = NOTIFY_STOP; + } else { + /* Not a kprobe trap */ + force_sig(SIGTRAP, current); + } + } else { + p = get_kprobe(addr); + if ((kcb->kprobe_status == KPROBE_HIT_SS) || + (kcb->kprobe_status == KPROBE_REENTER)) { + if (post_kprobe_handler(args->regs)) + ret = NOTIFY_STOP; + } else { + if (kprobe_handler(args->regs)) { + ret = NOTIFY_STOP; + } else { + p = __get_cpu_var(current_kprobe); + if (p->break_handler + && p->break_handler(p, args->regs)) + ret = NOTIFY_STOP; + } + } + } + } + + return ret; +} + +int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct jprobe *jp = container_of(p, struct jprobe, kp); + unsigned long addr; + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + kcb->jprobe_saved_regs = *regs; + kcb->jprobe_saved_r15 = regs->regs[15]; + addr = kcb->jprobe_saved_r15; + + /* + * TBD: As Linus pointed out, gcc assumes that the callee + * owns the argument space and could overwrite it, e.g. + * tailcall optimization. So, to be absolutely safe + * we also save and restore enough stack bytes to cover + * the argument area. + */ + memcpy(kcb->jprobes_stack, (kprobe_opcode_t *) addr, + MIN_STACK_SIZE(addr)); + + regs->pc = (unsigned long)(jp->entry); + + return 1; +} + +void __kprobes jprobe_return(void) +{ + __asm("trapa #-1\n\t" "jprobe_return_end:\n\t" "nop\n\t"); + +} + +int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + u8 *addr = (u8 *) regs->pc; + unsigned long stack_addr = kcb->jprobe_saved_r15; + + if ((addr >= (u8 *) jprobe_return) + && (addr <= (u8 *) jprobe_return_end)) { + *regs = kcb->jprobe_saved_regs; + + memcpy((kprobe_opcode_t *) stack_addr, kcb->jprobes_stack, + MIN_STACK_SIZE(stack_addr)); + + kcb->kprobe_status = KPROBE_HIT_SS; + return 1; + } + return 0; +} + +static struct kprobe trampoline_p = { + .addr = (kprobe_opcode_t *) &kretprobe_trampoline, + .pre_handler = trampoline_probe_handler +}; + +int __init arch_init_kprobes(void) +{ + saved_next_opcode.addr = 0x0; + saved_next_opcode.opcode = 0x0; + + saved_current_opcode.addr = 0x0; + saved_current_opcode.opcode = 0x0; + + saved_next_opcode2.addr = 0x0; + saved_next_opcode2.opcode = 0x0; + + return register_kprobe(&trampoline_p); +} diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c index 4901f67..862667a 100644 --- a/arch/sh/kernel/traps_32.c +++ b/arch/sh/kernel/traps_32.c @@ -26,6 +26,7 @@ #include #include #include +#include #ifdef CONFIG_SH_KGDB #include @@ -743,6 +744,10 @@ asmlinkage void do_illegal_slot_inst(unsigned long r4, unsigned long r5, struct pt_regs *regs = RELOC_HIDE(&__regs, 0); unsigned long error_code; struct task_struct *tsk = current; + + if (kprobe_handle_illslot(regs->pc) == 0) + return; + #ifdef CONFIG_SH_FPU_EMU unsigned short inst = 0; -- cgit v0.10.2 From 6907e6a601a4fd442535d977886bbd3761aa2b56 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 5 Sep 2008 17:27:37 +0900 Subject: sh: Add the rest of the boot targets to arch/sh/boot/.gitignore. Signed-off-by: Paul Mundt diff --git a/arch/sh/boot/.gitignore b/arch/sh/boot/.gitignore index b6718de..aad5edd 100644 --- a/arch/sh/boot/.gitignore +++ b/arch/sh/boot/.gitignore @@ -1 +1,4 @@ zImage +vmlinux.srec +uImage +uImage.srec -- cgit v0.10.2 From 205a3b4328de1c8ddd99ddd5092bed1344068213 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 5 Sep 2008 18:00:29 +0900 Subject: sh: uninline flush_icache_all(). This uses jump_to_uncached() which is now given the noinline attribute due to the special section mapping. Kill off the inline attribute to fix up compilation failure. Signed-off-by: Paul Mundt diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index 1fdc8d9..5cfe08d 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -261,7 +261,7 @@ void flush_dcache_page(struct page *page) } /* TODO: Selective icache invalidation through IC address array.. */ -static inline void __uses_jump_to_uncached flush_icache_all(void) +static void __uses_jump_to_uncached flush_icache_all(void) { unsigned long flags, ccr; -- cgit v0.10.2 From 53abf911fa6753dfbd6775ae541fb2f8b9f5b825 Mon Sep 17 00:00:00 2001 From: Luca Santini Date: Mon, 8 Sep 2008 11:54:56 +0900 Subject: sh: Enable IRLM mode for SH7760 IRQ_MODE_IRQ. Follows the same setting as SH7750. Signed-off-by: Luca Santini Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7760.c b/arch/sh/kernel/cpu/sh4/setup-sh7760.c index 254c5c5..d9bdc93 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh7760.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh7760.c @@ -11,6 +11,7 @@ #include #include #include +#include enum { UNUSED = 0, @@ -178,10 +179,14 @@ static int __init sh7760_devices_setup(void) } __initcall(sh7760_devices_setup); +#define INTC_ICR 0xffd00000UL +#define INTC_ICR_IRLM (1 << 7) + void __init plat_irq_setup_pins(int mode) { switch (mode) { case IRQ_MODE_IRQ: + ctrl_outw(ctrl_inw(INTC_ICR) | INTC_ICR_IRLM, INTC_ICR); register_intc_controller(&intc_desc_irq); break; default: -- cgit v0.10.2 From 3db9170880241d63aae7ab86a03aa15418c3e5c6 Mon Sep 17 00:00:00 2001 From: Luca Santini Date: Mon, 8 Sep 2008 12:01:15 +0900 Subject: sh: Add Renesas EDOSK7760 board support. This adds support for the Renesas (RTE) EDOSK7760 board. Currently supported devices are: - ramdisk support - ethernet support - nfs support - ext2/ext3 support - i2c support - fb support (M) Signed-off-by: Luca Santini Signed-off-by: Paul Mundt diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig index ae19486..c6b21e8 100644 --- a/arch/sh/boards/Kconfig +++ b/arch/sh/boards/Kconfig @@ -184,6 +184,13 @@ config SH_EDOSK7705 bool "EDOSK7705" depends on CPU_SUBTYPE_SH7705 +config SH_EDOSK7760 + bool "EDOSK7760" + depends on CPU_SUBTYPE_SH7760 + help + Select if configuring for a Renesas EDOSK7760 + evaluation board. + config SH_SH4202_MICRODEV bool "SH4-202 MicroDev" depends on CPU_SUBTYPE_SH4_202 diff --git a/arch/sh/boards/Makefile b/arch/sh/boards/Makefile index 463022c..d9efa39 100644 --- a/arch/sh/boards/Makefile +++ b/arch/sh/boards/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_SH_MAGIC_PANEL_R2) += board-magicpanelr2.o obj-$(CONFIG_SH_RSK7203) += board-rsk7203.o obj-$(CONFIG_SH_SH7785LCR) += board-sh7785lcr.o obj-$(CONFIG_SH_SHMIN) += board-shmin.o +obj-$(CONFIG_SH_EDOSK7760) += board-edosk7760.o diff --git a/arch/sh/boards/board-edosk7760.c b/arch/sh/boards/board-edosk7760.c new file mode 100644 index 0000000..7cc5e11 --- /dev/null +++ b/arch/sh/boards/board-edosk7760.c @@ -0,0 +1,144 @@ +/* + * Renesas Europe EDOSK7760 Board Support + * + * Copyright (C) 2008 SPES Societa' Progettazione Elettronica e Software Ltd. + * Author: Luca Santini + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Bus state controller registers for CS4 area */ +#define BSC_CS4BCR 0xA4FD0010 +#define BSC_CS4WCR 0xA4FD0030 + +#define SMC_IOBASE 0xA2000000 +#define SMC_IO_OFFSET 0x300 +#define SMC_IOADDR (SMC_IOBASE + SMC_IO_OFFSET) + +#define ETHERNET_IRQ 5 + +/* i2c initialization functions */ +static struct sh7760_i2c_platdata i2c_pd = { + .speed_khz = 400, +}; + +static struct resource sh7760_i2c1_res[] = { + { + .start = SH7760_I2C1_MMIO, + .end = SH7760_I2C1_MMIOEND, + .flags = IORESOURCE_MEM, + },{ + .start = SH7760_I2C1_IRQ, + .end = SH7760_I2C1_IRQ, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device sh7760_i2c1_dev = { + .dev = { + .platform_data = &i2c_pd, + }, + + .name = SH7760_I2C_DEVNAME, + .id = 1, + .resource = sh7760_i2c1_res, + .num_resources = ARRAY_SIZE(sh7760_i2c1_res), +}; + +static struct resource sh7760_i2c0_res[] = { + { + .start = SH7760_I2C0_MMIO, + .end = SH7760_I2C0_MMIOEND, + .flags = IORESOURCE_MEM, + }, { + .start = SH7760_I2C0_IRQ, + .end = SH7760_I2C0_IRQ, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device sh7760_i2c0_dev = { + .dev = { + .platform_data = &i2c_pd, + }, + .name = SH7760_I2C_DEVNAME, + .id = 0, + .resource = sh7760_i2c0_res, + .num_resources = ARRAY_SIZE(sh7760_i2c0_res), +}; + +/* eth initialization functions */ +static struct smc91x_platdata smc91x_info = { + .flags = SMC91X_USE_16BIT | SMC91X_IO_SHIFT_1 | IORESOURCE_IRQ_LOWLEVEL, +}; + +static struct resource smc91x_res[] = { + [0] = { + .start = SMC_IOADDR, + .end = SMC_IOADDR + 0x1f, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = ETHERNET_IRQ, + .end = ETHERNET_IRQ, + .flags = IORESOURCE_IRQ , + } +}; + +static struct platform_device smc91x_dev = { + .name = "smc91x", + .id = -1, + .num_resources = ARRAY_SIZE(smc91x_res), + .resource = smc91x_res, + + .dev = { + .platform_data = &smc91x_info, + }, +}; + +/* platform init code */ +static struct platform_device *edosk7760_devices[] __initdata = { + &sh7760_i2c0_dev, + &sh7760_i2c1_dev, + &smc91x_dev, +}; + +static int __init init_edosk7760_devices(void) +{ + plat_irq_setup_pins(IRQ_MODE_IRQ); + + return platform_add_devices(edosk7760_devices, + ARRAY_SIZE(edosk7760_devices)); +} +__initcall(init_edosk7760_devices); + +/* + * The Machine Vector + */ +struct sh_machine_vector mv_edosk7760 __initmv = { + .mv_name = "EDOSK7760", + .mv_nr_irqs = 128, +}; diff --git a/arch/sh/configs/edosk7760_defconfig b/arch/sh/configs/edosk7760_defconfig new file mode 100644 index 0000000..f8ec32a --- /dev/null +++ b/arch/sh/configs/edosk7760_defconfig @@ -0,0 +1,1050 @@ +# +# Automatically generated make config: don't edit +# Linux kernel version: 2.6.26 +# Tue Aug 26 11:36:09 2008 +# +CONFIG_SUPERH=y +CONFIG_SUPERH32=y +CONFIG_RWSEM_GENERIC_SPINLOCK=y +CONFIG_GENERIC_BUG=y +CONFIG_GENERIC_FIND_NEXT_BIT=y +CONFIG_GENERIC_HWEIGHT=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_GENERIC_TIME=y +CONFIG_GENERIC_CLOCKEVENTS=y +CONFIG_STACKTRACE_SUPPORT=y +CONFIG_LOCKDEP_SUPPORT=y +# CONFIG_ARCH_HAS_ILOG2_U32 is not set +# CONFIG_ARCH_HAS_ILOG2_U64 is not set +CONFIG_ARCH_NO_VIRT_TO_BUS=y +CONFIG_ARCH_SUPPORTS_AOUT=y +CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" + +# +# General setup +# +CONFIG_EXPERIMENTAL=y +CONFIG_BROKEN_ON_SMP=y +CONFIG_LOCK_KERNEL=y +CONFIG_INIT_ENV_ARG_LIMIT=32 +CONFIG_LOCALVERSION="_edosk7760" +CONFIG_LOCALVERSION_AUTO=y +CONFIG_SWAP=y +CONFIG_SYSVIPC=y +CONFIG_SYSVIPC_SYSCTL=y +CONFIG_POSIX_MQUEUE=y +CONFIG_BSD_PROCESS_ACCT=y +# CONFIG_BSD_PROCESS_ACCT_V3 is not set +# CONFIG_TASKSTATS is not set +# CONFIG_AUDIT is not set +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=17 +# CONFIG_CGROUPS is not set +# CONFIG_GROUP_SCHED is not set +CONFIG_SYSFS_DEPRECATED=y +CONFIG_SYSFS_DEPRECATED_V2=y +# CONFIG_RELAY is not set +# CONFIG_NAMESPACES is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="" +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_SYSCTL=y +CONFIG_EMBEDDED=y +CONFIG_UID16=y +CONFIG_SYSCTL_SYSCALL=y +CONFIG_SYSCTL_SYSCALL_CHECK=y +CONFIG_KALLSYMS=y +CONFIG_KALLSYMS_ALL=y +# CONFIG_KALLSYMS_EXTRA_PASS is not set +CONFIG_HOTPLUG=y +CONFIG_PRINTK=y +CONFIG_BUG=y +CONFIG_ELF_CORE=y +CONFIG_COMPAT_BRK=y +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_ANON_INODES=y +CONFIG_EPOLL=y +CONFIG_SIGNALFD=y +CONFIG_TIMERFD=y +CONFIG_EVENTFD=y +CONFIG_SHMEM=y +CONFIG_VM_EVENT_COUNTERS=y +CONFIG_SLUB_DEBUG=y +# CONFIG_SLAB is not set +CONFIG_SLUB=y +# CONFIG_SLOB is not set +# CONFIG_PROFILING is not set +# CONFIG_MARKERS is not set +CONFIG_HAVE_OPROFILE=y +# CONFIG_HAVE_KPROBES is not set +# CONFIG_HAVE_KRETPROBES is not set +# CONFIG_HAVE_DMA_ATTRS is not set +CONFIG_PROC_PAGE_MONITOR=y +CONFIG_SLABINFO=y +CONFIG_RT_MUTEXES=y +# CONFIG_TINY_SHMEM is not set +CONFIG_BASE_SMALL=0 +CONFIG_MODULES=y +# CONFIG_MODULE_FORCE_LOAD is not set +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y +# CONFIG_MODVERSIONS is not set +# CONFIG_MODULE_SRCVERSION_ALL is not set +CONFIG_KMOD=y +CONFIG_BLOCK=y +# CONFIG_LBD is not set +# CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_LSF is not set +# CONFIG_BLK_DEV_BSG is not set + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +CONFIG_IOSCHED_AS=y +CONFIG_IOSCHED_DEADLINE=y +CONFIG_IOSCHED_CFQ=y +# CONFIG_DEFAULT_AS is not set +# CONFIG_DEFAULT_DEADLINE is not set +CONFIG_DEFAULT_CFQ=y +# CONFIG_DEFAULT_NOOP is not set +CONFIG_DEFAULT_IOSCHED="cfq" +CONFIG_CLASSIC_RCU=y + +# +# System type +# +CONFIG_CPU_SH4=y +# CONFIG_CPU_SUBTYPE_SH7619 is not set +# CONFIG_CPU_SUBTYPE_SH7203 is not set +# CONFIG_CPU_SUBTYPE_SH7206 is not set +# CONFIG_CPU_SUBTYPE_SH7263 is not set +# CONFIG_CPU_SUBTYPE_MXG is not set +# CONFIG_CPU_SUBTYPE_SH7705 is not set +# CONFIG_CPU_SUBTYPE_SH7706 is not set +# CONFIG_CPU_SUBTYPE_SH7707 is not set +# CONFIG_CPU_SUBTYPE_SH7708 is not set +# CONFIG_CPU_SUBTYPE_SH7709 is not set +# CONFIG_CPU_SUBTYPE_SH7710 is not set +# CONFIG_CPU_SUBTYPE_SH7712 is not set +# CONFIG_CPU_SUBTYPE_SH7720 is not set +# CONFIG_CPU_SUBTYPE_SH7721 is not set +# CONFIG_CPU_SUBTYPE_SH7750 is not set +# CONFIG_CPU_SUBTYPE_SH7091 is not set +# CONFIG_CPU_SUBTYPE_SH7750R is not set +# CONFIG_CPU_SUBTYPE_SH7750S is not set +# CONFIG_CPU_SUBTYPE_SH7751 is not set +# CONFIG_CPU_SUBTYPE_SH7751R is not set +CONFIG_CPU_SUBTYPE_SH7760=y +# CONFIG_CPU_SUBTYPE_SH4_202 is not set +# CONFIG_CPU_SUBTYPE_SH7723 is not set +# CONFIG_CPU_SUBTYPE_SH7763 is not set +# CONFIG_CPU_SUBTYPE_SH7770 is not set +# CONFIG_CPU_SUBTYPE_SH7780 is not set +# CONFIG_CPU_SUBTYPE_SH7785 is not set +# CONFIG_CPU_SUBTYPE_SHX3 is not set +# CONFIG_CPU_SUBTYPE_SH7343 is not set +# CONFIG_CPU_SUBTYPE_SH7722 is not set +# CONFIG_CPU_SUBTYPE_SH7366 is not set +# CONFIG_CPU_SUBTYPE_SH5_101 is not set +# CONFIG_CPU_SUBTYPE_SH5_103 is not set + +# +# Memory management options +# +CONFIG_QUICKLIST=y +CONFIG_MMU=y +CONFIG_PAGE_OFFSET=0x80000000 +CONFIG_MEMORY_START=0x0c000000 +CONFIG_MEMORY_SIZE=0x04000000 +CONFIG_29BIT=y +CONFIG_VSYSCALL=y +CONFIG_ARCH_FLATMEM_ENABLE=y +CONFIG_ARCH_SPARSEMEM_ENABLE=y +CONFIG_ARCH_SPARSEMEM_DEFAULT=y +CONFIG_MAX_ACTIVE_REGIONS=1 +CONFIG_ARCH_POPULATES_NODE_MAP=y +CONFIG_ARCH_SELECT_MEMORY_MODEL=y +CONFIG_PAGE_SIZE_4KB=y +# CONFIG_PAGE_SIZE_8KB is not set +# CONFIG_PAGE_SIZE_64KB is not set +CONFIG_SELECT_MEMORY_MODEL=y +CONFIG_FLATMEM_MANUAL=y +# CONFIG_DISCONTIGMEM_MANUAL is not set +# CONFIG_SPARSEMEM_MANUAL is not set +CONFIG_FLATMEM=y +CONFIG_FLAT_NODE_MEM_MAP=y +CONFIG_SPARSEMEM_STATIC=y +# CONFIG_SPARSEMEM_VMEMMAP_ENABLE is not set +CONFIG_PAGEFLAGS_EXTENDED=y +CONFIG_SPLIT_PTLOCK_CPUS=4 +# CONFIG_RESOURCES_64BIT is not set +CONFIG_ZONE_DMA_FLAG=0 +CONFIG_NR_QUICK=2 + +# +# Cache configuration +# +# CONFIG_SH_DIRECT_MAPPED is not set +CONFIG_CACHE_WRITEBACK=y +# CONFIG_CACHE_WRITETHROUGH is not set +# CONFIG_CACHE_OFF is not set + +# +# Processor features +# +CONFIG_CPU_LITTLE_ENDIAN=y +# CONFIG_CPU_BIG_ENDIAN is not set +CONFIG_SH_FPU=y +CONFIG_SH_STORE_QUEUES=y +CONFIG_CPU_HAS_INTEVT=y +CONFIG_CPU_HAS_SR_RB=y +CONFIG_CPU_HAS_PTEA=y +CONFIG_CPU_HAS_FPU=y + +# +# Board support +# +CONFIG_SH_EDOSK7760=y + +# +# Timer and clock configuration +# +CONFIG_SH_TMU=y +CONFIG_SH_TIMER_IRQ=16 +CONFIG_SH_PCLK_FREQ=33333333 +CONFIG_TICK_ONESHOT=y +# CONFIG_NO_HZ is not set +CONFIG_HIGH_RES_TIMERS=y +CONFIG_GENERIC_CLOCKEVENTS_BUILD=y + +# +# CPU Frequency scaling +# +# CONFIG_CPU_FREQ is not set + +# +# DMA support +# +CONFIG_SH_DMA_API=y +CONFIG_SH_DMA=y +CONFIG_NR_ONCHIP_DMA_CHANNELS=4 +# CONFIG_NR_DMA_CHANNELS_BOOL is not set +# CONFIG_SH_DMABRG is not set + +# +# Companion Chips +# + +# +# Additional SuperH Device Drivers +# +# CONFIG_HEARTBEAT is not set +# CONFIG_PUSH_SWITCH is not set + +# +# Kernel features +# +# CONFIG_HZ_100 is not set +CONFIG_HZ_250=y +# CONFIG_HZ_300 is not set +# CONFIG_HZ_1000 is not set +CONFIG_HZ=250 +# CONFIG_SCHED_HRTICK is not set +# CONFIG_KEXEC is not set +# CONFIG_CRASH_DUMP is not set +# CONFIG_PREEMPT_NONE is not set +# CONFIG_PREEMPT_VOLUNTARY is not set +CONFIG_PREEMPT=y +# CONFIG_PREEMPT_RCU is not set +CONFIG_GUSA=y +# CONFIG_GUSA_RB is not set + +# +# Boot options +# +CONFIG_ZERO_PAGE_OFFSET=0x00001000 +CONFIG_BOOT_LINK_OFFSET=0x02000000 +# CONFIG_UBC_WAKEUP is not set +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="mem=64M console=ttySC2,115200 root=/dev/nfs rw nfsroot=192.168.0.3:/scripts/filesys ip=192.168.0.4" + +# +# Bus options +# +# CONFIG_ARCH_SUPPORTS_MSI is not set +# CONFIG_PCCARD is not set + +# +# Executable file formats +# +CONFIG_BINFMT_ELF=y +# CONFIG_BINFMT_MISC is not set + +# +# Networking +# +CONFIG_NET=y + +# +# Networking options +# +CONFIG_PACKET=y +# CONFIG_PACKET_MMAP is not set +CONFIG_UNIX=y +# CONFIG_NET_KEY is not set +CONFIG_INET=y +# CONFIG_IP_MULTICAST is not set +# CONFIG_IP_ADVANCED_ROUTER is not set +CONFIG_IP_FIB_HASH=y +CONFIG_IP_PNP=y +# CONFIG_IP_PNP_DHCP is not set +CONFIG_IP_PNP_BOOTP=y +# CONFIG_IP_PNP_RARP is not set +# CONFIG_NET_IPIP is not set +# CONFIG_NET_IPGRE is not set +# CONFIG_ARPD is not set +# CONFIG_SYN_COOKIES is not set +# CONFIG_INET_AH is not set +# CONFIG_INET_ESP is not set +# CONFIG_INET_IPCOMP is not set +# CONFIG_INET_XFRM_TUNNEL is not set +# CONFIG_INET_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_LRO is not set +CONFIG_INET_DIAG=y +CONFIG_INET_TCP_DIAG=y +# CONFIG_TCP_CONG_ADVANCED is not set +CONFIG_TCP_CONG_CUBIC=y +CONFIG_DEFAULT_TCP_CONG="cubic" +# CONFIG_TCP_MD5SIG is not set +# CONFIG_IPV6 is not set +# CONFIG_NETWORK_SECMARK is not set +# CONFIG_NETFILTER is not set +# CONFIG_IP_DCCP is not set +# CONFIG_IP_SCTP is not set +# CONFIG_TIPC is not set +# CONFIG_ATM is not set +# CONFIG_BRIDGE is not set +# CONFIG_VLAN_8021Q is not set +# CONFIG_DECNET is not set +# CONFIG_LLC2 is not set +# CONFIG_IPX is not set +# CONFIG_ATALK is not set +# CONFIG_X25 is not set +# CONFIG_LAPB is not set +# CONFIG_ECONET is not set +# CONFIG_WAN_ROUTER is not set +# CONFIG_NET_SCHED is not set + +# +# Network testing +# +# CONFIG_NET_PKTGEN is not set +# CONFIG_HAMRADIO is not set +# CONFIG_CAN is not set +# CONFIG_IRDA is not set +# CONFIG_BT is not set +# CONFIG_AF_RXRPC is not set + +# +# Wireless +# +# CONFIG_CFG80211 is not set +# CONFIG_WIRELESS_EXT is not set +# CONFIG_MAC80211 is not set +# CONFIG_IEEE80211 is not set +# CONFIG_RFKILL is not set +# CONFIG_NET_9P is not set + +# +# Device Drivers +# + +# +# Generic Driver Options +# +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_STANDALONE=y +CONFIG_PREVENT_FIRMWARE_BUILD=y +# CONFIG_FW_LOADER is not set +CONFIG_DEBUG_DRIVER=y +CONFIG_DEBUG_DEVRES=y +# CONFIG_SYS_HYPERVISOR is not set +# CONFIG_CONNECTOR is not set +CONFIG_MTD=y +CONFIG_MTD_DEBUG=y +CONFIG_MTD_DEBUG_VERBOSE=3 +CONFIG_MTD_CONCAT=y +CONFIG_MTD_PARTITIONS=y +# CONFIG_MTD_REDBOOT_PARTS is not set +# CONFIG_MTD_CMDLINE_PARTS is not set +# CONFIG_MTD_AR7_PARTS is not set + +# +# User Modules And Translation Layers +# +CONFIG_MTD_CHAR=y +CONFIG_MTD_BLKDEVS=y +CONFIG_MTD_BLOCK=y +# CONFIG_FTL is not set +# CONFIG_NFTL is not set +# CONFIG_INFTL is not set +# CONFIG_RFD_FTL is not set +# CONFIG_SSFDC is not set +# CONFIG_MTD_OOPS is not set + +# +# RAM/ROM/Flash chip drivers +# +CONFIG_MTD_CFI=y +CONFIG_MTD_JEDECPROBE=y +CONFIG_MTD_GEN_PROBE=y +CONFIG_MTD_CFI_ADV_OPTIONS=y +CONFIG_MTD_CFI_NOSWAP=y +# CONFIG_MTD_CFI_BE_BYTE_SWAP is not set +# CONFIG_MTD_CFI_LE_BYTE_SWAP is not set +CONFIG_MTD_CFI_GEOMETRY=y +# CONFIG_MTD_MAP_BANK_WIDTH_1 is not set +CONFIG_MTD_MAP_BANK_WIDTH_2=y +# CONFIG_MTD_MAP_BANK_WIDTH_4 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set +CONFIG_MTD_CFI_I1=y +# CONFIG_MTD_CFI_I2 is not set +# CONFIG_MTD_CFI_I4 is not set +# CONFIG_MTD_CFI_I8 is not set +# CONFIG_MTD_OTP is not set +CONFIG_MTD_CFI_INTELEXT=y +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_MTD_CFI_STAA=y +CONFIG_MTD_CFI_UTIL=y +CONFIG_MTD_RAM=y +CONFIG_MTD_ROM=y +CONFIG_MTD_ABSENT=y + +# +# Mapping drivers for chip access +# +# CONFIG_MTD_COMPLEX_MAPPINGS is not set +CONFIG_MTD_PHYSMAP=y +CONFIG_MTD_PHYSMAP_START=0xA0000000 +CONFIG_MTD_PHYSMAP_LEN=0x01000000 +CONFIG_MTD_PHYSMAP_BANKWIDTH=2 +# CONFIG_MTD_PLATRAM is not set + +# +# Self-contained MTD device drivers +# +# CONFIG_MTD_SLRAM is not set +# CONFIG_MTD_PHRAM is not set +# CONFIG_MTD_MTDRAM is not set +# CONFIG_MTD_BLOCK2MTD is not set + +# +# Disk-On-Chip Device Drivers +# +# CONFIG_MTD_DOC2000 is not set +# CONFIG_MTD_DOC2001 is not set +# CONFIG_MTD_DOC2001PLUS is not set +# CONFIG_MTD_NAND is not set +# CONFIG_MTD_ONENAND is not set + +# +# UBI - Unsorted block images +# +# CONFIG_MTD_UBI is not set +# CONFIG_PARPORT is not set +CONFIG_BLK_DEV=y +# CONFIG_BLK_DEV_COW_COMMON is not set +# CONFIG_BLK_DEV_LOOP is not set +# CONFIG_BLK_DEV_NBD is not set +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=16 +CONFIG_BLK_DEV_RAM_SIZE=26000 +# CONFIG_BLK_DEV_XIP is not set +# CONFIG_CDROM_PKTCDVD is not set +# CONFIG_ATA_OVER_ETH is not set +# CONFIG_MISC_DEVICES is not set +CONFIG_HAVE_IDE=y +# CONFIG_IDE is not set + +# +# SCSI device support +# +# CONFIG_RAID_ATTRS is not set +# CONFIG_SCSI is not set +# CONFIG_SCSI_DMA is not set +# CONFIG_SCSI_NETLINK is not set +# CONFIG_ATA is not set +# CONFIG_MD is not set +CONFIG_NETDEVICES=y +# CONFIG_NETDEVICES_MULTIQUEUE is not set +# CONFIG_DUMMY is not set +# CONFIG_BONDING is not set +# CONFIG_MACVLAN is not set +# CONFIG_EQUALIZER is not set +# CONFIG_TUN is not set +# CONFIG_VETH is not set +# CONFIG_PHYLIB is not set +CONFIG_NET_ETHERNET=y +CONFIG_MII=y +# CONFIG_AX88796 is not set +# CONFIG_STNIC is not set +# CONFIG_SMC9194 is not set +CONFIG_SMC91X=y +# CONFIG_IBM_NEW_EMAC_ZMII is not set +# CONFIG_IBM_NEW_EMAC_RGMII is not set +# CONFIG_IBM_NEW_EMAC_TAH is not set +# CONFIG_IBM_NEW_EMAC_EMAC4 is not set +# CONFIG_B44 is not set +# CONFIG_NETDEV_1000 is not set +# CONFIG_NETDEV_10000 is not set + +# +# Wireless LAN +# +# CONFIG_WLAN_PRE80211 is not set +# CONFIG_WLAN_80211 is not set +# CONFIG_IWLWIFI_LEDS is not set +# CONFIG_WAN is not set +# CONFIG_PPP is not set +# CONFIG_SLIP is not set +# CONFIG_NETCONSOLE is not set +# CONFIG_NETPOLL is not set +# CONFIG_NET_POLL_CONTROLLER is not set +# CONFIG_ISDN is not set +# CONFIG_PHONE is not set + +# +# Input device support +# +CONFIG_INPUT=y +# CONFIG_INPUT_FF_MEMLESS is not set +# CONFIG_INPUT_POLLDEV is not set + +# +# Userland interfaces +# +# CONFIG_INPUT_MOUSEDEV is not set +# CONFIG_INPUT_JOYDEV is not set +# CONFIG_INPUT_EVDEV is not set +# CONFIG_INPUT_EVBUG is not set + +# +# Input Device Drivers +# +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_INPUT_JOYSTICK is not set +# CONFIG_INPUT_TABLET is not set +# CONFIG_INPUT_TOUCHSCREEN is not set +# CONFIG_INPUT_MISC is not set + +# +# Hardware I/O ports +# +# CONFIG_SERIO is not set +# CONFIG_GAMEPORT is not set + +# +# Character devices +# +CONFIG_VT=y +CONFIG_VT_CONSOLE=y +CONFIG_HW_CONSOLE=y +# CONFIG_VT_HW_CONSOLE_BINDING is not set +CONFIG_DEVKMEM=y +# CONFIG_SERIAL_NONSTANDARD is not set + +# +# Serial drivers +# +# CONFIG_SERIAL_8250 is not set + +# +# Non-8250 serial port support +# +CONFIG_SERIAL_SH_SCI=y +CONFIG_SERIAL_SH_SCI_NR_UARTS=3 +CONFIG_SERIAL_SH_SCI_CONSOLE=y +CONFIG_SERIAL_CORE=y +CONFIG_SERIAL_CORE_CONSOLE=y +CONFIG_UNIX98_PTYS=y +CONFIG_LEGACY_PTYS=y +CONFIG_LEGACY_PTY_COUNT=256 +# CONFIG_IPMI_HANDLER is not set +CONFIG_HW_RANDOM=y +# CONFIG_R3964 is not set +# CONFIG_RAW_DRIVER is not set +# CONFIG_TCG_TPM is not set +CONFIG_I2C=y +CONFIG_I2C_BOARDINFO=y +CONFIG_I2C_CHARDEV=y + +# +# I2C Hardware Bus support +# +# CONFIG_I2C_OCORES is not set +# CONFIG_I2C_PARPORT_LIGHT is not set +# CONFIG_I2C_SIMTEC is not set +# CONFIG_I2C_TAOS_EVM is not set +# CONFIG_I2C_STUB is not set +# CONFIG_I2C_PCA_PLATFORM is not set +CONFIG_I2C_SH7760=y +# CONFIG_I2C_SH_MOBILE is not set + +# +# Miscellaneous I2C Chip support +# +# CONFIG_DS1682 is not set +# CONFIG_SENSORS_EEPROM is not set +# CONFIG_SENSORS_PCF8574 is not set +# CONFIG_PCF8575 is not set +# CONFIG_SENSORS_PCF8591 is not set +# CONFIG_SENSORS_MAX6875 is not set +# CONFIG_SENSORS_TSL2550 is not set +CONFIG_I2C_DEBUG_CORE=y +CONFIG_I2C_DEBUG_ALGO=y +CONFIG_I2C_DEBUG_BUS=y +CONFIG_I2C_DEBUG_CHIP=y +# CONFIG_SPI is not set +# CONFIG_W1 is not set +# CONFIG_POWER_SUPPLY is not set +# CONFIG_HWMON is not set +# CONFIG_THERMAL is not set +# CONFIG_THERMAL_HWMON is not set +# CONFIG_WATCHDOG is not set + +# +# Sonics Silicon Backplane +# +CONFIG_SSB_POSSIBLE=y +# CONFIG_SSB is not set + +# +# Multifunction device drivers +# +# CONFIG_MFD_SM501 is not set +# CONFIG_HTC_PASIC3 is not set + +# +# Multimedia devices +# + +# +# Multimedia core support +# +# CONFIG_VIDEO_DEV is not set +# CONFIG_DVB_CORE is not set +# CONFIG_VIDEO_MEDIA is not set + +# +# Multimedia drivers +# +# CONFIG_DAB is not set + +# +# Graphics support +# +# CONFIG_VGASTATE is not set +# CONFIG_VIDEO_OUTPUT_CONTROL is not set +CONFIG_FB=m +# CONFIG_FIRMWARE_EDID is not set +# CONFIG_FB_DDC is not set +CONFIG_FB_CFB_FILLRECT=m +CONFIG_FB_CFB_COPYAREA=m +CONFIG_FB_CFB_IMAGEBLIT=m +# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set +# CONFIG_FB_SYS_FILLRECT is not set +# CONFIG_FB_SYS_COPYAREA is not set +# CONFIG_FB_SYS_IMAGEBLIT is not set +# CONFIG_FB_FOREIGN_ENDIAN is not set +# CONFIG_FB_SYS_FOPS is not set +# CONFIG_FB_SVGALIB is not set +# CONFIG_FB_MACMODES is not set +# CONFIG_FB_BACKLIGHT is not set +# CONFIG_FB_MODE_HELPERS is not set +CONFIG_FB_TILEBLITTING=y + +# +# Frame buffer hardware drivers +# +# CONFIG_FB_MB86290_640X480_16BPP is not set +# CONFIG_FB_S1D13XXX is not set +# CONFIG_FB_VIRTUAL is not set +# CONFIG_BACKLIGHT_LCD_SUPPORT is not set + +# +# Display device support +# +# CONFIG_DISPLAY_SUPPORT is not set + +# +# Console display driver support +# +CONFIG_DUMMY_CONSOLE=y +# CONFIG_FRAMEBUFFER_CONSOLE is not set +# CONFIG_LOGO is not set + +# +# Sound +# +CONFIG_SOUND=y + +# +# Advanced Linux Sound Architecture +# +CONFIG_SND=y +CONFIG_SND_TIMER=y +CONFIG_SND_PCM=y +# CONFIG_SND_SEQUENCER is not set +# CONFIG_SND_MIXER_OSS is not set +# CONFIG_SND_PCM_OSS is not set +# CONFIG_SND_DYNAMIC_MINORS is not set +# CONFIG_SND_SUPPORT_OLD_API is not set +# CONFIG_SND_VERBOSE_PROCFS is not set +CONFIG_SND_VERBOSE_PRINTK=y +# CONFIG_SND_DEBUG is not set + +# +# Generic devices +# +# CONFIG_SND_DUMMY is not set +# CONFIG_SND_MTPAV is not set +# CONFIG_SND_SERIAL_U16550 is not set +# CONFIG_SND_MPU401 is not set + +# +# SUPERH devices +# + +# +# System on Chip audio support +# +CONFIG_SND_SOC=y + +# +# SoC Audio support for SuperH +# + +# +# ALSA SoC audio for Freescale SOCs +# + +# +# SoC Audio for the Texas Instruments OMAP +# + +# +# Open Sound System +# +# CONFIG_SOUND_PRIME is not set +# CONFIG_HID_SUPPORT is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_MMC is not set +# CONFIG_MEMSTICK is not set +# CONFIG_NEW_LEDS is not set +# CONFIG_ACCESSIBILITY is not set +# CONFIG_RTC_CLASS is not set +# CONFIG_UIO is not set + +# +# File systems +# +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +# CONFIG_EXT2_FS_POSIX_ACL is not set +# CONFIG_EXT2_FS_SECURITY is not set +CONFIG_EXT2_FS_XIP=y +CONFIG_FS_XIP=y +CONFIG_EXT3_FS=y +CONFIG_EXT3_FS_XATTR=y +# CONFIG_EXT3_FS_POSIX_ACL is not set +# CONFIG_EXT3_FS_SECURITY is not set +# CONFIG_EXT4DEV_FS is not set +CONFIG_JBD=y +CONFIG_FS_MBCACHE=y +# CONFIG_REISERFS_FS is not set +# CONFIG_JFS_FS is not set +CONFIG_FS_POSIX_ACL=y +# CONFIG_XFS_FS is not set +# CONFIG_OCFS2_FS is not set +CONFIG_DNOTIFY=y +CONFIG_INOTIFY=y +CONFIG_INOTIFY_USER=y +# CONFIG_QUOTA is not set +# CONFIG_AUTOFS_FS is not set +# CONFIG_AUTOFS4_FS is not set +# CONFIG_FUSE_FS is not set +CONFIG_GENERIC_ACL=y + +# +# CD-ROM/DVD Filesystems +# +# CONFIG_ISO9660_FS is not set +# CONFIG_UDF_FS is not set + +# +# DOS/FAT/NT Filesystems +# +# CONFIG_MSDOS_FS is not set +# CONFIG_VFAT_FS is not set +# CONFIG_NTFS_FS is not set + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +# CONFIG_PROC_KCORE is not set +CONFIG_PROC_SYSCTL=y +CONFIG_SYSFS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +# CONFIG_HUGETLBFS is not set +# CONFIG_HUGETLB_PAGE is not set +# CONFIG_CONFIGFS_FS is not set + +# +# Miscellaneous filesystems +# +# CONFIG_ADFS_FS is not set +# CONFIG_AFFS_FS is not set +# CONFIG_HFS_FS is not set +# CONFIG_HFSPLUS_FS is not set +# CONFIG_BEFS_FS is not set +# CONFIG_BFS_FS is not set +# CONFIG_EFS_FS is not set +# CONFIG_JFFS2_FS is not set +# CONFIG_CRAMFS is not set +# CONFIG_VXFS_FS is not set +# CONFIG_MINIX_FS is not set +# CONFIG_HPFS_FS is not set +# CONFIG_QNX4FS_FS is not set +# CONFIG_ROMFS_FS is not set +# CONFIG_SYSV_FS is not set +# CONFIG_UFS_FS is not set +CONFIG_NETWORK_FILESYSTEMS=y +CONFIG_NFS_FS=y +# CONFIG_NFS_V3 is not set +# CONFIG_NFS_V4 is not set +# CONFIG_NFSD is not set +CONFIG_ROOT_NFS=y +CONFIG_LOCKD=y +CONFIG_NFS_COMMON=y +CONFIG_SUNRPC=y +# CONFIG_SUNRPC_BIND34 is not set +# CONFIG_RPCSEC_GSS_KRB5 is not set +# CONFIG_RPCSEC_GSS_SPKM3 is not set +# CONFIG_SMB_FS is not set +# CONFIG_CIFS is not set +# CONFIG_NCP_FS is not set +# CONFIG_CODA_FS is not set +# CONFIG_AFS_FS is not set + +# +# Partition Types +# +# CONFIG_PARTITION_ADVANCED is not set +CONFIG_MSDOS_PARTITION=y +CONFIG_NLS=y +CONFIG_NLS_DEFAULT="iso8859-1" +CONFIG_NLS_CODEPAGE_437=y +# CONFIG_NLS_CODEPAGE_737 is not set +# CONFIG_NLS_CODEPAGE_775 is not set +# CONFIG_NLS_CODEPAGE_850 is not set +# CONFIG_NLS_CODEPAGE_852 is not set +# CONFIG_NLS_CODEPAGE_855 is not set +# CONFIG_NLS_CODEPAGE_857 is not set +# CONFIG_NLS_CODEPAGE_860 is not set +# CONFIG_NLS_CODEPAGE_861 is not set +# CONFIG_NLS_CODEPAGE_862 is not set +# CONFIG_NLS_CODEPAGE_863 is not set +# CONFIG_NLS_CODEPAGE_864 is not set +# CONFIG_NLS_CODEPAGE_865 is not set +# CONFIG_NLS_CODEPAGE_866 is not set +# CONFIG_NLS_CODEPAGE_869 is not set +# CONFIG_NLS_CODEPAGE_936 is not set +# CONFIG_NLS_CODEPAGE_950 is not set +# CONFIG_NLS_CODEPAGE_932 is not set +# CONFIG_NLS_CODEPAGE_949 is not set +# CONFIG_NLS_CODEPAGE_874 is not set +# CONFIG_NLS_ISO8859_8 is not set +# CONFIG_NLS_CODEPAGE_1250 is not set +# CONFIG_NLS_CODEPAGE_1251 is not set +CONFIG_NLS_ASCII=y +CONFIG_NLS_ISO8859_1=y +# CONFIG_NLS_ISO8859_2 is not set +# CONFIG_NLS_ISO8859_3 is not set +# CONFIG_NLS_ISO8859_4 is not set +# CONFIG_NLS_ISO8859_5 is not set +# CONFIG_NLS_ISO8859_6 is not set +# CONFIG_NLS_ISO8859_7 is not set +# CONFIG_NLS_ISO8859_9 is not set +# CONFIG_NLS_ISO8859_13 is not set +# CONFIG_NLS_ISO8859_14 is not set +CONFIG_NLS_ISO8859_15=y +# CONFIG_NLS_KOI8_R is not set +# CONFIG_NLS_KOI8_U is not set +CONFIG_NLS_UTF8=y +# CONFIG_DLM is not set + +# +# Kernel hacking +# +CONFIG_TRACE_IRQFLAGS_SUPPORT=y +CONFIG_PRINTK_TIME=y +CONFIG_ENABLE_WARN_DEPRECATED=y +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_FRAME_WARN=1024 +CONFIG_MAGIC_SYSRQ=y +CONFIG_UNUSED_SYMBOLS=y +# CONFIG_DEBUG_FS is not set +# CONFIG_HEADERS_CHECK is not set +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_SHIRQ=y +CONFIG_DETECT_SOFTLOCKUP=y +# CONFIG_SCHED_DEBUG is not set +# CONFIG_SCHEDSTATS is not set +CONFIG_TIMER_STATS=y +# CONFIG_DEBUG_OBJECTS is not set +# CONFIG_SLUB_DEBUG_ON is not set +# CONFIG_SLUB_STATS is not set +CONFIG_DEBUG_PREEMPT=y +# CONFIG_DEBUG_RT_MUTEXES is not set +# CONFIG_RT_MUTEX_TESTER is not set +# CONFIG_DEBUG_SPINLOCK is not set +# CONFIG_DEBUG_MUTEXES is not set +# CONFIG_DEBUG_LOCK_ALLOC is not set +# CONFIG_PROVE_LOCKING is not set +# CONFIG_LOCK_STAT is not set +# CONFIG_DEBUG_SPINLOCK_SLEEP is not set +# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set +# CONFIG_DEBUG_KOBJECT is not set +CONFIG_DEBUG_BUGVERBOSE=y +CONFIG_DEBUG_INFO=y +# CONFIG_DEBUG_VM is not set +# CONFIG_DEBUG_WRITECOUNT is not set +# CONFIG_DEBUG_LIST is not set +# CONFIG_DEBUG_SG is not set +# CONFIG_FRAME_POINTER is not set +# CONFIG_BOOT_PRINTK_DELAY is not set +# CONFIG_RCU_TORTURE_TEST is not set +# CONFIG_BACKTRACE_SELF_TEST is not set +# CONFIG_FAULT_INJECTION is not set +# CONFIG_SAMPLES is not set +# CONFIG_SH_STANDARD_BIOS is not set +CONFIG_EARLY_SCIF_CONSOLE=y +CONFIG_EARLY_SCIF_CONSOLE_PORT=0xffe80000 +CONFIG_EARLY_PRINTK=y +# CONFIG_DEBUG_BOOTMEM is not set +CONFIG_DEBUG_STACKOVERFLOW=y +# CONFIG_DEBUG_STACK_USAGE is not set +# CONFIG_4KSTACKS is not set +# CONFIG_IRQSTACKS is not set +# CONFIG_SH_KGDB is not set + +# +# Security options +# +# CONFIG_KEYS is not set +# CONFIG_SECURITY is not set +# CONFIG_SECURITY_FILE_CAPABILITIES is not set +CONFIG_CRYPTO=y + +# +# Crypto core or helper +# +CONFIG_CRYPTO_ALGAPI=y +# CONFIG_CRYPTO_MANAGER is not set +# CONFIG_CRYPTO_GF128MUL is not set +# CONFIG_CRYPTO_NULL is not set +# CONFIG_CRYPTO_CRYPTD is not set +# CONFIG_CRYPTO_AUTHENC is not set +# CONFIG_CRYPTO_TEST is not set + +# +# Authenticated Encryption with Associated Data +# +# CONFIG_CRYPTO_CCM is not set +# CONFIG_CRYPTO_GCM is not set +# CONFIG_CRYPTO_SEQIV is not set + +# +# Block modes +# +# CONFIG_CRYPTO_CBC is not set +# CONFIG_CRYPTO_CTR is not set +# CONFIG_CRYPTO_CTS is not set +# CONFIG_CRYPTO_ECB is not set +# CONFIG_CRYPTO_LRW is not set +# CONFIG_CRYPTO_PCBC is not set +# CONFIG_CRYPTO_XTS is not set + +# +# Hash modes +# +# CONFIG_CRYPTO_HMAC is not set +# CONFIG_CRYPTO_XCBC is not set + +# +# Digest +# +# CONFIG_CRYPTO_CRC32C is not set +# CONFIG_CRYPTO_MD4 is not set +CONFIG_CRYPTO_MD5=y +# CONFIG_CRYPTO_MICHAEL_MIC is not set +# CONFIG_CRYPTO_SHA1 is not set +# CONFIG_CRYPTO_SHA256 is not set +# CONFIG_CRYPTO_SHA512 is not set +# CONFIG_CRYPTO_TGR192 is not set +# CONFIG_CRYPTO_WP512 is not set + +# +# Ciphers +# +# CONFIG_CRYPTO_AES is not set +# CONFIG_CRYPTO_ANUBIS is not set +# CONFIG_CRYPTO_ARC4 is not set +# CONFIG_CRYPTO_BLOWFISH is not set +# CONFIG_CRYPTO_CAMELLIA is not set +# CONFIG_CRYPTO_CAST5 is not set +# CONFIG_CRYPTO_CAST6 is not set +CONFIG_CRYPTO_DES=y +# CONFIG_CRYPTO_FCRYPT is not set +# CONFIG_CRYPTO_KHAZAD is not set +# CONFIG_CRYPTO_SALSA20 is not set +# CONFIG_CRYPTO_SEED is not set +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_TWOFISH is not set + +# +# Compression +# +# CONFIG_CRYPTO_DEFLATE is not set +# CONFIG_CRYPTO_LZO is not set +CONFIG_CRYPTO_HW=y + +# +# Library routines +# +CONFIG_BITREVERSE=y +# CONFIG_GENERIC_FIND_FIRST_BIT is not set +# CONFIG_CRC_CCITT is not set +# CONFIG_CRC16 is not set +# CONFIG_CRC_ITU_T is not set +CONFIG_CRC32=y +# CONFIG_CRC7 is not set +# CONFIG_LIBCRC32C is not set +CONFIG_PLIST=y +CONFIG_HAS_IOMEM=y +CONFIG_HAS_IOPORT=y +CONFIG_HAS_DMA=y -- cgit v0.10.2 From 4ad06dd6f1ec745c5ee0e37ec26b1b817f88507a Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 8 Sep 2008 12:01:55 +0900 Subject: sh: Add EDOSK7760 mach type. Signed-off-by: Paul Mundt diff --git a/arch/sh/tools/mach-types b/arch/sh/tools/mach-types index 0a11cc08..d4fb11f 100644 --- a/arch/sh/tools/mach-types +++ b/arch/sh/tools/mach-types @@ -30,6 +30,7 @@ HP6XX SH_HP6XX DREAMCAST SH_DREAMCAST SNAPGEAR SH_SECUREEDGE5410 EDOSK7705 SH_EDOSK7705 +EDOSK7760 SH_EDOSK7760 SH4202_MICRODEV SH_SH4202_MICRODEV SH03 SH_SH03 LANDISK SH_LANDISK -- cgit v0.10.2 From e7cb016e5a3163e2999d8715390d64eb46816655 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 8 Sep 2008 12:02:17 +0900 Subject: sh: Mark kretprobe_trampoline_holder static and __used. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index c4f4a09..ac60749 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -277,7 +277,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) * here. When a retprobed function returns, this probe is hit and * trampoline_probe_handler() runs, calling the kretprobe's handler. */ -void kretprobe_trampoline_holder(void) +static void __used kretprobe_trampoline_holder(void) { asm volatile ("kretprobe_trampoline: \n" "nop\n"); } -- cgit v0.10.2 From fc63562ac2107dfa843f5288fe985fc6f0021c17 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 8 Sep 2008 12:10:35 +0900 Subject: sh: Disable seccomp support by default. This was initially checked in with a stupid default of y, while most everyone is going to want to have this disabled anyways. Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 334917a..c5b08eb 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -496,7 +496,6 @@ config CRASH_DUMP config SECCOMP bool "Enable seccomp to safely compute untrusted bytecode" depends on PROC_FS - default y help This kernel feature is useful for number crunching applications that may need to compute untrusted bytecode during their -- cgit v0.10.2 From 037c10a612e8b7461e33672fb3848807ac6e2346 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 8 Sep 2008 12:22:47 +0900 Subject: sh: kprobes: Hook up kprobe_fault_handler() in the page fault path. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h index 70fc629..756a5cd 100644 --- a/arch/sh/include/asm/kprobes.h +++ b/arch/sh/include/asm/kprobes.h @@ -6,8 +6,6 @@ #include #include -struct pt_regs; - typedef u16 kprobe_opcode_t; #define BREAKPOINT_INSTRUCTION 0xc3ff @@ -48,6 +46,7 @@ struct kprobe_ctlblk { struct prev_kprobe prev_kprobe; }; +extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); extern int kprobe_handle_illslot(unsigned long pc); diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index ac60749..81a3725 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -393,7 +393,7 @@ static inline int post_kprobe_handler(struct pt_regs *regs) return 1; } -static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) +int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c index e8efda9..659811c 100644 --- a/arch/sh/mm/fault_32.c +++ b/arch/sh/mm/fault_32.c @@ -2,7 +2,7 @@ * Page fault handler for SH with an MMU. * * Copyright (C) 1999 Niibe Yutaka - * Copyright (C) 2003 - 2007 Paul Mundt + * Copyright (C) 2003 - 2008 Paul Mundt * * Based on linux/arch/i386/mm/fault.c: * Copyright (C) 1995 Linus Torvalds @@ -21,6 +21,27 @@ #include #include +#ifdef CONFIG_KPROBES +static inline int notify_page_fault(struct pt_regs *regs, int trap) +{ + int ret = 0; + + if (!user_mode(regs)) { + preempt_disable(); + if (kprobe_running() && kprobe_fault_handler(regs, trap)) + ret = 1; + preempt_enable(); + } + + return ret; +} +#else +static inline int notify_page_fault(struct pt_regs *regs, int trap) +{ + return 0; +} +#endif + /* * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate @@ -37,6 +58,9 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, int fault; siginfo_t info; + if (notify_page_fault(regs, writeaccess)) + return; + #ifdef CONFIG_SH_KGDB if (kgdb_nofault && kgdb_bus_err_hook) kgdb_bus_err_hook(); @@ -269,6 +293,9 @@ asmlinkage int __kprobes __do_page_fault(struct pt_regs *regs, pte_t *pte; pte_t entry; + if (notify_page_fault(regs, writeaccess)) + return 0; + #ifdef CONFIG_SH_KGDB if (kgdb_nofault && kgdb_bus_err_hook) kgdb_bus_err_hook(); -- cgit v0.10.2 From 174b5c9923e0170c844e03d55a9f3fb3b329a8b7 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 8 Sep 2008 18:10:10 +0900 Subject: sh: kprobes: Use trapa #0x3a for breakpoint trap. Not all parts support trapa #0xff, so use something within the debug trap range that's accessible on all parts. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h index 756a5cd..6078d8e 100644 --- a/arch/sh/include/asm/kprobes.h +++ b/arch/sh/include/asm/kprobes.h @@ -7,7 +7,7 @@ #include typedef u16 kprobe_opcode_t; -#define BREAKPOINT_INSTRUCTION 0xc3ff +#define BREAKPOINT_INSTRUCTION 0xc33a #define MAX_INSN_SIZE 16 #define MAX_STACK_SIZE 64 diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index 81a3725..fdd049e 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -525,8 +525,7 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) void __kprobes jprobe_return(void) { - __asm("trapa #-1\n\t" "jprobe_return_end:\n\t" "nop\n\t"); - + asm volatile ("trapa #0x3a\n\t" "jprobe_return_end:\n\t" "nop\n\t"); } int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -- cgit v0.10.2 From ee386de77419f9fedf206d84c4d4b2de0ead5bcb Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 8 Sep 2008 18:12:33 +0900 Subject: sh: kprobes: Default to NOTIFY_DONE for unhandled debug traps. Presently this is doing a force_sig() SIGTRAP, which is already taken care of in the generic code if no one asserts NOTIFY_STOP. Switch the default return to NOTIFY_DONE in the case of unhandled traps, so that the same trap may pass through to other users on the same die chain. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index fdd049e..75accf9 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -474,7 +474,7 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, ret = NOTIFY_STOP; } else { /* Not a kprobe trap */ - force_sig(SIGTRAP, current); + ret = NOTIFY_DONE; } } else { p = get_kprobe(addr); -- cgit v0.10.2 From 247bc6d2ae3e2de08529977952c7d085f9d562d4 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 8 Sep 2008 18:14:50 +0900 Subject: sh: kprobes: Fix up a preemption imbalance on jprobe return. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index 75accf9..f0e1c78 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -542,6 +542,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) MIN_STACK_SIZE(stack_addr)); kcb->kprobe_status = KPROBE_HIT_SS; + preempt_enable_no_resched(); return 1; } return 0; -- cgit v0.10.2 From 734db3770de03fbe9ae4e78519a7d1678189788c Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 8 Sep 2008 18:15:55 +0900 Subject: sh: kprobes: Fix up race against probe point removal. Handle a corner case where another CPU or debugger removes the probe point from underneath us. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index f0e1c78..a478ba7 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -252,6 +252,17 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) p = get_kprobe(addr); if (!p) { /* Not one of ours: let kernel handle it */ + if (*(kprobe_opcode_t *)addr != BREAKPOINT_INSTRUCTION) { + /* + * The breakpoint instruction was removed right + * after we hit it. Another cpu has removed + * either a probepoint or a debugger breakpoint + * at this address. In either case, no further + * handling of this interrupt is appropriate. + */ + ret = 1; + } + goto no_kprobe; } -- cgit v0.10.2 From 4eb5845d6cbdb9bf03f563c22f3a54115121858f Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 8 Sep 2008 18:22:47 +0900 Subject: sh: kprobes: __kprobes annotations and formatting cleanups. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index a478ba7..e357e36 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -115,20 +115,20 @@ void __kprobes arch_remove_kprobe(struct kprobe *p) } } -static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb) +static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) { kcb->prev_kprobe.kp = kprobe_running(); kcb->prev_kprobe.status = kcb->kprobe_status; } -static inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb) +static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) { __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; kcb->kprobe_status = kcb->prev_kprobe.status; } -static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) +static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) { __get_cpu_var(current_kprobe) = p; } @@ -138,7 +138,7 @@ static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs, * on the next instruction, following branches. Two probes are set if the * branch is conditional. */ -static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) +static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs) { kprobe_opcode_t *addr = NULL; saved_current_opcode.addr = (kprobe_opcode_t *) (regs->pc); @@ -273,12 +273,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) /* handler has already set things up, so skip ss setup */ return 1; - ss_probe: +ss_probe: prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; return 1; - no_kprobe: +no_kprobe: preempt_enable_no_resched(); return ret; } @@ -358,7 +358,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) return orig_ret_address; } -static inline int post_kprobe_handler(struct pt_regs *regs) +static int __kprobes post_kprobe_handler(struct pt_regs *regs) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); @@ -391,14 +391,15 @@ static inline int post_kprobe_handler(struct pt_regs *regs) } } - /*Restore back the original saved kprobes variables and continue. */ + /* Restore back the original saved kprobes variables and continue. */ if (kcb->kprobe_status == KPROBE_REENTER) { restore_previous_kprobe(kcb); goto out; } + reset_current_kprobe(); - out: +out: preempt_enable_no_resched(); return 1; @@ -463,6 +464,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) default: break; } + return 0; } @@ -498,8 +500,8 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, ret = NOTIFY_STOP; } else { p = __get_cpu_var(current_kprobe); - if (p->break_handler - && p->break_handler(p, args->regs)) + if (p->break_handler && + p->break_handler(p, args->regs)) ret = NOTIFY_STOP; } } @@ -542,25 +544,26 @@ void __kprobes jprobe_return(void) int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - u8 *addr = (u8 *) regs->pc; unsigned long stack_addr = kcb->jprobe_saved_r15; + u8 *addr = (u8 *)regs->pc; - if ((addr >= (u8 *) jprobe_return) - && (addr <= (u8 *) jprobe_return_end)) { + if ((addr >= (u8 *)jprobe_return) && + (addr <= (u8 *)jprobe_return_end)) { *regs = kcb->jprobe_saved_regs; - memcpy((kprobe_opcode_t *) stack_addr, kcb->jprobes_stack, + memcpy((kprobe_opcode_t *)stack_addr, kcb->jprobes_stack, MIN_STACK_SIZE(stack_addr)); kcb->kprobe_status = KPROBE_HIT_SS; preempt_enable_no_resched(); return 1; } + return 0; } static struct kprobe trampoline_p = { - .addr = (kprobe_opcode_t *) &kretprobe_trampoline, + .addr = (kprobe_opcode_t *)&kretprobe_trampoline, .pre_handler = trampoline_probe_handler }; -- cgit v0.10.2 From cf204fa797cf968de8043491cd469ad0321d0940 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 8 Sep 2008 20:47:42 +0900 Subject: sh: Derive calibrate_delay lpj from clk fwk. All CPUs must have a sensible cpu_clk definition these days, which we can safely use for deriving the preset loops_per_jiffy. The only odd one out is SH-5, which hasn't been hammered in to the framework yet. Based on the ST patch. Signed-off-by: Francesco Virlinzi Signed-off-by: Carl Shaw Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index c5b08eb..bbdcd64 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -25,6 +25,7 @@ config SUPERH32 config SUPERH64 def_bool y if CPU_SH5 + select GENERIC_CALIBRATE_DELAY config ARCH_DEFCONFIG string @@ -57,7 +58,7 @@ config GENERIC_IRQ_PROBE def_bool y config GENERIC_CALIBRATE_DELAY - def_bool y + bool config GENERIC_IOMAP bool diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index fc098c8..267b344 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -27,6 +27,8 @@ #include #include #include +#include +#include #include #include #include @@ -180,6 +182,24 @@ static inline void __init reserve_crashkernel(void) {} #endif +#ifndef CONFIG_GENERIC_CALIBRATE_DELAY +void __cpuinit calibrate_delay(void) +{ + struct clk *clk = clk_get(NULL, "cpu_clk"); + + if (IS_ERR(clk)) + panic("Need a sane CPU clock definition!"); + + loops_per_jiffy = (clk_get_rate(clk) >> 1) / HZ; + + printk(KERN_INFO "Calibrating delay loop (skipped)... " + "%lu.%02lu BogoMIPS PRESET (lpj=%lu)\n", + loops_per_jiffy/(500000/HZ), + (loops_per_jiffy/(5000/HZ)) % 100, + loops_per_jiffy); +} +#endif + void __init __add_active_range(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn) { -- cgit v0.10.2 From 61098a086671e2d386104e562fb7cd97cc197d1b Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Tue, 9 Sep 2008 06:15:47 +0900 Subject: sh: Add R2D+ defconfig for qemu system emulator. This adds a defconfig for the R2D+ target in the qemu system emulator. Eventually it will be possible to simply use the r2d+ defconfig as it is. Provided by Shin-ichiro KAWASAKI. Signed-off-by: Paul Mundt diff --git a/arch/sh/configs/rts7751r2dplus_qemu_defconfig b/arch/sh/configs/rts7751r2dplus_qemu_defconfig new file mode 100644 index 0000000..a72796c --- /dev/null +++ b/arch/sh/configs/rts7751r2dplus_qemu_defconfig @@ -0,0 +1,909 @@ +# +# Automatically generated make config: don't edit +# Linux kernel version: 2.6.27-rc2 +# Mon Aug 18 22:17:44 2008 +# +CONFIG_SUPERH=y +CONFIG_SUPERH32=y +CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig" +CONFIG_RWSEM_GENERIC_SPINLOCK=y +CONFIG_GENERIC_BUG=y +CONFIG_GENERIC_FIND_NEXT_BIT=y +CONFIG_GENERIC_HWEIGHT=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y +CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_GENERIC_TIME=y +CONFIG_GENERIC_CLOCKEVENTS=y +CONFIG_SYS_SUPPORTS_PCI=y +CONFIG_STACKTRACE_SUPPORT=y +CONFIG_LOCKDEP_SUPPORT=y +# CONFIG_ARCH_HAS_ILOG2_U32 is not set +# CONFIG_ARCH_HAS_ILOG2_U64 is not set +CONFIG_ARCH_NO_VIRT_TO_BUS=y +CONFIG_IO_TRAPPED=y +CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" + +# +# General setup +# +CONFIG_EXPERIMENTAL=y +CONFIG_BROKEN_ON_SMP=y +CONFIG_INIT_ENV_ARG_LIMIT=32 +CONFIG_LOCALVERSION="" +CONFIG_LOCALVERSION_AUTO=y +CONFIG_SWAP=y +CONFIG_SYSVIPC=y +CONFIG_SYSVIPC_SYSCTL=y +# CONFIG_BSD_PROCESS_ACCT is not set +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=14 +# CONFIG_CGROUPS is not set +CONFIG_GROUP_SCHED=y +CONFIG_FAIR_GROUP_SCHED=y +# CONFIG_RT_GROUP_SCHED is not set +CONFIG_USER_SCHED=y +# CONFIG_CGROUP_SCHED is not set +CONFIG_SYSFS_DEPRECATED=y +CONFIG_SYSFS_DEPRECATED_V2=y +# CONFIG_RELAY is not set +# CONFIG_NAMESPACES is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="" +# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set +CONFIG_SYSCTL=y +CONFIG_EMBEDDED=y +CONFIG_UID16=y +# CONFIG_SYSCTL_SYSCALL is not set +CONFIG_KALLSYMS=y +# CONFIG_KALLSYMS_ALL is not set +# CONFIG_KALLSYMS_EXTRA_PASS is not set +# CONFIG_HOTPLUG is not set +CONFIG_PRINTK=y +CONFIG_BUG=y +CONFIG_ELF_CORE=y +CONFIG_COMPAT_BRK=y +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_ANON_INODES=y +CONFIG_EPOLL=y +CONFIG_SIGNALFD=y +CONFIG_TIMERFD=y +CONFIG_EVENTFD=y +CONFIG_SHMEM=y +CONFIG_VM_EVENT_COUNTERS=y +CONFIG_SLAB=y +# CONFIG_SLUB is not set +# CONFIG_SLOB is not set +CONFIG_PROFILING=y +# CONFIG_MARKERS is not set +CONFIG_OPROFILE=y +CONFIG_HAVE_OPROFILE=y +# CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is not set +# CONFIG_HAVE_IOREMAP_PROT is not set +# CONFIG_HAVE_KPROBES is not set +# CONFIG_HAVE_KRETPROBES is not set +# CONFIG_HAVE_ARCH_TRACEHOOK is not set +# CONFIG_HAVE_DMA_ATTRS is not set +# CONFIG_USE_GENERIC_SMP_HELPERS is not set +CONFIG_HAVE_CLK=y +CONFIG_PROC_PAGE_MONITOR=y +CONFIG_HAVE_GENERIC_DMA_COHERENT=y +CONFIG_SLABINFO=y +CONFIG_RT_MUTEXES=y +# CONFIG_TINY_SHMEM is not set +CONFIG_BASE_SMALL=0 +CONFIG_MODULES=y +# CONFIG_MODULE_FORCE_LOAD is not set +# CONFIG_MODULE_UNLOAD is not set +# CONFIG_MODVERSIONS is not set +# CONFIG_MODULE_SRCVERSION_ALL is not set +CONFIG_KMOD=y +CONFIG_BLOCK=y +# CONFIG_LBD is not set +# CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_LSF is not set +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_BLK_DEV_INTEGRITY is not set + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +CONFIG_IOSCHED_AS=y +CONFIG_IOSCHED_DEADLINE=y +CONFIG_IOSCHED_CFQ=y +CONFIG_DEFAULT_AS=y +# CONFIG_DEFAULT_DEADLINE is not set +# CONFIG_DEFAULT_CFQ is not set +# CONFIG_DEFAULT_NOOP is not set +CONFIG_DEFAULT_IOSCHED="anticipatory" +CONFIG_CLASSIC_RCU=y + +# +# System type +# +CONFIG_CPU_SH4=y +# CONFIG_CPU_SUBTYPE_SH7619 is not set +# CONFIG_CPU_SUBTYPE_SH7203 is not set +# CONFIG_CPU_SUBTYPE_SH7206 is not set +# CONFIG_CPU_SUBTYPE_SH7263 is not set +# CONFIG_CPU_SUBTYPE_MXG is not set +# CONFIG_CPU_SUBTYPE_SH7705 is not set +# CONFIG_CPU_SUBTYPE_SH7706 is not set +# CONFIG_CPU_SUBTYPE_SH7707 is not set +# CONFIG_CPU_SUBTYPE_SH7708 is not set +# CONFIG_CPU_SUBTYPE_SH7709 is not set +# CONFIG_CPU_SUBTYPE_SH7710 is not set +# CONFIG_CPU_SUBTYPE_SH7712 is not set +# CONFIG_CPU_SUBTYPE_SH7720 is not set +# CONFIG_CPU_SUBTYPE_SH7721 is not set +# CONFIG_CPU_SUBTYPE_SH7750 is not set +# CONFIG_CPU_SUBTYPE_SH7091 is not set +# CONFIG_CPU_SUBTYPE_SH7750R is not set +# CONFIG_CPU_SUBTYPE_SH7750S is not set +# CONFIG_CPU_SUBTYPE_SH7751 is not set +CONFIG_CPU_SUBTYPE_SH7751R=y +# CONFIG_CPU_SUBTYPE_SH7760 is not set +# CONFIG_CPU_SUBTYPE_SH4_202 is not set +# CONFIG_CPU_SUBTYPE_SH7723 is not set +# CONFIG_CPU_SUBTYPE_SH7763 is not set +# CONFIG_CPU_SUBTYPE_SH7770 is not set +# CONFIG_CPU_SUBTYPE_SH7780 is not set +# CONFIG_CPU_SUBTYPE_SH7785 is not set +# CONFIG_CPU_SUBTYPE_SHX3 is not set +# CONFIG_CPU_SUBTYPE_SH7343 is not set +# CONFIG_CPU_SUBTYPE_SH7722 is not set +# CONFIG_CPU_SUBTYPE_SH7366 is not set +# CONFIG_CPU_SUBTYPE_SH5_101 is not set +# CONFIG_CPU_SUBTYPE_SH5_103 is not set + +# +# Memory management options +# +CONFIG_QUICKLIST=y +CONFIG_MMU=y +CONFIG_PAGE_OFFSET=0x80000000 +CONFIG_MEMORY_START=0x0c000000 +CONFIG_MEMORY_SIZE=0x04000000 +CONFIG_29BIT=y +CONFIG_VSYSCALL=y +CONFIG_ARCH_FLATMEM_ENABLE=y +CONFIG_ARCH_SPARSEMEM_ENABLE=y +CONFIG_ARCH_SPARSEMEM_DEFAULT=y +CONFIG_MAX_ACTIVE_REGIONS=1 +CONFIG_ARCH_POPULATES_NODE_MAP=y +CONFIG_ARCH_SELECT_MEMORY_MODEL=y +CONFIG_PAGE_SIZE_4KB=y +# CONFIG_PAGE_SIZE_8KB is not set +# CONFIG_PAGE_SIZE_16KB is not set +# CONFIG_PAGE_SIZE_64KB is not set +CONFIG_ENTRY_OFFSET=0x00001000 +CONFIG_SELECT_MEMORY_MODEL=y +CONFIG_FLATMEM_MANUAL=y +# CONFIG_DISCONTIGMEM_MANUAL is not set +# CONFIG_SPARSEMEM_MANUAL is not set +CONFIG_FLATMEM=y +CONFIG_FLAT_NODE_MEM_MAP=y +CONFIG_SPARSEMEM_STATIC=y +# CONFIG_SPARSEMEM_VMEMMAP_ENABLE is not set +CONFIG_PAGEFLAGS_EXTENDED=y +CONFIG_SPLIT_PTLOCK_CPUS=4 +# CONFIG_RESOURCES_64BIT is not set +CONFIG_ZONE_DMA_FLAG=0 +CONFIG_NR_QUICK=2 + +# +# Cache configuration +# +# CONFIG_SH_DIRECT_MAPPED is not set +CONFIG_CACHE_WRITEBACK=y +# CONFIG_CACHE_WRITETHROUGH is not set +# CONFIG_CACHE_OFF is not set + +# +# Processor features +# +CONFIG_CPU_LITTLE_ENDIAN=y +# CONFIG_CPU_BIG_ENDIAN is not set +CONFIG_SH_FPU=y +# CONFIG_SH_STORE_QUEUES is not set +CONFIG_CPU_HAS_INTEVT=y +CONFIG_CPU_HAS_SR_RB=y +CONFIG_CPU_HAS_PTEA=y +CONFIG_CPU_HAS_FPU=y + +# +# Board support +# +# CONFIG_SH_7751_SYSTEMH is not set +# CONFIG_SH_SECUREEDGE5410 is not set +CONFIG_SH_RTS7751R2D=y +# CONFIG_SH_LANDISK is not set +# CONFIG_SH_TITAN is not set +# CONFIG_SH_LBOX_RE2 is not set + +# +# RTS7751R2D Board Revision +# +CONFIG_RTS7751R2D_PLUS=y +# CONFIG_RTS7751R2D_1 is not set + +# +# Timer and clock configuration +# +CONFIG_SH_TMU=y +CONFIG_SH_TIMER_IRQ=16 +CONFIG_SH_PCLK_FREQ=60000000 +# CONFIG_TICK_ONESHOT is not set +# CONFIG_NO_HZ is not set +# CONFIG_HIGH_RES_TIMERS is not set +CONFIG_GENERIC_CLOCKEVENTS_BUILD=y + +# +# CPU Frequency scaling +# +# CONFIG_CPU_FREQ is not set + +# +# DMA support +# +# CONFIG_SH_DMA is not set + +# +# Companion Chips +# + +# +# Additional SuperH Device Drivers +# +CONFIG_HEARTBEAT=y +# CONFIG_PUSH_SWITCH is not set + +# +# Kernel features +# +# CONFIG_HZ_100 is not set +CONFIG_HZ_250=y +# CONFIG_HZ_300 is not set +# CONFIG_HZ_1000 is not set +CONFIG_HZ=250 +# CONFIG_SCHED_HRTICK is not set +# CONFIG_KEXEC is not set +# CONFIG_CRASH_DUMP is not set +CONFIG_SECCOMP=y +CONFIG_PREEMPT_NONE=y +# CONFIG_PREEMPT_VOLUNTARY is not set +# CONFIG_PREEMPT is not set +CONFIG_GUSA=y +# CONFIG_GUSA_RB is not set + +# +# Boot options +# +CONFIG_ZERO_PAGE_OFFSET=0x00010000 +CONFIG_BOOT_LINK_OFFSET=0x00800000 +# CONFIG_UBC_WAKEUP is not set +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=tty0 console=ttySC0,115200 root=/dev/sda1 earlyprintk=serial" + +# +# Bus options +# +# CONFIG_PCI is not set +# CONFIG_ARCH_SUPPORTS_MSI is not set + +# +# Executable file formats +# +CONFIG_BINFMT_ELF=y +# CONFIG_BINFMT_MISC is not set +# CONFIG_NET is not set + +# +# Device Drivers +# + +# +# Generic Driver Options +# +CONFIG_STANDALONE=y +CONFIG_PREVENT_FIRMWARE_BUILD=y +# CONFIG_DEBUG_DRIVER is not set +# CONFIG_DEBUG_DEVRES is not set +# CONFIG_SYS_HYPERVISOR is not set +# CONFIG_MTD is not set +# CONFIG_PARPORT is not set +CONFIG_BLK_DEV=y +# CONFIG_BLK_DEV_COW_COMMON is not set +# CONFIG_BLK_DEV_LOOP is not set +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=16 +CONFIG_BLK_DEV_RAM_SIZE=4096 +# CONFIG_BLK_DEV_XIP is not set +# CONFIG_CDROM_PKTCDVD is not set +# CONFIG_BLK_DEV_HD is not set +CONFIG_MISC_DEVICES=y +# CONFIG_EEPROM_93CX6 is not set +# CONFIG_ENCLOSURE_SERVICES is not set +CONFIG_HAVE_IDE=y +# CONFIG_IDE is not set + +# +# SCSI device support +# +# CONFIG_RAID_ATTRS is not set +CONFIG_SCSI=y +CONFIG_SCSI_DMA=y +# CONFIG_SCSI_TGT is not set +# CONFIG_SCSI_NETLINK is not set +CONFIG_SCSI_PROC_FS=y + +# +# SCSI support type (disk, tape, CD-ROM) +# +CONFIG_BLK_DEV_SD=y +# CONFIG_CHR_DEV_ST is not set +# CONFIG_CHR_DEV_OSST is not set +# CONFIG_BLK_DEV_SR is not set +# CONFIG_CHR_DEV_SG is not set +# CONFIG_CHR_DEV_SCH is not set + +# +# Some SCSI devices (e.g. CD jukebox) support multiple LUNs +# +# CONFIG_SCSI_MULTI_LUN is not set +# CONFIG_SCSI_CONSTANTS is not set +# CONFIG_SCSI_LOGGING is not set +# CONFIG_SCSI_SCAN_ASYNC is not set +CONFIG_SCSI_WAIT_SCAN=m + +# +# SCSI Transports +# +# CONFIG_SCSI_SPI_ATTRS is not set +# CONFIG_SCSI_FC_ATTRS is not set +# CONFIG_SCSI_SAS_LIBSAS is not set +# CONFIG_SCSI_SRP_ATTRS is not set +CONFIG_SCSI_LOWLEVEL=y +# CONFIG_SCSI_DEBUG is not set +# CONFIG_SCSI_DH is not set +CONFIG_ATA=y +# CONFIG_ATA_NONSTANDARD is not set +CONFIG_SATA_PMP=y +CONFIG_ATA_SFF=y +# CONFIG_SATA_MV is not set +# CONFIG_PATA_PLATFORM is not set +# CONFIG_MD is not set +# CONFIG_PHONE is not set + +# +# Input device support +# +CONFIG_INPUT=y +# CONFIG_INPUT_FF_MEMLESS is not set +# CONFIG_INPUT_POLLDEV is not set + +# +# Userland interfaces +# +# CONFIG_INPUT_MOUSEDEV is not set +# CONFIG_INPUT_JOYDEV is not set +# CONFIG_INPUT_EVDEV is not set +# CONFIG_INPUT_EVBUG is not set + +# +# Input Device Drivers +# +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_INPUT_JOYSTICK is not set +# CONFIG_INPUT_TABLET is not set +# CONFIG_INPUT_TOUCHSCREEN is not set +# CONFIG_INPUT_MISC is not set + +# +# Hardware I/O ports +# +# CONFIG_SERIO is not set +# CONFIG_GAMEPORT is not set + +# +# Character devices +# +CONFIG_VT=y +CONFIG_CONSOLE_TRANSLATIONS=y +CONFIG_VT_CONSOLE=y +CONFIG_HW_CONSOLE=y +CONFIG_VT_HW_CONSOLE_BINDING=y +CONFIG_DEVKMEM=y +# CONFIG_SERIAL_NONSTANDARD is not set + +# +# Serial drivers +# +CONFIG_SERIAL_8250=y +# CONFIG_SERIAL_8250_CONSOLE is not set +CONFIG_SERIAL_8250_NR_UARTS=4 +CONFIG_SERIAL_8250_RUNTIME_UARTS=4 +# CONFIG_SERIAL_8250_EXTENDED is not set + +# +# Non-8250 serial port support +# +CONFIG_SERIAL_SH_SCI=y +CONFIG_SERIAL_SH_SCI_NR_UARTS=1 +CONFIG_SERIAL_SH_SCI_CONSOLE=y +CONFIG_SERIAL_CORE=y +CONFIG_SERIAL_CORE_CONSOLE=y +CONFIG_UNIX98_PTYS=y +CONFIG_LEGACY_PTYS=y +CONFIG_LEGACY_PTY_COUNT=256 +# CONFIG_IPMI_HANDLER is not set +CONFIG_HW_RANDOM=y +# CONFIG_R3964 is not set +# CONFIG_RAW_DRIVER is not set +# CONFIG_TCG_TPM is not set +# CONFIG_I2C is not set +CONFIG_SPI=y +# CONFIG_SPI_DEBUG is not set +CONFIG_SPI_MASTER=y + +# +# SPI Master Controller Drivers +# +CONFIG_SPI_BITBANG=y +# CONFIG_SPI_SH_SCI is not set + +# +# SPI Protocol Masters +# +# CONFIG_SPI_AT25 is not set +# CONFIG_SPI_SPIDEV is not set +# CONFIG_SPI_TLE62X0 is not set +# CONFIG_W1 is not set +# CONFIG_POWER_SUPPLY is not set +CONFIG_HWMON=y +# CONFIG_HWMON_VID is not set +# CONFIG_SENSORS_F71805F is not set +# CONFIG_SENSORS_F71882FG is not set +# CONFIG_SENSORS_IT87 is not set +# CONFIG_SENSORS_LM70 is not set +# CONFIG_SENSORS_PC87360 is not set +# CONFIG_SENSORS_PC87427 is not set +# CONFIG_SENSORS_SMSC47M1 is not set +# CONFIG_SENSORS_SMSC47B397 is not set +# CONFIG_SENSORS_VT1211 is not set +# CONFIG_SENSORS_W83627HF is not set +# CONFIG_SENSORS_W83627EHF is not set +# CONFIG_HWMON_DEBUG_CHIP is not set +# CONFIG_THERMAL is not set +# CONFIG_THERMAL_HWMON is not set +# CONFIG_WATCHDOG is not set + +# +# Sonics Silicon Backplane +# +CONFIG_SSB_POSSIBLE=y +# CONFIG_SSB is not set + +# +# Multifunction device drivers +# +# CONFIG_MFD_CORE is not set +CONFIG_MFD_SM501=y +# CONFIG_HTC_PASIC3 is not set + +# +# Multimedia devices +# + +# +# Multimedia core support +# +# CONFIG_VIDEO_DEV is not set +# CONFIG_VIDEO_MEDIA is not set + +# +# Multimedia drivers +# +CONFIG_DAB=y + +# +# Graphics support +# +# CONFIG_VGASTATE is not set +CONFIG_VIDEO_OUTPUT_CONTROL=m +CONFIG_FB=y +# CONFIG_FIRMWARE_EDID is not set +# CONFIG_FB_DDC is not set +CONFIG_FB_CFB_FILLRECT=y +CONFIG_FB_CFB_COPYAREA=y +CONFIG_FB_CFB_IMAGEBLIT=y +# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set +# CONFIG_FB_SYS_FILLRECT is not set +# CONFIG_FB_SYS_COPYAREA is not set +# CONFIG_FB_SYS_IMAGEBLIT is not set +# CONFIG_FB_FOREIGN_ENDIAN is not set +# CONFIG_FB_SYS_FOPS is not set +# CONFIG_FB_SVGALIB is not set +# CONFIG_FB_MACMODES is not set +# CONFIG_FB_BACKLIGHT is not set +# CONFIG_FB_MODE_HELPERS is not set +# CONFIG_FB_TILEBLITTING is not set + +# +# Frame buffer hardware drivers +# +# CONFIG_FB_S1D13XXX is not set +CONFIG_FB_SH_MOBILE_LCDC=m +CONFIG_FB_SM501=y +# CONFIG_FB_VIRTUAL is not set +# CONFIG_BACKLIGHT_LCD_SUPPORT is not set + +# +# Display device support +# +# CONFIG_DISPLAY_SUPPORT is not set + +# +# Console display driver support +# +CONFIG_DUMMY_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE=y +# CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY is not set +# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set +# CONFIG_FONTS is not set +CONFIG_FONT_8x8=y +CONFIG_FONT_8x16=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +# CONFIG_LOGO_LINUX_CLUT224 is not set +# CONFIG_LOGO_SUPERH_MONO is not set +# CONFIG_LOGO_SUPERH_VGA16 is not set +CONFIG_LOGO_SUPERH_CLUT224=y +CONFIG_SOUND=y +CONFIG_SND=m +# CONFIG_SND_SEQUENCER is not set +# CONFIG_SND_MIXER_OSS is not set +# CONFIG_SND_PCM_OSS is not set +# CONFIG_SND_DYNAMIC_MINORS is not set +CONFIG_SND_SUPPORT_OLD_API=y +CONFIG_SND_VERBOSE_PROCFS=y +# CONFIG_SND_VERBOSE_PRINTK is not set +# CONFIG_SND_DEBUG is not set +CONFIG_SND_DRIVERS=y +# CONFIG_SND_DUMMY is not set +# CONFIG_SND_MTPAV is not set +# CONFIG_SND_SERIAL_U16550 is not set +# CONFIG_SND_MPU401 is not set +CONFIG_SND_SPI=y +CONFIG_SND_SUPERH=y +# CONFIG_SND_SOC is not set +CONFIG_SOUND_PRIME=m +CONFIG_HID_SUPPORT=y +CONFIG_HID=y +# CONFIG_HID_DEBUG is not set +# CONFIG_HIDRAW is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_MMC is not set +# CONFIG_MEMSTICK is not set +# CONFIG_NEW_LEDS is not set +# CONFIG_ACCESSIBILITY is not set +CONFIG_RTC_LIB=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_HCTOSYS=y +CONFIG_RTC_HCTOSYS_DEVICE="rtc0" +# CONFIG_RTC_DEBUG is not set + +# +# RTC interfaces +# +CONFIG_RTC_INTF_SYSFS=y +CONFIG_RTC_INTF_PROC=y +CONFIG_RTC_INTF_DEV=y +# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set +# CONFIG_RTC_DRV_TEST is not set + +# +# SPI RTC drivers +# +# CONFIG_RTC_DRV_M41T94 is not set +# CONFIG_RTC_DRV_DS1305 is not set +# CONFIG_RTC_DRV_MAX6902 is not set +CONFIG_RTC_DRV_R9701=y +# CONFIG_RTC_DRV_RS5C348 is not set + +# +# Platform RTC drivers +# +# CONFIG_RTC_DRV_DS1511 is not set +# CONFIG_RTC_DRV_DS1553 is not set +# CONFIG_RTC_DRV_DS1742 is not set +# CONFIG_RTC_DRV_STK17TA8 is not set +# CONFIG_RTC_DRV_M48T86 is not set +# CONFIG_RTC_DRV_M48T59 is not set +# CONFIG_RTC_DRV_V3020 is not set + +# +# on-CPU RTC drivers +# +# CONFIG_RTC_DRV_SH is not set +# CONFIG_DMADEVICES is not set +# CONFIG_UIO is not set + +# +# File systems +# +CONFIG_EXT2_FS=y +# CONFIG_EXT2_FS_XATTR is not set +# CONFIG_EXT2_FS_XIP is not set +# CONFIG_EXT3_FS is not set +# CONFIG_EXT4DEV_FS is not set +# CONFIG_REISERFS_FS is not set +# CONFIG_JFS_FS is not set +# CONFIG_FS_POSIX_ACL is not set +# CONFIG_XFS_FS is not set +CONFIG_DNOTIFY=y +CONFIG_INOTIFY=y +CONFIG_INOTIFY_USER=y +# CONFIG_QUOTA is not set +# CONFIG_AUTOFS_FS is not set +# CONFIG_AUTOFS4_FS is not set +# CONFIG_FUSE_FS is not set + +# +# CD-ROM/DVD Filesystems +# +# CONFIG_ISO9660_FS is not set +# CONFIG_UDF_FS is not set + +# +# DOS/FAT/NT Filesystems +# +CONFIG_FAT_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_FAT_DEFAULT_CODEPAGE=437 +CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" +# CONFIG_NTFS_FS is not set + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +CONFIG_PROC_KCORE=y +CONFIG_PROC_SYSCTL=y +CONFIG_SYSFS=y +CONFIG_TMPFS=y +# CONFIG_TMPFS_POSIX_ACL is not set +# CONFIG_HUGETLBFS is not set +# CONFIG_HUGETLB_PAGE is not set +# CONFIG_CONFIGFS_FS is not set + +# +# Miscellaneous filesystems +# +# CONFIG_ADFS_FS is not set +# CONFIG_AFFS_FS is not set +# CONFIG_HFS_FS is not set +# CONFIG_HFSPLUS_FS is not set +# CONFIG_BEFS_FS is not set +# CONFIG_BFS_FS is not set +# CONFIG_EFS_FS is not set +# CONFIG_CRAMFS is not set +# CONFIG_VXFS_FS is not set +CONFIG_MINIX_FS=y +# CONFIG_OMFS_FS is not set +# CONFIG_HPFS_FS is not set +# CONFIG_QNX4FS_FS is not set +# CONFIG_ROMFS_FS is not set +# CONFIG_SYSV_FS is not set +# CONFIG_UFS_FS is not set + +# +# Partition Types +# +# CONFIG_PARTITION_ADVANCED is not set +CONFIG_MSDOS_PARTITION=y +CONFIG_NLS=y +CONFIG_NLS_DEFAULT="iso8859-1" +# CONFIG_NLS_CODEPAGE_437 is not set +# CONFIG_NLS_CODEPAGE_737 is not set +# CONFIG_NLS_CODEPAGE_775 is not set +# CONFIG_NLS_CODEPAGE_850 is not set +# CONFIG_NLS_CODEPAGE_852 is not set +# CONFIG_NLS_CODEPAGE_855 is not set +# CONFIG_NLS_CODEPAGE_857 is not set +# CONFIG_NLS_CODEPAGE_860 is not set +# CONFIG_NLS_CODEPAGE_861 is not set +# CONFIG_NLS_CODEPAGE_862 is not set +# CONFIG_NLS_CODEPAGE_863 is not set +# CONFIG_NLS_CODEPAGE_864 is not set +# CONFIG_NLS_CODEPAGE_865 is not set +# CONFIG_NLS_CODEPAGE_866 is not set +# CONFIG_NLS_CODEPAGE_869 is not set +# CONFIG_NLS_CODEPAGE_936 is not set +# CONFIG_NLS_CODEPAGE_950 is not set +CONFIG_NLS_CODEPAGE_932=y +# CONFIG_NLS_CODEPAGE_949 is not set +# CONFIG_NLS_CODEPAGE_874 is not set +# CONFIG_NLS_ISO8859_8 is not set +# CONFIG_NLS_CODEPAGE_1250 is not set +# CONFIG_NLS_CODEPAGE_1251 is not set +# CONFIG_NLS_ASCII is not set +# CONFIG_NLS_ISO8859_1 is not set +# CONFIG_NLS_ISO8859_2 is not set +# CONFIG_NLS_ISO8859_3 is not set +# CONFIG_NLS_ISO8859_4 is not set +# CONFIG_NLS_ISO8859_5 is not set +# CONFIG_NLS_ISO8859_6 is not set +# CONFIG_NLS_ISO8859_7 is not set +# CONFIG_NLS_ISO8859_9 is not set +# CONFIG_NLS_ISO8859_13 is not set +# CONFIG_NLS_ISO8859_14 is not set +# CONFIG_NLS_ISO8859_15 is not set +# CONFIG_NLS_KOI8_R is not set +# CONFIG_NLS_KOI8_U is not set +# CONFIG_NLS_UTF8 is not set + +# +# Kernel hacking +# +CONFIG_TRACE_IRQFLAGS_SUPPORT=y +# CONFIG_PRINTK_TIME is not set +CONFIG_ENABLE_WARN_DEPRECATED=y +CONFIG_ENABLE_MUST_CHECK=y +CONFIG_FRAME_WARN=1024 +# CONFIG_MAGIC_SYSRQ is not set +# CONFIG_UNUSED_SYMBOLS is not set +CONFIG_DEBUG_FS=y +# CONFIG_HEADERS_CHECK is not set +CONFIG_DEBUG_KERNEL=y +# CONFIG_DEBUG_SHIRQ is not set +CONFIG_DETECT_SOFTLOCKUP=y +# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0 +CONFIG_SCHED_DEBUG=y +# CONFIG_SCHEDSTATS is not set +# CONFIG_TIMER_STATS is not set +# CONFIG_DEBUG_OBJECTS is not set +# CONFIG_DEBUG_SLAB is not set +# CONFIG_DEBUG_RT_MUTEXES is not set +# CONFIG_RT_MUTEX_TESTER is not set +# CONFIG_DEBUG_SPINLOCK is not set +# CONFIG_DEBUG_MUTEXES is not set +# CONFIG_DEBUG_LOCK_ALLOC is not set +# CONFIG_PROVE_LOCKING is not set +# CONFIG_LOCK_STAT is not set +# CONFIG_DEBUG_SPINLOCK_SLEEP is not set +# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set +# CONFIG_DEBUG_KOBJECT is not set +# CONFIG_DEBUG_BUGVERBOSE is not set +CONFIG_DEBUG_INFO=y +# CONFIG_DEBUG_VM is not set +# CONFIG_DEBUG_WRITECOUNT is not set +# CONFIG_DEBUG_MEMORY_INIT is not set +# CONFIG_DEBUG_LIST is not set +# CONFIG_DEBUG_SG is not set +# CONFIG_FRAME_POINTER is not set +# CONFIG_BOOT_PRINTK_DELAY is not set +# CONFIG_RCU_TORTURE_TEST is not set +# CONFIG_BACKTRACE_SELF_TEST is not set +# CONFIG_FAULT_INJECTION is not set +# CONFIG_SAMPLES is not set +# CONFIG_SH_STANDARD_BIOS is not set +CONFIG_EARLY_SCIF_CONSOLE=y +CONFIG_EARLY_SCIF_CONSOLE_PORT=0xffe80000 +CONFIG_EARLY_PRINTK=y +# CONFIG_DEBUG_BOOTMEM is not set +# CONFIG_DEBUG_STACKOVERFLOW is not set +# CONFIG_DEBUG_STACK_USAGE is not set +# CONFIG_4KSTACKS is not set +# CONFIG_IRQSTACKS is not set +# CONFIG_SH_KGDB is not set + +# +# Security options +# +# CONFIG_KEYS is not set +# CONFIG_SECURITY is not set +# CONFIG_SECURITY_FILE_CAPABILITIES is not set +CONFIG_CRYPTO=y + +# +# Crypto core or helper +# +# CONFIG_CRYPTO_MANAGER is not set +# CONFIG_CRYPTO_GF128MUL is not set +# CONFIG_CRYPTO_NULL is not set +# CONFIG_CRYPTO_CRYPTD is not set +# CONFIG_CRYPTO_AUTHENC is not set +# CONFIG_CRYPTO_TEST is not set + +# +# Authenticated Encryption with Associated Data +# +# CONFIG_CRYPTO_CCM is not set +# CONFIG_CRYPTO_GCM is not set +# CONFIG_CRYPTO_SEQIV is not set + +# +# Block modes +# +# CONFIG_CRYPTO_CBC is not set +# CONFIG_CRYPTO_CTR is not set +# CONFIG_CRYPTO_CTS is not set +# CONFIG_CRYPTO_ECB is not set +# CONFIG_CRYPTO_LRW is not set +# CONFIG_CRYPTO_PCBC is not set +# CONFIG_CRYPTO_XTS is not set + +# +# Hash modes +# +# CONFIG_CRYPTO_HMAC is not set +# CONFIG_CRYPTO_XCBC is not set + +# +# Digest +# +# CONFIG_CRYPTO_CRC32C is not set +# CONFIG_CRYPTO_MD4 is not set +# CONFIG_CRYPTO_MD5 is not set +# CONFIG_CRYPTO_MICHAEL_MIC is not set +# CONFIG_CRYPTO_RMD128 is not set +# CONFIG_CRYPTO_RMD160 is not set +# CONFIG_CRYPTO_RMD256 is not set +# CONFIG_CRYPTO_RMD320 is not set +# CONFIG_CRYPTO_SHA1 is not set +# CONFIG_CRYPTO_SHA256 is not set +# CONFIG_CRYPTO_SHA512 is not set +# CONFIG_CRYPTO_TGR192 is not set +# CONFIG_CRYPTO_WP512 is not set + +# +# Ciphers +# +# CONFIG_CRYPTO_AES is not set +# CONFIG_CRYPTO_ANUBIS is not set +# CONFIG_CRYPTO_ARC4 is not set +# CONFIG_CRYPTO_BLOWFISH is not set +# CONFIG_CRYPTO_CAMELLIA is not set +# CONFIG_CRYPTO_CAST5 is not set +# CONFIG_CRYPTO_CAST6 is not set +# CONFIG_CRYPTO_DES is not set +# CONFIG_CRYPTO_FCRYPT is not set +# CONFIG_CRYPTO_KHAZAD is not set +# CONFIG_CRYPTO_SALSA20 is not set +# CONFIG_CRYPTO_SEED is not set +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_TWOFISH is not set + +# +# Compression +# +# CONFIG_CRYPTO_DEFLATE is not set +# CONFIG_CRYPTO_LZO is not set +CONFIG_CRYPTO_HW=y + +# +# Library routines +# +CONFIG_BITREVERSE=y +# CONFIG_GENERIC_FIND_FIRST_BIT is not set +# CONFIG_CRC_CCITT is not set +# CONFIG_CRC16 is not set +CONFIG_CRC_T10DIF=y +# CONFIG_CRC_ITU_T is not set +CONFIG_CRC32=y +# CONFIG_CRC7 is not set +# CONFIG_LIBCRC32C is not set +CONFIG_PLIST=y +CONFIG_HAS_IOMEM=y +CONFIG_HAS_IOPORT=y +CONFIG_HAS_DMA=y -- cgit v0.10.2 From 6eb2139b3dc3e1c5181a7cdf83a517c57c34bb12 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Tue, 9 Sep 2008 08:13:28 +0900 Subject: sh: kprobes: kretprobe_trampoline needs to be global. Needed by CONFIG_TRACING. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index e357e36..c96850b 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -290,7 +290,9 @@ no_kprobe: */ static void __used kretprobe_trampoline_holder(void) { - asm volatile ("kretprobe_trampoline: \n" "nop\n"); + asm volatile (".globl kretprobe_trampoline\n" + "kretprobe_trampoline:\n\t" + "nop\n"); } /* -- cgit v0.10.2 From b21a91043592434e2847c4b552be7b51851d92c3 Mon Sep 17 00:00:00 2001 From: roel kluin Date: Tue, 9 Sep 2008 23:02:43 +0200 Subject: sh: intc_prio_data() test before subtraction on unsigned bit is unsigned, so test before subtraction Signed-off-by: Roel Kluin Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/cpu/irq/intc.c b/arch/sh/kernel/cpu/irq/intc.c index 8c70e20..94536d3 100644 --- a/arch/sh/kernel/cpu/irq/intc.c +++ b/arch/sh/kernel/cpu/irq/intc.c @@ -464,9 +464,10 @@ static unsigned int __init intc_prio_data(struct intc_desc *desc, } fn += (pr->reg_width >> 3) - 1; - bit = pr->reg_width - ((j + 1) * pr->field_width); - BUG_ON(bit < 0); + BUG_ON((j + 1) * pr->field_width > pr->reg_width); + + bit = pr->reg_width - ((j + 1) * pr->field_width); return _INTC_MK(fn, mode, intc_get_reg(d, reg_e), @@ -531,9 +532,10 @@ static unsigned int __init intc_sense_data(struct intc_desc *desc, fn = REG_FN_MODIFY_BASE; fn += (sr->reg_width >> 3) - 1; - bit = sr->reg_width - ((j + 1) * sr->field_width); - BUG_ON(bit < 0); + BUG_ON((j + 1) * sr->field_width > sr->reg_width); + + bit = sr->reg_width - ((j + 1) * sr->field_width); return _INTC_MK(fn, 0, intc_get_reg(d, sr->reg), 0, sr->field_width, bit); -- cgit v0.10.2 From cc3c080d9f4484021e7b14f99de94a8c85a668d5 Mon Sep 17 00:00:00 2001 From: roel kluin Date: Wed, 10 Sep 2008 19:22:44 +0200 Subject: sh_eth: unsigned ndev->irq cannot be negative unsigned ndev->irq cannot be negative Signed-off-by: Roel Kluin Signed-off-by: Paul Mundt diff --git a/drivers/net/sh_eth.c b/drivers/net/sh_eth.c index 1c370e6..1a04814 100644 --- a/drivers/net/sh_eth.c +++ b/drivers/net/sh_eth.c @@ -1205,11 +1205,12 @@ static int sh_eth_drv_probe(struct platform_device *pdev) devno = 0; ndev->dma = -1; - ndev->irq = platform_get_irq(pdev, 0); - if (ndev->irq < 0) { + ret = platform_get_irq(pdev, 0); + if (ret < 0) { ret = -ENODEV; goto out_release; } + ndev->irq = ret; SET_NETDEV_DEV(ndev, &pdev->dev); -- cgit v0.10.2 From 2641dc92b3c7f979c7e4820cff2e765664358982 Mon Sep 17 00:00:00 2001 From: roel kluin Date: Wed, 10 Sep 2008 19:34:44 +0200 Subject: rtc-sh: Unsigned rtc->{periodic,carry,alarm}_irq cannot be negative possibly since commit b420b1a7a17ea88531d0e12b2f2679a0c8365803 Signed-off-by: Roel Kluin Signed-off-by: Paul Mundt diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c index 1f88e9e..690a780 100644 --- a/drivers/rtc/rtc-sh.c +++ b/drivers/rtc/rtc-sh.c @@ -575,7 +575,7 @@ static int __devinit sh_rtc_probe(struct platform_device *pdev) struct sh_rtc *rtc; struct resource *res; unsigned int tmp; - int ret = -ENOENT; + int ret; rtc = kzalloc(sizeof(struct sh_rtc), GFP_KERNEL); if (unlikely(!rtc)) @@ -584,26 +584,33 @@ static int __devinit sh_rtc_probe(struct platform_device *pdev) spin_lock_init(&rtc->lock); /* get periodic/carry/alarm irqs */ - rtc->periodic_irq = platform_get_irq(pdev, 0); - if (unlikely(rtc->periodic_irq < 0)) { + ret = platform_get_irq(pdev, 0); + if (unlikely(ret < 0)) { + ret = -ENOENT; dev_err(&pdev->dev, "No IRQ for period\n"); goto err_badres; } + rtc->periodic_irq = ret; - rtc->carry_irq = platform_get_irq(pdev, 1); - if (unlikely(rtc->carry_irq < 0)) { + ret = platform_get_irq(pdev, 1); + if (unlikely(ret < 0)) { + ret = -ENOENT; dev_err(&pdev->dev, "No IRQ for carry\n"); goto err_badres; } + rtc->carry_irq = ret; - rtc->alarm_irq = platform_get_irq(pdev, 2); - if (unlikely(rtc->alarm_irq < 0)) { + ret = platform_get_irq(pdev, 2); + if (unlikely(ret < 0)) { + ret = -ENOENT; dev_err(&pdev->dev, "No IRQ for alarm\n"); goto err_badres; } + rtc->alarm_irq = ret; res = platform_get_resource(pdev, IORESOURCE_IO, 0); if (unlikely(res == NULL)) { + ret = -ENOENT; dev_err(&pdev->dev, "No IO resource\n"); goto err_badres; } -- cgit v0.10.2 From 4018ffcfdf84faf17fbadcd29ea5eced26f9d9cb Mon Sep 17 00:00:00 2001 From: Luca Santini Date: Fri, 12 Sep 2008 18:07:16 +0900 Subject: sh: edosk7760 physmap-flash support. Signed-off-by: Luca Santini Signed-off-by: Paul Mundt diff --git a/arch/sh/boards/board-edosk7760.c b/arch/sh/boards/board-edosk7760.c index 7cc5e11..4890ba7 100644 --- a/arch/sh/boards/board-edosk7760.c +++ b/arch/sh/boards/board-edosk7760.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -40,6 +41,52 @@ #define ETHERNET_IRQ 5 +/* NOR flash */ +static struct mtd_partition edosk7760_nor_flash_partitions[] = { + { + .name = "bootloader", + .offset = 0, + .size = (1 * 1024 * 1024), /*1MB*/ + .mask_flags = MTD_WRITEABLE, /* Read-only */ + }, { + .name = "kernel", + .offset = MTDPART_OFS_APPEND, + .size = (2 * 1024 * 1024), /*2MB*/ + }, { + .name = "fs", + .offset = MTDPART_OFS_APPEND, + .size = (26 * 1024 * 1024), + }, { + .name = "other", + .offset = MTDPART_OFS_APPEND, + .size = MTDPART_SIZ_FULL, + }, +}; + +static struct physmap_flash_data edosk7760_nor_flash_data = { + .width = 4, + .parts = edosk7760_nor_flash_partitions, + .nr_parts = ARRAY_SIZE(edosk7760_nor_flash_partitions), +}; + +static struct resource edosk7760_nor_flash_resources[] = { + [0] = { + .name = "NOR Flash", + .start = 0x00000000, + .end = (32 * 1024 * 1024) -1, /* 32MB*/ + .flags = IORESOURCE_MEM, + } +}; + +static struct platform_device edosk7760_nor_flash_device = { + .name = "physmap-flash", + .resource = edosk7760_nor_flash_resources, + .num_resources = ARRAY_SIZE(edosk7760_nor_flash_resources), + .dev = { + .platform_data = &edosk7760_nor_flash_data, + }, +}; + /* i2c initialization functions */ static struct sh7760_i2c_platdata i2c_pd = { .speed_khz = 400, @@ -121,9 +168,10 @@ static struct platform_device smc91x_dev = { /* platform init code */ static struct platform_device *edosk7760_devices[] __initdata = { + &smc91x_dev, + &edosk7760_nor_flash_device, &sh7760_i2c0_dev, &sh7760_i2c1_dev, - &smc91x_dev, }; static int __init init_edosk7760_devices(void) -- cgit v0.10.2 From 1b582d19ce9e14bf5bbc36688bf818b3c42574da Mon Sep 17 00:00:00 2001 From: Luca Santini Date: Fri, 12 Sep 2008 18:08:01 +0900 Subject: sh: update edosk7760 defconfig for physmap-flash. Signed-off-by: Luca Santini Signed-off-by: Paul Mundt diff --git a/arch/sh/configs/edosk7760_defconfig b/arch/sh/configs/edosk7760_defconfig index f8ec32a..bef07fa 100644 --- a/arch/sh/configs/edosk7760_defconfig +++ b/arch/sh/configs/edosk7760_defconfig @@ -380,11 +380,11 @@ CONFIG_DEBUG_DEVRES=y # CONFIG_CONNECTOR is not set CONFIG_MTD=y CONFIG_MTD_DEBUG=y -CONFIG_MTD_DEBUG_VERBOSE=3 +CONFIG_MTD_DEBUG_VERBOSE=0 CONFIG_MTD_CONCAT=y CONFIG_MTD_PARTITIONS=y # CONFIG_MTD_REDBOOT_PARTS is not set -# CONFIG_MTD_CMDLINE_PARTS is not set +CONFIG_MTD_CMDLINE_PARTS=y # CONFIG_MTD_AR7_PARTS is not set # @@ -411,16 +411,16 @@ CONFIG_MTD_CFI_NOSWAP=y # CONFIG_MTD_CFI_BE_BYTE_SWAP is not set # CONFIG_MTD_CFI_LE_BYTE_SWAP is not set CONFIG_MTD_CFI_GEOMETRY=y -# CONFIG_MTD_MAP_BANK_WIDTH_1 is not set +CONFIG_MTD_MAP_BANK_WIDTH_1=y CONFIG_MTD_MAP_BANK_WIDTH_2=y -# CONFIG_MTD_MAP_BANK_WIDTH_4 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set +CONFIG_MTD_MAP_BANK_WIDTH_4=y +CONFIG_MTD_MAP_BANK_WIDTH_8=y +CONFIG_MTD_MAP_BANK_WIDTH_16=y +CONFIG_MTD_MAP_BANK_WIDTH_32=y CONFIG_MTD_CFI_I1=y -# CONFIG_MTD_CFI_I2 is not set -# CONFIG_MTD_CFI_I4 is not set -# CONFIG_MTD_CFI_I8 is not set +CONFIG_MTD_CFI_I2=y +CONFIG_MTD_CFI_I4=y +CONFIG_MTD_CFI_I8=y # CONFIG_MTD_OTP is not set CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y @@ -435,9 +435,9 @@ CONFIG_MTD_ABSENT=y # # CONFIG_MTD_COMPLEX_MAPPINGS is not set CONFIG_MTD_PHYSMAP=y -CONFIG_MTD_PHYSMAP_START=0xA0000000 -CONFIG_MTD_PHYSMAP_LEN=0x01000000 -CONFIG_MTD_PHYSMAP_BANKWIDTH=2 +CONFIG_MTD_PHYSMAP_START=0xffffffff +CONFIG_MTD_PHYSMAP_LEN=0x0 +CONFIG_MTD_PHYSMAP_BANKWIDTH=4 # CONFIG_MTD_PLATRAM is not set # -- cgit v0.10.2 From 09558748464a9afafe2848a3ad4cfd509c9b0fb6 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 12 Sep 2008 18:58:28 +0900 Subject: sh: Provide a fixed UTS_MACHINE definition for sh64. Signed-off-by: Paul Mundt diff --git a/arch/sh/Makefile b/arch/sh/Makefile index 01d85c7..0bc9560 100644 --- a/arch/sh/Makefile +++ b/arch/sh/Makefile @@ -76,8 +76,10 @@ KBUILD_IMAGE := $(defaultimage-y) # error messages during linking. # ifdef CONFIG_SUPERH32 +UTS_MACHINE := sh LDFLAGS_vmlinux += -e _stext else +UTS_MACHINE := sh64 LDFLAGS_vmlinux += --defsym phys_stext=_stext-$(CONFIG_PAGE_OFFSET) \ --defsym phys_stext_shmedia=phys_stext+1 \ -e phys_stext_shmedia -- cgit v0.10.2 From 934135c19d8a1be435bae75aefc09b8ae1698b16 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 12 Sep 2008 19:52:36 +0900 Subject: sh: ptrace: Introduce user_regset interface for gp regs. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h index f01449a..455d9e1 100644 --- a/arch/sh/include/asm/elf.h +++ b/arch/sh/include/asm/elf.h @@ -108,6 +108,15 @@ typedef struct user_fpu_struct elf_fpregset_t; #define elf_check_fdpic(x) ((x)->e_flags & EF_SH_FDPIC) #define elf_check_const_displacement(x) ((x)->e_flags & EF_SH_PIC) +#if defined(CONFIG_SUPERH32) && \ + (!defined(CONFIG_SH_FPU) && !defined(CONFIG_SH_DSP)) +/* + * Enable dump using regset for general purpose registers, use this as + * the default once the FPU and DSP registers are moved over also. + */ +#define CORE_DUMP_USE_REGSET +#endif + #define USE_ELF_CORE_DUMP #define ELF_FDPIC_CORE_EFLAGS EF_SH_FDPIC #define ELF_EXEC_PAGESIZE PAGE_SIZE diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h index b86aeab..bf73646 100644 --- a/arch/sh/include/asm/ptrace.h +++ b/arch/sh/include/asm/ptrace.h @@ -87,12 +87,18 @@ struct pt_dspregs { unsigned long mod; }; +#define PTRACE_GETREGS 12 /* General registers */ +#define PTRACE_SETREGS 13 + +#define PTRACE_GETFPREGS 14 /* FPU registers */ +#define PTRACE_SETFPREGS 15 + #define PTRACE_GETFDPIC 31 /* get the ELF fdpic loadmap address */ #define PTRACE_GETFDPIC_EXEC 0 /* [addr] request the executable loadmap */ #define PTRACE_GETFDPIC_INTERP 1 /* [addr] request the interpreter loadmap */ -#define PTRACE_GETDSPREGS 55 +#define PTRACE_GETDSPREGS 55 /* DSP registers */ #define PTRACE_SETDSPREGS 56 #endif diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c index 84bf342..5e3ba10 100644 --- a/arch/sh/kernel/ptrace_32.c +++ b/arch/sh/kernel/ptrace_32.c @@ -1,12 +1,14 @@ /* - * linux/arch/sh/kernel/ptrace.c + * SuperH process tracing * - * Original x86 implementation: - * By Ross Biro 1/23/92 - * edited by Linus Torvalds + * Copyright (C) 1999, 2000 Kaz Kojima & Niibe Yutaka + * Copyright (C) 2002 - 2008 Paul Mundt * - * SuperH version: Copyright (C) 1999, 2000 Kaz Kojima & Niibe Yutaka - * Audit support: Yuichi Nakamura + * Audit support by Yuichi Nakamura + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. */ #include #include @@ -22,6 +24,8 @@ #include #include #include +#include +#include #include #include #include @@ -30,11 +34,6 @@ #include /* - * does not yet catch signals sent when the child dies. - * in exit.c or in signal.c. - */ - -/* * This routine will get a word off of the process kernel stack. */ static inline int get_stack_long(struct task_struct *task, int offset) @@ -62,16 +61,12 @@ static inline int put_stack_long(struct task_struct *task, int offset, void user_enable_single_step(struct task_struct *child) { - struct pt_regs *regs = task_pt_regs(child); - long pc; - - pc = get_stack_long(child, (long)®s->pc); - /* Next scheduling will set up UBC */ if (child->thread.ubc_pc == 0) ubc_usercnt += 1; - child->thread.ubc_pc = pc; + child->thread.ubc_pc = get_stack_long(child, + offsetof(struct pt_regs, pc)); set_tsk_thread_flag(child, TIF_SINGLESTEP); } @@ -103,6 +98,83 @@ void ptrace_disable(struct task_struct *child) user_disable_single_step(child); } +static int genregs_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + const struct pt_regs *regs = task_pt_regs(target); + int ret; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + regs->regs, + 0, 16 * sizeof(unsigned long)); + if (!ret) + /* PC, PR, SR, GBR, MACH, MACL, TRA */ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + ®s->pc, + offsetof(struct pt_regs, pc), + sizeof(struct pt_regs)); + if (!ret) + ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, + sizeof(struct pt_regs), -1); + + return ret; +} + +static int genregs_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct pt_regs *regs = task_pt_regs(target); + int ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + regs->regs, + 0, 16 * sizeof(unsigned long)); + if (!ret && count > 0) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + ®s->pc, + offsetof(struct pt_regs, pc), + sizeof(struct pt_regs)); + if (!ret) + ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, + sizeof(struct pt_regs), -1); + + return ret; +} + +/* + * These are our native regset flavours. + */ +enum sh_regset { + REGSET_GENERAL, +}; + +static const struct user_regset sh_regsets[] = { + /* + * Format is: + * R0 --> R15 + * PC, PR, SR, GBR, MACH, MACL, TRA + */ + [REGSET_GENERAL] = { + .core_note_type = NT_PRSTATUS, + .n = ELF_NGREG, + .size = sizeof(long), + .align = sizeof(long), + .get = genregs_get, + .set = genregs_set, + }, +}; + +static const struct user_regset_view user_sh_native_view = { + .name = "sh", + .e_machine = EM_SH, + .regsets = sh_regsets, + .n = ARRAY_SIZE(sh_regsets), +}; + long arch_ptrace(struct task_struct *child, long request, long addr, long data) { struct user * dummy = NULL; @@ -159,6 +231,16 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } break; + case PTRACE_GETREGS: + return copy_regset_to_user(child, &user_sh_native_view, + REGSET_GENERAL, + 0, sizeof(struct pt_regs), + (void __user *)data); + case PTRACE_SETREGS: + return copy_regset_from_user(child, &user_sh_native_view, + REGSET_GENERAL, + 0, sizeof(struct pt_regs), + (const void __user *)data); #ifdef CONFIG_SH_DSP case PTRACE_GETDSPREGS: { unsigned long dp; -- cgit v0.10.2 From cb700aa4f13d38726defab3060d3ebeaf67dc189 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 12 Sep 2008 20:41:05 +0900 Subject: sh: ioremap_prot support. Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index bbdcd64..434183e 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -12,6 +12,7 @@ config SUPERH select HAVE_IDE select HAVE_OPROFILE select HAVE_GENERIC_DMA_COHERENT + select HAVE_IOREMAP_PROT help The SuperH is a RISC processor targeted for use in embedded systems and consumer electronics; it was also used in the Sega Dreamcast diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index e49cfee..1857666 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -347,6 +347,8 @@ __ioremap_mode(unsigned long offset, unsigned long size, unsigned long flags) __ioremap_mode((offset), (size), _PAGE_CACHABLE) #define p3_ioremap(offset, size, flags) \ __ioremap((offset), (size), (flags)) +#define ioremap_prot(offset, size, flags) \ + __ioremap_mode((offset), (size), (flags)) #define iounmap(addr) \ __iounmap((addr)) diff --git a/arch/sh/include/asm/page.h b/arch/sh/include/asm/page.h index 77fb8bf..5871d78 100644 --- a/arch/sh/include/asm/page.h +++ b/arch/sh/include/asm/page.h @@ -104,6 +104,8 @@ typedef struct { unsigned long pgd; } pgd_t; typedef struct page *pgtable_t; +#define pte_pgprot(x) __pgprot(pte_val(x) & PTE_FLAGS_MASK) + #endif /* !__ASSEMBLY__ */ /* diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h index a4a8f8b..52220d7 100644 --- a/arch/sh/include/asm/pgtable.h +++ b/arch/sh/include/asm/pgtable.h @@ -76,6 +76,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #endif #define PTE_PHYS_MASK (PHYS_ADDR_MASK & PAGE_MASK) +#define PTE_FLAGS_MASK (~(PTE_PHYS_MASK) << PAGE_SHIFT) #ifdef CONFIG_SUPERH32 #define VMALLOC_START (P3SEG) -- cgit v0.10.2 From f8b890ab4ca60c05b5621b267712709d329f7612 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 12 Sep 2008 22:08:20 +0900 Subject: sh: Flag T-bit for syscall restart. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c index 345de2f..be194d0 100644 --- a/arch/sh/kernel/signal_32.c +++ b/arch/sh/kernel/signal_32.c @@ -490,37 +490,43 @@ give_sigsegv: return -EFAULT; } +static inline void +handle_syscall_restart(unsigned long save_r0, struct pt_regs *regs, + struct sigaction *sa) +{ + /* If we're not from a syscall, bail out */ + if (regs->tra < 0) + return; + + /* check for system call restart.. */ + switch (regs->regs[0]) { + case -ERESTART_RESTARTBLOCK: + case -ERESTARTNOHAND: + no_system_call_restart: + regs->regs[0] = -EINTR; + regs->sr |= 1; + break; + + case -ERESTARTSYS: + if (!(sa->sa_flags & SA_RESTART)) + goto no_system_call_restart; + /* fallthrough */ + case -ERESTARTNOINTR: + regs->regs[0] = save_r0; + regs->pc -= instruction_size(ctrl_inw(regs->pc - 4)); + break; + } +} + /* * OK, we're invoking a handler */ - static int handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs, unsigned int save_r0) { int ret; - /* Are we from a system call? */ - if (regs->tra >= 0) { - /* If so, check system call restarting.. */ - switch (regs->regs[0]) { - case -ERESTART_RESTARTBLOCK: - case -ERESTARTNOHAND: - no_system_call_restart: - regs->regs[0] = -EINTR; - break; - - case -ERESTARTSYS: - if (!(ka->sa.sa_flags & SA_RESTART)) - goto no_system_call_restart; - /* fallthrough */ - case -ERESTARTNOINTR: - regs->regs[0] = save_r0; - regs->pc -= instruction_size( - ctrl_inw(regs->pc - 4)); - break; - } - } /* Set up the stack frame */ if (ka->sa.sa_flags & SA_SIGINFO) @@ -578,6 +584,9 @@ static void do_signal(struct pt_regs *regs, unsigned int save_r0) signr = get_signal_to_deliver(&info, &ka, regs, NULL); if (signr > 0) { + if (regs->sr & 1) + handle_syscall_restart(save_r0, regs, &ka.sa); + /* Whee! Actually deliver the signal. */ if (handle_signal(signr, &ka, &info, oldset, regs, save_r0) == 0) { -- cgit v0.10.2 From 9996b42ac06adb7555933366e071ec8824bcaa37 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 12 Sep 2008 22:11:36 +0900 Subject: sh: provide user_stack_pointer(), needed for tracehook support. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index 41d2321..1cd3a14 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -199,6 +199,8 @@ extern unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc) #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[15]) +#define user_stack_pointer(regs) ((regs)->regs[15]) + #define cpu_sleep() __asm__ __volatile__ ("sleep" : : : "memory") #define cpu_relax() barrier() diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h index 16609bc..ae19839 100644 --- a/arch/sh/include/asm/processor_64.h +++ b/arch/sh/include/asm/processor_64.h @@ -267,6 +267,8 @@ extern unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) ((tsk)->thread.pc) #define KSTK_ESP(tsk) ((tsk)->thread.sp) +#define user_stack_pointer(regs) ((regs)->sp) + #define cpu_relax() barrier() #endif /* __ASSEMBLY__ */ -- cgit v0.10.2 From fb4f87a2f048b4cb1a499c9baa78f1d8437b09c3 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 12 Sep 2008 22:13:13 +0900 Subject: sh: Provide the asm/syscall.h interface, needed by tracehook. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/syscall.h b/arch/sh/include/asm/syscall.h new file mode 100644 index 0000000..6a38142 --- /dev/null +++ b/arch/sh/include/asm/syscall.h @@ -0,0 +1,10 @@ +#ifndef __ASM_SH_SYSCALL_H +#define __ASM_SH_SYSCALL_H + +#ifdef CONFIG_SUPERH32 +# include "syscall_32.h" +#else +# include "syscall_64.h" +#endif + +#endif /* __ASM_SH_SYSCALL_H */ diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h new file mode 100644 index 0000000..54773f2 --- /dev/null +++ b/arch/sh/include/asm/syscall_32.h @@ -0,0 +1,110 @@ +#ifndef __ASM_SH_SYSCALL_32_H +#define __ASM_SH_SYSCALL_32_H + +#include +#include +#include + +/* The system call number is given by the user in %g1 */ +static inline long syscall_get_nr(struct task_struct *task, + struct pt_regs *regs) +{ + return (regs->tra >= 0) ? regs->regs[3] : -1L; +} + +static inline void syscall_rollback(struct task_struct *task, + struct pt_regs *regs) +{ + /* + * XXX: This needs some thought. On SH we don't + * save away the original r0 value anywhere. + */ +} + +static inline bool syscall_has_error(struct pt_regs *regs) +{ + return (regs->sr & 0x1) ? true : false; +} +static inline void syscall_set_error(struct pt_regs *regs) +{ + regs->sr |= 0x1; +} +static inline void syscall_clear_error(struct pt_regs *regs) +{ + regs->sr &= ~0x1; +} + +static inline long syscall_get_error(struct task_struct *task, + struct pt_regs *regs) +{ + return syscall_has_error(regs) ? regs->regs[0] : 0; +} + +static inline long syscall_get_return_value(struct task_struct *task, + struct pt_regs *regs) +{ + return regs->regs[0]; +} + +static inline void syscall_set_return_value(struct task_struct *task, + struct pt_regs *regs, + int error, long val) +{ + if (error) { + syscall_set_error(regs); + regs->regs[0] = -error; + } else { + syscall_clear_error(regs); + regs->regs[0] = val; + } +} + +static inline void syscall_get_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned int i, unsigned int n, + unsigned long *args) +{ + /* + * Do this simply for now. If we need to start supporting + * fetching arguments from arbitrary indices, this will need some + * extra logic. Presently there are no in-tree users that depend + * on this behaviour. + */ + BUG_ON(i); + + /* Argument pattern is: R4, R5, R6, R7, R0, R1 */ + switch (n) { + case 6: args[5] = regs->regs[1]; + case 5: args[4] = regs->regs[0]; + case 4: args[3] = regs->regs[7]; + case 3: args[2] = regs->regs[6]; + case 2: args[1] = regs->regs[5]; + case 1: args[0] = regs->regs[4]; + break; + default: + BUG(); + } +} + +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned int i, unsigned int n, + const unsigned long *args) +{ + /* Same note as above applies */ + BUG_ON(i); + + switch (n) { + case 6: regs->regs[1] = args[5]; + case 5: regs->regs[0] = args[4]; + case 4: regs->regs[7] = args[3]; + case 3: regs->regs[6] = args[2]; + case 2: regs->regs[5] = args[1]; + case 1: regs->regs[4] = args[0]; + break; + default: + BUG(); + } +} + +#endif /* __ASM_SH_SYSCALL_32_H */ diff --git a/arch/sh/include/asm/syscall_64.h b/arch/sh/include/asm/syscall_64.h new file mode 100644 index 0000000..bcaaa8c --- /dev/null +++ b/arch/sh/include/asm/syscall_64.h @@ -0,0 +1,6 @@ +#ifndef __ASM_SH_SYSCALL_64_H +#define __ASM_SH_SYSCALL_64_H + +#include + +#endif /* __ASM_SH_SYSCALL_64_H */ -- cgit v0.10.2 From 3231739d97b348c628a10fb49adfa9143e1de28b Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 12 Sep 2008 22:13:36 +0900 Subject: sh: Enable HAVE_ARCH_TRACEHOOK. Now that the rest of the support requirements are out of the way, finally enable support for tracehook. Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 434183e..f995d13 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -23,6 +23,7 @@ config SUPERH32 def_bool !SUPERH64 select HAVE_KPROBES select HAVE_KRETPROBES + select HAVE_ARCH_TRACEHOOK if (!SH_FPU && !SH_DSP) config SUPERH64 def_bool y if CPU_SH5 -- cgit v0.10.2 From 6bff1592d85c9fa1f1d9d4de1cd0e104279544a6 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 12 Sep 2008 22:41:30 +0900 Subject: sh: Fix up NUMA build error with se7722_defconfig. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/mmzone.h b/arch/sh/include/asm/mmzone.h index 2969253..7f5363b 100644 --- a/arch/sh/include/asm/mmzone.h +++ b/arch/sh/include/asm/mmzone.h @@ -4,6 +4,8 @@ #ifdef __KERNEL__ #ifdef CONFIG_NEED_MULTIPLE_NODES +#include + extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) diff --git a/arch/sh/include/asm/setup.h b/arch/sh/include/asm/setup.h index 554f865..1b7856f 100644 --- a/arch/sh/include/asm/setup.h +++ b/arch/sh/include/asm/setup.h @@ -1,7 +1,7 @@ #ifndef _SH_SETUP_H #define _SH_SETUP_H -#include +#include #define COMMAND_LINE_SIZE 256 -- cgit v0.10.2 From 5dadb34394d59313e2e763ae8e2fc911e9fc557c Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 12 Sep 2008 22:42:10 +0900 Subject: sh: Add DSP registers to regset interface. Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index f995d13..acaba1b 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -23,7 +23,7 @@ config SUPERH32 def_bool !SUPERH64 select HAVE_KPROBES select HAVE_KRETPROBES - select HAVE_ARCH_TRACEHOOK if (!SH_FPU && !SH_DSP) + select HAVE_ARCH_TRACEHOOK if !SH_FPU config SUPERH64 def_bool y if CPU_SH5 diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h index 455d9e1..7c2363f 100644 --- a/arch/sh/include/asm/elf.h +++ b/arch/sh/include/asm/elf.h @@ -108,11 +108,10 @@ typedef struct user_fpu_struct elf_fpregset_t; #define elf_check_fdpic(x) ((x)->e_flags & EF_SH_FDPIC) #define elf_check_const_displacement(x) ((x)->e_flags & EF_SH_PIC) -#if defined(CONFIG_SUPERH32) && \ - (!defined(CONFIG_SH_FPU) && !defined(CONFIG_SH_DSP)) +#if defined(CONFIG_SUPERH32) && !defined(CONFIG_SH_FPU) /* * Enable dump using regset for general purpose registers, use this as - * the default once the FPU and DSP registers are moved over also. + * the default once the FPU registers are moved over also. */ #define CORE_DUMP_USE_REGSET #endif diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h index bf73646..3ad18e9 100644 --- a/arch/sh/include/asm/ptrace.h +++ b/arch/sh/include/asm/ptrace.h @@ -123,6 +123,9 @@ extern void user_disable_single_step(struct task_struct *); #define task_pt_regs(task) \ ((struct pt_regs *) (task_stack_page(task) + THREAD_SIZE \ - sizeof(struct pt_dspregs) - sizeof(unsigned long)) - 1) +#define task_pt_dspregs(task) \ + ((struct pt_dspregs *) (task_stack_page(task) + THREAD_SIZE \ + - sizeof(unsigned long)) - 1) #else #define task_pt_regs(task) \ ((struct pt_regs *) (task_stack_page(task) + THREAD_SIZE \ diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c index 5e3ba10..20b103f 100644 --- a/arch/sh/kernel/ptrace_32.c +++ b/arch/sh/kernel/ptrace_32.c @@ -145,11 +145,50 @@ static int genregs_set(struct task_struct *target, return ret; } +#ifdef CONFIG_SH_DSP +static int dspregs_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + const struct pt_dspregs *regs = task_pt_dspregs(target); + int ret; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, regs, + 0, sizeof(struct pt_dspregs)); + if (!ret) + ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, + sizeof(struct pt_dspregs), -1); + + return ret; +} + +static int dspregs_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct pt_dspregs *regs = task_pt_dspregs(target); + int ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, + 0, sizeof(struct pt_dspregs)); + if (!ret) + ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, + sizeof(struct pt_dspregs), -1); + + return ret; +} +#endif + /* * These are our native regset flavours. */ enum sh_regset { REGSET_GENERAL, +#ifdef CONFIG_SH_DSP + REGSET_DSP, +#endif }; static const struct user_regset sh_regsets[] = { @@ -166,6 +205,16 @@ static const struct user_regset sh_regsets[] = { .get = genregs_get, .set = genregs_set, }, + +#ifdef CONFIG_SH_DSP + [REGSET_DSP] = { + .n = sizeof(struct pt_dspregs) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .get = dspregs_get, + .set = dspregs_set, + }, +#endif }; static const struct user_regset_view user_sh_native_view = { @@ -242,33 +291,16 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) 0, sizeof(struct pt_regs), (const void __user *)data); #ifdef CONFIG_SH_DSP - case PTRACE_GETDSPREGS: { - unsigned long dp; - - ret = -EIO; - dp = ((unsigned long) child) + THREAD_SIZE - - sizeof(struct pt_dspregs); - if (*((int *) (dp - 4)) == SR_FD) { - copy_to_user((void *)addr, (void *) dp, - sizeof(struct pt_dspregs)); - ret = 0; - } - break; - } - - case PTRACE_SETDSPREGS: { - unsigned long dp; - - ret = -EIO; - dp = ((unsigned long) child) + THREAD_SIZE - - sizeof(struct pt_dspregs); - if (*((int *) (dp - 4)) == SR_FD) { - copy_from_user((void *) dp, (void *)addr, - sizeof(struct pt_dspregs)); - ret = 0; - } - break; - } + case PTRACE_GETDSPREGS: + return copy_regset_to_user(child, &user_sh_native_view, + REGSET_DSP, + 0, sizeof(struct pt_dspregs), + (void __user *)data); + case PTRACE_SETDSPREGS: + return copy_regset_from_user(child, &user_sh_native_view, + REGSET_DSP, + 0, sizeof(struct pt_dspregs), + (const void __user *)data); #endif #ifdef CONFIG_BINFMT_ELF_FDPIC case PTRACE_GETFDPIC: { -- cgit v0.10.2 From f9540ececaa2cf94b6760741c82f25097e662383 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 12 Sep 2008 22:42:43 +0900 Subject: sh: Add missing task_user_regset_view() definition. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c index 20b103f..92fe203 100644 --- a/arch/sh/kernel/ptrace_32.c +++ b/arch/sh/kernel/ptrace_32.c @@ -224,6 +224,11 @@ static const struct user_regset_view user_sh_native_view = { .n = ARRAY_SIZE(sh_regsets), }; +const struct user_regset_view *task_user_regset_view(struct task_struct *task) +{ + return &user_sh_native_view; +} + long arch_ptrace(struct task_struct *child, long request, long addr, long data) { struct user * dummy = NULL; -- cgit v0.10.2 From 72461997c3c66c29775afa68ca31bea16bf17f39 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 12 Sep 2008 22:56:35 +0900 Subject: sh: Check SR.DSP bit for DSP regset validity. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c index 92fe203..0f44f2b 100644 --- a/arch/sh/kernel/ptrace_32.c +++ b/arch/sh/kernel/ptrace_32.c @@ -179,6 +179,14 @@ static int dspregs_set(struct task_struct *target, return ret; } + +static int dspregs_active(struct task_struct *target, + const struct user_regset *regset) +{ + struct pt_regs *regs = task_pt_regs(target); + + return regs->sr & SR_DSP ? regset->n : 0; +} #endif /* @@ -213,6 +221,7 @@ static const struct user_regset sh_regsets[] = { .align = sizeof(long), .get = dspregs_get, .set = dspregs_set, + .active = dspregs_active, }, #endif }; -- cgit v0.10.2 From 0e660d2d433393f983cd58fe8c54f831fa7c7713 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 12 Sep 2008 23:27:46 +0900 Subject: sh: Tidy up ELF core dumps. These have been using overrides for ELF_CORE_COPY_TASK_REGS and ELF_CORE_COPY_FPREGS while the generic versions can be used instead. Presently the pt_regs are also duplicated across elf_core_copy_regs() and elf_core_copy_task_regs(), this switches to simply copying out through elf_core_copy_regs() instead. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h index 7c2363f..6b2cec8 100644 --- a/arch/sh/include/asm/elf.h +++ b/arch/sh/include/asm/elf.h @@ -198,12 +198,6 @@ do { \ #endif #define SET_PERSONALITY(ex, ibcs2) set_personality(PER_LINUX_32BIT) -struct task_struct; -extern int dump_task_regs (struct task_struct *, elf_gregset_t *); -extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *); - -#define ELF_CORE_COPY_TASK_REGS(tsk, elf_regs) dump_task_regs(tsk, elf_regs) -#define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs) #ifdef CONFIG_VSYSCALL /* vDSO has arch_setup_additional_pages */ diff --git a/arch/sh/kernel/Makefile_32 b/arch/sh/kernel/Makefile_32 index 12e617b..8497de8 100644 --- a/arch/sh/kernel/Makefile_32 +++ b/arch/sh/kernel/Makefile_32 @@ -21,7 +21,6 @@ obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_PM) += pm.o obj-$(CONFIG_STACKTRACE) += stacktrace.o -obj-$(CONFIG_ELF_CORE) += dump_task.o obj-$(CONFIG_IO_TRAPPED) += io_trapped.o obj-$(CONFIG_KPROBES) += kprobes.o diff --git a/arch/sh/kernel/Makefile_64 b/arch/sh/kernel/Makefile_64 index 6edf53b..e987eb2 100644 --- a/arch/sh/kernel/Makefile_64 +++ b/arch/sh/kernel/Makefile_64 @@ -17,7 +17,6 @@ obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_PM) += pm.o obj-$(CONFIG_STACKTRACE) += stacktrace.o -obj-$(CONFIG_BINFMT_ELF) += dump_task.o obj-$(CONFIG_IO_TRAPPED) += io_trapped.o EXTRA_CFLAGS += -Werror diff --git a/arch/sh/kernel/dump_task.c b/arch/sh/kernel/dump_task.c deleted file mode 100644 index 1db7ce0..0000000 --- a/arch/sh/kernel/dump_task.c +++ /dev/null @@ -1,32 +0,0 @@ -#include -#include -#include - -/* - * Capture the user space registers if the task is not running (in user space) - */ -int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs) -{ - struct pt_regs ptregs; - - ptregs = *task_pt_regs(tsk); - elf_core_copy_regs(regs, &ptregs); - - return 1; -} - -int dump_task_fpu(struct task_struct *tsk, elf_fpregset_t *fpu) -{ - int fpvalid = 0; - -#if defined(CONFIG_SH_FPU) - fpvalid = !!tsk_used_math(tsk); - if (fpvalid) { - unlazy_fpu(tsk, task_pt_regs(tsk)); - memcpy(fpu, &tsk->thread.fpu.hard, sizeof(*fpu)); - } -#endif - - return fpvalid; -} - -- cgit v0.10.2 From 5a89f1adbc5ce44988aab0c370ae2f1478061307 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sat, 13 Sep 2008 01:44:03 +0900 Subject: sh: latencytop support. Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index acaba1b..18a1cc8 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -100,6 +100,10 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y +config HAVE_LATENCYTOP_SUPPORT + def_bool y + depends on !SMP + config ARCH_HAS_ILOG2_U32 def_bool n diff --git a/arch/sh/kernel/stacktrace.c b/arch/sh/kernel/stacktrace.c index 54d1f61..1a2a5eb 100644 --- a/arch/sh/kernel/stacktrace.c +++ b/arch/sh/kernel/stacktrace.c @@ -3,7 +3,7 @@ * * Stack trace management functions * - * Copyright (C) 2006 Paul Mundt + * Copyright (C) 2006 - 2008 Paul Mundt * * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive @@ -36,3 +36,24 @@ void save_stack_trace(struct stack_trace *trace) } } EXPORT_SYMBOL_GPL(save_stack_trace); + +void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + unsigned long *sp = (unsigned long *)tsk->thread.sp; + + while (!kstack_end(sp)) { + unsigned long addr = *sp++; + + if (__kernel_text_address(addr)) { + if (in_sched_functions(addr)) + break; + if (trace->skip > 0) + trace->skip--; + else + trace->entries[trace->nr_entries++] = addr; + if (trace->nr_entries >= trace->max_entries) + break; + } + } +} +EXPORT_SYMBOL_GPL(save_stack_trace_tsk); -- cgit v0.10.2 From fdb0ac80618729e6b12121c66449b8532990eaf3 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 13 Sep 2008 19:57:04 -0700 Subject: async_tx: make async_tx_run_dependencies() easier to read * Rename 'next' to 'dep' * Move the channel switch check inside the loop to simplify termination Acked-by: Ilya Yanok Signed-off-by: Dan Williams diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c index e8362c1..dcbf1be 100644 --- a/crypto/async_tx/async_tx.c +++ b/crypto/async_tx/async_tx.c @@ -115,34 +115,32 @@ EXPORT_SYMBOL_GPL(dma_wait_for_async_tx); * (start) dependent operations on their target channel * @tx: transaction with dependencies */ -void -async_tx_run_dependencies(struct dma_async_tx_descriptor *tx) +void async_tx_run_dependencies(struct dma_async_tx_descriptor *tx) { - struct dma_async_tx_descriptor *next = tx->next; + struct dma_async_tx_descriptor *dep = tx->next; + struct dma_async_tx_descriptor *dep_next; struct dma_chan *chan; - if (!next) + if (!dep) return; - tx->next = NULL; - chan = next->chan; + chan = dep->chan; /* keep submitting up until a channel switch is detected * in that case we will be called again as a result of * processing the interrupt from async_tx_channel_switch */ - while (next && next->chan == chan) { - struct dma_async_tx_descriptor *_next; - - spin_lock_bh(&next->lock); - next->parent = NULL; - _next = next->next; - if (_next && _next->chan == chan) - next->next = NULL; - spin_unlock_bh(&next->lock); - - next->tx_submit(next); - next = _next; + for (; dep; dep = dep_next) { + spin_lock_bh(&dep->lock); + dep->parent = NULL; + dep_next = dep->next; + if (dep_next && dep_next->chan == chan) + dep->next = NULL; /* ->next will be submitted */ + else + dep_next = NULL; /* submit current dep and terminate */ + spin_unlock_bh(&dep->lock); + + dep->tx_submit(dep); } chan->device->device_issue_pending(chan); -- cgit v0.10.2 From 89f72a0633d1d4f28c4c5c8831ec814523d7671a Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 13 Sep 2008 20:05:34 -0700 Subject: drivers/dma/ioat_dma.c: drop code after return The break after the return serves no purpose. Signed-off-by: Julia Lawall Reviewed-by: Richard Genoud Signed-off-by: Andrew Morton Signed-off-by: Dan Williams diff --git a/drivers/dma/ioat_dma.c b/drivers/dma/ioat_dma.c index bc8c6e3..1ef68b3 100644 --- a/drivers/dma/ioat_dma.c +++ b/drivers/dma/ioat_dma.c @@ -971,11 +971,9 @@ static struct ioat_desc_sw *ioat_dma_get_next_descriptor( switch (ioat_chan->device->version) { case IOAT_VER_1_2: return ioat1_dma_get_next_descriptor(ioat_chan); - break; case IOAT_VER_2_0: case IOAT_VER_3_0: return ioat2_dma_get_next_descriptor(ioat_chan); - break; } return NULL; } -- cgit v0.10.2 From f06febc96ba8e0af80bcc3eaec0a109e88275fac Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Fri, 12 Sep 2008 09:54:39 -0700 Subject: timers: fix itimer/many thread hang Overview This patch reworks the handling of POSIX CPU timers, including the ITIMER_PROF, ITIMER_VIRT timers and rlimit handling. It was put together with the help of Roland McGrath, the owner and original writer of this code. The problem we ran into, and the reason for this rework, has to do with using a profiling timer in a process with a large number of threads. It appears that the performance of the old implementation of run_posix_cpu_timers() was at least O(n*3) (where "n" is the number of threads in a process) or worse. Everything is fine with an increasing number of threads until the time taken for that routine to run becomes the same as or greater than the tick time, at which point things degrade rather quickly. This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF." Code Changes This rework corrects the implementation of run_posix_cpu_timers() to make it run in constant time for a particular machine. (Performance may vary between one machine and another depending upon whether the kernel is built as single- or multiprocessor and, in the latter case, depending upon the number of running processors.) To do this, at each tick we now update fields in signal_struct as well as task_struct. The run_posix_cpu_timers() function uses those fields to make its decisions. We define a new structure, "task_cputime," to contain user, system and scheduler times and use these in appropriate places: struct task_cputime { cputime_t utime; cputime_t stime; unsigned long long sum_exec_runtime; }; This is included in the structure "thread_group_cputime," which is a new substructure of signal_struct and which varies for uniprocessor versus multiprocessor kernels. For uniprocessor kernels, it uses "task_cputime" as a simple substructure, while for multiprocessor kernels it is a pointer: struct thread_group_cputime { struct task_cputime totals; }; struct thread_group_cputime { struct task_cputime *totals; }; We also add a new task_cputime substructure directly to signal_struct, to cache the earliest expiration of process-wide timers, and task_cputime also replaces the it_*_expires fields of task_struct (used for earliest expiration of thread timers). The "thread_group_cputime" structure contains process-wide timers that are updated via account_user_time() and friends. In the non-SMP case the structure is a simple aggregator; unfortunately in the SMP case that simplicity was not achievable due to cache-line contention between CPUs (in one measured case performance was actually _worse_ on a 16-cpu system than the same test on a 4-cpu system, due to this contention). For SMP, the thread_group_cputime counters are maintained as a per-cpu structure allocated using alloc_percpu(). The timer functions update only the timer field in the structure corresponding to the running CPU, obtained using per_cpu_ptr(). We define a set of inline functions in sched.h that we use to maintain the thread_group_cputime structure and hide the differences between UP and SMP implementations from the rest of the kernel. The thread_group_cputime_init() function initializes the thread_group_cputime structure for the given task. The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the out-of-line function thread_group_cputime_alloc_smp() to allocate and fill in the per-cpu structures and fields. The thread_group_cputime_free() function, also a no-op for UP, in SMP frees the per-cpu structures. The thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls thread_group_cputime_alloc() if the per-cpu structures haven't yet been allocated. The thread_group_cputime() function fills the task_cputime structure it is passed with the contents of the thread_group_cputime fields; in UP it's that simple but in SMP it must also safely check that tsk->signal is non-NULL (if it is it just uses the appropriate fields of task_struct) and, if so, sums the per-cpu values for each online CPU. Finally, the three functions account_group_user_time(), account_group_system_time() and account_group_exec_runtime() are used by timer functions to update the respective fields of the thread_group_cputime structure. Non-SMP operation is trivial and will not be mentioned further. The per-cpu structure is always allocated when a task creates its first new thread, via a call to thread_group_cputime_clone_thread() from copy_signal(). It is freed at process exit via a call to thread_group_cputime_free() from cleanup_signal(). All functions that formerly summed utime/stime/sum_sched_runtime values from from all threads in the thread group now use thread_group_cputime() to snapshot the values in the thread_group_cputime structure or the values in the task structure itself if the per-cpu structure hasn't been allocated. Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit. The run_posix_cpu_timers() function has been split into a fast path and a slow path; the former safely checks whether there are any expired thread timers and, if not, just returns, while the slow path does the heavy lifting. With the dedicated thread group fields, timers are no longer "rebalanced" and the process_timer_rebalance() function and related code has gone away. All summing loops are gone and all code that used them now uses the thread_group_cputime() inline. When process-wide timers are set, the new task_cputime structure in signal_struct is used to cache the earliest expiration; this is checked in the fast path. Performance The fix appears not to add significant overhead to existing operations. It generally performs the same as the current code except in two cases, one in which it performs slightly worse (Case 5 below) and one in which it performs very significantly better (Case 2 below). Overall it's a wash except in those two cases. I've since done somewhat more involved testing on a dual-core Opteron system. Case 1: With no itimer running, for a test with 100,000 threads, the fixed kernel took 1428.5 seconds, 513 seconds more than the unfixed system, all of which was spent in the system. There were twice as many voluntary context switches with the fix as without it. Case 2: With an itimer running at .01 second ticks and 4000 threads (the most an unmodified kernel can handle), the fixed kernel ran the test in eight percent of the time (5.8 seconds as opposed to 70 seconds) and had better tick accuracy (.012 seconds per tick as opposed to .023 seconds per tick). Case 3: A 4000-thread test with an initial timer tick of .01 second and an interval of 10,000 seconds (i.e. a timer that ticks only once) had very nearly the same performance in both cases: 6.3 seconds elapsed for the fixed kernel versus 5.5 seconds for the unfixed kernel. With fewer threads (eight in these tests), the Case 1 test ran in essentially the same time on both the modified and unmodified kernels (5.2 seconds versus 5.8 seconds). The Case 2 test ran in about the same time as well, 5.9 seconds versus 5.4 seconds but again with much better tick accuracy, .013 seconds per tick versus .025 seconds per tick for the unmodified kernel. Since the fix affected the rlimit code, I also tested soft and hard CPU limits. Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer running), the modified kernel was very slightly favored in that while it killed the process in 19.997 seconds of CPU time (5.002 seconds of wall time), only .003 seconds of that was system time, the rest was user time. The unmodified kernel killed the process in 20.001 seconds of CPU (5.014 seconds of wall time) of which .016 seconds was system time. Really, though, the results were too close to call. The results were essentially the same with no itimer running. Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds (where the hard limit would never be reached) and an itimer running, the modified kernel exhibited worse tick accuracy than the unmodified kernel: .050 seconds/tick versus .028 seconds/tick. Otherwise, performance was almost indistinguishable. With no itimer running this test exhibited virtually identical behavior and times in both cases. In times past I did some limited performance testing. those results are below. On a four-cpu Opteron system without this fix, a sixteen-thread test executed in 3569.991 seconds, of which user was 3568.435s and system was 1.556s. On the same system with the fix, user and elapsed time were about the same, but system time dropped to 0.007 seconds. Performance with eight, four and one thread were comparable. Interestingly, the timer ticks with the fix seemed more accurate: The sixteen-thread test with the fix received 149543 ticks for 0.024 seconds per tick, while the same test without the fix received 58720 for 0.061 seconds per tick. Both cases were configured for an interval of 0.01 seconds. Again, the other tests were comparable. Each thread in this test computed the primes up to 25,000,000. I also did a test with a large number of threads, 100,000 threads, which is impossible without the fix. In this case each thread computed the primes only up to 10,000 (to make the runtime manageable). System time dominated, at 1546.968 seconds out of a total 2176.906 seconds (giving a user time of 629.938s). It received 147651 ticks for 0.015 seconds per tick, still quite accurate. There is obviously no comparable test without the fix. Signed-off-by: Frank Mayhar Cc: Roland McGrath Cc: Alexey Dobriyan Cc: Andrew Morton Signed-off-by: Ingo Molnar diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 655ed8d..a8635f6 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1333,20 +1333,15 @@ static void fill_prstatus(struct elf_prstatus *prstatus, prstatus->pr_pgrp = task_pgrp_vnr(p); prstatus->pr_sid = task_session_vnr(p); if (thread_group_leader(p)) { + struct task_cputime cputime; + /* - * This is the record for the group leader. Add in the - * cumulative times of previous dead threads. This total - * won't include the time of each live thread whose state - * is included in the core dump. The final total reported - * to our parent process when it calls wait4 will include - * those sums as well as the little bit more time it takes - * this and each other thread to finish dying after the - * core dump synchronization phase. + * This is the record for the group leader. It shows the + * group-wide total, not its individual thread total. */ - cputime_to_timeval(cputime_add(p->utime, p->signal->utime), - &prstatus->pr_utime); - cputime_to_timeval(cputime_add(p->stime, p->signal->stime), - &prstatus->pr_stime); + thread_group_cputime(p, &cputime); + cputime_to_timeval(cputime.utime, &prstatus->pr_utime); + cputime_to_timeval(cputime.stime, &prstatus->pr_stime); } else { cputime_to_timeval(p->utime, &prstatus->pr_utime); cputime_to_timeval(p->stime, &prstatus->pr_stime); diff --git a/fs/proc/array.c b/fs/proc/array.c index 71c9be5..933953c 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -395,20 +395,20 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, /* add up live thread stats at the group level */ if (whole) { + struct task_cputime cputime; struct task_struct *t = task; do { min_flt += t->min_flt; maj_flt += t->maj_flt; - utime = cputime_add(utime, task_utime(t)); - stime = cputime_add(stime, task_stime(t)); gtime = cputime_add(gtime, task_gtime(t)); t = next_thread(t); } while (t != task); min_flt += sig->min_flt; maj_flt += sig->maj_flt; - utime = cputime_add(utime, sig->utime); - stime = cputime_add(stime, sig->stime); + thread_group_cputime(task, &cputime); + utime = cputime.utime; + stime = cputime.stime; gtime = cputime_add(gtime, sig->gtime); } diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index a7dd38f..f9d8e9e 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -115,4 +115,6 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, long clock_nanosleep_restart(struct restart_block *restart_block); +void update_rlimit_cpu(unsigned long rlim_new); + #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 3d9120c..26d7a5f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -425,6 +425,45 @@ struct pacct_struct { unsigned long ac_minflt, ac_majflt; }; +/** + * struct task_cputime - collected CPU time counts + * @utime: time spent in user mode, in &cputime_t units + * @stime: time spent in kernel mode, in &cputime_t units + * @sum_exec_runtime: total time spent on the CPU, in nanoseconds + * + * This structure groups together three kinds of CPU time that are + * tracked for threads and thread groups. Most things considering + * CPU time want to group these counts together and treat all three + * of them in parallel. + */ +struct task_cputime { + cputime_t utime; + cputime_t stime; + unsigned long long sum_exec_runtime; +}; +/* Alternate field names when used to cache expirations. */ +#define prof_exp stime +#define virt_exp utime +#define sched_exp sum_exec_runtime + +/** + * struct thread_group_cputime - thread group interval timer counts + * @totals: thread group interval timers; substructure for + * uniprocessor kernel, per-cpu for SMP kernel. + * + * This structure contains the version of task_cputime, above, that is + * used for thread group CPU clock calculations. + */ +#ifdef CONFIG_SMP +struct thread_group_cputime { + struct task_cputime *totals; +}; +#else +struct thread_group_cputime { + struct task_cputime totals; +}; +#endif + /* * NOTE! "signal_struct" does not have it's own * locking, because a shared signal_struct always @@ -470,6 +509,17 @@ struct signal_struct { cputime_t it_prof_expires, it_virt_expires; cputime_t it_prof_incr, it_virt_incr; + /* + * Thread group totals for process CPU clocks. + * See thread_group_cputime(), et al, for details. + */ + struct thread_group_cputime cputime; + + /* Earliest-expiration cache. */ + struct task_cputime cputime_expires; + + struct list_head cpu_timers[3]; + /* job control IDs */ /* @@ -500,7 +550,7 @@ struct signal_struct { * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ - cputime_t utime, stime, cutime, cstime; + cputime_t cutime, cstime; cputime_t gtime; cputime_t cgtime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; @@ -509,14 +559,6 @@ struct signal_struct { struct task_io_accounting ioac; /* - * Cumulative ns of scheduled CPU time for dead threads in the - * group, not including a zombie group leader. (This only differs - * from jiffies_to_ns(utime + stime) if sched_clock uses something - * other than jiffies.) - */ - unsigned long long sum_sched_runtime; - - /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs * to get both rlim_cur and rlim_max atomically, and either one @@ -527,8 +569,6 @@ struct signal_struct { */ struct rlimit rlim[RLIM_NLIMITS]; - struct list_head cpu_timers[3]; - /* keep the process-shared keyrings here so that they do the right * thing in threads created with CLONE_THREAD */ #ifdef CONFIG_KEYS @@ -1134,8 +1174,7 @@ struct task_struct { /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; - cputime_t it_prof_expires, it_virt_expires; - unsigned long long it_sched_expires; + struct task_cputime cputime_expires; struct list_head cpu_timers[3]; /* process credentials */ @@ -1585,6 +1624,7 @@ extern unsigned long long cpu_clock(int cpu); extern unsigned long long task_sched_runtime(struct task_struct *task); +extern unsigned long long thread_group_sched_runtime(struct task_struct *task); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP @@ -2082,6 +2122,197 @@ static inline int spin_needbreak(spinlock_t *lock) } /* + * Thread group CPU time accounting. + */ +#ifdef CONFIG_SMP + +extern int thread_group_cputime_alloc_smp(struct task_struct *); +extern void thread_group_cputime_smp(struct task_struct *, struct task_cputime *); + +static inline void thread_group_cputime_init(struct signal_struct *sig) +{ + sig->cputime.totals = NULL; +} + +static inline int thread_group_cputime_clone_thread(struct task_struct *curr, + struct task_struct *new) +{ + if (curr->signal->cputime.totals) + return 0; + return thread_group_cputime_alloc_smp(curr); +} + +static inline void thread_group_cputime_free(struct signal_struct *sig) +{ + free_percpu(sig->cputime.totals); +} + +/** + * thread_group_cputime - Sum the thread group time fields across all CPUs. + * + * This is a wrapper for the real routine, thread_group_cputime_smp(). See + * that routine for details. + */ +static inline void thread_group_cputime( + struct task_struct *tsk, + struct task_cputime *times) +{ + thread_group_cputime_smp(tsk, times); +} + +/** + * thread_group_cputime_account_user - Maintain utime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the utime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->utime = cputime_add(times->utime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_system - Maintain stime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the stime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->stime = cputime_add(times->stime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a + * thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of that structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->sum_exec_runtime += ns; + put_cpu_no_resched(); + } +} + +#else /* CONFIG_SMP */ + +static inline void thread_group_cputime_init(struct signal_struct *sig) +{ + sig->cputime.totals.utime = cputime_zero; + sig->cputime.totals.stime = cputime_zero; + sig->cputime.totals.sum_exec_runtime = 0; +} + +static inline int thread_group_cputime_alloc(struct task_struct *tsk) +{ + return 0; +} + +static inline void thread_group_cputime_free(struct signal_struct *sig) +{ +} + +static inline int thread_group_cputime_clone_thread(struct task_struct *curr, + struct task_struct *tsk) +{ +} + +static inline void thread_group_cputime(struct task_struct *tsk, + struct task_cputime *cputime) +{ + *cputime = tsk->signal->cputime.totals; +} + +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); +} + +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); +} + +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + tgtimes->totals->sum_exec_runtime += ns; +} + +#endif /* CONFIG_SMP */ + +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_user(&sig->cputime, cputime); +} + +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_system(&sig->cputime, cputime); +} + +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_exec_runtime(&sig->cputime, ns); +} + +/* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. * This is required every time the blocked sigset_t changes. diff --git a/include/linux/time.h b/include/linux/time.h index e15206a..1b70b3c 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -125,6 +125,9 @@ extern int timekeeping_valid_for_hres(void); extern void update_wall_time(void); extern void update_xtime_cache(u64 nsec); +struct tms; +extern void do_sys_times(struct tms *); + /** * timespec_to_ns - Convert timespec to nanoseconds * @ts: pointer to the timespec variable to be converted diff --git a/kernel/compat.c b/kernel/compat.c index 32c254a..72650e3 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -23,6 +23,7 @@ #include #include #include +#include #include @@ -150,49 +151,23 @@ asmlinkage long compat_sys_setitimer(int which, return 0; } +static compat_clock_t clock_t_to_compat_clock_t(clock_t x) +{ + return compat_jiffies_to_clock_t(clock_t_to_jiffies(x)); +} + asmlinkage long compat_sys_times(struct compat_tms __user *tbuf) { - /* - * In the SMP world we might just be unlucky and have one of - * the times increment as we use it. Since the value is an - * atomically safe type this is just fine. Conceptually its - * as if the syscall took an instant longer to occur. - */ if (tbuf) { + struct tms tms; struct compat_tms tmp; - struct task_struct *tsk = current; - struct task_struct *t; - cputime_t utime, stime, cutime, cstime; - - read_lock(&tasklist_lock); - utime = tsk->signal->utime; - stime = tsk->signal->stime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - t = next_thread(t); - } while (t != tsk); - - /* - * While we have tasklist_lock read-locked, no dying thread - * can be updating current->signal->[us]time. Instead, - * we got their counts included in the live thread loop. - * However, another thread can come in right now and - * do a wait call that updates current->signal->c[us]time. - * To make sure we always see that pair updated atomically, - * we take the siglock around fetching them. - */ - spin_lock_irq(&tsk->sighand->siglock); - cutime = tsk->signal->cutime; - cstime = tsk->signal->cstime; - spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); - - tmp.tms_utime = compat_jiffies_to_clock_t(cputime_to_jiffies(utime)); - tmp.tms_stime = compat_jiffies_to_clock_t(cputime_to_jiffies(stime)); - tmp.tms_cutime = compat_jiffies_to_clock_t(cputime_to_jiffies(cutime)); - tmp.tms_cstime = compat_jiffies_to_clock_t(cputime_to_jiffies(cstime)); + + do_sys_times(&tms); + /* Convert our struct tms to the compat version. */ + tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime); + tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime); + tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime); + tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime); if (copy_to_user(tbuf, &tmp, sizeof(tmp))) return -EFAULT; } diff --git a/kernel/exit.c b/kernel/exit.c index 1639564..40036ac 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -112,8 +112,6 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - sig->utime = cputime_add(sig->utime, task_utime(tsk)); - sig->stime = cputime_add(sig->stime, task_stime(tsk)); sig->gtime = cputime_add(sig->gtime, task_gtime(tsk)); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; @@ -122,7 +120,6 @@ static void __exit_signal(struct task_struct *tsk) sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); - sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig = NULL; /* Marker for below. */ } @@ -1294,6 +1291,7 @@ static int wait_task_zombie(struct task_struct *p, int options, if (likely(!traced)) { struct signal_struct *psig; struct signal_struct *sig; + struct task_cputime cputime; /* * The resource counters for the group leader are in its @@ -1309,20 +1307,23 @@ static int wait_task_zombie(struct task_struct *p, int options, * need to protect the access to p->parent->signal fields, * as other threads in the parent group can be right * here reaping other children at the same time. + * + * We use thread_group_cputime() to get times for the thread + * group, which consolidates times for all threads in the + * group including the group leader. */ spin_lock_irq(&p->parent->sighand->siglock); psig = p->parent->signal; sig = p->signal; + thread_group_cputime(p, &cputime); psig->cutime = cputime_add(psig->cutime, - cputime_add(p->utime, - cputime_add(sig->utime, - sig->cutime))); + cputime_add(cputime.utime, + sig->cutime)); psig->cstime = cputime_add(psig->cstime, - cputime_add(p->stime, - cputime_add(sig->stime, - sig->cstime))); + cputime_add(cputime.stime, + sig->cstime)); psig->cgtime = cputime_add(psig->cgtime, cputime_add(p->gtime, diff --git a/kernel/fork.c b/kernel/fork.c index 7ce2ebe..a8ac2ef 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -759,15 +759,44 @@ void __cleanup_sighand(struct sighand_struct *sighand) kmem_cache_free(sighand_cachep, sighand); } + +/* + * Initialize POSIX timer handling for a thread group. + */ +static void posix_cpu_timers_init_group(struct signal_struct *sig) +{ + /* Thread group counters. */ + thread_group_cputime_init(sig); + + /* Expiration times and increments. */ + sig->it_virt_expires = cputime_zero; + sig->it_virt_incr = cputime_zero; + sig->it_prof_expires = cputime_zero; + sig->it_prof_incr = cputime_zero; + + /* Cached expiration times. */ + sig->cputime_expires.prof_exp = cputime_zero; + sig->cputime_expires.virt_exp = cputime_zero; + sig->cputime_expires.sched_exp = 0; + + /* The timer lists. */ + INIT_LIST_HEAD(&sig->cpu_timers[0]); + INIT_LIST_HEAD(&sig->cpu_timers[1]); + INIT_LIST_HEAD(&sig->cpu_timers[2]); +} + static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; int ret; if (clone_flags & CLONE_THREAD) { - atomic_inc(¤t->signal->count); - atomic_inc(¤t->signal->live); - return 0; + ret = thread_group_cputime_clone_thread(current, tsk); + if (likely(!ret)) { + atomic_inc(¤t->signal->count); + atomic_inc(¤t->signal->live); + } + return ret; } sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; @@ -795,15 +824,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->it_real_incr.tv64 = 0; sig->real_timer.function = it_real_fn; - sig->it_virt_expires = cputime_zero; - sig->it_virt_incr = cputime_zero; - sig->it_prof_expires = cputime_zero; - sig->it_prof_incr = cputime_zero; - sig->leader = 0; /* session leadership doesn't inherit */ sig->tty_old_pgrp = NULL; - sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; + sig->cutime = sig->cstime = cputime_zero; sig->gtime = cputime_zero; sig->cgtime = cputime_zero; sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; @@ -820,14 +844,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); - if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { - /* - * New sole thread in the process gets an expiry time - * of the whole CPU time limit. - */ - tsk->it_prof_expires = - secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur); - } + posix_cpu_timers_init_group(sig); + acct_init_pacct(&sig->pacct); tty_audit_fork(sig); @@ -837,6 +855,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) void __cleanup_signal(struct signal_struct *sig) { + thread_group_cputime_free(sig); exit_thread_group_keys(sig); kmem_cache_free(signal_cachep, sig); } @@ -886,6 +905,19 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p) #endif /* CONFIG_MM_OWNER */ /* + * Initialize POSIX timer handling for a single task. + */ +static void posix_cpu_timers_init(struct task_struct *tsk) +{ + tsk->cputime_expires.prof_exp = cputime_zero; + tsk->cputime_expires.virt_exp = cputime_zero; + tsk->cputime_expires.sched_exp = 0; + INIT_LIST_HEAD(&tsk->cpu_timers[0]); + INIT_LIST_HEAD(&tsk->cpu_timers[1]); + INIT_LIST_HEAD(&tsk->cpu_timers[2]); +} + +/* * This creates a new process as a copy of the old one, * but does not actually start it yet. * @@ -995,12 +1027,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, task_io_accounting_init(&p->ioac); acct_clear_integrals(p); - p->it_virt_expires = cputime_zero; - p->it_prof_expires = cputime_zero; - p->it_sched_expires = 0; - INIT_LIST_HEAD(&p->cpu_timers[0]); - INIT_LIST_HEAD(&p->cpu_timers[1]); - INIT_LIST_HEAD(&p->cpu_timers[2]); + posix_cpu_timers_init(p); p->lock_depth = -1; /* -1 = no lock */ do_posix_clock_monotonic_gettime(&p->start_time); @@ -1201,21 +1228,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); - - if (!cputime_eq(current->signal->it_virt_expires, - cputime_zero) || - !cputime_eq(current->signal->it_prof_expires, - cputime_zero) || - current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY || - !list_empty(¤t->signal->cpu_timers[0]) || - !list_empty(¤t->signal->cpu_timers[1]) || - !list_empty(¤t->signal->cpu_timers[2])) { - /* - * Have child wake up on its first tick to check - * for process CPU timers. - */ - p->it_prof_expires = jiffies_to_cputime(1); - } } if (likely(p->pid)) { diff --git a/kernel/itimer.c b/kernel/itimer.c index ab98274..db7c358 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -55,17 +55,15 @@ int do_getitimer(int which, struct itimerval *value) spin_unlock_irq(&tsk->sighand->siglock); break; case ITIMER_VIRTUAL: - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_virt_expires; cinterval = tsk->signal->it_virt_incr; if (!cputime_eq(cval, cputime_zero)) { - struct task_struct *t = tsk; - cputime_t utime = tsk->signal->utime; - do { - utime = cputime_add(utime, t->utime); - t = next_thread(t); - } while (t != tsk); + struct task_cputime cputime; + cputime_t utime; + + thread_group_cputime(tsk, &cputime); + utime = cputime.utime; if (cputime_le(cval, utime)) { /* about to fire */ cval = jiffies_to_cputime(1); } else { @@ -73,25 +71,19 @@ int do_getitimer(int which, struct itimerval *value) } } spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); cputime_to_timeval(cval, &value->it_value); cputime_to_timeval(cinterval, &value->it_interval); break; case ITIMER_PROF: - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_prof_expires; cinterval = tsk->signal->it_prof_incr; if (!cputime_eq(cval, cputime_zero)) { - struct task_struct *t = tsk; - cputime_t ptime = cputime_add(tsk->signal->utime, - tsk->signal->stime); - do { - ptime = cputime_add(ptime, - cputime_add(t->utime, - t->stime)); - t = next_thread(t); - } while (t != tsk); + struct task_cputime times; + cputime_t ptime; + + thread_group_cputime(tsk, ×); + ptime = cputime_add(times.utime, times.stime); if (cputime_le(cval, ptime)) { /* about to fire */ cval = jiffies_to_cputime(1); } else { @@ -99,7 +91,6 @@ int do_getitimer(int which, struct itimerval *value) } } spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); cputime_to_timeval(cval, &value->it_value); cputime_to_timeval(cinterval, &value->it_interval); break; @@ -185,7 +176,6 @@ again: case ITIMER_VIRTUAL: nval = timeval_to_cputime(&value->it_value); ninterval = timeval_to_cputime(&value->it_interval); - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_virt_expires; cinterval = tsk->signal->it_virt_incr; @@ -200,7 +190,6 @@ again: tsk->signal->it_virt_expires = nval; tsk->signal->it_virt_incr = ninterval; spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); if (ovalue) { cputime_to_timeval(cval, &ovalue->it_value); cputime_to_timeval(cinterval, &ovalue->it_interval); @@ -209,7 +198,6 @@ again: case ITIMER_PROF: nval = timeval_to_cputime(&value->it_value); ninterval = timeval_to_cputime(&value->it_interval); - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_prof_expires; cinterval = tsk->signal->it_prof_incr; @@ -224,7 +212,6 @@ again: tsk->signal->it_prof_expires = nval; tsk->signal->it_prof_incr = ninterval; spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); if (ovalue) { cputime_to_timeval(cval, &ovalue->it_value); cputime_to_timeval(cinterval, &ovalue->it_interval); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index c42a03a..dba1c33 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -8,6 +8,99 @@ #include #include +#ifdef CONFIG_SMP +/* + * Allocate the thread_group_cputime structure appropriately for SMP kernels + * and fill in the current values of the fields. Called from copy_signal() + * via thread_group_cputime_clone_thread() when adding a second or subsequent + * thread to a thread group. Assumes interrupts are enabled when called. + */ +int thread_group_cputime_alloc_smp(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + struct task_cputime *cputime; + + /* + * If we have multiple threads and we don't already have a + * per-CPU task_cputime struct, allocate one and fill it in with + * the times accumulated so far. + */ + if (sig->cputime.totals) + return 0; + cputime = alloc_percpu(struct task_cputime); + if (cputime == NULL) + return -ENOMEM; + read_lock(&tasklist_lock); + spin_lock_irq(&tsk->sighand->siglock); + if (sig->cputime.totals) { + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + free_percpu(cputime); + return 0; + } + sig->cputime.totals = cputime; + cputime = per_cpu_ptr(sig->cputime.totals, get_cpu()); + cputime->utime = tsk->utime; + cputime->stime = tsk->stime; + cputime->sum_exec_runtime = tsk->se.sum_exec_runtime; + put_cpu_no_resched(); + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + return 0; +} + +/** + * thread_group_cputime_smp - Sum the thread group time fields across all CPUs. + * + * @tsk: The task we use to identify the thread group. + * @times: task_cputime structure in which we return the summed fields. + * + * Walk the list of CPUs to sum the per-CPU time fields in the thread group + * time structure. + */ +void thread_group_cputime_smp( + struct task_struct *tsk, + struct task_cputime *times) +{ + struct signal_struct *sig; + int i; + struct task_cputime *tot; + + sig = tsk->signal; + if (unlikely(!sig) || !sig->cputime.totals) { + times->utime = tsk->utime; + times->stime = tsk->stime; + times->sum_exec_runtime = tsk->se.sum_exec_runtime; + return; + } + times->stime = times->utime = cputime_zero; + times->sum_exec_runtime = 0; + for_each_possible_cpu(i) { + tot = per_cpu_ptr(tsk->signal->cputime.totals, i); + times->utime = cputime_add(times->utime, tot->utime); + times->stime = cputime_add(times->stime, tot->stime); + times->sum_exec_runtime += tot->sum_exec_runtime; + } +} + +#endif /* CONFIG_SMP */ + +/* + * Called after updating RLIMIT_CPU to set timer expiration if necessary. + */ +void update_rlimit_cpu(unsigned long rlim_new) +{ + cputime_t cputime; + + cputime = secs_to_cputime(rlim_new); + if (cputime_eq(current->signal->it_prof_expires, cputime_zero) || + cputime_lt(current->signal->it_prof_expires, cputime)) { + spin_lock_irq(¤t->sighand->siglock); + set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); + spin_unlock_irq(¤t->sighand->siglock); + } +} + static int check_clock(const clockid_t which_clock) { int error = 0; @@ -158,10 +251,6 @@ static inline cputime_t virt_ticks(struct task_struct *p) { return p->utime; } -static inline unsigned long long sched_ns(struct task_struct *p) -{ - return task_sched_runtime(p); -} int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp) { @@ -211,7 +300,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, cpu->cpu = virt_ticks(p); break; case CPUCLOCK_SCHED: - cpu->sched = sched_ns(p); + cpu->sched = task_sched_runtime(p); break; } return 0; @@ -226,31 +315,20 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx, struct task_struct *p, union cpu_time_count *cpu) { - struct task_struct *t = p; - switch (clock_idx) { + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + switch (clock_idx) { default: return -EINVAL; case CPUCLOCK_PROF: - cpu->cpu = cputime_add(p->signal->utime, p->signal->stime); - do { - cpu->cpu = cputime_add(cpu->cpu, prof_ticks(t)); - t = next_thread(t); - } while (t != p); + cpu->cpu = cputime_add(cputime.utime, cputime.stime); break; case CPUCLOCK_VIRT: - cpu->cpu = p->signal->utime; - do { - cpu->cpu = cputime_add(cpu->cpu, virt_ticks(t)); - t = next_thread(t); - } while (t != p); + cpu->cpu = cputime.utime; break; case CPUCLOCK_SCHED: - cpu->sched = p->signal->sum_sched_runtime; - /* Add in each other live thread. */ - while ((t = next_thread(t)) != p) { - cpu->sched += t->se.sum_exec_runtime; - } - cpu->sched += sched_ns(p); + cpu->sched = thread_group_sched_runtime(p); break; } return 0; @@ -471,80 +549,11 @@ void posix_cpu_timers_exit(struct task_struct *tsk) } void posix_cpu_timers_exit_group(struct task_struct *tsk) { - cleanup_timers(tsk->signal->cpu_timers, - cputime_add(tsk->utime, tsk->signal->utime), - cputime_add(tsk->stime, tsk->signal->stime), - tsk->se.sum_exec_runtime + tsk->signal->sum_sched_runtime); -} - - -/* - * Set the expiry times of all the threads in the process so one of them - * will go off before the process cumulative expiry total is reached. - */ -static void process_timer_rebalance(struct task_struct *p, - unsigned int clock_idx, - union cpu_time_count expires, - union cpu_time_count val) -{ - cputime_t ticks, left; - unsigned long long ns, nsleft; - struct task_struct *t = p; - unsigned int nthreads = atomic_read(&p->signal->live); - - if (!nthreads) - return; + struct task_cputime cputime; - switch (clock_idx) { - default: - BUG(); - break; - case CPUCLOCK_PROF: - left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu), - nthreads); - do { - if (likely(!(t->flags & PF_EXITING))) { - ticks = cputime_add(prof_ticks(t), left); - if (cputime_eq(t->it_prof_expires, - cputime_zero) || - cputime_gt(t->it_prof_expires, ticks)) { - t->it_prof_expires = ticks; - } - } - t = next_thread(t); - } while (t != p); - break; - case CPUCLOCK_VIRT: - left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu), - nthreads); - do { - if (likely(!(t->flags & PF_EXITING))) { - ticks = cputime_add(virt_ticks(t), left); - if (cputime_eq(t->it_virt_expires, - cputime_zero) || - cputime_gt(t->it_virt_expires, ticks)) { - t->it_virt_expires = ticks; - } - } - t = next_thread(t); - } while (t != p); - break; - case CPUCLOCK_SCHED: - nsleft = expires.sched - val.sched; - do_div(nsleft, nthreads); - nsleft = max_t(unsigned long long, nsleft, 1); - do { - if (likely(!(t->flags & PF_EXITING))) { - ns = t->se.sum_exec_runtime + nsleft; - if (t->it_sched_expires == 0 || - t->it_sched_expires > ns) { - t->it_sched_expires = ns; - } - } - t = next_thread(t); - } while (t != p); - break; - } + thread_group_cputime(tsk, &cputime); + cleanup_timers(tsk->signal->cpu_timers, + cputime.utime, cputime.stime, cputime.sum_exec_runtime); } static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now) @@ -608,29 +617,32 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) default: BUG(); case CPUCLOCK_PROF: - if (cputime_eq(p->it_prof_expires, + if (cputime_eq(p->cputime_expires.prof_exp, cputime_zero) || - cputime_gt(p->it_prof_expires, + cputime_gt(p->cputime_expires.prof_exp, nt->expires.cpu)) - p->it_prof_expires = nt->expires.cpu; + p->cputime_expires.prof_exp = + nt->expires.cpu; break; case CPUCLOCK_VIRT: - if (cputime_eq(p->it_virt_expires, + if (cputime_eq(p->cputime_expires.virt_exp, cputime_zero) || - cputime_gt(p->it_virt_expires, + cputime_gt(p->cputime_expires.virt_exp, nt->expires.cpu)) - p->it_virt_expires = nt->expires.cpu; + p->cputime_expires.virt_exp = + nt->expires.cpu; break; case CPUCLOCK_SCHED: - if (p->it_sched_expires == 0 || - p->it_sched_expires > nt->expires.sched) - p->it_sched_expires = nt->expires.sched; + if (p->cputime_expires.sched_exp == 0 || + p->cputime_expires.sched_exp > + nt->expires.sched) + p->cputime_expires.sched_exp = + nt->expires.sched; break; } } else { /* - * For a process timer, we must balance - * all the live threads' expirations. + * For a process timer, set the cached expiration time. */ switch (CPUCLOCK_WHICH(timer->it_clock)) { default: @@ -641,7 +653,9 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) cputime_lt(p->signal->it_virt_expires, timer->it.cpu.expires.cpu)) break; - goto rebalance; + p->signal->cputime_expires.virt_exp = + timer->it.cpu.expires.cpu; + break; case CPUCLOCK_PROF: if (!cputime_eq(p->signal->it_prof_expires, cputime_zero) && @@ -652,13 +666,12 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) if (i != RLIM_INFINITY && i <= cputime_to_secs(timer->it.cpu.expires.cpu)) break; - goto rebalance; + p->signal->cputime_expires.prof_exp = + timer->it.cpu.expires.cpu; + break; case CPUCLOCK_SCHED: - rebalance: - process_timer_rebalance( - timer->it.cpu.task, - CPUCLOCK_WHICH(timer->it_clock), - timer->it.cpu.expires, now); + p->signal->cputime_expires.sched_exp = + timer->it.cpu.expires.sched; break; } } @@ -969,13 +982,13 @@ static void check_thread_timers(struct task_struct *tsk, struct signal_struct *const sig = tsk->signal; maxfire = 20; - tsk->it_prof_expires = cputime_zero; + tsk->cputime_expires.prof_exp = cputime_zero; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) { - tsk->it_prof_expires = t->expires.cpu; + tsk->cputime_expires.prof_exp = t->expires.cpu; break; } t->firing = 1; @@ -984,13 +997,13 @@ static void check_thread_timers(struct task_struct *tsk, ++timers; maxfire = 20; - tsk->it_virt_expires = cputime_zero; + tsk->cputime_expires.virt_exp = cputime_zero; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) { - tsk->it_virt_expires = t->expires.cpu; + tsk->cputime_expires.virt_exp = t->expires.cpu; break; } t->firing = 1; @@ -999,13 +1012,13 @@ static void check_thread_timers(struct task_struct *tsk, ++timers; maxfire = 20; - tsk->it_sched_expires = 0; + tsk->cputime_expires.sched_exp = 0; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) { - tsk->it_sched_expires = t->expires.sched; + tsk->cputime_expires.sched_exp = t->expires.sched; break; } t->firing = 1; @@ -1055,10 +1068,10 @@ static void check_process_timers(struct task_struct *tsk, { int maxfire; struct signal_struct *const sig = tsk->signal; - cputime_t utime, stime, ptime, virt_expires, prof_expires; + cputime_t utime, ptime, virt_expires, prof_expires; unsigned long long sum_sched_runtime, sched_expires; - struct task_struct *t; struct list_head *timers = sig->cpu_timers; + struct task_cputime cputime; /* * Don't sample the current process CPU clocks if there are no timers. @@ -1074,18 +1087,10 @@ static void check_process_timers(struct task_struct *tsk, /* * Collect the current process totals. */ - utime = sig->utime; - stime = sig->stime; - sum_sched_runtime = sig->sum_sched_runtime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - sum_sched_runtime += t->se.sum_exec_runtime; - t = next_thread(t); - } while (t != tsk); - ptime = cputime_add(utime, stime); - + thread_group_cputime(tsk, &cputime); + utime = cputime.utime; + ptime = cputime_add(utime, cputime.stime); + sum_sched_runtime = cputime.sum_exec_runtime; maxfire = 20; prof_expires = cputime_zero; while (!list_empty(timers)) { @@ -1193,60 +1198,18 @@ static void check_process_timers(struct task_struct *tsk, } } - if (!cputime_eq(prof_expires, cputime_zero) || - !cputime_eq(virt_expires, cputime_zero) || - sched_expires != 0) { - /* - * Rebalance the threads' expiry times for the remaining - * process CPU timers. - */ - - cputime_t prof_left, virt_left, ticks; - unsigned long long sched_left, sched; - const unsigned int nthreads = atomic_read(&sig->live); - - if (!nthreads) - return; - - prof_left = cputime_sub(prof_expires, utime); - prof_left = cputime_sub(prof_left, stime); - prof_left = cputime_div_non_zero(prof_left, nthreads); - virt_left = cputime_sub(virt_expires, utime); - virt_left = cputime_div_non_zero(virt_left, nthreads); - if (sched_expires) { - sched_left = sched_expires - sum_sched_runtime; - do_div(sched_left, nthreads); - sched_left = max_t(unsigned long long, sched_left, 1); - } else { - sched_left = 0; - } - t = tsk; - do { - if (unlikely(t->flags & PF_EXITING)) - continue; - - ticks = cputime_add(cputime_add(t->utime, t->stime), - prof_left); - if (!cputime_eq(prof_expires, cputime_zero) && - (cputime_eq(t->it_prof_expires, cputime_zero) || - cputime_gt(t->it_prof_expires, ticks))) { - t->it_prof_expires = ticks; - } - - ticks = cputime_add(t->utime, virt_left); - if (!cputime_eq(virt_expires, cputime_zero) && - (cputime_eq(t->it_virt_expires, cputime_zero) || - cputime_gt(t->it_virt_expires, ticks))) { - t->it_virt_expires = ticks; - } - - sched = t->se.sum_exec_runtime + sched_left; - if (sched_expires && (t->it_sched_expires == 0 || - t->it_sched_expires > sched)) { - t->it_sched_expires = sched; - } - } while ((t = next_thread(t)) != tsk); - } + if (!cputime_eq(prof_expires, cputime_zero) && + (cputime_eq(sig->cputime_expires.prof_exp, cputime_zero) || + cputime_gt(sig->cputime_expires.prof_exp, prof_expires))) + sig->cputime_expires.prof_exp = prof_expires; + if (!cputime_eq(virt_expires, cputime_zero) && + (cputime_eq(sig->cputime_expires.virt_exp, cputime_zero) || + cputime_gt(sig->cputime_expires.virt_exp, virt_expires))) + sig->cputime_expires.virt_exp = virt_expires; + if (sched_expires != 0 && + (sig->cputime_expires.sched_exp == 0 || + sig->cputime_expires.sched_exp > sched_expires)) + sig->cputime_expires.sched_exp = sched_expires; } /* @@ -1314,6 +1277,78 @@ out: ++timer->it_requeue_pending; } +/** + * task_cputime_zero - Check a task_cputime struct for all zero fields. + * + * @cputime: The struct to compare. + * + * Checks @cputime to see if all fields are zero. Returns true if all fields + * are zero, false if any field is nonzero. + */ +static inline int task_cputime_zero(const struct task_cputime *cputime) +{ + if (cputime_eq(cputime->utime, cputime_zero) && + cputime_eq(cputime->stime, cputime_zero) && + cputime->sum_exec_runtime == 0) + return 1; + return 0; +} + +/** + * task_cputime_expired - Compare two task_cputime entities. + * + * @sample: The task_cputime structure to be checked for expiration. + * @expires: Expiration times, against which @sample will be checked. + * + * Checks @sample against @expires to see if any field of @sample has expired. + * Returns true if any field of the former is greater than the corresponding + * field of the latter if the latter field is set. Otherwise returns false. + */ +static inline int task_cputime_expired(const struct task_cputime *sample, + const struct task_cputime *expires) +{ + if (!cputime_eq(expires->utime, cputime_zero) && + cputime_ge(sample->utime, expires->utime)) + return 1; + if (!cputime_eq(expires->stime, cputime_zero) && + cputime_ge(cputime_add(sample->utime, sample->stime), + expires->stime)) + return 1; + if (expires->sum_exec_runtime != 0 && + sample->sum_exec_runtime >= expires->sum_exec_runtime) + return 1; + return 0; +} + +/** + * fastpath_timer_check - POSIX CPU timers fast path. + * + * @tsk: The task (thread) being checked. + * @sig: The signal pointer for that task. + * + * If there are no timers set return false. Otherwise snapshot the task and + * thread group timers, then compare them with the corresponding expiration + # times. Returns true if a timer has expired, else returns false. + */ +static inline int fastpath_timer_check(struct task_struct *tsk, + struct signal_struct *sig) +{ + struct task_cputime task_sample = { + .utime = tsk->utime, + .stime = tsk->stime, + .sum_exec_runtime = tsk->se.sum_exec_runtime + }; + struct task_cputime group_sample; + + if (task_cputime_zero(&tsk->cputime_expires) && + task_cputime_zero(&sig->cputime_expires)) + return 0; + if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) + return 1; + thread_group_cputime(tsk, &group_sample); + return task_cputime_expired(&group_sample, &sig->cputime_expires); +} + /* * This is called from the timer interrupt handler. The irq handler has * already updated our counts. We need to check if any timers fire now. @@ -1323,30 +1358,29 @@ void run_posix_cpu_timers(struct task_struct *tsk) { LIST_HEAD(firing); struct k_itimer *timer, *next; + struct signal_struct *sig; + struct sighand_struct *sighand; + unsigned long flags; BUG_ON(!irqs_disabled()); -#define UNEXPIRED(clock) \ - (cputime_eq(tsk->it_##clock##_expires, cputime_zero) || \ - cputime_lt(clock##_ticks(tsk), tsk->it_##clock##_expires)) - - if (UNEXPIRED(prof) && UNEXPIRED(virt) && - (tsk->it_sched_expires == 0 || - tsk->se.sum_exec_runtime < tsk->it_sched_expires)) - return; - -#undef UNEXPIRED - + /* Pick up tsk->signal and make sure it's valid. */ + sig = tsk->signal; /* - * Double-check with locks held. + * The fast path checks that there are no expired thread or thread + * group timers. If that's so, just return. Also check that + * tsk->signal is non-NULL; this probably can't happen but cover the + * possibility anyway. */ - read_lock(&tasklist_lock); - if (likely(tsk->signal != NULL)) { - spin_lock(&tsk->sighand->siglock); - + if (unlikely(!sig) || !fastpath_timer_check(tsk, sig)) { + return; + } + sighand = lock_task_sighand(tsk, &flags); + if (likely(sighand)) { /* - * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N] - * all the timers that are firing, and put them on the firing list. + * Here we take off tsk->signal->cpu_timers[N] and + * tsk->cpu_timers[N] all the timers that are firing, and + * put them on the firing list. */ check_thread_timers(tsk, &firing); check_process_timers(tsk, &firing); @@ -1359,9 +1393,8 @@ void run_posix_cpu_timers(struct task_struct *tsk) * that gets the timer lock before we do will give it up and * spin until we've taken care of that timer below. */ - spin_unlock(&tsk->sighand->siglock); } - read_unlock(&tasklist_lock); + unlock_task_sighand(tsk, &flags); /* * Now that all the timers on our list have the firing flag, @@ -1389,10 +1422,9 @@ void run_posix_cpu_timers(struct task_struct *tsk) /* * Set one of the process-wide special case CPU timers. - * The tasklist_lock and tsk->sighand->siglock must be held by the caller. - * The oldval argument is null for the RLIMIT_CPU timer, where *newval is - * absolute; non-null for ITIMER_*, where *newval is relative and we update - * it to be absolute, *oldval is absolute and we update it to be relative. + * The tsk->sighand->siglock must be held by the caller. + * The *newval argument is relative and we update it to be absolute, *oldval + * is absolute and we update it to be relative. */ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, cputime_t *newval, cputime_t *oldval) @@ -1435,13 +1467,14 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, cputime_ge(list_first_entry(head, struct cpu_timer_list, entry)->expires.cpu, *newval)) { - /* - * Rejigger each thread's expiry time so that one will - * notice before we hit the process-cumulative expiry time. - */ - union cpu_time_count expires = { .sched = 0 }; - expires.cpu = *newval; - process_timer_rebalance(tsk, clock_idx, expires, now); + switch (clock_idx) { + case CPUCLOCK_PROF: + tsk->signal->cputime_expires.prof_exp = *newval; + break; + case CPUCLOCK_VIRT: + tsk->signal->cputime_expires.virt_exp = *newval; + break; + } } } diff --git a/kernel/sched.c b/kernel/sched.c index cc1f81b..c51b5d2 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4037,23 +4037,56 @@ DEFINE_PER_CPU(struct kernel_stat, kstat); EXPORT_PER_CPU_SYMBOL(kstat); /* + * Return any ns on the sched_clock that have not yet been banked in + * @p in case that task is currently running. + * + * Called with task_rq_lock() held on @rq. + */ +static unsigned long long task_delta_exec(struct task_struct *p, struct rq *rq) +{ + if (task_current(rq, p)) { + u64 delta_exec; + + update_rq_clock(rq); + delta_exec = rq->clock - p->se.exec_start; + if ((s64)delta_exec > 0) + return delta_exec; + } + return 0; +} + +/* * Return p->sum_exec_runtime plus any more ns on the sched_clock * that have not yet been banked in case the task is currently running. */ unsigned long long task_sched_runtime(struct task_struct *p) { unsigned long flags; - u64 ns, delta_exec; + u64 ns; struct rq *rq; rq = task_rq_lock(p, &flags); - ns = p->se.sum_exec_runtime; - if (task_current(rq, p)) { - update_rq_clock(rq); - delta_exec = rq->clock - p->se.exec_start; - if ((s64)delta_exec > 0) - ns += delta_exec; - } + ns = p->se.sum_exec_runtime + task_delta_exec(p, rq); + task_rq_unlock(rq, &flags); + + return ns; +} + +/* + * Return sum_exec_runtime for the thread group plus any more ns on the + * sched_clock that have not yet been banked in case the task is currently + * running. + */ +unsigned long long thread_group_sched_runtime(struct task_struct *p) +{ + unsigned long flags; + u64 ns; + struct rq *rq; + struct task_cputime totals; + + rq = task_rq_lock(p, &flags); + thread_group_cputime(p, &totals); + ns = totals.sum_exec_runtime + task_delta_exec(p, rq); task_rq_unlock(rq, &flags); return ns; @@ -4070,6 +4103,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime) cputime64_t tmp; p->utime = cputime_add(p->utime, cputime); + account_group_user_time(p, cputime); /* Add user time to cpustat. */ tmp = cputime_to_cputime64(cputime); @@ -4094,6 +4128,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime) tmp = cputime_to_cputime64(cputime); p->utime = cputime_add(p->utime, cputime); + account_group_user_time(p, cputime); p->gtime = cputime_add(p->gtime, cputime); cpustat->user = cputime64_add(cpustat->user, tmp); @@ -4129,6 +4164,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset, } p->stime = cputime_add(p->stime, cputime); + account_group_system_time(p, cputime); /* Add system time to cpustat. */ tmp = cputime_to_cputime64(cputime); @@ -4170,6 +4206,7 @@ void account_steal_time(struct task_struct *p, cputime_t steal) if (p == rq->idle) { p->stime = cputime_add(p->stime, steal); + account_group_system_time(p, steal); if (atomic_read(&rq->nr_iowait) > 0) cpustat->iowait = cputime64_add(cpustat->iowait, tmp); else diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index fb8994c..99aa31a 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -507,6 +507,7 @@ static void update_curr(struct cfs_rq *cfs_rq) struct task_struct *curtask = task_of(curr); cpuacct_charge(curtask, delta_exec); + account_group_exec_runtime(curtask, delta_exec); } } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 5523107..8375e69 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -483,6 +483,8 @@ static void update_curr_rt(struct rq *rq) schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec)); curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + curr->se.exec_start = rq->clock; cpuacct_charge(curr, delta_exec); @@ -1412,7 +1414,7 @@ static void watchdog(struct rq *rq, struct task_struct *p) p->rt.timeout++; next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ); if (p->rt.timeout > next) - p->it_sched_expires = p->se.sum_exec_runtime; + p->cputime_expires.sched_exp = p->se.sum_exec_runtime; } } diff --git a/kernel/signal.c b/kernel/signal.c index e661b01..6eea582 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1338,6 +1338,7 @@ int do_notify_parent(struct task_struct *tsk, int sig) struct siginfo info; unsigned long flags; struct sighand_struct *psig; + struct task_cputime cputime; int ret = sig; BUG_ON(sig == -1); @@ -1368,10 +1369,9 @@ int do_notify_parent(struct task_struct *tsk, int sig) info.si_uid = tsk->uid; - info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime, - tsk->signal->utime)); - info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime, - tsk->signal->stime)); + thread_group_cputime(tsk, &cputime); + info.si_utime = cputime_to_jiffies(cputime.utime); + info.si_stime = cputime_to_jiffies(cputime.stime); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) diff --git a/kernel/sys.c b/kernel/sys.c index 038a7bc..d046a7a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -853,38 +853,28 @@ asmlinkage long sys_setfsgid(gid_t gid) return old_fsgid; } +void do_sys_times(struct tms *tms) +{ + struct task_cputime cputime; + cputime_t cutime, cstime; + + spin_lock_irq(¤t->sighand->siglock); + thread_group_cputime(current, &cputime); + cutime = current->signal->cutime; + cstime = current->signal->cstime; + spin_unlock_irq(¤t->sighand->siglock); + tms->tms_utime = cputime_to_clock_t(cputime.utime); + tms->tms_stime = cputime_to_clock_t(cputime.stime); + tms->tms_cutime = cputime_to_clock_t(cutime); + tms->tms_cstime = cputime_to_clock_t(cstime); +} + asmlinkage long sys_times(struct tms __user * tbuf) { - /* - * In the SMP world we might just be unlucky and have one of - * the times increment as we use it. Since the value is an - * atomically safe type this is just fine. Conceptually its - * as if the syscall took an instant longer to occur. - */ if (tbuf) { struct tms tmp; - struct task_struct *tsk = current; - struct task_struct *t; - cputime_t utime, stime, cutime, cstime; - - spin_lock_irq(&tsk->sighand->siglock); - utime = tsk->signal->utime; - stime = tsk->signal->stime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - t = next_thread(t); - } while (t != tsk); - - cutime = tsk->signal->cutime; - cstime = tsk->signal->cstime; - spin_unlock_irq(&tsk->sighand->siglock); - - tmp.tms_utime = cputime_to_clock_t(utime); - tmp.tms_stime = cputime_to_clock_t(stime); - tmp.tms_cutime = cputime_to_clock_t(cutime); - tmp.tms_cstime = cputime_to_clock_t(cstime); + + do_sys_times(&tmp); if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } @@ -1445,7 +1435,6 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) { struct rlimit new_rlim, *old_rlim; - unsigned long it_prof_secs; int retval; if (resource >= RLIM_NLIMITS) @@ -1491,18 +1480,7 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) if (new_rlim.rlim_cur == RLIM_INFINITY) goto out; - it_prof_secs = cputime_to_secs(current->signal->it_prof_expires); - if (it_prof_secs == 0 || new_rlim.rlim_cur <= it_prof_secs) { - unsigned long rlim_cur = new_rlim.rlim_cur; - cputime_t cputime; - - cputime = secs_to_cputime(rlim_cur); - read_lock(&tasklist_lock); - spin_lock_irq(¤t->sighand->siglock); - set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); - spin_unlock_irq(¤t->sighand->siglock); - read_unlock(&tasklist_lock); - } + update_rlimit_cpu(new_rlim.rlim_cur); out: return 0; } @@ -1540,11 +1518,8 @@ out: * */ -static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r, - cputime_t *utimep, cputime_t *stimep) +static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) { - *utimep = cputime_add(*utimep, t->utime); - *stimep = cputime_add(*stimep, t->stime); r->ru_nvcsw += t->nvcsw; r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; @@ -1558,12 +1533,13 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) struct task_struct *t; unsigned long flags; cputime_t utime, stime; + struct task_cputime cputime; memset((char *) r, 0, sizeof *r); utime = stime = cputime_zero; if (who == RUSAGE_THREAD) { - accumulate_thread_rusage(p, r, &utime, &stime); + accumulate_thread_rusage(p, r); goto out; } @@ -1586,8 +1562,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) break; case RUSAGE_SELF: - utime = cputime_add(utime, p->signal->utime); - stime = cputime_add(stime, p->signal->stime); + thread_group_cputime(p, &cputime); + utime = cputime_add(utime, cputime.utime); + stime = cputime_add(stime, cputime.stime); r->ru_nvcsw += p->signal->nvcsw; r->ru_nivcsw += p->signal->nivcsw; r->ru_minflt += p->signal->min_flt; @@ -1596,7 +1573,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) r->ru_oublock += p->signal->oublock; t = p; do { - accumulate_thread_rusage(t, r, &utime, &stime); + accumulate_thread_rusage(t, r); t = next_thread(t); } while (t != p); break; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 03fc6a8..6964978 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -75,6 +75,7 @@ #include #include #include +#include #include "avc.h" #include "objsec.h" @@ -2321,13 +2322,7 @@ static void selinux_bprm_post_apply_creds(struct linux_binprm *bprm) initrlim = init_task.signal->rlim+i; rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur); } - if (current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { - /* - * This will cause RLIMIT_CPU calculations - * to be refigured. - */ - current->it_prof_expires = jiffies_to_cputime(1); - } + update_rlimit_cpu(rlim->rlim_cur); } /* Wake up the parent if it is waiting so that it can -- cgit v0.10.2 From 430b5294bd72c085c730e1e4b86580f164d976bf Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 14 Sep 2008 16:33:01 +0200 Subject: timers: fix itimer/many thread hang, fix MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit fix: kernel/fork.c:843: error: ‘struct signal_struct’ has no member named ‘sum_sched_runtime’ kernel/irq/handle.c:117: warning: ‘sparse_irq_lock’ defined but not used Signed-off-by: Ingo Molnar diff --git a/kernel/fork.c b/kernel/fork.c index a8ac2ef..1181b9a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -834,7 +834,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; task_io_accounting_init(&sig->ioac); - sig->sum_sched_runtime = 0; INIT_LIST_HEAD(&sig->cpu_timers[0]); INIT_LIST_HEAD(&sig->cpu_timers[1]); INIT_LIST_HEAD(&sig->cpu_timers[2]); -- cgit v0.10.2 From 0a8eaa4f9b58759595a1bfe13a1295fdc25ba026 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 14 Sep 2008 17:03:52 +0200 Subject: timers: fix itimer/many thread hang, fix #2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit fix the UP build: In file included from arch/x86/kernel/asm-offsets_32.c:9, from arch/x86/kernel/asm-offsets.c:3: include/linux/sched.h: In function ‘thread_group_cputime_clone_thread’: include/linux/sched.h:2272: warning: no return statement in function returning non-void include/linux/sched.h: In function ‘thread_group_cputime_account_user’: include/linux/sched.h:2284: error: invalid type argument of ‘->’ (have ‘struct task_cputime’) include/linux/sched.h:2284: error: invalid type argument of ‘->’ (have ‘struct task_cputime’) include/linux/sched.h: In function ‘thread_group_cputime_account_system’: include/linux/sched.h:2291: error: invalid type argument of ‘->’ (have ‘struct task_cputime’) include/linux/sched.h:2291: error: invalid type argument of ‘->’ (have ‘struct task_cputime’) include/linux/sched.h: In function ‘thread_group_cputime_account_exec_runtime’: include/linux/sched.h:2298: error: invalid type argument of ‘->’ (have ‘struct task_cputime’) distcc[14501] ERROR: compile arch/x86/kernel/asm-offsets.c on a/30 failed make[1]: *** [arch/x86/kernel/asm-offsets.s] Error 1 Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index 26d7a5f..ed355f0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2251,6 +2251,7 @@ static inline void thread_group_cputime_free(struct signal_struct *sig) static inline int thread_group_cputime_clone_thread(struct task_struct *curr, struct task_struct *tsk) { + return 0; } static inline void thread_group_cputime(struct task_struct *tsk, @@ -2263,21 +2264,21 @@ static inline void thread_group_cputime_account_user( struct thread_group_cputime *tgtimes, cputime_t cputime) { - tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); + tgtimes->totals.utime = cputime_add(tgtimes->totals.utime, cputime); } static inline void thread_group_cputime_account_system( struct thread_group_cputime *tgtimes, cputime_t cputime) { - tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); + tgtimes->totals.stime = cputime_add(tgtimes->totals.stime, cputime); } static inline void thread_group_cputime_account_exec_runtime( struct thread_group_cputime *tgtimes, unsigned long long ns) { - tgtimes->totals->sum_exec_runtime += ns; + tgtimes->totals.sum_exec_runtime += ns; } #endif /* CONFIG_SMP */ -- cgit v0.10.2 From 5ce73a4a5a4893a1aa4cdeed1b1a5a6de42c43b6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 14 Sep 2008 17:11:46 +0200 Subject: timers: fix itimer/many thread hang, cleanups Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index ed355f0..7ce8d4e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -430,7 +430,7 @@ struct pacct_struct { * @utime: time spent in user mode, in &cputime_t units * @stime: time spent in kernel mode, in &cputime_t units * @sum_exec_runtime: total time spent on the CPU, in nanoseconds - * + * * This structure groups together three kinds of CPU time that are * tracked for threads and thread groups. Most things considering * CPU time want to group these counts together and treat all three diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index dba1c33..9a7ea04 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -94,7 +94,7 @@ void update_rlimit_cpu(unsigned long rlim_new) cputime = secs_to_cputime(rlim_new); if (cputime_eq(current->signal->it_prof_expires, cputime_zero) || - cputime_lt(current->signal->it_prof_expires, cputime)) { + cputime_lt(current->signal->it_prof_expires, cputime)) { spin_lock_irq(¤t->sighand->siglock); set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); spin_unlock_irq(¤t->sighand->siglock); @@ -1372,9 +1372,9 @@ void run_posix_cpu_timers(struct task_struct *tsk) * tsk->signal is non-NULL; this probably can't happen but cover the * possibility anyway. */ - if (unlikely(!sig) || !fastpath_timer_check(tsk, sig)) { + if (unlikely(!sig) || !fastpath_timer_check(tsk, sig)) return; - } + sighand = lock_task_sighand(tsk, &flags); if (likely(sighand)) { /* -- cgit v0.10.2 From 8afbc114542a6810b0a2e658abda6e911121cd22 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 25 Aug 2008 12:01:31 +0300 Subject: [MTD] [NAND] OMAP2: add retry after read timeout Very occasionally, (about one in a million) read operations are ongoing after the timeout has expired. So, retry three times while the ongoing bit remains set. Signed-off-by: Adrian Hunter Signed-off-by: David Woodhouse diff --git a/drivers/mtd/onenand/omap2.c b/drivers/mtd/onenand/omap2.c index 34b4253..8387e05 100644 --- a/drivers/mtd/onenand/omap2.c +++ b/drivers/mtd/onenand/omap2.c @@ -187,16 +187,36 @@ retry: } } } else { + int retry_cnt = 0; + /* Turn interrupts off */ syscfg = read_reg(c, ONENAND_REG_SYS_CFG1); syscfg &= ~ONENAND_SYS_CFG1_IOBE; write_reg(c, syscfg, ONENAND_REG_SYS_CFG1); timeout = jiffies + msecs_to_jiffies(20); - while (time_before(jiffies, timeout)) { - intr = read_reg(c, ONENAND_REG_INTERRUPT); - if (intr & ONENAND_INT_MASTER) + while (1) { + if (time_before(jiffies, timeout)) { + intr = read_reg(c, ONENAND_REG_INTERRUPT); + if (intr & ONENAND_INT_MASTER) + break; + } else { + /* Timeout after 20ms */ + ctrl = read_reg(c, ONENAND_REG_CTRL_STATUS); + if (ctrl & ONENAND_CTRL_ONGO) { + /* + * The operation seems to be still going + * so give it some more time. + */ + retry_cnt += 1; + if (retry_cnt < 3) { + timeout = jiffies + + msecs_to_jiffies(20); + continue; + } + } break; + } } } -- cgit v0.10.2 From ef89a8801321e0d0665c327c9d77d602ef764c87 Mon Sep 17 00:00:00 2001 From: Karl Beldan Date: Mon, 15 Sep 2008 14:37:29 +0200 Subject: [MTD] [NAND] nand_base.c: reset chip first Some chips require a RESET after power-up (e.g. Micron MT29FxGxxxxx). The first command sent is NAND_CMD_READID. Issue a NAND_CMD_RESET in nand_scan_ident before reading the device id. Tested with an MT29F4G08AAC. Signed-off-by: Karl Beldan Signed-off-by: David Woodhouse diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index d303db3..0a9c9cd 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -2318,6 +2318,12 @@ static struct nand_flash_dev *nand_get_flash_type(struct mtd_info *mtd, /* Select the device */ chip->select_chip(mtd, 0); + /* + * Reset the chip, required by some chips (e.g. Micron MT29FxGxxxxx) + * after power-up + */ + chip->cmdfunc(mtd, NAND_CMD_RESET, -1, -1); + /* Send the command for reading device ID */ chip->cmdfunc(mtd, NAND_CMD_READID, 0x00, -1); @@ -2488,6 +2494,8 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips) /* Check for a chip array */ for (i = 1; i < maxchips; i++) { chip->select_chip(mtd, i); + /* See comment in nand_get_flash_type for reset */ + chip->cmdfunc(mtd, NAND_CMD_RESET, -1, -1); /* Send the command for reading device ID */ chip->cmdfunc(mtd, NAND_CMD_READID, 0x00, -1); /* Read manufacturer and device IDs */ -- cgit v0.10.2 From b3d765f5df5707e2b3676768b6877db5d8db76a2 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 17 Sep 2008 23:12:11 +0900 Subject: sh: Fix up fpu emu build. The addition of the kprobes code pushed down a variable declaration, clean it up. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c index 862667a..35b901e 100644 --- a/arch/sh/kernel/traps_32.c +++ b/arch/sh/kernel/traps_32.c @@ -742,15 +742,13 @@ asmlinkage void do_illegal_slot_inst(unsigned long r4, unsigned long r5, struct pt_regs __regs) { struct pt_regs *regs = RELOC_HIDE(&__regs, 0); - unsigned long error_code; + unsigned long inst; struct task_struct *tsk = current; if (kprobe_handle_illslot(regs->pc) == 0) return; #ifdef CONFIG_SH_FPU_EMU - unsigned short inst = 0; - get_user(inst, (unsigned short *)regs->pc + 1); if (!do_fpu_inst(inst, regs)) { get_user(inst, (unsigned short *)regs->pc); @@ -761,12 +759,12 @@ asmlinkage void do_illegal_slot_inst(unsigned long r4, unsigned long r5, /* not a FPU inst. */ #endif - lookup_exception_vector(error_code); + lookup_exception_vector(inst); local_irq_enable(); CHK_REMOTE_DEBUG(regs); force_sig(SIGILL, tsk); - die_if_no_fixup("illegal slot instruction", regs, error_code); + die_if_no_fixup("illegal slot instruction", regs, inst); } asmlinkage void do_exception_error(unsigned long r4, unsigned long r5, -- cgit v0.10.2 From b85641bdde340f683e5baa7688832e185548c9bd Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 17 Sep 2008 23:13:27 +0900 Subject: sh: Make memory hot-add and hot-remove depend on MMU. Cleans up link numerous build issues with page migration and so on when enabled on nommu builds. Signed-off-by: Paul Mundt diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index f8e6dc5..555ec97 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -132,11 +132,11 @@ config ARCH_SELECT_MEMORY_MODEL config ARCH_ENABLE_MEMORY_HOTPLUG def_bool y - depends on SPARSEMEM + depends on SPARSEMEM && MMU config ARCH_ENABLE_MEMORY_HOTREMOVE def_bool y - depends on SPARSEMEM + depends on SPARSEMEM && MMU config ARCH_MEMORY_PROBE def_bool y -- cgit v0.10.2 From 8a80a5e9e89cf3aacf8165dd34b40c7c3fe91b4d Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 17 Sep 2008 23:14:36 +0900 Subject: sh: Fix up signal_64 conflicting handle_signal() definition. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/signal_64.c b/arch/sh/kernel/signal_64.c index 1d62dfe..37bd381 100644 --- a/arch/sh/kernel/signal_64.c +++ b/arch/sh/kernel/signal_64.c @@ -43,6 +43,10 @@ #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) +static void +handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, + sigset_t *oldset, struct pt_regs * regs); + /* * Note that 'init' is a special process: it doesn't get signals it doesn't * want to handle. Thus you cannot kill init even with a SIGKILL even by -- cgit v0.10.2 From 81b669952ed5fe0d6f65f8b9a97d1fdeac93ff10 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 17 Sep 2008 23:24:02 +0900 Subject: sh: Consolidate struct sh_cpuinfo definitions across _32/_64 split. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h index 58e2be5..693364a 100644 --- a/arch/sh/include/asm/processor.h +++ b/arch/sh/include/asm/processor.h @@ -3,6 +3,7 @@ #include #include +#include #ifndef __ASSEMBLY__ /* @@ -43,8 +44,45 @@ enum cpu_type { CPU_SH_NONE }; +/* + * TLB information structure + * + * Defined for both I and D tlb, per-processor. + */ +struct tlb_info { + unsigned long long next; + unsigned long long first; + unsigned long long last; + + unsigned int entries; + unsigned int step; + + unsigned long flags; +}; + +struct sh_cpuinfo { + unsigned int type; + int cut_major, cut_minor; + unsigned long loops_per_jiffy; + unsigned long asid_cache; + + struct cache_info icache; /* Primary I-cache */ + struct cache_info dcache; /* Primary D-cache */ + struct cache_info scache; /* Secondary cache */ + + /* TLB info */ + struct tlb_info itlb; + struct tlb_info dtlb; + + unsigned long flags; +} __attribute__ ((aligned(L1_CACHE_BYTES))); + +extern struct sh_cpuinfo cpu_data[]; +#define boot_cpu_data cpu_data[0] +#define current_cpu_data cpu_data[smp_processor_id()] +#define raw_current_cpu_data cpu_data[raw_smp_processor_id()] + /* Forward decl */ -struct sh_cpuinfo; struct seq_operations; extern struct pt_regs fake_swapper_regs; diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index 1cd3a14..a46a020 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -13,7 +13,6 @@ #include #include #include -#include #include /* @@ -27,24 +26,6 @@ #define CCN_CVR 0xff000040 #define CCN_PRR 0xff000044 -struct sh_cpuinfo { - unsigned int type; - int cut_major, cut_minor; - unsigned long loops_per_jiffy; - unsigned long asid_cache; - - struct cache_info icache; /* Primary I-cache */ - struct cache_info dcache; /* Primary D-cache */ - struct cache_info scache; /* Secondary cache */ - - unsigned long flags; -} __attribute__ ((aligned(L1_CACHE_BYTES))); - -extern struct sh_cpuinfo cpu_data[]; -#define boot_cpu_data cpu_data[0] -#define current_cpu_data cpu_data[smp_processor_id()] -#define raw_current_cpu_data cpu_data[raw_smp_processor_id()] - asmlinkage void __init sh_cpu_init(void); /* diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h index ae19839..b0b4824 100644 --- a/arch/sh/include/asm/processor_64.h +++ b/arch/sh/include/asm/processor_64.h @@ -17,7 +17,6 @@ #include #include #include -#include #include #include @@ -36,46 +35,6 @@ __asm__("gettr tr0, %1\n\t" \ : "1" (__dummy)); \ pc; }) -/* - * TLB information structure - * - * Defined for both I and D tlb, per-processor. - */ -struct tlb_info { - unsigned long long next; - unsigned long long first; - unsigned long long last; - - unsigned int entries; - unsigned int step; - - unsigned long flags; -}; - -struct sh_cpuinfo { - enum cpu_type type; - unsigned long loops_per_jiffy; - unsigned long asid_cache; - - unsigned int cpu_clock, master_clock, bus_clock, module_clock; - - /* Cache info */ - struct cache_info icache; - struct cache_info dcache; - struct cache_info scache; - - /* TLB info */ - struct tlb_info itlb; - struct tlb_info dtlb; - - unsigned long flags; -}; - -extern struct sh_cpuinfo cpu_data[]; -#define boot_cpu_data cpu_data[0] -#define current_cpu_data cpu_data[smp_processor_id()] -#define raw_current_cpu_data cpu_data[raw_smp_processor_id()] - #endif /* -- cgit v0.10.2 From b406efefd5246a67c691fd79871e65ce8f3f91ff Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 17 Sep 2008 23:24:59 +0900 Subject: sh: Fix up headers_check regression. linux/mmzone.h isn't exported, kill it off from asm/setup.h and simply deal with it in the places that have a dependency instead. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/setup.h b/arch/sh/include/asm/setup.h index 1b7856f..d450bcf 100644 --- a/arch/sh/include/asm/setup.h +++ b/arch/sh/include/asm/setup.h @@ -1,12 +1,9 @@ #ifndef _SH_SETUP_H #define _SH_SETUP_H -#include - #define COMMAND_LINE_SIZE 256 #ifdef __KERNEL__ - /* * This is set up by the setup-routine at boot-time */ -- cgit v0.10.2 From 2194478157127d52338be96ac9436dc54005816a Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 17 Sep 2008 23:26:44 +0900 Subject: sh: HAVE_IOREMAP_PROT depends on MMU. HAVE_IOREMAP_PROT enables an unconditional reference to generic_access_phys(), which remains undefined in the nommu case. As there's no point in supporting this there anyways, simply fix up the dependency. Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 18a1cc8..adef42c 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -12,7 +12,7 @@ config SUPERH select HAVE_IDE select HAVE_OPROFILE select HAVE_GENERIC_DMA_COHERENT - select HAVE_IOREMAP_PROT + select HAVE_IOREMAP_PROT if MMU help The SuperH is a RISC processor targeted for use in embedded systems and consumer electronics; it was also used in the Sega Dreamcast -- cgit v0.10.2 From 6b3141962dc82cfe1c30afdf91d564b309859cbe Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Fri, 19 Sep 2008 04:16:19 -0700 Subject: dmatest: properly handle duplicate DMA channels Update the the dmatest driver so that it handles duplicate DMA channels properly. When a DMA client is notified of an available DMA channel, it must check if it has already allocated resources for that channel. If so, it should return DMA_DUP. This can happen, for example, if a DMA driver calls dma_async_device_register() more than once. Acked-by: Haavard Skinnemoen Signed-off-by: Timur Tabi Signed-off-by: Dan Williams diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index a08d197..422500c 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -325,6 +325,11 @@ static enum dma_state_client dmatest_add_channel(struct dma_chan *chan) struct dmatest_thread *thread; unsigned int i; + /* Have we already been told about this channel? */ + list_for_each_entry(dtc, &dmatest_channels, node) + if (dtc->chan == chan) + return DMA_DUP; + dtc = kmalloc(sizeof(struct dmatest_chan), GFP_ATOMIC); if (!dtc) { pr_warning("dmatest: No memory for %s\n", chan->dev.bus_id); -- cgit v0.10.2 From 6fdb8bd47111d3f94be221082b725ec2dec1d5c7 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 19 Sep 2008 04:16:23 -0700 Subject: drivers/dma/dmatest.c: switch a GFP_ATOMIC to GFP_KERNEL It was needlessly using the unreliable GFP_ATOMIC. Cc: Timur Tabi Acked-by: Haavard Skinnemoen Signed-off-by: Andrew Morton Signed-off-by: Dan Williams diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 422500c..d1e381e 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -330,7 +330,7 @@ static enum dma_state_client dmatest_add_channel(struct dma_chan *chan) if (dtc->chan == chan) return DMA_DUP; - dtc = kmalloc(sizeof(struct dmatest_chan), GFP_ATOMIC); + dtc = kmalloc(sizeof(struct dmatest_chan), GFP_KERNEL); if (!dtc) { pr_warning("dmatest: No memory for %s\n", chan->dev.bus_id); return DMA_NAK; -- cgit v0.10.2 From b817f7e020958c8f79842076c137daa6f72eb366 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sat, 20 Sep 2008 20:16:35 +0900 Subject: sh: Disable 4kB stacks when using PAGE_SIZE_64KB. This combination triggers a divide by zero in kernel/fork.c when calculating the initial max_threads value: max_threads = mempages / (8 * THREAD_SIZE / PAGE_SIZE); Simply disable 4K stacks on 64kB PAGE_SIZE to work around this, as it's not a terribly useful combination to begin with. Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug index 4d2d102..e6d2c8b 100644 --- a/arch/sh/Kconfig.debug +++ b/arch/sh/Kconfig.debug @@ -82,7 +82,7 @@ config DEBUG_STACK_USAGE config 4KSTACKS bool "Use 4Kb for kernel stacks instead of 8Kb" - depends on DEBUG_KERNEL && (MMU || BROKEN) + depends on DEBUG_KERNEL && (MMU || BROKEN) && !PAGE_SIZE_64KB help If you say Y here the kernel will use a 4Kb stacksize for the kernel stack attached to each process/thread. This facilitates -- cgit v0.10.2 From c15c5f8c2bf0b00d036c5c6b67264764a6e5dffc Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sat, 20 Sep 2008 20:21:33 +0900 Subject: sh: Support kernel stacks smaller than a page. This follows the powerpc commit f6a616800e68b61807d0f7bb0d5dc70665ef8046 '[POWERPC] Fix kernel stack allocation alignment'. SH has traditionally forced the thread order to be relative to the page size, so there were never any situations where the same bug was triggered by slub. Regardless, the usage of > 8kB stacks for the larger page sizes is overkill, so we switch to using slab allocations there, as per the powerpc change. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h index 0a894ca..f09ac48 100644 --- a/arch/sh/include/asm/thread_info.h +++ b/arch/sh/include/asm/thread_info.h @@ -33,20 +33,12 @@ struct thread_info { #define PREEMPT_ACTIVE 0x10000000 #if defined(CONFIG_4KSTACKS) -#define THREAD_SIZE_ORDER (0) -#elif defined(CONFIG_PAGE_SIZE_4KB) -#define THREAD_SIZE_ORDER (1) -#elif defined(CONFIG_PAGE_SIZE_8KB) -#define THREAD_SIZE_ORDER (1) -#elif defined(CONFIG_PAGE_SIZE_16KB) -#define THREAD_SIZE_ORDER (0) -#elif defined(CONFIG_PAGE_SIZE_64KB) -#define THREAD_SIZE_ORDER (0) +#define THREAD_SHIFT 12 #else -#error "Unknown thread size" +#define THREAD_SHIFT 13 #endif -#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) +#define THREAD_SIZE (1 << THREAD_SHIFT) #define STACK_WARN (THREAD_SIZE >> 3) /* @@ -94,15 +86,19 @@ static inline struct thread_info *current_thread_info(void) return ti; } +/* thread information allocation */ +#if THREAD_SHIFT >= PAGE_SHIFT + +#define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT) + +#else /* THREAD_SHIFT < PAGE_SHIFT */ + #define __HAVE_ARCH_THREAD_INFO_ALLOCATOR -/* thread information allocation */ -#ifdef CONFIG_DEBUG_STACK_USAGE -#define alloc_thread_info(ti) kzalloc(THREAD_SIZE, GFP_KERNEL) -#else -#define alloc_thread_info(ti) kmalloc(THREAD_SIZE, GFP_KERNEL) -#endif -#define free_thread_info(ti) kfree(ti) +extern struct thread_info *alloc_thread_info(struct task_struct *tsk); +extern void free_thread_info(struct thread_info *ti); + +#endif /* THREAD_SHIFT < PAGE_SHIFT */ #endif /* __ASSEMBLY__ */ diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 31211bf..2a53943 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -265,6 +265,35 @@ void free_initrd_mem(unsigned long start, unsigned long end) } #endif +#if THREAD_SHIFT < PAGE_SHIFT +static struct kmem_cache *thread_info_cache; + +struct thread_info *alloc_thread_info(struct task_struct *tsk) +{ + struct thread_info *ti; + + ti = kmem_cache_alloc(thread_info_cache, GFP_KERNEL); + if (unlikely(ti == NULL)) + return NULL; +#ifdef CONFIG_DEBUG_STACK_USAGE + memset(ti, 0, THREAD_SIZE); +#endif + return ti; +} + +void free_thread_info(struct thread_info *ti) +{ + kmem_cache_free(thread_info_cache, ti); +} + +void thread_info_cache_init(void) +{ + thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE, + THREAD_SIZE, 0, NULL); + BUG_ON(thread_info_cache == NULL); +} +#endif /* THREAD_SHIFT < PAGE_SHIFT */ + #ifdef CONFIG_MEMORY_HOTPLUG int arch_add_memory(int nid, u64 start, u64 size) { -- cgit v0.10.2 From 837c946aad480d4773619707f115ed4c15738f77 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sun, 21 Sep 2008 10:24:18 +0900 Subject: sh: Copy in asm/sizes.h helper from ARM. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/sizes.h b/arch/sh/include/asm/sizes.h new file mode 100644 index 0000000..503843d --- /dev/null +++ b/arch/sh/include/asm/sizes.h @@ -0,0 +1,56 @@ +/* + * 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 + */ +/* DO NOT EDIT!! - this file automatically generated + * from .s file by awk -f s2h.awk + */ +/* Size definitions + * Copyright (C) ARM Limited 1998. All rights reserved. + */ + +#ifndef __sizes_h +#define __sizes_h 1 + +/* handy sizes */ +#define SZ_16 0x00000010 +#define SZ_256 0x00000100 +#define SZ_512 0x00000200 + +#define SZ_1K 0x00000400 +#define SZ_4K 0x00001000 +#define SZ_8K 0x00002000 +#define SZ_16K 0x00004000 +#define SZ_64K 0x00010000 +#define SZ_128K 0x00020000 +#define SZ_256K 0x00040000 +#define SZ_512K 0x00080000 + +#define SZ_1M 0x00100000 +#define SZ_2M 0x00200000 +#define SZ_4M 0x00400000 +#define SZ_8M 0x00800000 +#define SZ_16M 0x01000000 +#define SZ_32M 0x02000000 +#define SZ_64M 0x04000000 +#define SZ_128M 0x08000000 +#define SZ_256M 0x10000000 +#define SZ_512M 0x20000000 + +#define SZ_1G 0x40000000 +#define SZ_2G 0x80000000 + +#endif + +/* END */ -- cgit v0.10.2 From d3ea00a36da2e715217f0e31944dd220deefa38c Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sun, 21 Sep 2008 10:31:57 +0900 Subject: sh: Add a few more definitions to asm/sizes.h. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/sizes.h b/arch/sh/include/asm/sizes.h index 503843d..3a1fb97 100644 --- a/arch/sh/include/asm/sizes.h +++ b/arch/sh/include/asm/sizes.h @@ -25,6 +25,9 @@ /* handy sizes */ #define SZ_16 0x00000010 +#define SZ_32 0x00000020 +#define SZ_64 0x00000040 +#define SZ_128 0x00000080 #define SZ_256 0x00000100 #define SZ_512 0x00000200 @@ -32,6 +35,7 @@ #define SZ_4K 0x00001000 #define SZ_8K 0x00002000 #define SZ_16K 0x00004000 +#define SZ_32K 0x00008000 #define SZ_64K 0x00010000 #define SZ_128K 0x00020000 #define SZ_256K 0x00040000 @@ -42,6 +46,7 @@ #define SZ_4M 0x00400000 #define SZ_8M 0x00800000 #define SZ_16M 0x01000000 +#define SZ_26M 0x01a00000 #define SZ_32M 0x02000000 #define SZ_64M 0x04000000 #define SZ_128M 0x08000000 -- cgit v0.10.2 From 347cd34f4b32be30d2a6d92fe4d6eac04b00a637 Mon Sep 17 00:00:00 2001 From: Luca Santini Date: Sun, 21 Sep 2008 10:32:29 +0900 Subject: sh: edosk7760: Correct size of bootloader flash partition. This is 256K instead of 1M. [ Converted to use asm/sizes.h. -- PFM ] Signed-off-by: Luca Santini Signed-off-by: Paul Mundt diff --git a/arch/sh/boards/board-edosk7760.c b/arch/sh/boards/board-edosk7760.c index 4890ba7..35dc099 100644 --- a/arch/sh/boards/board-edosk7760.c +++ b/arch/sh/boards/board-edosk7760.c @@ -30,6 +30,7 @@ #include #include #include +#include /* Bus state controller registers for CS4 area */ #define BSC_CS4BCR 0xA4FD0010 @@ -46,16 +47,16 @@ static struct mtd_partition edosk7760_nor_flash_partitions[] = { { .name = "bootloader", .offset = 0, - .size = (1 * 1024 * 1024), /*1MB*/ + .size = SZ_256K, .mask_flags = MTD_WRITEABLE, /* Read-only */ }, { .name = "kernel", .offset = MTDPART_OFS_APPEND, - .size = (2 * 1024 * 1024), /*2MB*/ + .size = SZ_2M, }, { .name = "fs", .offset = MTDPART_OFS_APPEND, - .size = (26 * 1024 * 1024), + .size = SZ_26M, }, { .name = "other", .offset = MTDPART_OFS_APPEND, @@ -73,7 +74,7 @@ static struct resource edosk7760_nor_flash_resources[] = { [0] = { .name = "NOR Flash", .start = 0x00000000, - .end = (32 * 1024 * 1024) -1, /* 32MB*/ + .end = 0x00000000 + SZ_32M - 1, .flags = IORESOURCE_MEM, } }; @@ -145,7 +146,7 @@ static struct smc91x_platdata smc91x_info = { static struct resource smc91x_res[] = { [0] = { .start = SMC_IOADDR, - .end = SMC_IOADDR + 0x1f, + .end = SMC_IOADDR + SZ_32 - 1, .flags = IORESOURCE_MEM, }, [1] = { -- cgit v0.10.2 From 4c59e2942e92d2d776bcd038604a5c3c1d56d3ac Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sun, 21 Sep 2008 12:00:23 +0900 Subject: sh: Move lookup_exception_vector() out to asm/system_32.h. There are other places where we want to have access to the trap/exception number, so move out the lookup_exception_vector() helper. While we're at it, refactor it slightly to return the vector instead. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/system_32.h b/arch/sh/include/asm/system_32.h index f7f1056..a726d5d 100644 --- a/arch/sh/include/asm/system_32.h +++ b/arch/sh/include/asm/system_32.h @@ -97,6 +97,31 @@ do { \ : "=&r" (__dummy)); \ } while (0) +#ifdef CONFIG_CPU_HAS_SR_RB +#define lookup_exception_vector() \ +({ \ + unsigned long _vec; \ + \ + __asm__ __volatile__ ( \ + "stc r2_bank, %0\n\t" \ + : "=r" (_vec) \ + ); \ + \ + _vec; \ +}) +#else +#define lookup_exception_vector() \ +({ \ + unsigned long _vec; \ + __asm__ __volatile__ ( \ + "mov r4, %0\n\t" \ + : "=r" (_vec) \ + ); \ + \ + _vec; \ +}) +#endif + int handle_unaligned_access(opcode_t instruction, struct pt_regs *regs, struct mem_access *ma); diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c index 35b901e..b359b08 100644 --- a/arch/sh/kernel/traps_32.c +++ b/arch/sh/kernel/traps_32.c @@ -514,14 +514,6 @@ int handle_unaligned_access(opcode_t instruction, struct pt_regs *regs, return ret; } -#ifdef CONFIG_CPU_HAS_SR_RB -#define lookup_exception_vector(x) \ - __asm__ __volatile__ ("stc r2_bank, %0\n\t" : "=r" ((x))) -#else -#define lookup_exception_vector(x) \ - __asm__ __volatile__ ("mov r4, %0\n\t" : "=r" ((x))) -#endif - /* * Handle various address error exceptions: * - instruction address error: @@ -545,7 +537,7 @@ asmlinkage void do_address_error(struct pt_regs *regs, /* Intentional ifdef */ #ifdef CONFIG_CPU_HAS_SR_RB - lookup_exception_vector(error_code); + error_code = lookup_exception_vector(); #endif oldfs = get_fs(); @@ -686,7 +678,7 @@ asmlinkage void do_reserved_inst(unsigned long r4, unsigned long r5, } #endif - lookup_exception_vector(error_code); + error_code = lookup_exception_vector(); local_irq_enable(); CHK_REMOTE_DEBUG(regs); @@ -759,7 +751,7 @@ asmlinkage void do_illegal_slot_inst(unsigned long r4, unsigned long r5, /* not a FPU inst. */ #endif - lookup_exception_vector(inst); + inst = lookup_exception_vector(); local_irq_enable(); CHK_REMOTE_DEBUG(regs); @@ -774,7 +766,7 @@ asmlinkage void do_exception_error(unsigned long r4, unsigned long r5, struct pt_regs *regs = RELOC_HIDE(&__regs, 0); long ex; - lookup_exception_vector(ex); + ex = lookup_exception_vector(); die_if_kernel("exception", regs, ex); } -- cgit v0.10.2 From 887f1ae3bc1701604a7b5ef145e1021072675444 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sun, 21 Sep 2008 12:06:43 +0900 Subject: sh: Look up the trap vector for the page fault notifier. Signed-off-by: Paul Mundt diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c index 659811c..ef01f45 100644 --- a/arch/sh/mm/fault_32.c +++ b/arch/sh/mm/fault_32.c @@ -21,26 +21,21 @@ #include #include -#ifdef CONFIG_KPROBES static inline int notify_page_fault(struct pt_regs *regs, int trap) { int ret = 0; +#ifdef CONFIG_KPROBES if (!user_mode(regs)) { preempt_disable(); if (kprobe_running() && kprobe_fault_handler(regs, trap)) ret = 1; preempt_enable(); } +#endif return ret; } -#else -static inline int notify_page_fault(struct pt_regs *regs, int trap) -{ - return 0; -} -#endif /* * This routine handles page faults. It determines the address, @@ -58,7 +53,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, int fault; siginfo_t info; - if (notify_page_fault(regs, writeaccess)) + if (notify_page_fault(regs, lookup_exception_vector())) return; #ifdef CONFIG_SH_KGDB @@ -293,7 +288,7 @@ asmlinkage int __kprobes __do_page_fault(struct pt_regs *regs, pte_t *pte; pte_t entry; - if (notify_page_fault(regs, writeaccess)) + if (notify_page_fault(regs, lookup_exception_vector())) return 0; #ifdef CONFIG_SH_KGDB -- cgit v0.10.2 From 8f2baee28093ea77c7cc8da45049fd94cc76998e Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sun, 21 Sep 2008 12:11:25 +0900 Subject: sh: Kill off duplicate page fault notifiers in slow path. We already have hooks in place in the __do_page_fault() fast-path, so kill them off in the slow path. Signed-off-by: Paul Mundt diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c index ef01f45..08a08ea 100644 --- a/arch/sh/mm/fault_32.c +++ b/arch/sh/mm/fault_32.c @@ -53,13 +53,10 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, int fault; siginfo_t info; - if (notify_page_fault(regs, lookup_exception_vector())) - return; - -#ifdef CONFIG_SH_KGDB - if (kgdb_nofault && kgdb_bus_err_hook) - kgdb_bus_err_hook(); -#endif + /* + * We don't bother with any notifier callbacks here, as they are + * all handled through the __do_page_fault() fast-path. + */ tsk = current; si_code = SEGV_MAPERR; -- cgit v0.10.2 From 3d58695edbfac785161bf282dc11fd42a483d6c9 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sun, 21 Sep 2008 13:56:39 +0900 Subject: sh: Trivial trace_mark() instrumentation for core events. This implements a few trace points across events that are deemed interesting. This implements a number of trace points: - The page fault handler / TLB miss - IPC calls - Kernel thread creation The original LTTng patch had the slow-path instrumented, which fails to account for the vast majority of events. In general placing this in the fast-path is not a huge performance hit, as we don't take page faults for kernel addresses. The other bits of interest are some of the other trap handlers, as well as the syscall entry/exit (which is better off being handled through the tracehook API). Most of the other trap handlers are corner cases where alternate means of notification exist, so there is little value in placing extra trace points in these locations. Based on top of the points provided both by the LTTng instrumentation patch as well as the patch shipping in the ST-Linux tree, albeit in a stripped down form. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 914e543..7b013aa 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -169,6 +169,7 @@ __asm__(".align 5\n" int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) { struct pt_regs regs; + int pid; memset(®s, 0, sizeof(regs)); regs.regs[4] = (unsigned long)arg; @@ -178,8 +179,12 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) regs.sr = (1 << 30); /* Ok, create the new process.. */ - return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, - ®s, 0, NULL, NULL); + pid = do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, + ®s, 0, NULL, NULL); + + trace_mark(kernel_arch_kthread_create, "pid %d fn %p", pid, fn); + + return pid; } /* diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c index d0dddc4..b7aa092 100644 --- a/arch/sh/kernel/process_64.c +++ b/arch/sh/kernel/process_64.c @@ -396,6 +396,7 @@ ATTRIB_NORET void kernel_thread_helper(void *arg, int (*fn)(void *)) int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) { struct pt_regs regs; + int pid; memset(®s, 0, sizeof(regs)); regs.regs[2] = (unsigned long)arg; @@ -404,8 +405,13 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) regs.pc = (unsigned long)kernel_thread_helper; regs.sr = (1 << 30); - return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, - ®s, 0, NULL, NULL); + /* Ok, create the new process.. */ + pid = do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, + ®s, 0, NULL, NULL); + + trace_mark(kernel_arch_kthread_create, "pid %d fn %p", pid, fn); + + return pid; } /* diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c index 0dfb889..38f098c 100644 --- a/arch/sh/kernel/sys_sh.c +++ b/arch/sh/kernel/sys_sh.c @@ -171,6 +171,8 @@ asmlinkage int sys_ipc(uint call, int first, int second, version = call >> 16; /* hack for backward compatibility */ call &= 0xffff; + trace_mark(kernel_arch_ipc_call, "call %u first %d", call, first); + if (call <= SEMTIMEDOP) switch (call) { case SEMOP: diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c index 08a08ea..898d477 100644 --- a/arch/sh/mm/fault_32.c +++ b/arch/sh/mm/fault_32.c @@ -15,28 +15,13 @@ #include #include #include +#include #include #include #include #include #include -static inline int notify_page_fault(struct pt_regs *regs, int trap) -{ - int ret = 0; - -#ifdef CONFIG_KPROBES - if (!user_mode(regs)) { - preempt_disable(); - if (kprobe_running() && kprobe_fault_handler(regs, trap)) - ret = 1; - preempt_enable(); - } -#endif - - return ret; -} - /* * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate @@ -261,6 +246,25 @@ do_sigbus: goto no_context; } +static inline int notify_page_fault(struct pt_regs *regs, int trap) +{ + int ret = 0; + + trace_mark(kernel_arch_trap_entry, "trap_id %d ip #p%ld", + trap >> 5, instruction_pointer(regs)); + +#ifdef CONFIG_KPROBES + if (!user_mode(regs)) { + preempt_disable(); + if (kprobe_running() && kprobe_fault_handler(regs, trap)) + ret = 1; + preempt_enable(); + } +#endif + + return ret; +} + #ifdef CONFIG_SH_STORE_QUEUES /* * This is a special case for the SH-4 store queues, as pages for this @@ -284,15 +288,18 @@ asmlinkage int __kprobes __do_page_fault(struct pt_regs *regs, pmd_t *pmd; pte_t *pte; pte_t entry; + int ret = 0; if (notify_page_fault(regs, lookup_exception_vector())) - return 0; + goto out; #ifdef CONFIG_SH_KGDB if (kgdb_nofault && kgdb_bus_err_hook) kgdb_bus_err_hook(); #endif + ret = 1; + /* * We don't take page faults for P1, P2, and parts of P4, these * are always mapped, whether it be due to legacy behaviour in @@ -302,24 +309,23 @@ asmlinkage int __kprobes __do_page_fault(struct pt_regs *regs, pgd = pgd_offset_k(address); } else { if (unlikely(address >= TASK_SIZE || !current->mm)) - return 1; + goto out; pgd = pgd_offset(current->mm, address); } pud = pud_offset(pgd, address); if (pud_none_or_clear_bad(pud)) - return 1; + goto out; pmd = pmd_offset(pud, address); if (pmd_none_or_clear_bad(pmd)) - return 1; - + goto out; pte = pte_offset_kernel(pmd, address); entry = *pte; if (unlikely(pte_none(entry) || pte_not_present(entry))) - return 1; + goto out; if (unlikely(writeaccess && !pte_write(entry))) - return 1; + goto out; if (writeaccess) entry = pte_mkdirty(entry); @@ -336,5 +342,8 @@ asmlinkage int __kprobes __do_page_fault(struct pt_regs *regs, set_pte(pte, entry); update_mmu_cache(NULL, address, entry); - return 0; + ret = 0; +out: + trace_mark(kernel_arch_trap_exit, MARK_NOARGS); + return ret; } -- cgit v0.10.2 From 9d2b1f81dd93b198e12bca8120afec4a7b609b06 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sun, 21 Sep 2008 16:43:45 +0900 Subject: sh: ftrace support. This adds support for ftrace to SH. This only includes CONFIG_FTRACE, and does not handle dynamic ftrace presently. Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index adef42c..38a5a9e 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -24,6 +24,7 @@ config SUPERH32 select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_ARCH_TRACEHOOK if !SH_FPU + select HAVE_FTRACE config SUPERH64 def_bool y if CPU_SH5 diff --git a/arch/sh/boot/compressed/Makefile_32 b/arch/sh/boot/compressed/Makefile_32 index 47685f6..301e6d5 100644 --- a/arch/sh/boot/compressed/Makefile_32 +++ b/arch/sh/boot/compressed/Makefile_32 @@ -23,6 +23,11 @@ IMAGE_OFFSET := $(shell /bin/bash -c 'printf "0x%08x" \ LIBGCC := $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name) +ifeq ($(CONFIG_FTRACE),y) +ORIG_CFLAGS := $(KBUILD_CFLAGS) +KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS)) +endif + LDFLAGS_vmlinux := -Ttext $(IMAGE_OFFSET) -e startup -T $(obj)/../../kernel/vmlinux.lds $(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(LIBGCC) FORCE diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S index efbb426..1a5cf9d 100644 --- a/arch/sh/kernel/entry-common.S +++ b/arch/sh/kernel/entry-common.S @@ -371,3 +371,47 @@ syscall_exit: #endif 7: .long do_syscall_trace_enter 8: .long do_syscall_trace_leave + +#ifdef CONFIG_FTRACE + .align 2 + .globl _mcount + .type _mcount,@function + .globl mcount + .type mcount,@function +_mcount: +mcount: + mov.l r4, @-r15 + mov.l r5, @-r15 + mov.l r6, @-r15 + mov.l r7, @-r15 + sts.l pr, @-r15 + + mov.l @(20,r15),r4 + sts pr, r5 + + mov.l 1f, r6 + mov.l ftrace_stub, r7 + cmp/eq r6, r7 + bt skip_trace + + mov.l @r6, r6 + jsr @r6 + nop + +skip_trace: + + lds.l @r15+, pr + mov.l @r15+, r7 + mov.l @r15+, r6 + mov.l @r15+, r5 + rts + mov.l @r15+, r4 + + .align 2 +1: .long ftrace_trace_function + + .globl ftrace_stub +ftrace_stub: + rts + nop +#endif /* CONFIG_FTRACE */ diff --git a/arch/sh/kernel/sh_ksyms_32.c b/arch/sh/kernel/sh_ksyms_32.c index 6e1b1c2..d917b7b 100644 --- a/arch/sh/kernel/sh_ksyms_32.c +++ b/arch/sh/kernel/sh_ksyms_32.c @@ -16,6 +16,7 @@ #include #include #include +#include extern int dump_fpu(struct pt_regs *, elf_fpregset_t *); extern struct hw_interrupt_type no_irq_type; @@ -133,6 +134,9 @@ EXPORT_SYMBOL(__flush_purge_region); EXPORT_SYMBOL(clear_user_page); #endif +#ifdef CONFIG_FTRACE +EXPORT_SYMBOL(mcount); +#endif EXPORT_SYMBOL(csum_partial); EXPORT_SYMBOL(csum_partial_copy_generic); #ifdef CONFIG_IPV6 -- cgit v0.10.2 From 6902aa84f565153ce05f3438ecb8e445d4f468d8 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sun, 21 Sep 2008 17:14:42 +0900 Subject: doc: Add remaining SH parameters to kernel-parameters.txt. Signed-off-by: Paul Mundt diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 1150444..abeff96 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -796,6 +796,8 @@ and is between 256 and 4096 characters. It is defined in the file Defaults to the default architecture's huge page size if not specified. + hlt [BUGS=ARM,SH] + i8042.direct [HW] Put keyboard port into non-translated mode i8042.dumbkbd [HW] Pretend that controller can only read data from keyboard and cannot control its state @@ -1206,6 +1208,10 @@ and is between 256 and 4096 characters. It is defined in the file mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel memory. + memchunk=nn[KMG] + [KNL,SH] Allow user to override the default size for + per-device physically contiguous DMA buffers. + memmap=exactmap [KNL,X86-32,X86_64] Enable setting of an exact E820 memory map, as specified by the user. Such memmap=exactmap lines can be constructed based on @@ -1365,6 +1371,8 @@ and is between 256 and 4096 characters. It is defined in the file nodisconnect [HW,SCSI,M68K] Disables SCSI disconnects. + nodsp [SH] Disable hardware DSP at boot time. + noefi [X86-32,X86-64] Disable EFI runtime services support. noexec [IA-64] @@ -1381,13 +1389,15 @@ and is between 256 and 4096 characters. It is defined in the file noexec32=off: disable non-executable mappings read implies executable mappings + nofpu [SH] Disable hardware FPU at boot time. + nofxsr [BUGS=X86-32] Disables x86 floating point extended register save and restore. The kernel will only save legacy floating-point registers on task switch. noclflush [BUGS=X86] Don't use the CLFLUSH instruction - nohlt [BUGS=ARM] + nohlt [BUGS=ARM,SH] no-hlt [BUGS=X86-32] Tells the kernel that the hlt instruction doesn't work correctly and not to -- cgit v0.10.2 From 4b4cf7595a8bce9b4dd64c241a8cb7336ecb9489 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sun, 21 Sep 2008 17:17:53 +0900 Subject: sh: Add missing asm/ftrace.h. This was missed with the ftrace support commit.. check it in now. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/ftrace.h b/arch/sh/include/asm/ftrace.h new file mode 100644 index 0000000..3aed362 --- /dev/null +++ b/arch/sh/include/asm/ftrace.h @@ -0,0 +1,8 @@ +#ifndef __ASM_SH_FTRACE_H +#define __ASM_SH_FTRACE_H + +#ifndef __ASSEMBLY__ +extern void mcount(void); +#endif + +#endif /* __ASM_SH_FTRACE_H */ -- cgit v0.10.2 From e7ab3cd251926d57ee11d7d320e8fb42c882ad22 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Sun, 21 Sep 2008 19:04:55 +0900 Subject: sh: Add FPU registers to regset interface. Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 38a5a9e..71be7ff 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -23,7 +23,7 @@ config SUPERH32 def_bool !SUPERH64 select HAVE_KPROBES select HAVE_KRETPROBES - select HAVE_ARCH_TRACEHOOK if !SH_FPU + select HAVE_ARCH_TRACEHOOK select HAVE_FTRACE config SUPERH64 diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h index 6b2cec8..4da3a0b 100644 --- a/arch/sh/include/asm/elf.h +++ b/arch/sh/include/asm/elf.h @@ -108,10 +108,10 @@ typedef struct user_fpu_struct elf_fpregset_t; #define elf_check_fdpic(x) ((x)->e_flags & EF_SH_FDPIC) #define elf_check_const_displacement(x) ((x)->e_flags & EF_SH_PIC) -#if defined(CONFIG_SUPERH32) && !defined(CONFIG_SH_FPU) +#ifdef CONFIG_SUPERH32 /* - * Enable dump using regset for general purpose registers, use this as - * the default once the FPU registers are moved over also. + * Enable dump using regset. + * This covers all of general/DSP/FPU regs. */ #define CORE_DUMP_USE_REGSET #endif diff --git a/arch/sh/include/asm/fpu.h b/arch/sh/include/asm/fpu.h index 91462fe..1d3aee0 100644 --- a/arch/sh/include/asm/fpu.h +++ b/arch/sh/include/asm/fpu.h @@ -30,8 +30,15 @@ static inline void save_fpu(struct task_struct *tsk, struct pt_regs *regs) } #endif +struct user_regset; + extern int do_fpu_inst(unsigned short, struct pt_regs *); +extern int fpregs_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf); + static inline void unlazy_fpu(struct task_struct *tsk, struct pt_regs *regs) { preempt_disable(); @@ -50,6 +57,18 @@ static inline void clear_fpu(struct task_struct *tsk, struct pt_regs *regs) preempt_enable(); } +static inline int init_fpu(struct task_struct *tsk) +{ + if (tsk_used_math(tsk)) { + if ((boot_cpu_data.flags & CPU_HAS_FPU) && tsk == current) + unlazy_fpu(tsk, task_pt_regs(tsk)); + return 0; + } + + set_stopped_child_used_math(tsk); + return 0; +} + #endif /* __ASSEMBLY__ */ #endif /* __ASM_SH_FPU_H */ diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 7b013aa..b965f02 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -7,7 +7,11 @@ * * SuperH version: Copyright (C) 1999, 2000 Niibe Yutaka & Kaz Kojima * Copyright (C) 2006 Lineo Solutions Inc. support SH4A UBC - * Copyright (C) 2002 - 2007 Paul Mundt + * Copyright (C) 2002 - 2008 Paul Mundt + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. */ #include #include @@ -222,10 +226,10 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) struct task_struct *tsk = current; fpvalid = !!tsk_used_math(tsk); - if (fpvalid) { - unlazy_fpu(tsk, regs); - memcpy(fpu, &tsk->thread.fpu.hard, sizeof(*fpu)); - } + if (fpvalid) + fpvalid = !fpregs_get(tsk, NULL, 0, + sizeof(struct user_fpu_struct), + fpu, NULL); #endif return fpvalid; diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c index 0f44f2b..29ca09d 100644 --- a/arch/sh/kernel/ptrace_32.c +++ b/arch/sh/kernel/ptrace_32.c @@ -32,6 +32,7 @@ #include #include #include +#include /* * This routine will get a word off of the process kernel stack. @@ -145,6 +146,54 @@ static int genregs_set(struct task_struct *target, return ret; } +#ifdef CONFIG_SH_FPU +int fpregs_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + ret = init_fpu(target); + if (ret) + return ret; + + if ((boot_cpu_data.flags & CPU_HAS_FPU)) + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.fpu.hard, 0, -1); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.fpu.soft, 0, -1); +} + +static int fpregs_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + ret = init_fpu(target); + if (ret) + return ret; + + set_stopped_child_used_math(target); + + if ((boot_cpu_data.flags & CPU_HAS_FPU)) + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.fpu.hard, 0, -1); + + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.fpu.soft, 0, -1); +} + +static int fpregs_active(struct task_struct *target, + const struct user_regset *regset) +{ + return tsk_used_math(target) ? regset->n : 0; +} +#endif + #ifdef CONFIG_SH_DSP static int dspregs_get(struct task_struct *target, const struct user_regset *regset, @@ -194,6 +243,9 @@ static int dspregs_active(struct task_struct *target, */ enum sh_regset { REGSET_GENERAL, +#ifdef CONFIG_SH_FPU + REGSET_FPU, +#endif #ifdef CONFIG_SH_DSP REGSET_DSP, #endif @@ -214,6 +266,18 @@ static const struct user_regset sh_regsets[] = { .set = genregs_set, }, +#ifdef CONFIG_SH_FPU + [REGSET_FPU] = { + .core_note_type = NT_PRFPREG, + .n = sizeof(struct user_fpu_struct) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .get = fpregs_get, + .set = fpregs_set, + .active = fpregs_active, + }, +#endif + #ifdef CONFIG_SH_DSP [REGSET_DSP] = { .n = sizeof(struct pt_dspregs) / sizeof(long), @@ -304,6 +368,18 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) REGSET_GENERAL, 0, sizeof(struct pt_regs), (const void __user *)data); +#ifdef CONFIG_SH_FPU + case PTRACE_GETFPREGS: + return copy_regset_to_user(child, &user_sh_native_view, + REGSET_FPU, + 0, sizeof(struct user_fpu_struct), + (void __user *)data); + case PTRACE_SETFPREGS: + return copy_regset_from_user(child, &user_sh_native_view, + REGSET_FPU, + 0, sizeof(struct user_fpu_struct), + (const void __user *)data); +#endif #ifdef CONFIG_SH_DSP case PTRACE_GETDSPREGS: return copy_regset_to_user(child, &user_sh_native_view, -- cgit v0.10.2 From d7cfb60c5cf904ecf1e0ae23ec178175b86f0d4a Mon Sep 17 00:00:00 2001 From: Mark McLoughlin Date: Fri, 19 Sep 2008 13:13:44 +0100 Subject: hrtimer: remove hrtimer_clock_base::get_softirq_time() Peter Zijlstra noticed this 8 months ago and I just noticed it again. hrtimer_clock_base::get_softirq_time() is currently unused in the entire tree. In fact, looking at the logs, it appears as if it was never used. Remove it. Signed-off-by: Mark McLoughlin Signed-off-by: Ingo Molnar diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 6d93dce..1b079bd 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -145,7 +145,6 @@ struct hrtimer_sleeper { * @first: pointer to the timer node which expires first * @resolution: the resolution of the clock, in nanoseconds * @get_time: function to retrieve the current time of the clock - * @get_softirq_time: function to retrieve the current time from the softirq * @softirq_time: the time when running the hrtimer queue in the softirq * @offset: offset of this clock to the monotonic base * @reprogram: function to reprogram the timer event @@ -157,7 +156,6 @@ struct hrtimer_clock_base { struct rb_node *first; ktime_t resolution; ktime_t (*get_time)(void); - ktime_t (*get_softirq_time)(void); ktime_t softirq_time; #ifdef CONFIG_HIGH_RES_TIMERS ktime_t offset; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 03ea137..4d761d5 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1401,9 +1401,7 @@ void hrtimer_run_queues(void) if (!base->first) continue; - if (base->get_softirq_time) - base->softirq_time = base->get_softirq_time(); - else if (gettime) { + if (gettime) { hrtimer_get_softirq_time(cpu_base); gettime = 0; } -- cgit v0.10.2 From b91c4996df56fcd201f85c392a1de7bc3f6641f5 Mon Sep 17 00:00:00 2001 From: Mark McLoughlin Date: Fri, 19 Sep 2008 13:13:48 +0100 Subject: hrtimer: remove hrtimer_clock_base::reprogram() hrtimer_clock_base::reprogram() also appears to never have been used, so remove it. Signed-off-by: Mark McLoughlin Signed-off-by: Ingo Molnar diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 1b079bd..68b0196 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -147,7 +147,6 @@ struct hrtimer_sleeper { * @get_time: function to retrieve the current time of the clock * @softirq_time: the time when running the hrtimer queue in the softirq * @offset: offset of this clock to the monotonic base - * @reprogram: function to reprogram the timer event */ struct hrtimer_clock_base { struct hrtimer_cpu_base *cpu_base; @@ -159,9 +158,6 @@ struct hrtimer_clock_base { ktime_t softirq_time; #ifdef CONFIG_HIGH_RES_TIMERS ktime_t offset; - int (*reprogram)(struct hrtimer *t, - struct hrtimer_clock_base *b, - ktime_t n); #endif }; -- cgit v0.10.2 From bb34d92f643086d546b49cef680f6f305ed84414 Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Fri, 12 Sep 2008 09:54:39 -0700 Subject: timers: fix itimer/many thread hang, v2 This is the second resubmission of the posix timer rework patch, posted a few days ago. This includes the changes from the previous resubmittion, which addressed Oleg Nesterov's comments, removing the RCU stuff from the patch and un-inlining the thread_group_cputime() function for SMP. In addition, per Ingo Molnar it simplifies the UP code, consolidating much of it with the SMP version and depending on lower-level SMP/UP handling to take care of the differences. It also cleans up some UP compile errors, moves the scheduler stats-related macros into kernel/sched_stats.h, cleans up a merge error in kernel/fork.c and has a few other minor fixes and cleanups as suggested by Oleg and Ingo. Thanks for the review, guys. Signed-off-by: Frank Mayhar Cc: Roland McGrath Cc: Alexey Dobriyan Cc: Andrew Morton Signed-off-by: Ingo Molnar diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index cf9f40a..cac3750 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -52,6 +52,7 @@ static inline int kstat_irqs(int irq) return sum; } +extern unsigned long long task_delta_exec(struct task_struct *); extern void account_user_time(struct task_struct *, cputime_t); extern void account_user_time_scaled(struct task_struct *, cputime_t); extern void account_system_time(struct task_struct *, int, cputime_t); diff --git a/include/linux/sched.h b/include/linux/sched.h index 7ce8d4e..b982fb4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -454,15 +454,9 @@ struct task_cputime { * This structure contains the version of task_cputime, above, that is * used for thread group CPU clock calculations. */ -#ifdef CONFIG_SMP struct thread_group_cputime { struct task_cputime *totals; }; -#else -struct thread_group_cputime { - struct task_cputime totals; -}; -#endif /* * NOTE! "signal_struct" does not have it's own @@ -2124,193 +2118,26 @@ static inline int spin_needbreak(spinlock_t *lock) /* * Thread group CPU time accounting. */ -#ifdef CONFIG_SMP -extern int thread_group_cputime_alloc_smp(struct task_struct *); -extern void thread_group_cputime_smp(struct task_struct *, struct task_cputime *); +extern int thread_group_cputime_alloc(struct task_struct *); +extern void thread_group_cputime(struct task_struct *, struct task_cputime *); static inline void thread_group_cputime_init(struct signal_struct *sig) { sig->cputime.totals = NULL; } -static inline int thread_group_cputime_clone_thread(struct task_struct *curr, - struct task_struct *new) +static inline int thread_group_cputime_clone_thread(struct task_struct *curr) { if (curr->signal->cputime.totals) return 0; - return thread_group_cputime_alloc_smp(curr); + return thread_group_cputime_alloc(curr); } -static inline void thread_group_cputime_free(struct signal_struct *sig) -{ - free_percpu(sig->cputime.totals); -} - -/** - * thread_group_cputime - Sum the thread group time fields across all CPUs. - * - * This is a wrapper for the real routine, thread_group_cputime_smp(). See - * that routine for details. - */ -static inline void thread_group_cputime( - struct task_struct *tsk, - struct task_cputime *times) -{ - thread_group_cputime_smp(tsk, times); -} - -/** - * thread_group_cputime_account_user - Maintain utime for a thread group. - * - * @tgtimes: Pointer to thread_group_cputime structure. - * @cputime: Time value by which to increment the utime field of that - * structure. - * - * If thread group time is being maintained, get the structure for the - * running CPU and update the utime field there. - */ -static inline void thread_group_cputime_account_user( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - if (tgtimes->totals) { - struct task_cputime *times; - - times = per_cpu_ptr(tgtimes->totals, get_cpu()); - times->utime = cputime_add(times->utime, cputime); - put_cpu_no_resched(); - } -} - -/** - * thread_group_cputime_account_system - Maintain stime for a thread group. - * - * @tgtimes: Pointer to thread_group_cputime structure. - * @cputime: Time value by which to increment the stime field of that - * structure. - * - * If thread group time is being maintained, get the structure for the - * running CPU and update the stime field there. - */ -static inline void thread_group_cputime_account_system( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - if (tgtimes->totals) { - struct task_cputime *times; - - times = per_cpu_ptr(tgtimes->totals, get_cpu()); - times->stime = cputime_add(times->stime, cputime); - put_cpu_no_resched(); - } -} - -/** - * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a - * thread group. - * - * @tgtimes: Pointer to thread_group_cputime structure. - * @ns: Time value by which to increment the sum_exec_runtime field - * of that structure. - * - * If thread group time is being maintained, get the structure for the - * running CPU and update the sum_exec_runtime field there. - */ -static inline void thread_group_cputime_account_exec_runtime( - struct thread_group_cputime *tgtimes, - unsigned long long ns) -{ - if (tgtimes->totals) { - struct task_cputime *times; - - times = per_cpu_ptr(tgtimes->totals, get_cpu()); - times->sum_exec_runtime += ns; - put_cpu_no_resched(); - } -} - -#else /* CONFIG_SMP */ - -static inline void thread_group_cputime_init(struct signal_struct *sig) -{ - sig->cputime.totals.utime = cputime_zero; - sig->cputime.totals.stime = cputime_zero; - sig->cputime.totals.sum_exec_runtime = 0; -} - -static inline int thread_group_cputime_alloc(struct task_struct *tsk) -{ - return 0; -} static inline void thread_group_cputime_free(struct signal_struct *sig) { -} - -static inline int thread_group_cputime_clone_thread(struct task_struct *curr, - struct task_struct *tsk) -{ - return 0; -} - -static inline void thread_group_cputime(struct task_struct *tsk, - struct task_cputime *cputime) -{ - *cputime = tsk->signal->cputime.totals; -} - -static inline void thread_group_cputime_account_user( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - tgtimes->totals.utime = cputime_add(tgtimes->totals.utime, cputime); -} - -static inline void thread_group_cputime_account_system( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - tgtimes->totals.stime = cputime_add(tgtimes->totals.stime, cputime); -} - -static inline void thread_group_cputime_account_exec_runtime( - struct thread_group_cputime *tgtimes, - unsigned long long ns) -{ - tgtimes->totals.sum_exec_runtime += ns; -} - -#endif /* CONFIG_SMP */ - -static inline void account_group_user_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_user(&sig->cputime, cputime); -} - -static inline void account_group_system_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_system(&sig->cputime, cputime); -} - -static inline void account_group_exec_runtime(struct task_struct *tsk, - unsigned long long ns) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_exec_runtime(&sig->cputime, ns); + free_percpu(sig->cputime.totals); } /* diff --git a/kernel/fork.c b/kernel/fork.c index 1181b9a..021ae01 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -791,7 +791,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) int ret; if (clone_flags & CLONE_THREAD) { - ret = thread_group_cputime_clone_thread(current, tsk); + ret = thread_group_cputime_clone_thread(current); if (likely(!ret)) { atomic_inc(¤t->signal->count); atomic_inc(¤t->signal->live); @@ -834,9 +834,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; task_io_accounting_init(&sig->ioac); - INIT_LIST_HEAD(&sig->cpu_timers[0]); - INIT_LIST_HEAD(&sig->cpu_timers[1]); - INIT_LIST_HEAD(&sig->cpu_timers[2]); taskstats_tgid_init(sig); task_lock(current->group_leader); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 9a7ea04..153dcb2 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -7,50 +7,46 @@ #include #include #include +#include -#ifdef CONFIG_SMP /* - * Allocate the thread_group_cputime structure appropriately for SMP kernels - * and fill in the current values of the fields. Called from copy_signal() - * via thread_group_cputime_clone_thread() when adding a second or subsequent + * Allocate the thread_group_cputime structure appropriately and fill in the + * current values of the fields. Called from copy_signal() via + * thread_group_cputime_clone_thread() when adding a second or subsequent * thread to a thread group. Assumes interrupts are enabled when called. */ -int thread_group_cputime_alloc_smp(struct task_struct *tsk) +int thread_group_cputime_alloc(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; struct task_cputime *cputime; /* * If we have multiple threads and we don't already have a - * per-CPU task_cputime struct, allocate one and fill it in with - * the times accumulated so far. + * per-CPU task_cputime struct (checked in the caller), allocate + * one and fill it in with the times accumulated so far. We may + * race with another thread so recheck after we pick up the sighand + * lock. */ - if (sig->cputime.totals) - return 0; cputime = alloc_percpu(struct task_cputime); if (cputime == NULL) return -ENOMEM; - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); if (sig->cputime.totals) { spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); free_percpu(cputime); return 0; } sig->cputime.totals = cputime; - cputime = per_cpu_ptr(sig->cputime.totals, get_cpu()); + cputime = per_cpu_ptr(sig->cputime.totals, smp_processor_id()); cputime->utime = tsk->utime; cputime->stime = tsk->stime; cputime->sum_exec_runtime = tsk->se.sum_exec_runtime; - put_cpu_no_resched(); spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); return 0; } /** - * thread_group_cputime_smp - Sum the thread group time fields across all CPUs. + * thread_group_cputime - Sum the thread group time fields across all CPUs. * * @tsk: The task we use to identify the thread group. * @times: task_cputime structure in which we return the summed fields. @@ -58,7 +54,7 @@ int thread_group_cputime_alloc_smp(struct task_struct *tsk) * Walk the list of CPUs to sum the per-CPU time fields in the thread group * time structure. */ -void thread_group_cputime_smp( +void thread_group_cputime( struct task_struct *tsk, struct task_cputime *times) { @@ -83,8 +79,6 @@ void thread_group_cputime_smp( } } -#endif /* CONFIG_SMP */ - /* * Called after updating RLIMIT_CPU to set timer expiration if necessary. */ @@ -300,7 +294,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, cpu->cpu = virt_ticks(p); break; case CPUCLOCK_SCHED: - cpu->sched = task_sched_runtime(p); + cpu->sched = p->se.sum_exec_runtime + task_delta_exec(p); break; } return 0; @@ -309,16 +303,15 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, /* * Sample a process (thread group) clock for the given group_leader task. * Must be called with tasklist_lock held for reading. - * Must be called with tasklist_lock held for reading, and p->sighand->siglock. */ -static int cpu_clock_sample_group_locked(unsigned int clock_idx, - struct task_struct *p, - union cpu_time_count *cpu) +static int cpu_clock_sample_group(const clockid_t which_clock, + struct task_struct *p, + union cpu_time_count *cpu) { struct task_cputime cputime; thread_group_cputime(p, &cputime); - switch (clock_idx) { + switch (which_clock) { default: return -EINVAL; case CPUCLOCK_PROF: @@ -328,29 +321,12 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx, cpu->cpu = cputime.utime; break; case CPUCLOCK_SCHED: - cpu->sched = thread_group_sched_runtime(p); + cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p); break; } return 0; } -/* - * Sample a process (thread group) clock for the given group_leader task. - * Must be called with tasklist_lock held for reading. - */ -static int cpu_clock_sample_group(const clockid_t which_clock, - struct task_struct *p, - union cpu_time_count *cpu) -{ - int ret; - unsigned long flags; - spin_lock_irqsave(&p->sighand->siglock, flags); - ret = cpu_clock_sample_group_locked(CPUCLOCK_WHICH(which_clock), p, - cpu); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - return ret; -} - int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) { @@ -1324,29 +1300,37 @@ static inline int task_cputime_expired(const struct task_cputime *sample, * fastpath_timer_check - POSIX CPU timers fast path. * * @tsk: The task (thread) being checked. - * @sig: The signal pointer for that task. * - * If there are no timers set return false. Otherwise snapshot the task and - * thread group timers, then compare them with the corresponding expiration - # times. Returns true if a timer has expired, else returns false. + * Check the task and thread group timers. If both are zero (there are no + * timers set) return false. Otherwise snapshot the task and thread group + * timers and compare them with the corresponding expiration times. Return + * true if a timer has expired, else return false. */ -static inline int fastpath_timer_check(struct task_struct *tsk, - struct signal_struct *sig) +static inline int fastpath_timer_check(struct task_struct *tsk) { - struct task_cputime task_sample = { - .utime = tsk->utime, - .stime = tsk->stime, - .sum_exec_runtime = tsk->se.sum_exec_runtime - }; - struct task_cputime group_sample; + struct signal_struct *sig = tsk->signal; - if (task_cputime_zero(&tsk->cputime_expires) && - task_cputime_zero(&sig->cputime_expires)) + if (unlikely(!sig)) return 0; - if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) - return 1; - thread_group_cputime(tsk, &group_sample); - return task_cputime_expired(&group_sample, &sig->cputime_expires); + + if (!task_cputime_zero(&tsk->cputime_expires)) { + struct task_cputime task_sample = { + .utime = tsk->utime, + .stime = tsk->stime, + .sum_exec_runtime = tsk->se.sum_exec_runtime + }; + + if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) + return 1; + } + if (!task_cputime_zero(&sig->cputime_expires)) { + struct task_cputime group_sample; + + thread_group_cputime(tsk, &group_sample); + if (task_cputime_expired(&group_sample, &sig->cputime_expires)) + return 1; + } + return 0; } /* @@ -1358,43 +1342,34 @@ void run_posix_cpu_timers(struct task_struct *tsk) { LIST_HEAD(firing); struct k_itimer *timer, *next; - struct signal_struct *sig; - struct sighand_struct *sighand; - unsigned long flags; BUG_ON(!irqs_disabled()); - /* Pick up tsk->signal and make sure it's valid. */ - sig = tsk->signal; /* * The fast path checks that there are no expired thread or thread - * group timers. If that's so, just return. Also check that - * tsk->signal is non-NULL; this probably can't happen but cover the - * possibility anyway. + * group timers. If that's so, just return. */ - if (unlikely(!sig) || !fastpath_timer_check(tsk, sig)) + if (!fastpath_timer_check(tsk)) return; - sighand = lock_task_sighand(tsk, &flags); - if (likely(sighand)) { - /* - * Here we take off tsk->signal->cpu_timers[N] and - * tsk->cpu_timers[N] all the timers that are firing, and - * put them on the firing list. - */ - check_thread_timers(tsk, &firing); - check_process_timers(tsk, &firing); + spin_lock(&tsk->sighand->siglock); + /* + * Here we take off tsk->signal->cpu_timers[N] and + * tsk->cpu_timers[N] all the timers that are firing, and + * put them on the firing list. + */ + check_thread_timers(tsk, &firing); + check_process_timers(tsk, &firing); - /* - * We must release these locks before taking any timer's lock. - * There is a potential race with timer deletion here, as the - * siglock now protects our private firing list. We have set - * the firing flag in each timer, so that a deletion attempt - * that gets the timer lock before we do will give it up and - * spin until we've taken care of that timer below. - */ - } - unlock_task_sighand(tsk, &flags); + /* + * We must release these locks before taking any timer's lock. + * There is a potential race with timer deletion here, as the + * siglock now protects our private firing list. We have set + * the firing flag in each timer, so that a deletion attempt + * that gets the timer lock before we do will give it up and + * spin until we've taken care of that timer below. + */ + spin_unlock(&tsk->sighand->siglock); /* * Now that all the timers on our list have the firing flag, @@ -1433,7 +1408,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, struct list_head *head; BUG_ON(clock_idx == CPUCLOCK_SCHED); - cpu_clock_sample_group_locked(clock_idx, tsk, &now); + cpu_clock_sample_group(clock_idx, tsk, &now); if (oldval) { if (!cputime_eq(*oldval, cputime_zero)) { diff --git a/kernel/sched.c b/kernel/sched.c index c51b5d2..260c22c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4039,55 +4039,22 @@ EXPORT_PER_CPU_SYMBOL(kstat); /* * Return any ns on the sched_clock that have not yet been banked in * @p in case that task is currently running. - * - * Called with task_rq_lock() held on @rq. */ -static unsigned long long task_delta_exec(struct task_struct *p, struct rq *rq) +unsigned long long task_delta_exec(struct task_struct *p) { + struct rq *rq; + unsigned long flags; + u64 ns = 0; + + rq = task_rq_lock(p, &flags); if (task_current(rq, p)) { u64 delta_exec; update_rq_clock(rq); delta_exec = rq->clock - p->se.exec_start; if ((s64)delta_exec > 0) - return delta_exec; + ns = delta_exec; } - return 0; -} - -/* - * Return p->sum_exec_runtime plus any more ns on the sched_clock - * that have not yet been banked in case the task is currently running. - */ -unsigned long long task_sched_runtime(struct task_struct *p) -{ - unsigned long flags; - u64 ns; - struct rq *rq; - - rq = task_rq_lock(p, &flags); - ns = p->se.sum_exec_runtime + task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); - - return ns; -} - -/* - * Return sum_exec_runtime for the thread group plus any more ns on the - * sched_clock that have not yet been banked in case the task is currently - * running. - */ -unsigned long long thread_group_sched_runtime(struct task_struct *p) -{ - unsigned long flags; - u64 ns; - struct rq *rq; - struct task_cputime totals; - - rq = task_rq_lock(p, &flags); - thread_group_cputime(p, &totals); - ns = totals.sum_exec_runtime + task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); return ns; } diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 8385d43..d6903bd 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -270,3 +270,139 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) #define sched_info_switch(t, next) do { } while (0) #endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */ +/* + * The following are functions that support scheduler-internal time accounting. + * These functions are generally called at the timer tick. None of this depends + * on CONFIG_SCHEDSTATS. + */ + +#ifdef CONFIG_SMP + +/** + * thread_group_cputime_account_user - Maintain utime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the utime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->utime = cputime_add(times->utime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_system - Maintain stime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the stime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->stime = cputime_add(times->stime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a + * thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of that structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->sum_exec_runtime += ns; + put_cpu_no_resched(); + } +} + +#else /* CONFIG_SMP */ + +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); +} + +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); +} + +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + tgtimes->totals->sum_exec_runtime += ns; +} + +#endif /* CONFIG_SMP */ + +/* + * These are the generic time-accounting routines that use the above + * functions. They are the functions actually called by the scheduler. + */ +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_user(&sig->cputime, cputime); +} + +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_system(&sig->cputime, cputime); +} + +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_exec_runtime(&sig->cputime, ns); +} -- cgit v0.10.2 From 59f647c25a4f27c1e5c84710e0608b36303089f9 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Tue, 23 Sep 2008 15:55:56 -0700 Subject: fsldma: remove internal self-test from Freescale Elo DMA driver The Freescale Elo DMA driver runs an internal self-test before registering the channels with the DMA engine. This self-test has a fundemental flaw in that it calls the DMA engine's callback functions directly before the registration. However, the registration initializes some variables that the callback functions uses, namely the device struct. The code works today because there are two device structs: the one created by the DMA engine, and one created by the Open Firmware (OF) subsystem. The self-test currently uses the device struct created by OF. However, in the future, some of the device structs created by OF will be eliminated. This means that the self-test will only have access to the device struct created by the DMA engine. But this device struct isn't initialized when the self-test runs, and this causes a kernel panic. Since there is already a DMA test module (dmatest), the internal self-test code is not useful anyway. It is extremely unlikely that the test will fail in normal usage. It may have been helpful during development, but not any more. Cc: Kumar Gala Cc: Li Yang Cc: Scott Wood Signed-off-by: Timur Tabi Signed-off-by: Dan Williams diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index c0059ca..e9b2638 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -786,132 +786,6 @@ static void dma_do_tasklet(unsigned long data) fsl_chan_ld_cleanup(fsl_chan); } -static void fsl_dma_callback_test(void *param) -{ - struct fsl_dma_chan *fsl_chan = param; - if (fsl_chan) - dev_dbg(fsl_chan->dev, "selftest: callback is ok!\n"); -} - -static int fsl_dma_self_test(struct fsl_dma_chan *fsl_chan) -{ - struct dma_chan *chan; - int err = 0; - dma_addr_t dma_dest, dma_src; - dma_cookie_t cookie; - u8 *src, *dest; - int i; - size_t test_size; - struct dma_async_tx_descriptor *tx1, *tx2, *tx3; - - test_size = 4096; - - src = kmalloc(test_size * 2, GFP_KERNEL); - if (!src) { - dev_err(fsl_chan->dev, - "selftest: Cannot alloc memory for test!\n"); - return -ENOMEM; - } - - dest = src + test_size; - - for (i = 0; i < test_size; i++) - src[i] = (u8) i; - - chan = &fsl_chan->common; - - if (fsl_dma_alloc_chan_resources(chan, NULL) < 1) { - dev_err(fsl_chan->dev, - "selftest: Cannot alloc resources for DMA\n"); - err = -ENODEV; - goto out; - } - - /* TX 1 */ - dma_src = dma_map_single(fsl_chan->dev, src, test_size / 2, - DMA_TO_DEVICE); - dma_dest = dma_map_single(fsl_chan->dev, dest, test_size / 2, - DMA_FROM_DEVICE); - tx1 = fsl_dma_prep_memcpy(chan, dma_dest, dma_src, test_size / 2, 0); - async_tx_ack(tx1); - - cookie = fsl_dma_tx_submit(tx1); - fsl_dma_memcpy_issue_pending(chan); - msleep(2); - - if (fsl_dma_is_complete(chan, cookie, NULL, NULL) != DMA_SUCCESS) { - dev_err(fsl_chan->dev, "selftest: Time out!\n"); - err = -ENODEV; - goto free_resources; - } - - /* Test free and re-alloc channel resources */ - fsl_dma_free_chan_resources(chan); - - if (fsl_dma_alloc_chan_resources(chan, NULL) < 1) { - dev_err(fsl_chan->dev, - "selftest: Cannot alloc resources for DMA\n"); - err = -ENODEV; - goto free_resources; - } - - /* Continue to test - * TX 2 - */ - dma_src = dma_map_single(fsl_chan->dev, src + test_size / 2, - test_size / 4, DMA_TO_DEVICE); - dma_dest = dma_map_single(fsl_chan->dev, dest + test_size / 2, - test_size / 4, DMA_FROM_DEVICE); - tx2 = fsl_dma_prep_memcpy(chan, dma_dest, dma_src, test_size / 4, 0); - async_tx_ack(tx2); - - /* TX 3 */ - dma_src = dma_map_single(fsl_chan->dev, src + test_size * 3 / 4, - test_size / 4, DMA_TO_DEVICE); - dma_dest = dma_map_single(fsl_chan->dev, dest + test_size * 3 / 4, - test_size / 4, DMA_FROM_DEVICE); - tx3 = fsl_dma_prep_memcpy(chan, dma_dest, dma_src, test_size / 4, 0); - async_tx_ack(tx3); - - /* Interrupt tx test */ - tx1 = fsl_dma_prep_interrupt(chan, 0); - async_tx_ack(tx1); - cookie = fsl_dma_tx_submit(tx1); - - /* Test exchanging the prepared tx sort */ - cookie = fsl_dma_tx_submit(tx3); - cookie = fsl_dma_tx_submit(tx2); - - if (dma_has_cap(DMA_INTERRUPT, ((struct fsl_dma_device *) - dev_get_drvdata(fsl_chan->dev->parent))->common.cap_mask)) { - tx3->callback = fsl_dma_callback_test; - tx3->callback_param = fsl_chan; - } - fsl_dma_memcpy_issue_pending(chan); - msleep(2); - - if (fsl_dma_is_complete(chan, cookie, NULL, NULL) != DMA_SUCCESS) { - dev_err(fsl_chan->dev, "selftest: Time out!\n"); - err = -ENODEV; - goto free_resources; - } - - err = memcmp(src, dest, test_size); - if (err) { - for (i = 0; (*(src + i) == *(dest + i)) && (i < test_size); - i++); - dev_err(fsl_chan->dev, "selftest: Test failed, data %d/%ld is " - "error! src 0x%x, dest 0x%x\n", - i, (long)test_size, *(src + i), *(dest + i)); - } - -free_resources: - fsl_dma_free_chan_resources(chan); -out: - kfree(src); - return err; -} - static int __devinit of_fsl_dma_chan_probe(struct of_device *dev, const struct of_device_id *match) { @@ -1000,17 +874,11 @@ static int __devinit of_fsl_dma_chan_probe(struct of_device *dev, } } - err = fsl_dma_self_test(new_fsl_chan); - if (err) - goto err_self_test; - dev_info(&dev->dev, "#%d (%s), irq %d\n", new_fsl_chan->id, match->compatible, new_fsl_chan->irq); return 0; -err_self_test: - free_irq(new_fsl_chan->irq, new_fsl_chan); err_no_irq: list_del(&new_fsl_chan->common.device_node); err_no_chan: -- cgit v0.10.2 From aa88f169d6fc4305125b6917d9d5f2e08211f011 Mon Sep 17 00:00:00 2001 From: Nobuhiro Iwamatsu Date: Wed, 24 Sep 2008 11:46:48 +0900 Subject: sh: ap325rxa: create CPLD data area in mtd AP320 and AP325RXA has CPLD data in NOR Flash. If this area erased, this board can not boot. This patch create CPLD data area and set writeable mask bit. Signed-off-by: Nobuhiro Iwamatsu Signed-off-by: Paul Mundt diff --git a/arch/sh/boards/board-ap325rxa.c b/arch/sh/boards/board-ap325rxa.c index fd16125..00e632f 100644 --- a/arch/sh/boards/board-ap325rxa.c +++ b/arch/sh/boards/board-ap325rxa.c @@ -52,20 +52,33 @@ static struct platform_device smc9118_device = { }, }; +/* + * AP320 and AP325RXA has CPLD data in NOR Flash(0xA80000-0xABFFFF). + * If this area erased, this board can not boot. + */ static struct mtd_partition ap325rxa_nor_flash_partitions[] = { { - .name = "uboot", - .offset = 0, - .size = (1 * 1024 * 1024), - .mask_flags = MTD_WRITEABLE, /* Read-only */ + .name = "uboot", + .offset = 0, + .size = (1 * 1024 * 1024), + .mask_flags = MTD_WRITEABLE, /* Read-only */ + }, { + .name = "kernel", + .offset = MTDPART_OFS_APPEND, + .size = (2 * 1024 * 1024), + }, { + .name = "free-area0", + .offset = MTDPART_OFS_APPEND, + .size = ((7 * 1024 * 1024) + (512 * 1024)), }, { - .name = "kernel", - .offset = MTDPART_OFS_APPEND, - .size = (2 * 1024 * 1024), + .name = "CPLD-Data", + .offset = MTDPART_OFS_APPEND, + .mask_flags = MTD_WRITEABLE, /* Read-only */ + .size = (1024 * 128 * 2), }, { - .name = "other", - .offset = MTDPART_OFS_APPEND, - .size = MTDPART_SIZ_FULL, + .name = "free-area1", + .offset = MTDPART_OFS_APPEND, + .size = MTDPART_SIZ_FULL, }, }; -- cgit v0.10.2 From 1bec157a1f747d038026efabebdee4c929147b63 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 24 Sep 2008 14:37:35 +0900 Subject: sh: Force pending restarted system calls to return -EINTR. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c index be194d0..69d09c0 100644 --- a/arch/sh/kernel/signal_32.c +++ b/arch/sh/kernel/signal_32.c @@ -216,6 +216,9 @@ asmlinkage int sys_sigreturn(unsigned long r4, unsigned long r5, sigset_t set; int r0; + /* Always make any pending restarted system calls return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; @@ -250,6 +253,9 @@ asmlinkage int sys_rt_sigreturn(unsigned long r4, unsigned long r5, sigset_t set; int r0; + /* Always make any pending restarted system calls return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; diff --git a/arch/sh/kernel/signal_64.c b/arch/sh/kernel/signal_64.c index 37bd381..0582ae4 100644 --- a/arch/sh/kernel/signal_64.c +++ b/arch/sh/kernel/signal_64.c @@ -375,6 +375,9 @@ asmlinkage int sys_sigreturn(unsigned long r2, unsigned long r3, sigset_t set; long long ret; + /* Always make any pending restarted system calls return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; @@ -412,6 +415,9 @@ asmlinkage int sys_rt_sigreturn(unsigned long r2, unsigned long r3, stack_t __user st; long long ret; + /* Always make any pending restarted system calls return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; @@ -539,7 +545,7 @@ static void setup_frame(int sig, struct k_sigaction *ka, * On SH5 all edited pointers are subject to NEFF */ DEREF_REG_PR = (DEREF_REG_PR & NEFF_SIGN) ? - (DEREF_REG_PR | NEFF_MASK) : DEREF_REG_PR; + (DEREF_REG_PR | NEFF_MASK) : DEREF_REG_PR; } else { /* * Different approach on SH5. @@ -554,7 +560,7 @@ static void setup_frame(int sig, struct k_sigaction *ka, */ DEREF_REG_PR = (unsigned long) frame->retcode | 0x01; DEREF_REG_PR = (DEREF_REG_PR & NEFF_SIGN) ? - (DEREF_REG_PR | NEFF_MASK) : DEREF_REG_PR; + (DEREF_REG_PR | NEFF_MASK) : DEREF_REG_PR; if (__copy_to_user(frame->retcode, (unsigned long long)sa_default_restorer & (~1), 16) != 0) @@ -570,7 +576,7 @@ static void setup_frame(int sig, struct k_sigaction *ka, */ regs->regs[REG_SP] = (unsigned long) frame; regs->regs[REG_SP] = (regs->regs[REG_SP] & NEFF_SIGN) ? - (regs->regs[REG_SP] | NEFF_MASK) : regs->regs[REG_SP]; + (regs->regs[REG_SP] | NEFF_MASK) : regs->regs[REG_SP]; regs->regs[REG_ARG1] = signal; /* Arg for signal handler */ /* FIXME: @@ -656,7 +662,7 @@ static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, * On SH5 all edited pointers are subject to NEFF */ DEREF_REG_PR = (DEREF_REG_PR & NEFF_SIGN) ? - (DEREF_REG_PR | NEFF_MASK) : DEREF_REG_PR; + (DEREF_REG_PR | NEFF_MASK) : DEREF_REG_PR; } else { /* * Different approach on SH5. @@ -672,7 +678,7 @@ static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, DEREF_REG_PR = (unsigned long) frame->retcode | 0x01; DEREF_REG_PR = (DEREF_REG_PR & NEFF_SIGN) ? - (DEREF_REG_PR | NEFF_MASK) : DEREF_REG_PR; + (DEREF_REG_PR | NEFF_MASK) : DEREF_REG_PR; if (__copy_to_user(frame->retcode, (unsigned long long)sa_default_rt_restorer & (~1), 16) != 0) @@ -687,7 +693,7 @@ static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, */ regs->regs[REG_SP] = (unsigned long) frame; regs->regs[REG_SP] = (regs->regs[REG_SP] & NEFF_SIGN) ? - (regs->regs[REG_SP] | NEFF_MASK) : regs->regs[REG_SP]; + (regs->regs[REG_SP] | NEFF_MASK) : regs->regs[REG_SP]; regs->regs[REG_ARG1] = signal; /* Arg for signal handler */ regs->regs[REG_ARG2] = (unsigned long long)(unsigned long)(signed long)&frame->info; regs->regs[REG_ARG3] = (unsigned long long)(unsigned long)(signed long)&frame->uc.uc_mcontext; -- cgit v0.10.2 From 4aa7361179bed905fd0f35b236a5c65db683b9e0 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 22 Sep 2008 14:42:46 -0700 Subject: posix-timers: don't switch to ->group_leader if ->it_process dies posix_timer_event() drops SIGEV_THREAD_ID and switches to ->group_leader if send_sigqueue() fails. This is not very useful and doesn't work reliably. send_sigqueue() can only fail if ->it_process is dead. But it can die before it dequeues the SI_TIMER signal, in that case the timer stops anyway. Remove this code. I guess it was needed a long ago to ensure that the timer is not destroyed when when its creator thread dies. Q: perhaps it makes sense to change sys_timer_settime() to return an error if ->it_process is dead? Signed-off-by: Oleg Nesterov Cc: mingo@elte.hu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index e36d579..3dfd15a 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -298,6 +298,7 @@ void do_schedule_next_timer(struct siginfo *info) int posix_timer_event(struct k_itimer *timr, int si_private) { + int shared, ret; /* * FIXME: if ->sigq is queued we can race with * dequeue_signal()->do_schedule_next_timer(). @@ -316,20 +317,10 @@ int posix_timer_event(struct k_itimer *timr, int si_private) timr->sigq->info.si_tid = timr->it_id; timr->sigq->info.si_value = timr->it_sigev_value; - if (timr->it_sigev_notify & SIGEV_THREAD_ID) { - struct task_struct *leader; - int ret = send_sigqueue(timr->sigq, timr->it_process, 0); - - if (likely(ret >= 0)) - return ret; - - timr->it_sigev_notify = SIGEV_SIGNAL; - leader = timr->it_process->group_leader; - put_task_struct(timr->it_process); - timr->it_process = leader; - } - - return send_sigqueue(timr->sigq, timr->it_process, 1); + shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID); + ret = send_sigqueue(timr->sigq, timr->it_process, shared); + /* If we failed to send the signal the timer stops. */ + return ret > 0; } EXPORT_SYMBOL_GPL(posix_timer_event); -- cgit v0.10.2 From 918fc0372831dca73039e1577bfea0c2ce49bdb6 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 22 Sep 2008 14:42:46 -0700 Subject: posix-timers: always do get_task_struct(timer->it_process) Change the code to get/put timer->it_process regardless of SIGEV_THREAD_ID. This streamlines the create/destroy paths and allows us to simplify the usage of exit_itimers() in de_thread(). Signed-off-by: Oleg Nesterov Cc: mingo@elte.hu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 3dfd15a..bd9c931 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -540,11 +540,10 @@ sys_timer_create(const clockid_t which_clock, */ spin_lock_irqsave(&process->sighand->siglock, flags); if (!(process->flags & PF_EXITING)) { + get_task_struct(process); new_timer->it_process = process; list_add(&new_timer->list, &process->signal->posix_timers); - if (new_timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID)) - get_task_struct(process); spin_unlock_irqrestore(&process->sighand->siglock, flags); } else { spin_unlock_irqrestore(&process->sighand->siglock, flags); @@ -561,6 +560,7 @@ sys_timer_create(const clockid_t which_clock, new_timer->it_sigev_signo = SIGALRM; new_timer->it_sigev_value.sival_int = new_timer->it_id; process = current->group_leader; + get_task_struct(process); spin_lock_irqsave(&process->sighand->siglock, flags); new_timer->it_process = process; list_add(&new_timer->list, &process->signal->posix_timers); @@ -853,8 +853,7 @@ retry_delete: * This keeps any tasks waiting on the spin lock from thinking * they got something (see the lock code above). */ - if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID)) - put_task_struct(timer->it_process); + put_task_struct(timer->it_process); timer->it_process = NULL; unlock_timer(timer, flags); @@ -881,8 +880,7 @@ retry_delete: * This keeps any tasks waiting on the spin lock from thinking * they got something (see the lock code above). */ - if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID)) - put_task_struct(timer->it_process); + put_task_struct(timer->it_process); timer->it_process = NULL; unlock_timer(timer, flags); -- cgit v0.10.2 From 2cd499e38ec241691e4bce50bddc8f57e4cc9bd0 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 22 Sep 2008 14:42:47 -0700 Subject: posix-timers: sys_timer_create: remove the buggy PF_EXITING check sys_timer_create() return -EINVAL if the target thread has PF_EXITING. This doesn't really make sense, the sub-thread can die right after unlock. And in fact, this is just wrong. Without SIGEV_THREAD_ID good_sigevent() returns ->group_leader, and it is very possible that the leader is already dead. This is OK, we shouldn't return the error in this case. Remove this check and the comment. Note that the "process" was found under tasklist_lock, it must have ->sighand != NULL. Also, remove a couple of unneeded initializations. Signed-off-by: Oleg Nesterov Cc: mingo@elte.hu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index bd9c931..60b2620 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -460,9 +460,9 @@ sys_timer_create(const clockid_t which_clock, timer_t __user * created_timer_id) { int error = 0; - struct k_itimer *new_timer = NULL; + struct k_itimer *new_timer; int new_timer_id; - struct task_struct *process = NULL; + struct task_struct *process; unsigned long flags; sigevent_t event; int it_id_set = IT_ID_NOT_SET; @@ -523,32 +523,12 @@ sys_timer_create(const clockid_t which_clock, read_lock(&tasklist_lock); if ((process = good_sigevent(&event))) { - /* - * We may be setting up this process for another - * thread. It may be exiting. To catch this - * case the we check the PF_EXITING flag. If - * the flag is not set, the siglock will catch - * him before it is too late (in exit_itimers). - * - * The exec case is a bit more invloved but easy - * to code. If the process is in our thread - * group (and it must be or we would not allow - * it here) and is doing an exec, it will cause - * us to be killed. In this case it will wait - * for us to die which means we can finish this - * linkage with our last gasp. I.e. no code :) - */ + get_task_struct(process); spin_lock_irqsave(&process->sighand->siglock, flags); - if (!(process->flags & PF_EXITING)) { - get_task_struct(process); - new_timer->it_process = process; - list_add(&new_timer->list, - &process->signal->posix_timers); - spin_unlock_irqrestore(&process->sighand->siglock, flags); - } else { - spin_unlock_irqrestore(&process->sighand->siglock, flags); - process = NULL; - } + new_timer->it_process = process; + list_add(&new_timer->list, + &process->signal->posix_timers); + spin_unlock_irqrestore(&process->sighand->siglock, flags); } read_unlock(&tasklist_lock); if (!process) { -- cgit v0.10.2 From 36b2f046000b358b62b9d116cb10a2b1c5be5cbf Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 22 Sep 2008 14:42:48 -0700 Subject: posix-timers: sys_timer_create: simplify and s/tasklist/rcu/ - Change the code to do rcu_read_lock() instead of taking tasklist_lock, it is safe to get_task_struct(p) if p was found under RCU. However, now we must not use process's sighand/signal, they may be NULL. We can use current->sighand/signal instead, this "process" must belong to the current's thread-group. - Factor out the common code for 2 "if (timer_event_spec)" branches, the !timer_event_spec case can use current too. - use spin_lock_irq() instead of _irqsave(), kill "flags". Signed-off-by: Oleg Nesterov Cc: mingo@elte.hu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 60b2620..5b76190 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -463,7 +463,6 @@ sys_timer_create(const clockid_t which_clock, struct k_itimer *new_timer; int new_timer_id; struct task_struct *process; - unsigned long flags; sigevent_t event; int it_id_set = IT_ID_NOT_SET; @@ -521,16 +520,11 @@ sys_timer_create(const clockid_t which_clock, new_timer->it_sigev_signo = event.sigev_signo; new_timer->it_sigev_value = event.sigev_value; - read_lock(&tasklist_lock); - if ((process = good_sigevent(&event))) { + rcu_read_lock(); + process = good_sigevent(&event); + if (process) get_task_struct(process); - spin_lock_irqsave(&process->sighand->siglock, flags); - new_timer->it_process = process; - list_add(&new_timer->list, - &process->signal->posix_timers); - spin_unlock_irqrestore(&process->sighand->siglock, flags); - } - read_unlock(&tasklist_lock); + rcu_read_unlock(); if (!process) { error = -EINVAL; goto out; @@ -541,19 +535,18 @@ sys_timer_create(const clockid_t which_clock, new_timer->it_sigev_value.sival_int = new_timer->it_id; process = current->group_leader; get_task_struct(process); - spin_lock_irqsave(&process->sighand->siglock, flags); - new_timer->it_process = process; - list_add(&new_timer->list, &process->signal->posix_timers); - spin_unlock_irqrestore(&process->sighand->siglock, flags); } + spin_lock_irq(¤t->sighand->siglock); + new_timer->it_process = process; + list_add(&new_timer->list, ¤t->signal->posix_timers); + spin_unlock_irq(¤t->sighand->siglock); /* * In the case of the timer belonging to another task, after * the task is unlocked, the timer is owned by the other task * and may cease to exist at any time. Don't use or modify * new_timer after the unlock call. */ - out: if (error) release_posix_timer(new_timer, it_id_set); -- cgit v0.10.2 From 717835d94d3e3d343a302df0a3cb9405887c3e2a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 22 Sep 2008 14:42:49 -0700 Subject: posix-timers: move the initialization of timer->sigq from send to create path posix_timer_event() always populates timer->sigq with the same numbers, move this code into sys_timer_create(). Note that with this patch we can kill it_sigev_signo and it_sigev_value. Signed-off-by: Oleg Nesterov Cc: mingo@elte.hu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 5b76190..c459b29 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -312,11 +312,6 @@ int posix_timer_event(struct k_itimer *timr, int si_private) */ timr->sigq->info.si_sys_private = si_private; - timr->sigq->info.si_signo = timr->it_sigev_signo; - timr->sigq->info.si_code = SI_TIMER; - timr->sigq->info.si_tid = timr->it_id; - timr->sigq->info.si_value = timr->it_sigev_value; - shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID); ret = send_sigqueue(timr->sigq, timr->it_process, shared); /* If we failed to send the signal the timer stops. */ @@ -537,6 +532,11 @@ sys_timer_create(const clockid_t which_clock, get_task_struct(process); } + new_timer->sigq->info.si_code = SI_TIMER; + new_timer->sigq->info.si_tid = new_timer->it_id; + new_timer->sigq->info.si_signo = new_timer->it_sigev_signo; + new_timer->sigq->info.si_value = new_timer->it_sigev_value; + spin_lock_irq(¤t->sighand->siglock); new_timer->it_process = process; list_add(&new_timer->list, ¤t->signal->posix_timers); -- cgit v0.10.2 From ef864c958801768fb28bd3603cd0b098b394671c Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 22 Sep 2008 14:42:49 -0700 Subject: posix-timers: sys_timer_create: cleanup the error handling Cleanup. - sys_timer_create() is big and complicated. The code above the "out:" label relies on the fact that "error" must be == 0. This is not very robust, make the code more explicit. Remove the unneeded initialization of error. - If idr_get_new() succeeds (as it normally should), we check the returned value twice. Move the "-EAGAIN" check under "if (error)". Signed-off-by: Oleg Nesterov Cc: mingo@elte.hu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index c459b29..7be385f 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -454,9 +454,8 @@ sys_timer_create(const clockid_t which_clock, struct sigevent __user *timer_event_spec, timer_t __user * created_timer_id) { - int error = 0; struct k_itimer *new_timer; - int new_timer_id; + int error, new_timer_id; struct task_struct *process; sigevent_t event; int it_id_set = IT_ID_NOT_SET; @@ -478,9 +477,9 @@ sys_timer_create(const clockid_t which_clock, error = idr_get_new(&posix_timers_id, (void *) new_timer, &new_timer_id); spin_unlock_irq(&idr_lock); - if (error == -EAGAIN) - goto retry; - else if (error) { + if (error) { + if (error == -EAGAIN) + goto retry; /* * Weird looking, but we return EAGAIN if the IDR is * full (proper POSIX return value for this) @@ -541,6 +540,8 @@ sys_timer_create(const clockid_t which_clock, new_timer->it_process = process; list_add(&new_timer->list, ¤t->signal->posix_timers); spin_unlock_irq(¤t->sighand->siglock); + + return 0; /* * In the case of the timer belonging to another task, after * the task is unlocked, the timer is owned by the other task @@ -548,9 +549,7 @@ sys_timer_create(const clockid_t which_clock, * new_timer after the unlock call. */ out: - if (error) - release_posix_timer(new_timer, it_id_set); - + release_posix_timer(new_timer, it_id_set); return error; } -- cgit v0.10.2 From 5a9fa73072854981a5c05eb7ba18a96d49c2804f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 22 Sep 2008 14:42:50 -0700 Subject: posix-timers: kill ->it_sigev_signo and ->it_sigev_value With the recent changes ->it_sigev_signo and ->it_sigev_value are only used in sys_timer_create(), kill them. Signed-off-by: Oleg Nesterov Cc: mingo@elte.hu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index f9d8e9e..a7c7213 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -45,8 +45,6 @@ struct k_itimer { int it_requeue_pending; /* waiting to requeue this timer */ #define REQUEUE_PENDING 1 int it_sigev_notify; /* notify word of sigevent struct */ - int it_sigev_signo; /* signo word of sigevent struct */ - sigval_t it_sigev_value; /* value word of sigevent struct */ struct task_struct *it_process; /* process to send signal to */ struct sigqueue *sigq; /* signal queue entry. */ union { diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 7be385f..3eff47b 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -510,10 +510,6 @@ sys_timer_create(const clockid_t which_clock, error = -EFAULT; goto out; } - new_timer->it_sigev_notify = event.sigev_notify; - new_timer->it_sigev_signo = event.sigev_signo; - new_timer->it_sigev_value = event.sigev_value; - rcu_read_lock(); process = good_sigevent(&event); if (process) @@ -524,17 +520,18 @@ sys_timer_create(const clockid_t which_clock, goto out; } } else { - new_timer->it_sigev_notify = SIGEV_SIGNAL; - new_timer->it_sigev_signo = SIGALRM; - new_timer->it_sigev_value.sival_int = new_timer->it_id; + event.sigev_notify = SIGEV_SIGNAL; + event.sigev_signo = SIGALRM; + event.sigev_value.sival_int = new_timer->it_id; process = current->group_leader; get_task_struct(process); } - new_timer->sigq->info.si_code = SI_TIMER; + new_timer->it_sigev_notify = event.sigev_notify; + new_timer->sigq->info.si_signo = event.sigev_signo; + new_timer->sigq->info.si_value = event.sigev_value; new_timer->sigq->info.si_tid = new_timer->it_id; - new_timer->sigq->info.si_signo = new_timer->it_sigev_signo; - new_timer->sigq->info.si_value = new_timer->it_sigev_value; + new_timer->sigq->info.si_code = SI_TIMER; spin_lock_irq(¤t->sighand->siglock); new_timer->it_process = process; -- cgit v0.10.2 From 5a51b713ccf8835d5adf7217e2f86eb12b1ca851 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 22 Sep 2008 14:42:51 -0700 Subject: posix-timers: lock_timer: kill the bogus ->it_id check lock_timer() checks that the timer found by idr_find(timer_id) has ->it_id == timer_id. This buys nothing. This check can fail only if sys_timer_create() unlocked idr_lock after idr_get_new(), but didn't set ->it_id = new_timer_id yet. But in that case ->it_process == NULL so lock_timer() can't succeed anyway. Also remove a couple of unneeded typecasts. Note that with or without this patch we have a small problem. sys_timer_create() doesn't ensure that the result of setting (say) ->it_sigev_notify must be visible if lock_timer() succeeds. Signed-off-by: Oleg Nesterov Cc: mingo@elte.hu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 3eff47b..7185f05 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -474,8 +474,7 @@ sys_timer_create(const clockid_t which_clock, goto out; } spin_lock_irq(&idr_lock); - error = idr_get_new(&posix_timers_id, (void *) new_timer, - &new_timer_id); + error = idr_get_new(&posix_timers_id, new_timer, &new_timer_id); spin_unlock_irq(&idr_lock); if (error) { if (error == -EAGAIN) @@ -567,12 +566,12 @@ static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags) */ spin_lock_irqsave(&idr_lock, *flags); - timr = (struct k_itimer *) idr_find(&posix_timers_id, (int) timer_id); + timr = idr_find(&posix_timers_id, (int) timer_id); if (timr) { spin_lock(&timr->it_lock); - if ((timr->it_id != timer_id) || !(timr->it_process) || - !same_thread_group(timr->it_process, current)) { + if (!timr->it_process || + !same_thread_group(timr->it_process, current)) { spin_unlock(&timr->it_lock); spin_unlock_irqrestore(&idr_lock, *flags); timr = NULL; -- cgit v0.10.2 From 31d9284569e38fb97117497af3e8047a6a3c86f0 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 22 Sep 2008 14:42:51 -0700 Subject: posix-timers: lock_timer: make it readable Cleanup. Imho makes the code much more understandable. At least this patch lessens both the source and compiled code. Signed-off-by: Oleg Nesterov Cc: mingo@elte.hu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 7185f05..95451bf 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -556,7 +556,7 @@ out: * the find to the timer lock. To avoid a dead lock, the timer id MUST * be release with out holding the timer lock. */ -static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags) +static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags) { struct k_itimer *timr; /* @@ -564,23 +564,20 @@ static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags) * flags part over to the timer lock. Must not let interrupts in * while we are moving the lock. */ - spin_lock_irqsave(&idr_lock, *flags); - timr = idr_find(&posix_timers_id, (int) timer_id); + timr = idr_find(&posix_timers_id, (int)timer_id); if (timr) { spin_lock(&timr->it_lock); - - if (!timr->it_process || - !same_thread_group(timr->it_process, current)) { - spin_unlock(&timr->it_lock); - spin_unlock_irqrestore(&idr_lock, *flags); - timr = NULL; - } else + if (timr->it_process && + same_thread_group(timr->it_process, current)) { spin_unlock(&idr_lock); - } else - spin_unlock_irqrestore(&idr_lock, *flags); + return timr; + } + spin_unlock(&timr->it_lock); + } + spin_unlock_irqrestore(&idr_lock, *flags); - return timr; + return NULL; } /* -- cgit v0.10.2 From 1b02469088ac7a13d7e622b618b7410d0f1ce5ec Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Mon, 22 Sep 2008 14:42:43 -0700 Subject: hrtimer: reorder struct hrtimer to save 8 bytes on 64bit builds reorder struct hrtimer to save 8 bytes on 64 bit builds when CONFIG_TIMER_STATS selected. (also removes 8 bytes from signal_struct) Signed-off-by: Richard Kennedy Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 68b0196..8730b60 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -115,12 +115,12 @@ struct hrtimer { enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; unsigned long state; - enum hrtimer_cb_mode cb_mode; struct list_head cb_entry; + enum hrtimer_cb_mode cb_mode; #ifdef CONFIG_TIMER_STATS + int start_pid; void *start_site; char start_comm[16]; - int start_pid; #endif }; -- cgit v0.10.2 From eb3f938fd6292dc79f43a5fe14784b044776e9f0 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Mon, 22 Sep 2008 14:42:40 -0700 Subject: ntp: let update_persistent_clock() sleep This is a change that makes the 11-minute RTC update be run in the process context. This is so that update_persistent_clock() can sleep, which may be required for certain types of RTC hardware -- most notably I2C devices. Signed-off-by: Maciej W. Rozycki Cc: Roman Zippel Cc: Rik van Riel Cc: David Brownell Acked-by: Alessandro Zummo Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index c6921aa1..450a45c 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -10,13 +10,13 @@ #include #include -#include #include #include #include #include #include #include +#include #include /* @@ -218,11 +218,11 @@ void second_overflow(void) /* Disable the cmos update - used by virtualization and embedded */ int no_sync_cmos_clock __read_mostly; -static void sync_cmos_clock(unsigned long dummy); +static void sync_cmos_clock(struct work_struct *work); -static DEFINE_TIMER(sync_cmos_timer, sync_cmos_clock, 0, 0); +static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock); -static void sync_cmos_clock(unsigned long dummy) +static void sync_cmos_clock(struct work_struct *work) { struct timespec now, next; int fail = 1; @@ -258,13 +258,13 @@ static void sync_cmos_clock(unsigned long dummy) next.tv_sec++; next.tv_nsec -= NSEC_PER_SEC; } - mod_timer(&sync_cmos_timer, jiffies + timespec_to_jiffies(&next)); + schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next)); } static void notify_cmos_timer(void) { if (!no_sync_cmos_clock) - mod_timer(&sync_cmos_timer, jiffies + 1); + schedule_delayed_work(&sync_cmos_work, 0); } #else -- cgit v0.10.2 From 5cd1c9c5cf30d4b33df3d3f74d8142f278d536b7 Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Mon, 22 Sep 2008 14:42:43 -0700 Subject: timekeeping: fix rounding problem during clock update Due to a rounding problem during a clock update it's possible for readers to observe the clock jumping back by 1nsec. The following simplified example demonstrates the problem: cycle xtime 0 0 1000 999999.6 2000 1999999.2 3000 2999998.8 ... 1500 = 1499999.4 = 0.0 + 1499999.4 = 999999.6 + 499999.8 When reading the clock only the full nanosecond part is used, while timekeeping internally keeps nanosecond fractions. If the clock is now updated at cycle 1500 here, a nanosecond is missing due to the truncation. The simple fix is to round up the xtime value during the update, this also changes the distance to the reference time, but the adjustment will automatically take care that it stays under control. Signed-off-by: Roman Zippel Signed-off-by: John Stultz Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e91c29f..5ecbfc3 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -454,7 +454,7 @@ void update_wall_time(void) #else offset = clock->cycle_interval; #endif - clock->xtime_nsec += (s64)xtime.tv_nsec << clock->shift; + clock->xtime_nsec = (s64)xtime.tv_nsec << clock->shift; /* normally this loop will run just once, however in the * case of lost or late ticks, it will accumulate correctly. @@ -479,9 +479,12 @@ void update_wall_time(void) /* correct the clock when NTP error is too big */ clocksource_adjust(offset); - /* store full nanoseconds into xtime */ - xtime.tv_nsec = (s64)clock->xtime_nsec >> clock->shift; + /* store full nanoseconds into xtime after rounding it up and + * add the remainder to the error difference. + */ + xtime.tv_nsec = ((s64)clock->xtime_nsec >> clock->shift) + 1; clock->xtime_nsec -= (s64)xtime.tv_nsec << clock->shift; + clock->error += clock->xtime_nsec << (NTP_SCALE_SHIFT - clock->shift); update_xtime_cache(cyc2ns(clock, offset)); -- cgit v0.10.2 From d40e944c25fb4642adb2a4c580a48218a9f3f824 Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Mon, 22 Sep 2008 14:42:44 -0700 Subject: ntp: improve adjtimex frequency rounding Change PPM_SCALE_INV_SHIFT so that it doesn't throw away any input bits (19 is the amount of the factor 2 in PPM_SCALE), the output frequency can then be calculated back to its input value, as the inverse divide produce a slightly larger value, which is then correctly rounded by the final shift. Reported-by: Martin Ziegler Signed-off-by: Roman Zippel Cc: John Stultz Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/include/linux/timex.h b/include/linux/timex.h index c00bcdd..9007313 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -82,7 +82,7 @@ */ #define SHIFT_USEC 16 /* frequency offset scale (shift) */ #define PPM_SCALE (NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC)) -#define PPM_SCALE_INV_SHIFT 20 +#define PPM_SCALE_INV_SHIFT 19 #define PPM_SCALE_INV ((1ll << (PPM_SCALE_INV_SHIFT + NTP_SCALE_SHIFT)) / \ PPM_SCALE + 1) diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 450a45c..ddb0465 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -406,9 +406,8 @@ adj_done: if (time_status & (STA_UNSYNC|STA_CLOCKERR)) result = TIME_ERROR; - txc->freq = shift_right((s32)(time_freq >> PPM_SCALE_INV_SHIFT) * - (s64)PPM_SCALE_INV, - NTP_SCALE_SHIFT); + txc->freq = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) * + (s64)PPM_SCALE_INV, NTP_SCALE_SHIFT); txc->maxerror = time_maxerror; txc->esterror = time_esterror; txc->status = time_status; -- cgit v0.10.2 From 6a9037887ccea92152b034edeb15d453d1a98555 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 22 Sep 2008 14:06:01 -0700 Subject: power_supply: fix dependency of tosa_battery tosa_battery should also depend on wm97xx_ts as it uses dac-accessing functions from that module. Signed-off-by: Dmitry Baryshkov Signed-off-by: Andrew Morton Signed-off-by: Anton Vorontsov diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig index b2bd104..ae095a4 100644 --- a/drivers/power/Kconfig +++ b/drivers/power/Kconfig @@ -51,7 +51,7 @@ config BATTERY_OLPC config BATTERY_TOSA tristate "Sharp SL-6000 (tosa) battery" - depends on MACH_TOSA && MFD_TC6393XB + depends on MACH_TOSA && MFD_TC6393XB && TOUCHSCREEN_WM97XX help Say Y to enable support for the battery on the Sharp Zaurus SL-6000 (tosa) models. -- cgit v0.10.2 From 8aef7e8f8de2d900da892085edbf14ea35fe6881 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Mon, 22 Sep 2008 14:53:50 -0700 Subject: bq27x00_battery: use unaligned access helper Remove hand-rolled get_unaligned_be16, this points to a possible bug as bq27x00_read does another endian byteswap which sparse notices: drivers/power/bq27x00_battery.c:81:14: warning: cast to restricted __be16 Which should probably be checked. Signed-off-by: Harvey Harrison Cc: Rodolfo Giometti Signed-off-by: Andrew Morton Signed-off-by: Anton Vorontsov diff --git a/drivers/power/bq27x00_battery.c b/drivers/power/bq27x00_battery.c index 62d4948..0c056fc 100644 --- a/drivers/power/bq27x00_battery.c +++ b/drivers/power/bq27x00_battery.c @@ -23,8 +23,8 @@ #include #include #include - #include +#include #define DRIVER_VERSION "1.0.0" @@ -33,7 +33,6 @@ #define BQ27x00_REG_RSOC 0x0B /* Relative State-of-Charge */ #define BQ27x00_REG_AI 0x14 #define BQ27x00_REG_FLAGS 0x0A -#define HIGH_BYTE(A) ((A) << 8) /* If the system has several batteries we need a different name for each * of them... @@ -239,7 +238,7 @@ static int bq27200_read(u8 reg, int *rt_value, int b_single, err = i2c_transfer(client->adapter, msg, 1); if (err >= 0) { if (!b_single) - *rt_value = data[1] | HIGH_BYTE(data[0]); + *rt_value = get_unaligned_be16(data); else *rt_value = data[0]; -- cgit v0.10.2 From 0e4a008a4f389b468cfe8b58c7d77882a6e25695 Mon Sep 17 00:00:00 2001 From: Julien Brunel Date: Fri, 26 Sep 2008 15:27:25 +0200 Subject: UBI: fix IS_ERR test In case of error, the function add_volume returns an ERR pointer. The result of IS_ERR, which is supposed to be used in a test as it is, is here checked to be less than zero, which seems odd. We suggest to replace this test by a simple IS_ERR test. A simplified version of the semantic match that finds this problem is as follows: (http://www.emn.fr/x-info/coccinelle/) // @def0@ expression x; position p0; @@ x@p0 = add_volume(...) @protected@ expression def0.x,E; position def0.p0; position p; statement S; @@ x@p0 ... when != x = E if (!IS_ERR(x) && ...) {<... x@p ...>} else S @unprotected@ expression def0.x,E; identifier fld; position def0.p0; position p != protected.p; @@ x@p0 ... when != x = E * x@p->fld // Signed-off-by: Julien Brunel Signed-off-by: Julia Lawall Signed-off-by: Artem Bityutskiy diff --git a/drivers/mtd/ubi/scan.c b/drivers/mtd/ubi/scan.c index 967bb44..4f2daa5 100644 --- a/drivers/mtd/ubi/scan.c +++ b/drivers/mtd/ubi/scan.c @@ -387,7 +387,7 @@ int ubi_scan_add_used(struct ubi_device *ubi, struct ubi_scan_info *si, pnum, vol_id, lnum, ec, sqnum, bitflips); sv = add_volume(si, vol_id, pnum, vid_hdr); - if (IS_ERR(sv) < 0) + if (IS_ERR(sv)) return PTR_ERR(sv); if (si->max_sqnum < sqnum) -- cgit v0.10.2 From 77cd62e8082b9743b59ee1946a4c3ee2e3cd2bce Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Fri, 26 Sep 2008 17:00:11 -0700 Subject: fsldma: allow Freescale Elo DMA driver to be compiled as a module Modify the Freescale Elo / Elo Plus DMA driver so that it can be compiled as a module. The primary change is to stop treating the DMA controller as a bus, and the DMA channels as devices on the bus. This is because the Open Firmware (OF) kernel code does not allow busses to be removed, so although we can call of_platform_bus_probe() to probe the DMA channels, there is no of_platform_bus_remove(). Instead, the DMA channels are manually probed, similar to what fsl_elbc_nand.c does. Cc: Scott Wood Acked-by: Li Yang Signed-off-by: Timur Tabi Signed-off-by: Dan Williams diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index cd30390..904e575 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -48,13 +48,13 @@ config DW_DMAC can be integrated in chips such as the Atmel AT32ap7000. config FSL_DMA - bool "Freescale MPC85xx/MPC83xx DMA support" - depends on PPC + tristate "Freescale Elo and Elo Plus DMA support" + depends on FSL_SOC select DMA_ENGINE ---help--- - Enable support for the Freescale DMA engine. Now, it support - MPC8560/40, MPC8555, MPC8548 and MPC8641 processors. - The MPC8349, MPC8360 is also supported. + Enable support for the Freescale Elo and Elo Plus DMA controllers. + The Elo is the DMA controller on some 82xx and 83xx parts, and the + Elo Plus is the DMA controller on 85xx and 86xx parts. config MV_XOR bool "Marvell XOR engine support" diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index e9b2638..0b95dcc 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -370,7 +370,10 @@ static int fsl_dma_alloc_chan_resources(struct dma_chan *chan, struct dma_client *client) { struct fsl_dma_chan *fsl_chan = to_fsl_chan(chan); - LIST_HEAD(tmp_list); + + /* Has this channel already been allocated? */ + if (fsl_chan->desc_pool) + return 1; /* We need the descriptor to be aligned to 32bytes * for meeting FSL DMA specification requirement. @@ -410,6 +413,8 @@ static void fsl_dma_free_chan_resources(struct dma_chan *chan) } spin_unlock_irqrestore(&fsl_chan->desc_lock, flags); dma_pool_destroy(fsl_chan->desc_pool); + + fsl_chan->desc_pool = NULL; } static struct dma_async_tx_descriptor * @@ -786,33 +791,29 @@ static void dma_do_tasklet(unsigned long data) fsl_chan_ld_cleanup(fsl_chan); } -static int __devinit of_fsl_dma_chan_probe(struct of_device *dev, - const struct of_device_id *match) +static int __devinit fsl_dma_chan_probe(struct fsl_dma_device *fdev, + struct device_node *node, u32 feature, const char *compatible) { - struct fsl_dma_device *fdev; struct fsl_dma_chan *new_fsl_chan; int err; - fdev = dev_get_drvdata(dev->dev.parent); - BUG_ON(!fdev); - /* alloc channel */ new_fsl_chan = kzalloc(sizeof(struct fsl_dma_chan), GFP_KERNEL); if (!new_fsl_chan) { - dev_err(&dev->dev, "No free memory for allocating " + dev_err(fdev->dev, "No free memory for allocating " "dma channels!\n"); return -ENOMEM; } /* get dma channel register base */ - err = of_address_to_resource(dev->node, 0, &new_fsl_chan->reg); + err = of_address_to_resource(node, 0, &new_fsl_chan->reg); if (err) { - dev_err(&dev->dev, "Can't get %s property 'reg'\n", - dev->node->full_name); + dev_err(fdev->dev, "Can't get %s property 'reg'\n", + node->full_name); goto err_no_reg; } - new_fsl_chan->feature = *(u32 *)match->data; + new_fsl_chan->feature = feature; if (!fdev->feature) fdev->feature = new_fsl_chan->feature; @@ -822,13 +823,13 @@ static int __devinit of_fsl_dma_chan_probe(struct of_device *dev, */ WARN_ON(fdev->feature != new_fsl_chan->feature); - new_fsl_chan->dev = &dev->dev; + new_fsl_chan->dev = &new_fsl_chan->common.dev; new_fsl_chan->reg_base = ioremap(new_fsl_chan->reg.start, new_fsl_chan->reg.end - new_fsl_chan->reg.start + 1); new_fsl_chan->id = ((new_fsl_chan->reg.start - 0x100) & 0xfff) >> 7; if (new_fsl_chan->id > FSL_DMA_MAX_CHANS_PER_DEVICE) { - dev_err(&dev->dev, "There is no %d channel!\n", + dev_err(fdev->dev, "There is no %d channel!\n", new_fsl_chan->id); err = -EINVAL; goto err_no_chan; @@ -862,20 +863,20 @@ static int __devinit of_fsl_dma_chan_probe(struct of_device *dev, &fdev->common.channels); fdev->common.chancnt++; - new_fsl_chan->irq = irq_of_parse_and_map(dev->node, 0); + new_fsl_chan->irq = irq_of_parse_and_map(node, 0); if (new_fsl_chan->irq != NO_IRQ) { err = request_irq(new_fsl_chan->irq, &fsl_dma_chan_do_interrupt, IRQF_SHARED, "fsldma-channel", new_fsl_chan); if (err) { - dev_err(&dev->dev, "DMA channel %s request_irq error " - "with return %d\n", dev->node->full_name, err); + dev_err(fdev->dev, "DMA channel %s request_irq error " + "with return %d\n", node->full_name, err); goto err_no_irq; } } - dev_info(&dev->dev, "#%d (%s), irq %d\n", new_fsl_chan->id, - match->compatible, new_fsl_chan->irq); + dev_info(fdev->dev, "#%d (%s), irq %d\n", new_fsl_chan->id, + compatible, new_fsl_chan->irq); return 0; @@ -888,38 +889,20 @@ err_no_reg: return err; } -const u32 mpc8540_dma_ip_feature = FSL_DMA_IP_85XX | FSL_DMA_BIG_ENDIAN; -const u32 mpc8349_dma_ip_feature = FSL_DMA_IP_83XX | FSL_DMA_LITTLE_ENDIAN; - -static struct of_device_id of_fsl_dma_chan_ids[] = { - { - .compatible = "fsl,eloplus-dma-channel", - .data = (void *)&mpc8540_dma_ip_feature, - }, - { - .compatible = "fsl,elo-dma-channel", - .data = (void *)&mpc8349_dma_ip_feature, - }, - {} -}; - -static struct of_platform_driver of_fsl_dma_chan_driver = { - .name = "of-fsl-dma-channel", - .match_table = of_fsl_dma_chan_ids, - .probe = of_fsl_dma_chan_probe, -}; - -static __init int of_fsl_dma_chan_init(void) +static void fsl_dma_chan_remove(struct fsl_dma_chan *fchan) { - return of_register_platform_driver(&of_fsl_dma_chan_driver); + free_irq(fchan->irq, fchan); + list_del(&fchan->common.device_node); + iounmap(fchan->reg_base); + kfree(fchan); } static int __devinit of_fsl_dma_probe(struct of_device *dev, const struct of_device_id *match) { int err; - unsigned int irq; struct fsl_dma_device *fdev; + struct device_node *child; fdev = kzalloc(sizeof(struct fsl_dma_device), GFP_KERNEL); if (!fdev) { @@ -953,9 +936,9 @@ static int __devinit of_fsl_dma_probe(struct of_device *dev, fdev->common.device_issue_pending = fsl_dma_memcpy_issue_pending; fdev->common.dev = &dev->dev; - irq = irq_of_parse_and_map(dev->node, 0); - if (irq != NO_IRQ) { - err = request_irq(irq, &fsl_dma_do_interrupt, IRQF_SHARED, + fdev->irq = irq_of_parse_and_map(dev->node, 0); + if (fdev->irq != NO_IRQ) { + err = request_irq(fdev->irq, &fsl_dma_do_interrupt, IRQF_SHARED, "fsldma-device", fdev); if (err) { dev_err(&dev->dev, "DMA device request_irq error " @@ -965,7 +948,21 @@ static int __devinit of_fsl_dma_probe(struct of_device *dev, } dev_set_drvdata(&(dev->dev), fdev); - of_platform_bus_probe(dev->node, of_fsl_dma_chan_ids, &dev->dev); + + /* We cannot use of_platform_bus_probe() because there is no + * of_platform_bus_remove. Instead, we manually instantiate every DMA + * channel object. + */ + for_each_child_of_node(dev->node, child) { + if (of_device_is_compatible(child, "fsl,eloplus-dma-channel")) + fsl_dma_chan_probe(fdev, child, + FSL_DMA_IP_85XX | FSL_DMA_BIG_ENDIAN, + "fsl,eloplus-dma-channel"); + if (of_device_is_compatible(child, "fsl,elo-dma-channel")) + fsl_dma_chan_probe(fdev, child, + FSL_DMA_IP_83XX | FSL_DMA_LITTLE_ENDIAN, + "fsl,elo-dma-channel"); + } dma_async_device_register(&fdev->common); return 0; @@ -977,6 +974,30 @@ err_no_reg: return err; } +static int of_fsl_dma_remove(struct of_device *of_dev) +{ + struct fsl_dma_device *fdev; + unsigned int i; + + fdev = dev_get_drvdata(&of_dev->dev); + + dma_async_device_unregister(&fdev->common); + + for (i = 0; i < FSL_DMA_MAX_CHANS_PER_DEVICE; i++) + if (fdev->chan[i]) + fsl_dma_chan_remove(fdev->chan[i]); + + if (fdev->irq != NO_IRQ) + free_irq(fdev->irq, fdev); + + iounmap(fdev->reg_base); + + kfree(fdev); + dev_set_drvdata(&of_dev->dev, NULL); + + return 0; +} + static struct of_device_id of_fsl_dma_ids[] = { { .compatible = "fsl,eloplus-dma", }, { .compatible = "fsl,elo-dma", }, @@ -984,15 +1005,32 @@ static struct of_device_id of_fsl_dma_ids[] = { }; static struct of_platform_driver of_fsl_dma_driver = { - .name = "of-fsl-dma", + .name = "fsl-elo-dma", .match_table = of_fsl_dma_ids, .probe = of_fsl_dma_probe, + .remove = of_fsl_dma_remove, }; static __init int of_fsl_dma_init(void) { - return of_register_platform_driver(&of_fsl_dma_driver); + int ret; + + pr_info("Freescale Elo / Elo Plus DMA driver\n"); + + ret = of_register_platform_driver(&of_fsl_dma_driver); + if (ret) + pr_err("fsldma: failed to register platform driver\n"); + + return ret; +} + +static void __exit of_fsl_dma_exit(void) +{ + of_unregister_platform_driver(&of_fsl_dma_driver); } -subsys_initcall(of_fsl_dma_chan_init); subsys_initcall(of_fsl_dma_init); +module_exit(of_fsl_dma_exit); + +MODULE_DESCRIPTION("Freescale Elo / Elo Plus DMA driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h index 6faf07b..4f21a51 100644 --- a/drivers/dma/fsldma.h +++ b/drivers/dma/fsldma.h @@ -114,6 +114,7 @@ struct fsl_dma_device { struct dma_device common; struct fsl_dma_chan *chan[FSL_DMA_MAX_CHANS_PER_DEVICE]; u32 feature; /* The same as DMA channels */ + int irq; /* Channel IRQ */ }; /* Define macros for fsl_dma_chan->feature property */ -- cgit v0.10.2 From 3afe7eb37f4d47f31d30a81c1b42ca02eab01e44 Mon Sep 17 00:00:00 2001 From: Alexander Belyakov Date: Thu, 25 Sep 2008 17:53:24 +0400 Subject: [MTD] [NOR] fix cfi_cmdset_0001 FL_SYNCING race (take 2) The patch fixes CFI issue with multipartitional devices leading to the set of errors or even deadlock. The problem is CFI FL_SYNCING state race with flash operations (e.g. erase suspend). It is reproduced by running intensive writes on one JFFS2 partition and simultaneously performing mount/unmount cycle on another partition of the same chip. Signed-off-by: Alexander Belyakov Acked-by: Nicolas Pitre Signed-off-by: David Woodhouse diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c index 5157e3c..c93a8be 100644 --- a/drivers/mtd/chips/cfi_cmdset_0001.c +++ b/drivers/mtd/chips/cfi_cmdset_0001.c @@ -725,6 +725,10 @@ static int chip_ready (struct map_info *map, struct flchip *chip, unsigned long struct cfi_pri_intelext *cfip = cfi->cmdset_priv; unsigned long timeo = jiffies + HZ; + /* Prevent setting state FL_SYNCING for chip in suspended state. */ + if (mode == FL_SYNCING && chip->oldstate != FL_READY) + goto sleep; + switch (chip->state) { case FL_STATUS: @@ -830,8 +834,9 @@ static int get_chip(struct map_info *map, struct flchip *chip, unsigned long adr DECLARE_WAITQUEUE(wait, current); retry: - if (chip->priv && (mode == FL_WRITING || mode == FL_ERASING - || mode == FL_OTP_WRITE || mode == FL_SHUTDOWN)) { + if (chip->priv && + (mode == FL_WRITING || mode == FL_ERASING || mode == FL_OTP_WRITE + || mode == FL_SHUTDOWN) && chip->state != FL_SYNCING) { /* * OK. We have possibility for contention on the write/erase * operations which are global to the real chip and not per @@ -881,6 +886,14 @@ static int get_chip(struct map_info *map, struct flchip *chip, unsigned long adr return ret; } spin_lock(&shared->lock); + + /* We should not own chip if it is already + * in FL_SYNCING state. Put contender and retry. */ + if (chip->state == FL_SYNCING) { + put_chip(map, contender, contender->start); + spin_unlock(contender->mutex); + goto retry; + } spin_unlock(contender->mutex); } -- cgit v0.10.2 From e416de5e61e1a9b7f987804cbb67230b5f5293c6 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 23 Sep 2008 17:25:10 +0100 Subject: Export the ROM enable/disable helpers .... so that they can be used by MTD map drivers. Lets us close #9420 Signed-off-by: Alan Cox Signed-off-by: David Woodhouse diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c index bd5c0e0..1f5f614 100644 --- a/drivers/pci/rom.c +++ b/drivers/pci/rom.c @@ -21,7 +21,7 @@ * between the ROM and other resources, so enabling it may disable access * to MMIO registers or other card memory. */ -static int pci_enable_rom(struct pci_dev *pdev) +int pci_enable_rom(struct pci_dev *pdev) { struct resource *res = pdev->resource + PCI_ROM_RESOURCE; struct pci_bus_region region; @@ -45,7 +45,7 @@ static int pci_enable_rom(struct pci_dev *pdev) * Disable ROM decoding on a PCI device by turning off the last bit in the * ROM BAR. */ -static void pci_disable_rom(struct pci_dev *pdev) +void pci_disable_rom(struct pci_dev *pdev) { u32 rom_addr; pci_read_config_dword(pdev, pdev->rom_base_reg, &rom_addr); @@ -260,3 +260,5 @@ void pci_cleanup_rom(struct pci_dev *pdev) EXPORT_SYMBOL(pci_map_rom); EXPORT_SYMBOL(pci_unmap_rom); +EXPORT_SYMBOL_GPL(pci_enable_rom); +EXPORT_SYMBOL_GPL(pci_disable_rom); diff --git a/include/linux/pci.h b/include/linux/pci.h index c0e1400..7a4cee0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -631,6 +631,8 @@ int __must_check pci_assign_resource(struct pci_dev *dev, int i); int pci_select_bars(struct pci_dev *dev, unsigned long flags); /* ROM control related routines */ +int pci_enable_rom(struct pci_dev *pdev); +void pci_disable_rom(struct pci_dev *pdev); void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size); void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom); size_t pci_get_rom_size(void __iomem *rom, size_t size); -- cgit v0.10.2 From 4ab13943612673ef0822e1a041a9e629ba13a87c Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 23 Sep 2008 17:25:10 +0100 Subject: [MTD] [NOR] intel_dc21285 switch to ROM API Now that the needed helpers are exported, it becomes a nice simple switch over. Closes #9420 Signed-off-by: Alan Cox Signed-off-by: David Woodhouse diff --git a/drivers/mtd/maps/pci.c b/drivers/mtd/maps/pci.c index 5c6a25c..d978c2e 100644 --- a/drivers/mtd/maps/pci.c +++ b/drivers/mtd/maps/pci.c @@ -203,15 +203,8 @@ intel_dc21285_init(struct pci_dev *dev, struct map_pci_info *map) * not enabled, should we be allocating a new resource for it * or simply enabling it? */ - if (!(pci_resource_flags(dev, PCI_ROM_RESOURCE) & - IORESOURCE_ROM_ENABLE)) { - u32 val; - pci_resource_flags(dev, PCI_ROM_RESOURCE) |= IORESOURCE_ROM_ENABLE; - pci_read_config_dword(dev, PCI_ROM_ADDRESS, &val); - val |= PCI_ROM_ADDRESS_ENABLE; - pci_write_config_dword(dev, PCI_ROM_ADDRESS, val); - printk("%s: enabling expansion ROM\n", pci_name(dev)); - } + pci_enable_rom(dev); + printk("%s: enabling expansion ROM\n", pci_name(dev)); } if (!len || !base) @@ -240,10 +233,7 @@ intel_dc21285_exit(struct pci_dev *dev, struct map_pci_info *map) /* * We need to undo the PCI BAR2/PCI ROM BAR address alteration. */ - pci_resource_flags(dev, PCI_ROM_RESOURCE) &= ~IORESOURCE_ROM_ENABLE; - pci_read_config_dword(dev, PCI_ROM_ADDRESS, &val); - val &= ~PCI_ROM_ADDRESS_ENABLE; - pci_write_config_dword(dev, PCI_ROM_ADDRESS, val); + pci_disable_rom(dev); } static unsigned long -- cgit v0.10.2 From f324277cf70ad284dd99acf5ac5101e32bc8c55b Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Mon, 22 Sep 2008 14:49:52 -0700 Subject: [MTD] [MAPS] Maps: make uclinux mapping driver depend on MTD_RAM ...since it only probes that Signed-off-by: Mike Frysinger Signed-off-by: Bryan Wu Signed-off-by: Andrew Morton Signed-off-by: David Woodhouse diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig index 3ae76ec..5ea1693 100644 --- a/drivers/mtd/maps/Kconfig +++ b/drivers/mtd/maps/Kconfig @@ -491,7 +491,7 @@ config MTD_BFIN_ASYNC config MTD_UCLINUX tristate "Generic uClinux RAM/ROM filesystem support" - depends on MTD_PARTITIONS && !MMU + depends on MTD_PARTITIONS && MTD_RAM && !MMU help Map driver to support image based filesystems for uClinux. -- cgit v0.10.2 From 7086efe1c1536f6bc160e7d60a9bfd645b91f279 Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Fri, 12 Sep 2008 09:54:39 -0700 Subject: timers: fix itimer/many thread hang, v3 - fix UP lockup - another set of UP/SMP cleanups and simplifications Signed-off-by: Frank Mayhar Signed-off-by: Ingo Molnar diff --git a/include/linux/sched.h b/include/linux/sched.h index b982fb4..23d9d54 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2134,7 +2134,6 @@ static inline int thread_group_cputime_clone_thread(struct task_struct *curr) return thread_group_cputime_alloc(curr); } - static inline void thread_group_cputime_free(struct signal_struct *sig) { free_percpu(sig->cputime.totals); diff --git a/kernel/sched.c b/kernel/sched.c index 260c22c..29a3152 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4046,7 +4046,6 @@ unsigned long long task_delta_exec(struct task_struct *p) unsigned long flags; u64 ns = 0; - rq = task_rq_lock(p, &flags); if (task_current(rq, p)) { u64 delta_exec; diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index d6903bd..b8c1569 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -276,133 +276,83 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) * on CONFIG_SCHEDSTATS. */ -#ifdef CONFIG_SMP - /** - * thread_group_cputime_account_user - Maintain utime for a thread group. + * account_group_user_time - Maintain utime for a thread group. * - * @tgtimes: Pointer to thread_group_cputime structure. - * @cputime: Time value by which to increment the utime field of that - * structure. + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the utime field of the + * thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the utime field there. */ -static inline void thread_group_cputime_account_user( - struct thread_group_cputime *tgtimes, - cputime_t cputime) +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) { - if (tgtimes->totals) { + struct signal_struct *sig; + + sig = tsk->signal; + if (unlikely(!sig)) + return; + if (sig->cputime.totals) { struct task_cputime *times; - times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times = per_cpu_ptr(sig->cputime.totals, get_cpu()); times->utime = cputime_add(times->utime, cputime); put_cpu_no_resched(); } } /** - * thread_group_cputime_account_system - Maintain stime for a thread group. + * account_group_system_time - Maintain stime for a thread group. * - * @tgtimes: Pointer to thread_group_cputime structure. - * @cputime: Time value by which to increment the stime field of that - * structure. + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the stime field of the + * thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the stime field there. */ -static inline void thread_group_cputime_account_system( - struct thread_group_cputime *tgtimes, - cputime_t cputime) +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) { - if (tgtimes->totals) { + struct signal_struct *sig; + + sig = tsk->signal; + if (unlikely(!sig)) + return; + if (sig->cputime.totals) { struct task_cputime *times; - times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times = per_cpu_ptr(sig->cputime.totals, get_cpu()); times->stime = cputime_add(times->stime, cputime); put_cpu_no_resched(); } } /** - * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a - * thread group. + * account_group_exec_runtime - Maintain exec runtime for a thread group. * - * @tgtimes: Pointer to thread_group_cputime structure. + * @tsk: Pointer to task structure. * @ns: Time value by which to increment the sum_exec_runtime field - * of that structure. + * of the thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the sum_exec_runtime field there. */ -static inline void thread_group_cputime_account_exec_runtime( - struct thread_group_cputime *tgtimes, - unsigned long long ns) +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) { - if (tgtimes->totals) { + struct signal_struct *sig; + + sig = tsk->signal; + if (unlikely(!sig)) + return; + if (sig->cputime.totals) { struct task_cputime *times; - times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times = per_cpu_ptr(sig->cputime.totals, get_cpu()); times->sum_exec_runtime += ns; put_cpu_no_resched(); } } - -#else /* CONFIG_SMP */ - -static inline void thread_group_cputime_account_user( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); -} - -static inline void thread_group_cputime_account_system( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); -} - -static inline void thread_group_cputime_account_exec_runtime( - struct thread_group_cputime *tgtimes, - unsigned long long ns) -{ - tgtimes->totals->sum_exec_runtime += ns; -} - -#endif /* CONFIG_SMP */ - -/* - * These are the generic time-accounting routines that use the above - * functions. They are the functions actually called by the scheduler. - */ -static inline void account_group_user_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_user(&sig->cputime, cputime); -} - -static inline void account_group_system_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_system(&sig->cputime, cputime); -} - -static inline void account_group_exec_runtime(struct task_struct *tsk, - unsigned long long ns) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_exec_runtime(&sig->cputime, ns); -} -- cgit v0.10.2 From 88856d67cf6b787447889915bafd541be20b8630 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 29 Sep 2008 19:43:44 +0900 Subject: sh: Fix up uaccess_64 put/get_user() cast warnings. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/uaccess_64.h b/arch/sh/include/asm/uaccess_64.h index 5580fd4..0042c90 100644 --- a/arch/sh/include/asm/uaccess_64.h +++ b/arch/sh/include/asm/uaccess_64.h @@ -26,16 +26,20 @@ do { \ retval = 0; \ switch (size) { \ case 1: \ - retval = __get_user_asm_b(x, ptr); \ + retval = __get_user_asm_b((void *)&x, \ + (long)ptr); \ break; \ case 2: \ - retval = __get_user_asm_w(x, ptr); \ + retval = __get_user_asm_w((void *)&x, \ + (long)ptr); \ break; \ case 4: \ - retval = __get_user_asm_l(x, ptr); \ + retval = __get_user_asm_l((void *)&x, \ + (long)ptr); \ break; \ case 8: \ - retval = __get_user_asm_q(x, ptr); \ + retval = __get_user_asm_q((void *)&x, \ + (long)ptr); \ break; \ default: \ __get_user_unknown(); \ @@ -54,16 +58,20 @@ do { \ retval = 0; \ switch (size) { \ case 1: \ - retval = __put_user_asm_b(x, ptr); \ + retval = __put_user_asm_b((void *)&x, \ + (long)ptr); \ break; \ case 2: \ - retval = __put_user_asm_w(x, ptr); \ + retval = __put_user_asm_w((void *)&x, \ + (long)ptr); \ break; \ case 4: \ - retval = __put_user_asm_l(x, ptr); \ + retval = __put_user_asm_l((void *)&x, \ + (long)ptr); \ break; \ case 8: \ - retval = __put_user_asm_q(x, ptr); \ + retval = __put_user_asm_q((void *)&x, \ + (long)ptr); \ break; \ default: \ __put_user_unknown(); \ -- cgit v0.10.2 From 091db04559a62a00769553c9120623c2f6bc8b4d Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 29 Sep 2008 19:44:40 +0900 Subject: sh: Fix up signal_64 cast warnings. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/signal_64.c b/arch/sh/kernel/signal_64.c index 0582ae4..ce3e851 100644 --- a/arch/sh/kernel/signal_64.c +++ b/arch/sh/kernel/signal_64.c @@ -563,7 +563,7 @@ static void setup_frame(int sig, struct k_sigaction *ka, (DEREF_REG_PR | NEFF_MASK) : DEREF_REG_PR; if (__copy_to_user(frame->retcode, - (unsigned long long)sa_default_restorer & (~1), 16) != 0) + (void *)((unsigned long)sa_default_restorer & (~1)), 16) != 0) goto give_sigsegv; /* Cohere the trampoline with the I-cache. */ @@ -681,7 +681,7 @@ static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, (DEREF_REG_PR | NEFF_MASK) : DEREF_REG_PR; if (__copy_to_user(frame->retcode, - (unsigned long long)sa_default_rt_restorer & (~1), 16) != 0) + (void *)((unsigned long)sa_default_rt_restorer & (~1)), 16) != 0) goto give_sigsegv; flush_icache_range(DEREF_REG_PR-1, DEREF_REG_PR-1+15); -- cgit v0.10.2 From 50b72e600b62bcdf40971e55f609cf4771346cc1 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 29 Sep 2008 19:45:16 +0900 Subject: sh: sh_ksyms_64 needs __strncpy_from_user() definition. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/uaccess_64.h b/arch/sh/include/asm/uaccess_64.h index 0042c90..56fd20b 100644 --- a/arch/sh/include/asm/uaccess_64.h +++ b/arch/sh/include/asm/uaccess_64.h @@ -85,5 +85,7 @@ extern long __put_user_asm_q(void *, long); extern void __put_user_unknown(void); extern long __strnlen_user(const char *__s, long __n); +extern int __strncpy_from_user(unsigned long __dest, + unsigned long __user __src, int __count); #endif /* __ASM_SH_UACCESS_64_H */ -- cgit v0.10.2 From 4d01cdafbafc0fdeb730838ca38a48e5ca2894cd Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 29 Sep 2008 20:09:17 +0900 Subject: sh: SH-5 clk fwk support. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/cpu/sh5/Makefile b/arch/sh/kernel/cpu/sh5/Makefile index 8646363..ce4602e 100644 --- a/arch/sh/kernel/cpu/sh5/Makefile +++ b/arch/sh/kernel/cpu/sh5/Makefile @@ -5,3 +5,8 @@ obj-y := entry.o probe.o switchto.o obj-$(CONFIG_SH_FPU) += fpu.o obj-$(CONFIG_KALLSYMS) += unwind.o + +# Primary on-chip clocks (common) +clock-$(CONFIG_CPU_SH5) := clock-sh5.o + +obj-y += $(clock-y) diff --git a/arch/sh/kernel/cpu/sh5/clock-sh5.c b/arch/sh/kernel/cpu/sh5/clock-sh5.c new file mode 100644 index 0000000..52c4924 --- /dev/null +++ b/arch/sh/kernel/cpu/sh5/clock-sh5.c @@ -0,0 +1,79 @@ +/* + * arch/sh/kernel/cpu/sh5/clock-sh5.c + * + * SH-5 support for the clock framework + * + * Copyright (C) 2008 Paul Mundt + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ +#include +#include +#include +#include + +static int ifc_table[] = { 2, 4, 6, 8, 10, 12, 16, 24 }; + +/* Clock, Power and Reset Controller */ +#define CPRC_BLOCK_OFF 0x01010000 +#define CPRC_BASE (PHYS_PERIPHERAL_BLOCK + CPRC_BLOCK_OFF) + +static unsigned long cprc_base; + +static void master_clk_init(struct clk *clk) +{ + int idx = (ctrl_inl(cprc_base + 0x00) >> 6) & 0x0007; + clk->rate *= ifc_table[idx]; +} + +static struct clk_ops sh5_master_clk_ops = { + .init = master_clk_init, +}; + +static void module_clk_recalc(struct clk *clk) +{ + int idx = (ctrl_inw(cprc_base) >> 12) & 0x0007; + clk->rate = clk->parent->rate / ifc_table[idx]; +} + +static struct clk_ops sh5_module_clk_ops = { + .recalc = module_clk_recalc, +}; + +static void bus_clk_recalc(struct clk *clk) +{ + int idx = (ctrl_inw(cprc_base) >> 3) & 0x0007; + clk->rate = clk->parent->rate / ifc_table[idx]; +} + +static struct clk_ops sh5_bus_clk_ops = { + .recalc = bus_clk_recalc, +}; + +static void cpu_clk_recalc(struct clk *clk) +{ + int idx = (ctrl_inw(cprc_base) & 0x0007); + clk->rate = clk->parent->rate / ifc_table[idx]; +} + +static struct clk_ops sh5_cpu_clk_ops = { + .recalc = cpu_clk_recalc, +}; + +static struct clk_ops *sh5_clk_ops[] = { + &sh5_master_clk_ops, + &sh5_module_clk_ops, + &sh5_bus_clk_ops, + &sh5_cpu_clk_ops, +}; + +void __init arch_init_clk_ops(struct clk_ops **ops, int idx) +{ + cprc_base = onchip_remap(CPRC_BASE, 1024, "CPRC"); + BUG_ON(!cprc_base); + + if (idx < ARRAY_SIZE(sh5_clk_ops)) + *ops = sh5_clk_ops[idx]; +} diff --git a/arch/sh/kernel/time_64.c b/arch/sh/kernel/time_64.c index 791edab..bbb2af1 100644 --- a/arch/sh/kernel/time_64.c +++ b/arch/sh/kernel/time_64.c @@ -39,6 +39,7 @@ #include #include #include +#include #define TMU_TOCR_INIT 0x00 #define TMU0_TCR_INIT 0x0020 @@ -51,14 +52,6 @@ #define RTC_RCR1_CIE 0x10 /* Carry Interrupt Enable */ #define RTC_RCR1 (rtc_base + 0x38) -/* Clock, Power and Reset Controller */ -#define CPRC_BLOCK_OFF 0x01010000 -#define CPRC_BASE PHYS_PERIPHERAL_BLOCK + CPRC_BLOCK_OFF - -#define FRQCR (cprc_base+0x0) -#define WTCSR (cprc_base+0x0018) -#define STBCR (cprc_base+0x0030) - /* Time Management Unit */ #define TMU_BLOCK_OFF 0x01020000 #define TMU_BASE PHYS_PERIPHERAL_BLOCK + TMU_BLOCK_OFF @@ -293,103 +286,17 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } - -static __init unsigned int get_cpu_hz(void) -{ - unsigned int count; - unsigned long __dummy; - unsigned long ctc_val_init, ctc_val; - - /* - ** Regardless the toolchain, force the compiler to use the - ** arbitrary register r3 as a clock tick counter. - ** NOTE: r3 must be in accordance with sh64_rtc_interrupt() - */ - register unsigned long long __rtc_irq_flag __asm__ ("r3"); - - local_irq_enable(); - do {} while (ctrl_inb(rtc_base) != 0); - ctrl_outb(RTC_RCR1_CIE, RTC_RCR1); /* Enable carry interrupt */ - - /* - * r3 is arbitrary. CDC does not support "=z". - */ - ctc_val_init = 0xffffffff; - ctc_val = ctc_val_init; - - asm volatile("gettr tr0, %1\n\t" - "putcon %0, " __CTC "\n\t" - "and %2, r63, %2\n\t" - "pta $+4, tr0\n\t" - "beq/l %2, r63, tr0\n\t" - "ptabs %1, tr0\n\t" - "getcon " __CTC ", %0\n\t" - : "=r"(ctc_val), "=r" (__dummy), "=r" (__rtc_irq_flag) - : "0" (0)); - local_irq_disable(); - /* - * SH-3: - * CPU clock = 4 stages * loop - * tst rm,rm if id ex - * bt/s 1b if id ex - * add #1,rd if id ex - * (if) pipe line stole - * tst rm,rm if id ex - * .... - * - * - * SH-4: - * CPU clock = 6 stages * loop - * I don't know why. - * .... - * - * SH-5: - * Use CTC register to count. This approach returns the right value - * even if the I-cache is disabled (e.g. whilst debugging.) - * - */ - - count = ctc_val_init - ctc_val; /* CTC counts down */ - - /* - * This really is count by the number of clock cycles - * by the ratio between a complete R64CNT - * wrap-around (128) and CUI interrupt being raised (64). - */ - return count*2; -} - -static irqreturn_t sh64_rtc_interrupt(int irq, void *dev_id) -{ - struct pt_regs *regs = get_irq_regs(); - - ctrl_outb(0, RTC_RCR1); /* Disable Carry Interrupts */ - regs->regs[3] = 1; /* Using r3 */ - - return IRQ_HANDLED; -} - static struct irqaction irq0 = { .handler = timer_interrupt, .flags = IRQF_DISABLED, .mask = CPU_MASK_NONE, .name = "timer", }; -static struct irqaction irq1 = { - .handler = sh64_rtc_interrupt, - .flags = IRQF_DISABLED, - .mask = CPU_MASK_NONE, - .name = "rtc", -}; void __init time_init(void) { - unsigned int cpu_clock, master_clock, bus_clock, module_clock; unsigned long interval; - unsigned long frqcr, ifc, pfc; - static int ifc_table[] = { 2, 4, 6, 8, 10, 12, 16, 24 }; -#define bfc_table ifc_table /* Same */ -#define pfc_table ifc_table /* Same */ + struct clk *clk; tmu_base = onchip_remap(TMU_BASE, 1024, "TMU"); if (!tmu_base) { @@ -401,50 +308,19 @@ void __init time_init(void) panic("Unable to remap RTC\n"); } - cprc_base = onchip_remap(CPRC_BASE, 1024, "CPRC"); - if (!cprc_base) { - panic("Unable to remap CPRC\n"); - } + clk = clk_get(NULL, "cpu_clk"); + scaled_recip_ctc_ticks_per_jiffy = ((1ULL << CTC_JIFFY_SCALE_SHIFT) / + (unsigned long long)(clk_get_rate(clk) / HZ)); rtc_sh_get_time(&xtime); setup_irq(TIMER_IRQ, &irq0); - setup_irq(RTC_IRQ, &irq1); - - /* Check how fast it is.. */ - cpu_clock = get_cpu_hz(); - - /* Note careful order of operations to maintain reasonable precision and avoid overflow. */ - scaled_recip_ctc_ticks_per_jiffy = ((1ULL << CTC_JIFFY_SCALE_SHIFT) / (unsigned long long)(cpu_clock / HZ)); - - free_irq(RTC_IRQ, NULL); - - printk("CPU clock: %d.%02dMHz\n", - (cpu_clock / 1000000), (cpu_clock % 1000000)/10000); - { - unsigned short bfc; - frqcr = ctrl_inl(FRQCR); - ifc = ifc_table[(frqcr>> 6) & 0x0007]; - bfc = bfc_table[(frqcr>> 3) & 0x0007]; - pfc = pfc_table[(frqcr>> 12) & 0x0007]; - master_clock = cpu_clock * ifc; - bus_clock = master_clock/bfc; - } - printk("Bus clock: %d.%02dMHz\n", - (bus_clock/1000000), (bus_clock % 1000000)/10000); - module_clock = master_clock/pfc; - printk("Module clock: %d.%02dMHz\n", - (module_clock/1000000), (module_clock % 1000000)/10000); - interval = (module_clock/(HZ*4)); + clk = clk_get(NULL, "module_clk"); + interval = (clk_get_rate(clk)/(HZ*4)); printk("Interval = %ld\n", interval); - current_cpu_data.cpu_clock = cpu_clock; - current_cpu_data.master_clock = master_clock; - current_cpu_data.bus_clock = bus_clock; - current_cpu_data.module_clock = module_clock; - /* Start TMU0 */ ctrl_outb(TMU_TSTR_OFF, TMU_TSTR); ctrl_outb(TMU_TOCR_INIT, TMU_TOCR); @@ -454,36 +330,6 @@ void __init time_init(void) ctrl_outb(TMU_TSTR_INIT, TMU_TSTR); } -void enter_deep_standby(void) -{ - /* Disable watchdog timer */ - ctrl_outl(0xa5000000, WTCSR); - /* Configure deep standby on sleep */ - ctrl_outl(0x03, STBCR); - -#ifdef CONFIG_SH_ALPHANUMERIC - { - extern void mach_alphanum(int position, unsigned char value); - extern void mach_alphanum_brightness(int setting); - char halted[] = "Halted. "; - int i; - mach_alphanum_brightness(6); /* dimmest setting above off */ - for (i=0; i<8; i++) { - mach_alphanum(i, halted[i]); - } - asm __volatile__ ("synco"); - } -#endif - - asm __volatile__ ("sleep"); - asm __volatile__ ("synci"); - asm __volatile__ ("nop"); - asm __volatile__ ("nop"); - asm __volatile__ ("nop"); - asm __volatile__ ("nop"); - panic("Unexpected wakeup!\n"); -} - static struct resource rtc_resources[] = { [0] = { /* RTC base, filled in by rtc_init */ -- cgit v0.10.2 From bdeb3be7cc6911477b7169dad62a427d7a263d02 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 29 Sep 2008 20:14:44 +0900 Subject: sh: Use clk fwk for preset lpj on sh64, too. Signed-off-by: Paul Mundt diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 71be7ff..dca54cc 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -28,7 +28,6 @@ config SUPERH32 config SUPERH64 def_bool y if CPU_SH5 - select GENERIC_CALIBRATE_DELAY config ARCH_DEFCONFIG string -- cgit v0.10.2 From 1508487e7f16d992ad23cabd3712563ff912f413 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 30 Sep 2008 08:28:17 +0200 Subject: timers: fix itimer/many thread hang, fix fix bogus rq dereference: v3 removed the locking but also removed the rq initialization. Signed-off-by: Ingo Molnar diff --git a/kernel/sched.c b/kernel/sched.c index 29a3152..ebb03de 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4042,10 +4042,12 @@ EXPORT_PER_CPU_SYMBOL(kstat); */ unsigned long long task_delta_exec(struct task_struct *p) { - struct rq *rq; unsigned long flags; + struct rq *rq; u64 ns = 0; + rq = task_rq_lock(p, &flags); + if (task_current(rq, p)) { u64 delta_exec; @@ -4055,6 +4057,8 @@ unsigned long long task_delta_exec(struct task_struct *p) ns = delta_exec; } + task_rq_unlock(rq, &flags); + return ns; } -- cgit v0.10.2 From 948cfb219bbbc3c8e1b10a671ca88219fa42a052 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 20 Aug 2008 11:56:33 +0300 Subject: UBIFS: add a print, fix comments and more minor stuff This commit adds a reserved pool size print and tweaks the prints to make them look nicer. It also fixes and cleans-up some comments. Additionally, it deletes some blank lines to make the code look a little nicer. In other words, nothing essential. Signed-off-by: Artem Bityutskiy diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index 73db464..1a4973e 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -414,19 +414,21 @@ static int do_budget_space(struct ubifs_info *c) * @c->lst.empty_lebs + @c->freeable_cnt + @c->idx_gc_cnt - * @c->lst.taken_empty_lebs * - * @empty_lebs are available because they are empty. @freeable_cnt are - * available because they contain only free and dirty space and the - * index allocation always occurs after wbufs are synch'ed. - * @idx_gc_cnt are available because they are index LEBs that have been - * garbage collected (including trivial GC) and are awaiting the commit - * before they can be unmapped - note that the in-the-gaps method will - * grab these if it needs them. @taken_empty_lebs are empty_lebs that - * have already been allocated for some purpose (also includes those - * LEBs on the @idx_gc list). + * @c->lst.empty_lebs are available because they are empty. + * @c->freeable_cnt are available because they contain only free and + * dirty space, @c->idx_gc_cnt are available because they are index + * LEBs that have been garbage collected and are awaiting the commit + * before they can be used. And the in-the-gaps method will grab these + * if it needs them. @c->lst.taken_empty_lebs are empty LEBs that have + * already been allocated for some purpose. * - * Note, @taken_empty_lebs may temporarily be higher by one because of - * the way we serialize LEB allocations and budgeting. See a comment in - * 'ubifs_find_free_space()'. + * Note, @c->idx_gc_cnt is included to both @c->lst.empty_lebs (because + * these LEBs are empty) and to @c->lst.taken_empty_lebs (because they + * are taken until after the commit). + * + * Note, @c->lst.taken_empty_lebs may temporarily be higher by one + * because of the way we serialize LEB allocations and budgeting. See a + * comment in 'ubifs_find_free_space()'. */ lebs = c->lst.empty_lebs + c->freeable_cnt + c->idx_gc_cnt - c->lst.taken_empty_lebs; diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index 2ba93da..3659b88 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -125,6 +125,7 @@ static void adjust_lpt_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, } } } + /* Not greater than parent, so compare to children */ while (1) { /* Compare to left child */ @@ -576,7 +577,6 @@ const struct ubifs_lprops *ubifs_change_lp(struct ubifs_info *c, ubifs_assert(!(lprops->free & 7) && !(lprops->dirty & 7)); spin_lock(&c->space_lock); - if ((lprops->flags & LPROPS_TAKEN) && lprops->free == c->leb_size) c->lst.taken_empty_lebs -= 1; @@ -637,11 +637,8 @@ const struct ubifs_lprops *ubifs_change_lp(struct ubifs_info *c, c->lst.taken_empty_lebs += 1; change_category(c, lprops); - c->idx_gc_cnt += idx_gc_cnt; - spin_unlock(&c->space_lock); - return lprops; } @@ -1262,7 +1259,6 @@ static int scan_check_cb(struct ubifs_info *c, } ubifs_scan_destroy(sleb); - return LPT_SCAN_CONTINUE; out_print: diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 3f49020..667c72d 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1144,19 +1144,21 @@ static int mount_ubifs(struct ubifs_info *c) if (mounted_read_only) ubifs_msg("mounted read-only"); x = (long long)c->main_lebs * c->leb_size; - ubifs_msg("file system size: %lld bytes (%lld KiB, %lld MiB, %d LEBs)", - x, x >> 10, x >> 20, c->main_lebs); + ubifs_msg("file system size: %lld bytes (%lld KiB, %lld MiB, %d " + "LEBs)", x, x >> 10, x >> 20, c->main_lebs); x = (long long)c->log_lebs * c->leb_size + c->max_bud_bytes; - ubifs_msg("journal size: %lld bytes (%lld KiB, %lld MiB, %d LEBs)", - x, x >> 10, x >> 20, c->log_lebs + c->max_bud_cnt); - ubifs_msg("default compressor: %s", ubifs_compr_name(c->default_compr)); - ubifs_msg("media format %d, latest format %d", + ubifs_msg("journal size: %lld bytes (%lld KiB, %lld MiB, %d " + "LEBs)", x, x >> 10, x >> 20, c->log_lebs + c->max_bud_cnt); + ubifs_msg("media format: %d (latest is %d)", c->fmt_version, UBIFS_FORMAT_VERSION); + ubifs_msg("default compressor: %s", ubifs_compr_name(c->default_compr)); + ubifs_msg("reserved pool size: %llu bytes (%llu KiB)", + c->report_rp_size, c->report_rp_size >> 10); dbg_msg("compiled on: " __DATE__ " at " __TIME__); dbg_msg("min. I/O unit size: %d bytes", c->min_io_size); dbg_msg("LEB size: %d bytes (%d KiB)", - c->leb_size, c->leb_size / 1024); + c->leb_size, c->leb_size >> 10); dbg_msg("data journal heads: %d", c->jhead_cnt - NONDATA_JHEADS_CNT); dbg_msg("UUID: %02X%02X%02X%02X-%02X%02X" -- cgit v0.10.2 From 8d47aef43ba166bdd11d522307c61ab23aab61c3 Mon Sep 17 00:00:00 2001 From: Hirofumi Nakagawa Date: Thu, 21 Aug 2008 17:16:40 +0300 Subject: UBIFS: remove unneeded unlikely() IS_ERR() macro already has unlikely(), so do not use constructions like 'if (unlikely(IS_ERR())'. Signed-off-by: Hirofumi Nakagawa Signed-off-by: Artem Bityutskiy diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c index 47814cd..717d79c 100644 --- a/fs/ubifs/find.c +++ b/fs/ubifs/find.c @@ -901,11 +901,11 @@ static int get_idx_gc_leb(struct ubifs_info *c) * it is needed now for this commit. */ lp = ubifs_lpt_lookup_dirty(c, lnum); - if (unlikely(IS_ERR(lp))) + if (IS_ERR(lp)) return PTR_ERR(lp); lp = ubifs_change_lp(c, lp, LPROPS_NC, LPROPS_NC, lp->flags | LPROPS_INDEX, -1); - if (unlikely(IS_ERR(lp))) + if (IS_ERR(lp)) return PTR_ERR(lp); dbg_find("LEB %d, dirty %d and free %d flags %#x", lp->lnum, lp->dirty, lp->free, lp->flags); diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c index 02aba36..a6b633a 100644 --- a/fs/ubifs/gc.c +++ b/fs/ubifs/gc.c @@ -653,7 +653,7 @@ int ubifs_gc_start_commit(struct ubifs_info *c) */ while (1) { lp = ubifs_fast_find_freeable(c); - if (unlikely(IS_ERR(lp))) { + if (IS_ERR(lp)) { err = PTR_ERR(lp); goto out; } @@ -665,7 +665,7 @@ int ubifs_gc_start_commit(struct ubifs_info *c) if (err) goto out; lp = ubifs_change_lp(c, lp, c->leb_size, 0, lp->flags, 0); - if (unlikely(IS_ERR(lp))) { + if (IS_ERR(lp)) { err = PTR_ERR(lp); goto out; } @@ -680,7 +680,7 @@ int ubifs_gc_start_commit(struct ubifs_info *c) /* Record index freeable LEBs for unmapping after commit */ while (1) { lp = ubifs_fast_find_frdi_idx(c); - if (unlikely(IS_ERR(lp))) { + if (IS_ERR(lp)) { err = PTR_ERR(lp); goto out; } @@ -696,7 +696,7 @@ int ubifs_gc_start_commit(struct ubifs_info *c) /* Don't release the LEB until after the next commit */ flags = (lp->flags | LPROPS_TAKEN) ^ LPROPS_INDEX; lp = ubifs_change_lp(c, lp, c->leb_size, 0, flags, 1); - if (unlikely(IS_ERR(lp))) { + if (IS_ERR(lp)) { err = PTR_ERR(lp); kfree(idx_gc); goto out; diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 7634c59..ba13c92 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -284,7 +284,7 @@ static struct ubifs_znode *dirty_cow_znode(struct ubifs_info *c, } zn = copy_znode(c, znode); - if (unlikely(IS_ERR(zn))) + if (IS_ERR(zn)) return zn; if (zbr->len) { @@ -1128,7 +1128,7 @@ static struct ubifs_znode *dirty_cow_bottom_up(struct ubifs_info *c, ubifs_assert(znode == c->zroot.znode); znode = dirty_cow_znode(c, &c->zroot); } - if (unlikely(IS_ERR(znode)) || !p) + if (IS_ERR(znode) || !p) break; ubifs_assert(path[p - 1] >= 0); ubifs_assert(path[p - 1] < znode->child_cnt); diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 649bec7..cfd31e2 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -446,7 +446,7 @@ ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size) int type; xent = ubifs_tnc_next_ent(c, &key, &nm); - if (unlikely(IS_ERR(xent))) { + if (IS_ERR(xent)) { err = PTR_ERR(xent); break; } -- cgit v0.10.2 From 746103aca2ae2b044e32a6ab06a6536652124c99 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 27 Aug 2008 12:50:57 +0300 Subject: UBIFS: inline one-line functions 'ubifs_get_lprops()' and 'ubifs_release_lprops()' basically wrap mutex lock and unlock. We have them because we want lprops subsystem be separate and as independent as possible. And we planned better locking rules for lprops. Anyway, because they are short, it is better to inline them. Signed-off-by: Artem Bityutskiy diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index 3659b88..f27176e 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -461,18 +461,6 @@ static void change_category(struct ubifs_info *c, struct ubifs_lprops *lprops) } /** - * ubifs_get_lprops - get reference to LEB properties. - * @c: the UBIFS file-system description object - * - * This function locks lprops. Lprops have to be unlocked by - * 'ubifs_release_lprops()'. - */ -void ubifs_get_lprops(struct ubifs_info *c) -{ - mutex_lock(&c->lp_mutex); -} - -/** * calc_dark - calculate LEB dark space size. * @c: the UBIFS file-system description object * @spc: amount of free and dirty space in the LEB @@ -643,22 +631,6 @@ const struct ubifs_lprops *ubifs_change_lp(struct ubifs_info *c, } /** - * ubifs_release_lprops - release lprops lock. - * @c: the UBIFS file-system description object - * - * This function has to be called after each 'ubifs_get_lprops()' call to - * unlock lprops. - */ -void ubifs_release_lprops(struct ubifs_info *c) -{ - ubifs_assert(mutex_is_locked(&c->lp_mutex)); - ubifs_assert(c->lst.empty_lebs >= 0 && - c->lst.empty_lebs <= c->main_lebs); - - mutex_unlock(&c->lp_mutex); -} - -/** * ubifs_get_lp_stats - get lprops statistics. * @c: UBIFS file-system description object * @st: return statistics diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h index 4c12a92..4fa81d8 100644 --- a/fs/ubifs/misc.h +++ b/fs/ubifs/misc.h @@ -310,4 +310,31 @@ static inline int ubifs_tnc_lookup(struct ubifs_info *c, return ubifs_tnc_locate(c, key, node, NULL, NULL); } +/** + * ubifs_get_lprops - get reference to LEB properties. + * @c: the UBIFS file-system description object + * + * This function locks lprops. Lprops have to be unlocked by + * 'ubifs_release_lprops()'. + */ +static inline void ubifs_get_lprops(struct ubifs_info *c) +{ + mutex_lock(&c->lp_mutex); +} + +/** + * ubifs_release_lprops - release lprops lock. + * @c: the UBIFS file-system description object + * + * This function has to be called after each 'ubifs_get_lprops()' call to + * unlock lprops. + */ +static inline void ubifs_release_lprops(struct ubifs_info *c) +{ + ubifs_assert(mutex_is_locked(&c->lp_mutex)); + ubifs_assert(c->lst.empty_lebs >= 0 && + c->lst.empty_lebs <= c->main_lebs); + mutex_unlock(&c->lp_mutex); +} + #endif /* __UBIFS_MISC_H__ */ diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 17c620b..ce86549 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1586,12 +1586,10 @@ int ubifs_lpt_post_commit(struct ubifs_info *c); void ubifs_lpt_free(struct ubifs_info *c, int wr_only); /* lprops.c */ -void ubifs_get_lprops(struct ubifs_info *c); const struct ubifs_lprops *ubifs_change_lp(struct ubifs_info *c, const struct ubifs_lprops *lp, int free, int dirty, int flags, int idx_gc_cnt); -void ubifs_release_lprops(struct ubifs_info *c); void ubifs_get_lp_stats(struct ubifs_info *c, struct ubifs_lp_stats *stats); void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops, int cat); -- cgit v0.10.2 From a70948b564e9f6cb81115c606d46f5b74a77b7c2 Mon Sep 17 00:00:00 2001 From: Julien Brunel Date: Fri, 29 Aug 2008 11:08:32 +0200 Subject: UBIFS: use an IS_ERR test rather than a NULL test In case of error, the function kthread_create returns an ERR pointer, but never returns a NULL pointer. So a NULL test that comes before an IS_ERR test should be deleted. The semantic match that finds this problem is as follows: (http://www.emn.fr/x-info/coccinelle/) // @match_bad_null_test@ expression x, E; statement S1,S2; @@ x = kthread_create(...) ... when != x = E * if (x == NULL) S1 else S2 // Signed-off-by: Julien Brunel Signed-off-by: Julia Lawall Signed-off-by: Artem Bityutskiy diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 667c72d..d87b0cf 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1032,8 +1032,6 @@ static int mount_ubifs(struct ubifs_info *c) /* Create background thread */ c->bgt = kthread_create(ubifs_bg_thread, c, c->bgt_name); - if (!c->bgt) - c->bgt = ERR_PTR(-EINVAL); if (IS_ERR(c->bgt)) { err = PTR_ERR(c->bgt); c->bgt = NULL; @@ -1347,8 +1345,6 @@ static int ubifs_remount_rw(struct ubifs_info *c) /* Create background thread */ c->bgt = kthread_create(ubifs_bg_thread, c, c->bgt_name); - if (!c->bgt) - c->bgt = ERR_PTR(-EINVAL); if (IS_ERR(c->bgt)) { err = PTR_ERR(c->bgt); c->bgt = NULL; -- cgit v0.10.2 From 4793e7c5e1c88382ead18db5ca072bac54467318 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 2 Sep 2008 16:29:46 +0300 Subject: UBIFS: add bulk-read facility Some flash media are capable of reading sequentially at faster rates. UBIFS bulk-read facility is designed to take advantage of that, by reading in one go consecutive data nodes that are also located consecutively in the same LEB. Read speed on Arm platform with OneNAND goes from 17 MiB/s to 19 MiB/s. Signed-off-by: Adrian Hunter diff --git a/Documentation/filesystems/ubifs.txt b/Documentation/filesystems/ubifs.txt index 6a0d70a..340512c 100644 --- a/Documentation/filesystems/ubifs.txt +++ b/Documentation/filesystems/ubifs.txt @@ -86,6 +86,9 @@ norm_unmount (*) commit on unmount; the journal is committed fast_unmount do not commit on unmount; this option makes unmount faster, but the next mount slower because of the need to replay the journal. +bulk_read read more in one go to take advantage of flash + media that read faster sequentially +no_bulk_read (*) do not bulk-read Quick usage instructions diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 3d698e2..cdcfe95 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -577,8 +577,256 @@ out: return copied; } +/** + * populate_page - copy data nodes into a page for bulk-read. + * @c: UBIFS file-system description object + * @page: page + * @bu: bulk-read information + * @n: next zbranch slot + * + * This function returns %0 on success and a negative error code on failure. + */ +static int populate_page(struct ubifs_info *c, struct page *page, + struct bu_info *bu, int *n) +{ + int i = 0, nn = *n, offs = bu->zbranch[0].offs, hole = 1, read = 0; + struct inode *inode = page->mapping->host; + loff_t i_size = i_size_read(inode); + unsigned int page_block; + void *addr, *zaddr; + pgoff_t end_index; + + dbg_gen("ino %lu, pg %lu, i_size %lld, flags %#lx", + inode->i_ino, page->index, i_size, page->flags); + + addr = zaddr = kmap(page); + + end_index = (i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + if (!i_size || page->index > end_index) { + memset(addr, 0, PAGE_CACHE_SIZE); + goto out_hole; + } + + page_block = page->index << UBIFS_BLOCKS_PER_PAGE_SHIFT; + while (1) { + int err, len, out_len, dlen; + + if (nn >= bu->cnt || + key_block(c, &bu->zbranch[nn].key) != page_block) + memset(addr, 0, UBIFS_BLOCK_SIZE); + else { + struct ubifs_data_node *dn; + + dn = bu->buf + (bu->zbranch[nn].offs - offs); + + ubifs_assert(dn->ch.sqnum > + ubifs_inode(inode)->creat_sqnum); + + len = le32_to_cpu(dn->size); + if (len <= 0 || len > UBIFS_BLOCK_SIZE) + goto out_err; + + dlen = le32_to_cpu(dn->ch.len) - UBIFS_DATA_NODE_SZ; + out_len = UBIFS_BLOCK_SIZE; + err = ubifs_decompress(&dn->data, dlen, addr, &out_len, + le16_to_cpu(dn->compr_type)); + if (err || len != out_len) + goto out_err; + + if (len < UBIFS_BLOCK_SIZE) + memset(addr + len, 0, UBIFS_BLOCK_SIZE - len); + + nn += 1; + hole = 0; + read = (i << UBIFS_BLOCK_SHIFT) + len; + } + if (++i >= UBIFS_BLOCKS_PER_PAGE) + break; + addr += UBIFS_BLOCK_SIZE; + page_block += 1; + } + + if (end_index == page->index) { + int len = i_size & (PAGE_CACHE_SIZE - 1); + + if (len < read) + memset(zaddr + len, 0, read - len); + } + +out_hole: + if (hole) { + SetPageChecked(page); + dbg_gen("hole"); + } + + SetPageUptodate(page); + ClearPageError(page); + flush_dcache_page(page); + kunmap(page); + *n = nn; + return 0; + +out_err: + ClearPageUptodate(page); + SetPageError(page); + flush_dcache_page(page); + kunmap(page); + ubifs_err("bad data node (block %u, inode %lu)", + page_block, inode->i_ino); + return -EINVAL; +} + +/** + * ubifs_do_bulk_read - do bulk-read. + * @c: UBIFS file-system description object + * @page1: first page + * + * This function returns %1 if the bulk-read is done, otherwise %0 is returned. + */ +static int ubifs_do_bulk_read(struct ubifs_info *c, struct page *page1) +{ + pgoff_t offset = page1->index, end_index; + struct address_space *mapping = page1->mapping; + struct inode *inode = mapping->host; + struct ubifs_inode *ui = ubifs_inode(inode); + struct bu_info *bu; + int err, page_idx, page_cnt, ret = 0, n = 0; + loff_t isize; + + bu = kmalloc(sizeof(struct bu_info), GFP_NOFS); + if (!bu) + return 0; + + bu->buf_len = c->bulk_read_buf_size; + bu->buf = kmalloc(bu->buf_len, GFP_NOFS); + if (!bu->buf) + goto out_free; + + data_key_init(c, &bu->key, inode->i_ino, + offset << UBIFS_BLOCKS_PER_PAGE_SHIFT); + + err = ubifs_tnc_get_bu_keys(c, bu); + if (err) + goto out_warn; + + if (bu->eof) { + /* Turn off bulk-read at the end of the file */ + ui->read_in_a_row = 1; + ui->bulk_read = 0; + } + + page_cnt = bu->blk_cnt >> UBIFS_BLOCKS_PER_PAGE_SHIFT; + if (!page_cnt) { + /* + * This happens when there are multiple blocks per page and the + * blocks for the first page we are looking for, are not + * together. If all the pages were like this, bulk-read would + * reduce performance, so we turn it off for a while. + */ + ui->read_in_a_row = 0; + ui->bulk_read = 0; + goto out_free; + } + + if (bu->cnt) { + err = ubifs_tnc_bulk_read(c, bu); + if (err) + goto out_warn; + } + + err = populate_page(c, page1, bu, &n); + if (err) + goto out_warn; + + unlock_page(page1); + ret = 1; + + isize = i_size_read(inode); + if (isize == 0) + goto out_free; + end_index = ((isize - 1) >> PAGE_CACHE_SHIFT); + + for (page_idx = 1; page_idx < page_cnt; page_idx++) { + pgoff_t page_offset = offset + page_idx; + struct page *page; + + if (page_offset > end_index) + break; + page = find_or_create_page(mapping, page_offset, + GFP_NOFS | __GFP_COLD); + if (!page) + break; + if (!PageUptodate(page)) + err = populate_page(c, page, bu, &n); + unlock_page(page); + page_cache_release(page); + if (err) + break; + } + + ui->last_page_read = offset + page_idx - 1; + +out_free: + kfree(bu->buf); + kfree(bu); + return ret; + +out_warn: + ubifs_warn("ignoring error %d and skipping bulk-read", err); + goto out_free; +} + +/** + * ubifs_bulk_read - determine whether to bulk-read and, if so, do it. + * @page: page from which to start bulk-read. + * + * Some flash media are capable of reading sequentially at faster rates. UBIFS + * bulk-read facility is designed to take advantage of that, by reading in one + * go consecutive data nodes that are also located consecutively in the same + * LEB. This function returns %1 if a bulk-read is done and %0 otherwise. + */ +static int ubifs_bulk_read(struct page *page) +{ + struct inode *inode = page->mapping->host; + struct ubifs_info *c = inode->i_sb->s_fs_info; + struct ubifs_inode *ui = ubifs_inode(inode); + pgoff_t index = page->index, last_page_read = ui->last_page_read; + int ret = 0; + + ui->last_page_read = index; + + if (!c->bulk_read) + return 0; + /* + * Bulk-read is protected by ui_mutex, but it is an optimization, so + * don't bother if we cannot lock the mutex. + */ + if (!mutex_trylock(&ui->ui_mutex)) + return 0; + if (index != last_page_read + 1) { + /* Turn off bulk-read if we stop reading sequentially */ + ui->read_in_a_row = 1; + if (ui->bulk_read) + ui->bulk_read = 0; + goto out_unlock; + } + if (!ui->bulk_read) { + ui->read_in_a_row += 1; + if (ui->read_in_a_row < 3) + goto out_unlock; + /* Three reads in a row, so switch on bulk-read */ + ui->bulk_read = 1; + } + ret = ubifs_do_bulk_read(c, page); +out_unlock: + mutex_unlock(&ui->ui_mutex); + return ret; +} + static int ubifs_readpage(struct file *file, struct page *page) { + if (ubifs_bulk_read(page)) + return 0; do_readpage(page); unlock_page(page); return 0; diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h index 8f74760..9ee6508 100644 --- a/fs/ubifs/key.h +++ b/fs/ubifs/key.h @@ -484,7 +484,7 @@ static inline void key_copy(const struct ubifs_info *c, * @key2: the second key to compare * * This function compares 2 keys and returns %-1 if @key1 is less than - * @key2, 0 if the keys are equivalent and %1 if @key1 is greater than @key2. + * @key2, %0 if the keys are equivalent and %1 if @key1 is greater than @key2. */ static inline int keys_cmp(const struct ubifs_info *c, const union ubifs_key *key1, @@ -503,6 +503,26 @@ static inline int keys_cmp(const struct ubifs_info *c, } /** + * keys_eq - determine if keys are equivalent. + * @c: UBIFS file-system description object + * @key1: the first key to compare + * @key2: the second key to compare + * + * This function compares 2 keys and returns %1 if @key1 is equal to @key2 and + * %0 if not. + */ +static inline int keys_eq(const struct ubifs_info *c, + const union ubifs_key *key1, + const union ubifs_key *key2) +{ + if (key1->u32[0] != key2->u32[0]) + return 0; + if (key1->u32[1] != key2->u32[1]) + return 0; + return 1; +} + +/** * is_hash_key - is a key vulnerable to hash collisions. * @c: UBIFS file-system description object * @key: key diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index d87b0cf..b1c57e8 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -401,6 +401,11 @@ static int ubifs_show_options(struct seq_file *s, struct vfsmount *mnt) else if (c->mount_opts.unmount_mode == 1) seq_printf(s, ",norm_unmount"); + if (c->mount_opts.bulk_read == 2) + seq_printf(s, ",bulk_read"); + else if (c->mount_opts.bulk_read == 1) + seq_printf(s, ",no_bulk_read"); + return 0; } @@ -538,6 +543,18 @@ static int init_constants_early(struct ubifs_info *c) * calculations when reporting free space. */ c->leb_overhead = c->leb_size % UBIFS_MAX_DATA_NODE_SZ; + /* Buffer size for bulk-reads */ + c->bulk_read_buf_size = UBIFS_MAX_BULK_READ * UBIFS_MAX_DATA_NODE_SZ; + if (c->bulk_read_buf_size > c->leb_size) + c->bulk_read_buf_size = c->leb_size; + if (c->bulk_read_buf_size > 128 * 1024) { + /* Check if we can kmalloc more than 128KiB */ + void *try = kmalloc(c->bulk_read_buf_size, GFP_KERNEL); + + kfree(try); + if (!try) + c->bulk_read_buf_size = 128 * 1024; + } return 0; } @@ -840,17 +857,23 @@ static int check_volume_empty(struct ubifs_info *c) * * Opt_fast_unmount: do not run a journal commit before un-mounting * Opt_norm_unmount: run a journal commit before un-mounting + * Opt_bulk_read: enable bulk-reads + * Opt_no_bulk_read: disable bulk-reads * Opt_err: just end of array marker */ enum { Opt_fast_unmount, Opt_norm_unmount, + Opt_bulk_read, + Opt_no_bulk_read, Opt_err, }; static match_table_t tokens = { {Opt_fast_unmount, "fast_unmount"}, {Opt_norm_unmount, "norm_unmount"}, + {Opt_bulk_read, "bulk_read"}, + {Opt_no_bulk_read, "no_bulk_read"}, {Opt_err, NULL}, }; @@ -888,6 +911,14 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options, c->mount_opts.unmount_mode = 1; c->fast_unmount = 0; break; + case Opt_bulk_read: + c->mount_opts.bulk_read = 2; + c->bulk_read = 1; + break; + case Opt_no_bulk_read: + c->mount_opts.bulk_read = 1; + c->bulk_read = 0; + break; default: ubifs_err("unrecognized mount option \"%s\" " "or missing value", p); diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index ba13c92..d279012 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -1492,6 +1492,289 @@ out: } /** + * ubifs_tnc_get_bu_keys - lookup keys for bulk-read. + * @c: UBIFS file-system description object + * @bu: bulk-read parameters and results + * + * Lookup consecutive data node keys for the same inode that reside + * consecutively in the same LEB. + */ +int ubifs_tnc_get_bu_keys(struct ubifs_info *c, struct bu_info *bu) +{ + int n, err = 0, lnum = -1, uninitialized_var(offs); + int uninitialized_var(len); + unsigned int block = key_block(c, &bu->key); + struct ubifs_znode *znode; + + bu->cnt = 0; + bu->blk_cnt = 0; + bu->eof = 0; + + mutex_lock(&c->tnc_mutex); + /* Find first key */ + err = ubifs_lookup_level0(c, &bu->key, &znode, &n); + if (err < 0) + goto out; + if (err) { + /* Key found */ + len = znode->zbranch[n].len; + /* The buffer must be big enough for at least 1 node */ + if (len > bu->buf_len) { + err = -EINVAL; + goto out; + } + /* Add this key */ + bu->zbranch[bu->cnt++] = znode->zbranch[n]; + bu->blk_cnt += 1; + lnum = znode->zbranch[n].lnum; + offs = ALIGN(znode->zbranch[n].offs + len, 8); + } + while (1) { + struct ubifs_zbranch *zbr; + union ubifs_key *key; + unsigned int next_block; + + /* Find next key */ + err = tnc_next(c, &znode, &n); + if (err) + goto out; + zbr = &znode->zbranch[n]; + key = &zbr->key; + /* See if there is another data key for this file */ + if (key_inum(c, key) != key_inum(c, &bu->key) || + key_type(c, key) != UBIFS_DATA_KEY) { + err = -ENOENT; + goto out; + } + if (lnum < 0) { + /* First key found */ + lnum = zbr->lnum; + offs = ALIGN(zbr->offs + zbr->len, 8); + len = zbr->len; + if (len > bu->buf_len) { + err = -EINVAL; + goto out; + } + } else { + /* + * The data nodes must be in consecutive positions in + * the same LEB. + */ + if (zbr->lnum != lnum || zbr->offs != offs) + goto out; + offs += ALIGN(zbr->len, 8); + len = ALIGN(len, 8) + zbr->len; + /* Must not exceed buffer length */ + if (len > bu->buf_len) + goto out; + } + /* Allow for holes */ + next_block = key_block(c, key); + bu->blk_cnt += (next_block - block - 1); + if (bu->blk_cnt >= UBIFS_MAX_BULK_READ) + goto out; + block = next_block; + /* Add this key */ + bu->zbranch[bu->cnt++] = *zbr; + bu->blk_cnt += 1; + /* See if we have room for more */ + if (bu->cnt >= UBIFS_MAX_BULK_READ) + goto out; + if (bu->blk_cnt >= UBIFS_MAX_BULK_READ) + goto out; + } +out: + if (err == -ENOENT) { + bu->eof = 1; + err = 0; + } + bu->gc_seq = c->gc_seq; + mutex_unlock(&c->tnc_mutex); + if (err) + return err; + /* + * An enormous hole could cause bulk-read to encompass too many + * page cache pages, so limit the number here. + */ + if (bu->blk_cnt >= UBIFS_MAX_BULK_READ) + bu->blk_cnt = UBIFS_MAX_BULK_READ; + /* + * Ensure that bulk-read covers a whole number of page cache + * pages. + */ + if (UBIFS_BLOCKS_PER_PAGE == 1 || + !(bu->blk_cnt & (UBIFS_BLOCKS_PER_PAGE - 1))) + return 0; + if (bu->eof) { + /* At the end of file we can round up */ + bu->blk_cnt += UBIFS_BLOCKS_PER_PAGE - 1; + return 0; + } + /* Exclude data nodes that do not make up a whole page cache page */ + block = key_block(c, &bu->key) + bu->blk_cnt; + block &= ~(UBIFS_BLOCKS_PER_PAGE - 1); + while (bu->cnt) { + if (key_block(c, &bu->zbranch[bu->cnt - 1].key) < block) + break; + bu->cnt -= 1; + } + return 0; +} + +/** + * read_wbuf - bulk-read from a LEB with a wbuf. + * @wbuf: wbuf that may overlap the read + * @buf: buffer into which to read + * @len: read length + * @lnum: LEB number from which to read + * @offs: offset from which to read + * + * This functions returns %0 on success or a negative error code on failure. + */ +static int read_wbuf(struct ubifs_wbuf *wbuf, void *buf, int len, int lnum, + int offs) +{ + const struct ubifs_info *c = wbuf->c; + int rlen, overlap; + + dbg_io("LEB %d:%d, length %d", lnum, offs, len); + ubifs_assert(wbuf && lnum >= 0 && lnum < c->leb_cnt && offs >= 0); + ubifs_assert(!(offs & 7) && offs < c->leb_size); + ubifs_assert(offs + len <= c->leb_size); + + spin_lock(&wbuf->lock); + overlap = (lnum == wbuf->lnum && offs + len > wbuf->offs); + if (!overlap) { + /* We may safely unlock the write-buffer and read the data */ + spin_unlock(&wbuf->lock); + return ubi_read(c->ubi, lnum, buf, offs, len); + } + + /* Don't read under wbuf */ + rlen = wbuf->offs - offs; + if (rlen < 0) + rlen = 0; + + /* Copy the rest from the write-buffer */ + memcpy(buf + rlen, wbuf->buf + offs + rlen - wbuf->offs, len - rlen); + spin_unlock(&wbuf->lock); + + if (rlen > 0) + /* Read everything that goes before write-buffer */ + return ubi_read(c->ubi, lnum, buf, offs, rlen); + + return 0; +} + +/** + * validate_data_node - validate data nodes for bulk-read. + * @c: UBIFS file-system description object + * @buf: buffer containing data node to validate + * @zbr: zbranch of data node to validate + * + * This functions returns %0 on success or a negative error code on failure. + */ +static int validate_data_node(struct ubifs_info *c, void *buf, + struct ubifs_zbranch *zbr) +{ + union ubifs_key key1; + struct ubifs_ch *ch = buf; + int err, len; + + if (ch->node_type != UBIFS_DATA_NODE) { + ubifs_err("bad node type (%d but expected %d)", + ch->node_type, UBIFS_DATA_NODE); + goto out_err; + } + + err = ubifs_check_node(c, buf, zbr->lnum, zbr->offs, 0); + if (err) { + ubifs_err("expected node type %d", UBIFS_DATA_NODE); + goto out; + } + + len = le32_to_cpu(ch->len); + if (len != zbr->len) { + ubifs_err("bad node length %d, expected %d", len, zbr->len); + goto out_err; + } + + /* Make sure the key of the read node is correct */ + key_read(c, buf + UBIFS_KEY_OFFSET, &key1); + if (!keys_eq(c, &zbr->key, &key1)) { + ubifs_err("bad key in node at LEB %d:%d", + zbr->lnum, zbr->offs); + dbg_tnc("looked for key %s found node's key %s", + DBGKEY(&zbr->key), DBGKEY1(&key1)); + goto out_err; + } + + return 0; + +out_err: + err = -EINVAL; +out: + ubifs_err("bad node at LEB %d:%d", zbr->lnum, zbr->offs); + dbg_dump_node(c, buf); + dbg_dump_stack(); + return err; +} + +/** + * ubifs_tnc_bulk_read - read a number of data nodes in one go. + * @c: UBIFS file-system description object + * @bu: bulk-read parameters and results + * + * This functions reads and validates the data nodes that were identified by the + * 'ubifs_tnc_get_bu_keys()' function. This functions returns %0 on success, + * -EAGAIN to indicate a race with GC, or another negative error code on + * failure. + */ +int ubifs_tnc_bulk_read(struct ubifs_info *c, struct bu_info *bu) +{ + int lnum = bu->zbranch[0].lnum, offs = bu->zbranch[0].offs, len, err, i; + struct ubifs_wbuf *wbuf; + void *buf; + + len = bu->zbranch[bu->cnt - 1].offs; + len += bu->zbranch[bu->cnt - 1].len - offs; + if (len > bu->buf_len) { + ubifs_err("buffer too small %d vs %d", bu->buf_len, len); + return -EINVAL; + } + + /* Do the read */ + wbuf = ubifs_get_wbuf(c, lnum); + if (wbuf) + err = read_wbuf(wbuf, bu->buf, len, lnum, offs); + else + err = ubi_read(c->ubi, lnum, bu->buf, offs, len); + + /* Check for a race with GC */ + if (maybe_leb_gced(c, lnum, bu->gc_seq)) + return -EAGAIN; + + if (err && err != -EBADMSG) { + ubifs_err("failed to read from LEB %d:%d, error %d", + lnum, offs, err); + dbg_dump_stack(); + dbg_tnc("key %s", DBGKEY(&bu->key)); + return err; + } + + /* Validate the nodes read */ + buf = bu->buf; + for (i = 0; i < bu->cnt; i++) { + err = validate_data_node(c, buf, &bu->zbranch[i]); + if (err) + return err; + buf = buf + ALIGN(bu->zbranch[i].len, 8); + } + + return 0; +} + +/** * do_lookup_nm- look up a "hashed" node. * @c: UBIFS file-system description object * @key: node key to lookup diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index ce86549..8513239 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -142,6 +142,9 @@ /* Maximum expected tree height for use by bottom_up_buf */ #define BOTTOM_UP_HEIGHT 64 +/* Maximum number of data nodes to bulk-read */ +#define UBIFS_MAX_BULK_READ 32 + /* * Lockdep classes for UBIFS inode @ui_mutex. */ @@ -329,8 +332,8 @@ struct ubifs_gced_idx_leb { * @dirty: non-zero if the inode is dirty * @xattr: non-zero if this is an extended attribute inode * @ui_mutex: serializes inode write-back with the rest of VFS operations, - * serializes "clean <-> dirty" state changes, protects @dirty, - * @ui_size, and @xattr_size + * serializes "clean <-> dirty" state changes, serializes bulk-read, + * protects @dirty, @ui_size, and @xattr_size * @ui_lock: protects @synced_i_size * @synced_i_size: synchronized size of inode, i.e. the value of inode size * currently stored on the flash; used only for regular file @@ -338,6 +341,9 @@ struct ubifs_gced_idx_leb { * @ui_size: inode size used by UBIFS when writing to flash * @flags: inode flags (@UBIFS_COMPR_FL, etc) * @compr_type: default compression type used for this inode + * @last_page_read: page number of last page read (for bulk read) + * @read_in_a_row: number of consecutive pages read in a row (for bulk read) + * @bulk_read: indicates whether bulk-read should be used * @data_len: length of the data attached to the inode * @data: inode's data * @@ -385,6 +391,9 @@ struct ubifs_inode { loff_t ui_size; int flags; int compr_type; + pgoff_t last_page_read; + pgoff_t read_in_a_row; + int bulk_read; int data_len; void *data; }; @@ -744,6 +753,28 @@ struct ubifs_znode { }; /** + * struct bu_info - bulk-read information + * @key: first data node key + * @zbranch: zbranches of data nodes to bulk read + * @buf: buffer to read into + * @buf_len: buffer length + * @gc_seq: GC sequence number to detect races with GC + * @cnt: number of data nodes for bulk read + * @blk_cnt: number of data blocks including holes + * @oef: end of file reached + */ +struct bu_info { + union ubifs_key key; + struct ubifs_zbranch zbranch[UBIFS_MAX_BULK_READ]; + void *buf; + int buf_len; + int gc_seq; + int cnt; + int blk_cnt; + int eof; +}; + +/** * struct ubifs_node_range - node length range description data structure. * @len: fixed node length * @min_len: minimum possible node length @@ -862,9 +893,11 @@ struct ubifs_orphan { /** * struct ubifs_mount_opts - UBIFS-specific mount options information. * @unmount_mode: selected unmount mode (%0 default, %1 normal, %2 fast) + * @bulk_read: enable bulk-reads */ struct ubifs_mount_opts { unsigned int unmount_mode:2; + unsigned int bulk_read:2; }; /** @@ -965,6 +998,9 @@ struct ubifs_mount_opts { * @old_leb_cnt: count of logical eraseblocks before re-size * @ro_media: the underlying UBI volume is read-only * + * @bulk_read: enable bulk-reads + * @bulk_read_buf_size: buffer size for bulk-reads + * * @dirty_pg_cnt: number of dirty pages (not used) * @dirty_zn_cnt: number of dirty znodes * @clean_zn_cnt: number of clean znodes @@ -1205,6 +1241,9 @@ struct ubifs_info { int old_leb_cnt; int ro_media; + int bulk_read; + int bulk_read_buf_size; + atomic_long_t dirty_pg_cnt; atomic_long_t dirty_zn_cnt; atomic_long_t clean_zn_cnt; @@ -1490,6 +1529,8 @@ void destroy_old_idx(struct ubifs_info *c); int is_idx_node_in_tnc(struct ubifs_info *c, union ubifs_key *key, int level, int lnum, int offs); int insert_old_idx_znode(struct ubifs_info *c, struct ubifs_znode *znode); +int ubifs_tnc_get_bu_keys(struct ubifs_info *c, struct bu_info *bu); +int ubifs_tnc_bulk_read(struct ubifs_info *c, struct bu_info *bu); /* tnc_misc.c */ struct ubifs_znode *ubifs_tnc_levelorder_next(struct ubifs_znode *zr, -- cgit v0.10.2 From 2953e73f1ce4b3284b409aefb9d46bbde6515c37 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 4 Sep 2008 16:26:00 +0300 Subject: UBIFS: add no_chk_data_crc mount option UBIFS read performance can be improved by skipping the CRC check when data nodes are read. This option can be used if the underlying media is considered to be highly reliable. Note that CRCs are always checked for metadata. Read speed on Arm platform with OneNAND goes from 19 MiB/s to 27 MiB/s with data CRC checking disabled. Signed-off-by: Adrian Hunter diff --git a/Documentation/filesystems/ubifs.txt b/Documentation/filesystems/ubifs.txt index 340512c..dd84ea3 100644 --- a/Documentation/filesystems/ubifs.txt +++ b/Documentation/filesystems/ubifs.txt @@ -89,6 +89,12 @@ fast_unmount do not commit on unmount; this option makes bulk_read read more in one go to take advantage of flash media that read faster sequentially no_bulk_read (*) do not bulk-read +no_chk_data_crc skip checking of CRCs on data nodes in order to + improve read performance. Use this option only + if the flash media is highly reliable. The effect + of this option is that corruption of the contents + of a file can go unnoticed. +chk_data_crc (*) do not skip checking CRCs on data nodes Quick usage instructions diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index 054363f..40e2790 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -74,6 +74,7 @@ void ubifs_ro_mode(struct ubifs_info *c, int err) * @lnum: logical eraseblock number * @offs: offset within the logical eraseblock * @quiet: print no messages + * @chk_crc: indicates whether to always check the CRC * * This function checks node magic number and CRC checksum. This function also * validates node length to prevent UBIFS from becoming crazy when an attacker @@ -85,7 +86,7 @@ void ubifs_ro_mode(struct ubifs_info *c, int err) * or magic. */ int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, - int offs, int quiet) + int offs, int quiet, int chk_crc) { int err = -EINVAL, type, node_len; uint32_t crc, node_crc, magic; @@ -121,6 +122,10 @@ int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, node_len > c->ranges[type].max_len) goto out_len; + if (!chk_crc && type == UBIFS_DATA_NODE && !c->always_chk_crc) + if (c->no_chk_data_crc) + return 0; + crc = crc32(UBIFS_CRC32_INIT, buf + 8, node_len - 8); node_crc = le32_to_cpu(ch->crc); if (crc != node_crc) { @@ -722,7 +727,7 @@ int ubifs_read_node_wbuf(struct ubifs_wbuf *wbuf, void *buf, int type, int len, goto out; } - err = ubifs_check_node(c, buf, lnum, offs, 0); + err = ubifs_check_node(c, buf, lnum, offs, 0, 0); if (err) { ubifs_err("expected node type %d", type); return err; @@ -781,7 +786,7 @@ int ubifs_read_node(const struct ubifs_info *c, void *buf, int type, int len, goto out; } - err = ubifs_check_node(c, buf, lnum, offs, 0); + err = ubifs_check_node(c, buf, lnum, offs, 0, 0); if (err) { ubifs_err("expected node type %d", type); return err; diff --git a/fs/ubifs/scan.c b/fs/ubifs/scan.c index acf5c5f..0ed8247 100644 --- a/fs/ubifs/scan.c +++ b/fs/ubifs/scan.c @@ -87,7 +87,7 @@ int ubifs_scan_a_node(const struct ubifs_info *c, void *buf, int len, int lnum, dbg_scan("scanning %s", dbg_ntype(ch->node_type)); - if (ubifs_check_node(c, buf, lnum, offs, quiet)) + if (ubifs_check_node(c, buf, lnum, offs, quiet, 1)) return SCANNED_A_CORRUPT_NODE; if (ch->node_type == UBIFS_PAD_NODE) { diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index b1c57e8..cf078b5 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -406,6 +406,11 @@ static int ubifs_show_options(struct seq_file *s, struct vfsmount *mnt) else if (c->mount_opts.bulk_read == 1) seq_printf(s, ",no_bulk_read"); + if (c->mount_opts.chk_data_crc == 2) + seq_printf(s, ",chk_data_crc"); + else if (c->mount_opts.chk_data_crc == 1) + seq_printf(s, ",no_chk_data_crc"); + return 0; } @@ -859,6 +864,8 @@ static int check_volume_empty(struct ubifs_info *c) * Opt_norm_unmount: run a journal commit before un-mounting * Opt_bulk_read: enable bulk-reads * Opt_no_bulk_read: disable bulk-reads + * Opt_chk_data_crc: check CRCs when reading data nodes + * Opt_no_chk_data_crc: do not check CRCs when reading data nodes * Opt_err: just end of array marker */ enum { @@ -866,6 +873,8 @@ enum { Opt_norm_unmount, Opt_bulk_read, Opt_no_bulk_read, + Opt_chk_data_crc, + Opt_no_chk_data_crc, Opt_err, }; @@ -874,6 +883,8 @@ static match_table_t tokens = { {Opt_norm_unmount, "norm_unmount"}, {Opt_bulk_read, "bulk_read"}, {Opt_no_bulk_read, "no_bulk_read"}, + {Opt_chk_data_crc, "chk_data_crc"}, + {Opt_no_chk_data_crc, "no_chk_data_crc"}, {Opt_err, NULL}, }; @@ -919,6 +930,14 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options, c->mount_opts.bulk_read = 1; c->bulk_read = 0; break; + case Opt_chk_data_crc: + c->mount_opts.chk_data_crc = 2; + c->no_chk_data_crc = 0; + break; + case Opt_no_chk_data_crc: + c->mount_opts.chk_data_crc = 1; + c->no_chk_data_crc = 1; + break; default: ubifs_err("unrecognized mount option \"%s\" " "or missing value", p); @@ -1027,6 +1046,8 @@ static int mount_ubifs(struct ubifs_info *c) goto out_free; } + c->always_chk_crc = 1; + err = ubifs_read_superblock(c); if (err) goto out_free; @@ -1168,6 +1189,8 @@ static int mount_ubifs(struct ubifs_info *c) if (err) goto out_infos; + c->always_chk_crc = 0; + ubifs_msg("mounted UBI device %d, volume %d, name \"%s\"", c->vi.ubi_num, c->vi.vol_id, c->vi.name); if (mounted_read_only) @@ -1313,6 +1336,7 @@ static int ubifs_remount_rw(struct ubifs_info *c) mutex_lock(&c->umount_mutex); c->remounting_rw = 1; + c->always_chk_crc = 1; /* Check for enough free space */ if (ubifs_calc_available(c, c->min_idx_lebs) <= 0) { @@ -1381,13 +1405,15 @@ static int ubifs_remount_rw(struct ubifs_info *c) c->bgt = NULL; ubifs_err("cannot spawn \"%s\", error %d", c->bgt_name, err); - return err; + goto out; } wake_up_process(c->bgt); c->orph_buf = vmalloc(c->leb_size); - if (!c->orph_buf) - return -ENOMEM; + if (!c->orph_buf) { + err = -ENOMEM; + goto out; + } /* Check for enough log space */ lnum = c->lhead_lnum + 1; @@ -1414,6 +1440,7 @@ static int ubifs_remount_rw(struct ubifs_info *c) dbg_gen("re-mounted read-write"); c->vfs_sb->s_flags &= ~MS_RDONLY; c->remounting_rw = 0; + c->always_chk_crc = 0; mutex_unlock(&c->umount_mutex); return 0; @@ -1429,6 +1456,7 @@ out: c->ileb_buf = NULL; ubifs_lpt_free(c, 1); c->remounting_rw = 0; + c->always_chk_crc = 0; mutex_unlock(&c->umount_mutex); return err; } diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index d279012..66dc571 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -470,6 +470,10 @@ static int try_read_node(const struct ubifs_info *c, void *buf, int type, if (node_len != len) return 0; + if (type == UBIFS_DATA_NODE && !c->always_chk_crc) + if (c->no_chk_data_crc) + return 0; + crc = crc32(UBIFS_CRC32_INIT, buf + 8, node_len - 8); node_crc = le32_to_cpu(ch->crc); if (crc != node_crc) @@ -1687,7 +1691,7 @@ static int validate_data_node(struct ubifs_info *c, void *buf, goto out_err; } - err = ubifs_check_node(c, buf, zbr->lnum, zbr->offs, 0); + err = ubifs_check_node(c, buf, zbr->lnum, zbr->offs, 0, 0); if (err) { ubifs_err("expected node type %d", UBIFS_DATA_NODE); goto out; diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 8513239..d6ae3f7 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -894,10 +894,12 @@ struct ubifs_orphan { * struct ubifs_mount_opts - UBIFS-specific mount options information. * @unmount_mode: selected unmount mode (%0 default, %1 normal, %2 fast) * @bulk_read: enable bulk-reads + * @chk_data_crc: check CRCs when reading data nodes */ struct ubifs_mount_opts { unsigned int unmount_mode:2; unsigned int bulk_read:2; + unsigned int chk_data_crc:2; }; /** @@ -1001,6 +1003,9 @@ struct ubifs_mount_opts { * @bulk_read: enable bulk-reads * @bulk_read_buf_size: buffer size for bulk-reads * + * @no_chk_data_crc: do not check CRCs when reading data nodes (except during + * recovery) + * * @dirty_pg_cnt: number of dirty pages (not used) * @dirty_zn_cnt: number of dirty znodes * @clean_zn_cnt: number of clean znodes @@ -1138,6 +1143,7 @@ struct ubifs_mount_opts { * @rcvrd_mst_node: recovered master node to write when mounting ro to rw * @size_tree: inode size information for recovery * @remounting_rw: set while remounting from ro to rw (sb flags have MS_RDONLY) + * @always_chk_crc: always check CRCs (while mounting and remounting rw) * @mount_opts: UBIFS-specific mount options * * @dbg_buf: a buffer of LEB size used for debugging purposes @@ -1244,6 +1250,8 @@ struct ubifs_info { int bulk_read; int bulk_read_buf_size; + int no_chk_data_crc; + atomic_long_t dirty_pg_cnt; atomic_long_t dirty_zn_cnt; atomic_long_t clean_zn_cnt; @@ -1374,6 +1382,7 @@ struct ubifs_info { struct ubifs_mst_node *rcvrd_mst_node; struct rb_root size_tree; int remounting_rw; + int always_chk_crc; struct ubifs_mount_opts mount_opts; #ifdef CONFIG_UBIFS_FS_DEBUG @@ -1416,7 +1425,7 @@ int ubifs_read_node_wbuf(struct ubifs_wbuf *wbuf, void *buf, int type, int len, int ubifs_write_node(struct ubifs_info *c, void *node, int len, int lnum, int offs, int dtype); int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, - int offs, int quiet); + int offs, int quiet, int chk_crc); void ubifs_prepare_node(struct ubifs_info *c, void *buf, int len, int pad); void ubifs_prep_grp_node(struct ubifs_info *c, void *node, int len, int last); int ubifs_io_init(struct ubifs_info *c); -- cgit v0.10.2 From 2242c689ecc390fb4719f595751351d1ecc5c409 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 5 Sep 2008 11:56:05 +0300 Subject: UBIFS: improve znode splitting rules When inserting into a full znode it is split into two znodes. Because data node keys are usually consecutive, it is better to try to keep them together. This patch does a better job of that. Signed-off-by: Adrian Hunter diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 66dc571..e0878a4 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -1962,7 +1962,7 @@ static int tnc_insert(struct ubifs_info *c, struct ubifs_znode *znode, { struct ubifs_znode *zn, *zi, *zp; int i, keep, move, appending = 0; - union ubifs_key *key = &zbr->key; + union ubifs_key *key = &zbr->key, *key1; ubifs_assert(n >= 0 && n <= c->fanout); @@ -2003,20 +2003,33 @@ again: zn->level = znode->level; /* Decide where to split */ - if (znode->level == 0 && n == c->fanout && - key_type(c, key) == UBIFS_DATA_KEY) { - union ubifs_key *key1; - - /* - * If this is an inode which is being appended - do not split - * it because no other zbranches can be inserted between - * zbranches of consecutive data nodes anyway. - */ - key1 = &znode->zbranch[n - 1].key; - if (key_inum(c, key1) == key_inum(c, key) && - key_type(c, key1) == UBIFS_DATA_KEY && - key_block(c, key1) == key_block(c, key) - 1) - appending = 1; + if (znode->level == 0 && key_type(c, key) == UBIFS_DATA_KEY) { + /* Try not to split consecutive data keys */ + if (n == c->fanout) { + key1 = &znode->zbranch[n - 1].key; + if (key_inum(c, key1) == key_inum(c, key) && + key_type(c, key1) == UBIFS_DATA_KEY) + appending = 1; + } else + goto check_split; + } else if (appending && n != c->fanout) { + /* Try not to split consecutive data keys */ + appending = 0; +check_split: + if (n >= (c->fanout + 1) / 2) { + key1 = &znode->zbranch[0].key; + if (key_inum(c, key1) == key_inum(c, key) && + key_type(c, key1) == UBIFS_DATA_KEY) { + key1 = &znode->zbranch[n].key; + if (key_inum(c, key1) != key_inum(c, key) || + key_type(c, key1) != UBIFS_DATA_KEY) { + keep = n; + move = c->fanout - keep; + zi = znode; + goto do_split; + } + } + } } if (appending) { @@ -2046,6 +2059,8 @@ again: zbr->znode->parent = zn; } +do_split: + __set_bit(DIRTY_ZNODE, &zn->flags); atomic_long_inc(&c->dirty_zn_cnt); @@ -2072,14 +2087,11 @@ again: /* Insert new znode (produced by spitting) into the parent */ if (zp) { - i = n; + if (n == 0 && zi == znode && znode->iip == 0) + correct_parent_keys(c, znode); + /* Locate insertion point */ n = znode->iip + 1; - if (appending && n != c->fanout) - appending = 0; - - if (i == 0 && zi == znode && znode->iip == 0) - correct_parent_keys(c, znode); /* Tail recursion */ zbr->key = zn->zbranch[0].key; -- cgit v0.10.2 From ccb3eba72453a3b5aa37dda02e3a690449e3d229 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 8 Sep 2008 16:07:01 +0300 Subject: UBIFS: check data CRC when in error state When UBIFS switches to R/O mode because of an error, it is reasonable to enable data CRC checking. Signed-off-by: Artem Bityutskiy diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index 40e2790..0168271 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -62,6 +62,7 @@ void ubifs_ro_mode(struct ubifs_info *c, int err) { if (!c->ro_media) { c->ro_media = 1; + c->no_chk_data_crc = 0; ubifs_warn("switched to read-only mode, error %d", err); dbg_dump_stack(); } -- cgit v0.10.2 From 625bf371c1522764fc1cf2981b041c5f9a19e894 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 8 Sep 2008 16:13:38 +0300 Subject: UBIFS: use bit-fields when possible The "bulk_read" and "no_chk_data_crc" have only 2 values - 0 and 1. We already have bit-fields in corresponding data structers, so make "bulk_read" and "no_chk_data_crc" bit-fields as well. Signed-off-by: Artem Bityutskiy diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index d6ae3f7..542cbaf 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -331,6 +331,7 @@ struct ubifs_gced_idx_leb { * this inode * @dirty: non-zero if the inode is dirty * @xattr: non-zero if this is an extended attribute inode + * @bulk_read: non-zero if bulk-read should be used * @ui_mutex: serializes inode write-back with the rest of VFS operations, * serializes "clean <-> dirty" state changes, serializes bulk-read, * protects @dirty, @ui_size, and @xattr_size @@ -343,7 +344,6 @@ struct ubifs_gced_idx_leb { * @compr_type: default compression type used for this inode * @last_page_read: page number of last page read (for bulk read) * @read_in_a_row: number of consecutive pages read in a row (for bulk read) - * @bulk_read: indicates whether bulk-read should be used * @data_len: length of the data attached to the inode * @data: inode's data * @@ -385,6 +385,7 @@ struct ubifs_inode { unsigned int xattr_names; unsigned int dirty:1; unsigned int xattr:1; + unsigned int bulk_read:1; struct mutex ui_mutex; spinlock_t ui_lock; loff_t synced_i_size; @@ -393,7 +394,6 @@ struct ubifs_inode { int compr_type; pgoff_t last_page_read; pgoff_t read_in_a_row; - int bulk_read; int data_len; void *data; }; @@ -940,6 +940,7 @@ struct ubifs_mount_opts { * @cmt_state: commit state * @cs_lock: commit state lock * @cmt_wq: wait queue to sleep on if the log is full and a commit is running + * * @fast_unmount: do not run journal commit before un-mounting * @big_lpt: flag that LPT is too big to write whole during commit * @check_lpt_free: flag that indicates LPT GC may be needed @@ -947,6 +948,9 @@ struct ubifs_mount_opts { * optimization) * @nospace_rp: the same as @nospace, but additionally means that even reserved * pool is full + * @no_chk_data_crc: do not check CRCs when reading data nodes (except during + * recovery) + * @bulk_read: enable bulk-reads * * @tnc_mutex: protects the Tree Node Cache (TNC), @zroot, @cnext, @enext, and * @calc_idx_sz @@ -970,6 +974,7 @@ struct ubifs_mount_opts { * @mst_node: master node * @mst_offs: offset of valid master node * @mst_mutex: protects the master node area, @mst_node, and @mst_offs + * @bulk_read_buf_size: buffer size for bulk-reads * * @log_lebs: number of logical eraseblocks in the log * @log_bytes: log size in bytes @@ -1000,12 +1005,6 @@ struct ubifs_mount_opts { * @old_leb_cnt: count of logical eraseblocks before re-size * @ro_media: the underlying UBI volume is read-only * - * @bulk_read: enable bulk-reads - * @bulk_read_buf_size: buffer size for bulk-reads - * - * @no_chk_data_crc: do not check CRCs when reading data nodes (except during - * recovery) - * * @dirty_pg_cnt: number of dirty pages (not used) * @dirty_zn_cnt: number of dirty znodes * @clean_zn_cnt: number of clean znodes @@ -1188,11 +1187,14 @@ struct ubifs_info { int cmt_state; spinlock_t cs_lock; wait_queue_head_t cmt_wq; + unsigned int fast_unmount:1; unsigned int big_lpt:1; unsigned int check_lpt_free:1; unsigned int nospace:1; unsigned int nospace_rp:1; + unsigned int no_chk_data_crc:1; + unsigned int bulk_read:1; struct mutex tnc_mutex; struct ubifs_zbranch zroot; @@ -1217,6 +1219,7 @@ struct ubifs_info { struct ubifs_mst_node *mst_node; int mst_offs; struct mutex mst_mutex; + int bulk_read_buf_size; int log_lebs; long long log_bytes; @@ -1247,11 +1250,6 @@ struct ubifs_info { int old_leb_cnt; int ro_media; - int bulk_read; - int bulk_read_buf_size; - - int no_chk_data_crc; - atomic_long_t dirty_pg_cnt; atomic_long_t dirty_zn_cnt; atomic_long_t clean_zn_cnt; -- cgit v0.10.2 From 2094c334fdebbcceddf21f97cb16b144707af56e Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 5 Sep 2008 15:20:04 +0300 Subject: UBIFS: correct key comparison The comparison was working, but more by accident than design. Signed-off-by: Adrian Hunter diff --git a/fs/ubifs/tnc_misc.c b/fs/ubifs/tnc_misc.c index a25c1cc..b48db99 100644 --- a/fs/ubifs/tnc_misc.c +++ b/fs/ubifs/tnc_misc.c @@ -480,8 +480,8 @@ int ubifs_tnc_read_node(struct ubifs_info *c, struct ubifs_zbranch *zbr, } /* Make sure the key of the read node is correct */ - key_read(c, key, &key1); - if (memcmp(node + UBIFS_KEY_OFFSET, &key1, c->key_len)) { + key_read(c, node + UBIFS_KEY_OFFSET, &key1); + if (!keys_eq(c, key, &key1)) { ubifs_err("bad key in node at LEB %d:%d", zbr->lnum, zbr->offs); dbg_tnc("looked for key %s found node's key %s", -- cgit v0.10.2 From ed382d5898ccfc3d7ba775be2f1596f6a1547935 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 5 Sep 2008 16:17:42 +0300 Subject: UBIFS: ensure data read beyond i_size is zeroed out correctly Signed-off-by: Adrian Hunter diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index cdcfe95..2f20a49 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -147,6 +147,12 @@ static int do_readpage(struct page *page) err = ret; if (err != -ENOENT) break; + } else if (block + 1 == beyond) { + int dlen = le32_to_cpu(dn->size); + int ilen = i_size & (UBIFS_BLOCK_SIZE - 1); + + if (ilen && ilen < dlen) + memset(addr + ilen, 0, dlen - ilen); } } if (++i >= UBIFS_BLOCKS_PER_PAGE) @@ -601,7 +607,7 @@ static int populate_page(struct ubifs_info *c, struct page *page, addr = zaddr = kmap(page); - end_index = (i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + end_index = (i_size - 1) >> PAGE_CACHE_SHIFT; if (!i_size || page->index > end_index) { memset(addr, 0, PAGE_CACHE_SIZE); goto out_hole; @@ -649,7 +655,7 @@ static int populate_page(struct ubifs_info *c, struct page *page, if (end_index == page->index) { int len = i_size & (PAGE_CACHE_SIZE - 1); - if (len < read) + if (len && len < read) memset(zaddr + len, 0, read - len); } diff --git a/fs/ubifs/ubifs-media.h b/fs/ubifs/ubifs-media.h index a9ecbd9..0b37804 100644 --- a/fs/ubifs/ubifs-media.h +++ b/fs/ubifs/ubifs-media.h @@ -75,7 +75,6 @@ */ #define UBIFS_BLOCK_SIZE 4096 #define UBIFS_BLOCK_SHIFT 12 -#define UBIFS_BLOCK_MASK 0x00000FFF /* UBIFS padding byte pattern (must not be first or last byte of node magic) */ #define UBIFS_PADDING_BYTE 0xCE -- cgit v0.10.2 From ba60ecabf067c8ecbde47af4d99b74ee57234d8e Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 8 Sep 2008 16:38:01 +0300 Subject: UBIFS: fix races in bit-fields We cannot store bit-fields together if the processes which change them may race, unless we serialize them. Thus, move the nospc and nospc_rp bit-fields eway from the mount option/constant bit-fields, to avoid races. Signed-off-by: Artem Bityutskiy diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 542cbaf..c3ac5a8 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -334,7 +334,7 @@ struct ubifs_gced_idx_leb { * @bulk_read: non-zero if bulk-read should be used * @ui_mutex: serializes inode write-back with the rest of VFS operations, * serializes "clean <-> dirty" state changes, serializes bulk-read, - * protects @dirty, @ui_size, and @xattr_size + * protects @dirty, @bulk_read, @ui_size, and @xattr_size * @ui_lock: protects @synced_i_size * @synced_i_size: synchronized size of inode, i.e. the value of inode size * currently stored on the flash; used only for regular file @@ -944,10 +944,6 @@ struct ubifs_mount_opts { * @fast_unmount: do not run journal commit before un-mounting * @big_lpt: flag that LPT is too big to write whole during commit * @check_lpt_free: flag that indicates LPT GC may be needed - * @nospace: non-zero if the file-system does not have flash space (used as - * optimization) - * @nospace_rp: the same as @nospace, but additionally means that even reserved - * pool is full * @no_chk_data_crc: do not check CRCs when reading data nodes (except during * recovery) * @bulk_read: enable bulk-reads @@ -1017,12 +1013,17 @@ struct ubifs_mount_opts { * but which still have to be taken into account because * the index has not been committed so far * @space_lock: protects @budg_idx_growth, @budg_data_growth, @budg_dd_growth, - * @budg_uncommited_idx, @min_idx_lebs, @old_idx_sz, and @lst; + * @budg_uncommited_idx, @min_idx_lebs, @old_idx_sz, @lst, + * @nospace, and @nospace_rp; * @min_idx_lebs: minimum number of LEBs required for the index * @old_idx_sz: size of index on flash * @calc_idx_sz: temporary variable which is used to calculate new index size * (contains accurate new index size at end of TNC commit start) * @lst: lprops statistics + * @nospace: non-zero if the file-system does not have flash space (used as + * optimization) + * @nospace_rp: the same as @nospace, but additionally means that even reserved + * pool is full * * @page_budget: budget for a page * @inode_budget: budget for an inode @@ -1191,8 +1192,6 @@ struct ubifs_info { unsigned int fast_unmount:1; unsigned int big_lpt:1; unsigned int check_lpt_free:1; - unsigned int nospace:1; - unsigned int nospace_rp:1; unsigned int no_chk_data_crc:1; unsigned int bulk_read:1; @@ -1263,6 +1262,8 @@ struct ubifs_info { unsigned long long old_idx_sz; unsigned long long calc_idx_sz; struct ubifs_lp_stats lst; + unsigned int nospace:1; + unsigned int nospace_rp:1; int page_budget; int inode_budget; -- cgit v0.10.2 From be61678b1d97c9b47bb839beb3c3f48da36af072 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 8 Sep 2008 18:08:39 +0300 Subject: UBIFS: fix commentary Znode may refer both data nodes and indexing nodes Signed-off-by: Artem Bityutskiy diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index c3ac5a8..49b06c9 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -707,8 +707,8 @@ struct ubifs_jhead { * struct ubifs_zbranch - key/coordinate/length branch stored in znodes. * @key: key * @znode: znode address in memory - * @lnum: LEB number of the indexing node - * @offs: offset of the indexing node within @lnum + * @lnum: LEB number of the target node (indexing node or data node) + * @offs: target node offset within @lnum * @len: target node length */ struct ubifs_zbranch { -- cgit v0.10.2 From b5e426e9a4a8d4ccc65a6849420d47f87c080d5d Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 9 Sep 2008 11:20:35 +0300 Subject: UBIFS: update dbg_dump_inode 'dbg_dump_inode()' is quite outdated and does not print all the fileds. Signed-off-by: Artem Bityutskiy diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index d7f7645..32071ec 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -222,30 +222,38 @@ void dbg_dump_inode(const struct ubifs_info *c, const struct inode *inode) { const struct ubifs_inode *ui = ubifs_inode(inode); - printk(KERN_DEBUG "inode %lu\n", inode->i_ino); - printk(KERN_DEBUG "size %llu\n", + printk(KERN_DEBUG "Dump in-memory inode:"); + printk(KERN_DEBUG "\tinode %lu\n", inode->i_ino); + printk(KERN_DEBUG "\tsize %llu\n", (unsigned long long)i_size_read(inode)); - printk(KERN_DEBUG "nlink %u\n", inode->i_nlink); - printk(KERN_DEBUG "uid %u\n", (unsigned int)inode->i_uid); - printk(KERN_DEBUG "gid %u\n", (unsigned int)inode->i_gid); - printk(KERN_DEBUG "atime %u.%u\n", + printk(KERN_DEBUG "\tnlink %u\n", inode->i_nlink); + printk(KERN_DEBUG "\tuid %u\n", (unsigned int)inode->i_uid); + printk(KERN_DEBUG "\tgid %u\n", (unsigned int)inode->i_gid); + printk(KERN_DEBUG "\tatime %u.%u\n", (unsigned int)inode->i_atime.tv_sec, (unsigned int)inode->i_atime.tv_nsec); - printk(KERN_DEBUG "mtime %u.%u\n", + printk(KERN_DEBUG "\tmtime %u.%u\n", (unsigned int)inode->i_mtime.tv_sec, (unsigned int)inode->i_mtime.tv_nsec); - printk(KERN_DEBUG "ctime %u.%u\n", + printk(KERN_DEBUG "\tctime %u.%u\n", (unsigned int)inode->i_ctime.tv_sec, (unsigned int)inode->i_ctime.tv_nsec); - printk(KERN_DEBUG "creat_sqnum %llu\n", ui->creat_sqnum); - printk(KERN_DEBUG "xattr_size %u\n", ui->xattr_size); - printk(KERN_DEBUG "xattr_cnt %u\n", ui->xattr_cnt); - printk(KERN_DEBUG "xattr_names %u\n", ui->xattr_names); - printk(KERN_DEBUG "dirty %u\n", ui->dirty); - printk(KERN_DEBUG "xattr %u\n", ui->xattr); - printk(KERN_DEBUG "flags %d\n", ui->flags); - printk(KERN_DEBUG "compr_type %d\n", ui->compr_type); - printk(KERN_DEBUG "data_len %d\n", ui->data_len); + printk(KERN_DEBUG "\tcreat_sqnum %llu\n", ui->creat_sqnum); + printk(KERN_DEBUG "\txattr_size %u\n", ui->xattr_size); + printk(KERN_DEBUG "\txattr_cnt %u\n", ui->xattr_cnt); + printk(KERN_DEBUG "\txattr_names %u\n", ui->xattr_names); + printk(KERN_DEBUG "\tdirty %u\n", ui->dirty); + printk(KERN_DEBUG "\txattr %u\n", ui->xattr); + printk(KERN_DEBUG "\tbulk_read %u\n", ui->xattr); + printk(KERN_DEBUG "\tsynced_i_size %llu\n", + (unsigned long long)ui->synced_i_size); + printk(KERN_DEBUG "\tui_size %llu\n", + (unsigned long long)ui->ui_size); + printk(KERN_DEBUG "\tflags %d\n", ui->flags); + printk(KERN_DEBUG "\tcompr_type %d\n", ui->compr_type); + printk(KERN_DEBUG "\tlast_page_read %lu\n", ui->last_page_read); + printk(KERN_DEBUG "\tread_in_a_row %lu\n", ui->read_in_a_row); + printk(KERN_DEBUG "\tdata_len %d\n", ui->data_len); } void dbg_dump_node(const struct ubifs_info *c, const void *node) -- cgit v0.10.2 From af2eb5637b88f7b8edf295ad3880706c5c30c324 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 9 Sep 2008 12:23:50 +0300 Subject: UBIFS: correct comment for commit_on_unmount Signed-off-by: Artem Bityutskiy diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index cf078b5..dae1c62 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1465,12 +1465,9 @@ out: * commit_on_unmount - commit the journal when un-mounting. * @c: UBIFS file-system description object * - * This function is called during un-mounting and it commits the journal unless - * the "fast unmount" mode is enabled. It also avoids committing the journal if - * it contains too few data. - * - * Sometimes recovery requires the journal to be committed at least once, and - * this function takes care about this. + * This function is called during un-mounting and re-mounting, and it commits + * the journal unless the "fast unmount" mode is enabled. It also avoids + * committing the journal if it contains too few data. */ static void commit_on_unmount(struct ubifs_info *c) { -- cgit v0.10.2 From 403e12ab30ab160e1015bd998f0abc1865c574e0 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 9 Sep 2008 12:31:37 +0300 Subject: UBIFS: commit on sync_fs Commit the journal when the FS is sync'ed. This will make statfs provide better free space report. And we anyway advice our users to sync the FS if they want better statfs report. Signed-off-by: Artem Bityutskiy diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index dae1c62..7e1f3ef 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -418,6 +418,7 @@ static int ubifs_sync_fs(struct super_block *sb, int wait) { struct ubifs_info *c = sb->s_fs_info; int i, ret = 0, err; + long long bud_bytes; if (c->jheads) for (i = 0; i < c->jhead_cnt; i++) { @@ -425,6 +426,17 @@ static int ubifs_sync_fs(struct super_block *sb, int wait) if (err && !ret) ret = err; } + + /* Commit the journal unless it has too few data */ + spin_lock(&c->buds_lock); + bud_bytes = c->bud_bytes; + spin_unlock(&c->buds_lock); + if (bud_bytes > c->leb_size) { + err = ubifs_run_commit(c); + if (err) + return err; + } + /* * We ought to call sync for c->ubi but it does not have one. If it had * it would in turn call mtd->sync, however mtd operations are -- cgit v0.10.2 From bed79935de9a658678f44b88a097367d3b26429f Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 11 Sep 2008 14:25:44 +0300 Subject: UBIFS: allow for sync_fs when read-only sync_fs can be called even if the file system is mounted read-only. Ensure the commit is not run in that case. Reported-by: Zoltan Sogor Signed-off-by: Adrian Hunter diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 7e1f3ef..7fd759d 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -420,21 +420,22 @@ static int ubifs_sync_fs(struct super_block *sb, int wait) int i, ret = 0, err; long long bud_bytes; - if (c->jheads) + if (c->jheads) { for (i = 0; i < c->jhead_cnt; i++) { err = ubifs_wbuf_sync(&c->jheads[i].wbuf); if (err && !ret) ret = err; } - /* Commit the journal unless it has too few data */ - spin_lock(&c->buds_lock); - bud_bytes = c->bud_bytes; - spin_unlock(&c->buds_lock); - if (bud_bytes > c->leb_size) { - err = ubifs_run_commit(c); - if (err) - return err; + /* Commit the journal unless it has too little data */ + spin_lock(&c->buds_lock); + bud_bytes = c->bud_bytes; + spin_unlock(&c->buds_lock); + if (bud_bytes > c->leb_size) { + err = ubifs_run_commit(c); + if (err) + return err; + } } /* -- cgit v0.10.2 From 46773be497a05010a2873e9ad96d739fb352c1e4 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 11 Sep 2008 12:57:49 +0300 Subject: UBIFS: improve garbage collection Make garbage collection try to keep data nodes from the same inode together and in ascending order. This improves performance when reading those nodes especially when bulk-read is used. Signed-off-by: Adrian Hunter diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c index a6b633a..0bef650 100644 --- a/fs/ubifs/gc.c +++ b/fs/ubifs/gc.c @@ -96,6 +96,48 @@ static int switch_gc_head(struct ubifs_info *c) } /** + * joinup - bring data nodes for an inode together. + * @c: UBIFS file-system description object + * @sleb: describes scanned LEB + * @inum: inode number + * @blk: block number + * @data: list to which to add data nodes + * + * This function looks at the first few nodes in the scanned LEB @sleb and adds + * them to @data if they are data nodes from @inum and have a larger block + * number than @blk. This function returns %0 on success and a negative error + * code on failure. + */ +static int joinup(struct ubifs_info *c, struct ubifs_scan_leb *sleb, ino_t inum, + unsigned int blk, struct list_head *data) +{ + int err, cnt = 6, lnum = sleb->lnum, offs; + struct ubifs_scan_node *snod, *tmp; + union ubifs_key *key; + + list_for_each_entry_safe(snod, tmp, &sleb->nodes, list) { + key = &snod->key; + if (key_inum(c, key) == inum && + key_type(c, key) == UBIFS_DATA_KEY && + key_block(c, key) > blk) { + offs = snod->offs; + err = ubifs_tnc_has_node(c, key, 0, lnum, offs, 0); + if (err < 0) + return err; + list_del(&snod->list); + if (err) { + list_add_tail(&snod->list, data); + blk = key_block(c, key); + } else + kfree(snod); + cnt = 6; + } else if (--cnt == 0) + break; + } + return 0; +} + +/** * move_nodes - move nodes. * @c: UBIFS file-system description object * @sleb: describes nodes to move @@ -116,16 +158,21 @@ static int switch_gc_head(struct ubifs_info *c) static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb) { struct ubifs_scan_node *snod, *tmp; - struct list_head large, medium, small; + struct list_head data, large, medium, small; struct ubifs_wbuf *wbuf = &c->jheads[GCHD].wbuf; int avail, err, min = INT_MAX; + unsigned int blk = 0; + ino_t inum = 0; + INIT_LIST_HEAD(&data); INIT_LIST_HEAD(&large); INIT_LIST_HEAD(&medium); INIT_LIST_HEAD(&small); - list_for_each_entry_safe(snod, tmp, &sleb->nodes, list) { - struct list_head *lst; + while (!list_empty(&sleb->nodes)) { + struct list_head *lst = sleb->nodes.next; + + snod = list_entry(lst, struct ubifs_scan_node, list); ubifs_assert(snod->type != UBIFS_IDX_NODE); ubifs_assert(snod->type != UBIFS_REF_NODE); @@ -136,7 +183,6 @@ static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb) if (err < 0) goto out; - lst = &snod->list; list_del(lst); if (!err) { /* The node is obsolete, remove it from the list */ @@ -145,15 +191,30 @@ static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb) } /* - * Sort the list of nodes so that large nodes go first, and - * small nodes go last. + * Sort the list of nodes so that data nodes go first, large + * nodes go second, and small nodes go last. */ - if (snod->len > MEDIUM_NODE_WM) - list_add(lst, &large); + if (key_type(c, &snod->key) == UBIFS_DATA_KEY) { + if (inum != key_inum(c, &snod->key)) { + if (inum) { + /* + * Try to move data nodes from the same + * inode together. + */ + err = joinup(c, sleb, inum, blk, &data); + if (err) + goto out; + } + inum = key_inum(c, &snod->key); + blk = key_block(c, &snod->key); + } + list_add_tail(lst, &data); + } else if (snod->len > MEDIUM_NODE_WM) + list_add_tail(lst, &large); else if (snod->len > SMALL_NODE_WM) - list_add(lst, &medium); + list_add_tail(lst, &medium); else - list_add(lst, &small); + list_add_tail(lst, &small); /* And find the smallest node */ if (snod->len < min) @@ -164,6 +225,7 @@ static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb) * Join the tree lists so that we'd have one roughly sorted list * ('large' will be the head of the joined list). */ + list_splice(&data, &large); list_splice(&medium, large.prev); list_splice(&small, large.prev); -- cgit v0.10.2 From 5c0013c16bd2ee08ffef1a1365622556a57218f5 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 12 Sep 2008 10:34:51 +0300 Subject: UBIFS: fix bulk-read handling uptodate pages Bulk-read skips uptodate pages but this was putting its array index out and causing it to treat subsequent pages as holes. Signed-off-by: Adrian Hunter diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 2f20a49..51cf511 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -595,7 +595,7 @@ out: static int populate_page(struct ubifs_info *c, struct page *page, struct bu_info *bu, int *n) { - int i = 0, nn = *n, offs = bu->zbranch[0].offs, hole = 1, read = 0; + int i = 0, nn = *n, offs = bu->zbranch[0].offs, hole = 0, read = 0; struct inode *inode = page->mapping->host; loff_t i_size = i_size_read(inode); unsigned int page_block; @@ -609,6 +609,7 @@ static int populate_page(struct ubifs_info *c, struct page *page, end_index = (i_size - 1) >> PAGE_CACHE_SHIFT; if (!i_size || page->index > end_index) { + hole = 1; memset(addr, 0, PAGE_CACHE_SIZE); goto out_hole; } @@ -617,10 +618,10 @@ static int populate_page(struct ubifs_info *c, struct page *page, while (1) { int err, len, out_len, dlen; - if (nn >= bu->cnt || - key_block(c, &bu->zbranch[nn].key) != page_block) + if (nn >= bu->cnt) { + hole = 1; memset(addr, 0, UBIFS_BLOCK_SIZE); - else { + } else if (key_block(c, &bu->zbranch[nn].key) == page_block) { struct ubifs_data_node *dn; dn = bu->buf + (bu->zbranch[nn].offs - offs); @@ -643,8 +644,13 @@ static int populate_page(struct ubifs_info *c, struct page *page, memset(addr + len, 0, UBIFS_BLOCK_SIZE - len); nn += 1; - hole = 0; read = (i << UBIFS_BLOCK_SHIFT) + len; + } else if (key_block(c, &bu->zbranch[nn].key) < page_block) { + nn += 1; + continue; + } else { + hole = 1; + memset(addr, 0, UBIFS_BLOCK_SIZE); } if (++i >= UBIFS_BLOCKS_PER_PAGE) break; -- cgit v0.10.2 From 73944a6de048c2c49422e9063e57198256efd23e Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 12 Sep 2008 18:13:31 +0300 Subject: UBIFS: add more debugging messages for LPT Also add debugging checks for LPT size and separate out c->check_lpt_free from unrelated bitfields. Signed-off-by: Adrian Hunter diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 32071ec..7186400 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -655,6 +655,43 @@ void dbg_dump_lprops(struct ubifs_info *c) } } +void dbg_dump_lpt_info(struct ubifs_info *c) +{ + int i; + + spin_lock(&dbg_lock); + printk(KERN_DEBUG "\tlpt_sz: %lld\n", c->lpt_sz); + printk(KERN_DEBUG "\tpnode_sz: %d\n", c->pnode_sz); + printk(KERN_DEBUG "\tnnode_sz: %d\n", c->nnode_sz); + printk(KERN_DEBUG "\tltab_sz: %d\n", c->ltab_sz); + printk(KERN_DEBUG "\tlsave_sz: %d\n", c->lsave_sz); + printk(KERN_DEBUG "\tbig_lpt: %d\n", c->big_lpt); + printk(KERN_DEBUG "\tlpt_hght: %d\n", c->lpt_hght); + printk(KERN_DEBUG "\tpnode_cnt: %d\n", c->pnode_cnt); + printk(KERN_DEBUG "\tnnode_cnt: %d\n", c->nnode_cnt); + printk(KERN_DEBUG "\tdirty_pn_cnt: %d\n", c->dirty_pn_cnt); + printk(KERN_DEBUG "\tdirty_nn_cnt: %d\n", c->dirty_nn_cnt); + printk(KERN_DEBUG "\tlsave_cnt: %d\n", c->lsave_cnt); + printk(KERN_DEBUG "\tspace_bits: %d\n", c->space_bits); + printk(KERN_DEBUG "\tlpt_lnum_bits: %d\n", c->lpt_lnum_bits); + printk(KERN_DEBUG "\tlpt_offs_bits: %d\n", c->lpt_offs_bits); + printk(KERN_DEBUG "\tlpt_spc_bits: %d\n", c->lpt_spc_bits); + printk(KERN_DEBUG "\tpcnt_bits: %d\n", c->pcnt_bits); + printk(KERN_DEBUG "\tlnum_bits: %d\n", c->lnum_bits); + printk(KERN_DEBUG "\tLPT root is at %d:%d\n", c->lpt_lnum, c->lpt_offs); + printk(KERN_DEBUG "\tLPT head is at %d:%d\n", + c->nhead_lnum, c->nhead_offs); + printk(KERN_DEBUG "\tLPT ltab is at %d:%d\n", c->ltab_lnum, c->ltab_offs); + if (c->big_lpt) + printk(KERN_DEBUG "\tLPT lsave is at %d:%d\n", + c->lsave_lnum, c->lsave_offs); + for (i = 0; i < c->lpt_lebs; i++) + printk(KERN_DEBUG "\tLPT LEB %d free %d dirty %d tgc %d " + "cmt %d\n", i + c->lpt_first, c->ltab[i].free, + c->ltab[i].dirty, c->ltab[i].tgc, c->ltab[i].cmt); + spin_unlock(&dbg_lock); +} + void dbg_dump_leb(const struct ubifs_info *c, int lnum) { struct ubifs_scan_leb *sleb; diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h index 50315fc..33d6b95 100644 --- a/fs/ubifs/debug.h +++ b/fs/ubifs/debug.h @@ -224,6 +224,7 @@ void dbg_dump_lstats(const struct ubifs_lp_stats *lst); void dbg_dump_budg(struct ubifs_info *c); void dbg_dump_lprop(const struct ubifs_info *c, const struct ubifs_lprops *lp); void dbg_dump_lprops(struct ubifs_info *c); +void dbg_dump_lpt_info(struct ubifs_info *c); void dbg_dump_leb(const struct ubifs_info *c, int lnum); void dbg_dump_znode(const struct ubifs_info *c, const struct ubifs_znode *znode); @@ -249,6 +250,8 @@ int dbg_old_index_check_init(struct ubifs_info *c, struct ubifs_zbranch *zroot); int dbg_check_old_index(struct ubifs_info *c, struct ubifs_zbranch *zroot); int dbg_check_cats(struct ubifs_info *c); int dbg_check_ltab(struct ubifs_info *c); +int dbg_chk_lpt_free_spc(struct ubifs_info *c); +int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len); int dbg_check_synced_i_size(struct inode *inode); int dbg_check_dir_size(struct ubifs_info *c, const struct inode *dir); int dbg_check_tnc(struct ubifs_info *c, int extra); @@ -367,6 +370,7 @@ static inline int dbg_change(struct ubi_volume_desc *desc, int lnum, #define dbg_dump_budg(c) ({}) #define dbg_dump_lprop(c, lp) ({}) #define dbg_dump_lprops(c) ({}) +#define dbg_dump_lpt_info(c) ({}) #define dbg_dump_leb(c, lnum) ({}) #define dbg_dump_znode(c, znode) ({}) #define dbg_dump_heap(c, heap, cat) ({}) @@ -379,6 +383,8 @@ static inline int dbg_change(struct ubi_volume_desc *desc, int lnum, #define dbg_check_old_index(c, zroot) 0 #define dbg_check_cats(c) 0 #define dbg_check_ltab(c) 0 +#define dbg_chk_lpt_free_spc(c) 0 +#define dbg_chk_lpt_sz(c, action, len) 0 #define dbg_check_synced_i_size(inode) 0 #define dbg_check_dir_size(c, dir) 0 #define dbg_check_tnc(c, x) 0 diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index 9ff2463..cd11b23 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -109,7 +109,8 @@ static void do_calc_lpt_geom(struct ubifs_info *c) c->lpt_sz = (long long)c->pnode_cnt * c->pnode_sz; c->lpt_sz += (long long)c->nnode_cnt * c->nnode_sz; c->lpt_sz += c->ltab_sz; - c->lpt_sz += c->lsave_sz; + if (c->big_lpt) + c->lpt_sz += c->lsave_sz; /* Add wastage */ sz = c->lpt_sz; diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index 5f0b83e..8546865 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -177,8 +177,6 @@ static int alloc_lpt_leb(struct ubifs_info *c, int *lnum) return 0; } } - dbg_err("last LEB %d", *lnum); - dump_stack(); return -ENOSPC; } @@ -193,6 +191,9 @@ static int layout_cnodes(struct ubifs_info *c) int lnum, offs, len, alen, done_lsave, done_ltab, err; struct ubifs_cnode *cnode; + err = dbg_chk_lpt_sz(c, 0, 0); + if (err) + return err; cnode = c->lpt_cnext; if (!cnode) return 0; @@ -206,6 +207,7 @@ static int layout_cnodes(struct ubifs_info *c) c->lsave_lnum = lnum; c->lsave_offs = offs; offs += c->lsave_sz; + dbg_chk_lpt_sz(c, 1, c->lsave_sz); } if (offs + c->ltab_sz <= c->leb_size) { @@ -213,6 +215,7 @@ static int layout_cnodes(struct ubifs_info *c) c->ltab_lnum = lnum; c->ltab_offs = offs; offs += c->ltab_sz; + dbg_chk_lpt_sz(c, 1, c->ltab_sz); } do { @@ -226,9 +229,10 @@ static int layout_cnodes(struct ubifs_info *c) while (offs + len > c->leb_size) { alen = ALIGN(offs, c->min_io_size); upd_ltab(c, lnum, c->leb_size - alen, alen - offs); + dbg_chk_lpt_sz(c, 2, alen - offs); err = alloc_lpt_leb(c, &lnum); if (err) - return err; + goto no_space; offs = 0; ubifs_assert(lnum >= c->lpt_first && lnum <= c->lpt_last); @@ -238,6 +242,7 @@ static int layout_cnodes(struct ubifs_info *c) c->lsave_lnum = lnum; c->lsave_offs = offs; offs += c->lsave_sz; + dbg_chk_lpt_sz(c, 1, c->lsave_sz); continue; } if (!done_ltab) { @@ -245,6 +250,7 @@ static int layout_cnodes(struct ubifs_info *c) c->ltab_lnum = lnum; c->ltab_offs = offs; offs += c->ltab_sz; + dbg_chk_lpt_sz(c, 1, c->ltab_sz); continue; } break; @@ -257,6 +263,7 @@ static int layout_cnodes(struct ubifs_info *c) c->lpt_offs = offs; } offs += len; + dbg_chk_lpt_sz(c, 1, len); cnode = cnode->cnext; } while (cnode && cnode != c->lpt_cnext); @@ -265,9 +272,10 @@ static int layout_cnodes(struct ubifs_info *c) if (offs + c->lsave_sz > c->leb_size) { alen = ALIGN(offs, c->min_io_size); upd_ltab(c, lnum, c->leb_size - alen, alen - offs); + dbg_chk_lpt_sz(c, 2, alen - offs); err = alloc_lpt_leb(c, &lnum); if (err) - return err; + goto no_space; offs = 0; ubifs_assert(lnum >= c->lpt_first && lnum <= c->lpt_last); @@ -276,6 +284,7 @@ static int layout_cnodes(struct ubifs_info *c) c->lsave_lnum = lnum; c->lsave_offs = offs; offs += c->lsave_sz; + dbg_chk_lpt_sz(c, 1, c->lsave_sz); } /* Make sure to place LPT's own lprops table */ @@ -283,9 +292,10 @@ static int layout_cnodes(struct ubifs_info *c) if (offs + c->ltab_sz > c->leb_size) { alen = ALIGN(offs, c->min_io_size); upd_ltab(c, lnum, c->leb_size - alen, alen - offs); + dbg_chk_lpt_sz(c, 2, alen - offs); err = alloc_lpt_leb(c, &lnum); if (err) - return err; + goto no_space; offs = 0; ubifs_assert(lnum >= c->lpt_first && lnum <= c->lpt_last); @@ -294,11 +304,23 @@ static int layout_cnodes(struct ubifs_info *c) c->ltab_lnum = lnum; c->ltab_offs = offs; offs += c->ltab_sz; + dbg_chk_lpt_sz(c, 1, c->ltab_sz); } alen = ALIGN(offs, c->min_io_size); upd_ltab(c, lnum, c->leb_size - alen, alen - offs); + dbg_chk_lpt_sz(c, 4, alen - offs); + err = dbg_chk_lpt_sz(c, 3, alen); + if (err) + return err; return 0; + +no_space: + ubifs_err("LPT out of space"); + dbg_err("LPT out of space at LEB %d:%d needing %d, done_ltab %d, " + "done_lsave %d", lnum, offs, len, done_ltab, done_lsave); + dbg_dump_lpt_info(c); + return err; } /** @@ -333,8 +355,6 @@ static int realloc_lpt_leb(struct ubifs_info *c, int *lnum) *lnum = i + c->lpt_first; return 0; } - dbg_err("last LEB %d", *lnum); - dump_stack(); return -ENOSPC; } @@ -369,12 +389,14 @@ static int write_cnodes(struct ubifs_info *c) done_lsave = 1; ubifs_pack_lsave(c, buf + offs, c->lsave); offs += c->lsave_sz; + dbg_chk_lpt_sz(c, 1, c->lsave_sz); } if (offs + c->ltab_sz <= c->leb_size) { done_ltab = 1; ubifs_pack_ltab(c, buf + offs, c->ltab_cmt); offs += c->ltab_sz; + dbg_chk_lpt_sz(c, 1, c->ltab_sz); } /* Loop for each cnode */ @@ -392,10 +414,12 @@ static int write_cnodes(struct ubifs_info *c) alen, UBI_SHORTTERM); if (err) return err; + dbg_chk_lpt_sz(c, 4, alen - wlen); } + dbg_chk_lpt_sz(c, 2, 0); err = realloc_lpt_leb(c, &lnum); if (err) - return err; + goto no_space; offs = 0; from = 0; ubifs_assert(lnum >= c->lpt_first && @@ -408,12 +432,14 @@ static int write_cnodes(struct ubifs_info *c) done_lsave = 1; ubifs_pack_lsave(c, buf + offs, c->lsave); offs += c->lsave_sz; + dbg_chk_lpt_sz(c, 1, c->lsave_sz); continue; } if (!done_ltab) { done_ltab = 1; ubifs_pack_ltab(c, buf + offs, c->ltab_cmt); offs += c->ltab_sz; + dbg_chk_lpt_sz(c, 1, c->ltab_sz); continue; } break; @@ -435,6 +461,7 @@ static int write_cnodes(struct ubifs_info *c) clear_bit(COW_ZNODE, &cnode->flags); smp_mb__after_clear_bit(); offs += len; + dbg_chk_lpt_sz(c, 1, len); cnode = cnode->cnext; } while (cnode && cnode != c->lpt_cnext); @@ -448,9 +475,10 @@ static int write_cnodes(struct ubifs_info *c) UBI_SHORTTERM); if (err) return err; + dbg_chk_lpt_sz(c, 2, alen - wlen); err = realloc_lpt_leb(c, &lnum); if (err) - return err; + goto no_space; offs = 0; ubifs_assert(lnum >= c->lpt_first && lnum <= c->lpt_last); @@ -461,6 +489,7 @@ static int write_cnodes(struct ubifs_info *c) done_lsave = 1; ubifs_pack_lsave(c, buf + offs, c->lsave); offs += c->lsave_sz; + dbg_chk_lpt_sz(c, 1, c->lsave_sz); } /* Make sure to place LPT's own lprops table */ @@ -473,9 +502,10 @@ static int write_cnodes(struct ubifs_info *c) UBI_SHORTTERM); if (err) return err; + dbg_chk_lpt_sz(c, 2, alen - wlen); err = realloc_lpt_leb(c, &lnum); if (err) - return err; + goto no_space; offs = 0; ubifs_assert(lnum >= c->lpt_first && lnum <= c->lpt_last); @@ -486,6 +516,7 @@ static int write_cnodes(struct ubifs_info *c) done_ltab = 1; ubifs_pack_ltab(c, buf + offs, c->ltab_cmt); offs += c->ltab_sz; + dbg_chk_lpt_sz(c, 1, c->ltab_sz); } /* Write remaining data in buffer */ @@ -495,6 +526,12 @@ static int write_cnodes(struct ubifs_info *c) err = ubifs_leb_write(c, lnum, buf + from, from, alen, UBI_SHORTTERM); if (err) return err; + + dbg_chk_lpt_sz(c, 4, alen - wlen); + err = dbg_chk_lpt_sz(c, 3, ALIGN(offs, c->min_io_size)); + if (err) + return err; + c->nhead_lnum = lnum; c->nhead_offs = ALIGN(offs, c->min_io_size); @@ -503,7 +540,15 @@ static int write_cnodes(struct ubifs_info *c) dbg_lp("LPT ltab is at %d:%d", c->ltab_lnum, c->ltab_offs); if (c->big_lpt) dbg_lp("LPT lsave is at %d:%d", c->lsave_lnum, c->lsave_offs); + return 0; + +no_space: + ubifs_err("LPT out of space mismatch"); + dbg_err("LPT out of space mismatch at LEB %d:%d needing %d, done_ltab " + "%d, done_lsave %d", lnum, offs, len, done_ltab, done_lsave); + dbg_dump_lpt_info(c); + return err; } /** @@ -1156,6 +1201,9 @@ int ubifs_lpt_start_commit(struct ubifs_info *c) dbg_lp(""); mutex_lock(&c->lp_mutex); + err = dbg_chk_lpt_free_spc(c); + if (err) + goto out; err = dbg_check_ltab(c); if (err) goto out; @@ -1645,4 +1693,121 @@ int dbg_check_ltab(struct ubifs_info *c) return 0; } +/** + * dbg_chk_lpt_free_spc - check LPT free space is enough to write entire LPT. + * @c: the UBIFS file-system description object + * + * This function returns %0 on success and a negative error code on failure. + */ +int dbg_chk_lpt_free_spc(struct ubifs_info *c) +{ + long long free = 0; + int i; + + for (i = 0; i < c->lpt_lebs; i++) { + if (c->ltab[i].tgc || c->ltab[i].cmt) + continue; + if (i + c->lpt_first == c->nhead_lnum) + free += c->leb_size - c->nhead_offs; + else if (c->ltab[i].free == c->leb_size) + free += c->leb_size; + } + if (free < c->lpt_sz) { + dbg_err("LPT space error: free %lld lpt_sz %lld", + free, c->lpt_sz); + dbg_dump_lpt_info(c); + return -EINVAL; + } + return 0; +} + +/** + * dbg_chk_lpt_sz - check LPT does not write more than LPT size. + * @c: the UBIFS file-system description object + * @action: action + * @len: length written + * + * This function returns %0 on success and a negative error code on failure. + */ +int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len) +{ + long long chk_lpt_sz, lpt_sz; + int err = 0; + + switch (action) { + case 0: + c->chk_lpt_sz = 0; + c->chk_lpt_sz2 = 0; + c->chk_lpt_lebs = 0; + c->chk_lpt_wastage = 0; + if (c->dirty_pn_cnt > c->pnode_cnt) { + dbg_err("dirty pnodes %d exceed max %d", + c->dirty_pn_cnt, c->pnode_cnt); + err = -EINVAL; + } + if (c->dirty_nn_cnt > c->nnode_cnt) { + dbg_err("dirty nnodes %d exceed max %d", + c->dirty_nn_cnt, c->nnode_cnt); + err = -EINVAL; + } + return err; + case 1: + c->chk_lpt_sz += len; + return 0; + case 2: + c->chk_lpt_sz += len; + c->chk_lpt_wastage += len; + c->chk_lpt_lebs += 1; + return 0; + case 3: + chk_lpt_sz = c->leb_size; + chk_lpt_sz *= c->chk_lpt_lebs; + chk_lpt_sz += len - c->nhead_offs; + if (c->chk_lpt_sz != chk_lpt_sz) { + dbg_err("LPT wrote %lld but space used was %lld", + c->chk_lpt_sz, chk_lpt_sz); + err = -EINVAL; + } + if (c->chk_lpt_sz > c->lpt_sz) { + dbg_err("LPT wrote %lld but lpt_sz is %lld", + c->chk_lpt_sz, c->lpt_sz); + err = -EINVAL; + } + if (c->chk_lpt_sz2 && c->chk_lpt_sz != c->chk_lpt_sz2) { + dbg_err("LPT layout size %lld but wrote %lld", + c->chk_lpt_sz, c->chk_lpt_sz2); + err = -EINVAL; + } + if (c->chk_lpt_sz2 && c->new_nhead_offs != len) { + dbg_err("LPT new nhead offs: expected %d was %d", + c->new_nhead_offs, len); + err = -EINVAL; + } + lpt_sz = (long long)c->pnode_cnt * c->pnode_sz; + lpt_sz += (long long)c->nnode_cnt * c->nnode_sz; + lpt_sz += c->ltab_sz; + if (c->big_lpt) + lpt_sz += c->lsave_sz; + if (c->chk_lpt_sz - c->chk_lpt_wastage > lpt_sz) { + dbg_err("LPT chk_lpt_sz %lld + waste %lld exceeds %lld", + c->chk_lpt_sz, c->chk_lpt_wastage, lpt_sz); + err = -EINVAL; + } + if (err) + dbg_dump_lpt_info(c); + c->chk_lpt_sz2 = c->chk_lpt_sz; + c->chk_lpt_sz = 0; + c->chk_lpt_wastage = 0; + c->chk_lpt_lebs = 0; + c->new_nhead_offs = len; + return err; + case 4: + c->chk_lpt_sz += len; + c->chk_lpt_wastage += len; + return 0; + default: + return -EINVAL; + } +} + #endif /* CONFIG_UBIFS_FS_DEBUG */ diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 49b06c9..a7bd32f 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -943,7 +943,6 @@ struct ubifs_mount_opts { * * @fast_unmount: do not run journal commit before un-mounting * @big_lpt: flag that LPT is too big to write whole during commit - * @check_lpt_free: flag that indicates LPT GC may be needed * @no_chk_data_crc: do not check CRCs when reading data nodes (except during * recovery) * @bulk_read: enable bulk-reads @@ -1102,6 +1101,7 @@ struct ubifs_mount_opts { * @lpt_drty_flgs: dirty flags for LPT special nodes e.g. ltab * @dirty_nn_cnt: number of dirty nnodes * @dirty_pn_cnt: number of dirty pnodes + * @check_lpt_free: flag that indicates LPT GC may be needed * @lpt_sz: LPT size * @lpt_nod_buf: buffer for an on-flash nnode or pnode * @lpt_buf: buffer of LEB size used by LPT @@ -1191,7 +1191,6 @@ struct ubifs_info { unsigned int fast_unmount:1; unsigned int big_lpt:1; - unsigned int check_lpt_free:1; unsigned int no_chk_data_crc:1; unsigned int bulk_read:1; @@ -1340,6 +1339,7 @@ struct ubifs_info { int lpt_drty_flgs; int dirty_nn_cnt; int dirty_pn_cnt; + int check_lpt_free; long long lpt_sz; void *lpt_nod_buf; void *lpt_buf; @@ -1394,6 +1394,12 @@ struct ubifs_info { unsigned long fail_timeout; unsigned int fail_cnt; unsigned int fail_cnt_max; + long long chk_lpt_sz; + long long chk_lpt_sz2; + long long chk_lpt_wastage; + int chk_lpt_lebs; + int new_nhead_lnum; + int new_nhead_offs; #endif }; -- cgit v0.10.2 From 63c300b68fd93a9fadc5e317d4d001b7a6985486 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 17 Sep 2008 12:11:13 +0300 Subject: UBIFS: correct condition to eliminate unecessary assignment Signed-off-by: Adrian Hunter diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index e0878a4..d27fd91 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -1600,7 +1600,7 @@ out: * An enormous hole could cause bulk-read to encompass too many * page cache pages, so limit the number here. */ - if (bu->blk_cnt >= UBIFS_MAX_BULK_READ) + if (bu->blk_cnt > UBIFS_MAX_BULK_READ) bu->blk_cnt = UBIFS_MAX_BULK_READ; /* * Ensure that bulk-read covers a whole number of page cache -- cgit v0.10.2 From be2f6bd62d0d4246a9227dacbe2469e1f0eccf26 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 26 Sep 2008 12:52:21 +0300 Subject: UBIFS: check buffer length when scanning for LPT nodes 'is_a_node()' function was reading from a buffer before checking the buffer length, resulting in an OOPS as follows: BUG: unable to handle kernel paging request at f8f74002 IP: [] :ubifs:ubifs_unpack_bits+0xca/0x233 *pde = 19e95067 *pte = 00000000 Oops: 0000 [#1] PREEMPT SMP Modules linked in: ubifs ubi mtdchar bio2mtd mtd brd video output [last unloaded: mtd] Pid: 6414, comm: integck Not tainted (2.6.27-rc6ubifs34 #23) EIP: 0060:[] EFLAGS: 00010246 CPU: 0 EIP is at ubifs_unpack_bits+0xca/0x233 [ubifs] EAX: 00000000 EBX: f6090630 ECX: d9badcfc EDX: 00000000 ESI: 00000004 EDI: f8f74002 EBP: d9badcec ESP: d9badcc0 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process integck (pid: 6414, ti=d9bac000 task=f727dae0 task.ti=d9bac000) Stack: 00000006 f7306240 00000002 00000000 d9badcfc d9badd00 0000001c 00000000 f6090630 f6090630 f8f74000 d9badd10 f8fa1cc9 00000000 f8f74002 00000000 f8f74002 f60fe128 f6090630 f8f74000 d9badd68 f8fa1e46 00000000 0001e000 Call Trace: [] ? is_a_node+0x30/0x90 [ubifs] [] ? dbg_check_ltab+0x11d/0x5bd [ubifs] [] ? ubifs_lpt_start_commit+0x42/0xed3 [ubifs] [] ? mutex_unlock+0x8/0xa [] ? ubifs_tnc_start_commit+0x1c8/0xedb [ubifs] [] ? do_commit+0x187/0x523 [ubifs] [] ? mutex_unlock+0x8/0xa [] ? bud_wbuf_callback+0x22/0x28 [ubifs] [] ? ubifs_run_commit+0x76/0xc0 [ubifs] [] ? ubifs_sync_fs+0xd2/0xe6 [ubifs] [] ? vfs_quota_sync+0x0/0x17e [] ? quota_sync_sb+0x26/0xbb [] ? vfs_quota_sync+0x0/0x17e [] ? sync_dquots+0x22/0x12c [] ? __fsync_super+0x19/0x68 [] ? fsync_super+0xb/0x19 [] ? generic_shutdown_super+0x22/0xe7 [] ? vfs_quota_off+0x0/0x5fd [] ? ubifs_kill_sb+0x31/0x35 [ubifs] [] ? deactivate_super+0x5e/0x71 [] ? mntput_no_expire+0x82/0xe4 [] ? sys_umount+0x4c/0x2f6 [] ? sys_oldumount+0x19/0x1b [] ? sysenter_do_call+0x12/0x25 ======================= Code: c1 f8 03 8d 04 07 8b 4d e8 89 01 8b 45 e4 89 10 89 d8 89 f1 d3 e8 85 c0 74 07 29 d6 83 fe 20 75 2a 89 d8 83 c4 20 5b 5e 5f 5d EIP: [] ubifs_unpack_bits+0xca/0x233 [ubifs] SS:ESP 0068:d9badcc0 ---[ end trace 1f02572436518c13 ]--- Signed-off-by: Adrian Hunter diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index 8546865..eed5a00 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -1089,6 +1089,8 @@ static int is_a_node(struct ubifs_info *c, uint8_t *buf, int len) int pos = 0, node_type, node_len; uint16_t crc, calc_crc; + if (len < UBIFS_LPT_CRC_BYTES + (UBIFS_LPT_TYPE_BITS + 7) / 8) + return 0; node_type = ubifs_unpack_bits(&addr, &pos, UBIFS_LPT_TYPE_BITS); if (node_type == UBIFS_LPT_NOT_A_NODE) return 0; -- cgit v0.10.2 From 64c9627c2628bc3bd3291710b8ee6f8335883f8b Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 1 Oct 2008 15:12:27 +0900 Subject: sh: Fix up the __raw_read/writeX() definitions. These were doing largely bogus things and using the wrong typing for the address. Bring these in line with the ARM definitions. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index 1857666..d9e794e 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -101,44 +101,33 @@ #define outsw __outsw #define outsl __outsl -#define __raw_readb(a) __readb((void __iomem *)(a)) -#define __raw_readw(a) __readw((void __iomem *)(a)) -#define __raw_readl(a) __readl((void __iomem *)(a)) -#define __raw_writeb(v, a) __writeb(v, (void __iomem *)(a)) -#define __raw_writew(v, a) __writew(v, (void __iomem *)(a)) -#define __raw_writel(v, a) __writel(v, (void __iomem *)(a)) +#define __raw_writeb(v,a) (__chk_io_ptr(a), *(volatile unsigned char __force *)(a) = (v)) +#define __raw_writew(v,a) (__chk_io_ptr(a), *(volatile unsigned short __force *)(a) = (v)) +#define __raw_writel(v,a) (__chk_io_ptr(a), *(volatile unsigned int __force *)(a) = (v)) -void __raw_writesl(unsigned long addr, const void *data, int longlen); -void __raw_readsl(unsigned long addr, void *data, int longlen); +#define __raw_readb(a) (__chk_io_ptr(a), *(volatile unsigned char __force *)(a)) +#define __raw_readw(a) (__chk_io_ptr(a), *(volatile unsigned short __force *)(a)) +#define __raw_readl(a) (__chk_io_ptr(a), *(volatile unsigned int __force *)(a)) + +void __raw_writesl(void __iomem *addr, const void *data, int longlen); +void __raw_readsl(const void __iomem *addr, void *data, int longlen); /* * The platform header files may define some of these macros to use * the inlined versions where appropriate. These macros may also be * redefined by userlevel programs. */ -#ifdef __readb -# define readb(a) ({ unsigned int r_ = __raw_readb(a); mb(); r_; }) -#endif -#ifdef __raw_readw -# define readw(a) ({ unsigned int r_ = __raw_readw(a); mb(); r_; }) -#endif -#ifdef __raw_readl -# define readl(a) ({ unsigned int r_ = __raw_readl(a); mb(); r_; }) -#endif +#define readb(a) ({ unsigned int r_ = __readb(a); mb(); r_; }) +#define readw(a) ({ unsigned int r_ = __readw(a); mb(); r_; }) +#define readl(a) ({ unsigned int r_ = __readl(a); mb(); r_; }) -#ifdef __raw_writeb -# define writeb(v,a) ({ __raw_writeb((v),(a)); mb(); }) -#endif -#ifdef __raw_writew -# define writew(v,a) ({ __raw_writew((v),(a)); mb(); }) -#endif -#ifdef __raw_writel -# define writel(v,a) ({ __raw_writel((v),(a)); mb(); }) -#endif +#define writeb(v,a) ({ __writeb((v),(a)); mb(); }) +#define writew(v,a) ({ __writew((v),(a)); mb(); }) +#define writel(v,a) ({ __writel((v),(a)); mb(); }) #define __BUILD_MEMORY_STRING(bwlq, type) \ \ -static inline void writes##bwlq(volatile void __iomem *mem, \ +static inline void __raw_writes##bwlq(volatile void __iomem *mem, \ const void *addr, unsigned int count) \ { \ const volatile type *__addr = addr; \ @@ -149,8 +138,8 @@ static inline void writes##bwlq(volatile void __iomem *mem, \ } \ } \ \ -static inline void reads##bwlq(volatile void __iomem *mem, void *addr, \ - unsigned int count) \ +static inline void __raw_reads##bwlq(volatile void __iomem *mem, \ + void *addr, unsigned int count) \ { \ volatile type *__addr = addr; \ \ @@ -162,7 +151,13 @@ static inline void reads##bwlq(volatile void __iomem *mem, void *addr, \ __BUILD_MEMORY_STRING(b, u8) __BUILD_MEMORY_STRING(w, u16) + +#define writesb __raw_writesb +#define writesw __raw_writesw #define writesl __raw_writesl + +#define readsb __raw_readsb +#define readsw __raw_readsw #define readsl __raw_readsl #define readb_relaxed(a) readb(a) @@ -170,25 +165,25 @@ __BUILD_MEMORY_STRING(w, u16) #define readl_relaxed(a) readl(a) /* Simple MMIO */ -#define ioread8(a) readb(a) -#define ioread16(a) readw(a) +#define ioread8(a) __raw_readb(a) +#define ioread16(a) __raw_readw(a) #define ioread16be(a) be16_to_cpu(__raw_readw((a))) -#define ioread32(a) readl(a) +#define ioread32(a) __raw_readl(a) #define ioread32be(a) be32_to_cpu(__raw_readl((a))) -#define iowrite8(v,a) writeb((v),(a)) -#define iowrite16(v,a) writew((v),(a)) +#define iowrite8(v,a) __raw_writeb((v),(a)) +#define iowrite16(v,a) __raw_writew((v),(a)) #define iowrite16be(v,a) __raw_writew(cpu_to_be16((v)),(a)) -#define iowrite32(v,a) writel((v),(a)) +#define iowrite32(v,a) __raw_writel((v),(a)) #define iowrite32be(v,a) __raw_writel(cpu_to_be32((v)),(a)) -#define ioread8_rep(a, d, c) readsb((a), (d), (c)) -#define ioread16_rep(a, d, c) readsw((a), (d), (c)) -#define ioread32_rep(a, d, c) readsl((a), (d), (c)) +#define ioread8_rep(a, d, c) __raw_readsb((a), (d), (c)) +#define ioread16_rep(a, d, c) __raw_readsw((a), (d), (c)) +#define ioread32_rep(a, d, c) __raw_readsl((a), (d), (c)) -#define iowrite8_rep(a, s, c) writesb((a), (s), (c)) -#define iowrite16_rep(a, s, c) writesw((a), (s), (c)) -#define iowrite32_rep(a, s, c) writesl((a), (s), (c)) +#define iowrite8_rep(a, s, c) __raw_writesb((a), (s), (c)) +#define iowrite16_rep(a, s, c) __raw_writesw((a), (s), (c)) +#define iowrite32_rep(a, s, c) __raw_writesl((a), (s), (c)) #define mmiowb() wmb() /* synco on SH-4A, otherwise a nop */ diff --git a/arch/sh/lib/io.c b/arch/sh/lib/io.c index 4f54ec4..88dfe6e 100644 --- a/arch/sh/lib/io.c +++ b/arch/sh/lib/io.c @@ -14,12 +14,12 @@ #include #include -void __raw_readsl(unsigned long addr, void *datap, int len) +void __raw_readsl(const void __iomem *addr, void *datap, int len) { u32 *data; for (data = datap; (len != 0) && (((u32)data & 0x1f) != 0); len--) - *data++ = ctrl_inl(addr); + *data++ = __raw_readl(addr); if (likely(len >= (0x20 >> 2))) { int tmp2, tmp3, tmp4, tmp5, tmp6; @@ -59,11 +59,11 @@ void __raw_readsl(unsigned long addr, void *datap, int len) } for (; len != 0; len--) - *data++ = ctrl_inl(addr); + *data++ = __raw_readl(addr); } EXPORT_SYMBOL(__raw_readsl); -void __raw_writesl(unsigned long addr, const void *data, int len) +void __raw_writesl(void __iomem *addr, const void *data, int len) { if (likely(len != 0)) { int tmp1; -- cgit v0.10.2 From 62429e03644833693e6f94afe537f252e2d3b475 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 1 Oct 2008 15:19:10 +0900 Subject: sh: Use __raw_xxx() I/O accessors for INTC and IPR. Signed-off-by: Paul Mundt diff --git a/arch/sh/kernel/cpu/irq/intc.c b/arch/sh/kernel/cpu/irq/intc.c index 94536d3..138efa4 100644 --- a/arch/sh/kernel/cpu/irq/intc.c +++ b/arch/sh/kernel/cpu/irq/intc.c @@ -86,24 +86,24 @@ static inline unsigned int set_field(unsigned int value, static void write_8(unsigned long addr, unsigned long h, unsigned long data) { - ctrl_outb(set_field(0, data, h), addr); + __raw_writeb(set_field(0, data, h), addr); } static void write_16(unsigned long addr, unsigned long h, unsigned long data) { - ctrl_outw(set_field(0, data, h), addr); + __raw_writew(set_field(0, data, h), addr); } static void write_32(unsigned long addr, unsigned long h, unsigned long data) { - ctrl_outl(set_field(0, data, h), addr); + __raw_writel(set_field(0, data, h), addr); } static void modify_8(unsigned long addr, unsigned long h, unsigned long data) { unsigned long flags; local_irq_save(flags); - ctrl_outb(set_field(ctrl_inb(addr), data, h), addr); + __raw_writeb(set_field(__raw_readb(addr), data, h), addr); local_irq_restore(flags); } @@ -111,7 +111,7 @@ static void modify_16(unsigned long addr, unsigned long h, unsigned long data) { unsigned long flags; local_irq_save(flags); - ctrl_outw(set_field(ctrl_inw(addr), data, h), addr); + __raw_writew(set_field(__raw_readw(addr), data, h), addr); local_irq_restore(flags); } @@ -119,7 +119,7 @@ static void modify_32(unsigned long addr, unsigned long h, unsigned long data) { unsigned long flags; local_irq_save(flags); - ctrl_outl(set_field(ctrl_inl(addr), data, h), addr); + __raw_writel(set_field(__raw_readl(addr), data, h), addr); local_irq_restore(flags); } @@ -246,16 +246,16 @@ static void intc_mask_ack(unsigned int irq) addr = INTC_REG(d, _INTC_ADDR_D(handle), 0); switch (_INTC_FN(handle)) { case REG_FN_MODIFY_BASE + 0: /* 8bit */ - ctrl_inb(addr); - ctrl_outb(0xff ^ set_field(0, 1, handle), addr); + __raw_readb(addr); + __raw_writeb(0xff ^ set_field(0, 1, handle), addr); break; case REG_FN_MODIFY_BASE + 1: /* 16bit */ - ctrl_inw(addr); - ctrl_outw(0xffff ^ set_field(0, 1, handle), addr); + __raw_readw(addr); + __raw_writew(0xffff ^ set_field(0, 1, handle), addr); break; case REG_FN_MODIFY_BASE + 3: /* 32bit */ - ctrl_inl(addr); - ctrl_outl(0xffffffff ^ set_field(0, 1, handle), addr); + __raw_readl(addr); + __raw_writel(0xffffffff ^ set_field(0, 1, handle), addr); break; default: BUG(); diff --git a/arch/sh/kernel/cpu/irq/ipr.c b/arch/sh/kernel/cpu/irq/ipr.c index 56ea7b2..3eb17ee 100644 --- a/arch/sh/kernel/cpu/irq/ipr.c +++ b/arch/sh/kernel/cpu/irq/ipr.c @@ -33,7 +33,7 @@ static void disable_ipr_irq(unsigned int irq) struct ipr_data *p = get_irq_chip_data(irq); unsigned long addr = get_ipr_desc(irq)->ipr_offsets[p->ipr_idx]; /* Set the priority in IPR to 0 */ - ctrl_outw(ctrl_inw(addr) & (0xffff ^ (0xf << p->shift)), addr); + __raw_writew(__raw_readw(addr) & (0xffff ^ (0xf << p->shift)), addr); } static void enable_ipr_irq(unsigned int irq) @@ -41,7 +41,7 @@ static void enable_ipr_irq(unsigned int irq) struct ipr_data *p = get_irq_chip_data(irq); unsigned long addr = get_ipr_desc(irq)->ipr_offsets[p->ipr_idx]; /* Set priority in IPR back to original value */ - ctrl_outw(ctrl_inw(addr) | (p->priority << p->shift), addr); + __raw_writew(__raw_readw(addr) | (p->priority << p->shift), addr); } /* -- cgit v0.10.2 From 7ff731aeba1cdac473c818a9884eb94ddad18e7f Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 1 Oct 2008 15:46:58 +0900 Subject: serial: sh-sci: Handle the general UPF_IOREMAP case. Presently we don't do much with UPF_IOREMAP other than special case it for SH-5's onchip_remap() on the early console. Tie this in generically for platforms that need the remap. Signed-off-by: Paul Mundt diff --git a/drivers/serial/sh-sci.c b/drivers/serial/sh-sci.c index f5aebc9..ac658a7 100644 --- a/drivers/serial/sh-sci.c +++ b/drivers/serial/sh-sci.c @@ -3,7 +3,7 @@ * * SuperH on-chip serial module support. (SCI with no FIFO / with FIFO) * - * Copyright (C) 2002 - 2006 Paul Mundt + * Copyright (C) 2002 - 2008 Paul Mundt * Modified to support SH7720 SCIF. Markus Brunner, Mark Jonas (Jul 2007). * * based off of the old drivers/char/sh-sci.c by: @@ -46,6 +46,7 @@ #include #include #include +#include #ifdef CONFIG_SUPERH #include @@ -1145,12 +1146,16 @@ static void sci_config_port(struct uart_port *port, int flags) break; } -#if defined(CONFIG_CPU_SUBTYPE_SH5_101) || defined(CONFIG_CPU_SUBTYPE_SH5_103) - if (port->mapbase == 0) + if (port->flags & UPF_IOREMAP && !port->membase) { +#if defined(CONFIG_SUPERH64) port->mapbase = onchip_remap(SCIF_ADDR_SH5, 1024, "SCIF"); - - port->membase = (void __iomem *)port->mapbase; + port->membase = (void __iomem *)port->mapbase; +#else + port->membase = ioremap_nocache(port->mapbase, 0x40); #endif + + printk(KERN_ERR "sci: can't remap port#%d\n", port->line); + } } static int sci_verify_port(struct uart_port *port, struct serial_struct *ser) @@ -1436,7 +1441,7 @@ static struct uart_driver sci_uart_driver = { static int __devinit sci_probe(struct platform_device *dev) { struct plat_sci_port *p = dev->dev.platform_data; - int i; + int i, ret = -EINVAL; for (i = 0; p && p->flags != 0; p++, i++) { struct sci_port *sciport = &sci_ports[i]; @@ -1453,12 +1458,22 @@ static int __devinit sci_probe(struct platform_device *dev) sciport->port.mapbase = p->mapbase; - /* - * For the simple (and majority of) cases where we don't need - * to do any remapping, just cast the cookie directly. - */ - if (p->mapbase && !p->membase && !(p->flags & UPF_IOREMAP)) - p->membase = (void __iomem *)p->mapbase; + if (p->mapbase && !p->membase) { + if (p->flags & UPF_IOREMAP) { + p->membase = ioremap_nocache(p->mapbase, 0x40); + if (IS_ERR(p->membase)) { + ret = PTR_ERR(p->membase); + goto err_unreg; + } + } else { + /* + * For the simple (and majority of) cases + * where we don't need to do any remapping, + * just cast the cookie directly. + */ + p->membase = (void __iomem *)p->mapbase; + } + } sciport->port.membase = p->membase; @@ -1489,6 +1504,12 @@ static int __devinit sci_probe(struct platform_device *dev) #endif return 0; + +err_unreg: + for (i = i - 1; i >= 0; i--) + uart_remove_one_port(&sci_uart_driver, &sci_ports[i].port); + + return ret; } static int __devexit sci_remove(struct platform_device *dev) diff --git a/drivers/serial/sh-sci.h b/drivers/serial/sh-sci.h index 8a0749e..2b4c1df 100644 --- a/drivers/serial/sh-sci.h +++ b/drivers/serial/sh-sci.h @@ -320,18 +320,16 @@ #define SCI_EVENT_WRITE_WAKEUP 0 #define SCI_IN(size, offset) \ - unsigned int addr = port->mapbase + (offset); \ if ((size) == 8) { \ - return ctrl_inb(addr); \ + return ioread8(port->membase + (offset)); \ } else { \ - return ctrl_inw(addr); \ + return ioread16(port->membase + (offset)); \ } #define SCI_OUT(size, offset, value) \ - unsigned int addr = port->mapbase + (offset); \ if ((size) == 8) { \ - ctrl_outb(value, addr); \ + iowrite8(value, port->membase + (offset)); \ } else if ((size) == 16) { \ - ctrl_outw(value, addr); \ + iowrite16(value, port->membase + (offset)); \ } #define CPU_SCIx_FNS(name, sci_offset, sci_size, scif_offset, scif_size)\ -- cgit v0.10.2 From bbfbd8b151fe35c9a1180a7f5254c5d6b8387cc0 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 1 Oct 2008 16:13:54 +0900 Subject: sh: Move the shared INTC code out to drivers/sh/ The INTC code will be re-used across different architectures, so move this out to drivers/sh/ and include/linux/sh_intc.h respectively. Signed-off-by: Paul Mundt diff --git a/arch/sh/include/asm/hw_irq.h b/arch/sh/include/asm/hw_irq.h index d557b00..603cdde 100644 --- a/arch/sh/include/asm/hw_irq.h +++ b/arch/sh/include/asm/hw_irq.h @@ -2,6 +2,7 @@ #define __ASM_SH_HW_IRQ_H #include +#include #include extern atomic_t irq_err_count; @@ -23,101 +24,12 @@ struct ipr_desc { void register_ipr_controller(struct ipr_desc *); -typedef unsigned char intc_enum; - -struct intc_vect { - intc_enum enum_id; - unsigned short vect; -}; - -#define INTC_VECT(enum_id, vect) { enum_id, vect } -#define INTC_IRQ(enum_id, irq) INTC_VECT(enum_id, irq2evt(irq)) - -struct intc_group { - intc_enum enum_id; - intc_enum enum_ids[32]; -}; - -#define INTC_GROUP(enum_id, ids...) { enum_id, { ids } } - -struct intc_mask_reg { - unsigned long set_reg, clr_reg, reg_width; - intc_enum enum_ids[32]; -#ifdef CONFIG_SMP - unsigned long smp; -#endif -}; - -struct intc_prio_reg { - unsigned long set_reg, clr_reg, reg_width, field_width; - intc_enum enum_ids[16]; -#ifdef CONFIG_SMP - unsigned long smp; -#endif -}; - -struct intc_sense_reg { - unsigned long reg, reg_width, field_width; - intc_enum enum_ids[16]; -}; - -#ifdef CONFIG_SMP -#define INTC_SMP(stride, nr) .smp = (stride) | ((nr) << 8) -#else -#define INTC_SMP(stride, nr) -#endif - -struct intc_desc { - struct intc_vect *vectors; - unsigned int nr_vectors; - struct intc_group *groups; - unsigned int nr_groups; - struct intc_mask_reg *mask_regs; - unsigned int nr_mask_regs; - struct intc_prio_reg *prio_regs; - unsigned int nr_prio_regs; - struct intc_sense_reg *sense_regs; - unsigned int nr_sense_regs; - char *name; -#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) - struct intc_mask_reg *ack_regs; - unsigned int nr_ack_regs; -#endif -}; - -#define _INTC_ARRAY(a) a, sizeof(a)/sizeof(*a) -#define DECLARE_INTC_DESC(symbol, chipname, vectors, groups, \ - mask_regs, prio_regs, sense_regs) \ -struct intc_desc symbol __initdata = { \ - _INTC_ARRAY(vectors), _INTC_ARRAY(groups), \ - _INTC_ARRAY(mask_regs), _INTC_ARRAY(prio_regs), \ - _INTC_ARRAY(sense_regs), \ - chipname, \ -} - -#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) -#define DECLARE_INTC_DESC_ACK(symbol, chipname, vectors, groups, \ - mask_regs, prio_regs, sense_regs, ack_regs) \ -struct intc_desc symbol __initdata = { \ - _INTC_ARRAY(vectors), _INTC_ARRAY(groups), \ - _INTC_ARRAY(mask_regs), _INTC_ARRAY(prio_regs), \ - _INTC_ARRAY(sense_regs), \ - chipname, \ - _INTC_ARRAY(ack_regs), \ -} -#endif - -void __init register_intc_controller(struct intc_desc *desc); -int intc_set_priority(unsigned int irq, unsigned int prio); - void __init plat_irq_setup(void); -#ifdef CONFIG_CPU_SH3 void __init plat_irq_setup_sh3(void); -#endif +void __init plat_irq_setup_pins(int mode); enum { IRQ_MODE_IRQ, IRQ_MODE_IRQ7654, IRQ_MODE_IRQ3210, IRQ_MODE_IRL7654_MASK, IRQ_MODE_IRL3210_MASK, IRQ_MODE_IRL7654, IRQ_MODE_IRL3210 }; -void __init plat_irq_setup_pins(int mode); #endif /* __ASM_SH_HW_IRQ_H */ diff --git a/arch/sh/kernel/cpu/irq/Makefile b/arch/sh/kernel/cpu/irq/Makefile index 462a8f6..f0c7025 100644 --- a/arch/sh/kernel/cpu/irq/Makefile +++ b/arch/sh/kernel/cpu/irq/Makefile @@ -1,8 +1,6 @@ # # Makefile for the Linux/SuperH CPU-specifc IRQ handlers. # -obj-y += intc.o - obj-$(CONFIG_SUPERH32) += imask.o obj-$(CONFIG_CPU_SH5) += intc-sh5.o obj-$(CONFIG_CPU_HAS_IPR_IRQ) += ipr.o diff --git a/arch/sh/kernel/cpu/irq/intc.c b/arch/sh/kernel/cpu/irq/intc.c deleted file mode 100644 index 138efa4..0000000 --- a/arch/sh/kernel/cpu/irq/intc.c +++ /dev/null @@ -1,712 +0,0 @@ -/* - * Shared interrupt handling code for IPR and INTC2 types of IRQs. - * - * Copyright (C) 2007, 2008 Magnus Damm - * - * Based on intc2.c and ipr.c - * - * Copyright (C) 1999 Niibe Yutaka & Takeshi Yaegashi - * Copyright (C) 2000 Kazumoto Kojima - * Copyright (C) 2001 David J. Mckay (david.mckay@st.com) - * Copyright (C) 2003 Takashi Kusuda - * Copyright (C) 2005, 2006 Paul Mundt - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ -#include -#include -#include -#include -#include -#include - -#define _INTC_MK(fn, mode, addr_e, addr_d, width, shift) \ - ((shift) | ((width) << 5) | ((fn) << 9) | ((mode) << 13) | \ - ((addr_e) << 16) | ((addr_d << 24))) - -#define _INTC_SHIFT(h) (h & 0x1f) -#define _INTC_WIDTH(h) ((h >> 5) & 0xf) -#define _INTC_FN(h) ((h >> 9) & 0xf) -#define _INTC_MODE(h) ((h >> 13) & 0x7) -#define _INTC_ADDR_E(h) ((h >> 16) & 0xff) -#define _INTC_ADDR_D(h) ((h >> 24) & 0xff) - -struct intc_handle_int { - unsigned int irq; - unsigned long handle; -}; - -struct intc_desc_int { - unsigned long *reg; -#ifdef CONFIG_SMP - unsigned long *smp; -#endif - unsigned int nr_reg; - struct intc_handle_int *prio; - unsigned int nr_prio; - struct intc_handle_int *sense; - unsigned int nr_sense; - struct irq_chip chip; -}; - -#ifdef CONFIG_SMP -#define IS_SMP(x) x.smp -#define INTC_REG(d, x, c) (d->reg[(x)] + ((d->smp[(x)] & 0xff) * c)) -#define SMP_NR(d, x) ((d->smp[(x)] >> 8) ? (d->smp[(x)] >> 8) : 1) -#else -#define IS_SMP(x) 0 -#define INTC_REG(d, x, c) (d->reg[(x)]) -#define SMP_NR(d, x) 1 -#endif - -static unsigned int intc_prio_level[NR_IRQS]; /* for now */ -#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) -static unsigned long ack_handle[NR_IRQS]; -#endif - -static inline struct intc_desc_int *get_intc_desc(unsigned int irq) -{ - struct irq_chip *chip = get_irq_chip(irq); - return (void *)((char *)chip - offsetof(struct intc_desc_int, chip)); -} - -static inline unsigned int set_field(unsigned int value, - unsigned int field_value, - unsigned int handle) -{ - unsigned int width = _INTC_WIDTH(handle); - unsigned int shift = _INTC_SHIFT(handle); - - value &= ~(((1 << width) - 1) << shift); - value |= field_value << shift; - return value; -} - -static void write_8(unsigned long addr, unsigned long h, unsigned long data) -{ - __raw_writeb(set_field(0, data, h), addr); -} - -static void write_16(unsigned long addr, unsigned long h, unsigned long data) -{ - __raw_writew(set_field(0, data, h), addr); -} - -static void write_32(unsigned long addr, unsigned long h, unsigned long data) -{ - __raw_writel(set_field(0, data, h), addr); -} - -static void modify_8(unsigned long addr, unsigned long h, unsigned long data) -{ - unsigned long flags; - local_irq_save(flags); - __raw_writeb(set_field(__raw_readb(addr), data, h), addr); - local_irq_restore(flags); -} - -static void modify_16(unsigned long addr, unsigned long h, unsigned long data) -{ - unsigned long flags; - local_irq_save(flags); - __raw_writew(set_field(__raw_readw(addr), data, h), addr); - local_irq_restore(flags); -} - -static void modify_32(unsigned long addr, unsigned long h, unsigned long data) -{ - unsigned long flags; - local_irq_save(flags); - __raw_writel(set_field(__raw_readl(addr), data, h), addr); - local_irq_restore(flags); -} - -enum { REG_FN_ERR = 0, REG_FN_WRITE_BASE = 1, REG_FN_MODIFY_BASE = 5 }; - -static void (*intc_reg_fns[])(unsigned long addr, - unsigned long h, - unsigned long data) = { - [REG_FN_WRITE_BASE + 0] = write_8, - [REG_FN_WRITE_BASE + 1] = write_16, - [REG_FN_WRITE_BASE + 3] = write_32, - [REG_FN_MODIFY_BASE + 0] = modify_8, - [REG_FN_MODIFY_BASE + 1] = modify_16, - [REG_FN_MODIFY_BASE + 3] = modify_32, -}; - -enum { MODE_ENABLE_REG = 0, /* Bit(s) set -> interrupt enabled */ - MODE_MASK_REG, /* Bit(s) set -> interrupt disabled */ - MODE_DUAL_REG, /* Two registers, set bit to enable / disable */ - MODE_PRIO_REG, /* Priority value written to enable interrupt */ - MODE_PCLR_REG, /* Above plus all bits set to disable interrupt */ -}; - -static void intc_mode_field(unsigned long addr, - unsigned long handle, - void (*fn)(unsigned long, - unsigned long, - unsigned long), - unsigned int irq) -{ - fn(addr, handle, ((1 << _INTC_WIDTH(handle)) - 1)); -} - -static void intc_mode_zero(unsigned long addr, - unsigned long handle, - void (*fn)(unsigned long, - unsigned long, - unsigned long), - unsigned int irq) -{ - fn(addr, handle, 0); -} - -static void intc_mode_prio(unsigned long addr, - unsigned long handle, - void (*fn)(unsigned long, - unsigned long, - unsigned long), - unsigned int irq) -{ - fn(addr, handle, intc_prio_level[irq]); -} - -static void (*intc_enable_fns[])(unsigned long addr, - unsigned long handle, - void (*fn)(unsigned long, - unsigned long, - unsigned long), - unsigned int irq) = { - [MODE_ENABLE_REG] = intc_mode_field, - [MODE_MASK_REG] = intc_mode_zero, - [MODE_DUAL_REG] = intc_mode_field, - [MODE_PRIO_REG] = intc_mode_prio, - [MODE_PCLR_REG] = intc_mode_prio, -}; - -static void (*intc_disable_fns[])(unsigned long addr, - unsigned long handle, - void (*fn)(unsigned long, - unsigned long, - unsigned long), - unsigned int irq) = { - [MODE_ENABLE_REG] = intc_mode_zero, - [MODE_MASK_REG] = intc_mode_field, - [MODE_DUAL_REG] = intc_mode_field, - [MODE_PRIO_REG] = intc_mode_zero, - [MODE_PCLR_REG] = intc_mode_field, -}; - -static inline void _intc_enable(unsigned int irq, unsigned long handle) -{ - struct intc_desc_int *d = get_intc_desc(irq); - unsigned long addr; - unsigned int cpu; - - for (cpu = 0; cpu < SMP_NR(d, _INTC_ADDR_E(handle)); cpu++) { - addr = INTC_REG(d, _INTC_ADDR_E(handle), cpu); - intc_enable_fns[_INTC_MODE(handle)](addr, handle, intc_reg_fns\ - [_INTC_FN(handle)], irq); - } -} - -static void intc_enable(unsigned int irq) -{ - _intc_enable(irq, (unsigned long)get_irq_chip_data(irq)); -} - -static void intc_disable(unsigned int irq) -{ - struct intc_desc_int *d = get_intc_desc(irq); - unsigned long handle = (unsigned long) get_irq_chip_data(irq); - unsigned long addr; - unsigned int cpu; - - for (cpu = 0; cpu < SMP_NR(d, _INTC_ADDR_D(handle)); cpu++) { - addr = INTC_REG(d, _INTC_ADDR_D(handle), cpu); - intc_disable_fns[_INTC_MODE(handle)](addr, handle,intc_reg_fns\ - [_INTC_FN(handle)], irq); - } -} - -#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) -static void intc_mask_ack(unsigned int irq) -{ - struct intc_desc_int *d = get_intc_desc(irq); - unsigned long handle = ack_handle[irq]; - unsigned long addr; - - intc_disable(irq); - - /* read register and write zero only to the assocaited bit */ - - if (handle) { - addr = INTC_REG(d, _INTC_ADDR_D(handle), 0); - switch (_INTC_FN(handle)) { - case REG_FN_MODIFY_BASE + 0: /* 8bit */ - __raw_readb(addr); - __raw_writeb(0xff ^ set_field(0, 1, handle), addr); - break; - case REG_FN_MODIFY_BASE + 1: /* 16bit */ - __raw_readw(addr); - __raw_writew(0xffff ^ set_field(0, 1, handle), addr); - break; - case REG_FN_MODIFY_BASE + 3: /* 32bit */ - __raw_readl(addr); - __raw_writel(0xffffffff ^ set_field(0, 1, handle), addr); - break; - default: - BUG(); - break; - } - } -} -#endif - -static struct intc_handle_int *intc_find_irq(struct intc_handle_int *hp, - unsigned int nr_hp, - unsigned int irq) -{ - int i; - - /* this doesn't scale well, but... - * - * this function should only be used for cerain uncommon - * operations such as intc_set_priority() and intc_set_sense() - * and in those rare cases performance doesn't matter that much. - * keeping the memory footprint low is more important. - * - * one rather simple way to speed this up and still keep the - * memory footprint down is to make sure the array is sorted - * and then perform a bisect to lookup the irq. - */ - - for (i = 0; i < nr_hp; i++) { - if ((hp + i)->irq != irq) - continue; - - return hp + i; - } - - return NULL; -} - -int intc_set_priority(unsigned int irq, unsigned int prio) -{ - struct intc_desc_int *d = get_intc_desc(irq); - struct intc_handle_int *ihp; - - if (!intc_prio_level[irq] || prio <= 1) - return -EINVAL; - - ihp = intc_find_irq(d->prio, d->nr_prio, irq); - if (ihp) { - if (prio >= (1 << _INTC_WIDTH(ihp->handle))) - return -EINVAL; - - intc_prio_level[irq] = prio; - - /* - * only set secondary masking method directly - * primary masking method is using intc_prio_level[irq] - * priority level will be set during next enable() - */ - - if (_INTC_FN(ihp->handle) != REG_FN_ERR) - _intc_enable(irq, ihp->handle); - } - return 0; -} - -#define VALID(x) (x | 0x80) - -static unsigned char intc_irq_sense_table[IRQ_TYPE_SENSE_MASK + 1] = { - [IRQ_TYPE_EDGE_FALLING] = VALID(0), - [IRQ_TYPE_EDGE_RISING] = VALID(1), - [IRQ_TYPE_LEVEL_LOW] = VALID(2), - /* SH7706, SH7707 and SH7709 do not support high level triggered */ -#if !defined(CONFIG_CPU_SUBTYPE_SH7706) && \ - !defined(CONFIG_CPU_SUBTYPE_SH7707) && \ - !defined(CONFIG_CPU_SUBTYPE_SH7709) - [IRQ_TYPE_LEVEL_HIGH] = VALID(3), -#endif -}; - -static int intc_set_sense(unsigned int irq, unsigned int type) -{ - struct intc_desc_int *d = get_intc_desc(irq); - unsigned char value = intc_irq_sense_table[type & IRQ_TYPE_SENSE_MASK]; - struct intc_handle_int *ihp; - unsigned long addr; - - if (!value) - return -EINVAL; - - ihp = intc_find_irq(d->sense, d->nr_sense, irq); - if (ihp) { - addr = INTC_REG(d, _INTC_ADDR_E(ihp->handle), 0); - intc_reg_fns[_INTC_FN(ihp->handle)](addr, ihp->handle, value); - } - return 0; -} - -static unsigned int __init intc_get_reg(struct intc_desc_int *d, - unsigned long address) -{ - unsigned int k; - - for (k = 0; k < d->nr_reg; k++) { - if (d->reg[k] == address) - return k; - } - - BUG(); - return 0; -} - -static intc_enum __init intc_grp_id(struct intc_desc *desc, - intc_enum enum_id) -{ - struct intc_group *g = desc->groups; - unsigned int i, j; - - for (i = 0; g && enum_id && i < desc->nr_groups; i++) { - g = desc->groups + i; - - for (j = 0; g->enum_ids[j]; j++) { - if (g->enum_ids[j] != enum_id) - continue; - - return g->enum_id; - } - } - - return 0; -} - -static unsigned int __init intc_mask_data(struct intc_desc *desc, - struct intc_desc_int *d, - intc_enum enum_id, int do_grps) -{ - struct intc_mask_reg *mr = desc->mask_regs; - unsigned int i, j, fn, mode; - unsigned long reg_e, reg_d; - - for (i = 0; mr && enum_id && i < desc->nr_mask_regs; i++) { - mr = desc->mask_regs + i; - - for (j = 0; j < ARRAY_SIZE(mr->enum_ids); j++) { - if (mr->enum_ids[j] != enum_id) - continue; - - if (mr->set_reg && mr->clr_reg) { - fn = REG_FN_WRITE_BASE; - mode = MODE_DUAL_REG; - reg_e = mr->clr_reg; - reg_d = mr->set_reg; - } else { - fn = REG_FN_MODIFY_BASE; - if (mr->set_reg) { - mode = MODE_ENABLE_REG; - reg_e = mr->set_reg; - reg_d = mr->set_reg; - } else { - mode = MODE_MASK_REG; - reg_e = mr->clr_reg; - reg_d = mr->clr_reg; - } - } - - fn += (mr->reg_width >> 3) - 1; - return _INTC_MK(fn, mode, - intc_get_reg(d, reg_e), - intc_get_reg(d, reg_d), - 1, - (mr->reg_width - 1) - j); - } - } - - if (do_grps) - return intc_mask_data(desc, d, intc_grp_id(desc, enum_id), 0); - - return 0; -} - -static unsigned int __init intc_prio_data(struct intc_desc *desc, - struct intc_desc_int *d, - intc_enum enum_id, int do_grps) -{ - struct intc_prio_reg *pr = desc->prio_regs; - unsigned int i, j, fn, mode, bit; - unsigned long reg_e, reg_d; - - for (i = 0; pr && enum_id && i < desc->nr_prio_regs; i++) { - pr = desc->prio_regs + i; - - for (j = 0; j < ARRAY_SIZE(pr->enum_ids); j++) { - if (pr->enum_ids[j] != enum_id) - continue; - - if (pr->set_reg && pr->clr_reg) { - fn = REG_FN_WRITE_BASE; - mode = MODE_PCLR_REG; - reg_e = pr->set_reg; - reg_d = pr->clr_reg; - } else { - fn = REG_FN_MODIFY_BASE; - mode = MODE_PRIO_REG; - if (!pr->set_reg) - BUG(); - reg_e = pr->set_reg; - reg_d = pr->set_reg; - } - - fn += (pr->reg_width >> 3) - 1; - - BUG_ON((j + 1) * pr->field_width > pr->reg_width); - - bit = pr->reg_width - ((j + 1) * pr->field_width); - - return _INTC_MK(fn, mode, - intc_get_reg(d, reg_e), - intc_get_reg(d, reg_d), - pr->field_width, bit); - } - } - - if (do_grps) - return intc_prio_data(desc, d, intc_grp_id(desc, enum_id), 0); - - return 0; -} - -#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) -static unsigned int __init intc_ack_data(struct intc_desc *desc, - struct intc_desc_int *d, - intc_enum enum_id) -{ - struct intc_mask_reg *mr = desc->ack_regs; - unsigned int i, j, fn, mode; - unsigned long reg_e, reg_d; - - for (i = 0; mr && enum_id && i < desc->nr_ack_regs; i++) { - mr = desc->ack_regs + i; - - for (j = 0; j < ARRAY_SIZE(mr->enum_ids); j++) { - if (mr->enum_ids[j] != enum_id) - continue; - - fn = REG_FN_MODIFY_BASE; - mode = MODE_ENABLE_REG; - reg_e = mr->set_reg; - reg_d = mr->set_reg; - - fn += (mr->reg_width >> 3) - 1; - return _INTC_MK(fn, mode, - intc_get_reg(d, reg_e), - intc_get_reg(d, reg_d), - 1, - (mr->reg_width - 1) - j); - } - } - - return 0; -} -#endif - -static unsigned int __init intc_sense_data(struct intc_desc *desc, - struct intc_desc_int *d, - intc_enum enum_id) -{ - struct intc_sense_reg *sr = desc->sense_regs; - unsigned int i, j, fn, bit; - - for (i = 0; sr && enum_id && i < desc->nr_sense_regs; i++) { - sr = desc->sense_regs + i; - - for (j = 0; j < ARRAY_SIZE(sr->enum_ids); j++) { - if (sr->enum_ids[j] != enum_id) - continue; - - fn = REG_FN_MODIFY_BASE; - fn += (sr->reg_width >> 3) - 1; - - BUG_ON((j + 1) * sr->field_width > sr->reg_width); - - bit = sr->reg_width - ((j + 1) * sr->field_width); - - return _INTC_MK(fn, 0, intc_get_reg(d, sr->reg), - 0, sr->field_width, bit); - } - } - - return 0; -} - -static void __init intc_register_irq(struct intc_desc *desc, - struct intc_desc_int *d, - intc_enum enum_id, - unsigned int irq) -{ - struct intc_handle_int *hp; - unsigned int data[2], primary; - - /* Prefer single interrupt source bitmap over other combinations: - * 1. bitmap, single interrupt source - * 2. priority, single interrupt source - * 3. bitmap, multiple interrupt sources (groups) - * 4. priority, multiple interrupt sources (groups) - */ - - data[0] = intc_mask_data(desc, d, enum_id, 0); - data[1] = intc_prio_data(desc, d, enum_id, 0); - - primary = 0; - if (!data[0] && data[1]) - primary = 1; - - data[0] = data[0] ? data[0] : intc_mask_data(desc, d, enum_id, 1); - data[1] = data[1] ? data[1] : intc_prio_data(desc, d, enum_id, 1); - - if (!data[primary]) - primary ^= 1; - - BUG_ON(!data[primary]); /* must have primary masking method */ - - disable_irq_nosync(irq); - set_irq_chip_and_handler_name(irq, &d->chip, - handle_level_irq, "level"); - set_irq_chip_data(irq, (void *)data[primary]); - - /* set priority level - * - this needs to be at least 2 for 5-bit priorities on 7780 - */ - intc_prio_level[irq] = 2; - - /* enable secondary masking method if present */ - if (data[!primary]) - _intc_enable(irq, data[!primary]); - - /* add irq to d->prio list if priority is available */ - if (data[1]) { - hp = d->prio + d->nr_prio; - hp->irq = irq; - hp->handle = data[1]; - - if (primary) { - /* - * only secondary priority should access registers, so - * set _INTC_FN(h) = REG_FN_ERR for intc_set_priority() - */ - - hp->handle &= ~_INTC_MK(0x0f, 0, 0, 0, 0, 0); - hp->handle |= _INTC_MK(REG_FN_ERR, 0, 0, 0, 0, 0); - } - d->nr_prio++; - } - - /* add irq to d->sense list if sense is available */ - data[0] = intc_sense_data(desc, d, enum_id); - if (data[0]) { - (d->sense + d->nr_sense)->irq = irq; - (d->sense + d->nr_sense)->handle = data[0]; - d->nr_sense++; - } - - /* irq should be disabled by default */ - d->chip.mask(irq); - -#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) - if (desc->ack_regs) - ack_handle[irq] = intc_ack_data(desc, d, enum_id); -#endif -} - -static unsigned int __init save_reg(struct intc_desc_int *d, - unsigned int cnt, - unsigned long value, - unsigned int smp) -{ - if (value) { - d->reg[cnt] = value; -#ifdef CONFIG_SMP - d->smp[cnt] = smp; -#endif - return 1; - } - - return 0; -} - - -void __init register_intc_controller(struct intc_desc *desc) -{ - unsigned int i, k, smp; - struct intc_desc_int *d; - - d = alloc_bootmem(sizeof(*d)); - - d->nr_reg = desc->mask_regs ? desc->nr_mask_regs * 2 : 0; - d->nr_reg += desc->prio_regs ? desc->nr_prio_regs * 2 : 0; - d->nr_reg += desc->sense_regs ? desc->nr_sense_regs : 0; - -#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) - d->nr_reg += desc->ack_regs ? desc->nr_ack_regs : 0; -#endif - d->reg = alloc_bootmem(d->nr_reg * sizeof(*d->reg)); -#ifdef CONFIG_SMP - d->smp = alloc_bootmem(d->nr_reg * sizeof(*d->smp)); -#endif - k = 0; - - if (desc->mask_regs) { - for (i = 0; i < desc->nr_mask_regs; i++) { - smp = IS_SMP(desc->mask_regs[i]); - k += save_reg(d, k, desc->mask_regs[i].set_reg, smp); - k += save_reg(d, k, desc->mask_regs[i].clr_reg, smp); - } - } - - if (desc->prio_regs) { - d->prio = alloc_bootmem(desc->nr_vectors * sizeof(*d->prio)); - - for (i = 0; i < desc->nr_prio_regs; i++) { - smp = IS_SMP(desc->prio_regs[i]); - k += save_reg(d, k, desc->prio_regs[i].set_reg, smp); - k += save_reg(d, k, desc->prio_regs[i].clr_reg, smp); - } - } - - if (desc->sense_regs) { - d->sense = alloc_bootmem(desc->nr_vectors * sizeof(*d->sense)); - - for (i = 0; i < desc->nr_sense_regs; i++) { - k += save_reg(d, k, desc->sense_regs[i].reg, 0); - } - } - - d->chip.name = desc->name; - d->chip.mask = intc_disable; - d->chip.unmask = intc_enable; - d->chip.mask_ack = intc_disable; - d->chip.set_type = intc_set_sense; - -#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) - if (desc->ack_regs) { - for (i = 0; i < desc->nr_ack_regs; i++) - k += save_reg(d, k, desc->ack_regs[i].set_reg, 0); - - d->chip.mask_ack = intc_mask_ack; - } -#endif - - BUG_ON(k > 256); /* _INTC_ADDR_E() and _INTC_ADDR_D() are 8 bits */ - - for (i = 0; i < desc->nr_vectors; i++) { - struct intc_vect *vect = desc->vectors + i; - - intc_register_irq(desc, d, vect->enum_id, evt2irq(vect->vect)); - } -} diff --git a/drivers/sh/Makefile b/drivers/sh/Makefile index a96f4a8..6a025ce 100644 --- a/drivers/sh/Makefile +++ b/drivers/sh/Makefile @@ -1,6 +1,6 @@ # # Makefile for the SuperH specific drivers. # - obj-$(CONFIG_SUPERHYWAY) += superhyway/ obj-$(CONFIG_MAPLE) += maple/ +obj-y += intc.o diff --git a/drivers/sh/intc.c b/drivers/sh/intc.c new file mode 100644 index 0000000..58d24c5 --- /dev/null +++ b/drivers/sh/intc.c @@ -0,0 +1,713 @@ +/* + * Shared interrupt handling code for IPR and INTC2 types of IRQs. + * + * Copyright (C) 2007, 2008 Magnus Damm + * + * Based on intc2.c and ipr.c + * + * Copyright (C) 1999 Niibe Yutaka & Takeshi Yaegashi + * Copyright (C) 2000 Kazumoto Kojima + * Copyright (C) 2001 David J. Mckay (david.mckay@st.com) + * Copyright (C) 2003 Takashi Kusuda + * Copyright (C) 2005, 2006 Paul Mundt + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ +#include +#include +#include +#include +#include +#include +#include + +#define _INTC_MK(fn, mode, addr_e, addr_d, width, shift) \ + ((shift) | ((width) << 5) | ((fn) << 9) | ((mode) << 13) | \ + ((addr_e) << 16) | ((addr_d << 24))) + +#define _INTC_SHIFT(h) (h & 0x1f) +#define _INTC_WIDTH(h) ((h >> 5) & 0xf) +#define _INTC_FN(h) ((h >> 9) & 0xf) +#define _INTC_MODE(h) ((h >> 13) & 0x7) +#define _INTC_ADDR_E(h) ((h >> 16) & 0xff) +#define _INTC_ADDR_D(h) ((h >> 24) & 0xff) + +struct intc_handle_int { + unsigned int irq; + unsigned long handle; +}; + +struct intc_desc_int { + unsigned long *reg; +#ifdef CONFIG_SMP + unsigned long *smp; +#endif + unsigned int nr_reg; + struct intc_handle_int *prio; + unsigned int nr_prio; + struct intc_handle_int *sense; + unsigned int nr_sense; + struct irq_chip chip; +}; + +#ifdef CONFIG_SMP +#define IS_SMP(x) x.smp +#define INTC_REG(d, x, c) (d->reg[(x)] + ((d->smp[(x)] & 0xff) * c)) +#define SMP_NR(d, x) ((d->smp[(x)] >> 8) ? (d->smp[(x)] >> 8) : 1) +#else +#define IS_SMP(x) 0 +#define INTC_REG(d, x, c) (d->reg[(x)]) +#define SMP_NR(d, x) 1 +#endif + +static unsigned int intc_prio_level[NR_IRQS]; /* for now */ +#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) +static unsigned long ack_handle[NR_IRQS]; +#endif + +static inline struct intc_desc_int *get_intc_desc(unsigned int irq) +{ + struct irq_chip *chip = get_irq_chip(irq); + return (void *)((char *)chip - offsetof(struct intc_desc_int, chip)); +} + +static inline unsigned int set_field(unsigned int value, + unsigned int field_value, + unsigned int handle) +{ + unsigned int width = _INTC_WIDTH(handle); + unsigned int shift = _INTC_SHIFT(handle); + + value &= ~(((1 << width) - 1) << shift); + value |= field_value << shift; + return value; +} + +static void write_8(unsigned long addr, unsigned long h, unsigned long data) +{ + __raw_writeb(set_field(0, data, h), addr); +} + +static void write_16(unsigned long addr, unsigned long h, unsigned long data) +{ + __raw_writew(set_field(0, data, h), addr); +} + +static void write_32(unsigned long addr, unsigned long h, unsigned long data) +{ + __raw_writel(set_field(0, data, h), addr); +} + +static void modify_8(unsigned long addr, unsigned long h, unsigned long data) +{ + unsigned long flags; + local_irq_save(flags); + __raw_writeb(set_field(__raw_readb(addr), data, h), addr); + local_irq_restore(flags); +} + +static void modify_16(unsigned long addr, unsigned long h, unsigned long data) +{ + unsigned long flags; + local_irq_save(flags); + __raw_writew(set_field(__raw_readw(addr), data, h), addr); + local_irq_restore(flags); +} + +static void modify_32(unsigned long addr, unsigned long h, unsigned long data) +{ + unsigned long flags; + local_irq_save(flags); + __raw_writel(set_field(__raw_readl(addr), data, h), addr); + local_irq_restore(flags); +} + +enum { REG_FN_ERR = 0, REG_FN_WRITE_BASE = 1, REG_FN_MODIFY_BASE = 5 }; + +static void (*intc_reg_fns[])(unsigned long addr, + unsigned long h, + unsigned long data) = { + [REG_FN_WRITE_BASE + 0] = write_8, + [REG_FN_WRITE_BASE + 1] = write_16, + [REG_FN_WRITE_BASE + 3] = write_32, + [REG_FN_MODIFY_BASE + 0] = modify_8, + [REG_FN_MODIFY_BASE + 1] = modify_16, + [REG_FN_MODIFY_BASE + 3] = modify_32, +}; + +enum { MODE_ENABLE_REG = 0, /* Bit(s) set -> interrupt enabled */ + MODE_MASK_REG, /* Bit(s) set -> interrupt disabled */ + MODE_DUAL_REG, /* Two registers, set bit to enable / disable */ + MODE_PRIO_REG, /* Priority value written to enable interrupt */ + MODE_PCLR_REG, /* Above plus all bits set to disable interrupt */ +}; + +static void intc_mode_field(unsigned long addr, + unsigned long handle, + void (*fn)(unsigned long, + unsigned long, + unsigned long), + unsigned int irq) +{ + fn(addr, handle, ((1 << _INTC_WIDTH(handle)) - 1)); +} + +static void intc_mode_zero(unsigned long addr, + unsigned long handle, + void (*fn)(unsigned long, + unsigned long, + unsigned long), + unsigned int irq) +{ + fn(addr, handle, 0); +} + +static void intc_mode_prio(unsigned long addr, + unsigned long handle, + void (*fn)(unsigned long, + unsigned long, + unsigned long), + unsigned int irq) +{ + fn(addr, handle, intc_prio_level[irq]); +} + +static void (*intc_enable_fns[])(unsigned long addr, + unsigned long handle, + void (*fn)(unsigned long, + unsigned long, + unsigned long), + unsigned int irq) = { + [MODE_ENABLE_REG] = intc_mode_field, + [MODE_MASK_REG] = intc_mode_zero, + [MODE_DUAL_REG] = intc_mode_field, + [MODE_PRIO_REG] = intc_mode_prio, + [MODE_PCLR_REG] = intc_mode_prio, +}; + +static void (*intc_disable_fns[])(unsigned long addr, + unsigned long handle, + void (*fn)(unsigned long, + unsigned long, + unsigned long), + unsigned int irq) = { + [MODE_ENABLE_REG] = intc_mode_zero, + [MODE_MASK_REG] = intc_mode_field, + [MODE_DUAL_REG] = intc_mode_field, + [MODE_PRIO_REG] = intc_mode_zero, + [MODE_PCLR_REG] = intc_mode_field, +}; + +static inline void _intc_enable(unsigned int irq, unsigned long handle) +{ + struct intc_desc_int *d = get_intc_desc(irq); + unsigned long addr; + unsigned int cpu; + + for (cpu = 0; cpu < SMP_NR(d, _INTC_ADDR_E(handle)); cpu++) { + addr = INTC_REG(d, _INTC_ADDR_E(handle), cpu); + intc_enable_fns[_INTC_MODE(handle)](addr, handle, intc_reg_fns\ + [_INTC_FN(handle)], irq); + } +} + +static void intc_enable(unsigned int irq) +{ + _intc_enable(irq, (unsigned long)get_irq_chip_data(irq)); +} + +static void intc_disable(unsigned int irq) +{ + struct intc_desc_int *d = get_intc_desc(irq); + unsigned long handle = (unsigned long) get_irq_chip_data(irq); + unsigned long addr; + unsigned int cpu; + + for (cpu = 0; cpu < SMP_NR(d, _INTC_ADDR_D(handle)); cpu++) { + addr = INTC_REG(d, _INTC_ADDR_D(handle), cpu); + intc_disable_fns[_INTC_MODE(handle)](addr, handle,intc_reg_fns\ + [_INTC_FN(handle)], irq); + } +} + +#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) +static void intc_mask_ack(unsigned int irq) +{ + struct intc_desc_int *d = get_intc_desc(irq); + unsigned long handle = ack_handle[irq]; + unsigned long addr; + + intc_disable(irq); + + /* read register and write zero only to the assocaited bit */ + + if (handle) { + addr = INTC_REG(d, _INTC_ADDR_D(handle), 0); + switch (_INTC_FN(handle)) { + case REG_FN_MODIFY_BASE + 0: /* 8bit */ + __raw_readb(addr); + __raw_writeb(0xff ^ set_field(0, 1, handle), addr); + break; + case REG_FN_MODIFY_BASE + 1: /* 16bit */ + __raw_readw(addr); + __raw_writew(0xffff ^ set_field(0, 1, handle), addr); + break; + case REG_FN_MODIFY_BASE + 3: /* 32bit */ + __raw_readl(addr); + __raw_writel(0xffffffff ^ set_field(0, 1, handle), addr); + break; + default: + BUG(); + break; + } + } +} +#endif + +static struct intc_handle_int *intc_find_irq(struct intc_handle_int *hp, + unsigned int nr_hp, + unsigned int irq) +{ + int i; + + /* this doesn't scale well, but... + * + * this function should only be used for cerain uncommon + * operations such as intc_set_priority() and intc_set_sense() + * and in those rare cases performance doesn't matter that much. + * keeping the memory footprint low is more important. + * + * one rather simple way to speed this up and still keep the + * memory footprint down is to make sure the array is sorted + * and then perform a bisect to lookup the irq. + */ + + for (i = 0; i < nr_hp; i++) { + if ((hp + i)->irq != irq) + continue; + + return hp + i; + } + + return NULL; +} + +int intc_set_priority(unsigned int irq, unsigned int prio) +{ + struct intc_desc_int *d = get_intc_desc(irq); + struct intc_handle_int *ihp; + + if (!intc_prio_level[irq] || prio <= 1) + return -EINVAL; + + ihp = intc_find_irq(d->prio, d->nr_prio, irq); + if (ihp) { + if (prio >= (1 << _INTC_WIDTH(ihp->handle))) + return -EINVAL; + + intc_prio_level[irq] = prio; + + /* + * only set secondary masking method directly + * primary masking method is using intc_prio_level[irq] + * priority level will be set during next enable() + */ + + if (_INTC_FN(ihp->handle) != REG_FN_ERR) + _intc_enable(irq, ihp->handle); + } + return 0; +} + +#define VALID(x) (x | 0x80) + +static unsigned char intc_irq_sense_table[IRQ_TYPE_SENSE_MASK + 1] = { + [IRQ_TYPE_EDGE_FALLING] = VALID(0), + [IRQ_TYPE_EDGE_RISING] = VALID(1), + [IRQ_TYPE_LEVEL_LOW] = VALID(2), + /* SH7706, SH7707 and SH7709 do not support high level triggered */ +#if !defined(CONFIG_CPU_SUBTYPE_SH7706) && \ + !defined(CONFIG_CPU_SUBTYPE_SH7707) && \ + !defined(CONFIG_CPU_SUBTYPE_SH7709) + [IRQ_TYPE_LEVEL_HIGH] = VALID(3), +#endif +}; + +static int intc_set_sense(unsigned int irq, unsigned int type) +{ + struct intc_desc_int *d = get_intc_desc(irq); + unsigned char value = intc_irq_sense_table[type & IRQ_TYPE_SENSE_MASK]; + struct intc_handle_int *ihp; + unsigned long addr; + + if (!value) + return -EINVAL; + + ihp = intc_find_irq(d->sense, d->nr_sense, irq); + if (ihp) { + addr = INTC_REG(d, _INTC_ADDR_E(ihp->handle), 0); + intc_reg_fns[_INTC_FN(ihp->handle)](addr, ihp->handle, value); + } + return 0; +} + +static unsigned int __init intc_get_reg(struct intc_desc_int *d, + unsigned long address) +{ + unsigned int k; + + for (k = 0; k < d->nr_reg; k++) { + if (d->reg[k] == address) + return k; + } + + BUG(); + return 0; +} + +static intc_enum __init intc_grp_id(struct intc_desc *desc, + intc_enum enum_id) +{ + struct intc_group *g = desc->groups; + unsigned int i, j; + + for (i = 0; g && enum_id && i < desc->nr_groups; i++) { + g = desc->groups + i; + + for (j = 0; g->enum_ids[j]; j++) { + if (g->enum_ids[j] != enum_id) + continue; + + return g->enum_id; + } + } + + return 0; +} + +static unsigned int __init intc_mask_data(struct intc_desc *desc, + struct intc_desc_int *d, + intc_enum enum_id, int do_grps) +{ + struct intc_mask_reg *mr = desc->mask_regs; + unsigned int i, j, fn, mode; + unsigned long reg_e, reg_d; + + for (i = 0; mr && enum_id && i < desc->nr_mask_regs; i++) { + mr = desc->mask_regs + i; + + for (j = 0; j < ARRAY_SIZE(mr->enum_ids); j++) { + if (mr->enum_ids[j] != enum_id) + continue; + + if (mr->set_reg && mr->clr_reg) { + fn = REG_FN_WRITE_BASE; + mode = MODE_DUAL_REG; + reg_e = mr->clr_reg; + reg_d = mr->set_reg; + } else { + fn = REG_FN_MODIFY_BASE; + if (mr->set_reg) { + mode = MODE_ENABLE_REG; + reg_e = mr->set_reg; + reg_d = mr->set_reg; + } else { + mode = MODE_MASK_REG; + reg_e = mr->clr_reg; + reg_d = mr->clr_reg; + } + } + + fn += (mr->reg_width >> 3) - 1; + return _INTC_MK(fn, mode, + intc_get_reg(d, reg_e), + intc_get_reg(d, reg_d), + 1, + (mr->reg_width - 1) - j); + } + } + + if (do_grps) + return intc_mask_data(desc, d, intc_grp_id(desc, enum_id), 0); + + return 0; +} + +static unsigned int __init intc_prio_data(struct intc_desc *desc, + struct intc_desc_int *d, + intc_enum enum_id, int do_grps) +{ + struct intc_prio_reg *pr = desc->prio_regs; + unsigned int i, j, fn, mode, bit; + unsigned long reg_e, reg_d; + + for (i = 0; pr && enum_id && i < desc->nr_prio_regs; i++) { + pr = desc->prio_regs + i; + + for (j = 0; j < ARRAY_SIZE(pr->enum_ids); j++) { + if (pr->enum_ids[j] != enum_id) + continue; + + if (pr->set_reg && pr->clr_reg) { + fn = REG_FN_WRITE_BASE; + mode = MODE_PCLR_REG; + reg_e = pr->set_reg; + reg_d = pr->clr_reg; + } else { + fn = REG_FN_MODIFY_BASE; + mode = MODE_PRIO_REG; + if (!pr->set_reg) + BUG(); + reg_e = pr->set_reg; + reg_d = pr->set_reg; + } + + fn += (pr->reg_width >> 3) - 1; + + BUG_ON((j + 1) * pr->field_width > pr->reg_width); + + bit = pr->reg_width - ((j + 1) * pr->field_width); + + return _INTC_MK(fn, mode, + intc_get_reg(d, reg_e), + intc_get_reg(d, reg_d), + pr->field_width, bit); + } + } + + if (do_grps) + return intc_prio_data(desc, d, intc_grp_id(desc, enum_id), 0); + + return 0; +} + +#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) +static unsigned int __init intc_ack_data(struct intc_desc *desc, + struct intc_desc_int *d, + intc_enum enum_id) +{ + struct intc_mask_reg *mr = desc->ack_regs; + unsigned int i, j, fn, mode; + unsigned long reg_e, reg_d; + + for (i = 0; mr && enum_id && i < desc->nr_ack_regs; i++) { + mr = desc->ack_regs + i; + + for (j = 0; j < ARRAY_SIZE(mr->enum_ids); j++) { + if (mr->enum_ids[j] != enum_id) + continue; + + fn = REG_FN_MODIFY_BASE; + mode = MODE_ENABLE_REG; + reg_e = mr->set_reg; + reg_d = mr->set_reg; + + fn += (mr->reg_width >> 3) - 1; + return _INTC_MK(fn, mode, + intc_get_reg(d, reg_e), + intc_get_reg(d, reg_d), + 1, + (mr->reg_width - 1) - j); + } + } + + return 0; +} +#endif + +static unsigned int __init intc_sense_data(struct intc_desc *desc, + struct intc_desc_int *d, + intc_enum enum_id) +{ + struct intc_sense_reg *sr = desc->sense_regs; + unsigned int i, j, fn, bit; + + for (i = 0; sr && enum_id && i < desc->nr_sense_regs; i++) { + sr = desc->sense_regs + i; + + for (j = 0; j < ARRAY_SIZE(sr->enum_ids); j++) { + if (sr->enum_ids[j] != enum_id) + continue; + + fn = REG_FN_MODIFY_BASE; + fn += (sr->reg_width >> 3) - 1; + + BUG_ON((j + 1) * sr->field_width > sr->reg_width); + + bit = sr->reg_width - ((j + 1) * sr->field_width); + + return _INTC_MK(fn, 0, intc_get_reg(d, sr->reg), + 0, sr->field_width, bit); + } + } + + return 0; +} + +static void __init intc_register_irq(struct intc_desc *desc, + struct intc_desc_int *d, + intc_enum enum_id, + unsigned int irq) +{ + struct intc_handle_int *hp; + unsigned int data[2], primary; + + /* Prefer single interrupt source bitmap over other combinations: + * 1. bitmap, single interrupt source + * 2. priority, single interrupt source + * 3. bitmap, multiple interrupt sources (groups) + * 4. priority, multiple interrupt sources (groups) + */ + + data[0] = intc_mask_data(desc, d, enum_id, 0); + data[1] = intc_prio_data(desc, d, enum_id, 0); + + primary = 0; + if (!data[0] && data[1]) + primary = 1; + + data[0] = data[0] ? data[0] : intc_mask_data(desc, d, enum_id, 1); + data[1] = data[1] ? data[1] : intc_prio_data(desc, d, enum_id, 1); + + if (!data[primary]) + primary ^= 1; + + BUG_ON(!data[primary]); /* must have primary masking method */ + + disable_irq_nosync(irq); + set_irq_chip_and_handler_name(irq, &d->chip, + handle_level_irq, "level"); + set_irq_chip_data(irq, (void *)data[primary]); + + /* set priority level + * - this needs to be at least 2 for 5-bit priorities on 7780 + */ + intc_prio_level[irq] = 2; + + /* enable secondary masking method if present */ + if (data[!primary]) + _intc_enable(irq, data[!primary]); + + /* add irq to d->prio list if priority is available */ + if (data[1]) { + hp = d->prio + d->nr_prio; + hp->irq = irq; + hp->handle = data[1]; + + if (primary) { + /* + * only secondary priority should access registers, so + * set _INTC_FN(h) = REG_FN_ERR for intc_set_priority() + */ + + hp->handle &= ~_INTC_MK(0x0f, 0, 0, 0, 0, 0); + hp->handle |= _INTC_MK(REG_FN_ERR, 0, 0, 0, 0, 0); + } + d->nr_prio++; + } + + /* add irq to d->sense list if sense is available */ + data[0] = intc_sense_data(desc, d, enum_id); + if (data[0]) { + (d->sense + d->nr_sense)->irq = irq; + (d->sense + d->nr_sense)->handle = data[0]; + d->nr_sense++; + } + + /* irq should be disabled by default */ + d->chip.mask(irq); + +#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) + if (desc->ack_regs) + ack_handle[irq] = intc_ack_data(desc, d, enum_id); +#endif +} + +static unsigned int __init save_reg(struct intc_desc_int *d, + unsigned int cnt, + unsigned long value, + unsigned int smp) +{ + if (value) { + d->reg[cnt] = value; +#ifdef CONFIG_SMP + d->smp[cnt] = smp; +#endif + return 1; + } + + return 0; +} + + +void __init register_intc_controller(struct intc_desc *desc) +{ + unsigned int i, k, smp; + struct intc_desc_int *d; + + d = alloc_bootmem(sizeof(*d)); + + d->nr_reg = desc->mask_regs ? desc->nr_mask_regs * 2 : 0; + d->nr_reg += desc->prio_regs ? desc->nr_prio_regs * 2 : 0; + d->nr_reg += desc->sense_regs ? desc->nr_sense_regs : 0; + +#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) + d->nr_reg += desc->ack_regs ? desc->nr_ack_regs : 0; +#endif + d->reg = alloc_bootmem(d->nr_reg * sizeof(*d->reg)); +#ifdef CONFIG_SMP + d->smp = alloc_bootmem(d->nr_reg * sizeof(*d->smp)); +#endif + k = 0; + + if (desc->mask_regs) { + for (i = 0; i < desc->nr_mask_regs; i++) { + smp = IS_SMP(desc->mask_regs[i]); + k += save_reg(d, k, desc->mask_regs[i].set_reg, smp); + k += save_reg(d, k, desc->mask_regs[i].clr_reg, smp); + } + } + + if (desc->prio_regs) { + d->prio = alloc_bootmem(desc->nr_vectors * sizeof(*d->prio)); + + for (i = 0; i < desc->nr_prio_regs; i++) { + smp = IS_SMP(desc->prio_regs[i]); + k += save_reg(d, k, desc->prio_regs[i].set_reg, smp); + k += save_reg(d, k, desc->prio_regs[i].clr_reg, smp); + } + } + + if (desc->sense_regs) { + d->sense = alloc_bootmem(desc->nr_vectors * sizeof(*d->sense)); + + for (i = 0; i < desc->nr_sense_regs; i++) { + k += save_reg(d, k, desc->sense_regs[i].reg, 0); + } + } + + d->chip.name = desc->name; + d->chip.mask = intc_disable; + d->chip.unmask = intc_enable; + d->chip.mask_ack = intc_disable; + d->chip.set_type = intc_set_sense; + +#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) + if (desc->ack_regs) { + for (i = 0; i < desc->nr_ack_regs; i++) + k += save_reg(d, k, desc->ack_regs[i].set_reg, 0); + + d->chip.mask_ack = intc_mask_ack; + } +#endif + + BUG_ON(k > 256); /* _INTC_ADDR_E() and _INTC_ADDR_D() are 8 bits */ + + for (i = 0; i < desc->nr_vectors; i++) { + struct intc_vect *vect = desc->vectors + i; + + intc_register_irq(desc, d, vect->enum_id, evt2irq(vect->vect)); + } +} diff --git a/include/linux/sh_intc.h b/include/linux/sh_intc.h new file mode 100644 index 0000000..68e212f --- /dev/null +++ b/include/linux/sh_intc.h @@ -0,0 +1,91 @@ +#ifndef __SH_INTC_H +#define __SH_INTC_H + +typedef unsigned char intc_enum; + +struct intc_vect { + intc_enum enum_id; + unsigned short vect; +}; + +#define INTC_VECT(enum_id, vect) { enum_id, vect } +#define INTC_IRQ(enum_id, irq) INTC_VECT(enum_id, irq2evt(irq)) + +struct intc_group { + intc_enum enum_id; + intc_enum enum_ids[32]; +}; + +#define INTC_GROUP(enum_id, ids...) { enum_id, { ids } } + +struct intc_mask_reg { + unsigned long set_reg, clr_reg, reg_width; + intc_enum enum_ids[32]; +#ifdef CONFIG_SMP + unsigned long smp; +#endif +}; + +struct intc_prio_reg { + unsigned long set_reg, clr_reg, reg_width, field_width; + intc_enum enum_ids[16]; +#ifdef CONFIG_SMP + unsigned long smp; +#endif +}; + +struct intc_sense_reg { + unsigned long reg, reg_width, field_width; + intc_enum enum_ids[16]; +}; + +#ifdef CONFIG_SMP +#define INTC_SMP(stride, nr) .smp = (stride) | ((nr) << 8) +#else +#define INTC_SMP(stride, nr) +#endif + +struct intc_desc { + struct intc_vect *vectors; + unsigned int nr_vectors; + struct intc_group *groups; + unsigned int nr_groups; + struct intc_mask_reg *mask_regs; + unsigned int nr_mask_regs; + struct intc_prio_reg *prio_regs; + unsigned int nr_prio_regs; + struct intc_sense_reg *sense_regs; + unsigned int nr_sense_regs; + char *name; +#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) + struct intc_mask_reg *ack_regs; + unsigned int nr_ack_regs; +#endif +}; + +#define _INTC_ARRAY(a) a, sizeof(a)/sizeof(*a) +#define DECLARE_INTC_DESC(symbol, chipname, vectors, groups, \ + mask_regs, prio_regs, sense_regs) \ +struct intc_desc symbol __initdata = { \ + _INTC_ARRAY(vectors), _INTC_ARRAY(groups), \ + _INTC_ARRAY(mask_regs), _INTC_ARRAY(prio_regs), \ + _INTC_ARRAY(sense_regs), \ + chipname, \ +} + +#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A) +#define DECLARE_INTC_DESC_ACK(symbol, chipname, vectors, groups, \ + mask_regs, prio_regs, sense_regs, ack_regs) \ +struct intc_desc symbol __initdata = { \ + _INTC_ARRAY(vectors), _INTC_ARRAY(groups), \ + _INTC_ARRAY(mask_regs), _INTC_ARRAY(prio_regs), \ + _INTC_ARRAY(sense_regs), \ + chipname, \ + _INTC_ARRAY(ack_regs), \ +} +#endif + +void __init register_intc_controller(struct intc_desc *desc); +int intc_set_priority(unsigned int irq, unsigned int prio); + +#endif /* __SH_INTC_H */ -- cgit v0.10.2 From 225c9a8d1da274bf23efec43ec28b1c9e45e12f8 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 1 Oct 2008 16:24:32 +0900 Subject: video: sh_mobile_lcdcfb: Support HAVE_CLK=n configurations. This provides a workaround for users of sh_mobile_lcdcfb that don't define HAVE_CLK and have otherwise sane clock initialization. At the same time, move the sh_mobile_lcdc.h header to include/video/. Signed-off-by: Paul Mundt diff --git a/arch/sh/boards/board-ap325rxa.c b/arch/sh/boards/board-ap325rxa.c index 00e632f..7ae8dcd 100644 --- a/arch/sh/boards/board-ap325rxa.c +++ b/arch/sh/boards/board-ap325rxa.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include