diff options
320 files changed, 6530 insertions, 3656 deletions
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index 6e25340..accfe2f 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -298,3 +298,15 @@ over a rather long period of time, but improvements are always welcome! Note that, rcu_assign_pointer() and rcu_dereference() relate to SRCU just as they do to other forms of RCU. + +15. The whole point of call_rcu(), synchronize_rcu(), and friends + is to wait until all pre-existing readers have finished before + carrying out some otherwise-destructive operation. It is + therefore critically important to -first- remove any path + that readers can follow that could be affected by the + destructive operation, and -only- -then- invoke call_rcu(), + synchronize_rcu(), or friends. + + Because these primitives only wait for pre-existing readers, + it is the caller's responsibility to guarantee safety to + any subsequent readers. diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 5ddbe35..20d3b94 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -335,3 +335,12 @@ Why: In 2.6.18 the Secmark concept was introduced to replace the "compat_net" Secmark, it is time to deprecate the older mechanism and start the process of removing the old code. Who: Paul Moore <paul.moore@hp.com> +--------------------------- + +What: sysfs ui for changing p4-clockmod parameters +When: September 2009 +Why: See commits 129f8ae9b1b5be94517da76009ea956e89104ce8 and + e088e4c9cdb618675874becb91b2fd581ee707e6. + Removal is subject to fixing any remaining bugs in ACPI which may + cause the thermal throttling not to happen at the right time. +Who: Dave Jones <davej@redhat.com>, Matthew Garrett <mjg@redhat.com> diff --git a/Documentation/filesystems/squashfs.txt b/Documentation/filesystems/squashfs.txt index 3e79e4a..b324c03 100644 --- a/Documentation/filesystems/squashfs.txt +++ b/Documentation/filesystems/squashfs.txt @@ -22,7 +22,7 @@ Squashfs filesystem features versus Cramfs: Squashfs Cramfs -Max filesystem size: 2^64 16 MiB +Max filesystem size: 2^64 256 MiB Max file size: ~ 2 TiB 16 MiB Max files: unlimited unlimited Max directories: unlimited unlimited diff --git a/Documentation/networking/ipv6.txt b/Documentation/networking/ipv6.txt new file mode 100644 index 0000000..268e5c1 --- /dev/null +++ b/Documentation/networking/ipv6.txt @@ -0,0 +1,35 @@ + +Options for the ipv6 module are supplied as parameters at load time. + +Module options may be given as command line arguments to the insmod +or modprobe command, but are usually specified in either the +/etc/modules.conf or /etc/modprobe.conf configuration file, or in a +distro-specific configuration file. + +The available ipv6 module parameters are listed below. If a parameter +is not specified the default value is used. + +The parameters are as follows: + +disable + + Specifies whether to load the IPv6 module, but disable all + its functionality. This might be used when another module + has a dependency on the IPv6 module being loaded, but no + IPv6 addresses or operations are desired. + + The possible values and their effects are: + + 0 + IPv6 is enabled. + + This is the default value. + + 1 + IPv6 is disabled. + + No IPv6 addresses will be added to interfaces, and + it will not be possible to open an IPv6 socket. + + A reboot is required to enable IPv6. + diff --git a/Documentation/x86/earlyprintk.txt b/Documentation/x86/earlyprintk.txt new file mode 100644 index 0000000..607b1a0 --- /dev/null +++ b/Documentation/x86/earlyprintk.txt @@ -0,0 +1,101 @@ + +Mini-HOWTO for using the earlyprintk=dbgp boot option with a +USB2 Debug port key and a debug cable, on x86 systems. + +You need two computers, the 'USB debug key' special gadget and +and two USB cables, connected like this: + + [host/target] <-------> [USB debug key] <-------> [client/console] + +1. There are three specific hardware requirements: + + a.) Host/target system needs to have USB debug port capability. + + You can check this capability by looking at a 'Debug port' bit in + the lspci -vvv output: + + # lspci -vvv + ... + 00:1d.7 USB Controller: Intel Corporation 82801H (ICH8 Family) USB2 EHCI Controller #1 (rev 03) (prog-if 20 [EHCI]) + Subsystem: Lenovo ThinkPad T61 + Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B- DisINTx- + Status: Cap+ 66MHz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx- + Latency: 0 + Interrupt: pin D routed to IRQ 19 + Region 0: Memory at fe227000 (32-bit, non-prefetchable) [size=1K] + Capabilities: [50] Power Management version 2 + Flags: PMEClk- DSI- D1- D2- AuxCurrent=375mA PME(D0+,D1-,D2-,D3hot+,D3cold+) + Status: D0 PME-Enable- DSel=0 DScale=0 PME+ + Capabilities: [58] Debug port: BAR=1 offset=00a0 + ^^^^^^^^^^^ <==================== [ HERE ] + Kernel driver in use: ehci_hcd + Kernel modules: ehci-hcd + ... + +( If your system does not list a debug port capability then you probably + wont be able to use the USB debug key. ) + + b.) You also need a Netchip USB debug cable/key: + + http://www.plxtech.com/products/NET2000/NET20DC/default.asp + + This is a small blue plastic connector with two USB connections, + it draws power from its USB connections. + + c.) Thirdly, you need a second client/console system with a regular USB port. + +2. Software requirements: + + a.) On the host/target system: + + You need to enable the following kernel config option: + + CONFIG_EARLY_PRINTK_DBGP=y + + And you need to add the boot command line: "earlyprintk=dbgp". + (If you are using Grub, append it to the 'kernel' line in + /etc/grub.conf) + + NOTE: normally earlyprintk console gets turned off once the + regular console is alive - use "earlyprintk=dbgp,keep" to keep + this channel open beyond early bootup. This can be useful for + debugging crashes under Xorg, etc. + + b.) On the client/console system: + + You should enable the following kernel config option: + + CONFIG_USB_SERIAL_DEBUG=y + + On the next bootup with the modified kernel you should + get a /dev/ttyUSBx device(s). + + Now this channel of kernel messages is ready to be used: start + your favorite terminal emulator (minicom, etc.) and set + it up to use /dev/ttyUSB0 - or use a raw 'cat /dev/ttyUSBx' to + see the raw output. + + c.) On Nvidia Southbridge based systems: the kernel will try to probe + and find out which port has debug device connected. + +3. Testing that it works fine: + + You can test the output by using earlyprintk=dbgp,keep and provoking + kernel messages on the host/target system. You can provoke a harmless + kernel message by for example doing: + + echo h > /proc/sysrq-trigger + + On the host/target system you should see this help line in "dmesg" output: + + SysRq : HELP : loglevel(0-9) reBoot Crashdump terminate-all-tasks(E) memory-full-oom-kill(F) kill-all-tasks(I) saK show-backtrace-all-active-cpus(L) show-memory-usage(M) nice-all-RT-tasks(N) powerOff show-registers(P) show-all-timers(Q) unRaw Sync show-task-states(T) Unmount show-blocked-tasks(W) dump-ftrace-buffer(Z) + + On the client/console system do: + + cat /dev/ttyUSB0 + + And you should see the help line above displayed shortly after you've + provoked it on the host system. + +If it does not work then please ask about it on the linux-kernel@vger.kernel.org +mailing list or contact the x86 maintainers. @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 29 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Erotic Pickled Herring # *DOCUMENTATION* diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 5d7a16e..af71d38 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -189,9 +189,21 @@ callback_init(void * kernel_end) if (alpha_using_srm) { static struct vm_struct console_remap_vm; - unsigned long vaddr = VMALLOC_START; + unsigned long nr_pages = 0; + unsigned long vaddr; unsigned long i, j; + /* calculate needed size */ + for (i = 0; i < crb->map_entries; ++i) + nr_pages += crb->map[i].count; + + /* register the vm area */ + console_remap_vm.flags = VM_ALLOC; + console_remap_vm.size = nr_pages << PAGE_SHIFT; + vm_area_register_early(&console_remap_vm, PAGE_SIZE); + + vaddr = (unsigned long)console_remap_vm.addr; + /* Set up the third level PTEs and update the virtual addresses of the CRB entries. */ for (i = 0; i < crb->map_entries; ++i) { @@ -213,12 +225,6 @@ callback_init(void * kernel_end) vaddr += PAGE_SIZE; } } - - /* Let vmalloc know that we've allocated some space. */ - console_remap_vm.flags = VM_ALLOC; - console_remap_vm.addr = (void *) VMALLOC_START; - console_remap_vm.size = vaddr - VMALLOC_START; - vmlist = &console_remap_vm; } callback_init_done = 1; diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 7049815..68d6494 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -233,12 +233,13 @@ static void __init cacheid_init(void) unsigned int cachetype = read_cpuid_cachetype(); unsigned int arch = cpu_architecture(); - if (arch >= CPU_ARCH_ARMv7) { - cacheid = CACHEID_VIPT_NONALIASING; - if ((cachetype & (3 << 14)) == 1 << 14) - cacheid |= CACHEID_ASID_TAGGED; - } else if (arch >= CPU_ARCH_ARMv6) { - if (cachetype & (1 << 23)) + if (arch >= CPU_ARCH_ARMv6) { + if ((cachetype & (7 << 29)) == 4 << 29) { + /* ARMv7 register format */ + cacheid = CACHEID_VIPT_NONALIASING; + if ((cachetype & (3 << 14)) == 1 << 14) + cacheid |= CACHEID_ASID_TAGGED; + } else if (cachetype & (1 << 23)) cacheid = CACHEID_VIPT_ALIASING; else cacheid = CACHEID_VIPT_NONALIASING; diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c index 134af97..b7f2332 100644 --- a/arch/arm/mach-at91/at91sam9263_devices.c +++ b/arch/arm/mach-at91/at91sam9263_devices.c @@ -347,6 +347,111 @@ void __init at91_add_device_mmc(short mmc_id, struct at91_mmc_data *data) void __init at91_add_device_mmc(short mmc_id, struct at91_mmc_data *data) {} #endif +/* -------------------------------------------------------------------- + * Compact Flash (PCMCIA or IDE) + * -------------------------------------------------------------------- */ + +#if defined(CONFIG_AT91_CF) || defined(CONFIG_AT91_CF_MODULE) || \ + defined(CONFIG_BLK_DEV_IDE_AT91) || defined(CONFIG_BLK_DEV_IDE_AT91_MODULE) + +static struct at91_cf_data cf0_data; + +static struct resource cf0_resources[] = { + [0] = { + .start = AT91_CHIPSELECT_4, + .end = AT91_CHIPSELECT_4 + SZ_256M - 1, + .flags = IORESOURCE_MEM | IORESOURCE_MEM_8AND16BIT, + } +}; + +static struct platform_device cf0_device = { + .id = 0, + .dev = { + .platform_data = &cf0_data, + }, + .resource = cf0_resources, + .num_resources = ARRAY_SIZE(cf0_resources), +}; + +static struct at91_cf_data cf1_data; + +static struct resource cf1_resources[] = { + [0] = { + .start = AT91_CHIPSELECT_5, + .end = AT91_CHIPSELECT_5 + SZ_256M - 1, + .flags = IORESOURCE_MEM | IORESOURCE_MEM_8AND16BIT, + } +}; + +static struct platform_device cf1_device = { + .id = 1, + .dev = { + .platform_data = &cf1_data, + }, + .resource = cf1_resources, + .num_resources = ARRAY_SIZE(cf1_resources), +}; + +void __init at91_add_device_cf(struct at91_cf_data *data) +{ + unsigned long ebi0_csa; + struct platform_device *pdev; + + if (!data) + return; + + /* + * assign CS4 or CS5 to SMC with Compact Flash logic support, + * we assume SMC timings are configured by board code, + * except True IDE where timings are controlled by driver + */ + ebi0_csa = at91_sys_read(AT91_MATRIX_EBI0CSA); + switch (data->chipselect) { + case 4: + at91_set_A_periph(AT91_PIN_PD6, 0); /* EBI0_NCS4/CFCS0 */ + ebi0_csa |= AT91_MATRIX_EBI0_CS4A_SMC_CF1; + cf0_data = *data; + pdev = &cf0_device; + break; + case 5: + at91_set_A_periph(AT91_PIN_PD7, 0); /* EBI0_NCS5/CFCS1 */ + ebi0_csa |= AT91_MATRIX_EBI0_CS5A_SMC_CF2; + cf1_data = *data; + pdev = &cf1_device; + break; + default: + printk(KERN_ERR "AT91 CF: bad chip-select requested (%u)\n", + data->chipselect); + return; + } + at91_sys_write(AT91_MATRIX_EBI0CSA, ebi0_csa); + + if (data->det_pin) { + at91_set_gpio_input(data->det_pin, 1); + at91_set_deglitch(data->det_pin, 1); + } + + if (data->irq_pin) { + at91_set_gpio_input(data->irq_pin, 1); + at91_set_deglitch(data->irq_pin, 1); + } + + if (data->vcc_pin) + /* initially off */ + at91_set_gpio_output(data->vcc_pin, 0); + + /* enable EBI controlled pins */ + at91_set_A_periph(AT91_PIN_PD5, 1); /* NWAIT */ + at91_set_A_periph(AT91_PIN_PD8, 0); /* CFCE1 */ + at91_set_A_periph(AT91_PIN_PD9, 0); /* CFCE2 */ + at91_set_A_periph(AT91_PIN_PD14, 0); /* CFNRW */ + + pdev->name = (data->flags & AT91_CF_TRUE_IDE) ? "at91_ide" : "at91_cf"; + platform_device_register(pdev); +} +#else +void __init at91_add_device_cf(struct at91_cf_data *data) {} +#endif /* -------------------------------------------------------------------- * NAND / SmartMedia diff --git a/arch/arm/mach-at91/include/mach/board.h b/arch/arm/mach-at91/include/mach/board.h index 0b3ae21..793fe7b 100644 --- a/arch/arm/mach-at91/include/mach/board.h +++ b/arch/arm/mach-at91/include/mach/board.h @@ -56,6 +56,9 @@ struct at91_cf_data { u8 vcc_pin; /* power switching */ u8 rst_pin; /* card reset */ u8 chipselect; /* EBI Chip Select number */ + u8 flags; +#define AT91_CF_TRUE_IDE 0x01 +#define AT91_IDE_SWAP_A0_A2 0x02 }; extern void __init at91_add_device_cf(struct at91_cf_data *data); diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 9bb4f04..7ac812d 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -332,7 +332,6 @@ static int at91_pm_enter(suspend_state_t state) at91_sys_read(AT91_AIC_IPR) & at91_sys_read(AT91_AIC_IMR)); error: - sdram_selfrefresh_disable(); target_state = PM_SUSPEND_ON; at91_irq_resume(); at91_gpio_resume(); diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c index f6a1345..6031e17 100644 --- a/arch/arm/mach-omap2/board-ldp.c +++ b/arch/arm/mach-omap2/board-ldp.c @@ -81,7 +81,7 @@ static inline void __init ldp_init_smc911x(void) } ldp_smc911x_resources[0].start = cs_mem_base + 0x0; - ldp_smc911x_resources[0].end = cs_mem_base + 0xf; + ldp_smc911x_resources[0].end = cs_mem_base + 0xff; udelay(100); eth_gpio = LDP_SMC911X_GPIO; diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index 8a7f65b..94077fb 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -23,7 +23,8 @@ ENTRY(v6_early_abort) #ifdef CONFIG_CPU_32v6K clrex #else - strex r0, r1, [sp] @ Clear the exclusive monitor + sub r1, sp, #4 @ Get unused stack location + strex r0, r1, [r1] @ Clear the exclusive monitor #endif mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR diff --git a/arch/arm/plat-s3c64xx/irq-eint.c b/arch/arm/plat-s3c64xx/irq-eint.c index 1f7cc00..ebb305c 100644 --- a/arch/arm/plat-s3c64xx/irq-eint.c +++ b/arch/arm/plat-s3c64xx/irq-eint.c @@ -55,7 +55,7 @@ static void s3c_irq_eint_unmask(unsigned int irq) u32 mask; mask = __raw_readl(S3C64XX_EINT0MASK); - mask |= eint_irq_to_bit(irq); + mask &= ~eint_irq_to_bit(irq); __raw_writel(mask, S3C64XX_EINT0MASK); } diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig index b189680..05fe305 100644 --- a/arch/avr32/Kconfig +++ b/arch/avr32/Kconfig @@ -181,7 +181,7 @@ source "kernel/Kconfig.preempt" config QUICKLIST def_bool y -config HAVE_ARCH_BOOTMEM_NODE +config HAVE_ARCH_BOOTMEM def_bool n config ARCH_HAVE_MEMORY_PRESENT diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index 8f1f97d..0c1f86e 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -1129,6 +1129,7 @@ endchoice config PM_WAKEUP_BY_GPIO bool "Allow Wakeup from Standby by GPIO" + depends on PM && !BF54x config PM_WAKEUP_GPIO_NUMBER int "GPIO number" @@ -1168,6 +1169,12 @@ config PM_BFIN_WAKE_GP default n help Enable General-Purpose Wake-Up (Voltage Regulator Power-Up) + (all processors, except ADSP-BF549). This option sets + the general-purpose wake-up enable (GPWE) control bit to enable + wake-up upon detection of an active low signal on the /GPW (PH7) pin. + On ADSP-BF549 this option enables the the same functionality on the + /MRXON pin also PH7. + endmenu menu "CPU Frequency scaling" diff --git a/arch/blackfin/Kconfig.debug b/arch/blackfin/Kconfig.debug index 5f981d9..79e7e63 100644 --- a/arch/blackfin/Kconfig.debug +++ b/arch/blackfin/Kconfig.debug @@ -21,12 +21,6 @@ config DEBUG_STACK_USAGE config HAVE_ARCH_KGDB def_bool y -config KGDB_TESTCASE - tristate "KGDB: for test case in expect" - default n - help - This is a kgdb test case for automated testing. - config DEBUG_VERBOSE bool "Verbose fault messages" default y diff --git a/arch/blackfin/configs/BF518F-EZBRD_defconfig b/arch/blackfin/configs/BF518F-EZBRD_defconfig index 4fdb9e0..281f4b6 100644 --- a/arch/blackfin/configs/BF518F-EZBRD_defconfig +++ b/arch/blackfin/configs/BF518F-EZBRD_defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.28-rc2 -# Fri Jan 9 17:58:41 2009 +# Linux kernel version: 2.6.28 +# Fri Feb 20 10:01:44 2009 # # CONFIG_MMU is not set # CONFIG_FPU is not set @@ -133,10 +133,15 @@ CONFIG_BF518=y # CONFIG_BF538 is not set # CONFIG_BF539 is not set # CONFIG_BF542 is not set +# CONFIG_BF542M is not set # CONFIG_BF544 is not set +# CONFIG_BF544M is not set # CONFIG_BF547 is not set +# CONFIG_BF547M is not set # CONFIG_BF548 is not set +# CONFIG_BF548M is not set # CONFIG_BF549 is not set +# CONFIG_BF549M is not set # CONFIG_BF561 is not set CONFIG_BF_REV_MIN=0 CONFIG_BF_REV_MAX=2 @@ -426,7 +431,17 @@ CONFIG_DEFAULT_TCP_CONG="cubic" # CONFIG_TIPC is not set # CONFIG_ATM is not set # CONFIG_BRIDGE is not set -# CONFIG_NET_DSA is not set +CONFIG_NET_DSA=y +# CONFIG_NET_DSA_TAG_DSA is not set +# CONFIG_NET_DSA_TAG_EDSA is not set +# CONFIG_NET_DSA_TAG_TRAILER is not set +CONFIG_NET_DSA_TAG_STPID=y +# CONFIG_NET_DSA_MV88E6XXX is not set +# CONFIG_NET_DSA_MV88E6060 is not set +# CONFIG_NET_DSA_MV88E6XXX_NEED_PPU is not set +# CONFIG_NET_DSA_MV88E6131 is not set +# CONFIG_NET_DSA_MV88E6123_61_65 is not set +CONFIG_NET_DSA_KSZ8893M=y # CONFIG_VLAN_8021Q is not set # CONFIG_DECNET is not set # CONFIG_LLC2 is not set @@ -529,6 +544,8 @@ CONFIG_MTD_COMPLEX_MAPPINGS=y # # Self-contained MTD device drivers # +# CONFIG_MTD_DATAFLASH is not set +# CONFIG_MTD_M25P80 is not set # CONFIG_MTD_SLRAM is not set # CONFIG_MTD_PHRAM is not set # CONFIG_MTD_MTDRAM is not set @@ -561,7 +578,9 @@ CONFIG_BLK_DEV_RAM_SIZE=4096 # CONFIG_BLK_DEV_HD is not set CONFIG_MISC_DEVICES=y # CONFIG_EEPROM_93CX6 is not set +# CONFIG_ICS932S401 is not set # CONFIG_ENCLOSURE_SERVICES is not set +# CONFIG_C2PORT is not set CONFIG_HAVE_IDE=y # CONFIG_IDE is not set @@ -607,6 +626,7 @@ CONFIG_BFIN_RX_DESC_NUM=20 # CONFIG_SMC91X is not set # CONFIG_SMSC911X is not set # CONFIG_DM9000 is not set +# CONFIG_ENC28J60 is not set # CONFIG_IBM_NEW_EMAC_ZMII is not set # CONFIG_IBM_NEW_EMAC_RGMII is not set # CONFIG_IBM_NEW_EMAC_TAH is not set @@ -764,7 +784,23 @@ CONFIG_I2C_BLACKFIN_TWI_CLK_KHZ=100 # CONFIG_I2C_DEBUG_ALGO is not set # CONFIG_I2C_DEBUG_BUS is not set # CONFIG_I2C_DEBUG_CHIP is not set -# CONFIG_SPI is not set +CONFIG_SPI=y +# CONFIG_SPI_DEBUG is not set +CONFIG_SPI_MASTER=y + +# +# SPI Master Controller Drivers +# +CONFIG_SPI_BFIN=y +# CONFIG_SPI_BFIN_LOCK is not set +# CONFIG_SPI_BITBANG 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_ARCH_WANT_OPTIONAL_GPIOLIB=y # CONFIG_GPIOLIB is not set # CONFIG_W1 is not set @@ -788,8 +824,10 @@ CONFIG_BFIN_WDT=y # CONFIG_MFD_SM501 is not set # CONFIG_HTC_PASIC3 is not set # CONFIG_MFD_TMIO is not set +# CONFIG_PMIC_DA903X is not set # CONFIG_MFD_WM8400 is not set # CONFIG_MFD_WM8350_I2C is not set +# CONFIG_REGULATOR is not set # # Multimedia devices @@ -861,10 +899,18 @@ CONFIG_RTC_INTF_DEV=y # CONFIG_RTC_DRV_M41T80 is not set # CONFIG_RTC_DRV_S35390A is not set # CONFIG_RTC_DRV_FM3130 is not set +# CONFIG_RTC_DRV_RX8581 is not set # # SPI RTC drivers # +# CONFIG_RTC_DRV_M41T94 is not set +# CONFIG_RTC_DRV_DS1305 is not set +# CONFIG_RTC_DRV_DS1390 is not set +# CONFIG_RTC_DRV_MAX6902 is not set +# CONFIG_RTC_DRV_R9701 is not set +# CONFIG_RTC_DRV_RS5C348 is not set +# CONFIG_RTC_DRV_DS3234 is not set # # Platform RTC drivers @@ -1062,12 +1108,20 @@ CONFIG_DEBUG_INFO=y # CONFIG_DEBUG_BLOCK_EXT_DEVT is not set # CONFIG_FAULT_INJECTION is not set CONFIG_SYSCTL_SYSCALL_CHECK=y + +# +# Tracers +# +# CONFIG_SCHED_TRACER is not set +# CONFIG_CONTEXT_SWITCH_TRACER is not set +# CONFIG_BOOT_TRACER is not set # CONFIG_DYNAMIC_PRINTK_DEBUG is not set # CONFIG_SAMPLES is not set CONFIG_HAVE_ARCH_KGDB=y # CONFIG_KGDB is not set # CONFIG_DEBUG_STACKOVERFLOW is not set # CONFIG_DEBUG_STACK_USAGE is not set +# CONFIG_KGDB_TESTCASE is not set CONFIG_DEBUG_VERBOSE=y CONFIG_DEBUG_MMRS=y # CONFIG_DEBUG_HWERR is not set @@ -1100,6 +1154,7 @@ CONFIG_CRYPTO=y # # CONFIG_CRYPTO_FIPS is not set # CONFIG_CRYPTO_MANAGER is not set +# CONFIG_CRYPTO_MANAGER2 is not set # CONFIG_CRYPTO_GF128MUL is not set # CONFIG_CRYPTO_NULL is not set # CONFIG_CRYPTO_CRYPTD is not set diff --git a/arch/blackfin/configs/BF527-EZKIT_defconfig b/arch/blackfin/configs/BF527-EZKIT_defconfig index 833128b..a50050f 100644 --- a/arch/blackfin/configs/BF527-EZKIT_defconfig +++ b/arch/blackfin/configs/BF527-EZKIT_defconfig @@ -327,8 +327,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # diff --git a/arch/blackfin/configs/BF533-EZKIT_defconfig b/arch/blackfin/configs/BF533-EZKIT_defconfig index 334c94b..0a2a00d 100644 --- a/arch/blackfin/configs/BF533-EZKIT_defconfig +++ b/arch/blackfin/configs/BF533-EZKIT_defconfig @@ -290,8 +290,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # diff --git a/arch/blackfin/configs/BF533-STAMP_defconfig b/arch/blackfin/configs/BF533-STAMP_defconfig index 9d73343..eb02758 100644 --- a/arch/blackfin/configs/BF533-STAMP_defconfig +++ b/arch/blackfin/configs/BF533-STAMP_defconfig @@ -290,8 +290,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # diff --git a/arch/blackfin/configs/BF537-STAMP_defconfig b/arch/blackfin/configs/BF537-STAMP_defconfig index 4fb4108..9e62b9f 100644 --- a/arch/blackfin/configs/BF537-STAMP_defconfig +++ b/arch/blackfin/configs/BF537-STAMP_defconfig @@ -298,8 +298,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # @@ -568,15 +568,7 @@ CONFIG_MTD_PHYSMAP_BANKWIDTH=2 # CONFIG_MTD_DOC2000 is not set # CONFIG_MTD_DOC2001 is not set # CONFIG_MTD_DOC2001PLUS is not set -CONFIG_MTD_NAND=m -# CONFIG_MTD_NAND_VERIFY_WRITE is not set -# CONFIG_MTD_NAND_ECC_SMC is not set -# CONFIG_MTD_NAND_MUSEUM_IDS is not set -# CONFIG_MTD_NAND_BFIN is not set -CONFIG_MTD_NAND_IDS=m -# CONFIG_MTD_NAND_DISKONCHIP is not set -# CONFIG_MTD_NAND_NANDSIM is not set -CONFIG_MTD_NAND_PLATFORM=m +# CONFIG_MTD_NAND is not set # CONFIG_MTD_ONENAND is not set # diff --git a/arch/blackfin/configs/BF538-EZKIT_defconfig b/arch/blackfin/configs/BF538-EZKIT_defconfig index cb32f56..dd6ad6b 100644 --- a/arch/blackfin/configs/BF538-EZKIT_defconfig +++ b/arch/blackfin/configs/BF538-EZKIT_defconfig @@ -306,8 +306,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # diff --git a/arch/blackfin/configs/BF548-EZKIT_defconfig b/arch/blackfin/configs/BF548-EZKIT_defconfig index 0f869761..6bc2fb1 100644 --- a/arch/blackfin/configs/BF548-EZKIT_defconfig +++ b/arch/blackfin/configs/BF548-EZKIT_defconfig @@ -361,8 +361,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_BFIN_L2_CACHEABLE is not set # CONFIG_MPU is not set @@ -680,7 +680,7 @@ CONFIG_SCSI=y CONFIG_SCSI_DMA=y # CONFIG_SCSI_TGT is not set # CONFIG_SCSI_NETLINK is not set -CONFIG_SCSI_PROC_FS=y +# CONFIG_SCSI_PROC_FS is not set # # SCSI support type (disk, tape, CD-ROM) diff --git a/arch/blackfin/configs/BF561-EZKIT_defconfig b/arch/blackfin/configs/BF561-EZKIT_defconfig index 042c7ad..69714fb 100644 --- a/arch/blackfin/configs/BF561-EZKIT_defconfig +++ b/arch/blackfin/configs/BF561-EZKIT_defconfig @@ -329,8 +329,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_BFIN_L2_CACHEABLE is not set # CONFIG_MPU is not set diff --git a/arch/blackfin/configs/BlackStamp_defconfig b/arch/blackfin/configs/BlackStamp_defconfig index 3a20e28..017c6ea 100644 --- a/arch/blackfin/configs/BlackStamp_defconfig +++ b/arch/blackfin/configs/BlackStamp_defconfig @@ -288,8 +288,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # diff --git a/arch/blackfin/configs/CM-BF527_defconfig b/arch/blackfin/configs/CM-BF527_defconfig index 865ed85..d880ef7 100644 --- a/arch/blackfin/configs/CM-BF527_defconfig +++ b/arch/blackfin/configs/CM-BF527_defconfig @@ -332,8 +332,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # diff --git a/arch/blackfin/configs/CM-BF548_defconfig b/arch/blackfin/configs/CM-BF548_defconfig index efe9741..f410430 100644 --- a/arch/blackfin/configs/CM-BF548_defconfig +++ b/arch/blackfin/configs/CM-BF548_defconfig @@ -336,8 +336,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set CONFIG_L1_MAX_PIECE=16 # CONFIG_MPU is not set @@ -595,7 +595,7 @@ CONFIG_SCSI=y CONFIG_SCSI_DMA=y # CONFIG_SCSI_TGT is not set # CONFIG_SCSI_NETLINK is not set -CONFIG_SCSI_PROC_FS=y +# CONFIG_SCSI_PROC_FS is not set # # SCSI support type (disk, tape, CD-ROM) diff --git a/arch/blackfin/configs/IP0X_defconfig b/arch/blackfin/configs/IP0X_defconfig index eae83b5..7db9387 100644 --- a/arch/blackfin/configs/IP0X_defconfig +++ b/arch/blackfin/configs/IP0X_defconfig @@ -612,7 +612,7 @@ CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024 CONFIG_SCSI=y # CONFIG_SCSI_TGT is not set # CONFIG_SCSI_NETLINK is not set -CONFIG_SCSI_PROC_FS=y +# CONFIG_SCSI_PROC_FS is not set # # SCSI support type (disk, tape, CD-ROM) diff --git a/arch/blackfin/configs/SRV1_defconfig b/arch/blackfin/configs/SRV1_defconfig index fa580af..a46529c 100644 --- a/arch/blackfin/configs/SRV1_defconfig +++ b/arch/blackfin/configs/SRV1_defconfig @@ -282,8 +282,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set CONFIG_L1_MAX_PIECE=16 # diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild index 606ecfd..09c3141 100644 --- a/arch/blackfin/include/asm/Kbuild +++ b/arch/blackfin/include/asm/Kbuild @@ -1,3 +1,4 @@ include include/asm-generic/Kbuild.asm +unifdef-y += bfin_sport.h unifdef-y += fixed_code.h diff --git a/arch/blackfin/include/asm/bfin_sport.h b/arch/blackfin/include/asm/bfin_sport.h index fe88a2c..65a651d 100644 --- a/arch/blackfin/include/asm/bfin_sport.h +++ b/arch/blackfin/include/asm/bfin_sport.h @@ -1,30 +1,9 @@ /* - * File: include/asm-blackfin/bfin_sport.h - * Based on: - * Author: Roy Huang (roy.huang@analog.com) + * bfin_sport.h - userspace header for bfin sport driver * - * Created: Thu Aug. 24 2006 - * Description: + * Copyright 2004-2008 Analog Devices Inc. * - * Modified: - * Copyright 2004-2006 Analog Devices Inc. - * - * Bugs: Enter bugs at http://blackfin.uclinux.org/ - * - * 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, see the file COPYING, or write - * to the Free Software Foundation, Inc., - * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * Licensed under the GPL-2 or later. */ #ifndef __BFIN_SPORT_H__ @@ -42,11 +21,10 @@ #define NORM_FORMAT 0x0 #define ALAW_FORMAT 0x2 #define ULAW_FORMAT 0x3 -struct sport_register; /* Function driver which use sport must initialize the structure */ struct sport_config { - /*TDM (multichannels), I2S or other mode */ + /* TDM (multichannels), I2S or other mode */ unsigned int mode:3; /* if TDM mode is selected, channels must be set */ @@ -72,12 +50,18 @@ struct sport_config { int serial_clk; int fsync_clk; - unsigned int data_format:2; /*Normal, u-law or a-law */ + unsigned int data_format:2; /* Normal, u-law or a-law */ int word_len; /* How length of the word in bits, 3-32 bits */ int dma_enabled; }; +/* Userspace interface */ +#define SPORT_IOC_MAGIC 'P' +#define SPORT_IOC_CONFIG _IOWR('P', 0x01, struct sport_config) + +#ifdef __KERNEL__ + struct sport_register { unsigned short tcr1; unsigned short reserved0; @@ -117,9 +101,6 @@ struct sport_register { unsigned long mrcs3; }; -#define SPORT_IOC_MAGIC 'P' -#define SPORT_IOC_CONFIG _IOWR('P', 0x01, struct sport_config) - struct sport_dev { struct cdev cdev; /* Char device structure */ @@ -149,6 +130,8 @@ struct sport_dev { struct sport_config config; }; +#endif + #define SPORT_TCR1 0 #define SPORT_TCR2 1 #define SPORT_TCLKDIV 2 @@ -169,4 +152,4 @@ struct sport_dev { #define SPORT_MRCS2 22 #define SPORT_MRCS3 23 -#endif /*__BFIN_SPORT_H__*/ +#endif diff --git a/arch/blackfin/include/asm/ipipe.h b/arch/blackfin/include/asm/ipipe.h index 76f53d8..343b563 100644 --- a/arch/blackfin/include/asm/ipipe.h +++ b/arch/blackfin/include/asm/ipipe.h @@ -35,9 +35,9 @@ #include <asm/atomic.h> #include <asm/traps.h> -#define IPIPE_ARCH_STRING "1.8-00" +#define IPIPE_ARCH_STRING "1.9-00" #define IPIPE_MAJOR_NUMBER 1 -#define IPIPE_MINOR_NUMBER 8 +#define IPIPE_MINOR_NUMBER 9 #define IPIPE_PATCH_NUMBER 0 #ifdef CONFIG_SMP @@ -83,9 +83,9 @@ struct ipipe_sysinfo { "%2 = CYCLES2\n" \ "CC = %2 == %0\n" \ "if ! CC jump 1b\n" \ - : "=r" (((unsigned long *)&t)[1]), \ - "=r" (((unsigned long *)&t)[0]), \ - "=r" (__cy2) \ + : "=d,a" (((unsigned long *)&t)[1]), \ + "=d,a" (((unsigned long *)&t)[0]), \ + "=d,a" (__cy2) \ : /*no input*/ : "CC"); \ t; \ }) @@ -118,35 +118,40 @@ void __ipipe_disable_irqdesc(struct ipipe_domain *ipd, #define __ipipe_disable_irq(irq) (irq_desc[irq].chip->mask(irq)) -#define __ipipe_lock_root() \ - set_bit(IPIPE_ROOTLOCK_FLAG, &ipipe_root_domain->flags) +static inline int __ipipe_check_tickdev(const char *devname) +{ + return 1; +} -#define __ipipe_unlock_root() \ - clear_bit(IPIPE_ROOTLOCK_FLAG, &ipipe_root_domain->flags) +static inline void __ipipe_lock_root(void) +{ + set_bit(IPIPE_SYNCDEFER_FLAG, &ipipe_root_cpudom_var(status)); +} + +static inline void __ipipe_unlock_root(void) +{ + clear_bit(IPIPE_SYNCDEFER_FLAG, &ipipe_root_cpudom_var(status)); +} void __ipipe_enable_pipeline(void); #define __ipipe_hook_critical_ipi(ipd) do { } while (0) -#define __ipipe_sync_pipeline(syncmask) \ - do { \ - struct ipipe_domain *ipd = ipipe_current_domain; \ - if (likely(ipd != ipipe_root_domain || !test_bit(IPIPE_ROOTLOCK_FLAG, &ipd->flags))) \ - __ipipe_sync_stage(syncmask); \ - } while (0) +#define __ipipe_sync_pipeline ___ipipe_sync_pipeline +void ___ipipe_sync_pipeline(unsigned long syncmask); void __ipipe_handle_irq(unsigned irq, struct pt_regs *regs); int __ipipe_get_irq_priority(unsigned irq); -int __ipipe_get_irqthread_priority(unsigned irq); - void __ipipe_stall_root_raw(void); void __ipipe_unstall_root_raw(void); void __ipipe_serial_debug(const char *fmt, ...); +asmlinkage void __ipipe_call_irqtail(unsigned long addr); + DECLARE_PER_CPU(struct pt_regs, __ipipe_tick_regs); extern unsigned long __ipipe_core_clock; @@ -162,42 +167,25 @@ static inline unsigned long __ipipe_ffnz(unsigned long ul) #define __ipipe_run_irqtail() /* Must be a macro */ \ do { \ - asmlinkage void __ipipe_call_irqtail(void); \ unsigned long __pending; \ - CSYNC(); \ + CSYNC(); \ __pending = bfin_read_IPEND(); \ if (__pending & 0x8000) { \ __pending &= ~0x8010; \ if (__pending && (__pending & (__pending - 1)) == 0) \ - __ipipe_call_irqtail(); \ + __ipipe_call_irqtail(__ipipe_irq_tail_hook); \ } \ } while (0) #define __ipipe_run_isr(ipd, irq) \ do { \ if (ipd == ipipe_root_domain) { \ - /* \ - * Note: the I-pipe implements a threaded interrupt model on \ - * this arch for Linux external IRQs. The interrupt handler we \ - * call here only wakes up the associated IRQ thread. \ - */ \ - if (ipipe_virtual_irq_p(irq)) { \ - /* No irqtail here; virtual interrupts have no effect \ - on IPEND so there is no need for processing \ - deferral. */ \ - local_irq_enable_nohead(ipd); \ + local_irq_enable_hw(); \ + if (ipipe_virtual_irq_p(irq)) \ ipd->irqs[irq].handler(irq, ipd->irqs[irq].cookie); \ - local_irq_disable_nohead(ipd); \ - } else \ - /* \ - * No need to run the irqtail here either; \ - * we can't be preempted by hw IRQs, so \ - * non-Linux IRQs cannot stack over the short \ - * thread wakeup code. Which in turn means \ - * that no irqtail condition could be pending \ - * for domains above Linux in the pipeline. \ - */ \ + else \ ipd->irqs[irq].handler(irq, &__raw_get_cpu_var(__ipipe_tick_regs)); \ + local_irq_disable_hw(); \ } else { \ __clear_bit(IPIPE_SYNC_FLAG, &ipipe_cpudom_var(ipd, status)); \ local_irq_enable_nohead(ipd); \ @@ -217,42 +205,24 @@ void ipipe_init_irq_threads(void); int ipipe_start_irq_thread(unsigned irq, struct irq_desc *desc); -#define IS_SYSIRQ(irq) ((irq) > IRQ_CORETMR && (irq) <= SYS_IRQS) -#define IS_GPIOIRQ(irq) ((irq) >= GPIO_IRQ_BASE && (irq) < NR_IRQS) - +#ifdef CONFIG_GENERIC_CLOCKEVENTS +#define IRQ_SYSTMR IRQ_CORETMR +#define IRQ_PRIOTMR IRQ_CORETMR +#else #define IRQ_SYSTMR IRQ_TIMER0 #define IRQ_PRIOTMR CONFIG_IRQ_TIMER0 +#endif -#if defined(CONFIG_BF531) || defined(CONFIG_BF532) || defined(CONFIG_BF533) -#define PRIO_GPIODEMUX(irq) CONFIG_PFA -#elif defined(CONFIG_BF534) || defined(CONFIG_BF536) || defined(CONFIG_BF537) -#define PRIO_GPIODEMUX(irq) CONFIG_IRQ_PROG_INTA -#elif defined(CONFIG_BF52x) -#define PRIO_GPIODEMUX(irq) ((irq) == IRQ_PORTF_INTA ? CONFIG_IRQ_PORTF_INTA : \ - (irq) == IRQ_PORTG_INTA ? CONFIG_IRQ_PORTG_INTA : \ - (irq) == IRQ_PORTH_INTA ? CONFIG_IRQ_PORTH_INTA : \ - -1) -#elif defined(CONFIG_BF561) -#define PRIO_GPIODEMUX(irq) ((irq) == IRQ_PROG0_INTA ? CONFIG_IRQ_PROG0_INTA : \ - (irq) == IRQ_PROG1_INTA ? CONFIG_IRQ_PROG1_INTA : \ - (irq) == IRQ_PROG2_INTA ? CONFIG_IRQ_PROG2_INTA : \ - -1) +#ifdef CONFIG_BF561 #define bfin_write_TIMER_DISABLE(val) bfin_write_TMRS8_DISABLE(val) #define bfin_write_TIMER_ENABLE(val) bfin_write_TMRS8_ENABLE(val) #define bfin_write_TIMER_STATUS(val) bfin_write_TMRS8_STATUS(val) #define bfin_read_TIMER_STATUS() bfin_read_TMRS8_STATUS() #elif defined(CONFIG_BF54x) -#define PRIO_GPIODEMUX(irq) ((irq) == IRQ_PINT0 ? CONFIG_IRQ_PINT0 : \ - (irq) == IRQ_PINT1 ? CONFIG_IRQ_PINT1 : \ - (irq) == IRQ_PINT2 ? CONFIG_IRQ_PINT2 : \ - (irq) == IRQ_PINT3 ? CONFIG_IRQ_PINT3 : \ - -1) #define bfin_write_TIMER_DISABLE(val) bfin_write_TIMER_DISABLE0(val) #define bfin_write_TIMER_ENABLE(val) bfin_write_TIMER_ENABLE0(val) #define bfin_write_TIMER_STATUS(val) bfin_write_TIMER_STATUS0(val) #define bfin_read_TIMER_STATUS(val) bfin_read_TIMER_STATUS0(val) -#else -# error "no PRIO_GPIODEMUX() for this part" #endif #define __ipipe_root_tick_p(regs) ((regs->ipend & 0x10) != 0) @@ -275,4 +245,6 @@ int ipipe_start_irq_thread(unsigned irq, struct irq_desc *desc); #endif /* !CONFIG_IPIPE */ +#define ipipe_update_tick_evtdev(evtdev) do { } while (0) + #endif /* !__ASM_BLACKFIN_IPIPE_H */ diff --git a/arch/blackfin/include/asm/ipipe_base.h b/arch/blackfin/include/asm/ipipe_base.h index cb1025a..3e8acbd 100644 --- a/arch/blackfin/include/asm/ipipe_base.h +++ b/arch/blackfin/include/asm/ipipe_base.h @@ -1,5 +1,5 @@ /* -*- linux-c -*- - * include/asm-blackfin/_baseipipe.h + * include/asm-blackfin/ipipe_base.h * * Copyright (C) 2007 Philippe Gerum. * @@ -27,8 +27,9 @@ #define IPIPE_NR_XIRQS NR_IRQS #define IPIPE_IRQ_ISHIFT 5 /* 2^5 for 32bits arch. */ -/* Blackfin-specific, global domain flags */ -#define IPIPE_ROOTLOCK_FLAG 1 /* Lock pipeline for root */ +/* Blackfin-specific, per-cpu pipeline status */ +#define IPIPE_SYNCDEFER_FLAG 15 +#define IPIPE_SYNCDEFER_MASK (1L << IPIPE_SYNCDEFER_MASK) /* Blackfin traps -- i.e. exception vector numbers */ #define IPIPE_NR_FAULTS 52 /* We leave a gap after VEC_ILL_RES. */ @@ -48,11 +49,6 @@ #ifndef __ASSEMBLY__ -#include <linux/bitops.h> - -extern int test_bit(int nr, const void *addr); - - extern unsigned long __ipipe_root_status; /* Alias to ipipe_root_cpudom_var(status) */ static inline void __ipipe_stall_root(void) diff --git a/arch/blackfin/include/asm/irq.h b/arch/blackfin/include/asm/irq.h index 3d97790..7645e85 100644 --- a/arch/blackfin/include/asm/irq.h +++ b/arch/blackfin/include/asm/irq.h @@ -61,20 +61,38 @@ void __ipipe_restore_root(unsigned long flags); #define raw_irqs_disabled_flags(flags) (!irqs_enabled_from_flags_hw(flags)) #define local_test_iflag_hw(x) irqs_enabled_from_flags_hw(x) -#define local_save_flags(x) \ - do { \ - (x) = __ipipe_test_root() ? \ +#define local_save_flags(x) \ + do { \ + (x) = __ipipe_test_root() ? \ __all_masked_irq_flags : bfin_irq_flags; \ + barrier(); \ } while (0) -#define local_irq_save(x) \ - do { \ - (x) = __ipipe_test_and_stall_root(); \ +#define local_irq_save(x) \ + do { \ + (x) = __ipipe_test_and_stall_root() ? \ + __all_masked_irq_flags : bfin_irq_flags; \ + barrier(); \ + } while (0) + +static inline void local_irq_restore(unsigned long x) +{ + barrier(); + __ipipe_restore_root(x == __all_masked_irq_flags); +} + +#define local_irq_disable() \ + do { \ + __ipipe_stall_root(); \ + barrier(); \ } while (0) -#define local_irq_restore(x) __ipipe_restore_root(x) -#define local_irq_disable() __ipipe_stall_root() -#define local_irq_enable() __ipipe_unstall_root() +static inline void local_irq_enable(void) +{ + barrier(); + __ipipe_unstall_root(); +} + #define irqs_disabled() __ipipe_test_root() #define local_save_flags_hw(x) \ diff --git a/arch/blackfin/include/asm/percpu.h b/arch/blackfin/include/asm/percpu.h index 797c0c1..c94c7bc 100644 --- a/arch/blackfin/include/asm/percpu.h +++ b/arch/blackfin/include/asm/percpu.h @@ -3,14 +3,4 @@ #include <asm-generic/percpu.h> -#ifdef CONFIG_MODULES -#define PERCPU_MODULE_RESERVE 8192 -#else -#define PERCPU_MODULE_RESERVE 0 -#endif - -#define PERCPU_ENOUGH_ROOM \ - (ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \ - PERCPU_MODULE_RESERVE) - #endif /* __ARCH_BLACKFIN_PERCPU__ */ diff --git a/arch/blackfin/include/asm/thread_info.h b/arch/blackfin/include/asm/thread_info.h index e721ce5..2920087 100644 --- a/arch/blackfin/include/asm/thread_info.h +++ b/arch/blackfin/include/asm/thread_info.h @@ -122,6 +122,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_MEMDIE 4 #define TIF_RESTORE_SIGMASK 5 /* restore signal mask in do_signal() */ #define TIF_FREEZE 6 /* is freezing for suspend */ +#define TIF_IRQ_SYNC 7 /* sync pipeline stage */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) @@ -130,6 +131,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG) #define _TIF_RESTORE_SIGMASK (1<<TIF_RESTORE_SIGMASK) #define _TIF_FREEZE (1<<TIF_FREEZE) +#define _TIF_IRQ_SYNC (1<<TIF_IRQ_SYNC) #define _TIF_WORK_MASK 0x0000FFFE /* work to do on interrupt/exception return */ diff --git a/arch/blackfin/kernel/Makefile b/arch/blackfin/kernel/Makefile index 4a92a86..fd4d432 100644 --- a/arch/blackfin/kernel/Makefile +++ b/arch/blackfin/kernel/Makefile @@ -15,13 +15,15 @@ else obj-y += time.o endif -CFLAGS_kgdb_test.o := -mlong-calls -O0 - obj-$(CONFIG_IPIPE) += ipipe.o obj-$(CONFIG_IPIPE_TRACE_MCOUNT) += mcount.o obj-$(CONFIG_BFIN_GPTIMERS) += gptimers.o obj-$(CONFIG_CPLB_INFO) += cplbinfo.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_KGDB) += kgdb.o -obj-$(CONFIG_KGDB_TESTCASE) += kgdb_test.o +obj-$(CONFIG_KGDB_TESTS) += kgdb_test.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o + +# the kgdb test puts code into L2 and without linker +# relaxation, we need to force long calls to/from it +CFLAGS_kgdb_test.o := -mlong-calls -O0 diff --git a/arch/blackfin/kernel/cplb-nompu/cplbinit.c b/arch/blackfin/kernel/cplb-nompu/cplbinit.c index 0e28f75..d6c0677 100644 --- a/arch/blackfin/kernel/cplb-nompu/cplbinit.c +++ b/arch/blackfin/kernel/cplb-nompu/cplbinit.c @@ -53,9 +53,13 @@ void __init generate_cplb_tables_cpu(unsigned int cpu) i_d = i_i = 0; +#ifdef CONFIG_DEBUG_HUNT_FOR_ZERO /* Set up the zero page. */ d_tbl[i_d].addr = 0; d_tbl[i_d++].data = SDRAM_OOPS | PAGE_SIZE_1KB; + i_tbl[i_i].addr = 0; + i_tbl[i_i++].data = SDRAM_OOPS | PAGE_SIZE_1KB; +#endif /* Cover kernel memory with 4M pages. */ addr = 0; diff --git a/arch/blackfin/kernel/ipipe.c b/arch/blackfin/kernel/ipipe.c index 339be5a..a5de8d4 100644 --- a/arch/blackfin/kernel/ipipe.c +++ b/arch/blackfin/kernel/ipipe.c @@ -35,14 +35,8 @@ #include <asm/atomic.h> #include <asm/io.h> -static int create_irq_threads; - DEFINE_PER_CPU(struct pt_regs, __ipipe_tick_regs); -static DEFINE_PER_CPU(unsigned long, pending_irqthread_mask); - -static DEFINE_PER_CPU(int [IVG13 + 1], pending_irq_count); - asmlinkage void asm_do_IRQ(unsigned int irq, struct pt_regs *regs); static void __ipipe_no_irqtail(void); @@ -93,6 +87,7 @@ void __ipipe_enable_pipeline(void) */ void __ipipe_handle_irq(unsigned irq, struct pt_regs *regs) { + struct ipipe_percpu_domain_data *p = ipipe_root_cpudom_ptr(); struct ipipe_domain *this_domain, *next_domain; struct list_head *head, *pos; int m_ack, s = -1; @@ -104,7 +99,6 @@ void __ipipe_handle_irq(unsigned irq, struct pt_regs *regs) * interrupt. */ m_ack = (regs == NULL || irq == IRQ_SYSTMR || irq == IRQ_CORETMR); - this_domain = ipipe_current_domain; if (unlikely(test_bit(IPIPE_STICKY_FLAG, &this_domain->irqs[irq].control))) @@ -114,49 +108,28 @@ void __ipipe_handle_irq(unsigned irq, struct pt_regs *regs) next_domain = list_entry(head, struct ipipe_domain, p_link); if (likely(test_bit(IPIPE_WIRED_FLAG, &next_domain->irqs[irq].control))) { if (!m_ack && next_domain->irqs[irq].acknowledge != NULL) - next_domain->irqs[irq].acknowledge(irq, irq_desc + irq); - if (test_bit(IPIPE_ROOTLOCK_FLAG, &ipipe_root_domain->flags)) - s = __test_and_set_bit(IPIPE_STALL_FLAG, - &ipipe_root_cpudom_var(status)); + next_domain->irqs[irq].acknowledge(irq, irq_to_desc(irq)); + if (test_bit(IPIPE_SYNCDEFER_FLAG, &p->status)) + s = __test_and_set_bit(IPIPE_STALL_FLAG, &p->status); __ipipe_dispatch_wired(next_domain, irq); - goto finalize; - return; + goto out; } } /* Ack the interrupt. */ pos = head; - while (pos != &__ipipe_pipeline) { next_domain = list_entry(pos, struct ipipe_domain, p_link); - /* - * For each domain handling the incoming IRQ, mark it - * as pending in its log. - */ if (test_bit(IPIPE_HANDLE_FLAG, &next_domain->irqs[irq].control)) { - /* - * Domains that handle this IRQ are polled for - * acknowledging it by decreasing priority - * order. The interrupt must be made pending - * _first_ in the domain's status flags before - * the PIC is unlocked. - */ __ipipe_set_irq_pending(next_domain, irq); - if (!m_ack && next_domain->irqs[irq].acknowledge != NULL) { - next_domain->irqs[irq].acknowledge(irq, irq_desc + irq); + next_domain->irqs[irq].acknowledge(irq, irq_to_desc(irq)); m_ack = 1; } } - - /* - * If the domain does not want the IRQ to be passed - * down the interrupt pipe, exit the loop now. - */ if (!test_bit(IPIPE_PASS_FLAG, &next_domain->irqs[irq].control)) break; - pos = next_domain->p_link.next; } @@ -166,18 +139,24 @@ void __ipipe_handle_irq(unsigned irq, struct pt_regs *regs) * immediately to the current domain if the interrupt has been * marked as 'sticky'. This search does not go beyond the * current domain in the pipeline. We also enforce the - * additional root stage lock (blackfin-specific). */ + * additional root stage lock (blackfin-specific). + */ + if (test_bit(IPIPE_SYNCDEFER_FLAG, &p->status)) + s = __test_and_set_bit(IPIPE_STALL_FLAG, &p->status); - if (test_bit(IPIPE_ROOTLOCK_FLAG, &ipipe_root_domain->flags)) - s = __test_and_set_bit(IPIPE_STALL_FLAG, - &ipipe_root_cpudom_var(status)); -finalize: + /* + * If the interrupt preempted the head domain, then do not + * even try to walk the pipeline, unless an interrupt is + * pending for it. + */ + if (test_bit(IPIPE_AHEAD_FLAG, &this_domain->flags) && + ipipe_head_cpudom_var(irqpend_himask) == 0) + goto out; __ipipe_walk_pipeline(head); - +out: if (!s) - __clear_bit(IPIPE_STALL_FLAG, - &ipipe_root_cpudom_var(status)); + __clear_bit(IPIPE_STALL_FLAG, &p->status); } int __ipipe_check_root(void) @@ -187,7 +166,7 @@ int __ipipe_check_root(void) void __ipipe_enable_irqdesc(struct ipipe_domain *ipd, unsigned irq) { - struct irq_desc *desc = irq_desc + irq; + struct irq_desc *desc = irq_to_desc(irq); int prio = desc->ic_prio; desc->depth = 0; @@ -199,7 +178,7 @@ EXPORT_SYMBOL(__ipipe_enable_irqdesc); void __ipipe_disable_irqdesc(struct ipipe_domain *ipd, unsigned irq) { - struct irq_desc *desc = irq_desc + irq; + struct irq_desc *desc = irq_to_desc(irq); int prio = desc->ic_prio; if (ipd != &ipipe_root && @@ -236,15 +215,18 @@ int __ipipe_syscall_root(struct pt_regs *regs) { unsigned long flags; - /* We need to run the IRQ tail hook whenever we don't + /* + * We need to run the IRQ tail hook whenever we don't * propagate a syscall to higher domains, because we know that * important operations might be pending there (e.g. Xenomai - * deferred rescheduling). */ + * deferred rescheduling). + */ - if (!__ipipe_syscall_watched_p(current, regs->orig_p0)) { + if (regs->orig_p0 < NR_syscalls) { void (*hook)(void) = (void (*)(void))__ipipe_irq_tail_hook; hook(); - return 0; + if ((current->flags & PF_EVNOTIFY) == 0) + return 0; } /* @@ -312,112 +294,46 @@ int ipipe_trigger_irq(unsigned irq) { unsigned long flags; +#ifdef CONFIG_IPIPE_DEBUG if (irq >= IPIPE_NR_IRQS || (ipipe_virtual_irq_p(irq) && !test_bit(irq - IPIPE_VIRQ_BASE, &__ipipe_virtual_irq_map))) return -EINVAL; +#endif local_irq_save_hw(flags); - __ipipe_handle_irq(irq, NULL); - local_irq_restore_hw(flags); return 1; } -/* Move Linux IRQ to threads. */ - -static int do_irqd(void *__desc) +asmlinkage void __ipipe_sync_root(void) { - struct irq_desc *desc = __desc; - unsigned irq = desc - irq_desc; - int thrprio = desc->thr_prio; - int thrmask = 1 << thrprio; - int cpu = smp_processor_id(); - cpumask_t cpumask; - - sigfillset(¤t->blocked); - current->flags |= PF_NOFREEZE; - cpumask = cpumask_of_cpu(cpu); - set_cpus_allowed(current, cpumask); - ipipe_setscheduler_root(current, SCHED_FIFO, 50 + thrprio); - - while (!kthread_should_stop()) { - local_irq_disable(); - if (!(desc->status & IRQ_SCHEDULED)) { - set_current_state(TASK_INTERRUPTIBLE); -resched: - local_irq_enable(); - schedule(); - local_irq_disable(); - } - __set_current_state(TASK_RUNNING); - /* - * If higher priority interrupt servers are ready to - * run, reschedule immediately. We need this for the - * GPIO demux IRQ handler to unmask the interrupt line - * _last_, after all GPIO IRQs have run. - */ - if (per_cpu(pending_irqthread_mask, cpu) & ~(thrmask|(thrmask-1))) - goto resched; - if (--per_cpu(pending_irq_count[thrprio], cpu) == 0) - per_cpu(pending_irqthread_mask, cpu) &= ~thrmask; - desc->status &= ~IRQ_SCHEDULED; - desc->thr_handler(irq, &__raw_get_cpu_var(__ipipe_tick_regs)); - local_irq_enable(); - } - __set_current_state(TASK_RUNNING); - return 0; -} + unsigned long flags; -static void kick_irqd(unsigned irq, void *cookie) -{ - struct irq_desc *desc = irq_desc + irq; - int thrprio = desc->thr_prio; - int thrmask = 1 << thrprio; - int cpu = smp_processor_id(); - - if (!(desc->status & IRQ_SCHEDULED)) { - desc->status |= IRQ_SCHEDULED; - per_cpu(pending_irqthread_mask, cpu) |= thrmask; - ++per_cpu(pending_irq_count[thrprio], cpu); - wake_up_process(desc->thread); - } -} + BUG_ON(irqs_disabled()); -int ipipe_start_irq_thread(unsigned irq, struct irq_desc *desc) -{ - if (desc->thread || !create_irq_threads) - return 0; - - desc->thread = kthread_create(do_irqd, desc, "IRQ %d", irq); - if (desc->thread == NULL) { - printk(KERN_ERR "irqd: could not create IRQ thread %d!\n", irq); - return -ENOMEM; - } + local_irq_save_hw(flags); - wake_up_process(desc->thread); + clear_thread_flag(TIF_IRQ_SYNC); - desc->thr_handler = ipipe_root_domain->irqs[irq].handler; - ipipe_root_domain->irqs[irq].handler = &kick_irqd; + if (ipipe_root_cpudom_var(irqpend_himask) != 0) + __ipipe_sync_pipeline(IPIPE_IRQMASK_ANY); - return 0; + local_irq_restore_hw(flags); } -void __init ipipe_init_irq_threads(void) +void ___ipipe_sync_pipeline(unsigned long syncmask) { - unsigned irq; - struct irq_desc *desc; - - create_irq_threads = 1; + struct ipipe_domain *ipd = ipipe_current_domain; - for (irq = 0; irq < NR_IRQS; irq++) { - desc = irq_desc + irq; - if (desc->action != NULL || - (desc->status & IRQ_NOREQUEST) != 0) - ipipe_start_irq_thread(irq, desc); + if (ipd == ipipe_root_domain) { + if (test_bit(IPIPE_SYNCDEFER_FLAG, &ipipe_root_cpudom_var(status))) + return; } + + __ipipe_sync_stage(syncmask); } EXPORT_SYMBOL(show_stack); diff --git a/arch/blackfin/kernel/irqchip.c b/arch/blackfin/kernel/irqchip.c index 23e9aa0..1ab5b53 100644 --- a/arch/blackfin/kernel/irqchip.c +++ b/arch/blackfin/kernel/irqchip.c @@ -149,11 +149,15 @@ asmlinkage void asm_do_IRQ(unsigned int irq, struct pt_regs *regs) #endif generic_handle_irq(irq); -#ifndef CONFIG_IPIPE /* Useless and bugous over the I-pipe: IRQs are threaded. */ - /* If we're the only interrupt running (ignoring IRQ15 which is for - syscalls), lower our priority to IRQ14 so that softirqs run at - that level. If there's another, lower-level interrupt, irq_exit - will defer softirqs to that. */ +#ifndef CONFIG_IPIPE + /* + * If we're the only interrupt running (ignoring IRQ15 which + * is for syscalls), lower our priority to IRQ14 so that + * softirqs run at that level. If there's another, + * lower-level interrupt, irq_exit will defer softirqs to + * that. If the interrupt pipeline is enabled, we are already + * running at IRQ14 priority, so we don't need this code. + */ CSYNC(); pending = bfin_read_IPEND() & ~0x8000; other_ints = pending & (pending - 1); diff --git a/arch/blackfin/kernel/kgdb_test.c b/arch/blackfin/kernel/kgdb_test.c index 3dba9c1..dbcf3e4 100644 --- a/arch/blackfin/kernel/kgdb_test.c +++ b/arch/blackfin/kernel/kgdb_test.c @@ -20,6 +20,7 @@ static char cmdline[256]; static unsigned long len; +#ifndef CONFIG_SMP static int num1 __attribute__((l1_data)); void kgdb_l1_test(void) __attribute__((l1_text)); @@ -32,6 +33,8 @@ void kgdb_l1_test(void) printk(KERN_ALERT "L1(after change) : data variable addr = 0x%p, data value is %d\n", &num1, num1); return ; } +#endif + #if L2_LENGTH static int num2 __attribute__((l2)); @@ -59,10 +62,12 @@ int kgdb_test(char *name, int len, int count, int z) static int test_proc_output(char *buf) { kgdb_test("hello world!", 12, 0x55, 0x10); +#ifndef CONFIG_SMP kgdb_l1_test(); - #if L2_LENGTH +#endif +#if L2_LENGTH kgdb_l2_test(); - #endif +#endif return 0; } diff --git a/arch/blackfin/kernel/ptrace.c b/arch/blackfin/kernel/ptrace.c index 594e325..d76618d 100644 --- a/arch/blackfin/kernel/ptrace.c +++ b/arch/blackfin/kernel/ptrace.c @@ -45,6 +45,7 @@ #include <asm/asm-offsets.h> #include <asm/dma.h> #include <asm/fixed_code.h> +#include <asm/cacheflush.h> #include <asm/mem_map.h> #define TEXT_OFFSET 0 @@ -240,7 +241,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } else if (addr >= FIXED_CODE_START && addr + sizeof(tmp) <= FIXED_CODE_END) { - memcpy(&tmp, (const void *)(addr), sizeof(tmp)); + copy_from_user_page(0, 0, 0, &tmp, (const void *)(addr), sizeof(tmp)); copied = sizeof(tmp); } else @@ -320,7 +321,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } else if (addr >= FIXED_CODE_START && addr + sizeof(data) <= FIXED_CODE_END) { - memcpy((void *)(addr), &data, sizeof(data)); + copy_to_user_page(0, 0, 0, (void *)(addr), &data, sizeof(data)); copied = sizeof(data); } else diff --git a/arch/blackfin/kernel/setup.c b/arch/blackfin/kernel/setup.c index e5c1162..a58687b 100644 --- a/arch/blackfin/kernel/setup.c +++ b/arch/blackfin/kernel/setup.c @@ -889,6 +889,10 @@ void __init setup_arch(char **cmdline_p) CPU, bfin_revid()); } + /* We can't run on BF548-0.1 due to ANOMALY 05000448 */ + if (bfin_cpuid() == 0x27de && bfin_revid() == 1) + panic("You can't run on this processor due to 05000448\n"); + printk(KERN_INFO "Blackfin Linux support by http://blackfin.uclinux.org/\n"); printk(KERN_INFO "Processor Speed: %lu MHz core clock and %lu MHz System Clock\n", @@ -1141,12 +1145,12 @@ static int show_cpuinfo(struct seq_file *m, void *v) icache_size = 0; seq_printf(m, "cache size\t: %d KB(L1 icache) " - "%d KB(L1 dcache-%s) %d KB(L2 cache)\n", + "%d KB(L1 dcache%s) %d KB(L2 cache)\n", icache_size, dcache_size, #if defined CONFIG_BFIN_WB - "wb" + "-wb" #elif defined CONFIG_BFIN_WT - "wt" + "-wt" #endif "", 0); diff --git a/arch/blackfin/kernel/time.c b/arch/blackfin/kernel/time.c index 172b4c5..1bbacfb 100644 --- a/arch/blackfin/kernel/time.c +++ b/arch/blackfin/kernel/time.c @@ -134,7 +134,10 @@ irqreturn_t timer_interrupt(int irq, void *dummy) write_seqlock(&xtime_lock); #if defined(CONFIG_TICK_SOURCE_SYSTMR0) && !defined(CONFIG_IPIPE) -/* FIXME: Here TIMIL0 is not set when IPIPE enabled, why? */ + /* + * TIMIL0 is latched in __ipipe_grab_irq() when the I-Pipe is + * enabled. + */ if (get_gptimer_status(0) & TIMER_STATUS_TIMIL0) { #endif do_timer(1); diff --git a/arch/blackfin/mach-bf518/boards/ezbrd.c b/arch/blackfin/mach-bf518/boards/ezbrd.c index 0e17534..41f2eac 100644 --- a/arch/blackfin/mach-bf518/boards/ezbrd.c +++ b/arch/blackfin/mach-bf518/boards/ezbrd.c @@ -113,7 +113,6 @@ static struct platform_device bfin_mac_device = { .name = "bfin_mac", .dev.platform_data = &bfin_mii_bus, }; -#endif #if defined(CONFIG_NET_DSA_KSZ8893M) || defined(CONFIG_NET_DSA_KSZ8893M_MODULE) static struct dsa_platform_data ksz8893m_switch_data = { @@ -132,6 +131,7 @@ static struct platform_device ksz8893m_switch_device = { .dev.platform_data = &ksz8893m_switch_data, }; #endif +#endif #if defined(CONFIG_MTD_M25P80) \ || defined(CONFIG_MTD_M25P80_MODULE) @@ -171,6 +171,7 @@ static struct bfin5xx_spi_chip spi_adc_chip_info = { }; #endif +#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) #if defined(CONFIG_NET_DSA_KSZ8893M) \ || defined(CONFIG_NET_DSA_KSZ8893M_MODULE) /* SPI SWITCH CHIP */ @@ -179,10 +180,11 @@ static struct bfin5xx_spi_chip spi_switch_info = { .bits_per_word = 8, }; #endif +#endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -259,6 +261,7 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif +#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) #if defined(CONFIG_NET_DSA_KSZ8893M) \ || defined(CONFIG_NET_DSA_KSZ8893M_MODULE) { @@ -271,24 +274,15 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .mode = SPI_MODE_3, }, #endif +#endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc_dummy", + .modalias = "mmc_spi", .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, - { - .modalias = "spi_mmc", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif @@ -630,11 +624,10 @@ static struct platform_device *stamp_devices[] __initdata = { #if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) &bfin_mii_bus, &bfin_mac_device, -#endif - #if defined(CONFIG_NET_DSA_KSZ8893M) || defined(CONFIG_NET_DSA_KSZ8893M_MODULE) &ksz8893m_switch_device, #endif +#endif #if defined(CONFIG_SPI_BFIN) || defined(CONFIG_SPI_BFIN_MODULE) &bfin_spi0_device, diff --git a/arch/blackfin/mach-bf518/include/mach/anomaly.h b/arch/blackfin/mach-bf518/include/mach/anomaly.h index e5b4bef..c847bb1 100644 --- a/arch/blackfin/mach-bf518/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf518/include/mach/anomaly.h @@ -2,12 +2,12 @@ * File: include/asm-blackfin/mach-bf518/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ /* This file shoule be up to date with: - * - ???? + * - Revision B, 02/03/2009; ADSP-BF512/BF514/BF516/BF518 Blackfin Processor Anomaly List */ #ifndef _MACH_ANOMALY_H_ @@ -19,6 +19,8 @@ #define ANOMALY_05000122 (1) /* False Hardware Error from an Access in the Shadow of a Conditional Branch */ #define ANOMALY_05000245 (1) +/* Incorrect Timer Pulse Width in Single-Shot PWM_OUT Mode with External Clock */ +#define ANOMALY_05000254 (1) /* Sensitivity To Noise with Slow Input Edge Rates on External SPORT TX and RX Clocks */ #define ANOMALY_05000265 (1) /* False Hardware Errors Caused by Fetches at the Boundary of Reserved Memory */ @@ -53,6 +55,12 @@ #define ANOMALY_05000443 (1) /* Incorrect L1 Instruction Bank B Memory Map Location */ #define ANOMALY_05000444 (1) +/* Incorrect Default Hysteresis Setting for RESET, NMI, and BMODE Signals */ +#define ANOMALY_05000452 (1) +/* PWM_TRIPB Signal Not Available on PG10 */ +#define ANOMALY_05000453 (1) +/* PPI_FS3 is Driven One Half Cycle Later Than PPI Data */ +#define ANOMALY_05000455 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000125 (0) @@ -65,15 +73,20 @@ #define ANOMALY_05000263 (0) #define ANOMALY_05000266 (0) #define ANOMALY_05000273 (0) +#define ANOMALY_05000278 (0) #define ANOMALY_05000285 (0) +#define ANOMALY_05000305 (0) #define ANOMALY_05000307 (0) #define ANOMALY_05000311 (0) #define ANOMALY_05000312 (0) #define ANOMALY_05000323 (0) #define ANOMALY_05000353 (0) #define ANOMALY_05000363 (0) +#define ANOMALY_05000380 (0) #define ANOMALY_05000386 (0) #define ANOMALY_05000412 (0) #define ANOMALY_05000432 (0) +#define ANOMALY_05000447 (0) +#define ANOMALY_05000448 (0) #endif diff --git a/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h index b50a63b..e21c1c3 100644 --- a/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h @@ -144,7 +144,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART0_TX, CH_UART0_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif @@ -158,7 +158,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART1_TX, CH_UART1_RX, #endif -#ifdef CONFIG_BFIN_UART1_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART1_CTS_PIN, CONFIG_UART1_RTS_PIN, #endif diff --git a/arch/blackfin/mach-bf527/boards/cm_bf527.c b/arch/blackfin/mach-bf527/boards/cm_bf527.c index 856c097..48e69ee 100644 --- a/arch/blackfin/mach-bf527/boards/cm_bf527.c +++ b/arch/blackfin/mach-bf527/boards/cm_bf527.c @@ -487,9 +487,9 @@ static struct bfin5xx_spi_chip ad9960_spi_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -585,23 +585,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .controller_data = &ad9960_spi_chip_info, }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, - { - .modalias = "spi_mmc", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ + .modalias = "mmc_spi", + .max_speed_hz = 20000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf527/boards/ezbrd.c b/arch/blackfin/mach-bf527/boards/ezbrd.c index 83606fc..7fe480e 100644 --- a/arch/blackfin/mach-bf527/boards/ezbrd.c +++ b/arch/blackfin/mach-bf527/boards/ezbrd.c @@ -256,9 +256,9 @@ static struct bfin5xx_spi_chip spi_adc_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -366,23 +366,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc_dummy", + .modalias = "mmc_spi", .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, - { - .modalias = "spi_mmc", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf527/include/mach/anomaly.h b/arch/blackfin/mach-bf527/include/mach/anomaly.h index 035e8d8..df6808d 100644 --- a/arch/blackfin/mach-bf527/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf527/include/mach/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf527/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ @@ -167,12 +167,16 @@ #define ANOMALY_05000263 (0) #define ANOMALY_05000266 (0) #define ANOMALY_05000273 (0) +#define ANOMALY_05000278 (0) #define ANOMALY_05000285 (0) +#define ANOMALY_05000305 (0) #define ANOMALY_05000307 (0) #define ANOMALY_05000311 (0) #define ANOMALY_05000312 (0) #define ANOMALY_05000323 (0) #define ANOMALY_05000363 (0) #define ANOMALY_05000412 (0) +#define ANOMALY_05000447 (0) +#define ANOMALY_05000448 (0) #endif diff --git a/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h index 75722d6..e8c41fd 100644 --- a/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h @@ -144,7 +144,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART0_TX, CH_UART0_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif @@ -158,7 +158,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART1_TX, CH_UART1_RX, #endif -#ifdef CONFIG_BFIN_UART1_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART1_CTS_PIN, CONFIG_UART1_RTS_PIN, #endif diff --git a/arch/blackfin/mach-bf533/boards/Kconfig b/arch/blackfin/mach-bf533/boards/Kconfig index 308c98d..8d8b3e7 100644 --- a/arch/blackfin/mach-bf533/boards/Kconfig +++ b/arch/blackfin/mach-bf533/boards/Kconfig @@ -38,9 +38,4 @@ config BFIN532_IP0X help Core support for IP04/IP04 open hardware IP-PBX. -config GENERIC_BF533_BOARD - bool "Generic" - help - Generic or Custom board support. - endchoice diff --git a/arch/blackfin/mach-bf533/boards/Makefile b/arch/blackfin/mach-bf533/boards/Makefile index 9afbe72..ff1e832 100644 --- a/arch/blackfin/mach-bf533/boards/Makefile +++ b/arch/blackfin/mach-bf533/boards/Makefile @@ -2,7 +2,6 @@ # arch/blackfin/mach-bf533/boards/Makefile # -obj-$(CONFIG_GENERIC_BF533_BOARD) += generic_board.o obj-$(CONFIG_BFIN533_STAMP) += stamp.o obj-$(CONFIG_BFIN532_IP0X) += ip0x.o obj-$(CONFIG_BFIN533_EZKIT) += ezkit.o diff --git a/arch/blackfin/mach-bf533/boards/blackstamp.c b/arch/blackfin/mach-bf533/boards/blackstamp.c index 015c18f..0765872 100644 --- a/arch/blackfin/mach-bf533/boards/blackstamp.c +++ b/arch/blackfin/mach-bf533/boards/blackstamp.c @@ -101,9 +101,9 @@ static struct bfin5xx_spi_chip spi_flash_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -129,23 +129,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) - { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 20000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", + .modalias = "mmc_spi", .max_speed_hz = 20000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf533/boards/cm_bf533.c b/arch/blackfin/mach-bf533/boards/cm_bf533.c index e7061c7..e897487 100644 --- a/arch/blackfin/mach-bf533/boards/cm_bf533.c +++ b/arch/blackfin/mach-bf533/boards/cm_bf533.c @@ -96,9 +96,9 @@ static struct bfin5xx_spi_chip ad1836_spi_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -138,23 +138,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) - { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", + .modalias = "mmc_spi", .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf533/boards/generic_board.c b/arch/blackfin/mach-bf533/boards/generic_board.c deleted file mode 100644 index 986eeec..0000000 --- a/arch/blackfin/mach-bf533/boards/generic_board.c +++ /dev/null @@ -1,126 +0,0 @@ -/* - * File: arch/blackfin/mach-bf533/generic_board.c - * Based on: arch/blackfin/mach-bf533/ezkit.c - * Author: Aidan Williams <aidan@nicta.com.au> - * - * Created: 2005 - * Description: - * - * Modified: - * Copyright 2005 National ICT Australia (NICTA) - * Copyright 2004-2006 Analog Devices Inc. - * - * Bugs: Enter bugs at http://blackfin.uclinux.org/ - * - * 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, see the file COPYING, or write - * to the Free Software Foundation, Inc., - * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ - -#include <linux/device.h> -#include <linux/platform_device.h> -#include <linux/irq.h> - -/* - * Name the Board for the /proc/cpuinfo - */ -const char bfin_board_name[] = "UNKNOWN BOARD"; - -#if defined(CONFIG_RTC_DRV_BFIN) || defined(CONFIG_RTC_DRV_BFIN_MODULE) -static struct platform_device rtc_device = { - .name = "rtc-bfin", - .id = -1, -}; -#endif - -/* - * Driver needs to know address, irq and flag pin. - */ -#if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE) -static struct resource smc91x_resources[] = { - { - .start = 0x20300300, - .end = 0x20300300 + 16, - .flags = IORESOURCE_MEM, - }, { - .start = IRQ_PROG_INTB, - .end = IRQ_PROG_INTB, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, { - .start = IRQ_PF7, - .end = IRQ_PF7, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, -}; - -static struct platform_device smc91x_device = { - .name = "smc91x", - .id = 0, - .num_resources = ARRAY_SIZE(smc91x_resources), - .resource = smc91x_resources, -}; -#endif - -#if defined(CONFIG_BFIN_SIR) || defined(CONFIG_BFIN_SIR_MODULE) -#ifdef CONFIG_BFIN_SIR0 -static struct resource bfin_sir0_resources[] = { - { - .start = 0xFFC00400, - .end = 0xFFC004FF, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_UART0_RX, - .end = IRQ_UART0_RX+1, - .flags = IORESOURCE_IRQ, - }, - { - .start = CH_UART0_RX, - .end = CH_UART0_RX+1, - .flags = IORESOURCE_DMA, - }, -}; - -static struct platform_device bfin_sir0_device = { - .name = "bfin_sir", - .id = 0, - .num_resources = ARRAY_SIZE(bfin_sir0_resources), - .resource = bfin_sir0_resources, -}; -#endif -#endif - -static struct platform_device *generic_board_devices[] __initdata = { -#if defined(CONFIG_RTC_DRV_BFIN) || defined(CONFIG_RTC_DRV_BFIN_MODULE) - &rtc_device, -#endif - -#if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE) - &smc91x_device, -#endif - -#if defined(CONFIG_BFIN_SIR) || defined(CONFIG_BFIN_SIR_MODULE) -#ifdef CONFIG_BFIN_SIR0 - &bfin_sir0_device, -#endif -#endif -}; - -static int __init generic_board_init(void) -{ - printk(KERN_INFO "%s(): registering device resources\n", __func__); - return platform_add_devices(generic_board_devices, ARRAY_SIZE(generic_board_devices)); -} - -arch_initcall(generic_board_init); diff --git a/arch/blackfin/mach-bf533/boards/ip0x.c b/arch/blackfin/mach-bf533/boards/ip0x.c index e30b1b7..f19b633 100644 --- a/arch/blackfin/mach-bf533/boards/ip0x.c +++ b/arch/blackfin/mach-bf533/boards/ip0x.c @@ -127,8 +127,8 @@ static struct platform_device dm9000_device2 = { #if defined(CONFIG_SPI_BFIN) || defined(CONFIG_SPI_BFIN_MODULE) /* all SPI peripherals info goes here */ -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { /* * CPOL (Clock Polarity) * 0 - Active high SCK @@ -152,14 +152,13 @@ static struct bfin5xx_spi_chip spi_mmc_chip_info = { /* Notice: for blackfin, the speed_hz is the value of register * SPI_BAUD, not the real baudrate */ static struct spi_board_info bfin_spi_board_info[] __initdata = { -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", + .modalias = "mmc_spi", .max_speed_hz = 2, .bus_num = 1, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, }, #endif }; diff --git a/arch/blackfin/mach-bf533/include/mach/anomaly.h b/arch/blackfin/mach-bf533/include/mach/anomaly.h index 0d3a034..1cf893e 100644 --- a/arch/blackfin/mach-bf533/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf533/include/mach/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf533/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ @@ -160,7 +160,7 @@ #define ANOMALY_05000301 (__SILICON_REVISION__ < 6) /* SSYNCs After Writes To DMA MMR Registers May Not Be Handled Correctly */ #define ANOMALY_05000302 (__SILICON_REVISION__ < 5) -/* New Feature: Additional Hysteresis on SPORT Input Pins (Not Available On Older Silicon) */ +/* SPORT_HYS Bit in PLL_CTL Register Is Not Functional */ #define ANOMALY_05000305 (__SILICON_REVISION__ < 5) /* New Feature: Additional PPI Frame Sync Sampling Options (Not Available On Older Silicon) */ #define ANOMALY_05000306 (__SILICON_REVISION__ < 5) @@ -278,9 +278,12 @@ #define ANOMALY_05000266 (0) #define ANOMALY_05000323 (0) #define ANOMALY_05000353 (1) +#define ANOMALY_05000380 (0) #define ANOMALY_05000386 (1) #define ANOMALY_05000412 (0) #define ANOMALY_05000432 (0) #define ANOMALY_05000435 (0) +#define ANOMALY_05000447 (0) +#define ANOMALY_05000448 (0) #endif diff --git a/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h index f3d9e49..5f517f5 100644 --- a/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h @@ -134,7 +134,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART_TX, CH_UART_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif diff --git a/arch/blackfin/mach-bf537/boards/Kconfig b/arch/blackfin/mach-bf537/boards/Kconfig index 42a57b0..77c59da 100644 --- a/arch/blackfin/mach-bf537/boards/Kconfig +++ b/arch/blackfin/mach-bf537/boards/Kconfig @@ -33,9 +33,4 @@ config CAMSIG_MINOTAUR help Board supply package for CSP Minotaur -config GENERIC_BF537_BOARD - bool "Generic" - help - Generic or Custom board support. - endchoice diff --git a/arch/blackfin/mach-bf537/boards/Makefile b/arch/blackfin/mach-bf537/boards/Makefile index 7168cc1..68b98a7a 100644 --- a/arch/blackfin/mach-bf537/boards/Makefile +++ b/arch/blackfin/mach-bf537/boards/Makefile @@ -2,7 +2,6 @@ # arch/blackfin/mach-bf537/boards/Makefile # -obj-$(CONFIG_GENERIC_BF537_BOARD) += generic_board.o obj-$(CONFIG_BFIN537_STAMP) += stamp.o obj-$(CONFIG_BFIN537_BLUETECHNIX_CM) += cm_bf537.o obj-$(CONFIG_BFIN537_BLUETECHNIX_TCM) += tcm_bf537.o diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537.c b/arch/blackfin/mach-bf537/boards/cm_bf537.c index 9cd8fb2..41c75b9 100644 --- a/arch/blackfin/mach-bf537/boards/cm_bf537.c +++ b/arch/blackfin/mach-bf537/boards/cm_bf537.c @@ -108,9 +108,9 @@ static struct bfin5xx_spi_chip ad9960_spi_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -160,23 +160,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) - { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 7, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ + .modalias = "mmc_spi", + .max_speed_hz = 20000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 1, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf537/boards/generic_board.c b/arch/blackfin/mach-bf537/boards/generic_board.c deleted file mode 100644 index da710fd..0000000 --- a/arch/blackfin/mach-bf537/boards/generic_board.c +++ /dev/null @@ -1,745 +0,0 @@ -/* - * File: arch/blackfin/mach-bf537/boards/generic_board.c - * Based on: arch/blackfin/mach-bf533/boards/ezkit.c - * Author: Aidan Williams <aidan@nicta.com.au> - * - * Created: - * Description: - * - * Modified: - * Copyright 2005 National ICT Australia (NICTA) - * Copyright 2004-2008 Analog Devices Inc. - * - * Bugs: Enter bugs at http://blackfin.uclinux.org/ - * - * 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, see the file COPYING, or write - * to the Free Software Foundation, Inc., - * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ - -#include <linux/device.h> -#include <linux/etherdevice.h> -#include <linux/platform_device.h> -#include <linux/mtd/mtd.h> -#include <linux/mtd/partitions.h> -#include <linux/spi/spi.h> -#include <linux/spi/flash.h> -#if defined(CONFIG_USB_ISP1362_HCD) || defined(CONFIG_USB_ISP1362_HCD_MODULE) -#include <linux/usb/isp1362.h> -#endif -#include <linux/irq.h> -#include <linux/interrupt.h> -#include <linux/usb/sl811.h> -#include <asm/dma.h> -#include <asm/bfin5xx_spi.h> -#include <asm/reboot.h> -#include <asm/portmux.h> -#include <linux/spi/ad7877.h> - -/* - * Name the Board for the /proc/cpuinfo - */ -const char bfin_board_name[] = "UNKNOWN BOARD"; - -/* - * Driver needs to know address, irq and flag pin. - */ - -#if defined(CONFIG_USB_ISP1760_HCD) || defined(CONFIG_USB_ISP1760_HCD_MODULE) -#include <linux/usb/isp1760.h> -static struct resource bfin_isp1760_resources[] = { - [0] = { - .start = 0x203C0000, - .end = 0x203C0000 + 0x000fffff, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_PF7, - .end = IRQ_PF7, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct isp1760_platform_data isp1760_priv = { - .is_isp1761 = 0, - .port1_disable = 0, - .bus_width_16 = 1, - .port1_otg = 0, - .analog_oc = 0, - .dack_polarity_high = 0, - .dreq_polarity_high = 0, -}; - -static struct platform_device bfin_isp1760_device = { - .name = "isp1760-hcd", - .id = 0, - .dev = { - .platform_data = &isp1760_priv, - }, - .num_resources = ARRAY_SIZE(bfin_isp1760_resources), - .resource = bfin_isp1760_resources, -}; -#endif - -#if defined(CONFIG_BFIN_CFPCMCIA) || defined(CONFIG_BFIN_CFPCMCIA_MODULE) -static struct resource bfin_pcmcia_cf_resources[] = { - { - .start = 0x20310000, /* IO PORT */ - .end = 0x20312000, - .flags = IORESOURCE_MEM, - }, { - .start = 0x20311000, /* Attribute Memory */ - .end = 0x20311FFF, - .flags = IORESOURCE_MEM, - }, { - .start = IRQ_PF4, - .end = IRQ_PF4, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_LOWLEVEL, - }, { - .start = 6, /* Card Detect PF6 */ - .end = 6, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device bfin_pcmcia_cf_device = { - .name = "bfin_cf_pcmcia", - .id = -1, - .num_resources = ARRAY_SIZE(bfin_pcmcia_cf_resources), - .resource = bfin_pcmcia_cf_resources, -}; -#endif - -#if defined(CONFIG_RTC_DRV_BFIN) || defined(CONFIG_RTC_DRV_BFIN_MODULE) -static struct platform_device rtc_device = { - .name = "rtc-bfin", - .id = -1, -}; -#endif - -#if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE) -static struct resource smc91x_resources[] = { - { - .name = "smc91x-regs", - .start = 0x20300300, - .end = 0x20300300 + 16, - .flags = IORESOURCE_MEM, - }, { - - .start = IRQ_PF7, - .end = IRQ_PF7, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, -}; -static struct platform_device smc91x_device = { - .name = "smc91x", - .id = 0, - .num_resources = ARRAY_SIZE(smc91x_resources), - .resource = smc91x_resources, -}; -#endif - -#if defined(CONFIG_DM9000) || defined(CONFIG_DM9000_MODULE) -static struct resource dm9000_resources[] = { - [0] = { - .start = 0x203FB800, - .end = 0x203FB800 + 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = 0x203FB800 + 4, - .end = 0x203FB800 + 5, - .flags = IORESOURCE_MEM, - }, - [2] = { - .start = IRQ_PF9, - .end = IRQ_PF9, - .flags = (IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE), - }, -}; - -static struct platform_device dm9000_device = { - .name = "dm9000", - .id = -1, - .num_resources = ARRAY_SIZE(dm9000_resources), - .resource = dm9000_resources, -}; -#endif - -#if defined(CONFIG_USB_SL811_HCD) || defined(CONFIG_USB_SL811_HCD_MODULE) -static struct resource sl811_hcd_resources[] = { - { - .start = 0x20340000, - .end = 0x20340000, - .flags = IORESOURCE_MEM, - }, { - .start = 0x20340004, - .end = 0x20340004, - .flags = IORESOURCE_MEM, - }, { - .start = CONFIG_USB_SL811_BFIN_IRQ, - .end = CONFIG_USB_SL811_BFIN_IRQ, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, -}; - -#if defined(CONFIG_USB_SL811_BFIN_USE_VBUS) -void sl811_port_power(struct device *dev, int is_on) -{ - gpio_request(CONFIG_USB_SL811_BFIN_GPIO_VBUS, "usb:SL811_VBUS"); - gpio_direction_output(CONFIG_USB_SL811_BFIN_GPIO_VBUS, is_on); - -} -#endif - -static struct sl811_platform_data sl811_priv = { - .potpg = 10, - .power = 250, /* == 500mA */ -#if defined(CONFIG_USB_SL811_BFIN_USE_VBUS) - .port_power = &sl811_port_power, -#endif -}; - -static struct platform_device sl811_hcd_device = { - .name = "sl811-hcd", - .id = 0, - .dev = { - .platform_data = &sl811_priv, - }, - .num_resources = ARRAY_SIZE(sl811_hcd_resources), - .resource = sl811_hcd_resources, -}; -#endif - -#if defined(CONFIG_USB_ISP1362_HCD) || defined(CONFIG_USB_ISP1362_HCD_MODULE) -static struct resource isp1362_hcd_resources[] = { - { - .start = 0x20360000, - .end = 0x20360000, - .flags = IORESOURCE_MEM, - }, { - .start = 0x20360004, - .end = 0x20360004, - .flags = IORESOURCE_MEM, - }, { - .start = CONFIG_USB_ISP1362_BFIN_GPIO_IRQ, - .end = CONFIG_USB_ISP1362_BFIN_GPIO_IRQ, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, -}; - -static struct isp1362_platform_data isp1362_priv = { - .sel15Kres = 1, - .clknotstop = 0, - .oc_enable = 0, - .int_act_high = 0, - .int_edge_triggered = 0, - .remote_wakeup_connected = 0, - .no_power_switching = 1, - .power_switching_mode = 0, -}; - -static struct platform_device isp1362_hcd_device = { - .name = "isp1362-hcd", - .id = 0, - .dev = { - .platform_data = &isp1362_priv, - }, - .num_resources = ARRAY_SIZE(isp1362_hcd_resources), - .resource = isp1362_hcd_resources, -}; -#endif - -#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) -static struct platform_device bfin_mii_bus = { - .name = "bfin_mii_bus", -}; - -static struct platform_device bfin_mac_device = { - .name = "bfin_mac", - .dev.platform_data = &bfin_mii_bus, -}; -#endif - -#if defined(CONFIG_USB_NET2272) || defined(CONFIG_USB_NET2272_MODULE) -static struct resource net2272_bfin_resources[] = { - { - .start = 0x20300000, - .end = 0x20300000 + 0x100, - .flags = IORESOURCE_MEM, - }, { - .start = IRQ_PF7, - .end = IRQ_PF7, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, -}; - -static struct platform_device net2272_bfin_device = { - .name = "net2272", - .id = -1, - .num_resources = ARRAY_SIZE(net2272_bfin_resources), - .resource = net2272_bfin_resources, -}; -#endif - -#if defined(CONFIG_SPI_BFIN) || defined(CONFIG_SPI_BFIN_MODULE) -/* all SPI peripherals info goes here */ - -#if defined(CONFIG_MTD_M25P80) \ - || defined(CONFIG_MTD_M25P80_MODULE) -static struct mtd_partition bfin_spi_flash_partitions[] = { - { - .name = "bootloader(spi)", - .size = 0x00020000, - .offset = 0, - .mask_flags = MTD_CAP_ROM - }, { - .name = "linux kernel(spi)", - .size = 0xe0000, - .offset = 0x20000 - }, { - .name = "file system(spi)", - .size = 0x700000, - .offset = 0x00100000, - } -}; - -static struct flash_platform_data bfin_spi_flash_data = { - .name = "m25p80", - .parts = bfin_spi_flash_partitions, - .nr_parts = ARRAY_SIZE(bfin_spi_flash_partitions), - .type = "m25p64", -}; - -/* SPI flash chip (m25p64) */ -static struct bfin5xx_spi_chip spi_flash_chip_info = { - .enable_dma = 0, /* use dma transfer with this chip*/ - .bits_per_word = 8, -}; -#endif - -#if defined(CONFIG_SPI_ADC_BF533) \ - || defined(CONFIG_SPI_ADC_BF533_MODULE) -/* SPI ADC chip */ -static struct bfin5xx_spi_chip spi_adc_chip_info = { - .enable_dma = 1, /* use dma transfer with this chip*/ - .bits_per_word = 16, -}; -#endif - -#if defined(CONFIG_SND_BLACKFIN_AD1836) \ - || defined(CONFIG_SND_BLACKFIN_AD1836_MODULE) -static struct bfin5xx_spi_chip ad1836_spi_chip_info = { - .enable_dma = 0, - .bits_per_word = 16, -}; -#endif - -#if defined(CONFIG_AD9960) || defined(CONFIG_AD9960_MODULE) -static struct bfin5xx_spi_chip ad9960_spi_chip_info = { - .enable_dma = 0, - .bits_per_word = 16, -}; -#endif - -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, - .bits_per_word = 8, -}; -#endif - -#if defined(CONFIG_PBX) -static struct bfin5xx_spi_chip spi_si3xxx_chip_info = { - .ctl_reg = 0x4, /* send zero */ - .enable_dma = 0, - .bits_per_word = 8, - .cs_change_per_word = 1, -}; -#endif - -#if defined(CONFIG_TOUCHSCREEN_AD7877) || defined(CONFIG_TOUCHSCREEN_AD7877_MODULE) -static struct bfin5xx_spi_chip spi_ad7877_chip_info = { - .enable_dma = 0, - .bits_per_word = 16, -}; - -static const struct ad7877_platform_data bfin_ad7877_ts_info = { - .model = 7877, - .vref_delay_usecs = 50, /* internal, no capacitor */ - .x_plate_ohms = 419, - .y_plate_ohms = 486, - .pressure_max = 1000, - .pressure_min = 0, - .stopacq_polarity = 1, - .first_conversion_delay = 3, - .acquisition_time = 1, - .averaging = 1, - .pen_down_acc_interval = 1, -}; -#endif - -static struct spi_board_info bfin_spi_board_info[] __initdata = { -#if defined(CONFIG_MTD_M25P80) \ - || defined(CONFIG_MTD_M25P80_MODULE) - { - /* the modalias must be the same as spi device driver name */ - .modalias = "m25p80", /* Name of spi_driver for this device */ - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, /* Framework bus number */ - .chip_select = 1, /* Framework chip select. On STAMP537 it is SPISSEL1*/ - .platform_data = &bfin_spi_flash_data, - .controller_data = &spi_flash_chip_info, - .mode = SPI_MODE_3, - }, -#endif - -#if defined(CONFIG_SPI_ADC_BF533) \ - || defined(CONFIG_SPI_ADC_BF533_MODULE) - { - .modalias = "bfin_spi_adc", /* Name of spi_driver for this device */ - .max_speed_hz = 6250000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, /* Framework bus number */ - .chip_select = 1, /* Framework chip select. */ - .platform_data = NULL, /* No spi_driver specific config */ - .controller_data = &spi_adc_chip_info, - }, -#endif - -#if defined(CONFIG_SND_BLACKFIN_AD1836) \ - || defined(CONFIG_SND_BLACKFIN_AD1836_MODULE) - { - .modalias = "ad1836-spi", - .max_speed_hz = 3125000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = CONFIG_SND_BLACKFIN_SPI_PFBIT, - .controller_data = &ad1836_spi_chip_info, - }, -#endif -#if defined(CONFIG_AD9960) || defined(CONFIG_AD9960_MODULE) - { - .modalias = "ad9960-spi", - .max_speed_hz = 10000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 1, - .controller_data = &ad9960_spi_chip_info, - }, -#endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) - { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, - { - .modalias = "spi_mmc", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, -#endif -#if defined(CONFIG_PBX) - { - .modalias = "fxs-spi", - .max_speed_hz = 12500000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 8 - CONFIG_J11_JUMPER, - .controller_data = &spi_si3xxx_chip_info, - .mode = SPI_MODE_3, - }, - { - .modalias = "fxo-spi", - .max_speed_hz = 12500000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 8 - CONFIG_J19_JUMPER, - .controller_data = &spi_si3xxx_chip_info, - .mode = SPI_MODE_3, - }, -#endif -#if defined(CONFIG_TOUCHSCREEN_AD7877) || defined(CONFIG_TOUCHSCREEN_AD7877_MODULE) - { - .modalias = "ad7877", - .platform_data = &bfin_ad7877_ts_info, - .irq = IRQ_PF6, - .max_speed_hz = 12500000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 1, - .controller_data = &spi_ad7877_chip_info, - }, -#endif -}; - -/* SPI controller data */ -static struct bfin5xx_spi_master bfin_spi0_info = { - .num_chipselect = 8, - .enable_dma = 1, /* master has the ability to do dma transfer */ - .pin_req = {P_SPI0_SCK, P_SPI0_MISO, P_SPI0_MOSI, 0}, -}; - -/* SPI (0) */ -static struct resource bfin_spi0_resource[] = { - [0] = { - .start = SPI0_REGBASE, - .end = SPI0_REGBASE + 0xFF, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = CH_SPI, - .end = CH_SPI, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device bfin_spi0_device = { - .name = "bfin-spi", - .id = 0, /* Bus number */ - .num_resources = ARRAY_SIZE(bfin_spi0_resource), - .resource = bfin_spi0_resource, - .dev = { - .platform_data = &bfin_spi0_info, /* Passed to driver */ - }, -}; -#endif /* spi master and devices */ - -#if defined(CONFIG_FB_BF537_LQ035) || defined(CONFIG_FB_BF537_LQ035_MODULE) -static struct platform_device bfin_fb_device = { - .name = "bf537-lq035", -}; -#endif - -#if defined(CONFIG_FB_BFIN_7393) || defined(CONFIG_FB_BFIN_7393_MODULE) -static struct platform_device bfin_fb_adv7393_device = { - .name = "bfin-adv7393", -}; -#endif - -#if defined(CONFIG_SERIAL_BFIN) || defined(CONFIG_SERIAL_BFIN_MODULE) -static struct resource bfin_uart_resources[] = { - { - .start = 0xFFC00400, - .end = 0xFFC004FF, - .flags = IORESOURCE_MEM, - }, { - .start = 0xFFC02000, - .end = 0xFFC020FF, - .flags = IORESOURCE_MEM, - }, -}; - -static struct platform_device bfin_uart_device = { - .name = "bfin-uart", - .id = 1, - .num_resources = ARRAY_SIZE(bfin_uart_resources), - .resource = bfin_uart_resources, -}; -#endif - -#if defined(CONFIG_BFIN_SIR) || defined(CONFIG_BFIN_SIR_MODULE) -#ifdef CONFIG_BFIN_SIR0 -static struct resource bfin_sir0_resources[] = { - { - .start = 0xFFC00400, - .end = 0xFFC004FF, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_UART0_RX, - .end = IRQ_UART0_RX+1, - .flags = IORESOURCE_IRQ, - }, - { - .start = CH_UART0_RX, - .end = CH_UART0_RX+1, - .flags = IORESOURCE_DMA, - }, -}; - -static struct platform_device bfin_sir0_device = { - .name = "bfin_sir", - .id = 0, - .num_resources = ARRAY_SIZE(bfin_sir0_resources), - .resource = bfin_sir0_resources, -}; -#endif -#ifdef CONFIG_BFIN_SIR1 -static struct resource bfin_sir1_resources[] = { - { - .start = 0xFFC02000, - .end = 0xFFC020FF, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_UART1_RX, - .end = IRQ_UART1_RX+1, - .flags = IORESOURCE_IRQ, - }, - { - .start = CH_UART1_RX, - .end = CH_UART1_RX+1, - .flags = IORESOURCE_DMA, - }, -}; - -static struct platform_device bfin_sir1_device = { - .name = "bfin_sir", - .id = 1, - .num_resources = ARRAY_SIZE(bfin_sir1_resources), - .resource = bfin_sir1_resources, -}; -#endif -#endif - -#if defined(CONFIG_I2C_BLACKFIN_TWI) || defined(CONFIG_I2C_BLACKFIN_TWI_MODULE) -static struct resource bfin_twi0_resource[] = { - [0] = { - .start = TWI0_REGBASE, - .end = TWI0_REGBASE + 0xFF, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_TWI, - .end = IRQ_TWI, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device i2c_bfin_twi_device = { - .name = "i2c-bfin-twi", - .id = 0, - .num_resources = ARRAY_SIZE(bfin_twi0_resource), - .resource = bfin_twi0_resource, -}; -#endif - -#if defined(CONFIG_SERIAL_BFIN_SPORT) || defined(CONFIG_SERIAL_BFIN_SPORT_MODULE) -static struct platform_device bfin_sport0_uart_device = { - .name = "bfin-sport-uart", - .id = 0, -}; - -static struct platform_device bfin_sport1_uart_device = { - .name = "bfin-sport-uart", - .id = 1, -}; -#endif - -static struct platform_device *stamp_devices[] __initdata = { -#if defined(CONFIG_BFIN_CFPCMCIA) || defined(CONFIG_BFIN_CFPCMCIA_MODULE) - &bfin_pcmcia_cf_device, -#endif - -#if defined(CONFIG_RTC_DRV_BFIN) || defined(CONFIG_RTC_DRV_BFIN_MODULE) - &rtc_device, -#endif - -#if defined(CONFIG_USB_SL811_HCD) || defined(CONFIG_USB_SL811_HCD_MODULE) - &sl811_hcd_device, -#endif - -#if defined(CONFIG_USB_ISP1362_HCD) || defined(CONFIG_USB_ISP1362_HCD_MODULE) - &isp1362_hcd_device, -#endif - -#if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE) - &smc91x_device, -#endif - -#if defined(CONFIG_DM9000) || defined(CONFIG_DM9000_MODULE) - &dm9000_device, -#endif - -#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) - &bfin_mii_bus, - &bfin_mac_device, -#endif - -#if defined(CONFIG_USB_NET2272) || defined(CONFIG_USB_NET2272_MODULE) - &net2272_bfin_device, -#endif - -#if defined(CONFIG_USB_ISP1760_HCD) || defined(CONFIG_USB_ISP1760_HCD_MODULE) - &bfin_isp1760_device, -#endif - -#if defined(CONFIG_SPI_BFIN) || defined(CONFIG_SPI_BFIN_MODULE) - &bfin_spi0_device, -#endif - -#if defined(CONFIG_FB_BF537_LQ035) || defined(CONFIG_FB_BF537_LQ035_MODULE) - &bfin_fb_device, -#endif - -#if defined(CONFIG_FB_BFIN_7393) || defined(CONFIG_FB_BFIN_7393_MODULE) - &bfin_fb_adv7393_device, -#endif - -#if defined(CONFIG_SERIAL_BFIN) || defined(CONFIG_SERIAL_BFIN_MODULE) - &bfin_uart_device, -#endif - -#if defined(CONFIG_BFIN_SIR) || defined(CONFIG_BFIN_SIR_MODULE) -#ifdef CONFIG_BFIN_SIR0 - &bfin_sir0_device, -#endif -#ifdef CONFIG_BFIN_SIR1 - &bfin_sir1_device, -#endif -#endif - -#if defined(CONFIG_I2C_BLACKFIN_TWI) || defined(CONFIG_I2C_BLACKFIN_TWI_MODULE) - &i2c_bfin_twi_device, -#endif - -#if defined(CONFIG_SERIAL_BFIN_SPORT) || defined(CONFIG_SERIAL_BFIN_SPORT_MODULE) - &bfin_sport0_uart_device, - &bfin_sport1_uart_device, -#endif -}; - -static int __init generic_init(void) -{ - printk(KERN_INFO "%s(): registering device resources\n", __func__); - platform_add_devices(stamp_devices, ARRAY_SIZE(stamp_devices)); -#if defined(CONFIG_SPI_BFIN) || defined(CONFIG_SPI_BFIN_MODULE) - spi_register_board_info(bfin_spi_board_info, - ARRAY_SIZE(bfin_spi_board_info)); -#endif - - return 0; -} - -arch_initcall(generic_init); - -void native_machine_restart(char *cmd) -{ - /* workaround reboot hang when booting from SPI */ - if ((bfin_read_SYSCR() & 0x7) == 0x3) - bfin_reset_boot_spi_cs(P_DEFAULT_BOOT_SPI_CS); -} - -#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) -void bfin_get_ether_addr(char *addr) -{ - random_ether_addr(addr); - printk(KERN_WARNING "%s:%s: Setting Ethernet MAC to a random one\n", __FILE__, __func__); -} -EXPORT_SYMBOL(bfin_get_ether_addr); -#endif diff --git a/arch/blackfin/mach-bf537/boards/minotaur.c b/arch/blackfin/mach-bf537/boards/minotaur.c index db7d3a3..3c15981 100644 --- a/arch/blackfin/mach-bf537/boards/minotaur.c +++ b/arch/blackfin/mach-bf537/boards/minotaur.c @@ -134,9 +134,9 @@ static struct bfin5xx_spi_chip spi_flash_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -156,23 +156,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc_dummy", + .modalias = "mmc_spi", .max_speed_hz = 5000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, - { - .modalias = "spi_mmc", - .max_speed_hz = 5000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf537/boards/pnav10.c b/arch/blackfin/mach-bf537/boards/pnav10.c index 590eb3a..4e1de1e 100644 --- a/arch/blackfin/mach-bf537/boards/pnav10.c +++ b/arch/blackfin/mach-bf537/boards/pnav10.c @@ -289,9 +289,9 @@ static struct bfin5xx_spi_chip ad9960_spi_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -364,23 +364,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .controller_data = &ad9960_spi_chip_info, }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) - { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 7, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", + .modalias = "mmc_spi", .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf537/boards/tcm_bf537.c b/arch/blackfin/mach-bf537/boards/tcm_bf537.c index 3f4f203..53ad10f 100644 --- a/arch/blackfin/mach-bf537/boards/tcm_bf537.c +++ b/arch/blackfin/mach-bf537/boards/tcm_bf537.c @@ -108,9 +108,9 @@ static struct bfin5xx_spi_chip ad9960_spi_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -160,23 +160,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) - { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 7, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", + .modalias = "mmc_spi", .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf537/include/mach/anomaly.h b/arch/blackfin/mach-bf537/include/mach/anomaly.h index 9cb3912..1bfd80c 100644 --- a/arch/blackfin/mach-bf537/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf537/include/mach/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf537/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ @@ -110,7 +110,7 @@ #define ANOMALY_05000301 (1) /* SSYNCs After Writes To CAN/DMA MMR Registers Are Not Always Handled Correctly */ #define ANOMALY_05000304 (__SILICON_REVISION__ < 3) -/* New Feature: Additional Hysteresis on SPORT Input Pins (Not Available On Older Silicon) */ +/* SPORT_HYS Bit in PLL_CTL Register Is Not Functional */ #define ANOMALY_05000305 (__SILICON_REVISION__ < 3) /* SCKELOW Bit Does Not Maintain State Through Hibernate */ #define ANOMALY_05000307 (__SILICON_REVISION__ < 3) @@ -168,9 +168,12 @@ #define ANOMALY_05000323 (0) #define ANOMALY_05000353 (1) #define ANOMALY_05000363 (0) +#define ANOMALY_05000380 (0) #define ANOMALY_05000386 (1) #define ANOMALY_05000412 (0) #define ANOMALY_05000432 (0) #define ANOMALY_05000435 (0) +#define ANOMALY_05000447 (0) +#define ANOMALY_05000448 (0) #endif diff --git a/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h index b3f87e1..9e34700 100644 --- a/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h @@ -144,7 +144,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART0_TX, CH_UART0_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif @@ -158,7 +158,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART1_TX, CH_UART1_RX, #endif -#ifdef CONFIG_BFIN_UART1_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART1_CTS_PIN, CONFIG_UART1_RTS_PIN, #endif diff --git a/arch/blackfin/mach-bf538/include/mach/anomaly.h b/arch/blackfin/mach-bf538/include/mach/anomaly.h index e130b4f..3a56998 100644 --- a/arch/blackfin/mach-bf538/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf538/include/mach/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf538/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ @@ -120,13 +120,17 @@ #define ANOMALY_05000198 (0) #define ANOMALY_05000230 (0) #define ANOMALY_05000263 (0) +#define ANOMALY_05000305 (0) #define ANOMALY_05000311 (0) #define ANOMALY_05000323 (0) #define ANOMALY_05000353 (1) #define ANOMALY_05000363 (0) +#define ANOMALY_05000380 (0) #define ANOMALY_05000386 (1) #define ANOMALY_05000412 (0) #define ANOMALY_05000432 (0) #define ANOMALY_05000435 (0) +#define ANOMALY_05000447 (0) +#define ANOMALY_05000448 (0) #endif diff --git a/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h index 40503b6..3c2811e 100644 --- a/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h @@ -144,7 +144,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART0_TX, CH_UART0_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif @@ -158,7 +158,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART1_TX, CH_UART1_RX, #endif -#ifdef CONFIG_BFIN_UART1_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART1_CTS_PIN, CONFIG_UART1_RTS_PIN, #endif diff --git a/arch/blackfin/mach-bf548/include/mach/anomaly.h b/arch/blackfin/mach-bf548/include/mach/anomaly.h index 23d03c5..882e40c 100644 --- a/arch/blackfin/mach-bf548/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf548/include/mach/anomaly.h @@ -2,12 +2,12 @@ * File: include/asm-blackfin/mach-bf548/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ /* This file shoule be up to date with: - * - Revision G, 08/07/2008; ADSP-BF542/BF544/BF547/BF548/BF549 Blackfin Processor Anomaly List + * - Revision H, 01/16/2009; ADSP-BF542/BF544/BF547/BF548/BF549 Blackfin Processor Anomaly List */ #ifndef _MACH_ANOMALY_H_ @@ -91,8 +91,6 @@ #define ANOMALY_05000371 (__SILICON_REVISION__ < 2) /* USB DP/DM Data Pins May Lose State When Entering Hibernate */ #define ANOMALY_05000372 (__SILICON_REVISION__ < 1) -/* Mobile DDR Operation Not Functional */ -#define ANOMALY_05000377 (1) /* Security/Authentication Speedpath Causes Authentication To Fail To Initiate */ #define ANOMALY_05000378 (__SILICON_REVISION__ < 2) /* 16-Bit NAND FLASH Boot Mode Is Not Functional */ @@ -157,8 +155,22 @@ #define ANOMALY_05000429 (__SILICON_REVISION__ < 2) /* Software System Reset Corrupts PLL_LOCKCNT Register */ #define ANOMALY_05000430 (__SILICON_REVISION__ >= 2) +/* Incorrect Use of Stack in Lockbox Firmware During Authentication */ +#define ANOMALY_05000431 (__SILICON_REVISION__ < 3) +/* OTP Write Accesses Not Supported */ +#define ANOMALY_05000442 (__SILICON_REVISION__ < 1) /* IFLUSH Instruction at End of Hardware Loop Causes Infinite Stall */ #define ANOMALY_05000443 (1) +/* CDMAPRIO and L2DMAPRIO Bits in the SYSCR Register Are Not Functional */ +#define ANOMALY_05000446 (1) +/* UART IrDA Receiver Fails on Extended Bit Pulses */ +#define ANOMALY_05000447 (1) +/* DDR Clock Duty Cycle Spec Violation (tCH, tCL) */ +#define ANOMALY_05000448 (__SILICON_REVISION__ == 1) +/* Reduced Timing Margins on DDR Output Setup and Hold (tDS and tDH) */ +#define ANOMALY_05000449 (__SILICON_REVISION__ == 1) +/* USB DMA Mode 1 Short Packet Data Corruption */ +#define ANOMALY_05000450 (1 /* Anomalies that don't exist on this proc */ #define ANOMALY_05000125 (0) @@ -171,6 +183,8 @@ #define ANOMALY_05000263 (0) #define ANOMALY_05000266 (0) #define ANOMALY_05000273 (0) +#define ANOMALY_05000278 (0) +#define ANOMALY_05000305 (0) #define ANOMALY_05000307 (0) #define ANOMALY_05000311 (0) #define ANOMALY_05000323 (0) diff --git a/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h index e4cf35e..c05e79c 100644 --- a/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h @@ -63,7 +63,7 @@ #define UART_ENABLE_INTS(x, v) UART_SET_IER(x, v) #define UART_DISABLE_INTS(x) UART_CLEAR_IER(x, 0xF) -#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS) +#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART2_CTSRTS) # define CONFIG_SERIAL_BFIN_CTSRTS # ifndef CONFIG_UART0_CTS_PIN @@ -74,12 +74,12 @@ # define CONFIG_UART0_RTS_PIN -1 # endif -# ifndef CONFIG_UART1_CTS_PIN -# define CONFIG_UART1_CTS_PIN -1 +# ifndef CONFIG_UART2_CTS_PIN +# define CONFIG_UART2_CTS_PIN -1 # endif -# ifndef CONFIG_UART1_RTS_PIN -# define CONFIG_UART1_RTS_PIN -1 +# ifndef CONFIG_UART2_RTS_PIN +# define CONFIG_UART2_RTS_PIN -1 # endif #endif @@ -130,7 +130,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART0_TX, CH_UART0_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif @@ -144,6 +144,10 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART1_TX, CH_UART1_RX, #endif +#ifdef CONFIG_SERIAL_BFIN_CTSRTS + 0, + 0, +#endif }, #endif #ifdef CONFIG_SERIAL_BFIN_UART2 @@ -154,7 +158,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART2_TX, CH_UART2_RX, #endif -#ifdef CONFIG_BFIN_UART2_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART2_CTS_PIN, CONFIG_UART2_RTS_PIN, #endif @@ -168,6 +172,10 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART3_TX, CH_UART3_RX, #endif +#ifdef CONFIG_SERIAL_BFIN_CTSRTS + 0, + 0, +#endif }, #endif }; diff --git a/arch/blackfin/mach-bf548/include/mach/irq.h b/arch/blackfin/mach-bf548/include/mach/irq.h index 60299a7..f194625 100644 --- a/arch/blackfin/mach-bf548/include/mach/irq.h +++ b/arch/blackfin/mach-bf548/include/mach/irq.h @@ -123,8 +123,8 @@ Events (highest priority) EMU 0 #define IRQ_MXVR_ERROR BFIN_IRQ(51) /* MXVR Status (Error) Interrupt */ #define IRQ_MXVR_MSG BFIN_IRQ(52) /* MXVR Message Interrupt */ #define IRQ_MXVR_PKT BFIN_IRQ(53) /* MXVR Packet Interrupt */ -#define IRQ_EPP1_ERROR BFIN_IRQ(54) /* EPPI1 Error Interrupt */ -#define IRQ_EPP2_ERROR BFIN_IRQ(55) /* EPPI2 Error Interrupt */ +#define IRQ_EPPI1_ERROR BFIN_IRQ(54) /* EPPI1 Error Interrupt */ +#define IRQ_EPPI2_ERROR BFIN_IRQ(55) /* EPPI2 Error Interrupt */ #define IRQ_UART3_ERROR BFIN_IRQ(56) /* UART3 Status (Error) Interrupt */ #define IRQ_HOST_ERROR BFIN_IRQ(57) /* HOST Status (Error) Interrupt */ #define IRQ_PIXC_ERROR BFIN_IRQ(59) /* PIXC Status (Error) Interrupt */ @@ -361,8 +361,8 @@ Events (highest priority) EMU 0 #define IRQ_UART2_ERR IRQ_UART2_ERROR #define IRQ_CAN0_ERR IRQ_CAN0_ERROR #define IRQ_MXVR_ERR IRQ_MXVR_ERROR -#define IRQ_EPP1_ERR IRQ_EPP1_ERROR -#define IRQ_EPP2_ERR IRQ_EPP2_ERROR +#define IRQ_EPPI1_ERR IRQ_EPPI1_ERROR +#define IRQ_EPPI2_ERR IRQ_EPPI2_ERROR #define IRQ_UART3_ERR IRQ_UART3_ERROR #define IRQ_HOST_ERR IRQ_HOST_ERROR #define IRQ_PIXC_ERR IRQ_PIXC_ERROR diff --git a/arch/blackfin/mach-bf561/boards/Kconfig b/arch/blackfin/mach-bf561/boards/Kconfig index e41a67b..e4bc6d7 100644 --- a/arch/blackfin/mach-bf561/boards/Kconfig +++ b/arch/blackfin/mach-bf561/boards/Kconfig @@ -19,9 +19,4 @@ config BFIN561_BLUETECHNIX_CM help CM-BF561 support for EVAL- and DEV-Board. -config GENERIC_BF561_BOARD - bool "Generic" - help - Generic or Custom board support. - endchoice diff --git a/arch/blackfin/mach-bf561/boards/Makefile b/arch/blackfin/mach-bf561/boards/Makefile index 04add01..3a15255 100644 --- a/arch/blackfin/mach-bf561/boards/Makefile +++ b/arch/blackfin/mach-bf561/boards/Makefile @@ -2,7 +2,6 @@ # arch/blackfin/mach-bf561/boards/Makefile # -obj-$(CONFIG_GENERIC_BF561_BOARD) += generic_board.o obj-$(CONFIG_BFIN561_BLUETECHNIX_CM) += cm_bf561.o obj-$(CONFIG_BFIN561_EZKIT) += ezkit.o obj-$(CONFIG_BFIN561_TEPLA) += tepla.o diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c index 6880d1e..f623c6b 100644 --- a/arch/blackfin/mach-bf561/boards/cm_bf561.c +++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c @@ -105,9 +105,9 @@ static struct bfin5xx_spi_chip ad9960_spi_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -155,14 +155,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .controller_data = &ad9960_spi_chip_info, }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", + .modalias = "mmc_spi", .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf561/boards/generic_board.c b/arch/blackfin/mach-bf561/boards/generic_board.c deleted file mode 100644 index 0ba366a..0000000 --- a/arch/blackfin/mach-bf561/boards/generic_board.c +++ /dev/null @@ -1,113 +0,0 @@ -/* - * File: arch/blackfin/mach-bf561/generic_board.c - * Based on: arch/blackfin/mach-bf533/ezkit.c - * Author: Aidan Williams <aidan@nicta.com.au> - * - * Created: - * Description: - * - * Modified: - * Copyright 2005 National ICT Australia (NICTA) - * Copyright 2004-2006 Analog Devices Inc. - * - * Bugs: Enter bugs at http://blackfin.uclinux.org/ - * - * 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, see the file COPYING, or write - * to the Free Software Foundation, Inc., - * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ - -#include <linux/device.h> -#include <linux/platform_device.h> -#include <linux/irq.h> - -const char bfin_board_name[] = "UNKNOWN BOARD"; - -/* - * Driver needs to know address, irq and flag pin. - */ -#if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE) -static struct resource smc91x_resources[] = { - { - .start = 0x2C010300, - .end = 0x2C010300 + 16, - .flags = IORESOURCE_MEM, - }, { - .start = IRQ_PROG_INTB, - .end = IRQ_PROG_INTB, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, { - .start = IRQ_PF9, - .end = IRQ_PF9, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, -}; - -static struct platform_device smc91x_device = { - .name = "smc91x", - .id = 0, - .num_resources = ARRAY_SIZE(smc91x_resources), - .resource = smc91x_resources, -}; -#endif - -#if defined(CONFIG_BFIN_SIR) || defined(CONFIG_BFIN_SIR_MODULE) -#ifdef CONFIG_BFIN_SIR0 -static struct resource bfin_sir0_resources[] = { - { - .start = 0xFFC00400, - .end = 0xFFC004FF, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_UART0_RX, - .end = IRQ_UART0_RX+1, - .flags = IORESOURCE_IRQ, - }, - { - .start = CH_UART0_RX, - .end = CH_UART0_RX+1, - .flags = IORESOURCE_DMA, - }, -}; - -static struct platform_device bfin_sir0_device = { - .name = "bfin_sir", - .id = 0, - .num_resources = ARRAY_SIZE(bfin_sir0_resources), - .resource = bfin_sir0_resources, -}; -#endif -#endif - -static struct platform_device *generic_board_devices[] __initdata = { -#if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE) - &smc91x_device, -#endif - -#if defined(CONFIG_BFIN_SIR) || defined(CONFIG_BFIN_SIR_MODULE) -#ifdef CONFIG_BFIN_SIR0 - &bfin_sir0_device, -#endif -#endif -}; - -static int __init generic_board_init(void) -{ - printk(KERN_INFO "%s(): registering device resources\n", __func__); - return platform_add_devices(generic_board_devices, - ARRAY_SIZE(generic_board_devices)); -} - -arch_initcall(generic_board_init); diff --git a/arch/blackfin/mach-bf561/include/mach/anomaly.h b/arch/blackfin/mach-bf561/include/mach/anomaly.h index 1a9e175..d0b0b35 100644 --- a/arch/blackfin/mach-bf561/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf561/include/mach/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf561/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ @@ -224,7 +224,7 @@ #define ANOMALY_05000301 (1) /* SSYNCs After Writes To DMA MMR Registers May Not Be Handled Correctly */ #define ANOMALY_05000302 (1) -/* New Feature: Additional Hysteresis on SPORT Input Pins (Not Available On Older Silicon) */ +/* SPORT_HYS Bit in PLL_CTL Register Is Not Functional */ #define ANOMALY_05000305 (__SILICON_REVISION__ < 5) /* SCKELOW Bit Does Not Maintain State Through Hibernate */ #define ANOMALY_05000307 (__SILICON_REVISION__ < 5) @@ -283,8 +283,11 @@ #define ANOMALY_05000273 (0) #define ANOMALY_05000311 (0) #define ANOMALY_05000353 (1) +#define ANOMALY_05000380 (0) #define ANOMALY_05000386 (1) #define ANOMALY_05000432 (0) #define ANOMALY_05000435 (0) +#define ANOMALY_05000447 (0) +#define ANOMALY_05000448 (0) #endif diff --git a/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h index 043bfcf..ca8c5f6 100644 --- a/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h @@ -134,7 +134,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART_TX, CH_UART_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif diff --git a/arch/blackfin/mach-common/arch_checks.c b/arch/blackfin/mach-common/arch_checks.c index 98133b9..80d39b2 100644 --- a/arch/blackfin/mach-common/arch_checks.c +++ b/arch/blackfin/mach-common/arch_checks.c @@ -62,3 +62,12 @@ #if (CONFIG_BOOT_LOAD & 0x3) # error "The kernel load address must be 4 byte aligned" #endif + +/* The entire kernel must be able to make a 24bit pcrel call to start of L1 */ +#if ((0xffffffff - L1_CODE_START + 1) + CONFIG_BOOT_LOAD) > 0x1000000 +# error "The kernel load address is too high; keep it below 10meg for safety" +#endif + +#if ANOMALY_05000448 +# error You are using a part with anomaly 05000448, this issue causes random memory read/write failures - that means random crashes. +#endif diff --git a/arch/blackfin/mach-common/cache.S b/arch/blackfin/mach-common/cache.S index 3c98dac..aa0648c 100644 --- a/arch/blackfin/mach-common/cache.S +++ b/arch/blackfin/mach-common/cache.S @@ -66,11 +66,33 @@ /* Invalidate all instruction cache lines assocoiated with this memory area */ ENTRY(_blackfin_icache_flush_range) +/* + * Walkaround to avoid loading wrong instruction after invalidating icache + * and following sequence is met. + * + * 1) One instruction address is cached in the instruction cache. + * 2) This instruction in SDRAM is changed. + * 3) IFLASH[P0] is executed only once in blackfin_icache_flush_range(). + * 4) This instruction is executed again, but the old one is loaded. + */ + P0 = R0; + IFLUSH[P0]; do_flush IFLUSH, , nop ENDPROC(_blackfin_icache_flush_range) /* Flush all cache lines assocoiated with this area of memory. */ ENTRY(_blackfin_icache_dcache_flush_range) +/* + * Walkaround to avoid loading wrong instruction after invalidating icache + * and following sequence is met. + * + * 1) One instruction address is cached in the instruction cache. + * 2) This instruction in SDRAM is changed. + * 3) IFLASH[P0] is executed only once in blackfin_icache_flush_range(). + * 4) This instruction is executed again, but the old one is loaded. + */ + P0 = R0; + IFLUSH[P0]; do_flush FLUSH, IFLUSH ENDPROC(_blackfin_icache_dcache_flush_range) diff --git a/arch/blackfin/mach-common/clocks-init.c b/arch/blackfin/mach-common/clocks-init.c index 9dddb6f..3539365 100644 --- a/arch/blackfin/mach-common/clocks-init.c +++ b/arch/blackfin/mach-common/clocks-init.c @@ -17,7 +17,7 @@ #define SDGCTL_WIDTH (1 << 31) /* SDRAM external data path width */ #define PLL_CTL_VAL \ (((CONFIG_VCO_MULT & 63) << 9) | CLKIN_HALF | \ - (PLL_BYPASS << 8) | (ANOMALY_05000265 ? 0x8000 : 0)) + (PLL_BYPASS << 8) | (ANOMALY_05000305 ? 0 : 0x8000)) __attribute__((l1_text)) static void do_sync(void) diff --git a/arch/blackfin/mach-common/dpmc_modes.S b/arch/blackfin/mach-common/dpmc_modes.S index 4da50bc..8009a51 100644 --- a/arch/blackfin/mach-common/dpmc_modes.S +++ b/arch/blackfin/mach-common/dpmc_modes.S @@ -376,10 +376,22 @@ ENTRY(_do_hibernate) #endif #ifdef PINT0_ASSIGN + PM_SYS_PUSH(PINT0_MASK_SET) + PM_SYS_PUSH(PINT1_MASK_SET) + PM_SYS_PUSH(PINT2_MASK_SET) + PM_SYS_PUSH(PINT3_MASK_SET) PM_SYS_PUSH(PINT0_ASSIGN) PM_SYS_PUSH(PINT1_ASSIGN) PM_SYS_PUSH(PINT2_ASSIGN) PM_SYS_PUSH(PINT3_ASSIGN) + PM_SYS_PUSH(PINT0_INVERT_SET) + PM_SYS_PUSH(PINT1_INVERT_SET) + PM_SYS_PUSH(PINT2_INVERT_SET) + PM_SYS_PUSH(PINT3_INVERT_SET) + PM_SYS_PUSH(PINT0_EDGE_SET) + PM_SYS_PUSH(PINT1_EDGE_SET) + PM_SYS_PUSH(PINT2_EDGE_SET) + PM_SYS_PUSH(PINT3_EDGE_SET) #endif PM_SYS_PUSH(EBIU_AMBCTL0) @@ -714,10 +726,22 @@ ENTRY(_do_hibernate) PM_SYS_POP(EBIU_AMBCTL0) #ifdef PINT0_ASSIGN + PM_SYS_POP(PINT3_EDGE_SET) + PM_SYS_POP(PINT2_EDGE_SET) + PM_SYS_POP(PINT1_EDGE_SET) + PM_SYS_POP(PINT0_EDGE_SET) + PM_SYS_POP(PINT3_INVERT_SET) + PM_SYS_POP(PINT2_INVERT_SET) + PM_SYS_POP(PINT1_INVERT_SET) + PM_SYS_POP(PINT0_INVERT_SET) PM_SYS_POP(PINT3_ASSIGN) PM_SYS_POP(PINT2_ASSIGN) PM_SYS_POP(PINT1_ASSIGN) PM_SYS_POP(PINT0_ASSIGN) + PM_SYS_POP(PINT3_MASK_SET) + PM_SYS_POP(PINT2_MASK_SET) + PM_SYS_POP(PINT1_MASK_SET) + PM_SYS_POP(PINT0_MASK_SET) #endif #ifdef SICA_IWR1 diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S index 88de053..21e65a3 100644 --- a/arch/blackfin/mach-common/entry.S +++ b/arch/blackfin/mach-common/entry.S @@ -600,6 +600,19 @@ ENTRY(_system_call) p2 = [p2]; [p2+(TASK_THREAD+THREAD_KSP)] = sp; +#ifdef CONFIG_IPIPE + r0 = sp; + SP += -12; + call ___ipipe_syscall_root; + SP += 12; + cc = r0 == 1; + if cc jump .Lsyscall_really_exit; + cc = r0 == -1; + if cc jump .Lresume_userspace; + r3 = [sp + PT_R3]; + r4 = [sp + PT_R4]; + p0 = [sp + PT_ORIG_P0]; +#endif /* CONFIG_IPIPE */ /* Check the System Call */ r7 = __NR_syscall; @@ -654,6 +667,17 @@ ENTRY(_system_call) r7 = r7 & r4; .Lsyscall_resched: +#ifdef CONFIG_IPIPE + cc = BITTST(r7, TIF_IRQ_SYNC); + if !cc jump .Lsyscall_no_irqsync; + [--sp] = reti; + r0 = [sp++]; + SP += -12; + call ___ipipe_sync_root; + SP += 12; + jump .Lresume_userspace_1; +.Lsyscall_no_irqsync: +#endif cc = BITTST(r7, TIF_NEED_RESCHED); if !cc jump .Lsyscall_sigpending; @@ -685,6 +709,10 @@ ENTRY(_system_call) .Lsyscall_really_exit: r5 = [sp + PT_RESERVED]; rets = r5; +#ifdef CONFIG_IPIPE + [--sp] = reti; + r5 = [sp++]; +#endif /* CONFIG_IPIPE */ rts; ENDPROC(_system_call) @@ -771,6 +799,15 @@ _new_old_task: ENDPROC(_resume) ENTRY(_ret_from_exception) +#ifdef CONFIG_IPIPE + [--sp] = rets; + SP += -12; + call ___ipipe_check_root + SP += 12 + rets = [sp++]; + cc = r0 == 0; + if cc jump 4f; /* not on behalf of Linux, get out */ +#endif /* CONFIG_IPIPE */ p2.l = lo(IPEND); p2.h = hi(IPEND); @@ -827,6 +864,28 @@ ENTRY(_ret_from_exception) rts; ENDPROC(_ret_from_exception) +#ifdef CONFIG_IPIPE + +_sync_root_irqs: + [--sp] = reti; /* Reenable interrupts */ + r0 = [sp++]; + jump.l ___ipipe_sync_root + +_resume_kernel_from_int: + r0.l = _sync_root_irqs + r0.h = _sync_root_irqs + [--sp] = rets; + [--sp] = ( r7:4, p5:3 ); + SP += -12; + call ___ipipe_call_irqtail + SP += 12; + ( r7:4, p5:3 ) = [sp++]; + rets = [sp++]; + rts +#else +#define _resume_kernel_from_int 2f +#endif + ENTRY(_return_from_int) /* If someone else already raised IRQ 15, do nothing. */ csync; @@ -848,7 +907,7 @@ ENTRY(_return_from_int) r1 = r0 - r1; r2 = r0 & r1; cc = r2 == 0; - if !cc jump 2f; + if !cc jump _resume_kernel_from_int; /* Lower the interrupt level to 15. */ p0.l = lo(EVT15); diff --git a/arch/blackfin/mach-common/interrupt.S b/arch/blackfin/mach-common/interrupt.S index 43c4eb9..0069c2d 100644 --- a/arch/blackfin/mach-common/interrupt.S +++ b/arch/blackfin/mach-common/interrupt.S @@ -235,6 +235,7 @@ ENDPROC(_evt_system_call) #ifdef CONFIG_IPIPE ENTRY(___ipipe_call_irqtail) + p0 = r0; r0.l = 1f; r0.h = 1f; reti = r0; @@ -242,9 +243,6 @@ ENTRY(___ipipe_call_irqtail) 1: [--sp] = rets; [--sp] = ( r7:4, p5:3 ); - p0.l = ___ipipe_irq_tail_hook; - p0.h = ___ipipe_irq_tail_hook; - p0 = [p0]; sp += -12; call (p0); sp += 12; @@ -259,7 +257,7 @@ ENTRY(___ipipe_call_irqtail) p0.h = hi(EVT14); [p0] = r0; csync; - r0 = 0x401f; + r0 = 0x401f (z); sti r0; raise 14; [--sp] = reti; /* IRQs on. */ @@ -277,11 +275,7 @@ ENTRY(___ipipe_call_irqtail) p0.h = _bfin_irq_flags; r0 = [p0]; sti r0; -#if 0 /* FIXME: this actually raises scheduling latencies */ - /* Reenable interrupts */ - [--sp] = reti; - r0 = [sp++]; -#endif rts; ENDPROC(___ipipe_call_irqtail) + #endif /* CONFIG_IPIPE */ diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c index 2024945..a7d7b2d 100644 --- a/arch/blackfin/mach-common/ints-priority.c +++ b/arch/blackfin/mach-common/ints-priority.c @@ -161,11 +161,15 @@ static void bfin_core_unmask_irq(unsigned int irq) static void bfin_internal_mask_irq(unsigned int irq) { + unsigned long flags; + #ifdef CONFIG_BF53x + local_irq_save_hw(flags); bfin_write_SIC_IMASK(bfin_read_SIC_IMASK() & ~(1 << SIC_SYSIRQ(irq))); #else unsigned mask_bank, mask_bit; + local_irq_save_hw(flags); mask_bank = SIC_SYSIRQ(irq) / 32; mask_bit = SIC_SYSIRQ(irq) % 32; bfin_write_SIC_IMASK(mask_bank, bfin_read_SIC_IMASK(mask_bank) & @@ -175,15 +179,20 @@ static void bfin_internal_mask_irq(unsigned int irq) ~(1 << mask_bit)); #endif #endif + local_irq_restore_hw(flags); } static void bfin_internal_unmask_irq(unsigned int irq) { + unsigned long flags; + #ifdef CONFIG_BF53x + local_irq_save_hw(flags); bfin_write_SIC_IMASK(bfin_read_SIC_IMASK() | (1 << SIC_SYSIRQ(irq))); #else unsigned mask_bank, mask_bit; + local_irq_save_hw(flags); mask_bank = SIC_SYSIRQ(irq) / 32; mask_bit = SIC_SYSIRQ(irq) % 32; bfin_write_SIC_IMASK(mask_bank, bfin_read_SIC_IMASK(mask_bank) | @@ -193,6 +202,7 @@ static void bfin_internal_unmask_irq(unsigned int irq) (1 << mask_bit)); #endif #endif + local_irq_restore_hw(flags); } #ifdef CONFIG_PM @@ -390,7 +400,7 @@ static void bfin_demux_error_irq(unsigned int int_err_irq, static inline void bfin_set_irq_handler(unsigned irq, irq_flow_handler_t handle) { #ifdef CONFIG_IPIPE - _set_irq_handler(irq, handle_edge_irq); + _set_irq_handler(irq, handle_level_irq); #else struct irq_desc *desc = irq_desc + irq; /* May not call generic set_irq_handler() due to spinlock @@ -1055,13 +1065,18 @@ int __init init_arch_irq(void) #endif default: #ifdef CONFIG_IPIPE - /* - * We want internal interrupt sources to be masked, because - * ISRs may trigger interrupts recursively (e.g. DMA), but - * interrupts are _not_ masked at CPU level. So let's handle - * them as level interrupts. - */ - set_irq_handler(irq, handle_level_irq); + /* + * We want internal interrupt sources to be + * masked, because ISRs may trigger interrupts + * recursively (e.g. DMA), but interrupts are + * _not_ masked at CPU level. So let's handle + * most of them as level interrupts, except + * the timer interrupt which is special. + */ + if (irq == IRQ_SYSTMR || irq == IRQ_CORETMR) + set_irq_handler(irq, handle_simple_irq); + else + set_irq_handler(irq, handle_level_irq); #else /* !CONFIG_IPIPE */ set_irq_handler(irq, handle_simple_irq); #endif /* !CONFIG_IPIPE */ @@ -1123,9 +1138,8 @@ int __init init_arch_irq(void) #ifdef CONFIG_IPIPE for (irq = 0; irq < NR_IRQS; irq++) { - struct irq_desc *desc = irq_desc + irq; + struct irq_desc *desc = irq_to_desc(irq); desc->ic_prio = __ipipe_get_irq_priority(irq); - desc->thr_prio = __ipipe_get_irqthread_priority(irq); } #endif /* CONFIG_IPIPE */ @@ -1208,76 +1222,21 @@ int __ipipe_get_irq_priority(unsigned irq) return IVG15; } -int __ipipe_get_irqthread_priority(unsigned irq) -{ - int ient, prio; - int demux_irq; - - /* The returned priority value is rescaled to [0..IVG13+1] - * with 0 being the lowest effective priority level. */ - - if (irq <= IRQ_CORETMR) - return IVG13 - irq + 1; - - /* GPIO IRQs are given the priority of the demux - * interrupt. */ - if (IS_GPIOIRQ(irq)) { -#if defined(CONFIG_BF54x) - u32 bank = PINT_2_BANK(irq2pint_lut[irq - SYS_IRQS]); - demux_irq = (bank == 0 ? IRQ_PINT0 : - bank == 1 ? IRQ_PINT1 : - bank == 2 ? IRQ_PINT2 : - IRQ_PINT3); -#elif defined(CONFIG_BF561) - demux_irq = (irq >= IRQ_PF32 ? IRQ_PROG2_INTA : - irq >= IRQ_PF16 ? IRQ_PROG1_INTA : - IRQ_PROG0_INTA); -#elif defined(CONFIG_BF52x) - demux_irq = (irq >= IRQ_PH0 ? IRQ_PORTH_INTA : - irq >= IRQ_PG0 ? IRQ_PORTG_INTA : - IRQ_PORTF_INTA); -#else - demux_irq = irq; -#endif - return IVG13 - PRIO_GPIODEMUX(demux_irq) + 1; - } - - /* The GPIO demux interrupt is given a lower priority - * than the GPIO IRQs, so that its threaded handler - * unmasks the interrupt line after the decoded IRQs - * have been processed. */ - prio = PRIO_GPIODEMUX(irq); - /* demux irq? */ - if (prio != -1) - return IVG13 - prio; - - for (ient = 0; ient < NR_PERI_INTS; ient++) { - struct ivgx *ivg = ivg_table + ient; - if (ivg->irqno == irq) { - for (prio = 0; prio <= IVG13-IVG7; prio++) { - if (ivg7_13[prio].ifirst <= ivg && - ivg7_13[prio].istop > ivg) - return IVG7 - prio; - } - } - } - - return 0; -} - /* Hw interrupts are disabled on entry (check SAVE_CONTEXT). */ #ifdef CONFIG_DO_IRQ_L1 __attribute__((l1_text)) #endif asmlinkage int __ipipe_grab_irq(int vec, struct pt_regs *regs) { + struct ipipe_percpu_domain_data *p = ipipe_root_cpudom_ptr(); + struct ipipe_domain *this_domain = ipipe_current_domain; struct ivgx *ivg_stop = ivg7_13[vec-IVG7].istop; struct ivgx *ivg = ivg7_13[vec-IVG7].ifirst; - int irq; + int irq, s; if (likely(vec == EVT_IVTMR_P)) { irq = IRQ_CORETMR; - goto handle_irq; + goto core_tick; } SSYNC(); @@ -1319,24 +1278,39 @@ asmlinkage int __ipipe_grab_irq(int vec, struct pt_regs *regs) irq = ivg->irqno; if (irq == IRQ_SYSTMR) { +#ifdef CONFIG_GENERIC_CLOCKEVENTS +core_tick: +#else bfin_write_TIMER_STATUS(1); /* Latch TIMIL0 */ +#endif /* This is basically what we need from the register frame. */ __raw_get_cpu_var(__ipipe_tick_regs).ipend = regs->ipend; __raw_get_cpu_var(__ipipe_tick_regs).pc = regs->pc; - if (!ipipe_root_domain_p) - __raw_get_cpu_var(__ipipe_tick_regs).ipend |= 0x10; - else + if (this_domain != ipipe_root_domain) __raw_get_cpu_var(__ipipe_tick_regs).ipend &= ~0x10; + else + __raw_get_cpu_var(__ipipe_tick_regs).ipend |= 0x10; } -handle_irq: +#ifndef CONFIG_GENERIC_CLOCKEVENTS +core_tick: +#endif + if (this_domain == ipipe_root_domain) { + s = __test_and_set_bit(IPIPE_SYNCDEFER_FLAG, &p->status); + barrier(); + } ipipe_trace_irq_entry(irq); __ipipe_handle_irq(irq, regs); - ipipe_trace_irq_exit(irq); + ipipe_trace_irq_exit(irq); - if (ipipe_root_domain_p) - return !test_bit(IPIPE_STALL_FLAG, &ipipe_root_cpudom_var(status)); + if (this_domain == ipipe_root_domain) { + set_thread_flag(TIF_IRQ_SYNC); + if (!s) { + __clear_bit(IPIPE_SYNCDEFER_FLAG, &p->status); + return !test_bit(IPIPE_STALL_FLAG, &p->status); + } + } return 0; } diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index 77c9928..93eab61 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -158,10 +158,14 @@ static irqreturn_t ipi_handler(int irq, void *dev_instance) kfree(msg); break; case BFIN_IPI_CALL_FUNC: + spin_unlock(&msg_queue->lock); ipi_call_function(cpu, msg); + spin_lock(&msg_queue->lock); break; case BFIN_IPI_CPU_STOP: + spin_unlock(&msg_queue->lock); ipi_cpu_stop(cpu); + spin_lock(&msg_queue->lock); kfree(msg); break; default: @@ -457,7 +461,7 @@ void smp_icache_flush_range_others(unsigned long start, unsigned long end) smp_flush_data.start = start; smp_flush_data.end = end; - if (smp_call_function(&ipi_flush_icache, &smp_flush_data, 1)) + if (smp_call_function(&ipi_flush_icache, &smp_flush_data, 0)) printk(KERN_WARNING "SMP: failed to run I-cache flush request on other CPUs\n"); } EXPORT_SYMBOL_GPL(smp_icache_flush_range_others); diff --git a/arch/blackfin/mm/init.c b/arch/blackfin/mm/init.c index d0532b7..9c3629b 100644 --- a/arch/blackfin/mm/init.c +++ b/arch/blackfin/mm/init.c @@ -104,7 +104,7 @@ void __init paging_init(void) } } -asmlinkage void init_pda(void) +asmlinkage void __init init_pda(void) { unsigned int cpu = raw_smp_processor_id(); diff --git a/arch/ia64/sn/pci/pcibr/pcibr_dma.c b/arch/ia64/sn/pci/pcibr/pcibr_dma.c index e626e50..060df4a 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_dma.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_dma.c @@ -135,11 +135,10 @@ pcibr_dmatrans_direct64(struct pcidev_info * info, u64 paddr, if (SN_DMA_ADDRTYPE(dma_flags) == SN_DMA_ADDR_PHYS) pci_addr = IS_PIC_SOFT(pcibus_info) ? PHYS_TO_DMA(paddr) : - PHYS_TO_TIODMA(paddr) | dma_attributes; + PHYS_TO_TIODMA(paddr); else - pci_addr = IS_PIC_SOFT(pcibus_info) ? - paddr : - paddr | dma_attributes; + pci_addr = paddr; + pci_addr |= dma_attributes; /* Handle Bus mode */ if (IS_PCIX(pcibus_info)) diff --git a/arch/m68knommu/platform/5206e/config.c b/arch/m68knommu/platform/5206e/config.c index d01a5d2..db90254 100644 --- a/arch/m68knommu/platform/5206e/config.c +++ b/arch/m68knommu/platform/5206e/config.c @@ -17,6 +17,7 @@ #include <asm/coldfire.h> #include <asm/mcfsim.h> #include <asm/mcfdma.h> +#include <asm/mcfuart.h> /***************************************************************************/ diff --git a/arch/m68knommu/platform/528x/config.c b/arch/m68knommu/platform/528x/config.c index dfdb5c2..44baeb2 100644 --- a/arch/m68knommu/platform/528x/config.c +++ b/arch/m68knommu/platform/528x/config.c @@ -24,7 +24,6 @@ #include <asm/coldfire.h> #include <asm/mcfsim.h> #include <asm/mcfuart.h> -#include <asm/mcfqspi.h> #ifdef CONFIG_MTD_PARTITIONS #include <linux/mtd/partitions.h> @@ -33,233 +32,6 @@ /***************************************************************************/ void coldfire_reset(void); -static void coldfire_qspi_cs_control(u8 cs, u8 command); - -/***************************************************************************/ - -#if defined(CONFIG_SPI) - -#if defined(CONFIG_WILDFIRE) -#define SPI_NUM_CHIPSELECTS 0x02 -#define SPI_PAR_VAL 0x07 /* Enable DIN, DOUT, CLK */ -#define SPI_CS_MASK 0x18 - -#define FLASH_BLOCKSIZE (1024*64) -#define FLASH_NUMBLOCKS 16 -#define FLASH_TYPE "m25p80" - -#define M25P80_CS 0 -#define MMC_CS 1 - -#ifdef CONFIG_MTD_PARTITIONS -static struct mtd_partition stm25p_partitions[] = { - /* sflash */ - [0] = { - .name = "stm25p80", - .offset = 0x00000000, - .size = FLASH_BLOCKSIZE * FLASH_NUMBLOCKS, - .mask_flags = 0 - } -}; - -#endif - -#elif defined(CONFIG_WILDFIREMOD) - -#define SPI_NUM_CHIPSELECTS 0x08 -#define SPI_PAR_VAL 0x07 /* Enable DIN, DOUT, CLK */ -#define SPI_CS_MASK 0x78 - -#define FLASH_BLOCKSIZE (1024*64) -#define FLASH_NUMBLOCKS 64 -#define FLASH_TYPE "m25p32" -/* Reserve 1M for the kernel parition */ -#define FLASH_KERNEL_SIZE (1024 * 1024) - -#define M25P80_CS 5 -#define MMC_CS 6 - -#ifdef CONFIG_MTD_PARTITIONS -static struct mtd_partition stm25p_partitions[] = { - /* sflash */ - [0] = { - .name = "kernel", - .offset = FLASH_BLOCKSIZE * FLASH_NUMBLOCKS - FLASH_KERNEL_SIZE, - .size = FLASH_KERNEL_SIZE, - .mask_flags = 0 - }, - [1] = { - .name = "image", - .offset = 0x00000000, - .size = FLASH_BLOCKSIZE * FLASH_NUMBLOCKS - FLASH_KERNEL_SIZE, - .mask_flags = 0 - }, - [2] = { - .name = "all", - .offset = 0x00000000, - .size = FLASH_BLOCKSIZE * FLASH_NUMBLOCKS, - .mask_flags = 0 - } -}; -#endif - -#else -#define SPI_NUM_CHIPSELECTS 0x04 -#define SPI_PAR_VAL 0x7F /* Enable DIN, DOUT, CLK, CS0 - CS4 */ -#endif - -#ifdef MMC_CS -static struct coldfire_spi_chip flash_chip_info = { - .mode = SPI_MODE_0, - .bits_per_word = 16, - .del_cs_to_clk = 17, - .del_after_trans = 1, - .void_write_data = 0 -}; - -static struct coldfire_spi_chip mmc_chip_info = { - .mode = SPI_MODE_0, - .bits_per_word = 16, - .del_cs_to_clk = 17, - .del_after_trans = 1, - .void_write_data = 0xFFFF -}; -#endif - -#ifdef M25P80_CS -static struct flash_platform_data stm25p80_platform_data = { - .name = "ST M25P80 SPI Flash chip", -#ifdef CONFIG_MTD_PARTITIONS - .parts = stm25p_partitions, - .nr_parts = sizeof(stm25p_partitions) / sizeof(*stm25p_partitions), -#endif - .type = FLASH_TYPE -}; -#endif - -static struct spi_board_info spi_board_info[] __initdata = { -#ifdef M25P80_CS - { - .modalias = "m25p80", - .max_speed_hz = 16000000, - .bus_num = 1, - .chip_select = M25P80_CS, - .platform_data = &stm25p80_platform_data, - .controller_data = &flash_chip_info - }, -#endif -#ifdef MMC_CS - { - .modalias = "mmc_spi", - .max_speed_hz = 16000000, - .bus_num = 1, - .chip_select = MMC_CS, - .controller_data = &mmc_chip_info - } -#endif -}; - -static struct coldfire_spi_master coldfire_master_info = { - .bus_num = 1, - .num_chipselect = SPI_NUM_CHIPSELECTS, - .irq_source = MCF5282_QSPI_IRQ_SOURCE, - .irq_vector = MCF5282_QSPI_IRQ_VECTOR, - .irq_mask = ((0x01 << MCF5282_QSPI_IRQ_SOURCE) | 0x01), - .irq_lp = 0x2B, /* Level 5 and Priority 3 */ - .par_val = SPI_PAR_VAL, - .cs_control = coldfire_qspi_cs_control, -}; - -static struct resource coldfire_spi_resources[] = { - [0] = { - .name = "qspi-par", - .start = MCF5282_QSPI_PAR, - .end = MCF5282_QSPI_PAR, - .flags = IORESOURCE_MEM - }, - - [1] = { - .name = "qspi-module", - .start = MCF5282_QSPI_QMR, - .end = MCF5282_QSPI_QMR + 0x18, - .flags = IORESOURCE_MEM - }, - - [2] = { - .name = "qspi-int-level", - .start = MCF5282_INTC0 + MCFINTC_ICR0 + MCF5282_QSPI_IRQ_SOURCE, - .end = MCF5282_INTC0 + MCFINTC_ICR0 + MCF5282_QSPI_IRQ_SOURCE, - .flags = IORESOURCE_MEM - }, - - [3] = { - .name = "qspi-int-mask", - .start = MCF5282_INTC0 + MCFINTC_IMRL, - .end = MCF5282_INTC0 + MCFINTC_IMRL, - .flags = IORESOURCE_MEM - } -}; - -static struct platform_device coldfire_spi = { - .name = "spi_coldfire", - .id = -1, - .resource = coldfire_spi_resources, - .num_resources = ARRAY_SIZE(coldfire_spi_resources), - .dev = { - .platform_data = &coldfire_master_info, - } -}; - -static void coldfire_qspi_cs_control(u8 cs, u8 command) -{ - u8 cs_bit = ((0x01 << cs) << 3) & SPI_CS_MASK; - -#if defined(CONFIG_WILDFIRE) - u8 cs_mask = ~(((0x01 << cs) << 3) & SPI_CS_MASK); -#endif -#if defined(CONFIG_WILDFIREMOD) - u8 cs_mask = (cs << 3) & SPI_CS_MASK; -#endif - - /* - * Don't do anything if the chip select is not - * one of the port qs pins. - */ - if (command & QSPI_CS_INIT) { -#if defined(CONFIG_WILDFIRE) - MCF5282_GPIO_DDRQS |= cs_bit; - MCF5282_GPIO_PQSPAR &= ~cs_bit; -#endif - -#if defined(CONFIG_WILDFIREMOD) - MCF5282_GPIO_DDRQS |= SPI_CS_MASK; - MCF5282_GPIO_PQSPAR &= ~SPI_CS_MASK; -#endif - } - - if (command & QSPI_CS_ASSERT) { - MCF5282_GPIO_PORTQS &= ~SPI_CS_MASK; - MCF5282_GPIO_PORTQS |= cs_mask; - } else if (command & QSPI_CS_DROP) { - MCF5282_GPIO_PORTQS |= SPI_CS_MASK; - } -} - -static int __init spi_dev_init(void) -{ - int retval; - - retval = platform_device_register(&coldfire_spi); - if (retval < 0) - return retval; - - if (ARRAY_SIZE(spi_board_info)) - retval = spi_register_board_info(spi_board_info, ARRAY_SIZE(spi_board_info)); - - return retval; -} - -#endif /* CONFIG_SPI */ /***************************************************************************/ diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index ac5d541..6c5b409 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -3,6 +3,8 @@ /* * Architecture specific compatibility types */ +#include <linux/seccomp.h> +#include <linux/thread_info.h> #include <linux/types.h> #include <asm/page.h> #include <asm/ptrace.h> @@ -218,4 +220,9 @@ struct compat_shmid64_ds { compat_ulong_t __unused2; }; +static inline int is_compat_task(void) +{ + return test_thread_flag(TIF_32BIT); +} + #endif /* _ASM_COMPAT_H */ diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c index fb371f5..d6b772b 100644 --- a/arch/powerpc/platforms/86xx/gef_sbc610.c +++ b/arch/powerpc/platforms/86xx/gef_sbc610.c @@ -142,6 +142,10 @@ static void __init gef_sbc610_nec_fixup(struct pci_dev *pdev) { unsigned int val; + /* Do not do the fixup on other platforms! */ + if (!machine_is(gef_sbc610)) + return; + printk(KERN_INFO "Running NEC uPD720101 Fixup\n"); /* Ensure ports 1, 2, 3, 4 & 5 are enabled */ diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index c42cd89..6118890 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -556,7 +556,7 @@ static void __exit aes_s390_fini(void) module_init(aes_s390_init); module_exit(aes_s390_fini); -MODULE_ALIAS("aes"); +MODULE_ALIAS("aes-all"); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm"); MODULE_LICENSE("GPL"); diff --git a/arch/sh/boards/board-ap325rxa.c b/arch/sh/boards/board-ap325rxa.c index 72da416..15b6d45 100644 --- a/arch/sh/boards/board-ap325rxa.c +++ b/arch/sh/boards/board-ap325rxa.c @@ -22,6 +22,7 @@ #include <linux/gpio.h> #include <linux/spi/spi.h> #include <linux/spi/spi_gpio.h> +#include <media/soc_camera.h> #include <media/soc_camera_platform.h> #include <media/sh_mobile_ceu.h> #include <video/sh_mobile_lcdc.h> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 469f345..87717f3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -138,6 +138,9 @@ config ARCH_HAS_CACHE_LINE_SIZE config HAVE_SETUP_PER_CPU_AREA def_bool y +config HAVE_DYNAMIC_PER_CPU_AREA + def_bool y + config HAVE_CPUMASK_OF_CPU_MAP def_bool X86_64_SMP @@ -780,6 +783,11 @@ config X86_MCE_AMD Additional support for AMD specific MCE features such as the DRAM Error Threshold. +config X86_MCE_THRESHOLD + depends on X86_MCE_AMD || X86_MCE_INTEL + bool + default y + config X86_MCE_NONFATAL tristate "Check for non-fatal errors on AMD Athlon/Duron / Intel Pentium 4" depends on X86_32 && X86_MCE @@ -1125,7 +1133,7 @@ config NODES_SHIFT Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accomodate various tables. -config HAVE_ARCH_BOOTMEM_NODE +config HAVE_ARCH_BOOTMEM def_bool y depends on X86_32 && NUMA @@ -1423,7 +1431,7 @@ config CRASH_DUMP config KEXEC_JUMP bool "kexec jump (EXPERIMENTAL)" depends on EXPERIMENTAL - depends on KEXEC && HIBERNATION && X86_32 + depends on KEXEC && HIBERNATION ---help--- Jump between original kernel and kexeced kernel and invoke code in physical address mode via KEXEC diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 4ef949c..394d177 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -379,6 +379,7 @@ static inline u32 safe_apic_wait_icr_idle(void) static inline void ack_APIC_irq(void) { +#ifdef CONFIG_X86_LOCAL_APIC /* * ack_APIC_irq() actually gets compiled as a single instruction * ... yummie. @@ -386,6 +387,7 @@ static inline void ack_APIC_irq(void) /* Docs say use 0 for future compatibility */ apic_write(APIC_EOI, 0); +#endif } static inline unsigned default_get_apic_id(unsigned long x) diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 63134e3..bc9514f 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -53,6 +53,7 @@ #define APIC_ESR_SENDILL 0x00020 #define APIC_ESR_RECVILL 0x00040 #define APIC_ESR_ILLREGA 0x00080 +#define APIC_LVTCMCI 0x2f0 #define APIC_ICR 0x300 #define APIC_DEST_SELF 0x40000 #define APIC_DEST_ALLINC 0x80000 diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 2f84665..5b301b7 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -5,24 +5,43 @@ #include <linux/mm.h> /* Caches aren't brain-dead on the intel. */ -#define flush_cache_all() do { } while (0) -#define flush_cache_mm(mm) do { } while (0) -#define flush_cache_dup_mm(mm) do { } while (0) -#define flush_cache_range(vma, start, end) do { } while (0) -#define flush_cache_page(vma, vmaddr, pfn) do { } while (0) -#define flush_dcache_page(page) do { } while (0) -#define flush_dcache_mmap_lock(mapping) do { } while (0) -#define flush_dcache_mmap_unlock(mapping) do { } while (0) -#define flush_icache_range(start, end) do { } while (0) -#define flush_icache_page(vma, pg) do { } while (0) -#define flush_icache_user_range(vma, pg, adr, len) do { } while (0) -#define flush_cache_vmap(start, end) do { } while (0) -#define flush_cache_vunmap(start, end) do { } while (0) +static inline void flush_cache_all(void) { } +static inline void flush_cache_mm(struct mm_struct *mm) { } +static inline void flush_cache_dup_mm(struct mm_struct *mm) { } +static inline void flush_cache_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) { } +static inline void flush_cache_page(struct vm_area_struct *vma, + unsigned long vmaddr, unsigned long pfn) { } +static inline void flush_dcache_page(struct page *page) { } +static inline void flush_dcache_mmap_lock(struct address_space *mapping) { } +static inline void flush_dcache_mmap_unlock(struct address_space *mapping) { } +static inline void flush_icache_range(unsigned long start, + unsigned long end) { } +static inline void flush_icache_page(struct vm_area_struct *vma, + struct page *page) { } +static inline void flush_icache_user_range(struct vm_area_struct *vma, + struct page *page, + unsigned long addr, + unsigned long len) { } +static inline void flush_cache_vmap(unsigned long start, unsigned long end) { } +static inline void flush_cache_vunmap(unsigned long start, + unsigned long end) { } -#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ - memcpy((dst), (src), (len)) -#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ - memcpy((dst), (src), (len)) +static inline void copy_to_user_page(struct vm_area_struct *vma, + struct page *page, unsigned long vaddr, + void *dst, const void *src, + unsigned long len) +{ + memcpy(dst, src, len); +} + +static inline void copy_from_user_page(struct vm_area_struct *vma, + struct page *page, unsigned long vaddr, + void *dst, const void *src, + unsigned long len) +{ + memcpy(dst, src, len); +} #define PG_non_WB PG_arch_1 PAGEFLAG(NonWB, non_WB) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index ca5ffb2..edc90f2 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -37,8 +37,6 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #else /* !CONFIG_X86_32 */ -#define MAX_EFI_IO_PAGES 100 - extern u64 efi_call0(void *fp); extern u64 efi_call1(void *fp, u64 arg1); extern u64 efi_call2(void *fp, u64 arg1, u64 arg2); diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h index 854d538..c2e6bed 100644 --- a/arch/x86/include/asm/entry_arch.h +++ b/arch/x86/include/asm/entry_arch.h @@ -33,6 +33,8 @@ BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7, smp_invalidate_interrupt) #endif +BUILD_INTERRUPT(generic_interrupt, GENERIC_INTERRUPT_VECTOR) + /* * every pentium local APIC has two 'local interrupts', with a * soft-definable vector attached to both interrupts, one of diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index dca8f03..63a79c7 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -24,9 +24,6 @@ #include <asm/kmap_types.h> #else #include <asm/vsyscall.h> -#ifdef CONFIG_EFI -#include <asm/efi.h> -#endif #endif /* @@ -92,13 +89,6 @@ enum fixed_addresses { FIX_IO_APIC_BASE_0, FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1, #endif -#ifdef CONFIG_X86_64 -#ifdef CONFIG_EFI - FIX_EFI_IO_MAP_LAST_PAGE, - FIX_EFI_IO_MAP_FIRST_PAGE = FIX_EFI_IO_MAP_LAST_PAGE - + MAX_EFI_IO_PAGES - 1, -#endif -#endif #ifdef CONFIG_X86_VISWS_APIC FIX_CO_CPU, /* Cobalt timer */ FIX_CO_APIC, /* Cobalt APIC Redirection Table */ diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 176f058..039db6a 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -12,6 +12,7 @@ typedef struct { unsigned int apic_timer_irqs; /* arch dependent */ unsigned int irq_spurious_count; #endif + unsigned int generic_irqs; /* arch dependent */ #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 370e1c8..b762ea4 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -27,6 +27,7 @@ /* Interrupt handlers registered during init_IRQ */ extern void apic_timer_interrupt(void); +extern void generic_interrupt(void); extern void error_interrupt(void); extern void spurious_interrupt(void); extern void thermal_interrupt(void); diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 48f0004..71c9e51 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -172,7 +172,13 @@ static inline void __save_init_fpu(struct task_struct *tsk) #else /* CONFIG_X86_32 */ -extern void finit(void); +#ifdef CONFIG_MATH_EMULATION +extern void finit_task(struct task_struct *tsk); +#else +static inline void finit_task(struct task_struct *tsk) +{ +} +#endif static inline void tolerant_fwait(void) { diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h new file mode 100644 index 0000000..36fb1a6 --- /dev/null +++ b/arch/x86/include/asm/init.h @@ -0,0 +1,18 @@ +#ifndef _ASM_X86_INIT_32_H +#define _ASM_X86_INIT_32_H + +#ifdef CONFIG_X86_32 +extern void __init early_ioremap_page_table_range_init(void); +#endif + +extern unsigned long __init +kernel_physical_mapping_init(unsigned long start, + unsigned long end, + unsigned long page_size_mask); + + +extern unsigned long __initdata e820_table_start; +extern unsigned long __meminitdata e820_table_end; +extern unsigned long __meminitdata e820_table_top; + +#endif /* _ASM_X86_INIT_32_H */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 683d0b4..e5383e3 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -172,8 +172,6 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size) extern void iounmap(volatile void __iomem *addr); -extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys); - #ifdef CONFIG_X86_32 # include "io_32.h" @@ -198,7 +196,6 @@ extern void early_ioremap_reset(void); extern void __iomem *early_ioremap(unsigned long offset, unsigned long size); extern void __iomem *early_memremap(unsigned long offset, unsigned long size); extern void early_iounmap(void __iomem *addr, unsigned long size); -extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys); #define IO_SPACE_LIMIT 0xffff diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 107eb21..f38481b 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -36,6 +36,7 @@ static inline int irq_canonicalize(int irq) extern void fixup_irqs(void); #endif +extern void (*generic_interrupt_extension)(void); extern void init_IRQ(void); extern void native_init_IRQ(void); extern bool handle_irq(unsigned irq, struct pt_regs *regs); diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 8a285f3..3cbd79b 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -112,6 +112,11 @@ #define LOCAL_PERF_VECTOR 0xee /* + * Generic system vector for platform specific use + */ +#define GENERIC_INTERRUPT_VECTOR 0xed + +/* * First APIC vector available to drivers: (vectors 0x30-0xee) we * start at 0x31(0x41) to spread out vectors evenly between priority * levels. (0x80 is the syscall vector) diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 0ceb6d1..317ff17 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -9,13 +9,13 @@ # define PAGES_NR 4 #else # define PA_CONTROL_PAGE 0 -# define PA_TABLE_PAGE 1 -# define PAGES_NR 2 +# define VA_CONTROL_PAGE 1 +# define PA_TABLE_PAGE 2 +# define PA_SWAP_PAGE 3 +# define PAGES_NR 4 #endif -#ifdef CONFIG_X86_32 # define KEXEC_CONTROL_CODE_MAX_SIZE 2048 -#endif #ifndef __ASSEMBLY__ @@ -136,10 +136,11 @@ relocate_kernel(unsigned long indirection_page, unsigned int has_pae, unsigned int preserve_context); #else -NORET_TYPE void +unsigned long relocate_kernel(unsigned long indirection_page, unsigned long page_list, - unsigned long start_address) ATTRIB_NORET; + unsigned long start_address, + unsigned int preserve_context); #endif #define ARCH_HAS_KIMAGE_ARCH diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 9320e2a..a0d70b4 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -4,11 +4,6 @@ #undef notrace #define notrace __attribute__((no_instrument_function)) -#ifdef CONFIG_X86_64 -#define __ALIGN .p2align 4,,15 -#define __ALIGN_STR ".p2align 4,,15" -#endif - #ifdef CONFIG_X86_32 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0))) /* @@ -50,16 +45,25 @@ __asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \ "g" (arg4), "g" (arg5), "g" (arg6)) -#endif +#endif /* CONFIG_X86_32 */ + +#ifdef __ASSEMBLY__ #define GLOBAL(name) \ .globl name; \ name: +#ifdef CONFIG_X86_64 +#define __ALIGN .p2align 4,,15 +#define __ALIGN_STR ".p2align 4,,15" +#endif + #ifdef CONFIG_X86_ALIGNMENT_16 #define __ALIGN .align 16,0x90 #define __ALIGN_STR ".align 16,0x90" #endif +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_X86_LINKAGE_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 32c6e17..563933e 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -11,6 +11,8 @@ */ #define MCG_CTL_P (1UL<<8) /* MCG_CAP register available */ +#define MCG_EXT_P (1ULL<<9) /* Extended registers available */ +#define MCG_CMCI_P (1ULL<<10) /* CMCI supported */ #define MCG_STATUS_RIPV (1UL<<0) /* restart ip valid */ #define MCG_STATUS_EIPV (1UL<<1) /* ip points to correct instruction */ @@ -90,14 +92,29 @@ extern int mce_disabled; #include <asm/atomic.h> +void mce_setup(struct mce *m); void mce_log(struct mce *m); DECLARE_PER_CPU(struct sys_device, device_mce); extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); +/* + * To support more than 128 would need to escape the predefined + * Linux defined extended banks first. + */ +#define MAX_NR_BANKS (MCE_EXTENDED_BANK - 1) + #ifdef CONFIG_X86_MCE_INTEL void mce_intel_feature_init(struct cpuinfo_x86 *c); +void cmci_clear(void); +void cmci_reenable(void); +void cmci_rediscover(int dying); +void cmci_recheck(void); #else static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { } +static inline void cmci_clear(void) {} +static inline void cmci_reenable(void) {} +static inline void cmci_rediscover(int dying) {} +static inline void cmci_recheck(void) {} #endif #ifdef CONFIG_X86_MCE_AMD @@ -106,11 +123,23 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c); static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { } #endif -void mce_log_therm_throt_event(unsigned int cpu, __u64 status); +extern int mce_available(struct cpuinfo_x86 *c); + +void mce_log_therm_throt_event(__u64 status); extern atomic_t mce_entry; extern void do_machine_check(struct pt_regs *, long); + +typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS); +DECLARE_PER_CPU(mce_banks_t, mce_poll_banks); + +enum mcp_flags { + MCP_TIMESTAMP = (1 << 0), /* log time stamp */ + MCP_UC = (1 << 1), /* log uncorrected errors */ +}; +extern void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); + extern int mce_notify_user(void); #endif /* !CONFIG_X86_32 */ @@ -120,8 +149,8 @@ extern void mcheck_init(struct cpuinfo_x86 *c); #else #define mcheck_init(c) do { } while (0) #endif -extern void stop_mce(void); -extern void restart_mce(void); + +extern void (*mce_threshold_vector)(void); #endif /* __KERNEL__ */ #endif /* _ASM_X86_MCE_H */ diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index 105fb90..ede6998 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -91,46 +91,9 @@ static inline int pfn_valid(int pfn) #endif /* CONFIG_DISCONTIGMEM */ #ifdef CONFIG_NEED_MULTIPLE_NODES - -/* - * Following are macros that are specific to this numa platform. - */ -#define reserve_bootmem(addr, size, flags) \ - reserve_bootmem_node(NODE_DATA(0), (addr), (size), (flags)) -#define alloc_bootmem(x) \ - __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_nopanic(x) \ - __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), SMP_CACHE_BYTES, \ - __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_low(x) \ - __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0) -#define alloc_bootmem_pages(x) \ - __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_pages_nopanic(x) \ - __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), PAGE_SIZE, \ - __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_low_pages(x) \ - __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0) -#define alloc_bootmem_node(pgdat, x) \ -({ \ - struct pglist_data __maybe_unused \ - *__alloc_bootmem_node__pgdat = (pgdat); \ - __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, \ - __pa(MAX_DMA_ADDRESS)); \ -}) -#define alloc_bootmem_pages_node(pgdat, x) \ -({ \ - struct pglist_data __maybe_unused \ - *__alloc_bootmem_node__pgdat = (pgdat); \ - __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, \ - __pa(MAX_DMA_ADDRESS)); \ -}) -#define alloc_bootmem_low_pages_node(pgdat, x) \ -({ \ - struct pglist_data __maybe_unused \ - *__alloc_bootmem_node__pgdat = (pgdat); \ - __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0); \ -}) +/* always use node 0 for bootmem on this numa platform */ +#define bootmem_arch_preferred_node(__bdata, size, align, goal, limit) \ + (NODE_DATA(0)->bdata) #endif /* CONFIG_NEED_MULTIPLE_NODES */ #endif /* _ASM_X86_MMZONE_32_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 358acc5..2dbd231 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -77,6 +77,11 @@ #define MSR_IA32_MC0_ADDR 0x00000402 #define MSR_IA32_MC0_MISC 0x00000403 +/* These are consecutive and not in the normal 4er MCE bank block */ +#define MSR_IA32_MC0_CTL2 0x00000280 +#define CMCI_EN (1ULL << 30) +#define CMCI_THRESHOLD_MASK 0xffffULL + #define MSR_P6_PERFCTR0 0x000000c1 #define MSR_P6_PERFCTR1 0x000000c2 #define MSR_P6_EVNTSEL0 0x00000186 diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index 2d625da..826ad37 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -40,14 +40,8 @@ #ifndef __ASSEMBLY__ -struct pgprot; - extern int page_is_ram(unsigned long pagenr); extern int devmem_is_allowed(unsigned long pagenr); -extern void map_devmem(unsigned long pfn, unsigned long size, - struct pgprot vma_prot); -extern void unmap_devmem(unsigned long pfn, unsigned long size, - struct pgprot vma_prot); extern unsigned long max_low_pfn_mapped; extern unsigned long max_pfn_mapped; diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index b0e7005..2cd07b9 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -2,6 +2,7 @@ #define _ASM_X86_PAT_H #include <linux/types.h> +#include <asm/pgtable_types.h> #ifdef CONFIG_X86_PAT extern int pat_enabled; @@ -17,5 +18,9 @@ extern int free_memtype(u64 start, u64 end); extern int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flag); +extern void map_devmem(unsigned long pfn, unsigned long size, + struct pgprot vma_prot); +extern void unmap_devmem(unsigned long pfn, unsigned long size, + struct pgprot vma_prot); #endif /* _ASM_X86_PAT_H */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index aee103b..8f1d2fb 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -43,6 +43,14 @@ #else /* ...!ASSEMBLY */ #include <linux/stringify.h> +#include <asm/sections.h> + +#define __addr_to_pcpu_ptr(addr) \ + (void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr \ + + (unsigned long)__per_cpu_start) +#define __pcpu_ptr_to_addr(ptr) \ + (void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr \ + - (unsigned long)__per_cpu_start) #ifdef CONFIG_SMP #define __percpu_arg(x) "%%"__stringify(__percpu_seg)":%P" #x diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 1c097a3..d0812e1 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -288,6 +288,8 @@ static inline int is_new_memtype_allowed(unsigned long flags, return 1; } +pmd_t *populate_extra_pmd(unsigned long vaddr); +pte_t *populate_extra_pte(unsigned long vaddr); #endif /* __ASSEMBLY__ */ #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index bd8df3b..2733fad 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -25,6 +25,11 @@ * area for the same reason. ;) */ #define VMALLOC_OFFSET (8 * 1024 * 1024) + +#ifndef __ASSEMBLER__ +extern bool __vmalloc_start_set; /* set once high_memory is set */ +#endif + #define VMALLOC_START ((unsigned long)high_memory + VMALLOC_OFFSET) #ifdef CONFIG_X86_PAE #define LAST_PKMAP 512 diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 4d258ad..b8238dc 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -273,6 +273,7 @@ typedef struct page *pgtable_t; extern pteval_t __supported_pte_mask; extern int nx_enabled; +extern void set_nx(void); #define pgprot_writecombine pgprot_writecombine extern pgprot_t pgprot_writecombine(pgprot_t prot); diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 777327e..9f4dfba 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -199,6 +199,10 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info); #define SCIR_CPU_ACTIVITY 0x02 /* not idle */ #define SCIR_CPU_HB_INTERVAL (HZ) /* once per second */ +/* Loop through all installed blades */ +#define for_each_possible_blade(bid) \ + for ((bid) = 0; (bid) < uv_num_possible_blades(); (bid)++) + /* * Macros for converting between kernel virtual addresses, socket local physical * addresses, and UV global physical addresses. diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 4bd990e..1a918dd 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -164,6 +164,7 @@ static inline pte_t __pte_ma(pteval_t x) xmaddr_t arbitrary_virt_to_machine(void *address); +unsigned long arbitrary_virt_to_mfn(void *vaddr); void make_lowmem_page_readonly(void *vaddr); void make_lowmem_page_readwrite(void *vaddr); diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 95f216b..339ce35 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -111,7 +111,7 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o # NB rename without _64 ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) - obj-$(CONFIG_X86_UV) += tlb_uv.o bios_uv.o uv_irq.o uv_sysfs.o + obj-$(CONFIG_X86_UV) += tlb_uv.o bios_uv.o uv_irq.o uv_sysfs.o uv_time.o obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o obj-$(CONFIG_AUDIT) += audit_64.o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 6907b8e..4c80f15 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -414,9 +414,17 @@ void __init alternative_instructions(void) that might execute the to be patched code. Other CPUs are not running. */ stop_nmi(); -#ifdef CONFIG_X86_MCE - stop_mce(); -#endif + + /* + * Don't stop machine check exceptions while patching. + * MCEs only happen when something got corrupted and in this + * case we must do something about the corruption. + * Ignoring it is worse than a unlikely patching race. + * Also machine checks tend to be broadcast and if one CPU + * goes into machine check the others follow quickly, so we don't + * expect a machine check to cause undue problems during to code + * patching. + */ apply_alternatives(__alt_instructions, __alt_instructions_end); @@ -456,9 +464,6 @@ void __init alternative_instructions(void) (unsigned long)__smp_locks_end); restart_nmi(); -#ifdef CONFIG_X86_MCE - restart_mce(); -#endif } /** diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index f9cecdf..30909a2 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -46,6 +46,7 @@ #include <asm/idle.h> #include <asm/mtrr.h> #include <asm/smp.h> +#include <asm/mce.h> unsigned int num_processors; @@ -842,6 +843,14 @@ void clear_local_APIC(void) apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED); } #endif +#ifdef CONFIG_X86_MCE_INTEL + if (maxlvt >= 6) { + v = apic_read(APIC_LVTCMCI); + if (!(v & APIC_LVT_MASKED)) + apic_write(APIC_LVTCMCI, v | APIC_LVT_MASKED); + } +#endif + /* * Clean APIC state for other OSs: */ @@ -1241,6 +1250,12 @@ void __cpuinit setup_local_APIC(void) apic_write(APIC_LVT1, value); preempt_enable(); + +#ifdef CONFIG_X86_MCE_INTEL + /* Recheck CMCI information after local APIC is up on CPU #0 */ + if (smp_processor_id() == 0) + cmci_recheck(); +#endif } void __cpuinit end_local_APIC_setup(void) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 25423a5..f47df59 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -5,6 +5,7 @@ #include <asm/io.h> #include <asm/processor.h> #include <asm/apic.h> +#include <asm/cpu.h> #ifdef CONFIG_X86_64 # include <asm/numa_64.h> @@ -141,6 +142,55 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c) } } +static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + /* calling is from identify_secondary_cpu() ? */ + if (c->cpu_index == boot_cpu_id) + return; + + /* + * Certain Athlons might work (for various values of 'work') in SMP + * but they are not certified as MP capable. + */ + /* Athlon 660/661 is valid. */ + if ((c->x86_model == 6) && ((c->x86_mask == 0) || + (c->x86_mask == 1))) + goto valid_k7; + + /* Duron 670 is valid */ + if ((c->x86_model == 7) && (c->x86_mask == 0)) + goto valid_k7; + + /* + * Athlon 662, Duron 671, and Athlon >model 7 have capability + * bit. It's worth noting that the A5 stepping (662) of some + * Athlon XP's have the MP bit set. + * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for + * more. + */ + if (((c->x86_model == 6) && (c->x86_mask >= 2)) || + ((c->x86_model == 7) && (c->x86_mask >= 1)) || + (c->x86_model > 7)) + if (cpu_has_mp) + goto valid_k7; + + /* If we get here, not a certified SMP capable AMD system. */ + + /* + * Don't taint if we are running SMP kernel on a single non-MP + * approved Athlon + */ + WARN_ONCE(1, "WARNING: This combination of AMD" + "processors is not suitable for SMP.\n"); + if (!test_taint(TAINT_UNSAFE_SMP)) + add_taint(TAINT_UNSAFE_SMP); + +valid_k7: + ; +#endif +} + static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) { u32 l, h; @@ -175,6 +225,8 @@ static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) } set_cpu_cap(c, X86_FEATURE_K7); + + amd_k7_smp_check(c); } #endif diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 4b1c319..22590cf 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -601,7 +601,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) if (!data) return -ENOMEM; - data->acpi_data = percpu_ptr(acpi_perf_data, cpu); + data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu); per_cpu(drv_data, cpu) = data; if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index b585e04c..3178c3a 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -277,7 +277,6 @@ static struct cpufreq_driver p4clockmod_driver = { .name = "p4-clockmod", .owner = THIS_MODULE, .attr = p4clockmod_attr, - .hide_interface = 1, }; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 25c559b..191117f 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -13,6 +13,7 @@ #include <asm/uaccess.h> #include <asm/ds.h> #include <asm/bugs.h> +#include <asm/cpu.h> #ifdef CONFIG_X86_64 #include <asm/topology.h> @@ -110,6 +111,28 @@ static void __cpuinit trap_init_f00f_bug(void) } #endif +static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + /* calling is from identify_secondary_cpu() ? */ + if (c->cpu_index == boot_cpu_id) + return; + + /* + * Mask B, Pentium, but not Pentium MMX + */ + if (c->x86 == 5 && + c->x86_mask >= 1 && c->x86_mask <= 4 && + c->x86_model <= 3) { + /* + * Remember we have B step Pentia with bugs + */ + WARN_ONCE(1, "WARNING: SMP operation may be unreliable" + "with B stepping processors.\n"); + } +#endif +} + static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) { unsigned long lo, hi; @@ -186,6 +209,8 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_NUMAQ numaq_tsc_disable(); #endif + + intel_smp_check(c); } #else static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile index d7d2323..b2f8982 100644 --- a/arch/x86/kernel/cpu/mcheck/Makefile +++ b/arch/x86/kernel/cpu/mcheck/Makefile @@ -4,3 +4,4 @@ obj-$(CONFIG_X86_32) += k7.o p4.o p5.o p6.o winchip.o obj-$(CONFIG_X86_MCE_INTEL) += mce_intel_64.o obj-$(CONFIG_X86_MCE_AMD) += mce_amd_64.o obj-$(CONFIG_X86_MCE_NONFATAL) += non-fatal.o +obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o diff --git a/arch/x86/kernel/cpu/mcheck/mce_32.c b/arch/x86/kernel/cpu/mcheck/mce_32.c index dfaebce..3552119 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_32.c +++ b/arch/x86/kernel/cpu/mcheck/mce_32.c @@ -60,20 +60,6 @@ void mcheck_init(struct cpuinfo_x86 *c) } } -static unsigned long old_cr4 __initdata; - -void __init stop_mce(void) -{ - old_cr4 = read_cr4(); - clear_in_cr4(X86_CR4_MCE); -} - -void __init restart_mce(void) -{ - if (old_cr4 & X86_CR4_MCE) - set_in_cr4(X86_CR4_MCE); -} - static int __init mcheck_disable(char *str) { mce_disabled = 1; diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index fe79985..ca14604 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -3,6 +3,8 @@ * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs. * Rest from unknown author(s). * 2004 Andi Kleen. Rewrote most of it. + * Copyright 2008 Intel Corporation + * Author: Andi Kleen */ #include <linux/init.h> @@ -24,6 +26,9 @@ #include <linux/ctype.h> #include <linux/kmod.h> #include <linux/kdebug.h> +#include <linux/kobject.h> +#include <linux/sysfs.h> +#include <linux/ratelimit.h> #include <asm/processor.h> #include <asm/msr.h> #include <asm/mce.h> @@ -32,7 +37,6 @@ #include <asm/idle.h> #define MISC_MCELOG_MINOR 227 -#define NR_SYSFS_BANKS 6 atomic_t mce_entry; @@ -47,7 +51,7 @@ static int mce_dont_init; */ static int tolerant = 1; static int banks; -static unsigned long bank[NR_SYSFS_BANKS] = { [0 ... NR_SYSFS_BANKS-1] = ~0UL }; +static u64 *bank; static unsigned long notify_user; static int rip_msr; static int mce_bootlog = -1; @@ -58,6 +62,19 @@ static char *trigger_argv[2] = { trigger, NULL }; static DECLARE_WAIT_QUEUE_HEAD(mce_wait); +/* MCA banks polled by the period polling timer for corrected events */ +DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { + [0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL +}; + +/* Do initial initialization of a struct mce */ +void mce_setup(struct mce *m) +{ + memset(m, 0, sizeof(struct mce)); + m->cpu = smp_processor_id(); + rdtscll(m->tsc); +} + /* * Lockless MCE logging infrastructure. * This avoids deadlocks on printk locks without having to break locks. Also @@ -119,11 +136,11 @@ static void print_mce(struct mce *m) print_symbol("{%s}", m->ip); printk("\n"); } - printk(KERN_EMERG "TSC %Lx ", m->tsc); + printk(KERN_EMERG "TSC %llx ", m->tsc); if (m->addr) - printk("ADDR %Lx ", m->addr); + printk("ADDR %llx ", m->addr); if (m->misc) - printk("MISC %Lx ", m->misc); + printk("MISC %llx ", m->misc); printk("\n"); printk(KERN_EMERG "This is not a software problem!\n"); printk(KERN_EMERG "Run through mcelog --ascii to decode " @@ -149,8 +166,10 @@ static void mce_panic(char *msg, struct mce *backup, unsigned long start) panic(msg); } -static int mce_available(struct cpuinfo_x86 *c) +int mce_available(struct cpuinfo_x86 *c) { + if (mce_dont_init) + return 0; return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA); } @@ -172,7 +191,77 @@ static inline void mce_get_rip(struct mce *m, struct pt_regs *regs) } /* - * The actual machine check handler + * Poll for corrected events or events that happened before reset. + * Those are just logged through /dev/mcelog. + * + * This is executed in standard interrupt context. + */ +void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) +{ + struct mce m; + int i; + + mce_setup(&m); + + rdmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus); + for (i = 0; i < banks; i++) { + if (!bank[i] || !test_bit(i, *b)) + continue; + + m.misc = 0; + m.addr = 0; + m.bank = i; + m.tsc = 0; + + barrier(); + rdmsrl(MSR_IA32_MC0_STATUS + i*4, m.status); + if (!(m.status & MCI_STATUS_VAL)) + continue; + + /* + * Uncorrected events are handled by the exception handler + * when it is enabled. But when the exception is disabled log + * everything. + * + * TBD do the same check for MCI_STATUS_EN here? + */ + if ((m.status & MCI_STATUS_UC) && !(flags & MCP_UC)) + continue; + + if (m.status & MCI_STATUS_MISCV) + rdmsrl(MSR_IA32_MC0_MISC + i*4, m.misc); + if (m.status & MCI_STATUS_ADDRV) + rdmsrl(MSR_IA32_MC0_ADDR + i*4, m.addr); + + if (!(flags & MCP_TIMESTAMP)) + m.tsc = 0; + /* + * Don't get the IP here because it's unlikely to + * have anything to do with the actual error location. + */ + + mce_log(&m); + add_taint(TAINT_MACHINE_CHECK); + + /* + * Clear state for this bank. + */ + wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0); + } + + /* + * Don't clear MCG_STATUS here because it's only defined for + * exceptions. + */ +} + +/* + * The actual machine check handler. This only handles real + * exceptions when something got corrupted coming in through int 18. + * + * This is executed in NMI context not subject to normal locking rules. This + * implies that most kernel services cannot be safely used. Don't even + * think about putting a printk in there! */ void do_machine_check(struct pt_regs * regs, long error_code) { @@ -190,17 +279,18 @@ void do_machine_check(struct pt_regs * regs, long error_code) * error. */ int kill_it = 0; + DECLARE_BITMAP(toclear, MAX_NR_BANKS); atomic_inc(&mce_entry); - if ((regs - && notify_die(DIE_NMI, "machine check", regs, error_code, + if (notify_die(DIE_NMI, "machine check", regs, error_code, 18, SIGKILL) == NOTIFY_STOP) - || !banks) + goto out2; + if (!banks) goto out2; - memset(&m, 0, sizeof(struct mce)); - m.cpu = smp_processor_id(); + mce_setup(&m); + rdmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus); /* if the restart IP is not valid, we're done for */ if (!(m.mcgstatus & MCG_STATUS_RIPV)) @@ -210,18 +300,32 @@ void do_machine_check(struct pt_regs * regs, long error_code) barrier(); for (i = 0; i < banks; i++) { - if (i < NR_SYSFS_BANKS && !bank[i]) + __clear_bit(i, toclear); + if (!bank[i]) continue; m.misc = 0; m.addr = 0; m.bank = i; - m.tsc = 0; rdmsrl(MSR_IA32_MC0_STATUS + i*4, m.status); if ((m.status & MCI_STATUS_VAL) == 0) continue; + /* + * Non uncorrected errors are handled by machine_check_poll + * Leave them alone. + */ + if ((m.status & MCI_STATUS_UC) == 0) + continue; + + /* + * Set taint even when machine check was not enabled. + */ + add_taint(TAINT_MACHINE_CHECK); + + __set_bit(i, toclear); + if (m.status & MCI_STATUS_EN) { /* if PCC was set, there's no way out */ no_way_out |= !!(m.status & MCI_STATUS_PCC); @@ -235,6 +339,12 @@ void do_machine_check(struct pt_regs * regs, long error_code) no_way_out = 1; kill_it = 1; } + } else { + /* + * Machine check event was not enabled. Clear, but + * ignore. + */ + continue; } if (m.status & MCI_STATUS_MISCV) @@ -243,10 +353,7 @@ void do_machine_check(struct pt_regs * regs, long error_code) rdmsrl(MSR_IA32_MC0_ADDR + i*4, m.addr); mce_get_rip(&m, regs); - if (error_code >= 0) - rdtscll(m.tsc); - if (error_code != -2) - mce_log(&m); + mce_log(&m); /* Did this bank cause the exception? */ /* Assume that the bank with uncorrectable errors did it, @@ -255,14 +362,8 @@ void do_machine_check(struct pt_regs * regs, long error_code) panicm = m; panicm_found = 1; } - - add_taint(TAINT_MACHINE_CHECK); } - /* Never do anything final in the polling timer */ - if (!regs) - goto out; - /* If we didn't find an uncorrectable error, pick the last one (shouldn't happen, just being safe). */ if (!panicm_found) @@ -309,10 +410,11 @@ void do_machine_check(struct pt_regs * regs, long error_code) /* notify userspace ASAP */ set_thread_flag(TIF_MCE_NOTIFY); - out: /* the last thing we do is clear state */ - for (i = 0; i < banks; i++) - wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0); + for (i = 0; i < banks; i++) { + if (test_bit(i, toclear)) + wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0); + } wrmsrl(MSR_IA32_MCG_STATUS, 0); out2: atomic_dec(&mce_entry); @@ -332,15 +434,13 @@ void do_machine_check(struct pt_regs * regs, long error_code) * and historically has been the register value of the * MSR_IA32_THERMAL_STATUS (Intel) msr. */ -void mce_log_therm_throt_event(unsigned int cpu, __u64 status) +void mce_log_therm_throt_event(__u64 status) { struct mce m; - memset(&m, 0, sizeof(m)); - m.cpu = cpu; + mce_setup(&m); m.bank = MCE_THERMAL_BANK; m.status = status; - rdtscll(m.tsc); mce_log(&m); } #endif /* CONFIG_X86_MCE_INTEL */ @@ -353,18 +453,18 @@ void mce_log_therm_throt_event(unsigned int cpu, __u64 status) static int check_interval = 5 * 60; /* 5 minutes */ static int next_interval; /* in jiffies */ -static void mcheck_timer(struct work_struct *work); -static DECLARE_DELAYED_WORK(mcheck_work, mcheck_timer); +static void mcheck_timer(unsigned long); +static DEFINE_PER_CPU(struct timer_list, mce_timer); -static void mcheck_check_cpu(void *info) +static void mcheck_timer(unsigned long data) { - if (mce_available(¤t_cpu_data)) - do_machine_check(NULL, 0); -} + struct timer_list *t = &per_cpu(mce_timer, data); -static void mcheck_timer(struct work_struct *work) -{ - on_each_cpu(mcheck_check_cpu, NULL, 1); + WARN_ON(smp_processor_id() != data); + + if (mce_available(¤t_cpu_data)) + machine_check_poll(MCP_TIMESTAMP, + &__get_cpu_var(mce_poll_banks)); /* * Alert userspace if needed. If we logged an MCE, reduce the @@ -377,31 +477,41 @@ static void mcheck_timer(struct work_struct *work) (int)round_jiffies_relative(check_interval*HZ)); } - schedule_delayed_work(&mcheck_work, next_interval); + t->expires = jiffies + next_interval; + add_timer(t); +} + +static void mce_do_trigger(struct work_struct *work) +{ + call_usermodehelper(trigger, trigger_argv, NULL, UMH_NO_WAIT); } +static DECLARE_WORK(mce_trigger_work, mce_do_trigger); + /* - * This is only called from process context. This is where we do - * anything we need to alert userspace about new MCEs. This is called - * directly from the poller and also from entry.S and idle, thanks to - * TIF_MCE_NOTIFY. + * Notify the user(s) about new machine check events. + * Can be called from interrupt context, but not from machine check/NMI + * context. */ int mce_notify_user(void) { + /* Not more than two messages every minute */ + static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); + clear_thread_flag(TIF_MCE_NOTIFY); if (test_and_clear_bit(0, ¬ify_user)) { - static unsigned long last_print; - unsigned long now = jiffies; - wake_up_interruptible(&mce_wait); - if (trigger[0]) - call_usermodehelper(trigger, trigger_argv, NULL, - UMH_NO_WAIT); - if (time_after_eq(now, last_print + (check_interval*HZ))) { - last_print = now; + /* + * There is no risk of missing notifications because + * work_pending is always cleared before the function is + * executed. + */ + if (trigger[0] && !work_pending(&mce_trigger_work)) + schedule_work(&mce_trigger_work); + + if (__ratelimit(&ratelimit)) printk(KERN_INFO "Machine check events logged\n"); - } return 1; } @@ -425,63 +535,78 @@ static struct notifier_block mce_idle_notifier = { static __init int periodic_mcheck_init(void) { - next_interval = check_interval * HZ; - if (next_interval) - schedule_delayed_work(&mcheck_work, - round_jiffies_relative(next_interval)); - idle_notifier_register(&mce_idle_notifier); - return 0; + idle_notifier_register(&mce_idle_notifier); + return 0; } __initcall(periodic_mcheck_init); - /* * Initialize Machine Checks for a CPU. */ -static void mce_init(void *dummy) +static int mce_cap_init(void) { u64 cap; - int i; + unsigned b; rdmsrl(MSR_IA32_MCG_CAP, cap); - banks = cap & 0xff; - if (banks > MCE_EXTENDED_BANK) { - banks = MCE_EXTENDED_BANK; - printk(KERN_INFO "MCE: warning: using only %d banks\n", - MCE_EXTENDED_BANK); + b = cap & 0xff; + if (b > MAX_NR_BANKS) { + printk(KERN_WARNING + "MCE: Using only %u machine check banks out of %u\n", + MAX_NR_BANKS, b); + b = MAX_NR_BANKS; } + + /* Don't support asymmetric configurations today */ + WARN_ON(banks != 0 && b != banks); + banks = b; + if (!bank) { + bank = kmalloc(banks * sizeof(u64), GFP_KERNEL); + if (!bank) + return -ENOMEM; + memset(bank, 0xff, banks * sizeof(u64)); + } + /* Use accurate RIP reporting if available. */ if ((cap & (1<<9)) && ((cap >> 16) & 0xff) >= 9) rip_msr = MSR_IA32_MCG_EIP; - /* Log the machine checks left over from the previous reset. - This also clears all registers */ - do_machine_check(NULL, mce_bootlog ? -1 : -2); + return 0; +} + +static void mce_init(void *dummy) +{ + u64 cap; + int i; + mce_banks_t all_banks; + + /* + * Log the machine checks left over from the previous reset. + */ + bitmap_fill(all_banks, MAX_NR_BANKS); + machine_check_poll(MCP_UC, &all_banks); set_in_cr4(X86_CR4_MCE); + rdmsrl(MSR_IA32_MCG_CAP, cap); if (cap & MCG_CTL_P) wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); for (i = 0; i < banks; i++) { - if (i < NR_SYSFS_BANKS) - wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]); - else - wrmsrl(MSR_IA32_MC0_CTL+4*i, ~0UL); - + wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]); wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0); } } /* Add per CPU specific workarounds here */ -static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c) +static void mce_cpu_quirks(struct cpuinfo_x86 *c) { /* This should be disabled by the BIOS, but isn't always */ if (c->x86_vendor == X86_VENDOR_AMD) { - if(c->x86 == 15) + if (c->x86 == 15 && banks > 4) /* disable GART TBL walk error reporting, which trips off incorrectly with the IOMMU & 3ware & Cerberus. */ - clear_bit(10, &bank[4]); + clear_bit(10, (unsigned long *)&bank[4]); if(c->x86 <= 17 && mce_bootlog < 0) /* Lots of broken BIOS around that don't clear them by default and leave crap in there. Don't log. */ @@ -504,20 +629,38 @@ static void mce_cpu_features(struct cpuinfo_x86 *c) } } +static void mce_init_timer(void) +{ + struct timer_list *t = &__get_cpu_var(mce_timer); + + /* data race harmless because everyone sets to the same value */ + if (!next_interval) + next_interval = check_interval * HZ; + if (!next_interval) + return; + setup_timer(t, mcheck_timer, smp_processor_id()); + t->expires = round_jiffies(jiffies + next_interval); + add_timer(t); +} + /* * Called for each booted CPU to set up machine checks. * Must be called with preempt off. */ void __cpuinit mcheck_init(struct cpuinfo_x86 *c) { - mce_cpu_quirks(c); + if (!mce_available(c)) + return; - if (mce_dont_init || - !mce_available(c)) + if (mce_cap_init() < 0) { + mce_dont_init = 1; return; + } + mce_cpu_quirks(c); mce_init(NULL); mce_cpu_features(c); + mce_init_timer(); } /* @@ -573,7 +716,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, { unsigned long *cpu_tsc; static DEFINE_MUTEX(mce_read_mutex); - unsigned next; + unsigned prev, next; char __user *buf = ubuf; int i, err; @@ -592,25 +735,32 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, } err = 0; - for (i = 0; i < next; i++) { - unsigned long start = jiffies; - - while (!mcelog.entry[i].finished) { - if (time_after_eq(jiffies, start + 2)) { - memset(mcelog.entry + i,0, sizeof(struct mce)); - goto timeout; + prev = 0; + do { + for (i = prev; i < next; i++) { + unsigned long start = jiffies; + + while (!mcelog.entry[i].finished) { + if (time_after_eq(jiffies, start + 2)) { + memset(mcelog.entry + i, 0, + sizeof(struct mce)); + goto timeout; + } + cpu_relax(); } - cpu_relax(); + smp_rmb(); + err |= copy_to_user(buf, mcelog.entry + i, + sizeof(struct mce)); + buf += sizeof(struct mce); +timeout: + ; } - smp_rmb(); - err |= copy_to_user(buf, mcelog.entry + i, sizeof(struct mce)); - buf += sizeof(struct mce); - timeout: - ; - } - memset(mcelog.entry, 0, next * sizeof(struct mce)); - mcelog.next = 0; + memset(mcelog.entry + prev, 0, + (next - prev) * sizeof(struct mce)); + prev = next; + next = cmpxchg(&mcelog.next, prev, 0); + } while (next != prev); synchronize_sched(); @@ -680,20 +830,6 @@ static struct miscdevice mce_log_device = { &mce_chrdev_ops, }; -static unsigned long old_cr4 __initdata; - -void __init stop_mce(void) -{ - old_cr4 = read_cr4(); - clear_in_cr4(X86_CR4_MCE); -} - -void __init restart_mce(void) -{ - if (old_cr4 & X86_CR4_MCE) - set_in_cr4(X86_CR4_MCE); -} - /* * Old style boot options parsing. Only for compatibility. */ @@ -703,8 +839,7 @@ static int __init mcheck_disable(char *str) return 1; } -/* mce=off disables machine check. Note you can re-enable it later - using sysfs. +/* mce=off disables machine check. mce=TOLERANCELEVEL (number, see above) mce=bootlog Log MCEs from before booting. Disabled by default on AMD. mce=nobootlog Don't log MCEs from before booting. */ @@ -728,6 +863,29 @@ __setup("mce=", mcheck_enable); * Sysfs support */ +/* + * Disable machine checks on suspend and shutdown. We can't really handle + * them later. + */ +static int mce_disable(void) +{ + int i; + + for (i = 0; i < banks; i++) + wrmsrl(MSR_IA32_MC0_CTL + i*4, 0); + return 0; +} + +static int mce_suspend(struct sys_device *dev, pm_message_t state) +{ + return mce_disable(); +} + +static int mce_shutdown(struct sys_device *dev) +{ + return mce_disable(); +} + /* On resume clear all MCE state. Don't want to see leftovers from the BIOS. Only one CPU is active at this time, the others get readded later using CPU hotplug. */ @@ -738,20 +896,24 @@ static int mce_resume(struct sys_device *dev) return 0; } +static void mce_cpu_restart(void *data) +{ + del_timer_sync(&__get_cpu_var(mce_timer)); + if (mce_available(¤t_cpu_data)) + mce_init(NULL); + mce_init_timer(); +} + /* Reinit MCEs after user configuration changes */ static void mce_restart(void) { - if (next_interval) - cancel_delayed_work(&mcheck_work); - /* Timer race is harmless here */ - on_each_cpu(mce_init, NULL, 1); next_interval = check_interval * HZ; - if (next_interval) - schedule_delayed_work(&mcheck_work, - round_jiffies_relative(next_interval)); + on_each_cpu(mce_cpu_restart, NULL, 1); } static struct sysdev_class mce_sysclass = { + .suspend = mce_suspend, + .shutdown = mce_shutdown, .resume = mce_resume, .name = "machinecheck", }; @@ -778,16 +940,26 @@ void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu) __cpuinit } \ static SYSDEV_ATTR(name, 0644, show_ ## name, set_ ## name); -/* - * TBD should generate these dynamically based on number of available banks. - * Have only 6 contol banks in /sysfs until then. - */ -ACCESSOR(bank0ctl,bank[0],mce_restart()) -ACCESSOR(bank1ctl,bank[1],mce_restart()) -ACCESSOR(bank2ctl,bank[2],mce_restart()) -ACCESSOR(bank3ctl,bank[3],mce_restart()) -ACCESSOR(bank4ctl,bank[4],mce_restart()) -ACCESSOR(bank5ctl,bank[5],mce_restart()) +static struct sysdev_attribute *bank_attrs; + +static ssize_t show_bank(struct sys_device *s, struct sysdev_attribute *attr, + char *buf) +{ + u64 b = bank[attr - bank_attrs]; + return sprintf(buf, "%llx\n", b); +} + +static ssize_t set_bank(struct sys_device *s, struct sysdev_attribute *attr, + const char *buf, size_t siz) +{ + char *end; + u64 new = simple_strtoull(buf, &end, 0); + if (end == buf) + return -EINVAL; + bank[attr - bank_attrs] = new; + mce_restart(); + return end-buf; +} static ssize_t show_trigger(struct sys_device *s, struct sysdev_attribute *attr, char *buf) @@ -814,8 +986,6 @@ static SYSDEV_ATTR(trigger, 0644, show_trigger, set_trigger); static SYSDEV_INT_ATTR(tolerant, 0644, tolerant); ACCESSOR(check_interval,check_interval,mce_restart()) static struct sysdev_attribute *mce_attributes[] = { - &attr_bank0ctl, &attr_bank1ctl, &attr_bank2ctl, - &attr_bank3ctl, &attr_bank4ctl, &attr_bank5ctl, &attr_tolerant.attr, &attr_check_interval, &attr_trigger, NULL }; @@ -845,11 +1015,22 @@ static __cpuinit int mce_create_device(unsigned int cpu) if (err) goto error; } + for (i = 0; i < banks; i++) { + err = sysdev_create_file(&per_cpu(device_mce, cpu), + &bank_attrs[i]); + if (err) + goto error2; + } cpu_set(cpu, mce_device_initialized); return 0; +error2: + while (--i >= 0) { + sysdev_remove_file(&per_cpu(device_mce, cpu), + &bank_attrs[i]); + } error: - while (i--) { + while (--i >= 0) { sysdev_remove_file(&per_cpu(device_mce,cpu), mce_attributes[i]); } @@ -868,15 +1049,46 @@ static __cpuinit void mce_remove_device(unsigned int cpu) for (i = 0; mce_attributes[i]; i++) sysdev_remove_file(&per_cpu(device_mce,cpu), mce_attributes[i]); + for (i = 0; i < banks; i++) + sysdev_remove_file(&per_cpu(device_mce, cpu), + &bank_attrs[i]); sysdev_unregister(&per_cpu(device_mce,cpu)); cpu_clear(cpu, mce_device_initialized); } +/* Make sure there are no machine checks on offlined CPUs. */ +static void mce_disable_cpu(void *h) +{ + int i; + unsigned long action = *(unsigned long *)h; + + if (!mce_available(¤t_cpu_data)) + return; + if (!(action & CPU_TASKS_FROZEN)) + cmci_clear(); + for (i = 0; i < banks; i++) + wrmsrl(MSR_IA32_MC0_CTL + i*4, 0); +} + +static void mce_reenable_cpu(void *h) +{ + int i; + unsigned long action = *(unsigned long *)h; + + if (!mce_available(¤t_cpu_data)) + return; + if (!(action & CPU_TASKS_FROZEN)) + cmci_reenable(); + for (i = 0; i < banks; i++) + wrmsrl(MSR_IA32_MC0_CTL + i*4, bank[i]); +} + /* Get notified when a cpu comes on/off. Be hotplug friendly. */ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; + struct timer_list *t = &per_cpu(mce_timer, cpu); switch (action) { case CPU_ONLINE: @@ -891,6 +1103,21 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb, threshold_cpu_callback(action, cpu); mce_remove_device(cpu); break; + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + del_timer_sync(t); + smp_call_function_single(cpu, mce_disable_cpu, &action, 1); + break; + case CPU_DOWN_FAILED: + case CPU_DOWN_FAILED_FROZEN: + t->expires = round_jiffies(jiffies + next_interval); + add_timer_on(t, cpu); + smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); + break; + case CPU_POST_DEAD: + /* intentionally ignoring frozen here */ + cmci_rediscover(cpu); + break; } return NOTIFY_OK; } @@ -899,6 +1126,34 @@ static struct notifier_block mce_cpu_notifier __cpuinitdata = { .notifier_call = mce_cpu_callback, }; +static __init int mce_init_banks(void) +{ + int i; + + bank_attrs = kzalloc(sizeof(struct sysdev_attribute) * banks, + GFP_KERNEL); + if (!bank_attrs) + return -ENOMEM; + + for (i = 0; i < banks; i++) { + struct sysdev_attribute *a = &bank_attrs[i]; + a->attr.name = kasprintf(GFP_KERNEL, "bank%d", i); + if (!a->attr.name) + goto nomem; + a->attr.mode = 0644; + a->show = show_bank; + a->store = set_bank; + } + return 0; + +nomem: + while (--i >= 0) + kfree(bank_attrs[i].attr.name); + kfree(bank_attrs); + bank_attrs = NULL; + return -ENOMEM; +} + static __init int mce_init_device(void) { int err; @@ -906,6 +1161,11 @@ static __init int mce_init_device(void) if (!mce_available(&boot_cpu_data)) return -EIO; + + err = mce_init_banks(); + if (err) + return err; + err = sysdev_class_register(&mce_sysclass); if (err) return err; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c index 9817506..c5a32f9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c @@ -79,6 +79,8 @@ static unsigned char shared_bank[NR_BANKS] = { static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */ +static void amd_threshold_interrupt(void); + /* * CPU Initialization */ @@ -174,6 +176,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) tr.reset = 0; tr.old_limit = 0; threshold_restart_bank(&tr); + + mce_threshold_vector = amd_threshold_interrupt; } } } @@ -187,19 +191,13 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) * the interrupt goes off when error_count reaches threshold_limit. * the handler will simply log mcelog w/ software defined bank number. */ -asmlinkage void mce_threshold_interrupt(void) +static void amd_threshold_interrupt(void) { unsigned int bank, block; struct mce m; u32 low = 0, high = 0, address = 0; - ack_APIC_irq(); - exit_idle(); - irq_enter(); - - memset(&m, 0, sizeof(m)); - rdtscll(m.tsc); - m.cpu = smp_processor_id(); + mce_setup(&m); /* assume first bank caused it */ for (bank = 0; bank < NR_BANKS; ++bank) { @@ -233,7 +231,8 @@ asmlinkage void mce_threshold_interrupt(void) /* Log the machine check that caused the threshold event. */ - do_machine_check(NULL, 0); + machine_check_poll(MCP_TIMESTAMP, + &__get_cpu_var(mce_poll_banks)); if (high & MASK_OVERFLOW_HI) { rdmsrl(address, m.misc); @@ -243,13 +242,10 @@ asmlinkage void mce_threshold_interrupt(void) + bank * NR_BLOCKS + block; mce_log(&m); - goto out; + return; } } } -out: - inc_irq_stat(irq_threshold_count); - irq_exit(); } /* diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c index aa5e287..aaa7d97 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c @@ -1,6 +1,8 @@ /* * Intel specific MCE features. * Copyright 2004 Zwane Mwaikambo <zwane@linuxpower.ca> + * Copyright (C) 2008, 2009 Intel Corporation + * Author: Andi Kleen */ #include <linux/init.h> @@ -13,6 +15,7 @@ #include <asm/hw_irq.h> #include <asm/idle.h> #include <asm/therm_throt.h> +#include <asm/apic.h> asmlinkage void smp_thermal_interrupt(void) { @@ -25,7 +28,7 @@ asmlinkage void smp_thermal_interrupt(void) rdmsrl(MSR_IA32_THERM_STATUS, msr_val); if (therm_throt_process(msr_val & 1)) - mce_log_therm_throt_event(smp_processor_id(), msr_val); + mce_log_therm_throt_event(msr_val); inc_irq_stat(irq_thermal_count); irq_exit(); @@ -85,7 +88,209 @@ static void intel_init_thermal(struct cpuinfo_x86 *c) return; } +/* + * Support for Intel Correct Machine Check Interrupts. This allows + * the CPU to raise an interrupt when a corrected machine check happened. + * Normally we pick those up using a regular polling timer. + * Also supports reliable discovery of shared banks. + */ + +static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); + +/* + * cmci_discover_lock protects against parallel discovery attempts + * which could race against each other. + */ +static DEFINE_SPINLOCK(cmci_discover_lock); + +#define CMCI_THRESHOLD 1 + +static int cmci_supported(int *banks) +{ + u64 cap; + + /* + * Vendor check is not strictly needed, but the initial + * initialization is vendor keyed and this + * makes sure none of the backdoors are entered otherwise. + */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return 0; + if (!cpu_has_apic || lapic_get_maxlvt() < 6) + return 0; + rdmsrl(MSR_IA32_MCG_CAP, cap); + *banks = min_t(unsigned, MAX_NR_BANKS, cap & 0xff); + return !!(cap & MCG_CMCI_P); +} + +/* + * The interrupt handler. This is called on every event. + * Just call the poller directly to log any events. + * This could in theory increase the threshold under high load, + * but doesn't for now. + */ +static void intel_threshold_interrupt(void) +{ + machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); + mce_notify_user(); +} + +static void print_update(char *type, int *hdr, int num) +{ + if (*hdr == 0) + printk(KERN_INFO "CPU %d MCA banks", smp_processor_id()); + *hdr = 1; + printk(KERN_CONT " %s:%d", type, num); +} + +/* + * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks + * on this CPU. Use the algorithm recommended in the SDM to discover shared + * banks. + */ +static void cmci_discover(int banks, int boot) +{ + unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); + int hdr = 0; + int i; + + spin_lock(&cmci_discover_lock); + for (i = 0; i < banks; i++) { + u64 val; + + if (test_bit(i, owned)) + continue; + + rdmsrl(MSR_IA32_MC0_CTL2 + i, val); + + /* Already owned by someone else? */ + if (val & CMCI_EN) { + if (test_and_clear_bit(i, owned) || boot) + print_update("SHD", &hdr, i); + __clear_bit(i, __get_cpu_var(mce_poll_banks)); + continue; + } + + val |= CMCI_EN | CMCI_THRESHOLD; + wrmsrl(MSR_IA32_MC0_CTL2 + i, val); + rdmsrl(MSR_IA32_MC0_CTL2 + i, val); + + /* Did the enable bit stick? -- the bank supports CMCI */ + if (val & CMCI_EN) { + if (!test_and_set_bit(i, owned) || boot) + print_update("CMCI", &hdr, i); + __clear_bit(i, __get_cpu_var(mce_poll_banks)); + } else { + WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); + } + } + spin_unlock(&cmci_discover_lock); + if (hdr) + printk(KERN_CONT "\n"); +} + +/* + * Just in case we missed an event during initialization check + * all the CMCI owned banks. + */ +void cmci_recheck(void) +{ + unsigned long flags; + int banks; + + if (!mce_available(¤t_cpu_data) || !cmci_supported(&banks)) + return; + local_irq_save(flags); + machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); + local_irq_restore(flags); +} + +/* + * Disable CMCI on this CPU for all banks it owns when it goes down. + * This allows other CPUs to claim the banks on rediscovery. + */ +void cmci_clear(void) +{ + int i; + int banks; + u64 val; + + if (!cmci_supported(&banks)) + return; + spin_lock(&cmci_discover_lock); + for (i = 0; i < banks; i++) { + if (!test_bit(i, __get_cpu_var(mce_banks_owned))) + continue; + /* Disable CMCI */ + rdmsrl(MSR_IA32_MC0_CTL2 + i, val); + val &= ~(CMCI_EN|CMCI_THRESHOLD_MASK); + wrmsrl(MSR_IA32_MC0_CTL2 + i, val); + __clear_bit(i, __get_cpu_var(mce_banks_owned)); + } + spin_unlock(&cmci_discover_lock); +} + +/* + * After a CPU went down cycle through all the others and rediscover + * Must run in process context. + */ +void cmci_rediscover(int dying) +{ + int banks; + int cpu; + cpumask_var_t old; + + if (!cmci_supported(&banks)) + return; + if (!alloc_cpumask_var(&old, GFP_KERNEL)) + return; + cpumask_copy(old, ¤t->cpus_allowed); + + for_each_online_cpu (cpu) { + if (cpu == dying) + continue; + if (set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu))) + continue; + /* Recheck banks in case CPUs don't all have the same */ + if (cmci_supported(&banks)) + cmci_discover(banks, 0); + } + + set_cpus_allowed_ptr(current, old); + free_cpumask_var(old); +} + +/* + * Reenable CMCI on this CPU in case a CPU down failed. + */ +void cmci_reenable(void) +{ + int banks; + if (cmci_supported(&banks)) + cmci_discover(banks, 0); +} + +static __cpuinit void intel_init_cmci(void) +{ + int banks; + + if (!cmci_supported(&banks)) + return; + + mce_threshold_vector = intel_threshold_interrupt; + cmci_discover(banks, 1); + /* + * For CPU #0 this runs with still disabled APIC, but that's + * ok because only the vector is set up. We still do another + * check for the banks later for CPU #0 just to make sure + * to not miss any events. + */ + apic_write(APIC_LVTCMCI, THRESHOLD_APIC_VECTOR|APIC_DM_FIXED); + cmci_recheck(); +} + void mce_intel_feature_init(struct cpuinfo_x86 *c) { intel_init_thermal(c); + intel_init_cmci(); } diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c new file mode 100644 index 0000000..23ee9e7 --- /dev/null +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -0,0 +1,29 @@ +/* + * Common corrected MCE threshold handler code: + */ +#include <linux/interrupt.h> +#include <linux/kernel.h> + +#include <asm/irq_vectors.h> +#include <asm/apic.h> +#include <asm/idle.h> +#include <asm/mce.h> + +static void default_threshold_interrupt(void) +{ + printk(KERN_ERR "Unexpected threshold interrupt at vector %x\n", + THRESHOLD_APIC_VECTOR); +} + +void (*mce_threshold_vector)(void) = default_threshold_interrupt; + +asmlinkage void mce_threshold_interrupt(void) +{ + exit_idle(); + irq_enter(); + inc_irq_stat(irq_threshold_count); + mce_threshold_vector(); + irq_exit(); + /* Ack only at the end to avoid potential reentry */ + ack_APIC_irq(); +} diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c index 169a120..87b67e3 100644 --- a/arch/x86/kernel/ds.c +++ b/arch/x86/kernel/ds.c @@ -729,7 +729,7 @@ struct pebs_tracer *ds_request_pebs(struct task_struct *task, spin_unlock_irqrestore(&ds_lock, irq); - ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts); + ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs); ds_resume_pebs(tracer); return tracer; @@ -1029,5 +1029,4 @@ void ds_copy_thread(struct task_struct *tsk, struct task_struct *father) void ds_exit_thread(struct task_struct *tsk) { - WARN_ON(tsk->thread.ds_ctx); } diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c index b205272..1736acc 100644 --- a/arch/x86/kernel/efi.c +++ b/arch/x86/kernel/efi.c @@ -469,7 +469,7 @@ void __init efi_enter_virtual_mode(void) efi_memory_desc_t *md; efi_status_t status; unsigned long size; - u64 end, systab, addr, npages; + u64 end, systab, addr, npages, end_pfn; void *p, *va; efi.systab = NULL; @@ -481,7 +481,10 @@ void __init efi_enter_virtual_mode(void) size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; - if (PFN_UP(end) <= max_low_pfn_mapped) + end_pfn = PFN_UP(end); + if (end_pfn <= max_low_pfn_mapped + || (end_pfn > (1UL << (32 - PAGE_SHIFT)) + && end_pfn <= max_pfn_mapped)) va = __va(md->phys_addr); else va = efi_ioremap(md->phys_addr, size); diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c index a4ee291..22c3b78 100644 --- a/arch/x86/kernel/efi_64.c +++ b/arch/x86/kernel/efi_64.c @@ -100,24 +100,11 @@ void __init efi_call_phys_epilog(void) void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size) { - static unsigned pages_mapped __initdata; - unsigned i, pages; - unsigned long offset; + unsigned long last_map_pfn; - pages = PFN_UP(phys_addr + size) - PFN_DOWN(phys_addr); - offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; - - if (pages_mapped + pages > MAX_EFI_IO_PAGES) + last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size); + if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) return NULL; - for (i = 0; i < pages; i++) { - __set_fixmap(FIX_EFI_IO_MAP_FIRST_PAGE - pages_mapped, - phys_addr, PAGE_KERNEL); - phys_addr += PAGE_SIZE; - pages_mapped++; - } - - return (void __iomem *)__fix_to_virt(FIX_EFI_IO_MAP_FIRST_PAGE - \ - (pages_mapped - pages)) + offset; + return (void __iomem *)__va(phys_addr); } diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 83d1836..7ba4621 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -984,6 +984,8 @@ apicinterrupt UV_BAU_MESSAGE \ #endif apicinterrupt LOCAL_TIMER_VECTOR \ apic_timer_interrupt smp_apic_timer_interrupt +apicinterrupt GENERIC_INTERRUPT_VECTOR \ + generic_interrupt smp_generic_interrupt #ifdef CONFIG_SMP apicinterrupt INVALIDATE_TLB_VECTOR_START+0 \ diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index b0f61f0..f2f8540 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -136,7 +136,7 @@ int init_fpu(struct task_struct *tsk) #ifdef CONFIG_X86_32 if (!HAVE_HWFP) { memset(tsk->thread.xstate, 0, xstate_size); - finit(); + finit_task(tsk); set_stopped_child_used_math(tsk); return 0; } diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index f13ca16..b864341 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -15,6 +15,9 @@ atomic_t irq_err_count; +/* Function pointer for generic interrupt vector handling */ +void (*generic_interrupt_extension)(void) = NULL; + /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -56,6 +59,12 @@ static int show_other_interrupts(struct seq_file *p) seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs); seq_printf(p, " Local timer interrupts\n"); #endif + if (generic_interrupt_extension) { + seq_printf(p, "PLT: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->generic_irqs); + seq_printf(p, " Platform interrupts\n"); + } #ifdef CONFIG_SMP seq_printf(p, "RES: "); for_each_online_cpu(j) @@ -163,6 +172,8 @@ u64 arch_irq_stat_cpu(unsigned int cpu) #ifdef CONFIG_X86_LOCAL_APIC sum += irq_stats(cpu)->apic_timer_irqs; #endif + if (generic_interrupt_extension) + sum += irq_stats(cpu)->generic_irqs; #ifdef CONFIG_SMP sum += irq_stats(cpu)->irq_resched_count; sum += irq_stats(cpu)->irq_call_count; @@ -226,4 +237,27 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs) return 1; } +/* + * Handler for GENERIC_INTERRUPT_VECTOR. + */ +void smp_generic_interrupt(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + ack_APIC_irq(); + + exit_idle(); + + irq_enter(); + + inc_irq_stat(generic_irqs); + + if (generic_interrupt_extension) + generic_interrupt_extension(); + + irq_exit(); + + set_irq_regs(old_regs); +} + EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 9dc6b2b..3b09634 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -16,6 +16,7 @@ #include <linux/cpu.h> #include <linux/delay.h> #include <linux/uaccess.h> +#include <linux/percpu.h> #include <asm/apic.h> @@ -55,13 +56,13 @@ static inline void print_stack_overflow(void) { } union irq_ctx { struct thread_info tinfo; u32 stack[THREAD_SIZE/sizeof(u32)]; -}; +} __attribute__((aligned(PAGE_SIZE))); -static union irq_ctx *hardirq_ctx[NR_CPUS] __read_mostly; -static union irq_ctx *softirq_ctx[NR_CPUS] __read_mostly; +static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx); +static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx); -static char softirq_stack[NR_CPUS * THREAD_SIZE] __page_aligned_bss; -static char hardirq_stack[NR_CPUS * THREAD_SIZE] __page_aligned_bss; +static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, hardirq_stack); +static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, softirq_stack); static void call_on_stack(void *func, void *stack) { @@ -81,7 +82,7 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) u32 *isp, arg1, arg2; curctx = (union irq_ctx *) current_thread_info(); - irqctx = hardirq_ctx[smp_processor_id()]; + irqctx = __get_cpu_var(hardirq_ctx); /* * this is where we switch to the IRQ stack. However, if we are @@ -125,34 +126,34 @@ void __cpuinit irq_ctx_init(int cpu) { union irq_ctx *irqctx; - if (hardirq_ctx[cpu]) + if (per_cpu(hardirq_ctx, cpu)) return; - irqctx = (union irq_ctx*) &hardirq_stack[cpu*THREAD_SIZE]; + irqctx = &per_cpu(hardirq_stack, cpu); irqctx->tinfo.task = NULL; irqctx->tinfo.exec_domain = NULL; irqctx->tinfo.cpu = cpu; irqctx->tinfo.preempt_count = HARDIRQ_OFFSET; irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); - hardirq_ctx[cpu] = irqctx; + per_cpu(hardirq_ctx, cpu) = irqctx; - irqctx = (union irq_ctx *) &softirq_stack[cpu*THREAD_SIZE]; + irqctx = &per_cpu(softirq_stack, cpu); irqctx->tinfo.task = NULL; irqctx->tinfo.exec_domain = NULL; irqctx->tinfo.cpu = cpu; irqctx->tinfo.preempt_count = 0; irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); - softirq_ctx[cpu] = irqctx; + per_cpu(softirq_ctx, cpu) = irqctx; printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n", - cpu, hardirq_ctx[cpu], softirq_ctx[cpu]); + cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu)); } void irq_ctx_exit(int cpu) { - hardirq_ctx[cpu] = NULL; + per_cpu(hardirq_ctx, cpu) = NULL; } asmlinkage void do_softirq(void) @@ -169,7 +170,7 @@ asmlinkage void do_softirq(void) if (local_softirq_pending()) { curctx = current_thread_info(); - irqctx = softirq_ctx[smp_processor_id()]; + irqctx = __get_cpu_var(softirq_ctx); irqctx->tinfo.task = curctx->task; irqctx->tinfo.previous_esp = current_stack_pointer; diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c index 50b8c3a..bc13261 100644 --- a/arch/x86/kernel/irqinit_32.c +++ b/arch/x86/kernel/irqinit_32.c @@ -175,6 +175,9 @@ void __init native_init_IRQ(void) /* self generated IPI for local APIC timer */ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); + /* generic IPI for platform specific use */ + alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt); + /* IPI vectors for APIC spurious and error interrupts */ alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c index da481a1..c7a49e0 100644 --- a/arch/x86/kernel/irqinit_64.c +++ b/arch/x86/kernel/irqinit_64.c @@ -147,6 +147,9 @@ static void __init apic_intr_init(void) /* self generated IPI for local APIC timer */ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); + /* generic IPI for platform specific use */ + alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt); + /* IPI vectors for APIC spurious and error interrupts */ alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index f5fc8c7..e7368c1 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -14,12 +14,12 @@ #include <linux/ftrace.h> #include <linux/suspend.h> #include <linux/gfp.h> +#include <linux/io.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> -#include <asm/io.h> #include <asm/apic.h> #include <asm/cpufeature.h> #include <asm/desc.h> @@ -63,7 +63,7 @@ static void load_segments(void) "\tmovl %%eax,%%fs\n" "\tmovl %%eax,%%gs\n" "\tmovl %%eax,%%ss\n" - ::: "eax", "memory"); + : : : "eax", "memory"); #undef STR #undef __STR } @@ -205,7 +205,8 @@ void machine_kexec(struct kimage *image) if (image->preserve_context) { #ifdef CONFIG_X86_IO_APIC - /* We need to put APICs in legacy mode so that we can + /* + * We need to put APICs in legacy mode so that we can * get timer interrupts in second kernel. kexec/kdump * paths already have calls to disable_IO_APIC() in * one form or other. kexec jump path also need @@ -227,7 +228,8 @@ void machine_kexec(struct kimage *image) page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) << PAGE_SHIFT); - /* The segment registers are funny things, they have both a + /* + * The segment registers are funny things, they have both a * visible and an invisible part. Whenever the visible part is * set to a specific selector, the invisible part is loaded * with from a table in memory. At no other time is the @@ -237,11 +239,12 @@ void machine_kexec(struct kimage *image) * segments, before I zap the gdt with an invalid value. */ load_segments(); - /* The gdt & idt are now invalid. + /* + * The gdt & idt are now invalid. * If you want to load them you must set up your own idt & gdt. */ - set_gdt(phys_to_virt(0),0); - set_idt(phys_to_virt(0),0); + set_gdt(phys_to_virt(0), 0); + set_idt(phys_to_virt(0), 0); /* now call it */ image->start = relocate_kernel_ptr((unsigned long)image->head, diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 6993d51..89cea4d 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -12,11 +12,47 @@ #include <linux/reboot.h> #include <linux/numa.h> #include <linux/ftrace.h> +#include <linux/io.h> +#include <linux/suspend.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> -#include <asm/io.h> + +static int init_one_level2_page(struct kimage *image, pgd_t *pgd, + unsigned long addr) +{ + pud_t *pud; + pmd_t *pmd; + struct page *page; + int result = -ENOMEM; + + addr &= PMD_MASK; + pgd += pgd_index(addr); + if (!pgd_present(*pgd)) { + page = kimage_alloc_control_pages(image, 0); + if (!page) + goto out; + pud = (pud_t *)page_address(page); + memset(pud, 0, PAGE_SIZE); + set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); + } + pud = pud_offset(pgd, addr); + if (!pud_present(*pud)) { + page = kimage_alloc_control_pages(image, 0); + if (!page) + goto out; + pmd = (pmd_t *)page_address(page); + memset(pmd, 0, PAGE_SIZE); + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); + } + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) + set_pmd(pmd, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC)); + result = 0; +out: + return result; +} static void init_level2_page(pmd_t *level2p, unsigned long addr) { @@ -83,9 +119,8 @@ static int init_level4_page(struct kimage *image, pgd_t *level4p, } level3p = (pud_t *)page_address(page); result = init_level3_page(image, level3p, addr, last_addr); - if (result) { + if (result) goto out; - } set_pgd(level4p++, __pgd(__pa(level3p) | _KERNPG_TABLE)); addr += PGDIR_SIZE; } @@ -156,6 +191,13 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) result = init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT); if (result) return result; + /* + * image->start may be outside 0 ~ max_pfn, for example when + * jump back to original kernel from kexeced kernel + */ + result = init_one_level2_page(image, level4p, image->start); + if (result) + return result; return init_transition_pgtable(image, level4p); } @@ -229,20 +271,45 @@ void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; void *control_page; + int save_ftrace_enabled; - tracer_disable(); +#ifdef CONFIG_KEXEC_JUMP + if (kexec_image->preserve_context) + save_processor_state(); +#endif + + save_ftrace_enabled = __ftrace_enabled_save(); /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); + if (image->preserve_context) { +#ifdef CONFIG_X86_IO_APIC + /* + * We need to put APICs in legacy mode so that we can + * get timer interrupts in second kernel. kexec/kdump + * paths already have calls to disable_IO_APIC() in + * one form or other. kexec jump path also need + * one. + */ + disable_IO_APIC(); +#endif + } + control_page = page_address(image->control_code_page) + PAGE_SIZE; - memcpy(control_page, relocate_kernel, PAGE_SIZE); + memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE); page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page); + page_list[VA_CONTROL_PAGE] = (unsigned long)control_page; page_list[PA_TABLE_PAGE] = (unsigned long)__pa(page_address(image->control_code_page)); - /* The segment registers are funny things, they have both a + if (image->type == KEXEC_TYPE_DEFAULT) + page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) + << PAGE_SHIFT); + + /* + * The segment registers are funny things, they have both a * visible and an invisible part. Whenever the visible part is * set to a specific selector, the invisible part is loaded * with from a table in memory. At no other time is the @@ -252,15 +319,25 @@ void machine_kexec(struct kimage *image) * segments, before I zap the gdt with an invalid value. */ load_segments(); - /* The gdt & idt are now invalid. + /* + * The gdt & idt are now invalid. * If you want to load them you must set up your own idt & gdt. */ - set_gdt(phys_to_virt(0),0); - set_idt(phys_to_virt(0),0); + set_gdt(phys_to_virt(0), 0); + set_idt(phys_to_virt(0), 0); /* now call it */ - relocate_kernel((unsigned long)image->head, (unsigned long)page_list, - image->start); + image->start = relocate_kernel((unsigned long)image->head, + (unsigned long)page_list, + image->start, + image->preserve_context); + +#ifdef CONFIG_KEXEC_JUMP + if (kexec_image->preserve_context) + restore_processor_state(); +#endif + + __ftrace_enabled_restore(save_ftrace_enabled); } void arch_crash_save_vmcoreinfo(void) diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 37cb1bd..e819240 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -558,6 +558,19 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) static struct mpf_intel *mpf_found; +static unsigned long __init get_mpc_size(unsigned long physptr) +{ + struct mpc_table *mpc; + unsigned long size; + + mpc = early_ioremap(physptr, PAGE_SIZE); + size = mpc->length; + early_iounmap(mpc, PAGE_SIZE); + apic_printk(APIC_VERBOSE, " mpc: %lx-%lx\n", physptr, physptr + size); + + return size; +} + /* * Scan the memory blocks for an SMP configuration block. */ @@ -611,12 +624,16 @@ static void __init __get_smp_config(unsigned int early) construct_default_ISA_mptable(mpf->feature1); } else if (mpf->physptr) { + struct mpc_table *mpc; + unsigned long size; + size = get_mpc_size(mpf->physptr); + mpc = early_ioremap(mpf->physptr, size); /* * Read the physical hardware table. Anything here will * override the defaults. */ - if (!smp_read_mpc(phys_to_virt(mpf->physptr), early)) { + if (!smp_read_mpc(mpc, early)) { #ifdef CONFIG_X86_LOCAL_APIC smp_found_config = 0; #endif @@ -624,8 +641,10 @@ static void __init __get_smp_config(unsigned int early) "BIOS bug, MP table errors detected!...\n"); printk(KERN_ERR "... disabling SMP support. " "(tell your hw vendor)\n"); + early_iounmap(mpc, size); return; } + early_iounmap(mpc, size); if (early) return; @@ -697,10 +716,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, if (!reserve) return 1; - reserve_bootmem_generic(virt_to_phys(mpf), PAGE_SIZE, + reserve_bootmem_generic(virt_to_phys(mpf), sizeof(*mpf), BOOTMEM_DEFAULT); if (mpf->physptr) { - unsigned long size = PAGE_SIZE; + unsigned long size = get_mpc_size(mpf->physptr); #ifdef CONFIG_X86_32 /* * We cannot access to MPC table to compute diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 1cc18d4..2aef36d 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -216,6 +216,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq"), }, }, + { /* Handle problems with rebooting on Dell XPS710 */ + .callback = set_bios_reboot, + .ident = "Dell XPS710", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"), + }, + }, { } }; diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index 2064d0a..4123553 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -17,7 +17,8 @@ #define PTR(x) (x << 2) -/* control_page + KEXEC_CONTROL_CODE_MAX_SIZE +/* + * control_page + KEXEC_CONTROL_CODE_MAX_SIZE * ~ control_page + PAGE_SIZE are used as data storage and stack for * jumping back */ @@ -76,8 +77,10 @@ relocate_kernel: movl %eax, CP_PA_SWAP_PAGE(%edi) movl %ebx, CP_PA_BACKUP_PAGES_MAP(%edi) - /* get physical address of control page now */ - /* this is impossible after page table switch */ + /* + * get physical address of control page now + * this is impossible after page table switch + */ movl PTR(PA_CONTROL_PAGE)(%ebp), %edi /* switch to new set of page tables */ @@ -97,7 +100,8 @@ identity_mapped: /* store the start address on the stack */ pushl %edx - /* Set cr0 to a known state: + /* + * Set cr0 to a known state: * - Paging disabled * - Alignment check disabled * - Write protect disabled @@ -113,7 +117,8 @@ identity_mapped: /* clear cr4 if applicable */ testl %ecx, %ecx jz 1f - /* Set cr4 to a known state: + /* + * Set cr4 to a known state: * Setting everything to zero seems safe. */ xorl %eax, %eax @@ -132,15 +137,18 @@ identity_mapped: call swap_pages addl $8, %esp - /* To be certain of avoiding problems with self-modifying code + /* + * To be certain of avoiding problems with self-modifying code * I need to execute a serializing instruction here. * So I flush the TLB, it's handy, and not processor dependent. */ xorl %eax, %eax movl %eax, %cr3 - /* set all of the registers to known values */ - /* leave %esp alone */ + /* + * set all of the registers to known values + * leave %esp alone + */ testl %esi, %esi jnz 1f diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index d32cfb2..4de8f5b 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -19,29 +19,77 @@ #define PTR(x) (x << 3) #define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) +/* + * control_page + KEXEC_CONTROL_CODE_MAX_SIZE + * ~ control_page + PAGE_SIZE are used as data storage and stack for + * jumping back + */ +#define DATA(offset) (KEXEC_CONTROL_CODE_MAX_SIZE+(offset)) + +/* Minimal CPU state */ +#define RSP DATA(0x0) +#define CR0 DATA(0x8) +#define CR3 DATA(0x10) +#define CR4 DATA(0x18) + +/* other data */ +#define CP_PA_TABLE_PAGE DATA(0x20) +#define CP_PA_SWAP_PAGE DATA(0x28) +#define CP_PA_BACKUP_PAGES_MAP DATA(0x30) + .text .align PAGE_SIZE .code64 .globl relocate_kernel relocate_kernel: - /* %rdi indirection_page + /* + * %rdi indirection_page * %rsi page_list * %rdx start address + * %rcx preserve_context */ + /* Save the CPU context, used for jumping back */ + pushq %rbx + pushq %rbp + pushq %r12 + pushq %r13 + pushq %r14 + pushq %r15 + pushf + + movq PTR(VA_CONTROL_PAGE)(%rsi), %r11 + movq %rsp, RSP(%r11) + movq %cr0, %rax + movq %rax, CR0(%r11) + movq %cr3, %rax + movq %rax, CR3(%r11) + movq %cr4, %rax + movq %rax, CR4(%r11) + /* zero out flags, and disable interrupts */ pushq $0 popfq - /* get physical address of control page now */ - /* this is impossible after page table switch */ + /* + * get physical address of control page now + * this is impossible after page table switch + */ movq PTR(PA_CONTROL_PAGE)(%rsi), %r8 /* get physical address of page table now too */ - movq PTR(PA_TABLE_PAGE)(%rsi), %rcx + movq PTR(PA_TABLE_PAGE)(%rsi), %r9 + + /* get physical address of swap page now */ + movq PTR(PA_SWAP_PAGE)(%rsi), %r10 + + /* save some information for jumping back */ + movq %r9, CP_PA_TABLE_PAGE(%r11) + movq %r10, CP_PA_SWAP_PAGE(%r11) + movq %rdi, CP_PA_BACKUP_PAGES_MAP(%r11) /* Switch to the identity mapped page tables */ - movq %rcx, %cr3 + movq %r9, %cr3 /* setup a new stack at the end of the physical control page */ lea PAGE_SIZE(%r8), %rsp @@ -55,7 +103,8 @@ identity_mapped: /* store the start address on the stack */ pushq %rdx - /* Set cr0 to a known state: + /* + * Set cr0 to a known state: * - Paging enabled * - Alignment check disabled * - Write protect disabled @@ -68,7 +117,8 @@ identity_mapped: orl $(X86_CR0_PG | X86_CR0_PE), %eax movq %rax, %cr0 - /* Set cr4 to a known state: + /* + * Set cr4 to a known state: * - physical address extension enabled */ movq $X86_CR4_PAE, %rax @@ -78,9 +128,87 @@ identity_mapped: 1: /* Flush the TLB (needed?) */ - movq %rcx, %cr3 + movq %r9, %cr3 + + movq %rcx, %r11 + call swap_pages + + /* + * To be certain of avoiding problems with self-modifying code + * I need to execute a serializing instruction here. + * So I flush the TLB by reloading %cr3 here, it's handy, + * and not processor dependent. + */ + movq %cr3, %rax + movq %rax, %cr3 + + /* + * set all of the registers to known values + * leave %rsp alone + */ + + testq %r11, %r11 + jnz 1f + xorq %rax, %rax + xorq %rbx, %rbx + xorq %rcx, %rcx + xorq %rdx, %rdx + xorq %rsi, %rsi + xorq %rdi, %rdi + xorq %rbp, %rbp + xorq %r8, %r8 + xorq %r9, %r9 + xorq %r10, %r9 + xorq %r11, %r11 + xorq %r12, %r12 + xorq %r13, %r13 + xorq %r14, %r14 + xorq %r15, %r15 + + ret + +1: + popq %rdx + leaq PAGE_SIZE(%r10), %rsp + call *%rdx + + /* get the re-entry point of the peer system */ + movq 0(%rsp), %rbp + call 1f +1: + popq %r8 + subq $(1b - relocate_kernel), %r8 + movq CP_PA_SWAP_PAGE(%r8), %r10 + movq CP_PA_BACKUP_PAGES_MAP(%r8), %rdi + movq CP_PA_TABLE_PAGE(%r8), %rax + movq %rax, %cr3 + lea PAGE_SIZE(%r8), %rsp + call swap_pages + movq $virtual_mapped, %rax + pushq %rax + ret + +virtual_mapped: + movq RSP(%r8), %rsp + movq CR4(%r8), %rax + movq %rax, %cr4 + movq CR3(%r8), %rax + movq CR0(%r8), %r8 + movq %rax, %cr3 + movq %r8, %cr0 + movq %rbp, %rax + + popf + popq %r15 + popq %r14 + popq %r13 + popq %r12 + popq %rbp + popq %rbx + ret /* Do the copies */ +swap_pages: movq %rdi, %rcx /* Put the page_list in %rcx */ xorq %rdi, %rdi xorq %rsi, %rsi @@ -112,36 +240,27 @@ identity_mapped: movq %rcx, %rsi /* For ever source page do a copy */ andq $0xfffffffffffff000, %rsi + movq %rdi, %rdx + movq %rsi, %rax + + movq %r10, %rdi movq $512, %rcx rep ; movsq - jmp 0b -3: - - /* To be certain of avoiding problems with self-modifying code - * I need to execute a serializing instruction here. - * So I flush the TLB by reloading %cr3 here, it's handy, - * and not processor dependent. - */ - movq %cr3, %rax - movq %rax, %cr3 - /* set all of the registers to known values */ - /* leave %rsp alone */ + movq %rax, %rdi + movq %rdx, %rsi + movq $512, %rcx + rep ; movsq - xorq %rax, %rax - xorq %rbx, %rbx - xorq %rcx, %rcx - xorq %rdx, %rdx - xorq %rsi, %rsi - xorq %rdi, %rdi - xorq %rbp, %rbp - xorq %r8, %r8 - xorq %r9, %r9 - xorq %r10, %r9 - xorq %r11, %r11 - xorq %r12, %r12 - xorq %r13, %r13 - xorq %r14, %r14 - xorq %r15, %r15 + movq %rdx, %rdi + movq %r10, %rsi + movq $512, %rcx + rep ; movsq + lea PAGE_SIZE(%rax), %rsi + jmp 0b +3: ret + + .globl kexec_control_code_size +.set kexec_control_code_size, . - relocate_kernel diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 4c54bc0..f28c56e 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -202,7 +202,9 @@ struct ist_info ist_info; #endif #else -struct cpuinfo_x86 boot_cpu_data __read_mostly; +struct cpuinfo_x86 boot_cpu_data __read_mostly = { + .x86_phys_bits = MAX_PHYSMEM_BITS, +}; EXPORT_SYMBOL(boot_cpu_data); #endif @@ -770,6 +772,9 @@ void __init setup_arch(char **cmdline_p) finish_e820_parsing(); + if (efi_enabled) + efi_init(); + dmi_scan_machine(); dmi_check_system(bad_bios_dmi_table); @@ -789,8 +794,6 @@ void __init setup_arch(char **cmdline_p) insert_resource(&iomem_resource, &data_resource); insert_resource(&iomem_resource, &bss_resource); - if (efi_enabled) - efi_init(); #ifdef CONFIG_X86_32 if (ppro_with_ram_bug()) { diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index d992e6c..efa615f 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -7,6 +7,7 @@ #include <linux/crash_dump.h> #include <linux/smp.h> #include <linux/topology.h> +#include <linux/pfn.h> #include <asm/sections.h> #include <asm/processor.h> #include <asm/setup.h> @@ -41,6 +42,352 @@ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = { }; EXPORT_SYMBOL(__per_cpu_offset); +/* + * On x86_64 symbols referenced from code should be reachable using + * 32bit relocations. Reserve space for static percpu variables in + * modules so that they are always served from the first chunk which + * is located at the percpu segment base. On x86_32, anything can + * address anywhere. No need to reserve space in the first chunk. + */ +#ifdef CONFIG_X86_64 +#define PERCPU_FIRST_CHUNK_RESERVE PERCPU_MODULE_RESERVE +#else +#define PERCPU_FIRST_CHUNK_RESERVE 0 +#endif + +/** + * pcpu_need_numa - determine percpu allocation needs to consider NUMA + * + * If NUMA is not configured or there is only one NUMA node available, + * there is no reason to consider NUMA. This function determines + * whether percpu allocation should consider NUMA or not. + * + * RETURNS: + * true if NUMA should be considered; otherwise, false. + */ +static bool __init pcpu_need_numa(void) +{ +#ifdef CONFIG_NEED_MULTIPLE_NODES + pg_data_t *last = NULL; + unsigned int cpu; + + for_each_possible_cpu(cpu) { + int node = early_cpu_to_node(cpu); + + if (node_online(node) && NODE_DATA(node) && + last && last != NODE_DATA(node)) + return true; + + last = NODE_DATA(node); + } +#endif + return false; +} + +/** + * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu + * @cpu: cpu to allocate for + * @size: size allocation in bytes + * @align: alignment + * + * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper + * does the right thing for NUMA regardless of the current + * configuration. + * + * RETURNS: + * Pointer to the allocated area on success, NULL on failure. + */ +static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, + unsigned long align) +{ + const unsigned long goal = __pa(MAX_DMA_ADDRESS); +#ifdef CONFIG_NEED_MULTIPLE_NODES + int node = early_cpu_to_node(cpu); + void *ptr; + + if (!node_online(node) || !NODE_DATA(node)) { + ptr = __alloc_bootmem_nopanic(size, align, goal); + pr_info("cpu %d has no node %d or node-local memory\n", + cpu, node); + pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", + cpu, size, __pa(ptr)); + } else { + ptr = __alloc_bootmem_node_nopanic(NODE_DATA(node), + size, align, goal); + pr_debug("per cpu data for cpu%d %lu bytes on node%d at " + "%016lx\n", cpu, size, node, __pa(ptr)); + } + return ptr; +#else + return __alloc_bootmem_nopanic(size, align, goal); +#endif +} + +/* + * Remap allocator + * + * This allocator uses PMD page as unit. A PMD page is allocated for + * each cpu and each is remapped into vmalloc area using PMD mapping. + * As PMD page is quite large, only part of it is used for the first + * chunk. Unused part is returned to the bootmem allocator. + * + * So, the PMD pages are mapped twice - once to the physical mapping + * and to the vmalloc area for the first percpu chunk. The double + * mapping does add one more PMD TLB entry pressure but still is much + * better than only using 4k mappings while still being NUMA friendly. + */ +#ifdef CONFIG_NEED_MULTIPLE_NODES +static size_t pcpur_size __initdata; +static void **pcpur_ptrs __initdata; + +static struct page * __init pcpur_get_page(unsigned int cpu, int pageno) +{ + size_t off = (size_t)pageno << PAGE_SHIFT; + + if (off >= pcpur_size) + return NULL; + + return virt_to_page(pcpur_ptrs[cpu] + off); +} + +static ssize_t __init setup_pcpu_remap(size_t static_size) +{ + static struct vm_struct vm; + pg_data_t *last; + size_t ptrs_size, dyn_size; + unsigned int cpu; + ssize_t ret; + + /* + * If large page isn't supported, there's no benefit in doing + * this. Also, on non-NUMA, embedding is better. + */ + if (!cpu_has_pse || pcpu_need_numa()) + return -EINVAL; + + last = NULL; + for_each_possible_cpu(cpu) { + int node = early_cpu_to_node(cpu); + + if (node_online(node) && NODE_DATA(node) && + last && last != NODE_DATA(node)) + goto proceed; + + last = NODE_DATA(node); + } + return -EINVAL; + +proceed: + /* + * Currently supports only single page. Supporting multiple + * pages won't be too difficult if it ever becomes necessary. + */ + pcpur_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE + + PERCPU_DYNAMIC_RESERVE); + if (pcpur_size > PMD_SIZE) { + pr_warning("PERCPU: static data is larger than large page, " + "can't use large page\n"); + return -EINVAL; + } + dyn_size = pcpur_size - static_size - PERCPU_FIRST_CHUNK_RESERVE; + + /* allocate pointer array and alloc large pages */ + ptrs_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpur_ptrs[0])); + pcpur_ptrs = alloc_bootmem(ptrs_size); + + for_each_possible_cpu(cpu) { + pcpur_ptrs[cpu] = pcpu_alloc_bootmem(cpu, PMD_SIZE, PMD_SIZE); + if (!pcpur_ptrs[cpu]) + goto enomem; + + /* + * Only use pcpur_size bytes and give back the rest. + * + * Ingo: The 2MB up-rounding bootmem is needed to make + * sure the partial 2MB page is still fully RAM - it's + * not well-specified to have a PAT-incompatible area + * (unmapped RAM, device memory, etc.) in that hole. + */ + free_bootmem(__pa(pcpur_ptrs[cpu] + pcpur_size), + PMD_SIZE - pcpur_size); + + memcpy(pcpur_ptrs[cpu], __per_cpu_load, static_size); + } + + /* allocate address and map */ + vm.flags = VM_ALLOC; + vm.size = num_possible_cpus() * PMD_SIZE; + vm_area_register_early(&vm, PMD_SIZE); + + for_each_possible_cpu(cpu) { + pmd_t *pmd; + + pmd = populate_extra_pmd((unsigned long)vm.addr + + cpu * PMD_SIZE); + set_pmd(pmd, pfn_pmd(page_to_pfn(virt_to_page(pcpur_ptrs[cpu])), + PAGE_KERNEL_LARGE)); + } + + /* we're ready, commit */ + pr_info("PERCPU: Remapped at %p with large pages, static data " + "%zu bytes\n", vm.addr, static_size); + + ret = pcpu_setup_first_chunk(pcpur_get_page, static_size, + PERCPU_FIRST_CHUNK_RESERVE, + PMD_SIZE, dyn_size, vm.addr, NULL); + goto out_free_ar; + +enomem: + for_each_possible_cpu(cpu) + if (pcpur_ptrs[cpu]) + free_bootmem(__pa(pcpur_ptrs[cpu]), PMD_SIZE); + ret = -ENOMEM; +out_free_ar: + free_bootmem(__pa(pcpur_ptrs), ptrs_size); + return ret; +} +#else +static ssize_t __init setup_pcpu_remap(size_t static_size) +{ + return -EINVAL; +} +#endif + +/* + * Embedding allocator + * + * The first chunk is sized to just contain the static area plus + * module and dynamic reserves, and allocated as a contiguous area + * using bootmem allocator and used as-is without being mapped into + * vmalloc area. This enables the first chunk to piggy back on the + * linear physical PMD mapping and doesn't add any additional pressure + * to TLB. Note that if the needed size is smaller than the minimum + * unit size, the leftover is returned to the bootmem allocator. + */ +static void *pcpue_ptr __initdata; +static size_t pcpue_size __initdata; +static size_t pcpue_unit_size __initdata; + +static struct page * __init pcpue_get_page(unsigned int cpu, int pageno) +{ + size_t off = (size_t)pageno << PAGE_SHIFT; + + if (off >= pcpue_size) + return NULL; + + return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size + off); +} + +static ssize_t __init setup_pcpu_embed(size_t static_size) +{ + unsigned int cpu; + size_t dyn_size; + + /* + * If large page isn't supported, there's no benefit in doing + * this. Also, embedding allocation doesn't play well with + * NUMA. + */ + if (!cpu_has_pse || pcpu_need_numa()) + return -EINVAL; + + /* allocate and copy */ + pcpue_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE + + PERCPU_DYNAMIC_RESERVE); + pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE); + dyn_size = pcpue_size - static_size - PERCPU_FIRST_CHUNK_RESERVE; + + pcpue_ptr = pcpu_alloc_bootmem(0, num_possible_cpus() * pcpue_unit_size, + PAGE_SIZE); + if (!pcpue_ptr) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + void *ptr = pcpue_ptr + cpu * pcpue_unit_size; + + free_bootmem(__pa(ptr + pcpue_size), + pcpue_unit_size - pcpue_size); + memcpy(ptr, __per_cpu_load, static_size); + } + + /* we're ready, commit */ + pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n", + pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size); + + return pcpu_setup_first_chunk(pcpue_get_page, static_size, + PERCPU_FIRST_CHUNK_RESERVE, + pcpue_unit_size, dyn_size, + pcpue_ptr, NULL); +} + +/* + * 4k page allocator + * + * This is the basic allocator. Static percpu area is allocated + * page-by-page and most of initialization is done by the generic + * setup function. + */ +static struct page **pcpu4k_pages __initdata; +static int pcpu4k_nr_static_pages __initdata; + +static struct page * __init pcpu4k_get_page(unsigned int cpu, int pageno) +{ + if (pageno < pcpu4k_nr_static_pages) + return pcpu4k_pages[cpu * pcpu4k_nr_static_pages + pageno]; + return NULL; +} + +static void __init pcpu4k_populate_pte(unsigned long addr) +{ + populate_extra_pte(addr); +} + +static ssize_t __init setup_pcpu_4k(size_t static_size) +{ + size_t pages_size; + unsigned int cpu; + int i, j; + ssize_t ret; + + pcpu4k_nr_static_pages = PFN_UP(static_size); + + /* unaligned allocations can't be freed, round up to page size */ + pages_size = PFN_ALIGN(pcpu4k_nr_static_pages * num_possible_cpus() + * sizeof(pcpu4k_pages[0])); + pcpu4k_pages = alloc_bootmem(pages_size); + + /* allocate and copy */ + j = 0; + for_each_possible_cpu(cpu) + for (i = 0; i < pcpu4k_nr_static_pages; i++) { + void *ptr; + + ptr = pcpu_alloc_bootmem(cpu, PAGE_SIZE, PAGE_SIZE); + if (!ptr) + goto enomem; + + memcpy(ptr, __per_cpu_load + i * PAGE_SIZE, PAGE_SIZE); + pcpu4k_pages[j++] = virt_to_page(ptr); + } + + /* we're ready, commit */ + pr_info("PERCPU: Allocated %d 4k pages, static data %zu bytes\n", + pcpu4k_nr_static_pages, static_size); + + ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size, + PERCPU_FIRST_CHUNK_RESERVE, -1, -1, NULL, + pcpu4k_populate_pte); + goto out_free_ar; + +enomem: + while (--j >= 0) + free_bootmem(__pa(page_address(pcpu4k_pages[j])), PAGE_SIZE); + ret = -ENOMEM; +out_free_ar: + free_bootmem(__pa(pcpu4k_pages), pages_size); + return ret; +} + static inline void setup_percpu_segment(int cpu) { #ifdef CONFIG_X86_32 @@ -61,38 +408,35 @@ static inline void setup_percpu_segment(int cpu) */ void __init setup_per_cpu_areas(void) { - ssize_t size; - char *ptr; - int cpu; - - /* Copy section for each CPU (we discard the original) */ - size = roundup(PERCPU_ENOUGH_ROOM, PAGE_SIZE); + size_t static_size = __per_cpu_end - __per_cpu_start; + unsigned int cpu; + unsigned long delta; + size_t pcpu_unit_size; + ssize_t ret; pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n", NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids); - pr_info("PERCPU: Allocating %zd bytes of per cpu data\n", size); + /* + * Allocate percpu area. If PSE is supported, try to make use + * of large page mappings. Please read comments on top of + * each allocator for details. + */ + ret = setup_pcpu_remap(static_size); + if (ret < 0) + ret = setup_pcpu_embed(static_size); + if (ret < 0) + ret = setup_pcpu_4k(static_size); + if (ret < 0) + panic("cannot allocate static percpu area (%zu bytes, err=%zd)", + static_size, ret); - for_each_possible_cpu(cpu) { -#ifndef CONFIG_NEED_MULTIPLE_NODES - ptr = alloc_bootmem_pages(size); -#else - int node = early_cpu_to_node(cpu); - if (!node_online(node) || !NODE_DATA(node)) { - ptr = alloc_bootmem_pages(size); - pr_info("cpu %d has no node %d or node-local memory\n", - cpu, node); - pr_debug("per cpu data for cpu%d at %016lx\n", - cpu, __pa(ptr)); - } else { - ptr = alloc_bootmem_pages_node(NODE_DATA(node), size); - pr_debug("per cpu data for cpu%d on node%d at %016lx\n", - cpu, node, __pa(ptr)); - } -#endif + pcpu_unit_size = ret; - memcpy(ptr, __per_cpu_load, __per_cpu_end - __per_cpu_start); - per_cpu_offset(cpu) = ptr - __per_cpu_start; + /* alrighty, percpu areas up and running */ + delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; + for_each_possible_cpu(cpu) { + per_cpu_offset(cpu) = delta + cpu * pcpu_unit_size; per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu); per_cpu(cpu_number, cpu) = cpu; setup_percpu_segment(cpu); @@ -125,8 +469,6 @@ void __init setup_per_cpu_areas(void) */ if (cpu == boot_cpu_id) switch_to_new_gdt(cpu); - - DBG("PERCPU: cpu %4d %p\n", cpu, ptr); } /* indicate the early static arrays will soon be gone */ diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 249334f..ef7d101 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -114,10 +114,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info); atomic_t init_deasserted; - -/* Set if we find a B stepping CPU */ -static int __cpuinitdata smp_b_stepping; - #if defined(CONFIG_NUMA) && defined(CONFIG_X86_32) /* which logical CPUs are on which nodes */ @@ -271,8 +267,6 @@ static void __cpuinit smp_callin(void) cpumask_set_cpu(cpuid, cpu_callin_mask); } -static int __cpuinitdata unsafe_smp; - /* * Activate a secondary processor. */ @@ -340,76 +334,6 @@ notrace static void __cpuinit start_secondary(void *unused) cpu_idle(); } -static void __cpuinit smp_apply_quirks(struct cpuinfo_x86 *c) -{ - /* - * Mask B, Pentium, but not Pentium MMX - */ - if (c->x86_vendor == X86_VENDOR_INTEL && - c->x86 == 5 && - c->x86_mask >= 1 && c->x86_mask <= 4 && - c->x86_model <= 3) - /* - * Remember we have B step Pentia with bugs - */ - smp_b_stepping = 1; - - /* - * Certain Athlons might work (for various values of 'work') in SMP - * but they are not certified as MP capable. - */ - if ((c->x86_vendor == X86_VENDOR_AMD) && (c->x86 == 6)) { - - if (num_possible_cpus() == 1) - goto valid_k7; - - /* Athlon 660/661 is valid. */ - if ((c->x86_model == 6) && ((c->x86_mask == 0) || - (c->x86_mask == 1))) - goto valid_k7; - - /* Duron 670 is valid */ - if ((c->x86_model == 7) && (c->x86_mask == 0)) - goto valid_k7; - - /* - * Athlon 662, Duron 671, and Athlon >model 7 have capability - * bit. It's worth noting that the A5 stepping (662) of some - * Athlon XP's have the MP bit set. - * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for - * more. - */ - if (((c->x86_model == 6) && (c->x86_mask >= 2)) || - ((c->x86_model == 7) && (c->x86_mask >= 1)) || - (c->x86_model > 7)) - if (cpu_has_mp) - goto valid_k7; - - /* If we get here, not a certified SMP capable AMD system. */ - unsafe_smp = 1; - } - -valid_k7: - ; -} - -static void __cpuinit smp_checks(void) -{ - if (smp_b_stepping) - printk(KERN_WARNING "WARNING: SMP operation may be unreliable" - "with B stepping processors.\n"); - - /* - * Don't taint if we are running SMP kernel on a single non-MP - * approved Athlon - */ - if (unsafe_smp && num_online_cpus() > 1) { - printk(KERN_INFO "WARNING: This combination of AMD" - "processors is not suitable for SMP.\n"); - add_taint(TAINT_UNSAFE_SMP); - } -} - /* * The bootstrap kernel entry code has set these up. Save them for * a given CPU @@ -423,7 +347,6 @@ void __cpuinit smp_store_cpu_info(int id) c->cpu_index = id; if (id != 0) identify_secondary_cpu(c); - smp_apply_quirks(c); } @@ -1193,7 +1116,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus) pr_debug("Boot done.\n"); impress_friends(); - smp_checks(); #ifdef CONFIG_X86_IO_APIC setup_ioapic_dest(); #endif diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index f04549a..d038b9c 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -314,8 +314,6 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, int locals = 0; struct bau_desc *bau_desc; - WARN_ON(!in_atomic()); - cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu)); uv_cpu = uv_blade_processor_id(); diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c new file mode 100644 index 0000000..2ffb6c5 --- /dev/null +++ b/arch/x86/kernel/uv_time.c @@ -0,0 +1,393 @@ +/* + * SGI RTC clock/timer routines. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Copyright (c) 2009 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) Dimitri Sivanich + */ +#include <linux/clockchips.h> + +#include <asm/uv/uv_mmrs.h> +#include <asm/uv/uv_hub.h> +#include <asm/uv/bios.h> +#include <asm/uv/uv.h> +#include <asm/apic.h> +#include <asm/cpu.h> + +#define RTC_NAME "sgi_rtc" + +static cycle_t uv_read_rtc(void); +static int uv_rtc_next_event(unsigned long, struct clock_event_device *); +static void uv_rtc_timer_setup(enum clock_event_mode, + struct clock_event_device *); + +static struct clocksource clocksource_uv = { + .name = RTC_NAME, + .rating = 400, + .read = uv_read_rtc, + .mask = (cycle_t)UVH_RTC_REAL_TIME_CLOCK_MASK, + .shift = 10, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +static struct clock_event_device clock_event_device_uv = { + .name = RTC_NAME, + .features = CLOCK_EVT_FEAT_ONESHOT, + .shift = 20, + .rating = 400, + .irq = -1, + .set_next_event = uv_rtc_next_event, + .set_mode = uv_rtc_timer_setup, + .event_handler = NULL, +}; + +static DEFINE_PER_CPU(struct clock_event_device, cpu_ced); + +/* There is one of these allocated per node */ +struct uv_rtc_timer_head { + spinlock_t lock; + /* next cpu waiting for timer, local node relative: */ + int next_cpu; + /* number of cpus on this node: */ + int ncpus; + struct { + int lcpu; /* systemwide logical cpu number */ + u64 expires; /* next timer expiration for this cpu */ + } cpu[1]; +}; + +/* + * Access to uv_rtc_timer_head via blade id. + */ +static struct uv_rtc_timer_head **blade_info __read_mostly; + +static int uv_rtc_enable; + +/* + * Hardware interface routines + */ + +/* Send IPIs to another node */ +static void uv_rtc_send_IPI(int cpu) +{ + unsigned long apicid, val; + int pnode; + + apicid = cpu_physical_id(cpu); + pnode = uv_apicid_to_pnode(apicid); + val = (1UL << UVH_IPI_INT_SEND_SHFT) | + (apicid << UVH_IPI_INT_APIC_ID_SHFT) | + (GENERIC_INTERRUPT_VECTOR << UVH_IPI_INT_VECTOR_SHFT); + + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); +} + +/* Check for an RTC interrupt pending */ +static int uv_intr_pending(int pnode) +{ + return uv_read_global_mmr64(pnode, UVH_EVENT_OCCURRED0) & + UVH_EVENT_OCCURRED0_RTC1_MASK; +} + +/* Setup interrupt and return non-zero if early expiration occurred. */ +static int uv_setup_intr(int cpu, u64 expires) +{ + u64 val; + int pnode = uv_cpu_to_pnode(cpu); + + uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG, + UVH_RTC1_INT_CONFIG_M_MASK); + uv_write_global_mmr64(pnode, UVH_INT_CMPB, -1L); + + uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS, + UVH_EVENT_OCCURRED0_RTC1_MASK); + + val = (GENERIC_INTERRUPT_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) | + ((u64)cpu_physical_id(cpu) << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT); + + /* Set configuration */ + uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG, val); + /* Initialize comparator value */ + uv_write_global_mmr64(pnode, UVH_INT_CMPB, expires); + + return (expires < uv_read_rtc() && !uv_intr_pending(pnode)); +} + +/* + * Per-cpu timer tracking routines + */ + +static __init void uv_rtc_deallocate_timers(void) +{ + int bid; + + for_each_possible_blade(bid) { + kfree(blade_info[bid]); + } + kfree(blade_info); +} + +/* Allocate per-node list of cpu timer expiration times. */ +static __init int uv_rtc_allocate_timers(void) +{ + int cpu; + + blade_info = kmalloc(uv_possible_blades * sizeof(void *), GFP_KERNEL); + if (!blade_info) + return -ENOMEM; + memset(blade_info, 0, uv_possible_blades * sizeof(void *)); + + for_each_present_cpu(cpu) { + int nid = cpu_to_node(cpu); + int bid = uv_cpu_to_blade_id(cpu); + int bcpu = uv_cpu_hub_info(cpu)->blade_processor_id; + struct uv_rtc_timer_head *head = blade_info[bid]; + + if (!head) { + head = kmalloc_node(sizeof(struct uv_rtc_timer_head) + + (uv_blade_nr_possible_cpus(bid) * + 2 * sizeof(u64)), + GFP_KERNEL, nid); + if (!head) { + uv_rtc_deallocate_timers(); + return -ENOMEM; + } + spin_lock_init(&head->lock); + head->ncpus = uv_blade_nr_possible_cpus(bid); + head->next_cpu = -1; + blade_info[bid] = head; + } + + head->cpu[bcpu].lcpu = cpu; + head->cpu[bcpu].expires = ULLONG_MAX; + } + + return 0; +} + +/* Find and set the next expiring timer. */ +static void uv_rtc_find_next_timer(struct uv_rtc_timer_head *head, int pnode) +{ + u64 lowest = ULLONG_MAX; + int c, bcpu = -1; + + head->next_cpu = -1; + for (c = 0; c < head->ncpus; c++) { + u64 exp = head->cpu[c].expires; + if (exp < lowest) { + bcpu = c; + lowest = exp; + } + } + if (bcpu >= 0) { + head->next_cpu = bcpu; + c = head->cpu[bcpu].lcpu; + if (uv_setup_intr(c, lowest)) + /* If we didn't set it up in time, trigger */ + uv_rtc_send_IPI(c); + } else { + uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG, + UVH_RTC1_INT_CONFIG_M_MASK); + } +} + +/* + * Set expiration time for current cpu. + * + * Returns 1 if we missed the expiration time. + */ +static int uv_rtc_set_timer(int cpu, u64 expires) +{ + int pnode = uv_cpu_to_pnode(cpu); + int bid = uv_cpu_to_blade_id(cpu); + struct uv_rtc_timer_head *head = blade_info[bid]; + int bcpu = uv_cpu_hub_info(cpu)->blade_processor_id; + u64 *t = &head->cpu[bcpu].expires; + unsigned long flags; + int next_cpu; + + spin_lock_irqsave(&head->lock, flags); + + next_cpu = head->next_cpu; + *t = expires; + /* Will this one be next to go off? */ + if (next_cpu < 0 || bcpu == next_cpu || + expires < head->cpu[next_cpu].expires) { + head->next_cpu = bcpu; + if (uv_setup_intr(cpu, expires)) { + *t = ULLONG_MAX; + uv_rtc_find_next_timer(head, pnode); + spin_unlock_irqrestore(&head->lock, flags); + return 1; + } + } + + spin_unlock_irqrestore(&head->lock, flags); + return 0; +} + +/* + * Unset expiration time for current cpu. + * + * Returns 1 if this timer was pending. + */ +static int uv_rtc_unset_timer(int cpu) +{ + int pnode = uv_cpu_to_pnode(cpu); + int bid = uv_cpu_to_blade_id(cpu); + struct uv_rtc_timer_head *head = blade_info[bid]; + int bcpu = uv_cpu_hub_info(cpu)->blade_processor_id; + u64 *t = &head->cpu[bcpu].expires; + unsigned long flags; + int rc = 0; + + spin_lock_irqsave(&head->lock, flags); + + if (head->next_cpu == bcpu && uv_read_rtc() >= *t) + rc = 1; + + *t = ULLONG_MAX; + + /* Was the hardware setup for this timer? */ + if (head->next_cpu == bcpu) + uv_rtc_find_next_timer(head, pnode); + + spin_unlock_irqrestore(&head->lock, flags); + + return rc; +} + + +/* + * Kernel interface routines. + */ + +/* + * Read the RTC. + */ +static cycle_t uv_read_rtc(void) +{ + return (cycle_t)uv_read_local_mmr(UVH_RTC); +} + +/* + * Program the next event, relative to now + */ +static int uv_rtc_next_event(unsigned long delta, + struct clock_event_device *ced) +{ + int ced_cpu = cpumask_first(ced->cpumask); + + return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc()); +} + +/* + * Setup the RTC timer in oneshot mode + */ +static void uv_rtc_timer_setup(enum clock_event_mode mode, + struct clock_event_device *evt) +{ + int ced_cpu = cpumask_first(evt->cpumask); + + switch (mode) { + case CLOCK_EVT_MODE_PERIODIC: + case CLOCK_EVT_MODE_ONESHOT: + case CLOCK_EVT_MODE_RESUME: + /* Nothing to do here yet */ + break; + case CLOCK_EVT_MODE_UNUSED: + case CLOCK_EVT_MODE_SHUTDOWN: + uv_rtc_unset_timer(ced_cpu); + break; + } +} + +static void uv_rtc_interrupt(void) +{ + struct clock_event_device *ced = &__get_cpu_var(cpu_ced); + int cpu = smp_processor_id(); + + if (!ced || !ced->event_handler) + return; + + if (uv_rtc_unset_timer(cpu) != 1) + return; + + ced->event_handler(ced); +} + +static int __init uv_enable_rtc(char *str) +{ + uv_rtc_enable = 1; + + return 1; +} +__setup("uvrtc", uv_enable_rtc); + +static __init void uv_rtc_register_clockevents(struct work_struct *dummy) +{ + struct clock_event_device *ced = &__get_cpu_var(cpu_ced); + + *ced = clock_event_device_uv; + ced->cpumask = cpumask_of(smp_processor_id()); + clockevents_register_device(ced); +} + +static __init int uv_rtc_setup_clock(void) +{ + int rc; + + if (!uv_rtc_enable || !is_uv_system() || generic_interrupt_extension) + return -ENODEV; + + generic_interrupt_extension = uv_rtc_interrupt; + + clocksource_uv.mult = clocksource_hz2mult(sn_rtc_cycles_per_second, + clocksource_uv.shift); + + rc = clocksource_register(&clocksource_uv); + if (rc) { + generic_interrupt_extension = NULL; + return rc; + } + + /* Setup and register clockevents */ + rc = uv_rtc_allocate_timers(); + if (rc) { + clocksource_unregister(&clocksource_uv); + generic_interrupt_extension = NULL; + return rc; + } + + clock_event_device_uv.mult = div_sc(sn_rtc_cycles_per_second, + NSEC_PER_SEC, clock_event_device_uv.shift); + + clock_event_device_uv.min_delta_ns = NSEC_PER_SEC / + sn_rtc_cycles_per_second; + + clock_event_device_uv.max_delta_ns = clocksource_uv.mask * + (NSEC_PER_SEC / sn_rtc_cycles_per_second); + + rc = schedule_on_each_cpu(uv_rtc_register_clockevents); + if (rc) { + clocksource_unregister(&clocksource_uv); + generic_interrupt_extension = NULL; + uv_rtc_deallocate_timers(); + } + + return rc; +} +arch_initcall(uv_rtc_setup_clock); diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S index fbfced6..5bf54e4 100644 --- a/arch/x86/kernel/vmlinux_64.lds.S +++ b/arch/x86/kernel/vmlinux_64.lds.S @@ -275,3 +275,10 @@ ASSERT((_end - _text <= KERNEL_IMAGE_SIZE), ASSERT((per_cpu__irq_stack_union == 0), "irq_stack_union is not at start of per-cpu area"); #endif + +#ifdef CONFIG_KEXEC +#include <asm/kexec.h> + +ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE, + "kexec control code size is too big") +#endif diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index f3a5305..9fe4dda 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -348,6 +348,11 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, * flush_tlb_user() for both user and kernel mappings unless * the Page Global Enable (PGE) feature bit is set. */ *dx |= 0x00002000; + /* We also lie, and say we're family id 5. 6 or greater + * leads to a rdmsr in early_init_intel which we can't handle. + * Family ID is returned as bits 8-12 in ax. */ + *ax &= 0xFFFFF0FF; + *ax |= 0x00000500; break; case 0x80000000: /* Futureproof this a little: if they ask how much extended @@ -594,19 +599,21 @@ static void __init lguest_init_IRQ(void) /* Some systems map "vectors" to interrupts weirdly. Lguest has * a straightforward 1 to 1 mapping, so force that here. */ __get_cpu_var(vector_irq)[vector] = i; - if (vector != SYSCALL_VECTOR) { - set_intr_gate(vector, - interrupt[vector-FIRST_EXTERNAL_VECTOR]); - set_irq_chip_and_handler_name(i, &lguest_irq_controller, - handle_level_irq, - "level"); - } + if (vector != SYSCALL_VECTOR) + set_intr_gate(vector, interrupt[i]); } /* This call is required to set up for 4k stacks, where we have * separate stacks for hard and soft interrupts. */ irq_ctx_init(smp_processor_id()); } +void lguest_setup_irq(unsigned int irq) +{ + irq_to_desc_alloc_cpu(irq, 0); + set_irq_chip_and_handler_name(irq, &lguest_irq_controller, + handle_level_irq, "level"); +} + /* * Time. * diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c index 491e737..aa09870 100644 --- a/arch/x86/math-emu/fpu_aux.c +++ b/arch/x86/math-emu/fpu_aux.c @@ -30,20 +30,29 @@ static void fclex(void) } /* Needs to be externally visible */ -void finit(void) +void finit_task(struct task_struct *tsk) { - control_word = 0x037f; - partial_status = 0; - top = 0; /* We don't keep top in the status word internally. */ - fpu_tag_word = 0xffff; + struct i387_soft_struct *soft = &tsk->thread.xstate->soft; + struct address *oaddr, *iaddr; + soft->cwd = 0x037f; + soft->swd = 0; + soft->ftop = 0; /* We don't keep top in the status word internally. */ + soft->twd = 0xffff; /* The behaviour is different from that detailed in Section 15.1.6 of the Intel manual */ - operand_address.offset = 0; - operand_address.selector = 0; - instruction_address.offset = 0; - instruction_address.selector = 0; - instruction_address.opcode = 0; - no_ip_update = 1; + oaddr = (struct address *)&soft->foo; + oaddr->offset = 0; + oaddr->selector = 0; + iaddr = (struct address *)&soft->fip; + iaddr->offset = 0; + iaddr->selector = 0; + iaddr->opcode = 0; + soft->no_update = 1; +} + +void finit(void) +{ + finit_task(current); } /* diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 00f127c..d117453 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -158,7 +158,6 @@ EXPORT_SYMBOL(kunmap); EXPORT_SYMBOL(kmap_atomic); EXPORT_SYMBOL(kunmap_atomic); -#ifdef CONFIG_NUMA void __init set_highmem_pages_init(void) { struct zone *zone; @@ -182,11 +181,3 @@ void __init set_highmem_pages_init(void) } totalram_pages += totalhigh_pages; } -#else -void __init set_highmem_pages_init(void) -{ - add_highpages_with_active_regions(0, highstart_pfn, highend_pfn); - - totalram_pages += totalhigh_pages; -} -#endif /* CONFIG_NUMA */ diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index ce6a722..15219e0 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -1,8 +1,345 @@ +#include <linux/ioport.h> #include <linux/swap.h> + #include <asm/cacheflush.h> +#include <asm/e820.h> +#include <asm/init.h> #include <asm/page.h> +#include <asm/page_types.h> #include <asm/sections.h> #include <asm/system.h> +#include <asm/tlbflush.h> + +unsigned long __initdata e820_table_start; +unsigned long __meminitdata e820_table_end; +unsigned long __meminitdata e820_table_top; + +int after_bootmem; + +int direct_gbpages +#ifdef CONFIG_DIRECT_GBPAGES + = 1 +#endif +; + +static void __init find_early_table_space(unsigned long end, int use_pse, + int use_gbpages) +{ + unsigned long puds, pmds, ptes, tables, start; + + puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; + tables = roundup(puds * sizeof(pud_t), PAGE_SIZE); + + if (use_gbpages) { + unsigned long extra; + + extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT); + pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT; + } else + pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; + + tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE); + + if (use_pse) { + unsigned long extra; + + extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT); +#ifdef CONFIG_X86_32 + extra += PMD_SIZE; +#endif + ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT; + } else + ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; + + tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE); + +#ifdef CONFIG_X86_32 + /* for fixmap */ + tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE); +#endif + + /* + * RED-PEN putting page tables only on node 0 could + * cause a hotspot and fill up ZONE_DMA. The page tables + * need roughly 0.5KB per GB. + */ +#ifdef CONFIG_X86_32 + start = 0x7000; + e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT, + tables, PAGE_SIZE); +#else /* CONFIG_X86_64 */ + start = 0x8000; + e820_table_start = find_e820_area(start, end, tables, PAGE_SIZE); +#endif + if (e820_table_start == -1UL) + panic("Cannot find space for the kernel page tables"); + + e820_table_start >>= PAGE_SHIFT; + e820_table_end = e820_table_start; + e820_table_top = e820_table_start + (tables >> PAGE_SHIFT); + + printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n", + end, e820_table_start << PAGE_SHIFT, e820_table_top << PAGE_SHIFT); +} + +struct map_range { + unsigned long start; + unsigned long end; + unsigned page_size_mask; +}; + +#ifdef CONFIG_X86_32 +#define NR_RANGE_MR 3 +#else /* CONFIG_X86_64 */ +#define NR_RANGE_MR 5 +#endif + +static int save_mr(struct map_range *mr, int nr_range, + unsigned long start_pfn, unsigned long end_pfn, + unsigned long page_size_mask) +{ + if (start_pfn < end_pfn) { + if (nr_range >= NR_RANGE_MR) + panic("run out of range for init_memory_mapping\n"); + mr[nr_range].start = start_pfn<<PAGE_SHIFT; + mr[nr_range].end = end_pfn<<PAGE_SHIFT; + mr[nr_range].page_size_mask = page_size_mask; + nr_range++; + } + + return nr_range; +} + +#ifdef CONFIG_X86_64 +static void __init init_gbpages(void) +{ + if (direct_gbpages && cpu_has_gbpages) + printk(KERN_INFO "Using GB pages for direct mapping\n"); + else + direct_gbpages = 0; +} +#else +static inline void init_gbpages(void) +{ +} +#endif + +/* + * Setup the direct mapping of the physical memory at PAGE_OFFSET. + * This runs before bootmem is initialized and gets pages directly from + * the physical memory. To access them they are temporarily mapped. + */ +unsigned long __init_refok init_memory_mapping(unsigned long start, + unsigned long end) +{ + unsigned long page_size_mask = 0; + unsigned long start_pfn, end_pfn; + unsigned long ret = 0; + unsigned long pos; + + struct map_range mr[NR_RANGE_MR]; + int nr_range, i; + int use_pse, use_gbpages; + + printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end); + + if (!after_bootmem) + init_gbpages(); + +#ifdef CONFIG_DEBUG_PAGEALLOC + /* + * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages. + * This will simplify cpa(), which otherwise needs to support splitting + * large pages into small in interrupt context, etc. + */ + use_pse = use_gbpages = 0; +#else + use_pse = cpu_has_pse; + use_gbpages = direct_gbpages; +#endif + +#ifdef CONFIG_X86_32 +#ifdef CONFIG_X86_PAE + set_nx(); + if (nx_enabled) + printk(KERN_INFO "NX (Execute Disable) protection: active\n"); +#endif + + /* Enable PSE if available */ + if (cpu_has_pse) + set_in_cr4(X86_CR4_PSE); + + /* Enable PGE if available */ + if (cpu_has_pge) { + set_in_cr4(X86_CR4_PGE); + __supported_pte_mask |= _PAGE_GLOBAL; + } +#endif + + if (use_gbpages) + page_size_mask |= 1 << PG_LEVEL_1G; + if (use_pse) + page_size_mask |= 1 << PG_LEVEL_2M; + + memset(mr, 0, sizeof(mr)); + nr_range = 0; + + /* head if not big page alignment ? */ + start_pfn = start >> PAGE_SHIFT; + pos = start_pfn << PAGE_SHIFT; +#ifdef CONFIG_X86_32 + /* + * Don't use a large page for the first 2/4MB of memory + * because there are often fixed size MTRRs in there + * and overlapping MTRRs into large pages can cause + * slowdowns. + */ + if (pos == 0) + end_pfn = 1<<(PMD_SHIFT - PAGE_SHIFT); + else + end_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); +#else /* CONFIG_X86_64 */ + end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); +#endif + if (end_pfn > (end >> PAGE_SHIFT)) + end_pfn = end >> PAGE_SHIFT; + if (start_pfn < end_pfn) { + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); + pos = end_pfn << PAGE_SHIFT; + } + + /* big page (2M) range */ + start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); +#ifdef CONFIG_X86_32 + end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); +#else /* CONFIG_X86_64 */ + end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT) + << (PUD_SHIFT - PAGE_SHIFT); + if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT))) + end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)); +#endif + + if (start_pfn < end_pfn) { + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & (1<<PG_LEVEL_2M)); + pos = end_pfn << PAGE_SHIFT; + } + +#ifdef CONFIG_X86_64 + /* big page (1G) range */ + start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT) + << (PUD_SHIFT - PAGE_SHIFT); + end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT); + if (start_pfn < end_pfn) { + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & + ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G))); + pos = end_pfn << PAGE_SHIFT; + } + + /* tail is not big page (1G) alignment */ + start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); + end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); + if (start_pfn < end_pfn) { + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & (1<<PG_LEVEL_2M)); + pos = end_pfn << PAGE_SHIFT; + } +#endif + + /* tail is not big page (2M) alignment */ + start_pfn = pos>>PAGE_SHIFT; + end_pfn = end>>PAGE_SHIFT; + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); + + /* try to merge same page size and continuous */ + for (i = 0; nr_range > 1 && i < nr_range - 1; i++) { + unsigned long old_start; + if (mr[i].end != mr[i+1].start || + mr[i].page_size_mask != mr[i+1].page_size_mask) + continue; + /* move it */ + old_start = mr[i].start; + memmove(&mr[i], &mr[i+1], + (nr_range - 1 - i) * sizeof(struct map_range)); + mr[i--].start = old_start; + nr_range--; + } + + for (i = 0; i < nr_range; i++) + printk(KERN_DEBUG " %010lx - %010lx page %s\n", + mr[i].start, mr[i].end, + (mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":( + (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k")); + + /* + * Find space for the kernel direct mapping tables. + * + * Later we should allocate these tables in the local node of the + * memory mapped. Unfortunately this is done currently before the + * nodes are discovered. + */ + if (!after_bootmem) + find_early_table_space(end, use_pse, use_gbpages); + +#ifdef CONFIG_X86_32 + for (i = 0; i < nr_range; i++) + kernel_physical_mapping_init(mr[i].start, mr[i].end, + mr[i].page_size_mask); + ret = end; +#else /* CONFIG_X86_64 */ + for (i = 0; i < nr_range; i++) + ret = kernel_physical_mapping_init(mr[i].start, mr[i].end, + mr[i].page_size_mask); +#endif + +#ifdef CONFIG_X86_32 + early_ioremap_page_table_range_init(); + + load_cr3(swapper_pg_dir); +#endif + +#ifdef CONFIG_X86_64 + if (!after_bootmem) + mmu_cr4_features = read_cr4(); +#endif + __flush_tlb_all(); + + if (!after_bootmem && e820_table_end > e820_table_start) + reserve_early(e820_table_start << PAGE_SHIFT, + e820_table_end << PAGE_SHIFT, "PGTABLE"); + + if (!after_bootmem) + early_memtest(start, end); + + return ret >> PAGE_SHIFT; +} + + +/* + * devmem_is_allowed() checks to see if /dev/mem access to a certain address + * is valid. The argument is a physical page number. + * + * + * On x86, access has to be given to the first megabyte of ram because that area + * contains bios code and data regions used by X and dosemu and similar apps. + * Access has to be given to non-kernel-ram areas as well, these contain the PCI + * mmio resources as well as potential bios/acpi data regions. + */ +int devmem_is_allowed(unsigned long pagenr) +{ + if (pagenr <= 256) + return 1; + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + return 0; + if (!page_is_ram(pagenr)) + return 1; + return 0; +} void free_init_pages(char *what, unsigned long begin, unsigned long end) { @@ -47,3 +384,10 @@ void free_initmem(void) (unsigned long)(&__init_begin), (unsigned long)(&__init_end)); } + +#ifdef CONFIG_BLK_DEV_INITRD +void free_initrd_mem(unsigned long start, unsigned long end) +{ + free_init_pages("initrd memory", start, end); +} +#endif diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 0b087dc..db81e9a 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -49,6 +49,7 @@ #include <asm/paravirt.h> #include <asm/setup.h> #include <asm/cacheflush.h> +#include <asm/init.h> unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; @@ -58,19 +59,14 @@ unsigned long highstart_pfn, highend_pfn; static noinline int do_test_wp_bit(void); - -static unsigned long __initdata table_start; -static unsigned long __meminitdata table_end; -static unsigned long __meminitdata table_top; - -static int __initdata after_init_bootmem; +bool __read_mostly __vmalloc_start_set = false; static __init void *alloc_low_page(void) { - unsigned long pfn = table_end++; + unsigned long pfn = e820_table_end++; void *adr; - if (pfn >= table_top) + if (pfn >= e820_table_top) panic("alloc_low_page: ran out of memory"); adr = __va(pfn * PAGE_SIZE); @@ -90,7 +86,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd) #ifdef CONFIG_X86_PAE if (!(pgd_val(*pgd) & _PAGE_PRESENT)) { - if (after_init_bootmem) + if (after_bootmem) pmd_table = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE); else pmd_table = (pmd_t *)alloc_low_page(); @@ -117,7 +113,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd) if (!(pmd_val(*pmd) & _PAGE_PRESENT)) { pte_t *page_table = NULL; - if (after_init_bootmem) { + if (after_bootmem) { #ifdef CONFIG_DEBUG_PAGEALLOC page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE); #endif @@ -135,6 +131,23 @@ static pte_t * __init one_page_table_init(pmd_t *pmd) return pte_offset_kernel(pmd, 0); } +pmd_t * __init populate_extra_pmd(unsigned long vaddr) +{ + int pgd_idx = pgd_index(vaddr); + int pmd_idx = pmd_index(vaddr); + + return one_md_table_init(swapper_pg_dir + pgd_idx) + pmd_idx; +} + +pte_t * __init populate_extra_pte(unsigned long vaddr) +{ + int pte_idx = pte_index(vaddr); + pmd_t *pmd; + + pmd = populate_extra_pmd(vaddr); + return one_page_table_init(pmd) + pte_idx; +} + static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd, unsigned long vaddr, pte_t *lastpte) { @@ -151,12 +164,12 @@ static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd, if (pmd_idx_kmap_begin != pmd_idx_kmap_end && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end - && ((__pa(pte) >> PAGE_SHIFT) < table_start - || (__pa(pte) >> PAGE_SHIFT) >= table_end)) { + && ((__pa(pte) >> PAGE_SHIFT) < e820_table_start + || (__pa(pte) >> PAGE_SHIFT) >= e820_table_end)) { pte_t *newpte; int i; - BUG_ON(after_init_bootmem); + BUG_ON(after_bootmem); newpte = alloc_low_page(); for (i = 0; i < PTRS_PER_PTE; i++) set_pte(newpte + i, pte[i]); @@ -225,11 +238,14 @@ static inline int is_kernel_text(unsigned long addr) * of max_low_pfn pages, by creating page tables starting from address * PAGE_OFFSET: */ -static void __init kernel_physical_mapping_init(pgd_t *pgd_base, - unsigned long start_pfn, - unsigned long end_pfn, - int use_pse) +unsigned long __init +kernel_physical_mapping_init(unsigned long start, + unsigned long end, + unsigned long page_size_mask) { + int use_pse = page_size_mask == (1<<PG_LEVEL_2M); + unsigned long start_pfn, end_pfn; + pgd_t *pgd_base = swapper_pg_dir; int pgd_idx, pmd_idx, pte_ofs; unsigned long pfn; pgd_t *pgd; @@ -238,6 +254,9 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base, unsigned pages_2m, pages_4k; int mapping_iter; + start_pfn = start >> PAGE_SHIFT; + end_pfn = end >> PAGE_SHIFT; + /* * First iteration will setup identity mapping using large/small pages * based on use_pse, with other attributes same as set by @@ -352,26 +371,6 @@ repeat: mapping_iter = 2; goto repeat; } -} - -/* - * devmem_is_allowed() checks to see if /dev/mem access to a certain address - * is valid. The argument is a physical page number. - * - * - * On x86, access has to be given to the first megabyte of ram because that area - * contains bios code and data regions used by X and dosemu and similar apps. - * Access has to be given to non-kernel-ram areas as well, these contain the PCI - * mmio resources as well as potential bios/acpi data regions. - */ -int devmem_is_allowed(unsigned long pagenr) -{ - if (pagenr <= 256) - return 1; - if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) - return 0; - if (!page_is_ram(pagenr)) - return 1; return 0; } @@ -528,8 +527,9 @@ void __init native_pagetable_setup_done(pgd_t *base) * be partially populated, and so it avoids stomping on any existing * mappings. */ -static void __init early_ioremap_page_table_range_init(pgd_t *pgd_base) +void __init early_ioremap_page_table_range_init(void) { + pgd_t *pgd_base = swapper_pg_dir; unsigned long vaddr, end; /* @@ -624,7 +624,7 @@ static int __init noexec_setup(char *str) } early_param("noexec", noexec_setup); -static void __init set_nx(void) +void __init set_nx(void) { unsigned int v[4], l, h; @@ -776,6 +776,8 @@ void __init initmem_init(unsigned long start_pfn, #ifdef CONFIG_FLATMEM max_mapnr = num_physpages; #endif + __vmalloc_start_set = true; + printk(KERN_NOTICE "%ldMB LOWMEM available.\n", pages_to_mb(max_low_pfn)); @@ -797,176 +799,66 @@ static void __init zone_sizes_init(void) free_area_init_nodes(max_zone_pfns); } +static unsigned long __init setup_node_bootmem(int nodeid, + unsigned long start_pfn, + unsigned long end_pfn, + unsigned long bootmap) +{ + unsigned long bootmap_size; + + /* don't touch min_low_pfn */ + bootmap_size = init_bootmem_node(NODE_DATA(nodeid), + bootmap >> PAGE_SHIFT, + start_pfn, end_pfn); + printk(KERN_INFO " node %d low ram: %08lx - %08lx\n", + nodeid, start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT); + printk(KERN_INFO " node %d bootmap %08lx - %08lx\n", + nodeid, bootmap, bootmap + bootmap_size); + free_bootmem_with_active_regions(nodeid, end_pfn); + early_res_to_bootmem(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT); + + return bootmap + bootmap_size; +} + void __init setup_bootmem_allocator(void) { - int i; + int nodeid; unsigned long bootmap_size, bootmap; /* * Initialize the boot-time allocator (with low memory only): */ bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT; - bootmap = find_e820_area(min_low_pfn<<PAGE_SHIFT, - max_pfn_mapped<<PAGE_SHIFT, bootmap_size, + bootmap = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size, PAGE_SIZE); if (bootmap == -1L) panic("Cannot find bootmem map of size %ld\n", bootmap_size); reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP"); - /* don't touch min_low_pfn */ - bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT, - min_low_pfn, max_low_pfn); printk(KERN_INFO " mapped low ram: 0 - %08lx\n", max_pfn_mapped<<PAGE_SHIFT); - printk(KERN_INFO " low ram: %08lx - %08lx\n", - min_low_pfn<<PAGE_SHIFT, max_low_pfn<<PAGE_SHIFT); - printk(KERN_INFO " bootmap %08lx - %08lx\n", - bootmap, bootmap + bootmap_size); - for_each_online_node(i) - free_bootmem_with_active_regions(i, max_low_pfn); - early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT); - - after_init_bootmem = 1; -} - -static void __init find_early_table_space(unsigned long end, int use_pse) -{ - unsigned long puds, pmds, ptes, tables, start; - - puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; - tables = roundup(puds * sizeof(pud_t), PAGE_SIZE); - - pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; - tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE); - - if (use_pse) { - unsigned long extra; + printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT); - extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT); - extra += PMD_SIZE; - ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT; - } else - ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; + for_each_online_node(nodeid) { + unsigned long start_pfn, end_pfn; - tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE); - - /* for fixmap */ - tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE); - - /* - * RED-PEN putting page tables only on node 0 could - * cause a hotspot and fill up ZONE_DMA. The page tables - * need roughly 0.5KB per GB. - */ - start = 0x7000; - table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT, - tables, PAGE_SIZE); - if (table_start == -1UL) - panic("Cannot find space for the kernel page tables"); - - table_start >>= PAGE_SHIFT; - table_end = table_start; - table_top = table_start + (tables>>PAGE_SHIFT); - - printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n", - end, table_start << PAGE_SHIFT, - (table_start << PAGE_SHIFT) + tables); -} - -unsigned long __init_refok init_memory_mapping(unsigned long start, - unsigned long end) -{ - pgd_t *pgd_base = swapper_pg_dir; - unsigned long start_pfn, end_pfn; - unsigned long big_page_start; -#ifdef CONFIG_DEBUG_PAGEALLOC - /* - * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages. - * This will simplify cpa(), which otherwise needs to support splitting - * large pages into small in interrupt context, etc. - */ - int use_pse = 0; +#ifdef CONFIG_NEED_MULTIPLE_NODES + start_pfn = node_start_pfn[nodeid]; + end_pfn = node_end_pfn[nodeid]; + if (start_pfn > max_low_pfn) + continue; + if (end_pfn > max_low_pfn) + end_pfn = max_low_pfn; #else - int use_pse = cpu_has_pse; -#endif - - /* - * Find space for the kernel direct mapping tables. - */ - if (!after_init_bootmem) - find_early_table_space(end, use_pse); - -#ifdef CONFIG_X86_PAE - set_nx(); - if (nx_enabled) - printk(KERN_INFO "NX (Execute Disable) protection: active\n"); + start_pfn = 0; + end_pfn = max_low_pfn; #endif - - /* Enable PSE if available */ - if (cpu_has_pse) - set_in_cr4(X86_CR4_PSE); - - /* Enable PGE if available */ - if (cpu_has_pge) { - set_in_cr4(X86_CR4_PGE); - __supported_pte_mask |= _PAGE_GLOBAL; - } - - /* - * Don't use a large page for the first 2/4MB of memory - * because there are often fixed size MTRRs in there - * and overlapping MTRRs into large pages can cause - * slowdowns. - */ - big_page_start = PMD_SIZE; - - if (start < big_page_start) { - start_pfn = start >> PAGE_SHIFT; - end_pfn = min(big_page_start>>PAGE_SHIFT, end>>PAGE_SHIFT); - } else { - /* head is not big page alignment ? */ - start_pfn = start >> PAGE_SHIFT; - end_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); - } - if (start_pfn < end_pfn) - kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn, 0); - - /* big page range */ - start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); - if (start_pfn < (big_page_start >> PAGE_SHIFT)) - start_pfn = big_page_start >> PAGE_SHIFT; - end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); - if (start_pfn < end_pfn) - kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn, - use_pse); - - /* tail is not big page alignment ? */ - start_pfn = end_pfn; - if (start_pfn > (big_page_start>>PAGE_SHIFT)) { - end_pfn = end >> PAGE_SHIFT; - if (start_pfn < end_pfn) - kernel_physical_mapping_init(pgd_base, start_pfn, - end_pfn, 0); + bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn, + bootmap); } - early_ioremap_page_table_range_init(pgd_base); - - load_cr3(swapper_pg_dir); - - __flush_tlb_all(); - - if (!after_init_bootmem) - reserve_early(table_start << PAGE_SHIFT, - table_end << PAGE_SHIFT, "PGTABLE"); - - if (!after_init_bootmem) - early_memtest(start, end); - - return end >> PAGE_SHIFT; + after_bootmem = 1; } - /* * paging_init() sets up the page tables - note that the first 8MB are * already mapped by head.S. @@ -1200,13 +1092,6 @@ void mark_rodata_ro(void) } #endif -#ifdef CONFIG_BLK_DEV_INITRD -void free_initrd_mem(unsigned long start, unsigned long end) -{ - free_init_pages("initrd memory", start, end); -} -#endif - int __init reserve_bootmem_generic(unsigned long phys, unsigned long len, int flags) { diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 724e537..54efa57d 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -48,6 +48,7 @@ #include <asm/kdebug.h> #include <asm/numa.h> #include <asm/cacheflush.h> +#include <asm/init.h> /* * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. @@ -61,12 +62,6 @@ static unsigned long dma_reserve __initdata; DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); -int direct_gbpages -#ifdef CONFIG_DIRECT_GBPAGES - = 1 -#endif -; - static int __init parse_direct_gbpages_off(char *arg) { direct_gbpages = 0; @@ -87,12 +82,10 @@ early_param("gbpages", parse_direct_gbpages_on); * around without checking the pgd every time. */ -int after_bootmem; - pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP; EXPORT_SYMBOL_GPL(__supported_pte_mask); -static int do_not_nx __cpuinitdata; +static int disable_nx __cpuinitdata; /* * noexec=on|off @@ -107,9 +100,9 @@ static int __init nonx_setup(char *str) return -EINVAL; if (!strncmp(str, "on", 2)) { __supported_pte_mask |= _PAGE_NX; - do_not_nx = 0; + disable_nx = 0; } else if (!strncmp(str, "off", 3)) { - do_not_nx = 1; + disable_nx = 1; __supported_pte_mask &= ~_PAGE_NX; } return 0; @@ -121,7 +114,7 @@ void __cpuinit check_efer(void) unsigned long efer; rdmsrl(MSR_EFER, efer); - if (!(efer & EFER_NX) || do_not_nx) + if (!(efer & EFER_NX) || disable_nx) __supported_pte_mask &= ~_PAGE_NX; } @@ -168,34 +161,51 @@ static __ref void *spp_getpage(void) return ptr; } -void -set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) +static pud_t *fill_pud(pgd_t *pgd, unsigned long vaddr) { - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + if (pgd_none(*pgd)) { + pud_t *pud = (pud_t *)spp_getpage(); + pgd_populate(&init_mm, pgd, pud); + if (pud != pud_offset(pgd, 0)) + printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n", + pud, pud_offset(pgd, 0)); + } + return pud_offset(pgd, vaddr); +} - pud = pud_page + pud_index(vaddr); +static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr) +{ if (pud_none(*pud)) { - pmd = (pmd_t *) spp_getpage(); + pmd_t *pmd = (pmd_t *) spp_getpage(); pud_populate(&init_mm, pud, pmd); - if (pmd != pmd_offset(pud, 0)) { + if (pmd != pmd_offset(pud, 0)) printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n", - pmd, pmd_offset(pud, 0)); - return; - } + pmd, pmd_offset(pud, 0)); } - pmd = pmd_offset(pud, vaddr); + return pmd_offset(pud, vaddr); +} + +static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr) +{ if (pmd_none(*pmd)) { - pte = (pte_t *) spp_getpage(); + pte_t *pte = (pte_t *) spp_getpage(); pmd_populate_kernel(&init_mm, pmd, pte); - if (pte != pte_offset_kernel(pmd, 0)) { + if (pte != pte_offset_kernel(pmd, 0)) printk(KERN_ERR "PAGETABLE BUG #02!\n"); - return; - } } + return pte_offset_kernel(pmd, vaddr); +} + +void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) +{ + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pud = pud_page + pud_index(vaddr); + pmd = fill_pmd(pud, vaddr); + pte = fill_pte(pmd, vaddr); - pte = pte_offset_kernel(pmd, vaddr); set_pte(pte, new_pte); /* @@ -205,8 +215,7 @@ set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) __flush_tlb_one(vaddr); } -void -set_pte_vaddr(unsigned long vaddr, pte_t pteval) +void set_pte_vaddr(unsigned long vaddr, pte_t pteval) { pgd_t *pgd; pud_t *pud_page; @@ -223,6 +232,24 @@ set_pte_vaddr(unsigned long vaddr, pte_t pteval) set_pte_vaddr_pud(pud_page, vaddr, pteval); } +pmd_t * __init populate_extra_pmd(unsigned long vaddr) +{ + pgd_t *pgd; + pud_t *pud; + + pgd = pgd_offset_k(vaddr); + pud = fill_pud(pgd, vaddr); + return fill_pmd(pud, vaddr); +} + +pte_t * __init populate_extra_pte(unsigned long vaddr) +{ + pmd_t *pmd; + + pmd = populate_extra_pmd(vaddr); + return fill_pte(pmd, vaddr); +} + /* * Create large page table mappings for a range of physical addresses. */ @@ -291,13 +318,9 @@ void __init cleanup_highmap(void) } } -static unsigned long __initdata table_start; -static unsigned long __meminitdata table_end; -static unsigned long __meminitdata table_top; - static __ref void *alloc_low_page(unsigned long *phys) { - unsigned long pfn = table_end++; + unsigned long pfn = e820_table_end++; void *adr; if (after_bootmem) { @@ -307,7 +330,7 @@ static __ref void *alloc_low_page(unsigned long *phys) return adr; } - if (pfn >= table_top) + if (pfn >= e820_table_top) panic("alloc_low_page: ran out of memory"); adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE); @@ -547,58 +570,10 @@ phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end, return phys_pud_init(pud, addr, end, page_size_mask); } -static void __init find_early_table_space(unsigned long end, int use_pse, - int use_gbpages) -{ - unsigned long puds, pmds, ptes, tables, start; - - puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; - tables = roundup(puds * sizeof(pud_t), PAGE_SIZE); - if (use_gbpages) { - unsigned long extra; - extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT); - pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT; - } else - pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; - tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE); - - if (use_pse) { - unsigned long extra; - extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT); - ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT; - } else - ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; - tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE); - - /* - * RED-PEN putting page tables only on node 0 could - * cause a hotspot and fill up ZONE_DMA. The page tables - * need roughly 0.5KB per GB. - */ - start = 0x8000; - table_start = find_e820_area(start, end, tables, PAGE_SIZE); - if (table_start == -1UL) - panic("Cannot find space for the kernel page tables"); - - table_start >>= PAGE_SHIFT; - table_end = table_start; - table_top = table_start + (tables >> PAGE_SHIFT); - - printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n", - end, table_start << PAGE_SHIFT, table_top << PAGE_SHIFT); -} - -static void __init init_gbpages(void) -{ - if (direct_gbpages && cpu_has_gbpages) - printk(KERN_INFO "Using GB pages for direct mapping\n"); - else - direct_gbpages = 0; -} - -static unsigned long __meminit kernel_physical_mapping_init(unsigned long start, - unsigned long end, - unsigned long page_size_mask) +unsigned long __init +kernel_physical_mapping_init(unsigned long start, + unsigned long end, + unsigned long page_size_mask) { unsigned long next, last_map_addr = end; @@ -635,176 +610,6 @@ static unsigned long __meminit kernel_physical_mapping_init(unsigned long start, return last_map_addr; } -struct map_range { - unsigned long start; - unsigned long end; - unsigned page_size_mask; -}; - -#define NR_RANGE_MR 5 - -static int save_mr(struct map_range *mr, int nr_range, - unsigned long start_pfn, unsigned long end_pfn, - unsigned long page_size_mask) -{ - - if (start_pfn < end_pfn) { - if (nr_range >= NR_RANGE_MR) - panic("run out of range for init_memory_mapping\n"); - mr[nr_range].start = start_pfn<<PAGE_SHIFT; - mr[nr_range].end = end_pfn<<PAGE_SHIFT; - mr[nr_range].page_size_mask = page_size_mask; - nr_range++; - } - - return nr_range; -} - -/* - * Setup the direct mapping of the physical memory at PAGE_OFFSET. - * This runs before bootmem is initialized and gets pages directly from - * the physical memory. To access them they are temporarily mapped. - */ -unsigned long __init_refok init_memory_mapping(unsigned long start, - unsigned long end) -{ - unsigned long last_map_addr = 0; - unsigned long page_size_mask = 0; - unsigned long start_pfn, end_pfn; - unsigned long pos; - - struct map_range mr[NR_RANGE_MR]; - int nr_range, i; - int use_pse, use_gbpages; - - printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end); - - /* - * Find space for the kernel direct mapping tables. - * - * Later we should allocate these tables in the local node of the - * memory mapped. Unfortunately this is done currently before the - * nodes are discovered. - */ - if (!after_bootmem) - init_gbpages(); - -#ifdef CONFIG_DEBUG_PAGEALLOC - /* - * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages. - * This will simplify cpa(), which otherwise needs to support splitting - * large pages into small in interrupt context, etc. - */ - use_pse = use_gbpages = 0; -#else - use_pse = cpu_has_pse; - use_gbpages = direct_gbpages; -#endif - - if (use_gbpages) - page_size_mask |= 1 << PG_LEVEL_1G; - if (use_pse) - page_size_mask |= 1 << PG_LEVEL_2M; - - memset(mr, 0, sizeof(mr)); - nr_range = 0; - - /* head if not big page alignment ?*/ - start_pfn = start >> PAGE_SHIFT; - pos = start_pfn << PAGE_SHIFT; - end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); - if (end_pfn > (end >> PAGE_SHIFT)) - end_pfn = end >> PAGE_SHIFT; - if (start_pfn < end_pfn) { - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); - pos = end_pfn << PAGE_SHIFT; - } - - /* big page (2M) range*/ - start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); - end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT) - << (PUD_SHIFT - PAGE_SHIFT); - if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT))) - end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)); - if (start_pfn < end_pfn) { - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, - page_size_mask & (1<<PG_LEVEL_2M)); - pos = end_pfn << PAGE_SHIFT; - } - - /* big page (1G) range */ - start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT) - << (PUD_SHIFT - PAGE_SHIFT); - end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT); - if (start_pfn < end_pfn) { - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, - page_size_mask & - ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G))); - pos = end_pfn << PAGE_SHIFT; - } - - /* tail is not big page (1G) alignment */ - start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); - end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); - if (start_pfn < end_pfn) { - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, - page_size_mask & (1<<PG_LEVEL_2M)); - pos = end_pfn << PAGE_SHIFT; - } - - /* tail is not big page (2M) alignment */ - start_pfn = pos>>PAGE_SHIFT; - end_pfn = end>>PAGE_SHIFT; - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); - - /* try to merge same page size and continuous */ - for (i = 0; nr_range > 1 && i < nr_range - 1; i++) { - unsigned long old_start; - if (mr[i].end != mr[i+1].start || - mr[i].page_size_mask != mr[i+1].page_size_mask) - continue; - /* move it */ - old_start = mr[i].start; - memmove(&mr[i], &mr[i+1], - (nr_range - 1 - i) * sizeof (struct map_range)); - mr[i--].start = old_start; - nr_range--; - } - - for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG " %010lx - %010lx page %s\n", - mr[i].start, mr[i].end, - (mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":( - (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k")); - - if (!after_bootmem) - find_early_table_space(end, use_pse, use_gbpages); - - for (i = 0; i < nr_range; i++) - last_map_addr = kernel_physical_mapping_init( - mr[i].start, mr[i].end, - mr[i].page_size_mask); - - if (!after_bootmem) - mmu_cr4_features = read_cr4(); - __flush_tlb_all(); - - if (!after_bootmem && table_end > table_start) - reserve_early(table_start << PAGE_SHIFT, - table_end << PAGE_SHIFT, "PGTABLE"); - - printk(KERN_INFO "last_map_addr: %lx end: %lx\n", - last_map_addr, end); - - if (!after_bootmem) - early_memtest(start, end); - - return last_map_addr >> PAGE_SHIFT; -} - #ifndef CONFIG_NUMA void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn) { @@ -876,28 +681,6 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif /* CONFIG_MEMORY_HOTPLUG */ -/* - * devmem_is_allowed() checks to see if /dev/mem access to a certain address - * is valid. The argument is a physical page number. - * - * - * On x86, access has to be given to the first megabyte of ram because that area - * contains bios code and data regions used by X and dosemu and similar apps. - * Access has to be given to non-kernel-ram areas as well, these contain the PCI - * mmio resources as well as potential bios/acpi data regions. - */ -int devmem_is_allowed(unsigned long pagenr) -{ - if (pagenr <= 256) - return 1; - if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) - return 0; - if (!page_is_ram(pagenr)) - return 1; - return 0; -} - - static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules, kcore_vsyscall; @@ -985,13 +768,6 @@ void mark_rodata_ro(void) #endif -#ifdef CONFIG_BLK_DEV_INITRD -void free_initrd_mem(unsigned long start, unsigned long end) -{ - free_init_pages("initrd memory", start, end); -} -#endif - int __init reserve_bootmem_generic(unsigned long phys, unsigned long len, int flags) { diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 433f7bd..aca924a 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -38,8 +38,7 @@ unsigned long __phys_addr(unsigned long x) } else { VIRTUAL_BUG_ON(x < PAGE_OFFSET); x -= PAGE_OFFSET; - VIRTUAL_BUG_ON(system_state == SYSTEM_BOOTING ? x > MAXMEM : - !phys_addr_valid(x)); + VIRTUAL_BUG_ON(!phys_addr_valid(x)); } return x; } @@ -56,10 +55,8 @@ bool __virt_addr_valid(unsigned long x) if (x < PAGE_OFFSET) return false; x -= PAGE_OFFSET; - if (system_state == SYSTEM_BOOTING ? - x > MAXMEM : !phys_addr_valid(x)) { + if (!phys_addr_valid(x)) return false; - } } return pfn_valid(x >> PAGE_SHIFT); @@ -76,10 +73,9 @@ static inline int phys_addr_valid(unsigned long addr) #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { - /* VMALLOC_* aren't constants; not available at the boot time */ + /* VMALLOC_* aren't constants */ VIRTUAL_BUG_ON(x < PAGE_OFFSET); - VIRTUAL_BUG_ON(system_state != SYSTEM_BOOTING && - is_vmalloc_addr((void *) x)); + VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x)); return x - PAGE_OFFSET; } EXPORT_SYMBOL(__phys_addr); @@ -89,7 +85,9 @@ bool __virt_addr_valid(unsigned long x) { if (x < PAGE_OFFSET) return false; - if (system_state != SYSTEM_BOOTING && is_vmalloc_addr((void *) x)) + if (__vmalloc_start_set && is_vmalloc_addr((void *) x)) + return false; + if (x >= FIXADDR_START) return false; return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT); } @@ -508,13 +506,19 @@ static inline pte_t * __init early_ioremap_pte(unsigned long addr) return &bm_pte[pte_index(addr)]; } +static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata; + void __init early_ioremap_init(void) { pmd_t *pmd; + int i; if (early_ioremap_debug) printk(KERN_INFO "early_ioremap_init()\n"); + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + slot_virt[i] = fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i); + pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); memset(bm_pte, 0, sizeof(bm_pte)); pmd_populate_kernel(&init_mm, pmd, bm_pte); @@ -581,6 +585,7 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx) static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata; static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata; + static int __init check_early_ioremap_leak(void) { int count = 0; @@ -602,7 +607,8 @@ static int __init check_early_ioremap_leak(void) } late_initcall(check_early_ioremap_leak); -static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) +static void __init __iomem * +__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) { unsigned long offset, last_addr; unsigned int nrpages; @@ -668,9 +674,9 @@ static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned lo --nrpages; } if (early_ioremap_debug) - printk(KERN_CONT "%08lx + %08lx\n", offset, fix_to_virt(idx0)); + printk(KERN_CONT "%08lx + %08lx\n", offset, slot_virt[slot]); - prev_map[slot] = (void __iomem *)(offset + fix_to_virt(idx0)); + prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]); return prev_map[slot]; } @@ -738,8 +744,3 @@ void __init early_iounmap(void __iomem *addr, unsigned long size) } prev_map[slot] = NULL; } - -void __this_fixmap_does_not_exist(void) -{ - WARN_ON(1); -} diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 93d8203..6a518dd 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -32,11 +32,14 @@ struct kmmio_fault_page { struct list_head list; struct kmmio_fault_page *release_next; unsigned long page; /* location of the fault page */ + bool old_presence; /* page presence prior to arming */ + bool armed; /* * Number of times this page has been registered as a part * of a probe. If zero, page is disarmed and this may be freed. - * Used only by writers (RCU). + * Used only by writers (RCU) and post_kmmio_handler(). + * Protected by kmmio_lock, when linked into kmmio_page_table. */ int count; }; @@ -105,57 +108,85 @@ static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page) return NULL; } -static void set_page_present(unsigned long addr, bool present, - unsigned int *pglevel) +static void set_pmd_presence(pmd_t *pmd, bool present, bool *old) +{ + pmdval_t v = pmd_val(*pmd); + *old = !!(v & _PAGE_PRESENT); + v &= ~_PAGE_PRESENT; + if (present) + v |= _PAGE_PRESENT; + set_pmd(pmd, __pmd(v)); +} + +static void set_pte_presence(pte_t *pte, bool present, bool *old) +{ + pteval_t v = pte_val(*pte); + *old = !!(v & _PAGE_PRESENT); + v &= ~_PAGE_PRESENT; + if (present) + v |= _PAGE_PRESENT; + set_pte_atomic(pte, __pte(v)); +} + +static int set_page_presence(unsigned long addr, bool present, bool *old) { - pteval_t pteval; - pmdval_t pmdval; unsigned int level; - pmd_t *pmd; pte_t *pte = lookup_address(addr, &level); if (!pte) { pr_err("kmmio: no pte for page 0x%08lx\n", addr); - return; + return -1; } - if (pglevel) - *pglevel = level; - switch (level) { case PG_LEVEL_2M: - pmd = (pmd_t *)pte; - pmdval = pmd_val(*pmd) & ~_PAGE_PRESENT; - if (present) - pmdval |= _PAGE_PRESENT; - set_pmd(pmd, __pmd(pmdval)); + set_pmd_presence((pmd_t *)pte, present, old); break; - case PG_LEVEL_4K: - pteval = pte_val(*pte) & ~_PAGE_PRESENT; - if (present) - pteval |= _PAGE_PRESENT; - set_pte_atomic(pte, __pte(pteval)); + set_pte_presence(pte, present, old); break; - default: pr_err("kmmio: unexpected page level 0x%x.\n", level); - return; + return -1; } __flush_tlb_one(addr); + return 0; } -/** Mark the given page as not present. Access to it will trigger a fault. */ -static void arm_kmmio_fault_page(unsigned long page, unsigned int *pglevel) +/* + * Mark the given page as not present. Access to it will trigger a fault. + * + * Struct kmmio_fault_page is protected by RCU and kmmio_lock, but the + * protection is ignored here. RCU read lock is assumed held, so the struct + * will not disappear unexpectedly. Furthermore, the caller must guarantee, + * that double arming the same virtual address (page) cannot occur. + * + * Double disarming on the other hand is allowed, and may occur when a fault + * and mmiotrace shutdown happen simultaneously. + */ +static int arm_kmmio_fault_page(struct kmmio_fault_page *f) { - set_page_present(page & PAGE_MASK, false, pglevel); + int ret; + WARN_ONCE(f->armed, KERN_ERR "kmmio page already armed.\n"); + if (f->armed) { + pr_warning("kmmio double-arm: page 0x%08lx, ref %d, old %d\n", + f->page, f->count, f->old_presence); + } + ret = set_page_presence(f->page, false, &f->old_presence); + WARN_ONCE(ret < 0, KERN_ERR "kmmio arming 0x%08lx failed.\n", f->page); + f->armed = true; + return ret; } -/** Mark the given page as present. */ -static void disarm_kmmio_fault_page(unsigned long page, unsigned int *pglevel) +/** Restore the given page to saved presence state. */ +static void disarm_kmmio_fault_page(struct kmmio_fault_page *f) { - set_page_present(page & PAGE_MASK, true, pglevel); + bool tmp; + int ret = set_page_presence(f->page, f->old_presence, &tmp); + WARN_ONCE(ret < 0, + KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page); + f->armed = false; } /* @@ -202,28 +233,32 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) ctx = &get_cpu_var(kmmio_ctx); if (ctx->active) { - disarm_kmmio_fault_page(faultpage->page, NULL); if (addr == ctx->addr) { /* - * On SMP we sometimes get recursive probe hits on the - * same address. Context is already saved, fall out. + * A second fault on the same page means some other + * condition needs handling by do_page_fault(), the + * page really not being present is the most common. */ - pr_debug("kmmio: duplicate probe hit on CPU %d, for " - "address 0x%08lx.\n", - smp_processor_id(), addr); - ret = 1; - goto no_kmmio_ctx; - } - /* - * Prevent overwriting already in-flight context. - * This should not happen, let's hope disarming at least - * prevents a panic. - */ - pr_emerg("kmmio: recursive probe hit on CPU %d, " + pr_debug("kmmio: secondary hit for 0x%08lx CPU %d.\n", + addr, smp_processor_id()); + + if (!faultpage->old_presence) + pr_info("kmmio: unexpected secondary hit for " + "address 0x%08lx on CPU %d.\n", addr, + smp_processor_id()); + } else { + /* + * Prevent overwriting already in-flight context. + * This should not happen, let's hope disarming at + * least prevents a panic. + */ + pr_emerg("kmmio: recursive probe hit on CPU %d, " "for address 0x%08lx. Ignoring.\n", smp_processor_id(), addr); - pr_emerg("kmmio: previous hit was at 0x%08lx.\n", - ctx->addr); + pr_emerg("kmmio: previous hit was at 0x%08lx.\n", + ctx->addr); + disarm_kmmio_fault_page(faultpage); + } goto no_kmmio_ctx; } ctx->active++; @@ -244,7 +279,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) regs->flags &= ~X86_EFLAGS_IF; /* Now we set present bit in PTE and single step. */ - disarm_kmmio_fault_page(ctx->fpage->page, NULL); + disarm_kmmio_fault_page(ctx->fpage); /* * If another cpu accesses the same page while we are stepping, @@ -275,7 +310,7 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs) struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx); if (!ctx->active) { - pr_debug("kmmio: spurious debug trap on CPU %d.\n", + pr_warning("kmmio: spurious debug trap on CPU %d.\n", smp_processor_id()); goto out; } @@ -283,7 +318,11 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs) if (ctx->probe && ctx->probe->post_handler) ctx->probe->post_handler(ctx->probe, condition, regs); - arm_kmmio_fault_page(ctx->fpage->page, NULL); + /* Prevent racing against release_kmmio_fault_page(). */ + spin_lock(&kmmio_lock); + if (ctx->fpage->count) + arm_kmmio_fault_page(ctx->fpage); + spin_unlock(&kmmio_lock); regs->flags &= ~X86_EFLAGS_TF; regs->flags |= ctx->saved_flags; @@ -315,20 +354,24 @@ static int add_kmmio_fault_page(unsigned long page) f = get_kmmio_fault_page(page); if (f) { if (!f->count) - arm_kmmio_fault_page(f->page, NULL); + arm_kmmio_fault_page(f); f->count++; return 0; } - f = kmalloc(sizeof(*f), GFP_ATOMIC); + f = kzalloc(sizeof(*f), GFP_ATOMIC); if (!f) return -1; f->count = 1; f->page = page; - list_add_rcu(&f->list, kmmio_page_list(f->page)); - arm_kmmio_fault_page(f->page, NULL); + if (arm_kmmio_fault_page(f)) { + kfree(f); + return -1; + } + + list_add_rcu(&f->list, kmmio_page_list(f->page)); return 0; } @@ -347,7 +390,7 @@ static void release_kmmio_fault_page(unsigned long page, f->count--; BUG_ON(f->count < 0); if (!f->count) { - disarm_kmmio_fault_page(f->page, NULL); + disarm_kmmio_fault_page(f); f->release_next = *release_list; *release_list = f; } @@ -408,23 +451,24 @@ static void rcu_free_kmmio_fault_pages(struct rcu_head *head) static void remove_kmmio_fault_pages(struct rcu_head *head) { - struct kmmio_delayed_release *dr = container_of( - head, - struct kmmio_delayed_release, - rcu); + struct kmmio_delayed_release *dr = + container_of(head, struct kmmio_delayed_release, rcu); struct kmmio_fault_page *p = dr->release_list; struct kmmio_fault_page **prevp = &dr->release_list; unsigned long flags; + spin_lock_irqsave(&kmmio_lock, flags); while (p) { - if (!p->count) + if (!p->count) { list_del_rcu(&p->list); - else + prevp = &p->release_next; + } else { *prevp = p->release_next; - prevp = &p->release_next; + } p = p->release_next; } spin_unlock_irqrestore(&kmmio_lock, flags); + /* This is the real RCU destroy call. */ call_rcu(&dr->rcu, rcu_free_kmmio_fault_pages); } diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c index 0bcd788..605c8be 100644 --- a/arch/x86/mm/memtest.c +++ b/arch/x86/mm/memtest.c @@ -100,6 +100,9 @@ static int __init parse_memtest(char *arg) { if (arg) memtest_pattern = simple_strtoul(arg, NULL, 0); + else + memtest_pattern = ARRAY_SIZE(patterns); + return 0; } diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 451fe95..3daefa0 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -416,10 +416,11 @@ void __init initmem_init(unsigned long start_pfn, for_each_online_node(nid) propagate_e820_map_node(nid); - for_each_online_node(nid) + for_each_online_node(nid) { memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); + NODE_DATA(nid)->bdata = &bootmem_node_data[nid]; + } - NODE_DATA(0)->bdata = &bootmem_node_data[0]; setup_bootmem_allocator(); } diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c index ab50a8d..427fd1b 100644 --- a/arch/x86/mm/testmmiotrace.c +++ b/arch/x86/mm/testmmiotrace.c @@ -1,5 +1,5 @@ /* - * Written by Pekka Paalanen, 2008 <pq@iki.fi> + * Written by Pekka Paalanen, 2008-2009 <pq@iki.fi> */ #include <linux/module.h> #include <linux/io.h> @@ -9,35 +9,74 @@ static unsigned long mmio_address; module_param(mmio_address, ulong, 0); -MODULE_PARM_DESC(mmio_address, "Start address of the mapping of 16 kB."); +MODULE_PARM_DESC(mmio_address, " Start address of the mapping of 16 kB " + "(or 8 MB if read_far is non-zero)."); + +static unsigned long read_far = 0x400100; +module_param(read_far, ulong, 0); +MODULE_PARM_DESC(read_far, " Offset of a 32-bit read within 8 MB " + "(default: 0x400100)."); + +static unsigned v16(unsigned i) +{ + return i * 12 + 7; +} + +static unsigned v32(unsigned i) +{ + return i * 212371 + 13; +} static void do_write_test(void __iomem *p) { unsigned int i; + pr_info(MODULE_NAME ": write test.\n"); mmiotrace_printk("Write test.\n"); + for (i = 0; i < 256; i++) iowrite8(i, p + i); + for (i = 1024; i < (5 * 1024); i += 2) - iowrite16(i * 12 + 7, p + i); + iowrite16(v16(i), p + i); + for (i = (5 * 1024); i < (16 * 1024); i += 4) - iowrite32(i * 212371 + 13, p + i); + iowrite32(v32(i), p + i); } static void do_read_test(void __iomem *p) { unsigned int i; + unsigned errs[3] = { 0 }; + pr_info(MODULE_NAME ": read test.\n"); mmiotrace_printk("Read test.\n"); + for (i = 0; i < 256; i++) - ioread8(p + i); + if (ioread8(p + i) != i) + ++errs[0]; + for (i = 1024; i < (5 * 1024); i += 2) - ioread16(p + i); + if (ioread16(p + i) != v16(i)) + ++errs[1]; + for (i = (5 * 1024); i < (16 * 1024); i += 4) - ioread32(p + i); + if (ioread32(p + i) != v32(i)) + ++errs[2]; + + mmiotrace_printk("Read errors: 8-bit %d, 16-bit %d, 32-bit %d.\n", + errs[0], errs[1], errs[2]); } -static void do_test(void) +static void do_read_far_test(void __iomem *p) { - void __iomem *p = ioremap_nocache(mmio_address, 0x4000); + pr_info(MODULE_NAME ": read far test.\n"); + mmiotrace_printk("Read far test.\n"); + + ioread32(p + read_far); +} + +static void do_test(unsigned long size) +{ + void __iomem *p = ioremap_nocache(mmio_address, size); if (!p) { pr_err(MODULE_NAME ": could not ioremap, aborting.\n"); return; @@ -45,11 +84,15 @@ static void do_test(void) mmiotrace_printk("ioremap returned %p.\n", p); do_write_test(p); do_read_test(p); + if (read_far && read_far < size - 4) + do_read_far_test(p); iounmap(p); } static int __init init(void) { + unsigned long size = (read_far) ? (8 << 20) : (16 << 10); + if (mmio_address == 0) { pr_err(MODULE_NAME ": you have to use the module argument " "mmio_address.\n"); @@ -58,10 +101,11 @@ static int __init init(void) return -ENXIO; } - pr_warning(MODULE_NAME ": WARNING: mapping 16 kB @ 0x%08lx " - "in PCI address space, and writing " - "rubbish in there.\n", mmio_address); - do_test(); + pr_warning(MODULE_NAME ": WARNING: mapping %lu kB @ 0x%08lx in PCI " + "address space, and writing 16 kB of rubbish in there.\n", + size >> 10, mmio_address); + do_test(size); + pr_info(MODULE_NAME ": All done.\n"); return 0; } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c52f403..82cd39a 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -103,7 +103,7 @@ static void xen_vcpu_setup(int cpu) vcpup = &per_cpu(xen_vcpu_info, cpu); - info.mfn = virt_to_mfn(vcpup); + info.mfn = arbitrary_virt_to_mfn(vcpup); info.offset = offset_in_page(vcpup); printk(KERN_DEBUG "trying to map vcpu_info %d at %p, mfn %llx, offset %d\n", @@ -301,8 +301,10 @@ static void xen_load_gdt(const struct desc_ptr *dtr) frames = mcs.args; for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) { - frames[f] = virt_to_mfn(va); + frames[f] = arbitrary_virt_to_mfn((void *)va); + make_lowmem_page_readonly((void *)va); + make_lowmem_page_readonly(mfn_to_virt(frames[f])); } MULTI_set_gdt(mcs.mc, frames, size / sizeof(struct desc_struct)); @@ -314,7 +316,7 @@ static void load_TLS_descriptor(struct thread_struct *t, unsigned int cpu, unsigned int i) { struct desc_struct *gdt = get_cpu_gdt_table(cpu); - xmaddr_t maddr = virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]); + xmaddr_t maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]); struct multicall_space mc = __xen_mc_entry(0); MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]); @@ -488,7 +490,7 @@ static void xen_write_gdt_entry(struct desc_struct *dt, int entry, break; default: { - xmaddr_t maddr = virt_to_machine(&dt[entry]); + xmaddr_t maddr = arbitrary_virt_to_machine(&dt[entry]); xen_mc_flush(); if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc)) diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 319bd40..cb6afa4 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -276,6 +276,13 @@ void set_phys_to_machine(unsigned long pfn, unsigned long mfn) p2m_top[topidx][idx] = mfn; } +unsigned long arbitrary_virt_to_mfn(void *vaddr) +{ + xmaddr_t maddr = arbitrary_virt_to_machine(vaddr); + + return PFN_DOWN(maddr.maddr); +} + xmaddr_t arbitrary_virt_to_machine(void *vaddr) { unsigned long address = (unsigned long)vaddr; diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 035582a..8d47056 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -219,6 +219,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) { struct vcpu_guest_context *ctxt; struct desc_struct *gdt; + unsigned long gdt_mfn; if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map)) return 0; @@ -248,9 +249,12 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) ctxt->ldt_ents = 0; BUG_ON((unsigned long)gdt & ~PAGE_MASK); + + gdt_mfn = arbitrary_virt_to_mfn(gdt); make_lowmem_page_readonly(gdt); + make_lowmem_page_readonly(mfn_to_virt(gdt_mfn)); - ctxt->gdt_frames[0] = virt_to_mfn(gdt); + ctxt->gdt_frames[0] = gdt_mfn; ctxt->gdt_ents = GDT_ENTRIES; ctxt->user_regs.cs = __KERNEL_CS; diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 6c873dc..9812008 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -103,9 +103,6 @@ config MATH_EMULATION help Can we use information of configuration file? -config HIGHMEM - bool "High memory support" - endmenu menu "Platform options" diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 9606d2b..4ec1633 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -44,6 +44,8 @@ #include <asm/setup.h> #include <asm/param.h> +#include <platform/hardware.h> + #if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE) struct screen_info screen_info = { 0, 24, 0, 0, 0, 80, 0, 0, 0, 24, 1, 16}; #endif diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index c7a021d..c44f830 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -30,6 +30,7 @@ #include <linux/stringify.h> #include <linux/kallsyms.h> #include <linux/delay.h> +#include <linux/hardirq.h> #include <asm/ptrace.h> #include <asm/timex.h> diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 33f366b..bdd860d 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -14,6 +14,7 @@ #include <linux/mm.h> #include <linux/module.h> +#include <linux/hardirq.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/hardirq.h> diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index efed889..25d46c8 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -140,16 +140,14 @@ static void rs_poll(unsigned long priv) } -static void rs_put_char(struct tty_struct *tty, unsigned char ch) +static int rs_put_char(struct tty_struct *tty, unsigned char ch) { char buf[2]; - if (!tty) - return; - buf[0] = ch; buf[1] = '\0'; /* Is this NULL necessary? */ __simc (SYS_write, 1, (unsigned long) buf, 1, 0, 0); + return 1; } static void rs_flush_chars(struct tty_struct *tty) diff --git a/block/blk-merge.c b/block/blk-merge.c index a104593..5a244f0 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -39,14 +39,13 @@ void blk_recalc_rq_sectors(struct request *rq, int nsect) } static unsigned int __blk_recalc_rq_segments(struct request_queue *q, - struct bio *bio, - unsigned int *seg_size_ptr) + struct bio *bio) { unsigned int phys_size; struct bio_vec *bv, *bvprv = NULL; int cluster, i, high, highprv = 1; unsigned int seg_size, nr_phys_segs; - struct bio *fbio; + struct bio *fbio, *bbio; if (!bio) return 0; @@ -87,26 +86,20 @@ new_segment: seg_size = bv->bv_len; highprv = high; } + bbio = bio; } - if (seg_size_ptr) - *seg_size_ptr = seg_size; + if (nr_phys_segs == 1 && seg_size > fbio->bi_seg_front_size) + fbio->bi_seg_front_size = seg_size; + if (seg_size > bbio->bi_seg_back_size) + bbio->bi_seg_back_size = seg_size; return nr_phys_segs; } void blk_recalc_rq_segments(struct request *rq) { - unsigned int seg_size = 0, phys_segs; - - phys_segs = __blk_recalc_rq_segments(rq->q, rq->bio, &seg_size); - - if (phys_segs == 1 && seg_size > rq->bio->bi_seg_front_size) - rq->bio->bi_seg_front_size = seg_size; - if (seg_size > rq->biotail->bi_seg_back_size) - rq->biotail->bi_seg_back_size = seg_size; - - rq->nr_phys_segments = phys_segs; + rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio); } void blk_recount_segments(struct request_queue *q, struct bio *bio) @@ -114,7 +107,7 @@ void blk_recount_segments(struct request_queue *q, struct bio *bio) struct bio *nxt = bio->bi_next; bio->bi_next = NULL; - bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio, NULL); + bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio); bio->bi_next = nxt; bio->bi_flags |= (1 << BIO_SEG_VALID); } diff --git a/block/blktrace.c b/block/blktrace.c index 7cf9d1f..028120a 100644 --- a/block/blktrace.c +++ b/block/blktrace.c @@ -363,7 +363,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (!bt->sequence) goto err; - bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG); + bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char)); if (!bt->msg_data) goto err; diff --git a/crypto/api.c b/crypto/api.c index efe77df..38a2bc0 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -215,8 +215,19 @@ struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, u32 mask) mask &= ~(CRYPTO_ALG_LARVAL | CRYPTO_ALG_DEAD); type &= mask; - alg = try_then_request_module(crypto_alg_lookup(name, type, mask), - name); + alg = crypto_alg_lookup(name, type, mask); + if (!alg) { + char tmp[CRYPTO_MAX_ALG_NAME]; + + request_module(name); + + if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask) && + snprintf(tmp, sizeof(tmp), "%s-all", name) < sizeof(tmp)) + request_module(tmp); + + alg = crypto_alg_lookup(name, type, mask); + } + if (alg) return crypto_is_larval(alg) ? crypto_larval_wait(alg) : alg; diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 9cc769b..68fd3d2 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -516,12 +516,12 @@ int acpi_processor_preregister_performance( continue; } - if (!performance || !percpu_ptr(performance, i)) { + if (!performance || !per_cpu_ptr(performance, i)) { retval = -EINVAL; continue; } - pr->performance = percpu_ptr(performance, i); + pr->performance = per_cpu_ptr(performance, i); cpumask_set_cpu(i, pr->performance->shared_cpu_map); if (acpi_processor_get_psd(pr)) { retval = -EINVAL; diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index a603bbf..66e012c 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -582,18 +582,18 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(NVIDIA, 0x0abd), board_ahci }, /* MCP79 */ { PCI_VDEVICE(NVIDIA, 0x0abe), board_ahci }, /* MCP79 */ { PCI_VDEVICE(NVIDIA, 0x0abf), board_ahci }, /* MCP79 */ - { PCI_VDEVICE(NVIDIA, 0x0bc8), board_ahci }, /* MCP7B */ - { PCI_VDEVICE(NVIDIA, 0x0bc9), board_ahci }, /* MCP7B */ - { PCI_VDEVICE(NVIDIA, 0x0bca), board_ahci }, /* MCP7B */ - { PCI_VDEVICE(NVIDIA, 0x0bcb), board_ahci }, /* MCP7B */ - { PCI_VDEVICE(NVIDIA, 0x0bcc), board_ahci }, /* MCP7B */ - { PCI_VDEVICE(NVIDIA, 0x0bcd), board_ahci }, /* MCP7B */ - { PCI_VDEVICE(NVIDIA, 0x0bce), board_ahci }, /* MCP7B */ - { PCI_VDEVICE(NVIDIA, 0x0bcf), board_ahci }, /* MCP7B */ - { PCI_VDEVICE(NVIDIA, 0x0bc4), board_ahci }, /* MCP7B */ - { PCI_VDEVICE(NVIDIA, 0x0bc5), board_ahci }, /* MCP7B */ - { PCI_VDEVICE(NVIDIA, 0x0bc6), board_ahci }, /* MCP7B */ - { PCI_VDEVICE(NVIDIA, 0x0bc7), board_ahci }, /* MCP7B */ + { PCI_VDEVICE(NVIDIA, 0x0d84), board_ahci }, /* MCP89 */ + { PCI_VDEVICE(NVIDIA, 0x0d85), board_ahci }, /* MCP89 */ + { PCI_VDEVICE(NVIDIA, 0x0d86), board_ahci }, /* MCP89 */ + { PCI_VDEVICE(NVIDIA, 0x0d87), board_ahci }, /* MCP89 */ + { PCI_VDEVICE(NVIDIA, 0x0d88), board_ahci }, /* MCP89 */ + { PCI_VDEVICE(NVIDIA, 0x0d89), board_ahci }, /* MCP89 */ + { PCI_VDEVICE(NVIDIA, 0x0d8a), board_ahci }, /* MCP89 */ + { PCI_VDEVICE(NVIDIA, 0x0d8b), board_ahci }, /* MCP89 */ + { PCI_VDEVICE(NVIDIA, 0x0d8c), board_ahci }, /* MCP89 */ + { PCI_VDEVICE(NVIDIA, 0x0d8d), board_ahci }, /* MCP89 */ + { PCI_VDEVICE(NVIDIA, 0x0d8e), board_ahci }, /* MCP89 */ + { PCI_VDEVICE(NVIDIA, 0x0d8f), board_ahci }, /* MCP89 */ /* SiS */ { PCI_VDEVICE(SI, 0x1184), board_ahci }, /* SiS 966 */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 9fbf059..060bcd6 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -1322,14 +1322,16 @@ static u64 ata_id_n_sectors(const u16 *id) { if (ata_id_has_lba(id)) { if (ata_id_has_lba48(id)) - return ata_id_u64(id, 100); + return ata_id_u64(id, ATA_ID_LBA_CAPACITY_2); else - return ata_id_u32(id, 60); + return ata_id_u32(id, ATA_ID_LBA_CAPACITY); } else { if (ata_id_current_chs_valid(id)) - return ata_id_u32(id, 57); + return id[ATA_ID_CUR_CYLS] * id[ATA_ID_CUR_HEADS] * + id[ATA_ID_CUR_SECTORS]; else - return id[1] * id[3] * id[6]; + return id[ATA_ID_CYLS] * id[ATA_ID_HEADS] * + id[ATA_ID_SECTORS]; } } @@ -4612,7 +4614,7 @@ void ata_sg_clean(struct ata_queued_cmd *qc) VPRINTK("unmapping %u sg elements\n", qc->n_elem); if (qc->n_elem) - dma_unmap_sg(ap->dev, sg, qc->n_elem, dir); + dma_unmap_sg(ap->dev, sg, qc->orig_n_elem, dir); qc->flags &= ~ATA_QCFLAG_DMAMAP; qc->sg = NULL; @@ -4727,7 +4729,7 @@ static int ata_sg_setup(struct ata_queued_cmd *qc) return -1; DPRINTK("%d sg elements mapped\n", n_elem); - + qc->orig_n_elem = qc->n_elem; qc->n_elem = n_elem; qc->flags |= ATA_QCFLAG_DMAMAP; diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index ce2ef04..ea89091 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -2423,11 +2423,14 @@ int ata_eh_reset(struct ata_link *link, int classify, } /* prereset() might have cleared ATA_EH_RESET. If so, - * bang classes and return. + * bang classes, thaw and return. */ if (reset && !(ehc->i.action & ATA_EH_RESET)) { ata_for_each_dev(dev, link, ALL) classes[dev->devno] = ATA_DEV_NONE; + if ((ap->pflags & ATA_PFLAG_FROZEN) && + ata_is_host_link(link)) + ata_eh_thaw_port(ap); rc = 0; goto out; } @@ -2901,7 +2904,7 @@ static int atapi_eh_clear_ua(struct ata_device *dev) int i; for (i = 0; i < ATA_EH_UA_TRIES; i++) { - u8 sense_buffer[SCSI_SENSE_BUFFERSIZE]; + u8 *sense_buffer = dev->link->ap->sector_buf; u8 sense_key = 0; unsigned int err_mask; diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 55a8eed..f65b537 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -2523,7 +2523,7 @@ static void __exit nv_exit(void) module_init(nv_init); module_exit(nv_exit); module_param_named(adma, adma_enabled, bool, 0444); -MODULE_PARM_DESC(adma, "Enable use of ADMA (Default: true)"); +MODULE_PARM_DESC(adma, "Enable use of ADMA (Default: false)"); module_param_named(swncq, swncq_enabled, bool, 0444); MODULE_PARM_DESC(swncq, "Enable use of SWNCQ (Default: true)"); diff --git a/drivers/base/node.c b/drivers/base/node.c index 43fa90b..f8f578a 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -303,7 +303,7 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk) sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index); sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1; for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) { - unsigned int nid; + int nid; nid = get_nid_for_pfn(pfn); if (nid < 0) diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c index cc25057..eeea477 100644 --- a/drivers/block/aoe/aoedev.c +++ b/drivers/block/aoe/aoedev.c @@ -173,7 +173,7 @@ skbfree(struct sk_buff *skb) return; while (atomic_read(&skb_shinfo(skb)->dataref) != 1 && i-- > 0) msleep(Sms); - if (i <= 0) { + if (i < 0) { printk(KERN_ERR "aoe: %s holds ref: %s\n", skb->dev ? skb->dev->name : "netif", diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index b5a0611..4f9b6d7 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -3606,11 +3606,9 @@ static int __devinit cciss_init_one(struct pci_dev *pdev, if (cciss_hard_reset_controller(pdev) || cciss_reset_msi(pdev)) return -ENODEV; - /* Some devices (notably the HP Smart Array 5i Controller) - need a little pause here */ - schedule_timeout_uninterruptible(30*HZ); - - /* Now try to get the controller to respond to a no-op */ + /* Now try to get the controller to respond to a no-op. Some + devices (notably the HP Smart Array 5i Controller) need + up to 30 seconds to respond. */ for (i=0; i<30; i++) { if (cciss_noop(pdev) == 0) break; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index edbaac6..bf03455 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -392,8 +392,7 @@ lo_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct loop_device *lo = p->lo; struct page *page = buf->page; sector_t IV; - size_t size; - int ret; + int size, ret; ret = buf->ops->confirm(pipe, buf); if (unlikely(ret)) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index b6c8ce2..8f90508 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -977,6 +977,8 @@ static void backend_changed(struct xenbus_device *dev, break; case XenbusStateClosing: + if (info->gd == NULL) + xenbus_dev_fatal(dev, -ENODEV, "gd is NULL"); bd = bdget_disk(info->gd, 0); if (bd == NULL) xenbus_dev_fatal(dev, -ENODEV, "bdget failed"); diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c index 52f4361..d765afd 100644 --- a/drivers/char/agp/amd64-agp.c +++ b/drivers/char/agp/amd64-agp.c @@ -271,15 +271,15 @@ static __devinit int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp, nb_order = (nb_order >> 1) & 7; pci_read_config_dword(nb, AMD64_GARTAPERTUREBASE, &nb_base); nb_aper = nb_base << 25; - if (agp_aperture_valid(nb_aper, (32*1024*1024)<<nb_order)) { - return 0; - } /* Northbridge seems to contain crap. Try the AGP bridge. */ pci_read_config_word(agp, cap+0x14, &apsize); - if (apsize == 0xffff) + if (apsize == 0xffff) { + if (agp_aperture_valid(nb_aper, (32*1024*1024)<<nb_order)) + return 0; return -1; + } apsize &= 0xfff; /* Some BIOS use weird encodings not in the AGPv3 table. */ @@ -301,6 +301,11 @@ static __devinit int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp, order = nb_order; } + if (nb_order >= order) { + if (agp_aperture_valid(nb_aper, (32*1024*1024)<<nb_order)) + return 0; + } + dev_info(&agp->dev, "aperture from AGP @ %Lx size %u MB\n", aper, 32 << order); if (order < 0 || !agp_aperture_valid(aper, (32*1024*1024)<<order)) diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index c771418..4373adb 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -633,13 +633,15 @@ static void intel_i830_init_gtt_entries(void) break; } } - if (gtt_entries > 0) + if (gtt_entries > 0) { dev_info(&agp_bridge->dev->dev, "detected %dK %s memory\n", gtt_entries / KB(1), local ? "local" : "stolen"); - else + gtt_entries /= KB(4); + } else { dev_info(&agp_bridge->dev->dev, "no pre-allocated video memory detected\n"); - gtt_entries /= KB(4); + gtt_entries = 0; + } intel_private.gtt_entries = gtt_entries; } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index b55cb67..d6daf3c 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -754,11 +754,6 @@ static struct kobj_type ktype_cpufreq = { .release = cpufreq_sysfs_release, }; -static struct kobj_type ktype_empty_cpufreq = { - .sysfs_ops = &sysfs_ops, - .release = cpufreq_sysfs_release, -}; - /** * cpufreq_add_dev - add a CPU device @@ -892,36 +887,26 @@ static int cpufreq_add_dev(struct sys_device *sys_dev) memcpy(&new_policy, policy, sizeof(struct cpufreq_policy)); /* prepare interface data */ - if (!cpufreq_driver->hide_interface) { - ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, - &sys_dev->kobj, "cpufreq"); + ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, &sys_dev->kobj, + "cpufreq"); + if (ret) + goto err_out_driver_exit; + + /* set up files for this cpu device */ + drv_attr = cpufreq_driver->attr; + while ((drv_attr) && (*drv_attr)) { + ret = sysfs_create_file(&policy->kobj, &((*drv_attr)->attr)); if (ret) goto err_out_driver_exit; - - /* set up files for this cpu device */ - drv_attr = cpufreq_driver->attr; - while ((drv_attr) && (*drv_attr)) { - ret = sysfs_create_file(&policy->kobj, - &((*drv_attr)->attr)); - if (ret) - goto err_out_driver_exit; - drv_attr++; - } - if (cpufreq_driver->get) { - ret = sysfs_create_file(&policy->kobj, - &cpuinfo_cur_freq.attr); - if (ret) - goto err_out_driver_exit; - } - if (cpufreq_driver->target) { - ret = sysfs_create_file(&policy->kobj, - &scaling_cur_freq.attr); - if (ret) - goto err_out_driver_exit; - } - } else { - ret = kobject_init_and_add(&policy->kobj, &ktype_empty_cpufreq, - &sys_dev->kobj, "cpufreq"); + drv_attr++; + } + if (cpufreq_driver->get) { + ret = sysfs_create_file(&policy->kobj, &cpuinfo_cur_freq.attr); + if (ret) + goto err_out_driver_exit; + } + if (cpufreq_driver->target) { + ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr); if (ret) goto err_out_driver_exit; } diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c index 2d637e0..d9e751b 100644 --- a/drivers/crypto/ixp4xx_crypto.c +++ b/drivers/crypto/ixp4xx_crypto.c @@ -457,10 +457,12 @@ static int init_ixp_crypto(void) if (!ctx_pool) { goto err; } - ret = qmgr_request_queue(SEND_QID, NPE_QLEN_TOTAL, 0, 0); + ret = qmgr_request_queue(SEND_QID, NPE_QLEN_TOTAL, 0, 0, + "ixp_crypto:out", NULL); if (ret) goto err; - ret = qmgr_request_queue(RECV_QID, NPE_QLEN, 0, 0); + ret = qmgr_request_queue(RECV_QID, NPE_QLEN, 0, 0, + "ixp_crypto:in", NULL); if (ret) { qmgr_release_queue(SEND_QID); goto err; diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index 856b3cc..3f0fdd1 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -489,4 +489,4 @@ MODULE_DESCRIPTION("VIA PadLock AES algorithm support"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michal Ludvig"); -MODULE_ALIAS("aes"); +MODULE_ALIAS("aes-all"); diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c index a7fbade..a2c8e85 100644 --- a/drivers/crypto/padlock-sha.c +++ b/drivers/crypto/padlock-sha.c @@ -304,7 +304,7 @@ MODULE_DESCRIPTION("VIA PadLock SHA1/SHA256 algorithms support."); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michal Ludvig"); -MODULE_ALIAS("sha1"); -MODULE_ALIAS("sha256"); +MODULE_ALIAS("sha1-all"); +MODULE_ALIAS("sha256-all"); MODULE_ALIAS("sha1-padlock"); MODULE_ALIAS("sha256-padlock"); diff --git a/drivers/dca/dca-core.c b/drivers/dca/dca-core.c index 33bd753..25b743a 100644 --- a/drivers/dca/dca-core.c +++ b/drivers/dca/dca-core.c @@ -1,5 +1,5 @@ /* - * Copyright(c) 2007 Intel Corporation. All rights reserved. + * Copyright(c) 2007 - 2009 Intel Corporation. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 732fa1e..e190d8b 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -430,13 +430,15 @@ late_initcall(dmatest_init); static void __exit dmatest_exit(void) { struct dmatest_chan *dtc, *_dtc; + struct dma_chan *chan; list_for_each_entry_safe(dtc, _dtc, &dmatest_channels, node) { list_del(&dtc->node); + chan = dtc->chan; dmatest_cleanup_channel(dtc); pr_debug("dmatest: dropped channel %s\n", - dma_chan_name(dtc->chan)); - dma_release_channel(dtc->chan); + dma_chan_name(chan)); + dma_release_channel(chan); } } module_exit(dmatest_exit); diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index 70126a6..86d6da4 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -158,7 +158,8 @@ static void dma_start(struct fsl_dma_chan *fsl_chan) static void dma_halt(struct fsl_dma_chan *fsl_chan) { - int i = 0; + int i; + DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr, DMA_IN(fsl_chan, &fsl_chan->reg_base->mr, 32) | FSL_DMA_MR_CA, 32); @@ -166,8 +167,11 @@ static void dma_halt(struct fsl_dma_chan *fsl_chan) DMA_IN(fsl_chan, &fsl_chan->reg_base->mr, 32) & ~(FSL_DMA_MR_CS | FSL_DMA_MR_EMS_EN | FSL_DMA_MR_CA), 32); - while (!dma_is_idle(fsl_chan) && (i++ < 100)) + for (i = 0; i < 100; i++) { + if (dma_is_idle(fsl_chan)) + break; udelay(10); + } if (i >= 100 && !dma_is_idle(fsl_chan)) dev_err(fsl_chan->dev, "DMA halt timeout!\n"); } diff --git a/drivers/dma/ioat.c b/drivers/dma/ioat.c index 4105d65..ed83dd9 100644 --- a/drivers/dma/ioat.c +++ b/drivers/dma/ioat.c @@ -1,6 +1,6 @@ /* * Intel I/OAT DMA Linux driver - * Copyright(c) 2007 Intel Corporation. + * Copyright(c) 2007 - 2009 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, diff --git a/drivers/dma/ioat_dca.c b/drivers/dma/ioat_dca.c index 6cf622d..c012a1e 100644 --- a/drivers/dma/ioat_dca.c +++ b/drivers/dma/ioat_dca.c @@ -1,6 +1,6 @@ /* * Intel I/OAT DMA Linux driver - * Copyright(c) 2007 Intel Corporation. + * Copyright(c) 2007 - 2009 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -49,6 +49,23 @@ #define DCA_TAG_MAP_MASK 0xDF +/* expected tag map bytes for I/OAT ver.2 */ +#define DCA2_TAG_MAP_BYTE0 0x80 +#define DCA2_TAG_MAP_BYTE1 0x0 +#define DCA2_TAG_MAP_BYTE2 0x81 +#define DCA2_TAG_MAP_BYTE3 0x82 +#define DCA2_TAG_MAP_BYTE4 0x82 + +/* verify if tag map matches expected values */ +static inline int dca2_tag_map_valid(u8 *tag_map) +{ + return ((tag_map[0] == DCA2_TAG_MAP_BYTE0) && + (tag_map[1] == DCA2_TAG_MAP_BYTE1) && + (tag_map[2] == DCA2_TAG_MAP_BYTE2) && + (tag_map[3] == DCA2_TAG_MAP_BYTE3) && + (tag_map[4] == DCA2_TAG_MAP_BYTE4)); +} + /* * "Legacy" DCA systems do not implement the DCA register set in the * I/OAT device. Software needs direct support for their tag mappings. @@ -452,6 +469,13 @@ struct dca_provider *ioat2_dca_init(struct pci_dev *pdev, void __iomem *iobase) ioatdca->tag_map[i] = 0; } + if (!dca2_tag_map_valid(ioatdca->tag_map)) { + dev_err(&pdev->dev, "APICID_TAG_MAP set incorrectly by BIOS, " + "disabling DCA\n"); + free_dca_provider(dca); + return NULL; + } + err = register_dca_provider(dca, &pdev->dev); if (err) { free_dca_provider(dca); diff --git a/drivers/dma/ioat_dma.c b/drivers/dma/ioat_dma.c index b3759c4..5905cd3 100644 --- a/drivers/dma/ioat_dma.c +++ b/drivers/dma/ioat_dma.c @@ -1,6 +1,6 @@ /* * Intel I/OAT DMA Linux driver - * Copyright(c) 2004 - 2007 Intel Corporation. + * Copyright(c) 2004 - 2009 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -189,11 +189,13 @@ static int ioat_dma_enumerate_channels(struct ioatdma_device *device) ioat_chan->xfercap = xfercap; ioat_chan->desccount = 0; INIT_DELAYED_WORK(&ioat_chan->work, ioat_dma_chan_reset_part2); - if (ioat_chan->device->version != IOAT_VER_1_2) { - writel(IOAT_DCACTRL_CMPL_WRITE_ENABLE - | IOAT_DMA_DCA_ANY_CPU, - ioat_chan->reg_base + IOAT_DCACTRL_OFFSET); - } + if (ioat_chan->device->version == IOAT_VER_2_0) + writel(IOAT_DCACTRL_CMPL_WRITE_ENABLE | + IOAT_DMA_DCA_ANY_CPU, + ioat_chan->reg_base + IOAT_DCACTRL_OFFSET); + else if (ioat_chan->device->version == IOAT_VER_3_0) + writel(IOAT_DMA_DCA_ANY_CPU, + ioat_chan->reg_base + IOAT_DCACTRL_OFFSET); spin_lock_init(&ioat_chan->cleanup_lock); spin_lock_init(&ioat_chan->desc_lock); INIT_LIST_HEAD(&ioat_chan->free_desc); @@ -1169,9 +1171,8 @@ static void ioat_dma_memcpy_cleanup(struct ioat_dma_chan *ioat_chan) * up if the client is done with the descriptor */ if (async_tx_test_ack(&desc->async_tx)) { - list_del(&desc->node); - list_add_tail(&desc->node, - &ioat_chan->free_desc); + list_move_tail(&desc->node, + &ioat_chan->free_desc); } else desc->async_tx.cookie = 0; } else { @@ -1362,6 +1363,7 @@ static int ioat_dma_self_test(struct ioatdma_device *device) dma_cookie_t cookie; int err = 0; struct completion cmp; + unsigned long tmo; src = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL); if (!src) @@ -1413,9 +1415,10 @@ static int ioat_dma_self_test(struct ioatdma_device *device) } device->common.device_issue_pending(dma_chan); - wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)); + tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)); - if (device->common.device_is_tx_complete(dma_chan, cookie, NULL, NULL) + if (tmo == 0 || + device->common.device_is_tx_complete(dma_chan, cookie, NULL, NULL) != DMA_SUCCESS) { dev_err(&device->pdev->dev, "Self-test copy timed out, disabling\n"); @@ -1657,6 +1660,13 @@ struct ioatdma_device *ioat_dma_probe(struct pci_dev *pdev, " %d channels, device version 0x%02x, driver version %s\n", device->common.chancnt, device->version, IOAT_DMA_VERSION); + if (!device->common.chancnt) { + dev_err(&device->pdev->dev, + "Intel(R) I/OAT DMA Engine problem found: " + "zero channels detected\n"); + goto err_setup_interrupts; + } + err = ioat_dma_setup_interrupts(device); if (err) goto err_setup_interrupts; @@ -1696,6 +1706,9 @@ void ioat_dma_remove(struct ioatdma_device *device) struct dma_chan *chan, *_chan; struct ioat_dma_chan *ioat_chan; + if (device->version != IOAT_VER_3_0) + cancel_delayed_work(&device->work); + ioat_dma_remove_interrupts(device); dma_async_device_unregister(&device->common); @@ -1707,10 +1720,6 @@ void ioat_dma_remove(struct ioatdma_device *device) pci_release_regions(device->pdev); pci_disable_device(device->pdev); - if (device->version != IOAT_VER_3_0) { - cancel_delayed_work(&device->work); - } - list_for_each_entry_safe(chan, _chan, &device->common.channels, device_node) { ioat_chan = to_ioat_chan(chan); diff --git a/drivers/dma/ioatdma.h b/drivers/dma/ioatdma.h index a3306d0..a52ff4b 100644 --- a/drivers/dma/ioatdma.h +++ b/drivers/dma/ioatdma.h @@ -1,5 +1,5 @@ /* - * Copyright(c) 2004 - 2007 Intel Corporation. All rights reserved. + * Copyright(c) 2004 - 2009 Intel Corporation. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free @@ -29,7 +29,7 @@ #include <linux/pci_ids.h> #include <net/tcp.h> -#define IOAT_DMA_VERSION "3.30" +#define IOAT_DMA_VERSION "3.64" enum ioat_interrupt { none = 0, @@ -135,12 +135,14 @@ static inline void ioat_set_tcp_copy_break(struct ioatdma_device *dev) #ifdef CONFIG_NET_DMA switch (dev->version) { case IOAT_VER_1_2: - case IOAT_VER_3_0: sysctl_tcp_dma_copybreak = 4096; break; case IOAT_VER_2_0: sysctl_tcp_dma_copybreak = 2048; break; + case IOAT_VER_3_0: + sysctl_tcp_dma_copybreak = 262144; + break; } #endif } diff --git a/drivers/dma/ioatdma_hw.h b/drivers/dma/ioatdma_hw.h index f1ae2c7..afa57ee 100644 --- a/drivers/dma/ioatdma_hw.h +++ b/drivers/dma/ioatdma_hw.h @@ -1,5 +1,5 @@ /* - * Copyright(c) 2004 - 2007 Intel Corporation. All rights reserved. + * Copyright(c) 2004 - 2009 Intel Corporation. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free diff --git a/drivers/dma/ioatdma_registers.h b/drivers/dma/ioatdma_registers.h index 827cb50..49bc277 100644 --- a/drivers/dma/ioatdma_registers.h +++ b/drivers/dma/ioatdma_registers.h @@ -1,5 +1,5 @@ /* - * Copyright(c) 2004 - 2007 Intel Corporation. All rights reserved. + * Copyright(c) 2004 - 2009 Intel Corporation. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c index ea5440d..16adbe6 100644 --- a/drivers/dma/iop-adma.c +++ b/drivers/dma/iop-adma.c @@ -928,19 +928,19 @@ iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device) for (src_idx = 0; src_idx < IOP_ADMA_NUM_SRC_TEST; src_idx++) { xor_srcs[src_idx] = alloc_page(GFP_KERNEL); - if (!xor_srcs[src_idx]) - while (src_idx--) { + if (!xor_srcs[src_idx]) { + while (src_idx--) __free_page(xor_srcs[src_idx]); - return -ENOMEM; - } + return -ENOMEM; + } } dest = alloc_page(GFP_KERNEL); - if (!dest) - while (src_idx--) { + if (!dest) { + while (src_idx--) __free_page(xor_srcs[src_idx]); - return -ENOMEM; - } + return -ENOMEM; + } /* Fill in src buffers */ for (src_idx = 0; src_idx < IOP_ADMA_NUM_SRC_TEST; src_idx++) { @@ -1401,7 +1401,7 @@ MODULE_ALIAS("platform:iop-adma"); static struct platform_driver iop_adma_driver = { .probe = iop_adma_probe, - .remove = iop_adma_remove, + .remove = __devexit_p(iop_adma_remove), .driver = { .owner = THIS_MODULE, .name = "iop-adma", diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c index 1f154d0..ae50a9d 100644 --- a/drivers/dma/ipu/ipu_idmac.c +++ b/drivers/dma/ipu/ipu_idmac.c @@ -729,7 +729,7 @@ static int ipu_init_channel_buffer(struct idmac_channel *ichan, ichan->status = IPU_CHANNEL_READY; - spin_unlock_irqrestore(ipu->lock, flags); + spin_unlock_irqrestore(&ipu->lock, flags); return 0; } diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index d35cbd1..cb7f26f 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -1019,19 +1019,19 @@ mv_xor_xor_self_test(struct mv_xor_device *device) for (src_idx = 0; src_idx < MV_XOR_NUM_SRC_TEST; src_idx++) { xor_srcs[src_idx] = alloc_page(GFP_KERNEL); - if (!xor_srcs[src_idx]) - while (src_idx--) { + if (!xor_srcs[src_idx]) { + while (src_idx--) __free_page(xor_srcs[src_idx]); - return -ENOMEM; - } + return -ENOMEM; + } } dest = alloc_page(GFP_KERNEL); - if (!dest) - while (src_idx--) { + if (!dest) { + while (src_idx--) __free_page(xor_srcs[src_idx]); - return -ENOMEM; - } + return -ENOMEM; + } /* Fill in src buffers */ for (src_idx = 0; src_idx < MV_XOR_NUM_SRC_TEST; src_idx++) { @@ -1287,7 +1287,7 @@ mv_xor_conf_mbus_windows(struct mv_xor_shared_private *msp, static struct platform_driver mv_xor_driver = { .probe = mv_xor_probe, - .remove = mv_xor_remove, + .remove = __devexit_p(mv_xor_remove), .driver = { .owner = THIS_MODULE, .name = MV_XOR_NAME, diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c index 096e2a3..7c8b15b 100644 --- a/drivers/gpu/drm/drm_stub.c +++ b/drivers/gpu/drm/drm_stub.c @@ -168,7 +168,7 @@ int drm_setmaster_ioctl(struct drm_device *dev, void *data, file_priv->minor->master != file_priv->master) { mutex_lock(&dev->struct_mutex); file_priv->minor->master = drm_master_get(file_priv->master); - mutex_lock(&dev->struct_mutex); + mutex_unlock(&dev->struct_mutex); } return 0; diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c index cfc1ee9..b251d86 100644 --- a/drivers/hwmon/lm85.c +++ b/drivers/hwmon/lm85.c @@ -72,6 +72,7 @@ I2C_CLIENT_INSMOD_7(lm85b, lm85c, adm1027, adt7463, adt7468, emc6d100, #define LM85_COMPANY_SMSC 0x5c #define LM85_VERSTEP_VMASK 0xf0 #define LM85_VERSTEP_GENERIC 0x60 +#define LM85_VERSTEP_GENERIC2 0x70 #define LM85_VERSTEP_LM85C 0x60 #define LM85_VERSTEP_LM85B 0x62 #define LM85_VERSTEP_ADM1027 0x60 @@ -334,6 +335,7 @@ static struct lm85_data *lm85_update_device(struct device *dev); static const struct i2c_device_id lm85_id[] = { { "adm1027", adm1027 }, { "adt7463", adt7463 }, + { "adt7468", adt7468 }, { "lm85", any_chip }, { "lm85b", lm85b }, { "lm85c", lm85c }, @@ -408,7 +410,8 @@ static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr, struct lm85_data *data = lm85_update_device(dev); int vid; - if (data->type == adt7463 && (data->vid & 0x80)) { + if ((data->type == adt7463 || data->type == adt7468) && + (data->vid & 0x80)) { /* 6-pin VID (VRM 10) */ vid = vid_from_reg(data->vid & 0x3f, data->vrm); } else { @@ -1153,7 +1156,8 @@ static int lm85_detect(struct i2c_client *client, int kind, address, company, verstep); /* All supported chips have the version in common */ - if ((verstep & LM85_VERSTEP_VMASK) != LM85_VERSTEP_GENERIC) { + if ((verstep & LM85_VERSTEP_VMASK) != LM85_VERSTEP_GENERIC && + (verstep & LM85_VERSTEP_VMASK) != LM85_VERSTEP_GENERIC2) { dev_dbg(&adapter->dev, "Autodetection failed: " "unsupported version\n"); return -ENODEV; diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index eeda276f..7f186bb 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -482,7 +482,7 @@ mv64xxx_i2c_map_regs(struct platform_device *pd, return 0; } -static void __devexit +static void mv64xxx_i2c_unmap_regs(struct mv64xxx_i2c_data *drv_data) { if (drv_data->reg_base) { @@ -577,7 +577,7 @@ mv64xxx_i2c_remove(struct platform_device *dev) static struct platform_driver mv64xxx_i2c_driver = { .probe = mv64xxx_i2c_probe, - .remove = mv64xxx_i2c_remove, + .remove = __devexit_p(mv64xxx_i2c_remove), .driver = { .owner = THIS_MODULE, .name = MV64XXX_I2C_CTLR_NAME, diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig index e072903..5ea3bfa 100644 --- a/drivers/ide/Kconfig +++ b/drivers/ide/Kconfig @@ -721,6 +721,11 @@ config BLK_DEV_IDE_TX4939 depends on SOC_TX4939 select BLK_DEV_IDEDMA_SFF +config BLK_DEV_IDE_AT91 + tristate "Atmel AT91 (SAM9, CAP9, AT572D940HF) IDE support" + depends on ARM && ARCH_AT91 && !ARCH_AT91RM9200 && !ARCH_AT91X40 + select IDE_TIMINGS + config IDE_ARM tristate "ARM IDE support" depends on ARM && (ARCH_RPC || ARCH_SHARK) diff --git a/drivers/ide/Makefile b/drivers/ide/Makefile index d0e3d7d..1c326d9 100644 --- a/drivers/ide/Makefile +++ b/drivers/ide/Makefile @@ -116,3 +116,4 @@ obj-$(CONFIG_BLK_DEV_IDE_AU1XXX) += au1xxx-ide.o obj-$(CONFIG_BLK_DEV_IDE_TX4938) += tx4938ide.o obj-$(CONFIG_BLK_DEV_IDE_TX4939) += tx4939ide.o +obj-$(CONFIG_BLK_DEV_IDE_AT91) += at91_ide.o diff --git a/drivers/ide/at91_ide.c b/drivers/ide/at91_ide.c new file mode 100644 index 0000000..1bb50f4 --- /dev/null +++ b/drivers/ide/at91_ide.c @@ -0,0 +1,467 @@ +/* + * IDE host driver for AT91 (SAM9, CAP9, AT572D940HF) Static Memory Controller + * with Compact Flash True IDE logic + * + * Copyright (c) 2008, 2009 Kelvatek Ltd. + * + * 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 <linux/version.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/clk.h> +#include <linux/err.h> +#include <linux/ide.h> +#include <linux/platform_device.h> + +#include <mach/board.h> +#include <mach/gpio.h> +#include <mach/at91sam9263.h> +#include <mach/at91sam9_smc.h> +#include <mach/at91sam9263_matrix.h> + +#define DRV_NAME "at91_ide" + +#define perr(fmt, args...) pr_err(DRV_NAME ": " fmt, ##args) +#define pdbg(fmt, args...) pr_debug("%s " fmt, __func__, ##args) + +/* + * Access to IDE device is possible through EBI Static Memory Controller + * with Compact Flash logic. For details see EBI and SMC datasheet sections + * of any microcontroller from AT91SAM9 family. + * + * Within SMC chip select address space, lines A[23:21] distinguish Compact + * Flash modes (I/O, common memory, attribute memory, True IDE). IDE modes are: + * 0x00c0000 - True IDE + * 0x00e0000 - Alternate True IDE (Alt Status Register) + * + * On True IDE mode Task File and Data Register are mapped at the same address. + * To distinguish access between these two different bus data width is used: + * 8Bit for Task File, 16Bit for Data I/O. + * + * After initialization we do 8/16 bit flipping (changes in SMC MODE register) + * only inside IDE callback routines which are serialized by IDE layer, + * so no additional locking needed. + */ + +#define TASK_FILE 0x00c00000 +#define ALT_MODE 0x00e00000 +#define REGS_SIZE 8 + +#define enter_16bit(cs, mode) do { \ + mode = at91_sys_read(AT91_SMC_MODE(cs)); \ + at91_sys_write(AT91_SMC_MODE(cs), mode | AT91_SMC_DBW_16); \ +} while (0) + +#define leave_16bit(cs, mode) at91_sys_write(AT91_SMC_MODE(cs), mode); + +static void set_smc_timings(const u8 chipselect, const u16 cycle, + const u16 setup, const u16 pulse, + const u16 data_float, int use_iordy) +{ + unsigned long mode = AT91_SMC_READMODE | AT91_SMC_WRITEMODE | + AT91_SMC_BAT_SELECT; + + /* disable or enable waiting for IORDY signal */ + if (use_iordy) + mode |= AT91_SMC_EXNWMODE_READY; + + /* add data float cycles if needed */ + if (data_float) + mode |= AT91_SMC_TDF_(data_float); + + at91_sys_write(AT91_SMC_MODE(chipselect), mode); + + /* setup timings in SMC */ + at91_sys_write(AT91_SMC_SETUP(chipselect), AT91_SMC_NWESETUP_(setup) | + AT91_SMC_NCS_WRSETUP_(0) | + AT91_SMC_NRDSETUP_(setup) | + AT91_SMC_NCS_RDSETUP_(0)); + at91_sys_write(AT91_SMC_PULSE(chipselect), AT91_SMC_NWEPULSE_(pulse) | + AT91_SMC_NCS_WRPULSE_(cycle) | + AT91_SMC_NRDPULSE_(pulse) | + AT91_SMC_NCS_RDPULSE_(cycle)); + at91_sys_write(AT91_SMC_CYCLE(chipselect), AT91_SMC_NWECYCLE_(cycle) | + AT91_SMC_NRDCYCLE_(cycle)); +} + +static unsigned int calc_mck_cycles(unsigned int ns, unsigned int mck_hz) +{ + u64 tmp = ns; + + tmp *= mck_hz; + tmp += 1000*1000*1000 - 1; /* round up */ + do_div(tmp, 1000*1000*1000); + return (unsigned int) tmp; +} + +static void apply_timings(const u8 chipselect, const u8 pio, + const struct ide_timing *timing, int use_iordy) +{ + unsigned int t0, t1, t2, t6z; + unsigned int cycle, setup, pulse, data_float; + unsigned int mck_hz; + struct clk *mck; + + /* see table 22 of Compact Flash standard 4.1 for the meaning, + * we do not stretch active (t2) time, so setup (t1) + hold time (th) + * assure at least minimal recovery (t2i) time */ + t0 = timing->cyc8b; + t1 = timing->setup; + t2 = timing->act8b; + t6z = (pio < 5) ? 30 : 20; + + pdbg("t0=%u t1=%u t2=%u t6z=%u\n", t0, t1, t2, t6z); + + mck = clk_get(NULL, "mck"); + BUG_ON(IS_ERR(mck)); + mck_hz = clk_get_rate(mck); + pdbg("mck_hz=%u\n", mck_hz); + + cycle = calc_mck_cycles(t0, mck_hz); + setup = calc_mck_cycles(t1, mck_hz); + pulse = calc_mck_cycles(t2, mck_hz); + data_float = calc_mck_cycles(t6z, mck_hz); + + pdbg("cycle=%u setup=%u pulse=%u data_float=%u\n", + cycle, setup, pulse, data_float); + + set_smc_timings(chipselect, cycle, setup, pulse, data_float, use_iordy); +} + +static void at91_ide_input_data(ide_drive_t *drive, struct request *rq, + void *buf, unsigned int len) +{ + ide_hwif_t *hwif = drive->hwif; + struct ide_io_ports *io_ports = &hwif->io_ports; + u8 chipselect = hwif->select_data; + unsigned long mode; + + pdbg("cs %u buf %p len %d\n", chipselect, buf, len); + + len++; + + enter_16bit(chipselect, mode); + __ide_mm_insw((void __iomem *) io_ports->data_addr, buf, len / 2); + leave_16bit(chipselect, mode); +} + +static void at91_ide_output_data(ide_drive_t *drive, struct request *rq, + void *buf, unsigned int len) +{ + ide_hwif_t *hwif = drive->hwif; + struct ide_io_ports *io_ports = &hwif->io_ports; + u8 chipselect = hwif->select_data; + unsigned long mode; + + pdbg("cs %u buf %p len %d\n", chipselect, buf, len); + + enter_16bit(chipselect, mode); + __ide_mm_outsw((void __iomem *) io_ports->data_addr, buf, len / 2); + leave_16bit(chipselect, mode); +} + +static u8 ide_mm_inb(unsigned long port) +{ + return readb((void __iomem *) port); +} + +static void ide_mm_outb(u8 value, unsigned long port) +{ + writeb(value, (void __iomem *) port); +} + +static void at91_ide_tf_load(ide_drive_t *drive, ide_task_t *task) +{ + ide_hwif_t *hwif = drive->hwif; + struct ide_io_ports *io_ports = &hwif->io_ports; + struct ide_taskfile *tf = &task->tf; + u8 HIHI = (task->tf_flags & IDE_TFLAG_LBA48) ? 0xE0 : 0xEF; + + if (task->tf_flags & IDE_TFLAG_FLAGGED) + HIHI = 0xFF; + + if (task->tf_flags & IDE_TFLAG_OUT_DATA) { + u16 data = (tf->hob_data << 8) | tf->data; + + at91_ide_output_data(drive, NULL, &data, 2); + } + + if (task->tf_flags & IDE_TFLAG_OUT_HOB_FEATURE) + ide_mm_outb(tf->hob_feature, io_ports->feature_addr); + if (task->tf_flags & IDE_TFLAG_OUT_HOB_NSECT) + ide_mm_outb(tf->hob_nsect, io_ports->nsect_addr); + if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAL) + ide_mm_outb(tf->hob_lbal, io_ports->lbal_addr); + if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAM) + ide_mm_outb(tf->hob_lbam, io_ports->lbam_addr); + if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAH) + ide_mm_outb(tf->hob_lbah, io_ports->lbah_addr); + + if (task->tf_flags & IDE_TFLAG_OUT_FEATURE) + ide_mm_outb(tf->feature, io_ports->feature_addr); + if (task->tf_flags & IDE_TFLAG_OUT_NSECT) + ide_mm_outb(tf->nsect, io_ports->nsect_addr); + if (task->tf_flags & IDE_TFLAG_OUT_LBAL) + ide_mm_outb(tf->lbal, io_ports->lbal_addr); + if (task->tf_flags & IDE_TFLAG_OUT_LBAM) + ide_mm_outb(tf->lbam, io_ports->lbam_addr); + if (task->tf_flags & IDE_TFLAG_OUT_LBAH) + ide_mm_outb(tf->lbah, io_ports->lbah_addr); + + if (task->tf_flags & IDE_TFLAG_OUT_DEVICE) + ide_mm_outb((tf->device & HIHI) | drive->select, io_ports->device_addr); +} + +static void at91_ide_tf_read(ide_drive_t *drive, ide_task_t *task) +{ + ide_hwif_t *hwif = drive->hwif; + struct ide_io_ports *io_ports = &hwif->io_ports; + struct ide_taskfile *tf = &task->tf; + + if (task->tf_flags & IDE_TFLAG_IN_DATA) { + u16 data; + + at91_ide_input_data(drive, NULL, &data, 2); + tf->data = data & 0xff; + tf->hob_data = (data >> 8) & 0xff; + } + + /* be sure we're looking at the low order bits */ + ide_mm_outb(ATA_DEVCTL_OBS & ~0x80, io_ports->ctl_addr); + + if (task->tf_flags & IDE_TFLAG_IN_FEATURE) + tf->feature = ide_mm_inb(io_ports->feature_addr); + if (task->tf_flags & IDE_TFLAG_IN_NSECT) + tf->nsect = ide_mm_inb(io_ports->nsect_addr); + if (task->tf_flags & IDE_TFLAG_IN_LBAL) + tf->lbal = ide_mm_inb(io_ports->lbal_addr); + if (task->tf_flags & IDE_TFLAG_IN_LBAM) + tf->lbam = ide_mm_inb(io_ports->lbam_addr); + if (task->tf_flags & IDE_TFLAG_IN_LBAH) + tf->lbah = ide_mm_inb(io_ports->lbah_addr); + if (task->tf_flags & IDE_TFLAG_IN_DEVICE) + tf->device = ide_mm_inb(io_ports->device_addr); + + if (task->tf_flags & IDE_TFLAG_LBA48) { + ide_mm_outb(ATA_DEVCTL_OBS | 0x80, io_ports->ctl_addr); + + if (task->tf_flags & IDE_TFLAG_IN_HOB_FEATURE) + tf->hob_feature = ide_mm_inb(io_ports->feature_addr); + if (task->tf_flags & IDE_TFLAG_IN_HOB_NSECT) + tf->hob_nsect = ide_mm_inb(io_ports->nsect_addr); + if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAL) + tf->hob_lbal = ide_mm_inb(io_ports->lbal_addr); + if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAM) + tf->hob_lbam = ide_mm_inb(io_ports->lbam_addr); + if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAH) + tf->hob_lbah = ide_mm_inb(io_ports->lbah_addr); + } +} + +static void at91_ide_set_pio_mode(ide_drive_t *drive, const u8 pio) +{ + struct ide_timing *timing; + u8 chipselect = drive->hwif->select_data; + int use_iordy = 0; + + pdbg("chipselect %u pio %u\n", chipselect, pio); + + timing = ide_timing_find_mode(XFER_PIO_0 + pio); + BUG_ON(!timing); + + if ((pio > 2 || ata_id_has_iordy(drive->id)) && + !(ata_id_is_cfa(drive->id) && pio > 4)) + use_iordy = 1; + + apply_timings(chipselect, pio, timing, use_iordy); +} + +static const struct ide_tp_ops at91_ide_tp_ops = { + .exec_command = ide_exec_command, + .read_status = ide_read_status, + .read_altstatus = ide_read_altstatus, + .set_irq = ide_set_irq, + + .tf_load = at91_ide_tf_load, + .tf_read = at91_ide_tf_read, + + .input_data = at91_ide_input_data, + .output_data = at91_ide_output_data, +}; + +static const struct ide_port_ops at91_ide_port_ops = { + .set_pio_mode = at91_ide_set_pio_mode, +}; + +static const struct ide_port_info at91_ide_port_info __initdata = { + .port_ops = &at91_ide_port_ops, + .tp_ops = &at91_ide_tp_ops, + .host_flags = IDE_HFLAG_MMIO | IDE_HFLAG_NO_DMA | IDE_HFLAG_SINGLE | + IDE_HFLAG_NO_IO_32BIT | IDE_HFLAG_UNMASK_IRQS, + .pio_mask = ATA_PIO5, +}; + +/* + * If interrupt is delivered through GPIO, IRQ are triggered on falling + * and rising edge of signal. Whereas IDE device request interrupt on high + * level (rising edge in our case). This mean we have fake interrupts, so + * we need to check interrupt pin and exit instantly from ISR when line + * is on low level. + */ + +irqreturn_t at91_irq_handler(int irq, void *dev_id) +{ + int ntries = 8; + int pin_val1, pin_val2; + + /* additional deglitch, line can be noisy in badly designed PCB */ + do { + pin_val1 = at91_get_gpio_value(irq); + pin_val2 = at91_get_gpio_value(irq); + } while (pin_val1 != pin_val2 && --ntries > 0); + + if (pin_val1 == 0 || ntries <= 0) + return IRQ_HANDLED; + + return ide_intr(irq, dev_id); +} + +static int __init at91_ide_probe(struct platform_device *pdev) +{ + int ret; + hw_regs_t hw; + hw_regs_t *hws[] = { &hw, NULL, NULL, NULL }; + struct ide_host *host; + struct resource *res; + unsigned long tf_base = 0, ctl_base = 0; + struct at91_cf_data *board = pdev->dev.platform_data; + + if (!board) + return -ENODEV; + + if (board->det_pin && at91_get_gpio_value(board->det_pin) != 0) { + perr("no device detected\n"); + return -ENODEV; + } + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + perr("can't get memory resource\n"); + return -ENODEV; + } + + if (!devm_request_mem_region(&pdev->dev, res->start + TASK_FILE, + REGS_SIZE, "ide") || + !devm_request_mem_region(&pdev->dev, res->start + ALT_MODE, + REGS_SIZE, "alt")) { + perr("memory resources in use\n"); + return -EBUSY; + } + + pdbg("chipselect %u irq %u res %08lx\n", board->chipselect, + board->irq_pin, (unsigned long) res->start); + + tf_base = (unsigned long) devm_ioremap(&pdev->dev, res->start + TASK_FILE, + REGS_SIZE); + ctl_base = (unsigned long) devm_ioremap(&pdev->dev, res->start + ALT_MODE, + REGS_SIZE); + if (!tf_base || !ctl_base) { + perr("can't map memory regions\n"); + return -EBUSY; + } + + memset(&hw, 0, sizeof(hw)); + + if (board->flags & AT91_IDE_SWAP_A0_A2) { + /* workaround for stupid hardware bug */ + hw.io_ports.data_addr = tf_base + 0; + hw.io_ports.error_addr = tf_base + 4; + hw.io_ports.nsect_addr = tf_base + 2; + hw.io_ports.lbal_addr = tf_base + 6; + hw.io_ports.lbam_addr = tf_base + 1; + hw.io_ports.lbah_addr = tf_base + 5; + hw.io_ports.device_addr = tf_base + 3; + hw.io_ports.command_addr = tf_base + 7; + hw.io_ports.ctl_addr = ctl_base + 3; + } else + ide_std_init_ports(&hw, tf_base, ctl_base + 6); + + hw.irq = board->irq_pin; + hw.chipset = ide_generic; + hw.dev = &pdev->dev; + + host = ide_host_alloc(&at91_ide_port_info, hws); + if (!host) { + perr("failed to allocate ide host\n"); + return -ENOMEM; + } + + /* setup Static Memory Controller - PIO 0 as default */ + apply_timings(board->chipselect, 0, ide_timing_find_mode(XFER_PIO_0), 0); + + /* with GPIO interrupt we have to do quirks in handler */ + if (board->irq_pin >= PIN_BASE) + host->irq_handler = at91_irq_handler; + + host->ports[0]->select_data = board->chipselect; + + ret = ide_host_register(host, &at91_ide_port_info, hws); + if (ret) { + perr("failed to register ide host\n"); + goto err_free_host; + } + platform_set_drvdata(pdev, host); + return 0; + +err_free_host: + ide_host_free(host); + return ret; +} + +static int __exit at91_ide_remove(struct platform_device *pdev) +{ + struct ide_host *host = platform_get_drvdata(pdev); + + ide_host_remove(host); + return 0; +} + +static struct platform_driver at91_ide_driver = { + .driver = { + .name = DRV_NAME, + .owner = THIS_MODULE, + }, + .remove = __exit_p(at91_ide_remove), +}; + +static int __init at91_ide_init(void) +{ + return platform_driver_probe(&at91_ide_driver, at91_ide_probe); +} + +static void __exit at91_ide_exit(void) +{ + platform_driver_unregister(&at91_ide_driver); +} + +module_init(at91_ide_init); +module_exit(at91_ide_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Stanislaw Gruszka <stf_xl@wp.pl>"); + diff --git a/drivers/ide/ide-disk_proc.c b/drivers/ide/ide-disk_proc.c index 1146f42..1f86dcb 100644 --- a/drivers/ide/ide-disk_proc.c +++ b/drivers/ide/ide-disk_proc.c @@ -125,5 +125,5 @@ const struct ide_proc_devset ide_disk_settings[] = { IDE_PROC_DEVSET(multcount, 0, 16), IDE_PROC_DEVSET(nowerr, 0, 1), IDE_PROC_DEVSET(wcache, 0, 1), - { 0 }, + { NULL }, }; diff --git a/drivers/ide/ide-floppy_proc.c b/drivers/ide/ide-floppy_proc.c index 3ec762c..fcd4d81 100644 --- a/drivers/ide/ide-floppy_proc.c +++ b/drivers/ide/ide-floppy_proc.c @@ -29,5 +29,5 @@ const struct ide_proc_devset ide_floppy_settings[] = { IDE_PROC_DEVSET(bios_head, 0, 255), IDE_PROC_DEVSET(bios_sect, 0, 63), IDE_PROC_DEVSET(ticks, 0, 255), - { 0 }, + { NULL }, }; diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 9ee51ad..a9a6c20 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -908,7 +908,7 @@ void ide_timer_expiry (unsigned long data) ide_drive_t *uninitialized_var(drive); ide_handler_t *handler; unsigned long flags; - unsigned long wait = -1; + int wait = -1; int plug_device = 0; spin_lock_irqsave(&hwif->lock, flags); @@ -1162,6 +1162,7 @@ out_early: return irq_ret; } +EXPORT_SYMBOL_GPL(ide_intr); /** * ide_do_drive_cmd - issue IDE special command diff --git a/drivers/ide/ide-iops.c b/drivers/ide/ide-iops.c index 753b92e..b1892bd 100644 --- a/drivers/ide/ide-iops.c +++ b/drivers/ide/ide-iops.c @@ -315,6 +315,8 @@ void ide_output_data(ide_drive_t *drive, struct request *rq, void *buf, u8 io_32bit = drive->io_32bit; u8 mmio = (hwif->host_flags & IDE_HFLAG_MMIO) ? 1 : 0; + len++; + if (io_32bit) { unsigned long uninitialized_var(flags); diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index ce0818a..ee8e3e7 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -950,6 +950,7 @@ static int ide_port_setup_devices(ide_hwif_t *hwif) static int init_irq (ide_hwif_t *hwif) { struct ide_io_ports *io_ports = &hwif->io_ports; + irq_handler_t irq_handler; int sa = 0; mutex_lock(&ide_cfg_mtx); @@ -959,6 +960,10 @@ static int init_irq (ide_hwif_t *hwif) hwif->timer.function = &ide_timer_expiry; hwif->timer.data = (unsigned long)hwif; + irq_handler = hwif->host->irq_handler; + if (irq_handler == NULL) + irq_handler = ide_intr; + #if defined(__mc68000__) sa = IRQF_SHARED; #endif /* __mc68000__ */ @@ -969,7 +974,7 @@ static int init_irq (ide_hwif_t *hwif) if (io_ports->ctl_addr) hwif->tp_ops->set_irq(hwif, 1); - if (request_irq(hwif->irq, &ide_intr, sa, hwif->name, hwif)) + if (request_irq(hwif->irq, irq_handler, sa, hwif->name, hwif)) goto out_up; if (!hwif->rqsize) { diff --git a/drivers/ide/ide-proc.c b/drivers/ide/ide-proc.c index 1d8978b..a7b9287 100644 --- a/drivers/ide/ide-proc.c +++ b/drivers/ide/ide-proc.c @@ -231,7 +231,7 @@ static const struct ide_proc_devset ide_generic_settings[] = { IDE_PROC_DEVSET(pio_mode, 0, 255), IDE_PROC_DEVSET(unmaskirq, 0, 1), IDE_PROC_DEVSET(using_dma, 0, 1), - { 0 }, + { NULL }, }; static void proc_ide_settings_warn(void) diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index bb450a7..4e6181c 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -2166,7 +2166,7 @@ static const struct ide_proc_devset idetape_settings[] = { __IDE_PROC_DEVSET(speed, 0, 0xffff, NULL, NULL), __IDE_PROC_DEVSET(tdsc, IDETAPE_DSC_RW_MIN, IDETAPE_DSC_RW_MAX, mulf_tdsc, divf_tdsc), - { 0 }, + { NULL }, }; #endif diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c index b4d44e5..8132533 100644 --- a/drivers/lguest/lguest_device.c +++ b/drivers/lguest/lguest_device.c @@ -212,6 +212,9 @@ static void lg_notify(struct virtqueue *vq) hcall(LHCALL_NOTIFY, lvq->config.pfn << PAGE_SHIFT, 0, 0); } +/* An extern declaration inside a C file is bad form. Don't do it. */ +extern void lguest_setup_irq(unsigned int irq); + /* This routine finds the first virtqueue described in the configuration of * this device and sets it up. * @@ -266,6 +269,9 @@ static struct virtqueue *lg_find_vq(struct virtio_device *vdev, goto unmap; } + /* Make sure the interrupt is allocated. */ + lguest_setup_irq(lvq->config.irq); + /* Tell the interrupt for this virtqueue to go to the virtio_ring * interrupt handler. */ /* FIXME: We used to have a flag for the Host to tell us we could use diff --git a/drivers/md/md.c b/drivers/md/md.c index 03b4cd0..a307f87 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -214,12 +214,7 @@ static inline mddev_t *mddev_get(mddev_t *mddev) return mddev; } -static void mddev_delayed_delete(struct work_struct *ws) -{ - mddev_t *mddev = container_of(ws, mddev_t, del_work); - kobject_del(&mddev->kobj); - kobject_put(&mddev->kobj); -} +static void mddev_delayed_delete(struct work_struct *ws); static void mddev_put(mddev_t *mddev) { @@ -3542,6 +3537,21 @@ static struct kobj_type md_ktype = { int mdp_major = 0; +static void mddev_delayed_delete(struct work_struct *ws) +{ + mddev_t *mddev = container_of(ws, mddev_t, del_work); + + if (mddev->private == &md_redundancy_group) { + sysfs_remove_group(&mddev->kobj, &md_redundancy_group); + if (mddev->sysfs_action) + sysfs_put(mddev->sysfs_action); + mddev->sysfs_action = NULL; + mddev->private = NULL; + } + kobject_del(&mddev->kobj); + kobject_put(&mddev->kobj); +} + static int md_alloc(dev_t dev, char *name) { static DEFINE_MUTEX(disks_mutex); @@ -4033,13 +4043,9 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) mddev->queue->merge_bvec_fn = NULL; mddev->queue->unplug_fn = NULL; mddev->queue->backing_dev_info.congested_fn = NULL; - if (mddev->pers->sync_request) { - sysfs_remove_group(&mddev->kobj, &md_redundancy_group); - if (mddev->sysfs_action) - sysfs_put(mddev->sysfs_action); - mddev->sysfs_action = NULL; - } module_put(mddev->pers->owner); + if (mddev->pers->sync_request) + mddev->private = &md_redundancy_group; mddev->pers = NULL; /* tell userspace to handle 'inactive' */ sysfs_notify_dirent(mddev->sysfs_state); diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c index 9c50e6f..34ce270 100644 --- a/drivers/mmc/core/mmc_ops.c +++ b/drivers/mmc/core/mmc_ops.c @@ -248,12 +248,15 @@ mmc_send_cxd_data(struct mmc_card *card, struct mmc_host *host, sg_init_one(&sg, data_buf, len); - /* - * The spec states that CSR and CID accesses have a timeout - * of 64 clock cycles. - */ - data.timeout_ns = 0; - data.timeout_clks = 64; + if (opcode == MMC_SEND_CSD || opcode == MMC_SEND_CID) { + /* + * The spec states that CSR and CID accesses have a timeout + * of 64 clock cycles. + */ + data.timeout_ns = 0; + data.timeout_clks = 64; + } else + mmc_set_data_timeout(&data, card); mmc_wait_for_req(host, &mrq); diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c index d44f741..6d9f810 100644 --- a/drivers/mtd/devices/mtd_dataflash.c +++ b/drivers/mtd/devices/mtd_dataflash.c @@ -821,7 +821,8 @@ static struct flash_info *__devinit jedec_probe(struct spi_device *spi) if (!(info->flags & IS_POW2PS)) return info; } - } + } else + return info; } } diff --git a/drivers/mtd/maps/physmap.c b/drivers/mtd/maps/physmap.c index 4b122e7..2297182 100644 --- a/drivers/mtd/maps/physmap.c +++ b/drivers/mtd/maps/physmap.c @@ -46,16 +46,19 @@ static int physmap_flash_remove(struct platform_device *dev) physmap_data = dev->dev.platform_data; + if (info->cmtd) { #ifdef CONFIG_MTD_PARTITIONS - if (info->nr_parts) { - del_mtd_partitions(info->cmtd); - kfree(info->parts); - } else if (physmap_data->nr_parts) - del_mtd_partitions(info->cmtd); - else - del_mtd_device(info->cmtd); + if (info->nr_parts || physmap_data->nr_parts) + del_mtd_partitions(info->cmtd); + else + del_mtd_device(info->cmtd); #else - del_mtd_device(info->cmtd); + del_mtd_device(info->cmtd); +#endif + } +#ifdef CONFIG_MTD_PARTITIONS + if (info->nr_parts) + kfree(info->parts); #endif #ifdef CONFIG_MTD_CONCAT diff --git a/drivers/mtd/nand/orion_nand.c b/drivers/mtd/nand/orion_nand.c index 917cf8d..c2dfd3e 100644 --- a/drivers/mtd/nand/orion_nand.c +++ b/drivers/mtd/nand/orion_nand.c @@ -149,7 +149,7 @@ static int __devexit orion_nand_remove(struct platform_device *pdev) static struct platform_driver orion_nand_driver = { .probe = orion_nand_probe, - .remove = orion_nand_remove, + .remove = __devexit_p(orion_nand_remove), .driver = { .name = "orion_nand", .owner = THIS_MODULE, diff --git a/drivers/net/arm/Makefile b/drivers/net/arm/Makefile index c69c0cd..811a3cc 100644 --- a/drivers/net/arm/Makefile +++ b/drivers/net/arm/Makefile @@ -4,7 +4,7 @@ # obj-$(CONFIG_ARM_AM79C961A) += am79c961a.o -obj-$(CONFIG_ARM_ETHERH) += etherh.o ../8390.o +obj-$(CONFIG_ARM_ETHERH) += etherh.o obj-$(CONFIG_ARM_ETHER3) += ether3.o obj-$(CONFIG_ARM_ETHER1) += ether1.o obj-$(CONFIG_ARM_AT91_ETHER) += at91_ether.o diff --git a/drivers/net/arm/etherh.c b/drivers/net/arm/etherh.c index 54b52e5..f52f668 100644 --- a/drivers/net/arm/etherh.c +++ b/drivers/net/arm/etherh.c @@ -641,15 +641,15 @@ static const struct net_device_ops etherh_netdev_ops = { .ndo_open = etherh_open, .ndo_stop = etherh_close, .ndo_set_config = etherh_set_config, - .ndo_start_xmit = ei_start_xmit, - .ndo_tx_timeout = ei_tx_timeout, - .ndo_get_stats = ei_get_stats, - .ndo_set_multicast_list = ei_set_multicast_list, + .ndo_start_xmit = __ei_start_xmit, + .ndo_tx_timeout = __ei_tx_timeout, + .ndo_get_stats = __ei_get_stats, + .ndo_set_multicast_list = __ei_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ei_poll, + .ndo_poll_controller = __ei_poll, #endif }; diff --git a/drivers/net/arm/ks8695net.c b/drivers/net/arm/ks8695net.c index 1cf2f94..f3a1274 100644 --- a/drivers/net/arm/ks8695net.c +++ b/drivers/net/arm/ks8695net.c @@ -560,7 +560,7 @@ ks8695_reset(struct ks8695_priv *ksp) msleep(1); } - if (reset_timeout == 0) { + if (reset_timeout < 0) { dev_crit(ksp->dev, "Timeout waiting for DMA engines to reset\n"); /* And blithely carry on */ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 9fb3883..e0578fe 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4113,7 +4113,7 @@ static int bond_neigh_setup(struct net_device *dev, struct neigh_parms *parms) const struct net_device_ops *slave_ops = slave->dev->netdev_ops; if (slave_ops->ndo_neigh_setup) - return slave_ops->ndo_neigh_setup(dev, parms); + return slave_ops->ndo_neigh_setup(slave->dev, parms); } return 0; } diff --git a/drivers/net/jme.c b/drivers/net/jme.c index 08b3405..a6e1a35 100644 --- a/drivers/net/jme.c +++ b/drivers/net/jme.c @@ -957,13 +957,14 @@ jme_process_receive(struct jme_adapter *jme, int limit) goto out_inc; i = atomic_read(&rxring->next_to_clean); - while (limit-- > 0) { + while (limit > 0) { rxdesc = rxring->desc; rxdesc += i; if ((rxdesc->descwb.flags & cpu_to_le16(RXWBFLAG_OWN)) || !(rxdesc->descwb.desccnt & RXWBDCNT_WBCPL)) goto out; + --limit; desccnt = rxdesc->descwb.desccnt & RXWBDCNT_DCNT; diff --git a/drivers/net/pcmcia/3c574_cs.c b/drivers/net/pcmcia/3c574_cs.c index e5cb6b1..2404a83 100644 --- a/drivers/net/pcmcia/3c574_cs.c +++ b/drivers/net/pcmcia/3c574_cs.c @@ -1035,7 +1035,8 @@ static int el3_rx(struct net_device *dev, int worklimit) DEBUG(3, "%s: in rx_packet(), status %4.4x, rx_status %4.4x.\n", dev->name, inw(ioaddr+EL3_STATUS), inw(ioaddr+RxStatus)); while (!((rx_status = inw(ioaddr + RxStatus)) & 0x8000) && - (--worklimit >= 0)) { + worklimit > 0) { + worklimit--; if (rx_status & 0x4000) { /* Error, update stats. */ short error = rx_status & 0x3800; dev->stats.rx_errors++; diff --git a/drivers/net/pcmcia/3c589_cs.c b/drivers/net/pcmcia/3c589_cs.c index 73ecc65..1e01b8a 100644 --- a/drivers/net/pcmcia/3c589_cs.c +++ b/drivers/net/pcmcia/3c589_cs.c @@ -857,7 +857,8 @@ static int el3_rx(struct net_device *dev) DEBUG(3, "%s: in rx_packet(), status %4.4x, rx_status %4.4x.\n", dev->name, inw(ioaddr+EL3_STATUS), inw(ioaddr+RX_STATUS)); while (!((rx_status = inw(ioaddr + RX_STATUS)) & 0x8000) && - (--worklimit >= 0)) { + worklimit > 0) { + worklimit--; if (rx_status & 0x4000) { /* Error, update stats. */ short error = rx_status & 0x3800; dev->stats.rx_errors++; diff --git a/drivers/net/smc911x.h b/drivers/net/smc911x.h index 870b4c3..a45952e 100644 --- a/drivers/net/smc911x.h +++ b/drivers/net/smc911x.h @@ -42,6 +42,16 @@ #define SMC_USE_16BIT 0 #define SMC_USE_32BIT 1 #define SMC_IRQ_SENSE IRQF_TRIGGER_LOW +#elif defined(CONFIG_ARCH_OMAP34XX) + #define SMC_USE_16BIT 0 + #define SMC_USE_32BIT 1 + #define SMC_IRQ_SENSE IRQF_TRIGGER_LOW + #define SMC_MEM_RESERVED 1 +#elif defined(CONFIG_ARCH_OMAP24XX) + #define SMC_USE_16BIT 0 + #define SMC_USE_32BIT 1 + #define SMC_IRQ_SENSE IRQF_TRIGGER_LOW + #define SMC_MEM_RESERVED 1 #else /* * Default configuration @@ -675,6 +685,7 @@ smc_pxa_dma_outsl(struct smc911x_local *lp, u_long physaddr, #define CHIP_9116 0x0116 #define CHIP_9117 0x0117 #define CHIP_9118 0x0118 +#define CHIP_9211 0x9211 #define CHIP_9215 0x115A #define CHIP_9217 0x117A #define CHIP_9218 0x118A @@ -689,6 +700,7 @@ static const struct chip_id chip_ids[] = { { CHIP_9116, "LAN9116" }, { CHIP_9117, "LAN9117" }, { CHIP_9118, "LAN9118" }, + { CHIP_9211, "LAN9211" }, { CHIP_9215, "LAN9215" }, { CHIP_9217, "LAN9217" }, { CHIP_9218, "LAN9218" }, diff --git a/drivers/net/sungem.c b/drivers/net/sungem.c index 8d64b1d..0fcb750 100644 --- a/drivers/net/sungem.c +++ b/drivers/net/sungem.c @@ -1229,7 +1229,7 @@ static void gem_reset(struct gem *gp) break; } while (val & (GREG_SWRST_TXRST | GREG_SWRST_RXRST)); - if (limit <= 0) + if (limit < 0) printk(KERN_ERR "%s: SW reset is ghetto.\n", gp->dev->name); if (gp->phy_type == phy_serialink || gp->phy_type == phy_serdes) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index b080f94..dabdf59 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -1473,7 +1473,8 @@ static void tg3_phy_toggle_apd(struct tg3 *tp, bool enable) { u32 reg; - if (!(tp->tg3_flags2 & TG3_FLG2_5705_PLUS)) + if (!(tp->tg3_flags2 & TG3_FLG2_5705_PLUS) || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) return; reg = MII_TG3_MISC_SHDW_WREN | diff --git a/drivers/net/tokenring/tmspci.c b/drivers/net/tokenring/tmspci.c index 5f60177..e2150b3 100644 --- a/drivers/net/tokenring/tmspci.c +++ b/drivers/net/tokenring/tmspci.c @@ -121,11 +121,6 @@ static int __devinit tms_pci_attach(struct pci_dev *pdev, const struct pci_devic goto err_out_trdev; } - ret = request_irq(pdev->irq, tms380tr_interrupt, IRQF_SHARED, - dev->name, dev); - if (ret) - goto err_out_region; - dev->base_addr = pci_ioaddr; dev->irq = pci_irq_line; dev->dma = 0; @@ -142,7 +137,7 @@ static int __devinit tms_pci_attach(struct pci_dev *pdev, const struct pci_devic ret = tmsdev_init(dev, &pdev->dev); if (ret) { printk("%s: unable to get memory for dev->priv.\n", dev->name); - goto err_out_irq; + goto err_out_region; } tp = netdev_priv(dev); @@ -157,6 +152,11 @@ static int __devinit tms_pci_attach(struct pci_dev *pdev, const struct pci_devic tp->tmspriv = cardinfo; + ret = request_irq(pdev->irq, tms380tr_interrupt, IRQF_SHARED, + dev->name, dev); + if (ret) + goto err_out_tmsdev; + dev->open = tms380tr_open; dev->stop = tms380tr_close; pci_set_drvdata(pdev, dev); @@ -164,15 +164,15 @@ static int __devinit tms_pci_attach(struct pci_dev *pdev, const struct pci_devic ret = register_netdev(dev); if (ret) - goto err_out_tmsdev; + goto err_out_irq; return 0; +err_out_irq: + free_irq(pdev->irq, dev); err_out_tmsdev: pci_set_drvdata(pdev, NULL); tmsdev_term(dev); -err_out_irq: - free_irq(pdev->irq, dev); err_out_region: release_region(pci_ioaddr, TMS_PCI_IO_EXTENT); err_out_trdev: diff --git a/drivers/net/ucc_geth_mii.c b/drivers/net/ucc_geth_mii.c index 5463591..0ada4ed 100644 --- a/drivers/net/ucc_geth_mii.c +++ b/drivers/net/ucc_geth_mii.c @@ -107,7 +107,7 @@ int uec_mdio_read(struct mii_bus *bus, int mii_id, int regnum) static int uec_mdio_reset(struct mii_bus *bus) { struct ucc_mii_mng __iomem *regs = (void __iomem *)bus->priv; - unsigned int timeout = PHY_INIT_TIMEOUT; + int timeout = PHY_INIT_TIMEOUT; mutex_lock(&bus->mdio_lock); @@ -123,7 +123,7 @@ static int uec_mdio_reset(struct mii_bus *bus) mutex_unlock(&bus->mdio_lock); - if (timeout <= 0) { + if (timeout < 0) { printk(KERN_ERR "%s: The MII Bus is stuck!\n", bus->name); return -EBUSY; } diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 5b67bbf..81682c6 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -635,6 +635,10 @@ static const struct usb_device_id products[] = { USB_DEVICE(0x0a47, 0x9601), /* Hirose USB-100 */ .driver_info = (unsigned long)&dm9601_info, }, + { + USB_DEVICE(0x0fe6, 0x8101), /* DM9601 USB to Fast Ethernet Adapter */ + .driver_info = (unsigned long)&dm9601_info, + }, {}, // END }; diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c index 36bafeb..129e2d3 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn.c @@ -3868,7 +3868,7 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } err = iwl_eeprom_check_version(priv); if (err) - goto out_iounmap; + goto out_free_eeprom; /* extract MAC Address */ iwl_eeprom_get_mac(priv, priv->mac_addr); @@ -3945,6 +3945,8 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; out_remove_sysfs: + destroy_workqueue(priv->workqueue); + priv->workqueue = NULL; sysfs_remove_group(&pdev->dev.kobj, &iwl_attribute_group); out_uninit_drv: iwl_uninit_drv(priv); @@ -3953,8 +3955,8 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) out_iounmap: pci_iounmap(pdev, priv->hw_base); out_pci_release_regions: - pci_release_regions(pdev); pci_set_drvdata(pdev, NULL); + pci_release_regions(pdev); out_pci_disable_device: pci_disable_device(pdev); out_ieee80211_free_hw: diff --git a/drivers/net/wireless/iwlwifi/iwl3945-base.c b/drivers/net/wireless/iwlwifi/iwl3945-base.c index 93be74a..57dd34e 100644 --- a/drivers/net/wireless/iwlwifi/iwl3945-base.c +++ b/drivers/net/wireless/iwlwifi/iwl3945-base.c @@ -7911,7 +7911,7 @@ static int iwl3945_pci_probe(struct pci_dev *pdev, const struct pci_device_id *e CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY, 25000); if (err < 0) { IWL_DEBUG_INFO("Failed to init the card\n"); - goto out_remove_sysfs; + goto out_iounmap; } /*********************** @@ -7921,7 +7921,7 @@ static int iwl3945_pci_probe(struct pci_dev *pdev, const struct pci_device_id *e err = iwl3945_eeprom_init(priv); if (err) { IWL_ERROR("Unable to init EEPROM\n"); - goto out_remove_sysfs; + goto out_iounmap; } /* MAC Address location in EEPROM same for 3945/4965 */ get_eeprom_mac(priv, priv->mac_addr); @@ -7975,7 +7975,7 @@ static int iwl3945_pci_probe(struct pci_dev *pdev, const struct pci_device_id *e err = iwl3945_init_channel_map(priv); if (err) { IWL_ERROR("initializing regulatory failed: %d\n", err); - goto out_release_irq; + goto out_unset_hw_setting; } err = iwl3945_init_geos(priv); @@ -8045,25 +8045,22 @@ static int iwl3945_pci_probe(struct pci_dev *pdev, const struct pci_device_id *e return 0; out_remove_sysfs: + destroy_workqueue(priv->workqueue); + priv->workqueue = NULL; sysfs_remove_group(&pdev->dev.kobj, &iwl3945_attribute_group); out_free_geos: iwl3945_free_geos(priv); out_free_channel_map: iwl3945_free_channel_map(priv); - - - out_release_irq: - destroy_workqueue(priv->workqueue); - priv->workqueue = NULL; + out_unset_hw_setting: iwl3945_unset_hw_setting(priv); - out_iounmap: pci_iounmap(pdev, priv->hw_base); out_pci_release_regions: pci_release_regions(pdev); out_pci_disable_device: - pci_disable_device(pdev); pci_set_drvdata(pdev, NULL); + pci_disable_device(pdev); out_ieee80211_free_hw: ieee80211_free_hw(priv->hw); out: diff --git a/drivers/net/wireless/p54/p54common.c b/drivers/net/wireless/p54/p54common.c index 34561e6..f170106 100644 --- a/drivers/net/wireless/p54/p54common.c +++ b/drivers/net/wireless/p54/p54common.c @@ -710,10 +710,11 @@ static struct sk_buff *p54_find_tx_entry(struct ieee80211_hw *dev, __le32 req_id) { struct p54_common *priv = dev->priv; - struct sk_buff *entry = priv->tx_queue.next; + struct sk_buff *entry; unsigned long flags; spin_lock_irqsave(&priv->tx_queue.lock, flags); + entry = priv->tx_queue.next; while (entry != (struct sk_buff *)&priv->tx_queue) { struct p54_hdr *hdr = (struct p54_hdr *) entry->data; @@ -732,7 +733,7 @@ static void p54_rx_frame_sent(struct ieee80211_hw *dev, struct sk_buff *skb) struct p54_common *priv = dev->priv; struct p54_hdr *hdr = (struct p54_hdr *) skb->data; struct p54_frame_sent *payload = (struct p54_frame_sent *) hdr->data; - struct sk_buff *entry = (struct sk_buff *) priv->tx_queue.next; + struct sk_buff *entry; u32 addr = le32_to_cpu(hdr->req_id) - priv->headroom; struct memrecord *range = NULL; u32 freed = 0; @@ -741,6 +742,7 @@ static void p54_rx_frame_sent(struct ieee80211_hw *dev, struct sk_buff *skb) int count, idx; spin_lock_irqsave(&priv->tx_queue.lock, flags); + entry = (struct sk_buff *) priv->tx_queue.next; while (entry != (struct sk_buff *)&priv->tx_queue) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(entry); struct p54_hdr *entry_hdr; @@ -976,7 +978,7 @@ static int p54_assign_address(struct ieee80211_hw *dev, struct sk_buff *skb, struct p54_hdr *data, u32 len) { struct p54_common *priv = dev->priv; - struct sk_buff *entry = priv->tx_queue.next; + struct sk_buff *entry; struct sk_buff *target_skb = NULL; struct ieee80211_tx_info *info; struct memrecord *range; @@ -1014,6 +1016,7 @@ static int p54_assign_address(struct ieee80211_hw *dev, struct sk_buff *skb, } } + entry = priv->tx_queue.next; while (left--) { u32 hole_size; info = IEEE80211_SKB_CB(entry); diff --git a/drivers/net/wireless/rt2x00/rt2500usb.c b/drivers/net/wireless/rt2x00/rt2500usb.c index af6b584..3e2ac2b 100644 --- a/drivers/net/wireless/rt2x00/rt2500usb.c +++ b/drivers/net/wireless/rt2x00/rt2500usb.c @@ -1952,6 +1952,8 @@ static struct usb_device_id rt2500usb_device_table[] = { { USB_DEVICE(0x13b1, 0x000d), USB_DEVICE_DATA(&rt2500usb_ops) }, { USB_DEVICE(0x13b1, 0x0011), USB_DEVICE_DATA(&rt2500usb_ops) }, { USB_DEVICE(0x13b1, 0x001a), USB_DEVICE_DATA(&rt2500usb_ops) }, + /* CNet */ + { USB_DEVICE(0x1371, 0x9022), USB_DEVICE_DATA(&rt2500usb_ops) }, /* Conceptronic */ { USB_DEVICE(0x14b2, 0x3c02), USB_DEVICE_DATA(&rt2500usb_ops) }, /* D-LINK */ @@ -1976,14 +1978,20 @@ static struct usb_device_id rt2500usb_device_table[] = { { USB_DEVICE(0x148f, 0x2570), USB_DEVICE_DATA(&rt2500usb_ops) }, { USB_DEVICE(0x148f, 0x2573), USB_DEVICE_DATA(&rt2500usb_ops) }, { USB_DEVICE(0x148f, 0x9020), USB_DEVICE_DATA(&rt2500usb_ops) }, + /* Sagem */ + { USB_DEVICE(0x079b, 0x004b), USB_DEVICE_DATA(&rt2500usb_ops) }, /* Siemens */ { USB_DEVICE(0x0681, 0x3c06), USB_DEVICE_DATA(&rt2500usb_ops) }, /* SMC */ { USB_DEVICE(0x0707, 0xee13), USB_DEVICE_DATA(&rt2500usb_ops) }, /* Spairon */ { USB_DEVICE(0x114b, 0x0110), USB_DEVICE_DATA(&rt2500usb_ops) }, + /* SURECOM */ + { USB_DEVICE(0x0769, 0x11f3), USB_DEVICE_DATA(&rt2500usb_ops) }, /* Trust */ { USB_DEVICE(0x0eb0, 0x9020), USB_DEVICE_DATA(&rt2500usb_ops) }, + /* VTech */ + { USB_DEVICE(0x0f88, 0x3012), USB_DEVICE_DATA(&rt2500usb_ops) }, /* Zinwell */ { USB_DEVICE(0x5a57, 0x0260), USB_DEVICE_DATA(&rt2500usb_ops) }, { 0, } diff --git a/drivers/net/wireless/rt2x00/rt73usb.c b/drivers/net/wireless/rt2x00/rt73usb.c index 96a8d69..cefee1b 100644 --- a/drivers/net/wireless/rt2x00/rt73usb.c +++ b/drivers/net/wireless/rt2x00/rt73usb.c @@ -2281,7 +2281,18 @@ static const struct rt2x00_ops rt73usb_ops = { */ static struct usb_device_id rt73usb_device_table[] = { /* AboCom */ + { USB_DEVICE(0x07b8, 0xb21b), USB_DEVICE_DATA(&rt73usb_ops) }, + { USB_DEVICE(0x07b8, 0xb21c), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x07b8, 0xb21d), USB_DEVICE_DATA(&rt73usb_ops) }, + { USB_DEVICE(0x07b8, 0xb21e), USB_DEVICE_DATA(&rt73usb_ops) }, + { USB_DEVICE(0x07b8, 0xb21f), USB_DEVICE_DATA(&rt73usb_ops) }, + /* AL */ + { USB_DEVICE(0x14b2, 0x3c10), USB_DEVICE_DATA(&rt73usb_ops) }, + /* Amigo */ + { USB_DEVICE(0x148f, 0x9021), USB_DEVICE_DATA(&rt73usb_ops) }, + { USB_DEVICE(0x0eb0, 0x9021), USB_DEVICE_DATA(&rt73usb_ops) }, + /* AMIT */ + { USB_DEVICE(0x18c5, 0x0002), USB_DEVICE_DATA(&rt73usb_ops) }, /* Askey */ { USB_DEVICE(0x1690, 0x0722), USB_DEVICE_DATA(&rt73usb_ops) }, /* ASUS */ @@ -2294,7 +2305,9 @@ static struct usb_device_id rt73usb_device_table[] = { { USB_DEVICE(0x050d, 0x905c), USB_DEVICE_DATA(&rt73usb_ops) }, /* Billionton */ { USB_DEVICE(0x1631, 0xc019), USB_DEVICE_DATA(&rt73usb_ops) }, + { USB_DEVICE(0x08dd, 0x0120), USB_DEVICE_DATA(&rt73usb_ops) }, /* Buffalo */ + { USB_DEVICE(0x0411, 0x00d8), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x0411, 0x00f4), USB_DEVICE_DATA(&rt73usb_ops) }, /* CNet */ { USB_DEVICE(0x1371, 0x9022), USB_DEVICE_DATA(&rt73usb_ops) }, @@ -2308,6 +2321,11 @@ static struct usb_device_id rt73usb_device_table[] = { { USB_DEVICE(0x07d1, 0x3c04), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x07d1, 0x3c06), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x07d1, 0x3c07), USB_DEVICE_DATA(&rt73usb_ops) }, + /* Edimax */ + { USB_DEVICE(0x7392, 0x7318), USB_DEVICE_DATA(&rt73usb_ops) }, + { USB_DEVICE(0x7392, 0x7618), USB_DEVICE_DATA(&rt73usb_ops) }, + /* EnGenius */ + { USB_DEVICE(0x1740, 0x3701), USB_DEVICE_DATA(&rt73usb_ops) }, /* Gemtek */ { USB_DEVICE(0x15a9, 0x0004), USB_DEVICE_DATA(&rt73usb_ops) }, /* Gigabyte */ @@ -2328,22 +2346,34 @@ static struct usb_device_id rt73usb_device_table[] = { { USB_DEVICE(0x0db0, 0xa861), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x0db0, 0xa874), USB_DEVICE_DATA(&rt73usb_ops) }, /* Ralink */ + { USB_DEVICE(0x04bb, 0x093d), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x148f, 0x2573), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x148f, 0x2671), USB_DEVICE_DATA(&rt73usb_ops) }, /* Qcom */ { USB_DEVICE(0x18e8, 0x6196), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x18e8, 0x6229), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x18e8, 0x6238), USB_DEVICE_DATA(&rt73usb_ops) }, + /* Samsung */ + { USB_DEVICE(0x04e8, 0x4471), USB_DEVICE_DATA(&rt73usb_ops) }, /* Senao */ { USB_DEVICE(0x1740, 0x7100), USB_DEVICE_DATA(&rt73usb_ops) }, /* Sitecom */ - { USB_DEVICE(0x0df6, 0x9712), USB_DEVICE_DATA(&rt73usb_ops) }, + { USB_DEVICE(0x0df6, 0x0024), USB_DEVICE_DATA(&rt73usb_ops) }, + { USB_DEVICE(0x0df6, 0x0027), USB_DEVICE_DATA(&rt73usb_ops) }, + { USB_DEVICE(0x0df6, 0x002f), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x0df6, 0x90ac), USB_DEVICE_DATA(&rt73usb_ops) }, + { USB_DEVICE(0x0df6, 0x9712), USB_DEVICE_DATA(&rt73usb_ops) }, /* Surecom */ { USB_DEVICE(0x0769, 0x31f3), USB_DEVICE_DATA(&rt73usb_ops) }, + /* Philips */ + { USB_DEVICE(0x0471, 0x200a), USB_DEVICE_DATA(&rt73usb_ops) }, /* Planex */ { USB_DEVICE(0x2019, 0xab01), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x2019, 0xab50), USB_DEVICE_DATA(&rt73usb_ops) }, + /* Zcom */ + { USB_DEVICE(0x0cde, 0x001c), USB_DEVICE_DATA(&rt73usb_ops) }, + /* ZyXEL */ + { USB_DEVICE(0x0586, 0x3415), USB_DEVICE_DATA(&rt73usb_ops) }, { 0, } }; diff --git a/drivers/video/i810/i810_main.c b/drivers/video/i810/i810_main.c index a24e680..2e94019 100644 --- a/drivers/video/i810/i810_main.c +++ b/drivers/video/i810/i810_main.c @@ -993,6 +993,7 @@ static int i810_check_params(struct fb_var_screeninfo *var, struct i810fb_par *par = info->par; int line_length, vidmem, mode_valid = 0, retval = 0; u32 vyres = var->yres_virtual, vxres = var->xres_virtual; + /* * Memory limit */ @@ -1002,12 +1003,12 @@ static int i810_check_params(struct fb_var_screeninfo *var, if (vidmem > par->fb.size) { vyres = par->fb.size/line_length; if (vyres < var->yres) { - vyres = yres; + vyres = info->var.yres; vxres = par->fb.size/vyres; vxres /= var->bits_per_pixel >> 3; line_length = get_line_length(par, vxres, var->bits_per_pixel); - vidmem = line_length * yres; + vidmem = line_length * info->var.yres; if (vxres < var->xres) { printk("i810fb: required video memory, " "%d bytes, for %dx%d-%d (virtual) " diff --git a/drivers/video/pxafb.c b/drivers/video/pxafb.c index 48ff701..2552b9f 100644 --- a/drivers/video/pxafb.c +++ b/drivers/video/pxafb.c @@ -2230,7 +2230,7 @@ static int __devexit pxafb_remove(struct platform_device *dev) static struct platform_driver pxafb_driver = { .probe = pxafb_probe, - .remove = pxafb_remove, + .remove = __devexit_p(pxafb_remove), .suspend = pxafb_suspend, .resume = pxafb_resume, .driver = { diff --git a/drivers/video/sh_mobile_lcdcfb.c b/drivers/video/sh_mobile_lcdcfb.c index 0e2b8fd..2c5d069 100644 --- a/drivers/video/sh_mobile_lcdcfb.c +++ b/drivers/video/sh_mobile_lcdcfb.c @@ -446,7 +446,6 @@ static void sh_mobile_lcdc_stop(struct sh_mobile_lcdc_priv *priv) { struct sh_mobile_lcdc_chan *ch; struct sh_mobile_lcdc_board_cfg *board_cfg; - unsigned long tmp; int k; /* tell the board code to disable the panel */ @@ -456,9 +455,8 @@ static void sh_mobile_lcdc_stop(struct sh_mobile_lcdc_priv *priv) if (board_cfg->display_off) board_cfg->display_off(board_cfg->board_data); - /* cleanup deferred io if SYS bus */ - tmp = ch->cfg.sys_bus_cfg.deferred_io_msec; - if (ch->ldmt1r_value & (1 << 12) && tmp) { + /* cleanup deferred io if enabled */ + if (ch->info.fbdefio) { fb_deferred_io_cleanup(&ch->info); ch->info.fbdefio = NULL; } diff --git a/drivers/watchdog/gef_wdt.c b/drivers/watchdog/gef_wdt.c index f0c2b7a..734d980 100644 --- a/drivers/watchdog/gef_wdt.c +++ b/drivers/watchdog/gef_wdt.c @@ -269,7 +269,7 @@ static int __devinit gef_wdt_probe(struct of_device *dev, bus_clk = 133; /* in MHz */ freq = fsl_get_sys_freq(); - if (freq > 0) + if (freq != -1) bus_clk = freq; /* Map devices registers into memory */ diff --git a/drivers/watchdog/ks8695_wdt.c b/drivers/watchdog/ks8695_wdt.c index 0b798fd..74c92d3 100644 --- a/drivers/watchdog/ks8695_wdt.c +++ b/drivers/watchdog/ks8695_wdt.c @@ -21,6 +21,7 @@ #include <linux/watchdog.h> #include <linux/io.h> #include <linux/uaccess.h> +#include <mach/timex.h> #include <mach/regs-timer.h> #define WDT_DEFAULT_TIME 5 /* seconds */ diff --git a/drivers/watchdog/orion5x_wdt.c b/drivers/watchdog/orion5x_wdt.c index 14a339f..b64ae1a 100644 --- a/drivers/watchdog/orion5x_wdt.c +++ b/drivers/watchdog/orion5x_wdt.c @@ -29,6 +29,7 @@ #define WDT_EN 0x0010 #define WDT_VAL (TIMER_VIRT_BASE + 0x0024) +#define ORION5X_TCLK 166666667 #define WDT_MAX_DURATION (0xffffffff / ORION5X_TCLK) #define WDT_IN_USE 0 #define WDT_OK_TO_CLOSE 1 diff --git a/drivers/watchdog/rc32434_wdt.c b/drivers/watchdog/rc32434_wdt.c index 57027f4..f3553fa 100644 --- a/drivers/watchdog/rc32434_wdt.c +++ b/drivers/watchdog/rc32434_wdt.c @@ -34,104 +34,89 @@ #include <asm/time.h> #include <asm/mach-rc32434/integ.h> -#define MAX_TIMEOUT 20 -#define RC32434_WDT_INTERVAL (15 * HZ) - -#define VERSION "0.2" +#define VERSION "0.4" static struct { - struct completion stop; - int running; - struct timer_list timer; - int queue; - int default_ticks; unsigned long inuse; } rc32434_wdt_device; static struct integ __iomem *wdt_reg; -static int ticks = 100 * HZ; static int expect_close; -static int timeout; + +/* Board internal clock speed in Hz, + * the watchdog timer ticks at. */ +extern unsigned int idt_cpu_freq; + +/* translate wtcompare value to seconds and vice versa */ +#define WTCOMP2SEC(x) (x / idt_cpu_freq) +#define SEC2WTCOMP(x) (x * idt_cpu_freq) + +/* Use a default timeout of 20s. This should be + * safe for CPU clock speeds up to 400MHz, as + * ((2 ^ 32) - 1) / (400MHz / 2) = 21s. */ +#define WATCHDOG_TIMEOUT 20 + +static int timeout = WATCHDOG_TIMEOUT; static int nowayout = WATCHDOG_NOWAYOUT; module_param(nowayout, int, 0); MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); +/* apply or and nand masks to data read from addr and write back */ +#define SET_BITS(addr, or, nand) \ + writel((readl(&addr) | or) & ~nand, &addr) static void rc32434_wdt_start(void) { - u32 val; - - if (!rc32434_wdt_device.inuse) { - writel(0, &wdt_reg->wtcount); + u32 or, nand; - val = RC32434_ERR_WRE; - writel(readl(&wdt_reg->errcs) | val, &wdt_reg->errcs); + /* zero the counter before enabling */ + writel(0, &wdt_reg->wtcount); - val = RC32434_WTC_EN; - writel(readl(&wdt_reg->wtc) | val, &wdt_reg->wtc); - } - rc32434_wdt_device.running++; -} + /* don't generate a non-maskable interrupt, + * do a warm reset instead */ + nand = 1 << RC32434_ERR_WNE; + or = 1 << RC32434_ERR_WRE; -static void rc32434_wdt_stop(void) -{ - u32 val; + /* reset the ERRCS timeout bit in case it's set */ + nand |= 1 << RC32434_ERR_WTO; - if (rc32434_wdt_device.running) { + SET_BITS(wdt_reg->errcs, or, nand); - val = ~RC32434_WTC_EN; - writel(readl(&wdt_reg->wtc) & val, &wdt_reg->wtc); + /* reset WTC timeout bit and enable WDT */ + nand = 1 << RC32434_WTC_TO; + or = 1 << RC32434_WTC_EN; - val = ~RC32434_ERR_WRE; - writel(readl(&wdt_reg->errcs) & val, &wdt_reg->errcs); + SET_BITS(wdt_reg->wtc, or, nand); +} - rc32434_wdt_device.running = 0; - } +static void rc32434_wdt_stop(void) +{ + /* Disable WDT */ + SET_BITS(wdt_reg->wtc, 0, 1 << RC32434_WTC_EN); } -static void rc32434_wdt_set(int new_timeout) +static int rc32434_wdt_set(int new_timeout) { - u32 cmp = new_timeout * HZ; - u32 state, val; + int max_to = WTCOMP2SEC((u32)-1); + if (new_timeout < 0 || new_timeout > max_to) { + printk(KERN_ERR KBUILD_MODNAME + ": timeout value must be between 0 and %d", + max_to); + return -EINVAL; + } timeout = new_timeout; - /* - * store and disable WTC - */ - state = (u32)(readl(&wdt_reg->wtc) & RC32434_WTC_EN); - val = ~RC32434_WTC_EN; - writel(readl(&wdt_reg->wtc) & val, &wdt_reg->wtc); - - writel(0, &wdt_reg->wtcount); - writel(cmp, &wdt_reg->wtcompare); - - /* - * restore WTC - */ - - writel(readl(&wdt_reg->wtc) | state, &wdt_reg); -} + writel(SEC2WTCOMP(timeout), &wdt_reg->wtcompare); -static void rc32434_wdt_reset(void) -{ - ticks = rc32434_wdt_device.default_ticks; + return 0; } -static void rc32434_wdt_update(unsigned long unused) +static void rc32434_wdt_ping(void) { - if (rc32434_wdt_device.running) - ticks--; - writel(0, &wdt_reg->wtcount); - - if (rc32434_wdt_device.queue && ticks) - mod_timer(&rc32434_wdt_device.timer, - jiffies + RC32434_WDT_INTERVAL); - else - complete(&rc32434_wdt_device.stop); } static int rc32434_wdt_open(struct inode *inode, struct file *file) @@ -142,19 +127,23 @@ static int rc32434_wdt_open(struct inode *inode, struct file *file) if (nowayout) __module_get(THIS_MODULE); + rc32434_wdt_start(); + rc32434_wdt_ping(); + return nonseekable_open(inode, file); } static int rc32434_wdt_release(struct inode *inode, struct file *file) { - if (expect_close && nowayout == 0) { + if (expect_close == 42) { rc32434_wdt_stop(); printk(KERN_INFO KBUILD_MODNAME ": disabling watchdog timer\n"); module_put(THIS_MODULE); - } else + } else { printk(KERN_CRIT KBUILD_MODNAME ": device closed unexpectedly. WDT will not stop !\n"); - + rc32434_wdt_ping(); + } clear_bit(0, &rc32434_wdt_device.inuse); return 0; } @@ -174,10 +163,10 @@ static ssize_t rc32434_wdt_write(struct file *file, const char *data, if (get_user(c, data + i)) return -EFAULT; if (c == 'V') - expect_close = 1; + expect_close = 42; } } - rc32434_wdt_update(0); + rc32434_wdt_ping(); return len; } return 0; @@ -197,11 +186,11 @@ static long rc32434_wdt_ioctl(struct file *file, unsigned int cmd, }; switch (cmd) { case WDIOC_KEEPALIVE: - rc32434_wdt_reset(); + rc32434_wdt_ping(); break; case WDIOC_GETSTATUS: case WDIOC_GETBOOTSTATUS: - value = readl(&wdt_reg->wtcount); + value = 0; if (copy_to_user(argp, &value, sizeof(int))) return -EFAULT; break; @@ -218,6 +207,7 @@ static long rc32434_wdt_ioctl(struct file *file, unsigned int cmd, break; case WDIOS_DISABLECARD: rc32434_wdt_stop(); + break; default: return -EINVAL; } @@ -225,11 +215,9 @@ static long rc32434_wdt_ioctl(struct file *file, unsigned int cmd, case WDIOC_SETTIMEOUT: if (copy_from_user(&new_timeout, argp, sizeof(int))) return -EFAULT; - if (new_timeout < 1) + if (rc32434_wdt_set(new_timeout)) return -EINVAL; - if (new_timeout > MAX_TIMEOUT) - return -EINVAL; - rc32434_wdt_set(new_timeout); + /* Fall through */ case WDIOC_GETTIMEOUT: return copy_to_user(argp, &timeout, sizeof(int)); default: @@ -254,15 +242,15 @@ static struct miscdevice rc32434_wdt_miscdev = { .fops = &rc32434_wdt_fops, }; -static char banner[] = KERN_INFO KBUILD_MODNAME +static char banner[] __devinitdata = KERN_INFO KBUILD_MODNAME ": Watchdog Timer version " VERSION ", timer margin: %d sec\n"; -static int rc32434_wdt_probe(struct platform_device *pdev) +static int __devinit rc32434_wdt_probe(struct platform_device *pdev) { int ret; struct resource *r; - r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rb500_wdt_res"); + r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rb532_wdt_res"); if (!r) { printk(KERN_ERR KBUILD_MODNAME "failed to retrieve resources\n"); @@ -277,24 +265,12 @@ static int rc32434_wdt_probe(struct platform_device *pdev) } ret = misc_register(&rc32434_wdt_miscdev); - if (ret < 0) { printk(KERN_ERR KBUILD_MODNAME "failed to register watchdog device\n"); goto unmap; } - init_completion(&rc32434_wdt_device.stop); - rc32434_wdt_device.queue = 0; - - clear_bit(0, &rc32434_wdt_device.inuse); - - setup_timer(&rc32434_wdt_device.timer, rc32434_wdt_update, 0L); - - rc32434_wdt_device.default_ticks = ticks; - - rc32434_wdt_start(); - printk(banner, timeout); return 0; @@ -304,23 +280,17 @@ unmap: return ret; } -static int rc32434_wdt_remove(struct platform_device *pdev) +static int __devexit rc32434_wdt_remove(struct platform_device *pdev) { - if (rc32434_wdt_device.queue) { - rc32434_wdt_device.queue = 0; - wait_for_completion(&rc32434_wdt_device.stop); - } misc_deregister(&rc32434_wdt_miscdev); - iounmap(wdt_reg); - return 0; } static struct platform_driver rc32434_wdt = { .probe = rc32434_wdt_probe, - .remove = rc32434_wdt_remove, - .driver = { + .remove = __devexit_p(rc32434_wdt_remove), + .driver = { .name = "rc32434_wdt", } }; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 42491d7..37f31b5 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -277,7 +277,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if (*cow_ret == buf) unlock_orig = 1; - WARN_ON(!btrfs_tree_locked(buf)); + btrfs_assert_tree_locked(buf); if (parent) parent_start = parent->start; @@ -2365,7 +2365,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root if (slot >= btrfs_header_nritems(upper) - 1) return 1; - WARN_ON(!btrfs_tree_locked(path->nodes[1])); + btrfs_assert_tree_locked(path->nodes[1]); right = read_node_slot(root, upper, slot + 1); btrfs_tree_lock(right); @@ -2562,7 +2562,7 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root if (right_nritems == 0) return 1; - WARN_ON(!btrfs_tree_locked(path->nodes[1])); + btrfs_assert_tree_locked(path->nodes[1]); left = read_node_slot(root, path->nodes[1], slot - 1); btrfs_tree_lock(left); @@ -4101,7 +4101,7 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path) next = read_node_slot(root, c, slot); if (!path->skip_locking) { - WARN_ON(!btrfs_tree_locked(c)); + btrfs_assert_tree_locked(c); btrfs_tree_lock(next); btrfs_set_lock_blocking(next); } @@ -4126,7 +4126,7 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path) reada_for_search(root, path, level, slot, 0); next = read_node_slot(root, next, 0); if (!path->skip_locking) { - WARN_ON(!btrfs_tree_locked(path->nodes[level])); + btrfs_assert_tree_locked(path->nodes[level]); btrfs_tree_lock(next); btrfs_set_lock_blocking(next); } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index adda739..3e18175 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -857,7 +857,7 @@ int clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *btree_inode = root->fs_info->btree_inode; if (btrfs_header_generation(buf) == root->fs_info->running_transaction->transid) { - WARN_ON(!btrfs_tree_locked(buf)); + btrfs_assert_tree_locked(buf); /* ugh, clear_extent_buffer_dirty can be expensive */ btrfs_set_lock_blocking(buf); @@ -2361,7 +2361,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) btrfs_set_lock_blocking(buf); - WARN_ON(!btrfs_tree_locked(buf)); + btrfs_assert_tree_locked(buf); if (transid != root->fs_info->generation) { printk(KERN_CRIT "btrfs transid mismatch buffer %llu, " "found %llu running %llu\n", diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 6b5966a..9abf81f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4418,13 +4418,13 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); BUG_ON(!path); - BUG_ON(!btrfs_tree_locked(parent)); + btrfs_assert_tree_locked(parent); parent_level = btrfs_header_level(parent); extent_buffer_get(parent); path->nodes[parent_level] = parent; path->slots[parent_level] = btrfs_header_nritems(parent); - BUG_ON(!btrfs_tree_locked(node)); + btrfs_assert_tree_locked(node); level = btrfs_header_level(node); extent_buffer_get(node); path->nodes[level] = node; diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 85506c4..47b0a88 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -220,8 +220,8 @@ int btrfs_tree_unlock(struct extent_buffer *eb) return 0; } -int btrfs_tree_locked(struct extent_buffer *eb) +void btrfs_assert_tree_locked(struct extent_buffer *eb) { - return test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags) || - spin_is_locked(&eb->lock); + if (!test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags)) + assert_spin_locked(&eb->lock); } diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h index 6bb0afb..6c4ce45 100644 --- a/fs/btrfs/locking.h +++ b/fs/btrfs/locking.h @@ -21,11 +21,11 @@ int btrfs_tree_lock(struct extent_buffer *eb); int btrfs_tree_unlock(struct extent_buffer *eb); -int btrfs_tree_locked(struct extent_buffer *eb); int btrfs_try_tree_lock(struct extent_buffer *eb); int btrfs_try_spin_lock(struct extent_buffer *eb); void btrfs_set_lock_blocking(struct extent_buffer *eb); void btrfs_clear_lock_blocking(struct extent_buffer *eb); +void btrfs_assert_tree_locked(struct extent_buffer *eb); #endif diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 5f3231b..bff4052 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -198,9 +198,6 @@ static int mknod_ptmx(struct super_block *sb) fsi->ptmx_dentry = dentry; rc = 0; - - printk(KERN_DEBUG "Created ptmx node in devpts ino %lu\n", - inode->i_ino); out: mutex_unlock(&root->d_inode->i_mutex); return rc; @@ -369,8 +366,6 @@ static int new_pts_mount(struct file_system_type *fs_type, int flags, struct pts_fs_info *fsi; struct pts_mount_opts *opts; - printk(KERN_NOTICE "devpts: newinstance mount\n"); - err = get_sb_nodev(fs_type, flags, data, devpts_fill_super, mnt); if (err) return err; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index f18a919..627f8c3 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -188,7 +188,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) struct ext4_group_desc *gdp; struct ext4_super_block *es; struct ext4_sb_info *sbi; - int fatal = 0, err, count; + int fatal = 0, err, count, cleared; ext4_group_t flex_group; if (atomic_read(&inode->i_count) > 1) { @@ -248,8 +248,10 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) goto error_return; /* Ok, now we can actually update the inode bitmaps.. */ - if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group), - bit, bitmap_bh->b_data)) + spin_lock(sb_bgl_lock(sbi, block_group)); + cleared = ext4_clear_bit(bit, bitmap_bh->b_data); + spin_unlock(sb_bgl_lock(sbi, block_group)); + if (!cleared) ext4_error(sb, "ext4_free_inode", "bit already cleared for inode %lu", ino); else { diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index c837dfc..321728f 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -80,7 +80,7 @@ static struct buffer_head *get_block_length(struct super_block *sb, * generated a larger block - this does occasionally happen with zlib). */ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, - int length, u64 *next_index, int srclength) + int length, u64 *next_index, int srclength, int pages) { struct squashfs_sb_info *msblk = sb->s_fs_info; struct buffer_head **bh; @@ -185,6 +185,14 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, } if (msblk->stream.avail_out == 0) { + if (page == pages) { + ERROR("zlib_inflate tried to " + "decompress too much data, " + "expected %d bytes. Zlib " + "data probably corrupt\n", + srclength); + goto release_mutex; + } msblk->stream.next_out = buffer[page++]; msblk->stream.avail_out = PAGE_CACHE_SIZE; } @@ -268,7 +276,8 @@ block_release: put_bh(bh[k]); read_failure: - ERROR("sb_bread failed reading block 0x%llx\n", cur_index); + ERROR("squashfs_read_data failed to read block 0x%llx\n", + (unsigned long long) index); kfree(bh); return -EIO; } diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index f29eda1..1c4739e 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -119,7 +119,7 @@ struct squashfs_cache_entry *squashfs_cache_get(struct super_block *sb, entry->length = squashfs_read_data(sb, entry->data, block, length, &entry->next_index, - cache->block_size); + cache->block_size, cache->pages); spin_lock(&cache->lock); @@ -406,7 +406,7 @@ int squashfs_read_table(struct super_block *sb, void *buffer, u64 block, for (i = 0; i < pages; i++, buffer += PAGE_CACHE_SIZE) data[i] = buffer; res = squashfs_read_data(sb, data, block, length | - SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, length); + SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, length, pages); kfree(data); return res; } diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index 7a63398..9101dbd 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -133,7 +133,8 @@ int squashfs_read_inode(struct inode *inode, long long ino) type = le16_to_cpu(sqshb_ino->inode_type); switch (type) { case SQUASHFS_REG_TYPE: { - unsigned int frag_offset, frag_size, frag; + unsigned int frag_offset, frag; + int frag_size; u64 frag_blk; struct squashfs_reg_inode *sqsh_ino = &squashfs_ino.reg; @@ -175,7 +176,8 @@ int squashfs_read_inode(struct inode *inode, long long ino) break; } case SQUASHFS_LREG_TYPE: { - unsigned int frag_offset, frag_size, frag; + unsigned int frag_offset, frag; + int frag_size; u64 frag_blk; struct squashfs_lreg_inode *sqsh_ino = &squashfs_ino.lreg; diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index 6b2515d..0e9feb6 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -34,7 +34,7 @@ static inline struct squashfs_inode_info *squashfs_i(struct inode *inode) /* block.c */ extern int squashfs_read_data(struct super_block *, void **, u64, int, u64 *, - int); + int, int); /* cache.c */ extern struct squashfs_cache *squashfs_cache_init(char *, int, int); diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 071df5b..681ec0d 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -389,7 +389,7 @@ static int __init init_squashfs_fs(void) return err; } - printk(KERN_INFO "squashfs: version 4.0 (2009/01/03) " + printk(KERN_INFO "squashfs: version 4.0 (2009/01/31) " "Phillip Lougher\n"); return 0; diff --git a/include/linux/ata.h b/include/linux/ata.h index 08a86d5..9a061ac 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -89,6 +89,8 @@ enum { ATA_ID_DLF = 128, ATA_ID_CSFO = 129, ATA_ID_CFA_POWER = 160, + ATA_ID_CFA_KEY_MGMT = 162, + ATA_ID_CFA_MODES = 163, ATA_ID_ROT_SPEED = 217, ATA_ID_PIO4 = (1 << 1), diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 95837bf..455d832 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -65,23 +65,20 @@ extern void free_bootmem(unsigned long addr, unsigned long size); #define BOOTMEM_DEFAULT 0 #define BOOTMEM_EXCLUSIVE (1<<0) +extern int reserve_bootmem(unsigned long addr, + unsigned long size, + int flags); extern int reserve_bootmem_node(pg_data_t *pgdat, - unsigned long physaddr, - unsigned long size, - int flags); -#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE -extern int reserve_bootmem(unsigned long addr, unsigned long size, int flags); -#endif + unsigned long physaddr, + unsigned long size, + int flags); -extern void *__alloc_bootmem_nopanic(unsigned long size, +extern void *__alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal); -extern void *__alloc_bootmem(unsigned long size, +extern void *__alloc_bootmem_nopanic(unsigned long size, unsigned long align, unsigned long goal); -extern void *__alloc_bootmem_low(unsigned long size, - unsigned long align, - unsigned long goal); extern void *__alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, unsigned long align, @@ -90,30 +87,35 @@ extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal); +extern void *__alloc_bootmem_low(unsigned long size, + unsigned long align, + unsigned long goal); extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal); -#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE + #define alloc_bootmem(x) \ __alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_nopanic(x) \ __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_low(x) \ - __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) #define alloc_bootmem_pages(x) \ __alloc_bootmem(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_pages_nopanic(x) \ __alloc_bootmem_nopanic(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_low_pages(x) \ - __alloc_bootmem_low(x, PAGE_SIZE, 0) #define alloc_bootmem_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_pages_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) +#define alloc_bootmem_pages_node_nopanic(pgdat, x) \ + __alloc_bootmem_node_nopanic(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) + +#define alloc_bootmem_low(x) \ + __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) +#define alloc_bootmem_low_pages(x) \ + __alloc_bootmem_low(x, PAGE_SIZE, 0) #define alloc_bootmem_low_pages_node(pgdat, x) \ __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) -#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */ extern int reserve_bootmem_generic(unsigned long addr, unsigned long size, int flags); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 384b38d..1610427 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -234,7 +234,6 @@ struct cpufreq_driver { int (*suspend) (struct cpufreq_policy *policy, pm_message_t pmsg); int (*resume) (struct cpufreq_policy *policy); struct freq_attr **attr; - bool hide_interface; }; /* flags */ diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index f041384..1956c8d 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -97,7 +97,6 @@ typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t; /** * struct dma_chan_percpu - the per-CPU part of struct dma_chan - * @refcount: local_t used for open-coded "bigref" counting * @memcpy_count: transaction counter * @bytes_transferred: byte counter */ @@ -114,9 +113,6 @@ struct dma_chan_percpu { * @cookie: last cookie value returned to client * @chan_id: channel ID for sysfs * @dev: class device for sysfs - * @refcount: kref, used in "bigref" slow-mode - * @slow_ref: indicates that the DMA channel is free - * @rcu: the DMA channel's RCU head * @device_node: used to add this to the device chan list * @local: per-cpu pointer to a struct dma_chan_percpu * @client-count: how many clients are using this channel @@ -213,8 +209,6 @@ struct dma_async_tx_descriptor { * @global_node: list_head for global dma_device_list * @cap_mask: one or more dma_capability flags * @max_xor: maximum number of xor sources, 0 if no capability - * @refcount: reference count - * @done: IO completion struct * @dev_id: unique device ID * @dev: struct device reference for dma mapping api * @device_alloc_chan_resources: allocate resources and return the @@ -227,6 +221,7 @@ struct dma_async_tx_descriptor { * @device_prep_dma_interrupt: prepares an end of chain interrupt operation * @device_prep_slave_sg: prepares a slave dma operation * @device_terminate_all: terminate all pending operations + * @device_is_tx_complete: poll for transaction completion * @device_issue_pending: push pending transactions to hardware */ struct dma_device { diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h index c37e924..ed21bd3 100644 --- a/include/linux/hdreg.h +++ b/include/linux/hdreg.h @@ -511,7 +511,6 @@ struct hd_driveid { unsigned short words69_70[2]; /* reserved words 69-70 * future command overlap and queuing */ - /* HDIO_GET_IDENTITY currently returns only words 0 through 70 */ unsigned short words71_74[4]; /* reserved words 71-74 * for IDENTIFY PACKET DEVICE command */ diff --git a/include/linux/ide.h b/include/linux/ide.h index fe235b6..e0cedfe 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -866,6 +866,7 @@ struct ide_host { unsigned int n_ports; struct device *dev[2]; unsigned int (*init_chipset)(struct pci_dev *); + irq_handler_t irq_handler; unsigned long host_flags; void *host_priv; ide_hwif_t *cur_port; /* for hosts requiring serialization */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 5d87bc0..dc18b87 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -275,7 +275,7 @@ enum { * advised to wait only for the following duration before * doing SRST. */ - ATA_TMOUT_PMP_SRST_WAIT = 1000, + ATA_TMOUT_PMP_SRST_WAIT = 5000, /* ATA bus states */ BUS_UNKNOWN = 0, @@ -530,6 +530,7 @@ struct ata_queued_cmd { unsigned long flags; /* ATA_QCFLAG_xxx */ unsigned int tag; unsigned int n_elem; + unsigned int orig_n_elem; int dma_dir; @@ -750,7 +751,8 @@ struct ata_port { acpi_handle acpi_handle; struct ata_acpi_gtm __acpi_init_gtm; /* use ata_acpi_init_gtm() */ #endif - u8 sector_buf[ATA_SECT_SIZE]; /* owned by EH */ + /* owned by EH */ + u8 sector_buf[ATA_SECT_SIZE] ____cacheline_aligned; }; /* The following initializer overrides a method to NULL whether one of diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ec54785..6593667 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1079,6 +1079,7 @@ extern void synchronize_net(void); extern int register_netdevice_notifier(struct notifier_block *nb); extern int unregister_netdevice_notifier(struct notifier_block *nb); extern int init_dummy_netdev(struct net_device *dev); +extern void netdev_resync_ops(struct net_device *dev); extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); extern struct net_device *dev_get_by_index(struct net *net, int ifindex); diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 3577ffd..54a968b 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -5,6 +5,7 @@ #include <linux/slab.h> /* For kmalloc() */ #include <linux/smp.h> #include <linux/cpumask.h> +#include <linux/pfn.h> #include <asm/percpu.h> @@ -52,17 +53,18 @@ #define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var) #define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var) -/* Enough to cover all DEFINE_PER_CPUs in kernel, including modules. */ -#ifndef PERCPU_ENOUGH_ROOM +/* enough to cover all DEFINE_PER_CPUs in modules */ #ifdef CONFIG_MODULES -#define PERCPU_MODULE_RESERVE 8192 +#define PERCPU_MODULE_RESERVE (8 << 10) #else -#define PERCPU_MODULE_RESERVE 0 +#define PERCPU_MODULE_RESERVE 0 #endif +#ifndef PERCPU_ENOUGH_ROOM #define PERCPU_ENOUGH_ROOM \ - (__per_cpu_end - __per_cpu_start + PERCPU_MODULE_RESERVE) -#endif /* PERCPU_ENOUGH_ROOM */ + (ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \ + PERCPU_MODULE_RESERVE) +#endif /* * Must be an lvalue. Since @var must be a simple identifier, @@ -76,52 +78,90 @@ #ifdef CONFIG_SMP +#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA + +/* minimum unit size, also is the maximum supported allocation size */ +#define PCPU_MIN_UNIT_SIZE PFN_ALIGN(64 << 10) + +/* + * PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy + * back on the first chunk for dynamic percpu allocation if arch is + * manually allocating and mapping it for faster access (as a part of + * large page mapping for example). + * + * The following values give between one and two pages of free space + * after typical minimal boot (2-way SMP, single disk and NIC) with + * both defconfig and a distro config on x86_64 and 32. More + * intelligent way to determine this would be nice. + */ +#if BITS_PER_LONG > 32 +#define PERCPU_DYNAMIC_RESERVE (20 << 10) +#else +#define PERCPU_DYNAMIC_RESERVE (12 << 10) +#endif + +extern void *pcpu_base_addr; + +typedef struct page * (*pcpu_get_page_fn_t)(unsigned int cpu, int pageno); +typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr); + +extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, + size_t static_size, size_t reserved_size, + ssize_t unit_size, ssize_t dyn_size, + void *base_addr, + pcpu_populate_pte_fn_t populate_pte_fn); + +/* + * Use this to get to a cpu's version of the per-cpu object + * dynamically allocated. Non-atomic access to the current CPU's + * version should probably be combined with get_cpu()/put_cpu(). + */ +#define per_cpu_ptr(ptr, cpu) SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu))) + +extern void *__alloc_reserved_percpu(size_t size, size_t align); + +#else /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ + struct percpu_data { void *ptrs[1]; }; #define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata) -/* - * Use this to get to a cpu's version of the per-cpu object dynamically - * allocated. Non-atomic access to the current CPU's version should - * probably be combined with get_cpu()/put_cpu(). - */ -#define percpu_ptr(ptr, cpu) \ -({ \ - struct percpu_data *__p = __percpu_disguise(ptr); \ - (__typeof__(ptr))__p->ptrs[(cpu)]; \ + +#define per_cpu_ptr(ptr, cpu) \ +({ \ + struct percpu_data *__p = __percpu_disguise(ptr); \ + (__typeof__(ptr))__p->ptrs[(cpu)]; \ }) -extern void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask); -extern void percpu_free(void *__pdata); +#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ + +extern void *__alloc_percpu(size_t size, size_t align); +extern void free_percpu(void *__pdata); #else /* CONFIG_SMP */ -#define percpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) +#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) -static __always_inline void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask) +static inline void *__alloc_percpu(size_t size, size_t align) { - return kzalloc(size, gfp); + /* + * Can't easily make larger alignment work with kmalloc. WARN + * on it. Larger alignment should only be used for module + * percpu sections on SMP for which this path isn't used. + */ + WARN_ON_ONCE(align > SMP_CACHE_BYTES); + return kzalloc(size, GFP_KERNEL); } -static inline void percpu_free(void *__pdata) +static inline void free_percpu(void *p) { - kfree(__pdata); + kfree(p); } #endif /* CONFIG_SMP */ -#define percpu_alloc_mask(size, gfp, mask) \ - __percpu_alloc_mask((size), (gfp), &(mask)) - -#define percpu_alloc(size, gfp) percpu_alloc_mask((size), (gfp), cpu_online_map) - -/* (legacy) interface for use without CPU hotplug handling */ - -#define __alloc_percpu(size) percpu_alloc_mask((size), GFP_KERNEL, \ - cpu_possible_map) -#define alloc_percpu(type) (type *)__alloc_percpu(sizeof(type)) -#define free_percpu(ptr) percpu_free((ptr)) -#define per_cpu_ptr(ptr, cpu) percpu_ptr((ptr), (cpu)) +#define alloc_percpu(type) (type *)__alloc_percpu(sizeof(type), \ + __alignof__(type)) #endif /* __LINUX_PERCPU_H */ diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h index f3f697d..80044a4 100644 --- a/include/linux/rcuclassic.h +++ b/include/linux/rcuclassic.h @@ -181,4 +181,10 @@ extern long rcu_batches_completed_bh(void); #define rcu_enter_nohz() do { } while (0) #define rcu_exit_nohz() do { } while (0) +/* A context switch is a grace period for rcuclassic. */ +static inline int rcu_blocking_is_gp(void) +{ + return num_online_cpus() == 1; +} + #endif /* __LINUX_RCUCLASSIC_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 921340a..528343e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -52,6 +52,9 @@ struct rcu_head { void (*func)(struct rcu_head *head); }; +/* Internal to kernel, but needed by rcupreempt.h. */ +extern int rcu_scheduler_active; + #if defined(CONFIG_CLASSIC_RCU) #include <linux/rcuclassic.h> #elif defined(CONFIG_TREE_RCU) @@ -265,6 +268,7 @@ extern void rcu_barrier_sched(void); /* Internal to kernel */ extern void rcu_init(void); +extern void rcu_scheduler_starting(void); extern int rcu_needs_cpu(int cpu); #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h index 3e05c09..74304b4 100644 --- a/include/linux/rcupreempt.h +++ b/include/linux/rcupreempt.h @@ -142,4 +142,19 @@ static inline void rcu_exit_nohz(void) #define rcu_exit_nohz() do { } while (0) #endif /* CONFIG_NO_HZ */ +/* + * A context switch is a grace period for rcupreempt synchronize_rcu() + * only during early boot, before the scheduler has been initialized. + * So, how the heck do we get a context switch? Well, if the caller + * invokes synchronize_rcu(), they are willing to accept a context + * switch, so we simply pretend that one happened. + * + * After boot, there might be a blocked or preempted task in an RCU + * read-side critical section, so we cannot then take the fastpath. + */ +static inline int rcu_blocking_is_gp(void) +{ + return num_online_cpus() == 1 && !rcu_scheduler_active; +} + #endif /* __LINUX_RCUPREEMPT_H */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index d4368b7..a722fb6 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -326,4 +326,10 @@ static inline void rcu_exit_nohz(void) } #endif /* CONFIG_NO_HZ */ +/* A context switch is a grace period for rcutree. */ +static inline int rcu_blocking_is_gp(void) +{ + return num_online_cpus() == 1; +} + #endif /* __LINUX_RCUTREE_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index f0a50b2..a7c7698 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2303,9 +2303,13 @@ extern long sched_group_rt_runtime(struct task_group *tg); extern int sched_group_set_rt_period(struct task_group *tg, long rt_period_us); extern long sched_group_rt_period(struct task_group *tg); +extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk); #endif #endif +extern int task_can_switch_user(struct user_struct *up, + struct task_struct *tsk); + #ifdef CONFIG_TASK_XACCT static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { diff --git a/include/linux/serio.h b/include/linux/serio.h index 1bcb357..e0417e4 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -212,7 +212,7 @@ static inline void serio_unpin_driver(struct serio *serio) #define SERIO_FUJITSU 0x35 #define SERIO_ZHENHUA 0x36 #define SERIO_INEXIO 0x37 -#define SERIO_TOUCHIT213 0x37 +#define SERIO_TOUCHIT213 0x38 #define SERIO_W8001 0x39 #endif diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 9c0890c..a43ebec 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -95,6 +95,9 @@ extern struct vm_struct *remove_vm_area(const void *addr); extern int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages); +extern int map_kernel_range_noflush(unsigned long start, unsigned long size, + pgprot_t prot, struct page **pages); +extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size); extern void unmap_kernel_range(unsigned long addr, unsigned long size); /* Allocate/destroy a 'vmalloc' VM area. */ @@ -110,5 +113,6 @@ extern long vwrite(char *buf, char *addr, unsigned long count); */ extern rwlock_t vmlist_lock; extern struct vm_struct *vmlist; +extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); #endif /* _LINUX_VMALLOC_H */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 6fc13d9..ded434b 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -109,11 +109,6 @@ extern struct list_head net_namespace_list; #ifdef CONFIG_NET_NS extern void __put_net(struct net *net); -static inline int net_alive(struct net *net) -{ - return net && atomic_read(&net->count); -} - static inline struct net *get_net(struct net *net) { atomic_inc(&net->count); @@ -145,11 +140,6 @@ int net_eq(const struct net *net1, const struct net *net2) } #else -static inline int net_alive(struct net *net) -{ - return 1; -} - static inline struct net *get_net(struct net *net) { return net; @@ -234,6 +224,23 @@ struct pernet_operations { void (*exit)(struct net *net); }; +/* + * Use these carefully. If you implement a network device and it + * needs per network namespace operations use device pernet operations, + * otherwise use pernet subsys operations. + * + * This is critically important. Most of the network code cleanup + * runs with the assumption that dev_remove_pack has been called so no + * new packets will arrive during and after the cleanup functions have + * been called. dev_remove_pack is not per namespace so instead the + * guarantee of no more packets arriving in a network namespace is + * provided by ensuring that all network devices and all sockets have + * left the network namespace before the cleanup methods are called. + * + * For the longest time the ipv4 icmp code was registered as a pernet + * device which caused kernel oops, and panics during network + * namespace cleanup. So please don't get this wrong. + */ extern int register_pernet_subsys(struct pernet_operations *); extern void unregister_pernet_subsys(struct pernet_operations *); extern int register_pernet_gen_subsys(int *id, struct pernet_operations *); diff --git a/init/Kconfig b/init/Kconfig index 95a6613..38396ec 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -735,6 +735,9 @@ config CC_OPTIMIZE_FOR_SIZE config SYSCTL bool +config ANON_INODES + bool + menuconfig EMBEDDED bool "Configure standard kernel features (for small systems)" help @@ -840,18 +843,6 @@ config PCSPKR_PLATFORM This option allows to disable the internal PC-Speaker support, saving some memory. -config COMPAT_BRK - bool "Disable heap randomization" - default y - help - Randomizing heap placement makes heap exploits harder, but it - also breaks ancient binaries (including anything libc5 based). - This option changes the bootup default to heap randomization - disabled, and can be overriden runtime by setting - /proc/sys/kernel/randomize_va_space to 2. - - On non-ancient distros (post-2000 ones) N is usually a safe choice. - config BASE_FULL default y bool "Enable full-sized data structures for core" if EMBEDDED @@ -869,9 +860,6 @@ config FUTEX support for "fast userspace mutexes". The resulting kernel may not run glibc-based applications correctly. -config ANON_INODES - bool - config EPOLL bool "Enable eventpoll support" if EMBEDDED default y @@ -957,6 +945,18 @@ config SLUB_DEBUG SLUB sysfs support. /sys/slab will not exist and there will be no support for cache validation etc. +config COMPAT_BRK + bool "Disable heap randomization" + default y + help + Randomizing heap placement makes heap exploits harder, but it + also breaks ancient binaries (including anything libc5 based). + This option changes the bootup default to heap randomization + disabled, and can be overriden runtime by setting + /proc/sys/kernel/randomize_va_space to 2. + + On non-ancient distros (post-2000 ones) N is usually a safe choice. + choice prompt "Choose SLAB allocator" default SLUB diff --git a/init/main.c b/init/main.c index 6441083..6bf83af 100644 --- a/init/main.c +++ b/init/main.c @@ -98,7 +98,7 @@ static inline void mark_rodata_ro(void) { } extern void tc_init(void); #endif -enum system_states system_state; +enum system_states system_state __read_mostly; EXPORT_SYMBOL(system_state); /* @@ -464,6 +464,7 @@ static noinline void __init_refok rest_init(void) * at least once to get things moving: */ init_idle_bootup_task(current); + rcu_scheduler_starting(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/kernel/fork.c b/kernel/fork.c index 8de303b..6715ebc 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1184,10 +1184,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, #endif clear_all_latency_tracing(p); - /* Our parent execution domain becomes current domain - These must match for thread signalling to apply */ - p->parent_exec_id = p->self_exec_id; - /* ok, now we should be set up.. */ p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL); p->pdeath_signal = 0; @@ -1225,10 +1221,13 @@ static struct task_struct *copy_process(unsigned long clone_flags, set_task_cpu(p, smp_processor_id()); /* CLONE_PARENT re-uses the old parent */ - if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) + if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; - else + p->parent_exec_id = current->parent_exec_id; + } else { p->real_parent = current; + p->parent_exec_id = current->self_exec_id; + } spin_lock(¤t->sighand->siglock); diff --git a/kernel/module.c b/kernel/module.c index ba22484..f0e04d6 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -51,6 +51,7 @@ #include <linux/tracepoint.h> #include <linux/ftrace.h> #include <linux/async.h> +#include <linux/percpu.h> #if 0 #define DEBUGP printk @@ -366,6 +367,34 @@ static struct module *find_module(const char *name) } #ifdef CONFIG_SMP + +#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA + +static void *percpu_modalloc(unsigned long size, unsigned long align, + const char *name) +{ + void *ptr; + + if (align > PAGE_SIZE) { + printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n", + name, align, PAGE_SIZE); + align = PAGE_SIZE; + } + + ptr = __alloc_reserved_percpu(size, align); + if (!ptr) + printk(KERN_WARNING + "Could not allocate %lu bytes percpu data\n", size); + return ptr; +} + +static void percpu_modfree(void *freeme) +{ + free_percpu(freeme); +} + +#else /* ... !CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ + /* Number of blocks used and allocated. */ static unsigned int pcpu_num_used, pcpu_num_allocated; /* Size of each block. -ve means used. */ @@ -480,21 +509,6 @@ static void percpu_modfree(void *freeme) } } -static unsigned int find_pcpusec(Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, - const char *secstrings) -{ - return find_sec(hdr, sechdrs, secstrings, ".data.percpu"); -} - -static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size) -{ - int cpu; - - for_each_possible_cpu(cpu) - memcpy(pcpudest + per_cpu_offset(cpu), from, size); -} - static int percpu_modinit(void) { pcpu_num_used = 2; @@ -513,7 +527,26 @@ static int percpu_modinit(void) return 0; } __initcall(percpu_modinit); + +#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ + +static unsigned int find_pcpusec(Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, + const char *secstrings) +{ + return find_sec(hdr, sechdrs, secstrings, ".data.percpu"); +} + +static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size) +{ + int cpu; + + for_each_possible_cpu(cpu) + memcpy(pcpudest + per_cpu_offset(cpu), from, size); +} + #else /* ... !CONFIG_SMP */ + static inline void *percpu_modalloc(unsigned long size, unsigned long align, const char *name) { @@ -535,6 +568,7 @@ static inline void percpu_modcopy(void *pcpudst, const void *src, /* pcpusec should be 0, and size of that section should be 0. */ BUG_ON(size != 0); } + #endif /* CONFIG_SMP */ #define MODINFO_ATTR(field) \ diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c index bd5a900..654c640 100644 --- a/kernel/rcuclassic.c +++ b/kernel/rcuclassic.c @@ -679,8 +679,8 @@ int rcu_needs_cpu(int cpu) void rcu_check_callbacks(int cpu, int user) { if (user || - (idle_cpu(cpu) && !in_softirq() && - hardirq_count() <= (1 << HARDIRQ_SHIFT))) { + (idle_cpu(cpu) && rcu_scheduler_active && + !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) { /* * Get here if this CPU took its interrupt from user diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index d92a76a..cae8a05 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -44,6 +44,7 @@ #include <linux/cpu.h> #include <linux/mutex.h> #include <linux/module.h> +#include <linux/kernel_stat.h> enum rcu_barrier { RCU_BARRIER_STD, @@ -55,6 +56,7 @@ static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL}; static atomic_t rcu_barrier_cpu_count; static DEFINE_MUTEX(rcu_barrier_mutex); static struct completion rcu_barrier_completion; +int rcu_scheduler_active __read_mostly; /* * Awaken the corresponding synchronize_rcu() instance now that a @@ -80,6 +82,10 @@ void wakeme_after_rcu(struct rcu_head *head) void synchronize_rcu(void) { struct rcu_synchronize rcu; + + if (rcu_blocking_is_gp()) + return; + init_completion(&rcu.completion); /* Will wake me after RCU finished. */ call_rcu(&rcu.head, wakeme_after_rcu); @@ -175,3 +181,9 @@ void __init rcu_init(void) __rcu_init(); } +void rcu_scheduler_starting(void) +{ + WARN_ON(num_online_cpus() != 1); + WARN_ON(nr_context_switches() > 0); + rcu_scheduler_active = 1; +} diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c index 33cfc50..5d59e85 100644 --- a/kernel/rcupreempt.c +++ b/kernel/rcupreempt.c @@ -1181,6 +1181,9 @@ void __synchronize_sched(void) { struct rcu_synchronize rcu; + if (num_online_cpus() == 1) + return; /* blocking is gp if only one CPU! */ + init_completion(&rcu.completion); /* Will wake me after RCU finished. */ call_rcu_sched(&rcu.head, wakeme_after_rcu); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index b2fd602..97ce315 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -948,8 +948,8 @@ static void rcu_do_batch(struct rcu_data *rdp) void rcu_check_callbacks(int cpu, int user) { if (user || - (idle_cpu(cpu) && !in_softirq() && - hardirq_count() <= (1 << HARDIRQ_SHIFT))) { + (idle_cpu(cpu) && rcu_scheduler_active && + !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) { /* * Get here if this CPU took its interrupt from user diff --git a/kernel/sched.c b/kernel/sched.c index 7d97ff7..0a76d0b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -223,7 +223,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) { ktime_t now; - if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF) + if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) return; if (hrtimer_active(&rt_b->rt_period_timer)) @@ -9219,6 +9219,16 @@ static int sched_rt_global_constraints(void) return ret; } + +int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) +{ + /* Don't accept realtime tasks when there is no way for them to run */ + if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) + return 0; + + return 1; +} + #else /* !CONFIG_RT_GROUP_SCHED */ static int sched_rt_global_constraints(void) { @@ -9312,8 +9322,7 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, struct task_struct *tsk) { #ifdef CONFIG_RT_GROUP_SCHED - /* Don't accept realtime tasks when there is no way for them to run */ - if (rt_task(tsk) && cgroup_tg(cgrp)->rt_bandwidth.rt_runtime == 0) + if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk)) return -EINVAL; #else /* We don't support RT-tasks being in separate groups */ @@ -9476,7 +9485,7 @@ cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) { - u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu); + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); u64 data; #ifndef CONFIG_64BIT @@ -9495,7 +9504,7 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) { - u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu); + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); #ifndef CONFIG_64BIT /* @@ -9591,7 +9600,7 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime) ca = task_ca(tsk); for (; ca; ca = ca->parent) { - u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu); + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); *cpuusage += cputime; } } diff --git a/kernel/softirq.c b/kernel/softirq.c index 0365b48..57d3f67 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -626,6 +626,7 @@ static int ksoftirqd(void * __bind_cpu) preempt_enable_no_resched(); cond_resched(); preempt_disable(); + rcu_qsctr_inc((long)__bind_cpu); } preempt_enable(); set_current_state(TASK_INTERRUPTIBLE); diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 0cd415e..74541ca 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -170,7 +170,7 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) * doesn't hit this CPU until we're ready. */ get_cpu(); for_each_online_cpu(i) { - sm_work = percpu_ptr(stop_machine_work, i); + sm_work = per_cpu_ptr(stop_machine_work, i); INIT_WORK(sm_work, stop_cpu); queue_work_on(i, stop_machine_wq, sm_work); } diff --git a/kernel/sys.c b/kernel/sys.c index f145c41..37f458e 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -559,7 +559,7 @@ error: abort_creds(new); return retval; } - + /* * change the user struct in a credentials set to match the new UID */ @@ -571,6 +571,11 @@ static int set_user(struct cred *new) if (!new_user) return -EAGAIN; + if (!task_can_switch_user(new_user, current)) { + free_uid(new_user); + return -EINVAL; + } + if (atomic_read(&new_user->processes) >= current->signal->rlim[RLIMIT_NPROC].rlim_cur && new_user != INIT_USER) { @@ -631,10 +636,11 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) goto error; } - retval = -EAGAIN; - if (new->uid != old->uid && set_user(new) < 0) - goto error; - + if (new->uid != old->uid) { + retval = set_user(new); + if (retval < 0) + goto error; + } if (ruid != (uid_t) -1 || (euid != (uid_t) -1 && euid != old->uid)) new->suid = new->euid; @@ -680,9 +686,10 @@ SYSCALL_DEFINE1(setuid, uid_t, uid) retval = -EPERM; if (capable(CAP_SETUID)) { new->suid = new->uid = uid; - if (uid != old->uid && set_user(new) < 0) { - retval = -EAGAIN; - goto error; + if (uid != old->uid) { + retval = set_user(new); + if (retval < 0) + goto error; } } else if (uid != old->uid && uid != new->suid) { goto error; @@ -734,11 +741,13 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) goto error; } - retval = -EAGAIN; if (ruid != (uid_t) -1) { new->uid = ruid; - if (ruid != old->uid && set_user(new) < 0) - goto error; + if (ruid != old->uid) { + retval = set_user(new); + if (retval < 0) + goto error; + } } if (euid != (uid_t) -1) new->euid = euid; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 43f891b..00d59d0 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -122,8 +122,10 @@ void acct_update_integrals(struct task_struct *tsk) if (likely(tsk->mm)) { cputime_t time, dtime; struct timeval value; + unsigned long flags; u64 delta; + local_irq_save(flags); time = tsk->stime + tsk->utime; dtime = cputime_sub(time, tsk->acct_timexpd); jiffies_to_timeval(cputime_to_jiffies(dtime), &value); @@ -131,10 +133,12 @@ void acct_update_integrals(struct task_struct *tsk) delta = delta * USEC_PER_SEC + value.tv_usec; if (delta == 0) - return; + goto out; tsk->acct_timexpd = time; tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm); tsk->acct_vm_mem1 += delta * tsk->mm->total_vm; + out: + local_irq_restore(flags); } } diff --git a/kernel/user.c b/kernel/user.c index 3551ac7..fbb300e 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -286,14 +286,12 @@ int __init uids_sysfs_init(void) /* work function to remove sysfs directory for a user and free up * corresponding structures. */ -static void remove_user_sysfs_dir(struct work_struct *w) +static void cleanup_user_struct(struct work_struct *w) { struct user_struct *up = container_of(w, struct user_struct, work); unsigned long flags; int remove_user = 0; - if (up->user_ns != &init_user_ns) - return; /* Make uid_hash_remove() + sysfs_remove_file() + kobject_del() * atomic. */ @@ -312,9 +310,11 @@ static void remove_user_sysfs_dir(struct work_struct *w) if (!remove_user) goto done; - kobject_uevent(&up->kobj, KOBJ_REMOVE); - kobject_del(&up->kobj); - kobject_put(&up->kobj); + if (up->user_ns == &init_user_ns) { + kobject_uevent(&up->kobj, KOBJ_REMOVE); + kobject_del(&up->kobj); + kobject_put(&up->kobj); + } sched_destroy_user(up); key_put(up->uid_keyring); @@ -335,7 +335,7 @@ static void free_user(struct user_struct *up, unsigned long flags) atomic_inc(&up->__count); spin_unlock_irqrestore(&uidhash_lock, flags); - INIT_WORK(&up->work, remove_user_sysfs_dir); + INIT_WORK(&up->work, cleanup_user_struct); schedule_work(&up->work); } @@ -362,6 +362,24 @@ static void free_user(struct user_struct *up, unsigned long flags) #endif +#if defined(CONFIG_RT_GROUP_SCHED) && defined(CONFIG_USER_SCHED) +/* + * We need to check if a setuid can take place. This function should be called + * before successfully completing the setuid. + */ +int task_can_switch_user(struct user_struct *up, struct task_struct *tsk) +{ + + return sched_rt_can_attach(up->tg, tsk); + +} +#else +int task_can_switch_user(struct user_struct *up, struct task_struct *tsk) +{ + return 1; +} +#endif + /* * Locate the user_struct for the passed UID. If found, take a ref on it. The * caller must undo that ref with free_uid(). @@ -449,6 +449,7 @@ void idr_remove_all(struct idr *idp) n = idp->layers * IDR_BITS; p = idp->top; + rcu_assign_pointer(idp->top, NULL); max = 1 << n; id = 0; @@ -467,7 +468,6 @@ void idr_remove_all(struct idr *idp) p = *--paa; } } - rcu_assign_pointer(idp->top, NULL); idp->layers = 0; } EXPORT_SYMBOL(idr_remove_all); diff --git a/mm/Makefile b/mm/Makefile index 72255be..818569b 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -30,6 +30,10 @@ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o +ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA +obj-$(CONFIG_SMP) += percpu.o +else obj-$(CONFIG_SMP) += allocpercpu.o +endif obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c index 4297bc4..3653c57 100644 --- a/mm/allocpercpu.c +++ b/mm/allocpercpu.c @@ -99,45 +99,51 @@ static int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp, __percpu_populate_mask((__pdata), (size), (gfp), &(mask)) /** - * percpu_alloc_mask - initial setup of per-cpu data + * alloc_percpu - initial setup of per-cpu data * @size: size of per-cpu object - * @gfp: may sleep or not etc. - * @mask: populate per-data for cpu's selected through mask bits + * @align: alignment * - * Populating per-cpu data for all online cpu's would be a typical use case, - * which is simplified by the percpu_alloc() wrapper. - * Per-cpu objects are populated with zeroed buffers. + * Allocate dynamic percpu area. Percpu objects are populated with + * zeroed buffers. */ -void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask) +void *__alloc_percpu(size_t size, size_t align) { /* * We allocate whole cache lines to avoid false sharing */ size_t sz = roundup(nr_cpu_ids * sizeof(void *), cache_line_size()); - void *pdata = kzalloc(sz, gfp); + void *pdata = kzalloc(sz, GFP_KERNEL); void *__pdata = __percpu_disguise(pdata); + /* + * Can't easily make larger alignment work with kmalloc. WARN + * on it. Larger alignment should only be used for module + * percpu sections on SMP for which this path isn't used. + */ + WARN_ON_ONCE(align > __alignof__(unsigned long long)); + if (unlikely(!pdata)) return NULL; - if (likely(!__percpu_populate_mask(__pdata, size, gfp, mask))) + if (likely(!__percpu_populate_mask(__pdata, size, GFP_KERNEL, + &cpu_possible_map))) return __pdata; kfree(pdata); return NULL; } -EXPORT_SYMBOL_GPL(__percpu_alloc_mask); +EXPORT_SYMBOL_GPL(__alloc_percpu); /** - * percpu_free - final cleanup of per-cpu data + * free_percpu - final cleanup of per-cpu data * @__pdata: object to clean up * * We simply clean up any per-cpu object left. No need for the client to * track and specify through a bis mask which per-cpu objects are to free. */ -void percpu_free(void *__pdata) +void free_percpu(void *__pdata) { if (unlikely(!__pdata)) return; __percpu_depopulate_mask(__pdata, &cpu_possible_map); kfree(__percpu_disguise(__pdata)); } -EXPORT_SYMBOL_GPL(percpu_free); +EXPORT_SYMBOL_GPL(free_percpu); diff --git a/mm/bootmem.c b/mm/bootmem.c index 51a0ccf..daf9271 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -382,7 +382,6 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, return mark_bootmem_node(pgdat->bdata, start, end, 1, flags); } -#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE /** * reserve_bootmem - mark a page range as usable * @addr: starting address of the range @@ -403,7 +402,6 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size, return mark_bootmem(start, end, 1, flags); } -#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */ static unsigned long align_idx(struct bootmem_data *bdata, unsigned long idx, unsigned long step) @@ -429,8 +427,8 @@ static unsigned long align_off(struct bootmem_data *bdata, unsigned long off, } static void * __init alloc_bootmem_core(struct bootmem_data *bdata, - unsigned long size, unsigned long align, - unsigned long goal, unsigned long limit) + unsigned long size, unsigned long align, + unsigned long goal, unsigned long limit) { unsigned long fallback = 0; unsigned long min, max, start, sidx, midx, step; @@ -530,17 +528,34 @@ find_block: return NULL; } +static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata, + unsigned long size, unsigned long align, + unsigned long goal, unsigned long limit) +{ +#ifdef CONFIG_HAVE_ARCH_BOOTMEM + bootmem_data_t *p_bdata; + + p_bdata = bootmem_arch_preferred_node(bdata, size, align, goal, limit); + if (p_bdata) + return alloc_bootmem_core(p_bdata, size, align, goal, limit); +#endif + return NULL; +} + static void * __init ___alloc_bootmem_nopanic(unsigned long size, unsigned long align, unsigned long goal, unsigned long limit) { bootmem_data_t *bdata; + void *region; restart: - list_for_each_entry(bdata, &bdata_list, list) { - void *region; + region = alloc_arch_preferred_bootmem(NULL, size, align, goal, limit); + if (region) + return region; + list_for_each_entry(bdata, &bdata_list, list) { if (goal && bdata->node_low_pfn <= PFN_DOWN(goal)) continue; if (limit && bdata->node_min_pfn >= PFN_DOWN(limit)) @@ -618,6 +633,10 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata, { void *ptr; + ptr = alloc_arch_preferred_bootmem(bdata, size, align, goal, limit); + if (ptr) + return ptr; + ptr = alloc_bootmem_core(bdata, size, align, goal, limit); if (ptr) return ptr; @@ -674,6 +693,10 @@ void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, { void *ptr; + ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size, align, goal, 0); + if (ptr) + return ptr; + ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0); if (ptr) return ptr; diff --git a/mm/percpu.c b/mm/percpu.c new file mode 100644 index 0000000..bfe6a3a --- /dev/null +++ b/mm/percpu.c @@ -0,0 +1,1226 @@ +/* + * linux/mm/percpu.c - percpu memory allocator + * + * Copyright (C) 2009 SUSE Linux Products GmbH + * Copyright (C) 2009 Tejun Heo <tj@kernel.org> + * + * This file is released under the GPLv2. + * + * This is percpu allocator which can handle both static and dynamic + * areas. Percpu areas are allocated in chunks in vmalloc area. Each + * chunk is consisted of num_possible_cpus() units and the first chunk + * is used for static percpu variables in the kernel image (special + * boot time alloc/init handling necessary as these areas need to be + * brought up before allocation services are running). Unit grows as + * necessary and all units grow or shrink in unison. When a chunk is + * filled up, another chunk is allocated. ie. in vmalloc area + * + * c0 c1 c2 + * ------------------- ------------------- ------------ + * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u + * ------------------- ...... ------------------- .... ------------ + * + * Allocation is done in offset-size areas of single unit space. Ie, + * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0, + * c1:u1, c1:u2 and c1:u3. Percpu access can be done by configuring + * percpu base registers UNIT_SIZE apart. + * + * There are usually many small percpu allocations many of them as + * small as 4 bytes. The allocator organizes chunks into lists + * according to free size and tries to allocate from the fullest one. + * Each chunk keeps the maximum contiguous area size hint which is + * guaranteed to be eqaul to or larger than the maximum contiguous + * area in the chunk. This helps the allocator not to iterate the + * chunk maps unnecessarily. + * + * Allocation state in each chunk is kept using an array of integers + * on chunk->map. A positive value in the map represents a free + * region and negative allocated. Allocation inside a chunk is done + * by scanning this map sequentially and serving the first matching + * entry. This is mostly copied from the percpu_modalloc() allocator. + * Chunks are also linked into a rb tree to ease address to chunk + * mapping during free. + * + * To use this allocator, arch code should do the followings. + * + * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA + * + * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate + * regular address to percpu pointer and back + * + * - use pcpu_setup_first_chunk() during percpu area initialization to + * setup the first chunk containing the kernel static percpu area + */ + +#include <linux/bitmap.h> +#include <linux/bootmem.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/percpu.h> +#include <linux/pfn.h> +#include <linux/rbtree.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/vmalloc.h> +#include <linux/workqueue.h> + +#include <asm/cacheflush.h> +#include <asm/tlbflush.h> + +#define PCPU_SLOT_BASE_SHIFT 5 /* 1-31 shares the same slot */ +#define PCPU_DFL_MAP_ALLOC 16 /* start a map with 16 ents */ + +struct pcpu_chunk { + struct list_head list; /* linked to pcpu_slot lists */ + struct rb_node rb_node; /* key is chunk->vm->addr */ + int free_size; /* free bytes in the chunk */ + int contig_hint; /* max contiguous size hint */ + struct vm_struct *vm; /* mapped vmalloc region */ + int map_used; /* # of map entries used */ + int map_alloc; /* # of map entries allocated */ + int *map; /* allocation map */ + bool immutable; /* no [de]population allowed */ + struct page **page; /* points to page array */ + struct page *page_ar[]; /* #cpus * UNIT_PAGES */ +}; + +static int pcpu_unit_pages __read_mostly; +static int pcpu_unit_size __read_mostly; +static int pcpu_chunk_size __read_mostly; +static int pcpu_nr_slots __read_mostly; +static size_t pcpu_chunk_struct_size __read_mostly; + +/* the address of the first chunk which starts with the kernel static area */ +void *pcpu_base_addr __read_mostly; +EXPORT_SYMBOL_GPL(pcpu_base_addr); + +/* optional reserved chunk, only accessible for reserved allocations */ +static struct pcpu_chunk *pcpu_reserved_chunk; +/* offset limit of the reserved chunk */ +static int pcpu_reserved_chunk_limit; + +/* + * Synchronization rules. + * + * There are two locks - pcpu_alloc_mutex and pcpu_lock. The former + * protects allocation/reclaim paths, chunks and chunk->page arrays. + * The latter is a spinlock and protects the index data structures - + * chunk slots, rbtree, chunks and area maps in chunks. + * + * During allocation, pcpu_alloc_mutex is kept locked all the time and + * pcpu_lock is grabbed and released as necessary. All actual memory + * allocations are done using GFP_KERNEL with pcpu_lock released. + * + * Free path accesses and alters only the index data structures, so it + * can be safely called from atomic context. When memory needs to be + * returned to the system, free path schedules reclaim_work which + * grabs both pcpu_alloc_mutex and pcpu_lock, unlinks chunks to be + * reclaimed, release both locks and frees the chunks. Note that it's + * necessary to grab both locks to remove a chunk from circulation as + * allocation path might be referencing the chunk with only + * pcpu_alloc_mutex locked. + */ +static DEFINE_MUTEX(pcpu_alloc_mutex); /* protects whole alloc and reclaim */ +static DEFINE_SPINLOCK(pcpu_lock); /* protects index data structures */ + +static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */ +static struct rb_root pcpu_addr_root = RB_ROOT; /* chunks by address */ + +/* reclaim work to release fully free chunks, scheduled from free path */ +static void pcpu_reclaim(struct work_struct *work); +static DECLARE_WORK(pcpu_reclaim_work, pcpu_reclaim); + +static int __pcpu_size_to_slot(int size) +{ + int highbit = fls(size); /* size is in bytes */ + return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); +} + +static int pcpu_size_to_slot(int size) +{ + if (size == pcpu_unit_size) + return pcpu_nr_slots - 1; + return __pcpu_size_to_slot(size); +} + +static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) +{ + if (chunk->free_size < sizeof(int) || chunk->contig_hint < sizeof(int)) + return 0; + + return pcpu_size_to_slot(chunk->free_size); +} + +static int pcpu_page_idx(unsigned int cpu, int page_idx) +{ + return cpu * pcpu_unit_pages + page_idx; +} + +static struct page **pcpu_chunk_pagep(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + return &chunk->page[pcpu_page_idx(cpu, page_idx)]; +} + +static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + return (unsigned long)chunk->vm->addr + + (pcpu_page_idx(cpu, page_idx) << PAGE_SHIFT); +} + +static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk, + int page_idx) +{ + return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL; +} + +/** + * pcpu_mem_alloc - allocate memory + * @size: bytes to allocate + * + * Allocate @size bytes. If @size is smaller than PAGE_SIZE, + * kzalloc() is used; otherwise, vmalloc() is used. The returned + * memory is always zeroed. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Pointer to the allocated area on success, NULL on failure. + */ +static void *pcpu_mem_alloc(size_t size) +{ + if (size <= PAGE_SIZE) + return kzalloc(size, GFP_KERNEL); + else { + void *ptr = vmalloc(size); + if (ptr) + memset(ptr, 0, size); + return ptr; + } +} + +/** + * pcpu_mem_free - free memory + * @ptr: memory to free + * @size: size of the area + * + * Free @ptr. @ptr should have been allocated using pcpu_mem_alloc(). + */ +static void pcpu_mem_free(void *ptr, size_t size) +{ + if (size <= PAGE_SIZE) + kfree(ptr); + else + vfree(ptr); +} + +/** + * pcpu_chunk_relocate - put chunk in the appropriate chunk slot + * @chunk: chunk of interest + * @oslot: the previous slot it was on + * + * This function is called after an allocation or free changed @chunk. + * New slot according to the changed state is determined and @chunk is + * moved to the slot. Note that the reserved chunk is never put on + * chunk slots. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) +{ + int nslot = pcpu_chunk_slot(chunk); + + if (chunk != pcpu_reserved_chunk && oslot != nslot) { + if (oslot < nslot) + list_move(&chunk->list, &pcpu_slot[nslot]); + else + list_move_tail(&chunk->list, &pcpu_slot[nslot]); + } +} + +static struct rb_node **pcpu_chunk_rb_search(void *addr, + struct rb_node **parentp) +{ + struct rb_node **p = &pcpu_addr_root.rb_node; + struct rb_node *parent = NULL; + struct pcpu_chunk *chunk; + + while (*p) { + parent = *p; + chunk = rb_entry(parent, struct pcpu_chunk, rb_node); + + if (addr < chunk->vm->addr) + p = &(*p)->rb_left; + else if (addr > chunk->vm->addr) + p = &(*p)->rb_right; + else + break; + } + + if (parentp) + *parentp = parent; + return p; +} + +/** + * pcpu_chunk_addr_search - search for chunk containing specified address + * @addr: address to search for + * + * Look for chunk which might contain @addr. More specifically, it + * searchs for the chunk with the highest start address which isn't + * beyond @addr. + * + * CONTEXT: + * pcpu_lock. + * + * RETURNS: + * The address of the found chunk. + */ +static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) +{ + struct rb_node *n, *parent; + struct pcpu_chunk *chunk; + + /* is it in the reserved chunk? */ + if (pcpu_reserved_chunk) { + void *start = pcpu_reserved_chunk->vm->addr; + + if (addr >= start && addr < start + pcpu_reserved_chunk_limit) + return pcpu_reserved_chunk; + } + + /* nah... search the regular ones */ + n = *pcpu_chunk_rb_search(addr, &parent); + if (!n) { + /* no exactly matching chunk, the parent is the closest */ + n = parent; + BUG_ON(!n); + } + chunk = rb_entry(n, struct pcpu_chunk, rb_node); + + if (addr < chunk->vm->addr) { + /* the parent was the next one, look for the previous one */ + n = rb_prev(n); + BUG_ON(!n); + chunk = rb_entry(n, struct pcpu_chunk, rb_node); + } + + return chunk; +} + +/** + * pcpu_chunk_addr_insert - insert chunk into address rb tree + * @new: chunk to insert + * + * Insert @new into address rb tree. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_chunk_addr_insert(struct pcpu_chunk *new) +{ + struct rb_node **p, *parent; + + p = pcpu_chunk_rb_search(new->vm->addr, &parent); + BUG_ON(*p); + rb_link_node(&new->rb_node, parent, p); + rb_insert_color(&new->rb_node, &pcpu_addr_root); +} + +/** + * pcpu_extend_area_map - extend area map for allocation + * @chunk: target chunk + * + * Extend area map of @chunk so that it can accomodate an allocation. + * A single allocation can split an area into three areas, so this + * function makes sure that @chunk->map has at least two extra slots. + * + * CONTEXT: + * pcpu_alloc_mutex, pcpu_lock. pcpu_lock is released and reacquired + * if area map is extended. + * + * RETURNS: + * 0 if noop, 1 if successfully extended, -errno on failure. + */ +static int pcpu_extend_area_map(struct pcpu_chunk *chunk) +{ + int new_alloc; + int *new; + size_t size; + + /* has enough? */ + if (chunk->map_alloc >= chunk->map_used + 2) + return 0; + + spin_unlock_irq(&pcpu_lock); + + new_alloc = PCPU_DFL_MAP_ALLOC; + while (new_alloc < chunk->map_used + 2) + new_alloc *= 2; + + new = pcpu_mem_alloc(new_alloc * sizeof(new[0])); + if (!new) { + spin_lock_irq(&pcpu_lock); + return -ENOMEM; + } + + /* + * Acquire pcpu_lock and switch to new area map. Only free + * could have happened inbetween, so map_used couldn't have + * grown. + */ + spin_lock_irq(&pcpu_lock); + BUG_ON(new_alloc < chunk->map_used + 2); + + size = chunk->map_alloc * sizeof(chunk->map[0]); + memcpy(new, chunk->map, size); + + /* + * map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is + * one of the first chunks and still using static map. + */ + if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC) + pcpu_mem_free(chunk->map, size); + + chunk->map_alloc = new_alloc; + chunk->map = new; + return 0; +} + +/** + * pcpu_split_block - split a map block + * @chunk: chunk of interest + * @i: index of map block to split + * @head: head size in bytes (can be 0) + * @tail: tail size in bytes (can be 0) + * + * Split the @i'th map block into two or three blocks. If @head is + * non-zero, @head bytes block is inserted before block @i moving it + * to @i+1 and reducing its size by @head bytes. + * + * If @tail is non-zero, the target block, which can be @i or @i+1 + * depending on @head, is reduced by @tail bytes and @tail byte block + * is inserted after the target block. + * + * @chunk->map must have enough free slots to accomodate the split. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_split_block(struct pcpu_chunk *chunk, int i, + int head, int tail) +{ + int nr_extra = !!head + !!tail; + + BUG_ON(chunk->map_alloc < chunk->map_used + nr_extra); + + /* insert new subblocks */ + memmove(&chunk->map[i + nr_extra], &chunk->map[i], + sizeof(chunk->map[0]) * (chunk->map_used - i)); + chunk->map_used += nr_extra; + + if (head) { + chunk->map[i + 1] = chunk->map[i] - head; + chunk->map[i++] = head; + } + if (tail) { + chunk->map[i++] -= tail; + chunk->map[i] = tail; + } +} + +/** + * pcpu_alloc_area - allocate area from a pcpu_chunk + * @chunk: chunk of interest + * @size: wanted size in bytes + * @align: wanted align + * + * Try to allocate @size bytes area aligned at @align from @chunk. + * Note that this function only allocates the offset. It doesn't + * populate or map the area. + * + * @chunk->map must have at least two free slots. + * + * CONTEXT: + * pcpu_lock. + * + * RETURNS: + * Allocated offset in @chunk on success, -1 if no matching area is + * found. + */ +static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) +{ + int oslot = pcpu_chunk_slot(chunk); + int max_contig = 0; + int i, off; + + for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) { + bool is_last = i + 1 == chunk->map_used; + int head, tail; + + /* extra for alignment requirement */ + head = ALIGN(off, align) - off; + BUG_ON(i == 0 && head != 0); + + if (chunk->map[i] < 0) + continue; + if (chunk->map[i] < head + size) { + max_contig = max(chunk->map[i], max_contig); + continue; + } + + /* + * If head is small or the previous block is free, + * merge'em. Note that 'small' is defined as smaller + * than sizeof(int), which is very small but isn't too + * uncommon for percpu allocations. + */ + if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) { + if (chunk->map[i - 1] > 0) + chunk->map[i - 1] += head; + else { + chunk->map[i - 1] -= head; + chunk->free_size -= head; + } + chunk->map[i] -= head; + off += head; + head = 0; + } + + /* if tail is small, just keep it around */ + tail = chunk->map[i] - head - size; + if (tail < sizeof(int)) + tail = 0; + + /* split if warranted */ + if (head || tail) { + pcpu_split_block(chunk, i, head, tail); + if (head) { + i++; + off += head; + max_contig = max(chunk->map[i - 1], max_contig); + } + if (tail) + max_contig = max(chunk->map[i + 1], max_contig); + } + + /* update hint and mark allocated */ + if (is_last) + chunk->contig_hint = max_contig; /* fully scanned */ + else + chunk->contig_hint = max(chunk->contig_hint, + max_contig); + + chunk->free_size -= chunk->map[i]; + chunk->map[i] = -chunk->map[i]; + + pcpu_chunk_relocate(chunk, oslot); + return off; + } + + chunk->contig_hint = max_contig; /* fully scanned */ + pcpu_chunk_relocate(chunk, oslot); + + /* tell the upper layer that this chunk has no matching area */ + return -1; +} + +/** + * pcpu_free_area - free area to a pcpu_chunk + * @chunk: chunk of interest + * @freeme: offset of area to free + * + * Free area starting from @freeme to @chunk. Note that this function + * only modifies the allocation map. It doesn't depopulate or unmap + * the area. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme) +{ + int oslot = pcpu_chunk_slot(chunk); + int i, off; + + for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) + if (off == freeme) + break; + BUG_ON(off != freeme); + BUG_ON(chunk->map[i] > 0); + + chunk->map[i] = -chunk->map[i]; + chunk->free_size += chunk->map[i]; + + /* merge with previous? */ + if (i > 0 && chunk->map[i - 1] >= 0) { + chunk->map[i - 1] += chunk->map[i]; + chunk->map_used--; + memmove(&chunk->map[i], &chunk->map[i + 1], + (chunk->map_used - i) * sizeof(chunk->map[0])); + i--; + } + /* merge with next? */ + if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) { + chunk->map[i] += chunk->map[i + 1]; + chunk->map_used--; + memmove(&chunk->map[i + 1], &chunk->map[i + 2], + (chunk->map_used - (i + 1)) * sizeof(chunk->map[0])); + } + + chunk->contig_hint = max(chunk->map[i], chunk->contig_hint); + pcpu_chunk_relocate(chunk, oslot); +} + +/** + * pcpu_unmap - unmap pages out of a pcpu_chunk + * @chunk: chunk of interest + * @page_start: page index of the first page to unmap + * @page_end: page index of the last page to unmap + 1 + * @flush: whether to flush cache and tlb or not + * + * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. + * If @flush is true, vcache is flushed before unmapping and tlb + * after. + */ +static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end, + bool flush) +{ + unsigned int last = num_possible_cpus() - 1; + unsigned int cpu; + + /* unmap must not be done on immutable chunk */ + WARN_ON(chunk->immutable); + + /* + * Each flushing trial can be very expensive, issue flush on + * the whole region at once rather than doing it for each cpu. + * This could be an overkill but is more scalable. + */ + if (flush) + flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); + + for_each_possible_cpu(cpu) + unmap_kernel_range_noflush( + pcpu_chunk_addr(chunk, cpu, page_start), + (page_end - page_start) << PAGE_SHIFT); + + /* ditto as flush_cache_vunmap() */ + if (flush) + flush_tlb_kernel_range(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); +} + +/** + * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk + * @chunk: chunk to depopulate + * @off: offset to the area to depopulate + * @size: size of the area to depopulate in bytes + * @flush: whether to flush cache and tlb or not + * + * For each cpu, depopulate and unmap pages [@page_start,@page_end) + * from @chunk. If @flush is true, vcache is flushed before unmapping + * and tlb after. + * + * CONTEXT: + * pcpu_alloc_mutex. + */ +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size, + bool flush) +{ + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + int unmap_start = -1; + int uninitialized_var(unmap_end); + unsigned int cpu; + int i; + + for (i = page_start; i < page_end; i++) { + for_each_possible_cpu(cpu) { + struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i); + + if (!*pagep) + continue; + + __free_page(*pagep); + + /* + * If it's partial depopulation, it might get + * populated or depopulated again. Mark the + * page gone. + */ + *pagep = NULL; + + unmap_start = unmap_start < 0 ? i : unmap_start; + unmap_end = i + 1; + } + } + + if (unmap_start >= 0) + pcpu_unmap(chunk, unmap_start, unmap_end, flush); +} + +/** + * pcpu_map - map pages into a pcpu_chunk + * @chunk: chunk of interest + * @page_start: page index of the first page to map + * @page_end: page index of the last page to map + 1 + * + * For each cpu, map pages [@page_start,@page_end) into @chunk. + * vcache is flushed afterwards. + */ +static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end) +{ + unsigned int last = num_possible_cpus() - 1; + unsigned int cpu; + int err; + + /* map must not be done on immutable chunk */ + WARN_ON(chunk->immutable); + + for_each_possible_cpu(cpu) { + err = map_kernel_range_noflush( + pcpu_chunk_addr(chunk, cpu, page_start), + (page_end - page_start) << PAGE_SHIFT, + PAGE_KERNEL, + pcpu_chunk_pagep(chunk, cpu, page_start)); + if (err < 0) + return err; + } + + /* flush at once, please read comments in pcpu_unmap() */ + flush_cache_vmap(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); + return 0; +} + +/** + * pcpu_populate_chunk - populate and map an area of a pcpu_chunk + * @chunk: chunk of interest + * @off: offset to the area to populate + * @size: size of the area to populate in bytes + * + * For each cpu, populate and map pages [@page_start,@page_end) into + * @chunk. The area is cleared on return. + * + * CONTEXT: + * pcpu_alloc_mutex, does GFP_KERNEL allocation. + */ +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + const gfp_t alloc_mask = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + int map_start = -1; + int uninitialized_var(map_end); + unsigned int cpu; + int i; + + for (i = page_start; i < page_end; i++) { + if (pcpu_chunk_page_occupied(chunk, i)) { + if (map_start >= 0) { + if (pcpu_map(chunk, map_start, map_end)) + goto err; + map_start = -1; + } + continue; + } + + map_start = map_start < 0 ? i : map_start; + map_end = i + 1; + + for_each_possible_cpu(cpu) { + struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i); + + *pagep = alloc_pages_node(cpu_to_node(cpu), + alloc_mask, 0); + if (!*pagep) + goto err; + } + } + + if (map_start >= 0 && pcpu_map(chunk, map_start, map_end)) + goto err; + + for_each_possible_cpu(cpu) + memset(chunk->vm->addr + cpu * pcpu_unit_size + off, 0, + size); + + return 0; +err: + /* likely under heavy memory pressure, give memory back */ + pcpu_depopulate_chunk(chunk, off, size, true); + return -ENOMEM; +} + +static void free_pcpu_chunk(struct pcpu_chunk *chunk) +{ + if (!chunk) + return; + if (chunk->vm) + free_vm_area(chunk->vm); + pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0])); + kfree(chunk); +} + +static struct pcpu_chunk *alloc_pcpu_chunk(void) +{ + struct pcpu_chunk *chunk; + + chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL); + if (!chunk) + return NULL; + + chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); + chunk->map_alloc = PCPU_DFL_MAP_ALLOC; + chunk->map[chunk->map_used++] = pcpu_unit_size; + chunk->page = chunk->page_ar; + + chunk->vm = get_vm_area(pcpu_chunk_size, GFP_KERNEL); + if (!chunk->vm) { + free_pcpu_chunk(chunk); + return NULL; + } + + INIT_LIST_HEAD(&chunk->list); + chunk->free_size = pcpu_unit_size; + chunk->contig_hint = pcpu_unit_size; + + return chunk; +} + +/** + * pcpu_alloc - the percpu allocator + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * @reserved: allocate from the reserved chunk if available + * + * Allocate percpu area of @size bytes aligned at @align. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +static void *pcpu_alloc(size_t size, size_t align, bool reserved) +{ + struct pcpu_chunk *chunk; + int slot, off; + + if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) { + WARN(true, "illegal size (%zu) or align (%zu) for " + "percpu allocation\n", size, align); + return NULL; + } + + mutex_lock(&pcpu_alloc_mutex); + spin_lock_irq(&pcpu_lock); + + /* serve reserved allocations from the reserved chunk if available */ + if (reserved && pcpu_reserved_chunk) { + chunk = pcpu_reserved_chunk; + if (size > chunk->contig_hint || + pcpu_extend_area_map(chunk) < 0) + goto fail_unlock; + off = pcpu_alloc_area(chunk, size, align); + if (off >= 0) + goto area_found; + goto fail_unlock; + } + +restart: + /* search through normal chunks */ + for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) { + list_for_each_entry(chunk, &pcpu_slot[slot], list) { + if (size > chunk->contig_hint) + continue; + + switch (pcpu_extend_area_map(chunk)) { + case 0: + break; + case 1: + goto restart; /* pcpu_lock dropped, restart */ + default: + goto fail_unlock; + } + + off = pcpu_alloc_area(chunk, size, align); + if (off >= 0) + goto area_found; + } + } + + /* hmmm... no space left, create a new chunk */ + spin_unlock_irq(&pcpu_lock); + + chunk = alloc_pcpu_chunk(); + if (!chunk) + goto fail_unlock_mutex; + + spin_lock_irq(&pcpu_lock); + pcpu_chunk_relocate(chunk, -1); + pcpu_chunk_addr_insert(chunk); + goto restart; + +area_found: + spin_unlock_irq(&pcpu_lock); + + /* populate, map and clear the area */ + if (pcpu_populate_chunk(chunk, off, size)) { + spin_lock_irq(&pcpu_lock); + pcpu_free_area(chunk, off); + goto fail_unlock; + } + + mutex_unlock(&pcpu_alloc_mutex); + + return __addr_to_pcpu_ptr(chunk->vm->addr + off); + +fail_unlock: + spin_unlock_irq(&pcpu_lock); +fail_unlock_mutex: + mutex_unlock(&pcpu_alloc_mutex); + return NULL; +} + +/** + * __alloc_percpu - allocate dynamic percpu area + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * + * Allocate percpu area of @size bytes aligned at @align. Might + * sleep. Might trigger writeouts. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +void *__alloc_percpu(size_t size, size_t align) +{ + return pcpu_alloc(size, align, false); +} +EXPORT_SYMBOL_GPL(__alloc_percpu); + +/** + * __alloc_reserved_percpu - allocate reserved percpu area + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * + * Allocate percpu area of @size bytes aligned at @align from reserved + * percpu area if arch has set it up; otherwise, allocation is served + * from the same dynamic area. Might sleep. Might trigger writeouts. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +void *__alloc_reserved_percpu(size_t size, size_t align) +{ + return pcpu_alloc(size, align, true); +} + +/** + * pcpu_reclaim - reclaim fully free chunks, workqueue function + * @work: unused + * + * Reclaim all fully free chunks except for the first one. + * + * CONTEXT: + * workqueue context. + */ +static void pcpu_reclaim(struct work_struct *work) +{ + LIST_HEAD(todo); + struct list_head *head = &pcpu_slot[pcpu_nr_slots - 1]; + struct pcpu_chunk *chunk, *next; + + mutex_lock(&pcpu_alloc_mutex); + spin_lock_irq(&pcpu_lock); + + list_for_each_entry_safe(chunk, next, head, list) { + WARN_ON(chunk->immutable); + + /* spare the first one */ + if (chunk == list_first_entry(head, struct pcpu_chunk, list)) + continue; + + rb_erase(&chunk->rb_node, &pcpu_addr_root); + list_move(&chunk->list, &todo); + } + + spin_unlock_irq(&pcpu_lock); + mutex_unlock(&pcpu_alloc_mutex); + + list_for_each_entry_safe(chunk, next, &todo, list) { + pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size, false); + free_pcpu_chunk(chunk); + } +} + +/** + * free_percpu - free percpu area + * @ptr: pointer to area to free + * + * Free percpu area @ptr. + * + * CONTEXT: + * Can be called from atomic context. + */ +void free_percpu(void *ptr) +{ + void *addr = __pcpu_ptr_to_addr(ptr); + struct pcpu_chunk *chunk; + unsigned long flags; + int off; + + if (!ptr) + return; + + spin_lock_irqsave(&pcpu_lock, flags); + + chunk = pcpu_chunk_addr_search(addr); + off = addr - chunk->vm->addr; + + pcpu_free_area(chunk, off); + + /* if there are more than one fully free chunks, wake up grim reaper */ + if (chunk->free_size == pcpu_unit_size) { + struct pcpu_chunk *pos; + + list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list) + if (pos != chunk) { + schedule_work(&pcpu_reclaim_work); + break; + } + } + + spin_unlock_irqrestore(&pcpu_lock, flags); +} +EXPORT_SYMBOL_GPL(free_percpu); + +/** + * pcpu_setup_first_chunk - initialize the first percpu chunk + * @get_page_fn: callback to fetch page pointer + * @static_size: the size of static percpu area in bytes + * @reserved_size: the size of reserved percpu area in bytes + * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto + * @dyn_size: free size for dynamic allocation in bytes, -1 for auto + * @base_addr: mapped address, NULL for auto + * @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary + * + * Initialize the first percpu chunk which contains the kernel static + * perpcu area. This function is to be called from arch percpu area + * setup path. The first two parameters are mandatory. The rest are + * optional. + * + * @get_page_fn() should return pointer to percpu page given cpu + * number and page number. It should at least return enough pages to + * cover the static area. The returned pages for static area should + * have been initialized with valid data. If @unit_size is specified, + * it can also return pages after the static area. NULL return + * indicates end of pages for the cpu. Note that @get_page_fn() must + * return the same number of pages for all cpus. + * + * @reserved_size, if non-zero, specifies the amount of bytes to + * reserve after the static area in the first chunk. This reserves + * the first chunk such that it's available only through reserved + * percpu allocation. This is primarily used to serve module percpu + * static areas on architectures where the addressing model has + * limited offset range for symbol relocations to guarantee module + * percpu symbols fall inside the relocatable range. + * + * @unit_size, if non-negative, specifies unit size and must be + * aligned to PAGE_SIZE and equal to or larger than @static_size + + * @reserved_size + @dyn_size. + * + * @dyn_size, if non-negative, limits the number of bytes available + * for dynamic allocation in the first chunk. Specifying non-negative + * value make percpu leave alone the area beyond @static_size + + * @reserved_size + @dyn_size. + * + * Non-null @base_addr means that the caller already allocated virtual + * region for the first chunk and mapped it. percpu must not mess + * with the chunk. Note that @base_addr with 0 @unit_size or non-NULL + * @populate_pte_fn doesn't make any sense. + * + * @populate_pte_fn is used to populate the pagetable. NULL means the + * caller already populated the pagetable. + * + * If the first chunk ends up with both reserved and dynamic areas, it + * is served by two chunks - one to serve the core static and reserved + * areas and the other for the dynamic area. They share the same vm + * and page map but uses different area allocation map to stay away + * from each other. The latter chunk is circulated in the chunk slots + * and available for dynamic allocation like any other chunks. + * + * RETURNS: + * The determined pcpu_unit_size which can be used to initialize + * percpu access. + */ +size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, + size_t static_size, size_t reserved_size, + ssize_t unit_size, ssize_t dyn_size, + void *base_addr, + pcpu_populate_pte_fn_t populate_pte_fn) +{ + static struct vm_struct first_vm; + static int smap[2], dmap[2]; + struct pcpu_chunk *schunk, *dchunk = NULL; + unsigned int cpu; + int nr_pages; + int err, i; + + /* santiy checks */ + BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC || + ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC); + BUG_ON(!static_size); + if (unit_size >= 0) { + BUG_ON(unit_size < static_size + reserved_size + + (dyn_size >= 0 ? dyn_size : 0)); + BUG_ON(unit_size & ~PAGE_MASK); + } else { + BUG_ON(dyn_size >= 0); + BUG_ON(base_addr); + } + BUG_ON(base_addr && populate_pte_fn); + + if (unit_size >= 0) + pcpu_unit_pages = unit_size >> PAGE_SHIFT; + else + pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT, + PFN_UP(static_size + reserved_size)); + + pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; + pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size; + pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) + + num_possible_cpus() * pcpu_unit_pages * sizeof(struct page *); + + if (dyn_size < 0) + dyn_size = pcpu_unit_size - static_size - reserved_size; + + /* + * Allocate chunk slots. The additional last slot is for + * empty chunks. + */ + pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; + pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0])); + for (i = 0; i < pcpu_nr_slots; i++) + INIT_LIST_HEAD(&pcpu_slot[i]); + + /* + * Initialize static chunk. If reserved_size is zero, the + * static chunk covers static area + dynamic allocation area + * in the first chunk. If reserved_size is not zero, it + * covers static area + reserved area (mostly used for module + * static percpu allocation). + */ + schunk = alloc_bootmem(pcpu_chunk_struct_size); + INIT_LIST_HEAD(&schunk->list); + schunk->vm = &first_vm; + schunk->map = smap; + schunk->map_alloc = ARRAY_SIZE(smap); + schunk->page = schunk->page_ar; + + if (reserved_size) { + schunk->free_size = reserved_size; + pcpu_reserved_chunk = schunk; /* not for dynamic alloc */ + } else { + schunk->free_size = dyn_size; + dyn_size = 0; /* dynamic area covered */ + } + schunk->contig_hint = schunk->free_size; + + schunk->map[schunk->map_used++] = -static_size; + if (schunk->free_size) + schunk->map[schunk->map_used++] = schunk->free_size; + + pcpu_reserved_chunk_limit = static_size + schunk->free_size; + + /* init dynamic chunk if necessary */ + if (dyn_size) { + dchunk = alloc_bootmem(sizeof(struct pcpu_chunk)); + INIT_LIST_HEAD(&dchunk->list); + dchunk->vm = &first_vm; + dchunk->map = dmap; + dchunk->map_alloc = ARRAY_SIZE(dmap); + dchunk->page = schunk->page_ar; /* share page map with schunk */ + + dchunk->contig_hint = dchunk->free_size = dyn_size; + dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit; + dchunk->map[dchunk->map_used++] = dchunk->free_size; + } + + /* allocate vm address */ + first_vm.flags = VM_ALLOC; + first_vm.size = pcpu_chunk_size; + + if (!base_addr) + vm_area_register_early(&first_vm, PAGE_SIZE); + else { + /* + * Pages already mapped. No need to remap into + * vmalloc area. In this case the first chunks can't + * be mapped or unmapped by percpu and are marked + * immutable. + */ + first_vm.addr = base_addr; + schunk->immutable = true; + if (dchunk) + dchunk->immutable = true; + } + + /* assign pages */ + nr_pages = -1; + for_each_possible_cpu(cpu) { + for (i = 0; i < pcpu_unit_pages; i++) { + struct page *page = get_page_fn(cpu, i); + + if (!page) + break; + *pcpu_chunk_pagep(schunk, cpu, i) = page; + } + + BUG_ON(i < PFN_UP(static_size)); + + if (nr_pages < 0) + nr_pages = i; + else + BUG_ON(nr_pages != i); + } + + /* map them */ + if (populate_pte_fn) { + for_each_possible_cpu(cpu) + for (i = 0; i < nr_pages; i++) + populate_pte_fn(pcpu_chunk_addr(schunk, + cpu, i)); + + err = pcpu_map(schunk, 0, nr_pages); + if (err) + panic("failed to setup static percpu area, err=%d\n", + err); + } + + /* link the first chunk in */ + if (!dchunk) { + pcpu_chunk_relocate(schunk, -1); + pcpu_chunk_addr_insert(schunk); + } else { + pcpu_chunk_relocate(dchunk, -1); + pcpu_chunk_addr_insert(dchunk); + } + + /* we're done */ + pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0); + return pcpu_unit_size; +} diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 11a9298..af58324 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -24,6 +24,7 @@ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/bootmem.h> +#include <linux/pfn.h> #include <asm/atomic.h> #include <asm/uaccess.h> @@ -152,8 +153,8 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr, * * Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N] */ -static int vmap_page_range(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages) +static int vmap_page_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages) { pgd_t *pgd; unsigned long next; @@ -169,13 +170,22 @@ static int vmap_page_range(unsigned long start, unsigned long end, if (err) break; } while (pgd++, addr = next, addr != end); - flush_cache_vmap(start, end); if (unlikely(err)) return err; return nr; } +static int vmap_page_range(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages) +{ + int ret; + + ret = vmap_page_range_noflush(start, end, prot, pages); + flush_cache_vmap(start, end); + return ret; +} + static inline int is_vmalloc_or_module_addr(const void *x) { /* @@ -990,6 +1000,32 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro } EXPORT_SYMBOL(vm_map_ram); +/** + * vm_area_register_early - register vmap area early during boot + * @vm: vm_struct to register + * @align: requested alignment + * + * This function is used to register kernel vm area before + * vmalloc_init() is called. @vm->size and @vm->flags should contain + * proper values on entry and other fields should be zero. On return, + * vm->addr contains the allocated address. + * + * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. + */ +void __init vm_area_register_early(struct vm_struct *vm, size_t align) +{ + static size_t vm_init_off __initdata; + unsigned long addr; + + addr = ALIGN(VMALLOC_START + vm_init_off, align); + vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START; + + vm->addr = (void *)addr; + + vm->next = vmlist; + vmlist = vm; +} + void __init vmalloc_init(void) { struct vmap_area *va; @@ -1017,6 +1053,58 @@ void __init vmalloc_init(void) vmap_initialized = true; } +/** + * map_kernel_range_noflush - map kernel VM area with the specified pages + * @addr: start of the VM area to map + * @size: size of the VM area to map + * @prot: page protection flags to use + * @pages: pages to map + * + * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size + * specify should have been allocated using get_vm_area() and its + * friends. + * + * NOTE: + * This function does NOT do any cache flushing. The caller is + * responsible for calling flush_cache_vmap() on to-be-mapped areas + * before calling this function. + * + * RETURNS: + * The number of pages mapped on success, -errno on failure. + */ +int map_kernel_range_noflush(unsigned long addr, unsigned long size, + pgprot_t prot, struct page **pages) +{ + return vmap_page_range_noflush(addr, addr + size, prot, pages); +} + +/** + * unmap_kernel_range_noflush - unmap kernel VM area + * @addr: start of the VM area to unmap + * @size: size of the VM area to unmap + * + * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size + * specify should have been allocated using get_vm_area() and its + * friends. + * + * NOTE: + * This function does NOT do any cache flushing. The caller is + * responsible for calling flush_cache_vunmap() on to-be-mapped areas + * before calling this function and flush_tlb_kernel_range() after. + */ +void unmap_kernel_range_noflush(unsigned long addr, unsigned long size) +{ + vunmap_page_range(addr, addr + size); +} + +/** + * unmap_kernel_range - unmap kernel VM area and flush cache and TLB + * @addr: start of the VM area to unmap + * @size: size of the VM area to unmap + * + * Similar to unmap_kernel_range_noflush() but flushes vcache before + * the unmapping and tlb after. + */ void unmap_kernel_range(unsigned long addr, unsigned long size) { unsigned long end = addr + size; diff --git a/net/802/tr.c b/net/802/tr.c index 158150f..f47ae28 100644 --- a/net/802/tr.c +++ b/net/802/tr.c @@ -668,3 +668,5 @@ module_init(rif_init); EXPORT_SYMBOL(tr_type_trans); EXPORT_SYMBOL(alloc_trdev); + +MODULE_LICENSE("GPL"); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 4a19acd..1b34135 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -553,7 +553,7 @@ static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa) int err = 0; if (netif_device_present(real_dev) && ops->ndo_neigh_setup) - err = ops->ndo_neigh_setup(dev, pa); + err = ops->ndo_neigh_setup(real_dev, pa); return err; } @@ -639,6 +639,7 @@ static int vlan_dev_init(struct net_device *dev) dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN; dev->netdev_ops = &vlan_netdev_ops; } + netdev_resync_ops(dev); if (is_vlan_dev(real_dev)) subclass = 1; diff --git a/net/core/dev.c b/net/core/dev.c index 72b0d26f..f112970 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2267,12 +2267,6 @@ int netif_receive_skb(struct sk_buff *skb) rcu_read_lock(); - /* Don't receive packets in an exiting network namespace */ - if (!net_alive(dev_net(skb->dev))) { - kfree_skb(skb); - goto out; - } - #ifdef CONFIG_NET_CLS_ACT if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); @@ -4288,6 +4282,39 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) } EXPORT_SYMBOL(netdev_fix_features); +/* Some devices need to (re-)set their netdev_ops inside + * ->init() or similar. If that happens, we have to setup + * the compat pointers again. + */ +void netdev_resync_ops(struct net_device *dev) +{ +#ifdef CONFIG_COMPAT_NET_DEV_OPS + const struct net_device_ops *ops = dev->netdev_ops; + + dev->init = ops->ndo_init; + dev->uninit = ops->ndo_uninit; + dev->open = ops->ndo_open; + dev->change_rx_flags = ops->ndo_change_rx_flags; + dev->set_rx_mode = ops->ndo_set_rx_mode; + dev->set_multicast_list = ops->ndo_set_multicast_list; + dev->set_mac_address = ops->ndo_set_mac_address; + dev->validate_addr = ops->ndo_validate_addr; + dev->do_ioctl = ops->ndo_do_ioctl; + dev->set_config = ops->ndo_set_config; + dev->change_mtu = ops->ndo_change_mtu; + dev->neigh_setup = ops->ndo_neigh_setup; + dev->tx_timeout = ops->ndo_tx_timeout; + dev->get_stats = ops->ndo_get_stats; + dev->vlan_rx_register = ops->ndo_vlan_rx_register; + dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid; + dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid; +#ifdef CONFIG_NET_POLL_CONTROLLER + dev->poll_controller = ops->ndo_poll_controller; +#endif +#endif +} +EXPORT_SYMBOL(netdev_resync_ops); + /** * register_netdevice - register a network device * @dev: device to register @@ -4332,27 +4359,7 @@ int register_netdevice(struct net_device *dev) * This is temporary until all network devices are converted. */ if (dev->netdev_ops) { - const struct net_device_ops *ops = dev->netdev_ops; - - dev->init = ops->ndo_init; - dev->uninit = ops->ndo_uninit; - dev->open = ops->ndo_open; - dev->change_rx_flags = ops->ndo_change_rx_flags; - dev->set_rx_mode = ops->ndo_set_rx_mode; - dev->set_multicast_list = ops->ndo_set_multicast_list; - dev->set_mac_address = ops->ndo_set_mac_address; - dev->validate_addr = ops->ndo_validate_addr; - dev->do_ioctl = ops->ndo_do_ioctl; - dev->set_config = ops->ndo_set_config; - dev->change_mtu = ops->ndo_change_mtu; - dev->tx_timeout = ops->ndo_tx_timeout; - dev->get_stats = ops->ndo_get_stats; - dev->vlan_rx_register = ops->ndo_vlan_rx_register; - dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid; - dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid; -#ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = ops->ndo_poll_controller; -#endif + netdev_resync_ops(dev); } else { char drivername[64]; pr_info("%s (%s): not using net_device_ops yet\n", diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 6ac29a4..484f587 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -77,7 +77,9 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, if (endp == buf) goto err; - rtnl_lock(); + if (!rtnl_trylock()) + return -ERESTARTSYS; + if (dev_isalive(net)) { if ((ret = (*set)(net, new)) == 0) ret = len; diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 2adb1a7..e3bebd3 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -157,9 +157,6 @@ static void cleanup_net(struct work_struct *work) struct pernet_operations *ops; struct net *net; - /* Be very certain incoming network packets will not find us */ - rcu_barrier(); - net = container_of(work, struct net, work); mutex_lock(&net_mutex); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 743f554..3a3dad8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1375,10 +1375,10 @@ EXPORT_SYMBOL_GPL(snmp_fold_field); int snmp_mib_init(void *ptr[2], size_t mibsize) { BUG_ON(ptr == NULL); - ptr[0] = __alloc_percpu(mibsize); + ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long long)); if (!ptr[0]) goto err0; - ptr[1] = __alloc_percpu(mibsize); + ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long long)); if (!ptr[1]) goto err1; return 0; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 705b33b..fc562d2 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -1205,7 +1205,7 @@ static struct pernet_operations __net_initdata icmp_sk_ops = { int __init icmp_init(void) { - return register_pernet_device(&icmp_sk_ops); + return register_pernet_subsys(&icmp_sk_ops); } EXPORT_SYMBOL(icmp_err_convert); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 97f7115..bf89540 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3376,7 +3376,7 @@ int __init ip_rt_init(void) int rc = 0; #ifdef CONFIG_NET_CLS_ROUTE - ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct)); + ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) panic("IP: failed to allocate ip_rt_acct\n"); #endif diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 19d7b42..cf74c41 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2443,7 +2443,7 @@ static struct pernet_operations __net_initdata tcp_sk_ops = { void __init tcp_v4_init(void) { inet_hashinfo_init(&tcp_hashinfo); - if (register_pernet_device(&tcp_sk_ops)) + if (register_pernet_subsys(&tcp_sk_ops)) panic("Failed to create the TCP control socket.\n"); } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f9afb45..1220e2c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -493,15 +493,17 @@ static void addrconf_forward_change(struct net *net, __s32 newf) read_unlock(&dev_base_lock); } -static void addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) +static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) { struct net *net; net = (struct net *)table->extra2; if (p == &net->ipv6.devconf_dflt->forwarding) - return; + return 0; + + if (!rtnl_trylock()) + return -ERESTARTSYS; - rtnl_lock(); if (p == &net->ipv6.devconf_all->forwarding) { __s32 newf = net->ipv6.devconf_all->forwarding; net->ipv6.devconf_dflt->forwarding = newf; @@ -512,6 +514,7 @@ static void addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) if (*p) rt6_purge_dflt_routers(net); + return 1; } #endif @@ -2608,9 +2611,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) ASSERT_RTNL(); - if ((dev->flags & IFF_LOOPBACK) && how == 1) - how = 0; - rt6_ifdown(net, dev); neigh_ifdown(&nd_tbl, dev); @@ -3983,7 +3983,7 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write, struct file * filp, ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); if (write) - addrconf_fixup_forwarding(ctl, valp, val); + ret = addrconf_fixup_forwarding(ctl, valp, val); return ret; } @@ -4019,8 +4019,7 @@ static int addrconf_sysctl_forward_strategy(ctl_table *table, } *valp = new; - addrconf_fixup_forwarding(table, valp, val); - return 1; + return addrconf_fixup_forwarding(table, valp, val); } static struct addrconf_sysctl_table @@ -4446,25 +4445,6 @@ int unregister_inet6addr_notifier(struct notifier_block *nb) EXPORT_SYMBOL(unregister_inet6addr_notifier); -static void addrconf_net_exit(struct net *net) -{ - struct net_device *dev; - - rtnl_lock(); - /* clean dev list */ - for_each_netdev(net, dev) { - if (__in6_dev_get(dev) == NULL) - continue; - addrconf_ifdown(dev, 1); - } - addrconf_ifdown(net->loopback_dev, 2); - rtnl_unlock(); -} - -static struct pernet_operations addrconf_net_ops = { - .exit = addrconf_net_exit, -}; - /* * Init / cleanup code */ @@ -4506,10 +4486,6 @@ int __init addrconf_init(void) if (err) goto errlo; - err = register_pernet_device(&addrconf_net_ops); - if (err) - return err; - register_netdevice_notifier(&ipv6_dev_notf); addrconf_verify(0); @@ -4539,15 +4515,22 @@ errlo: void addrconf_cleanup(void) { struct inet6_ifaddr *ifa; + struct net_device *dev; int i; unregister_netdevice_notifier(&ipv6_dev_notf); - unregister_pernet_device(&addrconf_net_ops); - unregister_pernet_subsys(&addrconf_ops); rtnl_lock(); + /* clean dev list */ + for_each_netdev(&init_net, dev) { + if (__in6_dev_get(dev) == NULL) + continue; + addrconf_ifdown(dev, 1); + } + addrconf_ifdown(init_net.loopback_dev, 2); + /* * Check hash table. */ @@ -4568,6 +4551,4 @@ void addrconf_cleanup(void) del_timer(&addr_chk_timer); rtnl_unlock(); - - unregister_pernet_subsys(&addrconf_net_ops); } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index c802bc1..da944ec 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -72,6 +72,10 @@ MODULE_LICENSE("GPL"); static struct list_head inetsw6[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw6_lock); +static int disable_ipv6 = 0; +module_param_named(disable, disable_ipv6, int, 0); +MODULE_PARM_DESC(disable, "Disable IPv6 such that it is non-functional"); + static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) { const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo); @@ -991,10 +995,21 @@ static int __init inet6_init(void) { struct sk_buff *dummy_skb; struct list_head *r; - int err; + int err = 0; BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb)); + /* Register the socket-side information for inet6_create. */ + for(r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) + INIT_LIST_HEAD(r); + + if (disable_ipv6) { + printk(KERN_INFO + "IPv6: Loaded, but administratively disabled, " + "reboot required to enable\n"); + goto out; + } + err = proto_register(&tcpv6_prot, 1); if (err) goto out; @@ -1012,10 +1027,6 @@ static int __init inet6_init(void) goto out_unregister_udplite_proto; - /* Register the socket-side information for inet6_create. */ - for(r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) - INIT_LIST_HEAD(r); - /* We MUST register RAW sockets before we create the ICMP6, * IGMP6, or NDISC control sockets. */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 9eb895c..3ae3cb8 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1084,6 +1084,13 @@ out: return 0; } +/** + * netlink_set_err - report error to broadcast listeners + * @ssk: the kernel netlink socket, as returned by netlink_kernel_create() + * @pid: the PID of a process that we want to skip (if any) + * @groups: the broadcast group that will notice the error + * @code: error code, must be negative (as usual in kernelspace) + */ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code) { struct netlink_set_err_data info; @@ -1093,7 +1100,8 @@ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code) info.exclude_sk = ssk; info.pid = pid; info.group = group; - info.code = code; + /* sk->sk_err wants a positive error value */ + info.code = -code; read_lock(&nl_table_lock); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 5c72a11..f8f047b 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -183,13 +183,6 @@ override: if (R_tab == NULL) goto failure; - if (!est && (ret == ACT_P_CREATED || - !gen_estimator_active(&police->tcf_bstats, - &police->tcf_rate_est))) { - err = -EINVAL; - goto failure; - } - if (parm->peakrate.rate) { P_tab = qdisc_get_rtab(&parm->peakrate, tb[TCA_POLICE_PEAKRATE]); @@ -205,6 +198,12 @@ override: &police->tcf_lock, est); if (err) goto failure_unlock; + } else if (tb[TCA_POLICE_AVRATE] && + (ret == ACT_P_CREATED || + !gen_estimator_active(&police->tcf_bstats, + &police->tcf_rate_est))) { + err = -EINVAL; + goto failure_unlock; } /* No failure allowed after this point */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index b78e3be..c4986d0 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -717,15 +717,20 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, static int sctp_ctl_sock_init(void) { int err; - sa_family_t family; + sa_family_t family = PF_INET; if (sctp_get_pf_specific(PF_INET6)) family = PF_INET6; - else - family = PF_INET; err = inet_ctl_sock_create(&sctp_ctl_sock, family, SOCK_SEQPACKET, IPPROTO_SCTP, &init_net); + + /* If IPv6 socket could not be created, try the IPv4 socket */ + if (err < 0 && family == PF_INET6) + err = inet_ctl_sock_create(&sctp_ctl_sock, AF_INET, + SOCK_SEQPACKET, IPPROTO_SCTP, + &init_net); + if (err < 0) { printk(KERN_ERR "SCTP: Failed to create the SCTP control socket.\n"); @@ -1322,9 +1327,8 @@ SCTP_STATIC __init int sctp_init(void) out: return status; err_v6_add_protocol: - sctp_v6_del_protocol(); -err_add_protocol: sctp_v4_del_protocol(); +err_add_protocol: inet_ctl_sock_destroy(sctp_ctl_sock); err_ctl_sock_init: sctp_v6_protosw_exit(); @@ -1335,7 +1339,6 @@ err_protosw_init: sctp_v4_pf_exit(); sctp_v6_pf_exit(); sctp_sysctl_unregister(); - list_del(&sctp_af_inet.list); free_pages((unsigned long)sctp_port_hashtable, get_order(sctp_port_hashsize * sizeof(struct sctp_bind_hashbucket))); @@ -1383,7 +1386,6 @@ SCTP_STATIC __exit void sctp_exit(void) sctp_v4_pf_exit(); sctp_sysctl_unregister(); - list_del(&sctp_af_inet.list); free_pages((unsigned long)sctp_assoc_hashtable, get_order(sctp_assoc_hashsize * diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index e1d6076..b5495ae 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -787,36 +787,48 @@ static void sctp_cmd_process_operr(sctp_cmd_seq_t *cmds, struct sctp_association *asoc, struct sctp_chunk *chunk) { - struct sctp_operr_chunk *operr_chunk; struct sctp_errhdr *err_hdr; + struct sctp_ulpevent *ev; - operr_chunk = (struct sctp_operr_chunk *)chunk->chunk_hdr; - err_hdr = &operr_chunk->err_hdr; + while (chunk->chunk_end > chunk->skb->data) { + err_hdr = (struct sctp_errhdr *)(chunk->skb->data); - switch (err_hdr->cause) { - case SCTP_ERROR_UNKNOWN_CHUNK: - { - struct sctp_chunkhdr *unk_chunk_hdr; + ev = sctp_ulpevent_make_remote_error(asoc, chunk, 0, + GFP_ATOMIC); + if (!ev) + return; - unk_chunk_hdr = (struct sctp_chunkhdr *)err_hdr->variable; - switch (unk_chunk_hdr->type) { - /* ADDIP 4.1 A9) If the peer responds to an ASCONF with an - * ERROR chunk reporting that it did not recognized the ASCONF - * chunk type, the sender of the ASCONF MUST NOT send any - * further ASCONF chunks and MUST stop its T-4 timer. - */ - case SCTP_CID_ASCONF: - asoc->peer.asconf_capable = 0; - sctp_add_cmd_sf(cmds, SCTP_CMD_TIMER_STOP, + sctp_ulpq_tail_event(&asoc->ulpq, ev); + + switch (err_hdr->cause) { + case SCTP_ERROR_UNKNOWN_CHUNK: + { + sctp_chunkhdr_t *unk_chunk_hdr; + + unk_chunk_hdr = (sctp_chunkhdr_t *)err_hdr->variable; + switch (unk_chunk_hdr->type) { + /* ADDIP 4.1 A9) If the peer responds to an ASCONF with + * an ERROR chunk reporting that it did not recognized + * the ASCONF chunk type, the sender of the ASCONF MUST + * NOT send any further ASCONF chunks and MUST stop its + * T-4 timer. + */ + case SCTP_CID_ASCONF: + if (asoc->peer.asconf_capable == 0) + break; + + asoc->peer.asconf_capable = 0; + sctp_add_cmd_sf(cmds, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); + break; + default: + break; + } break; + } default: break; } - break; - } - default: - break; } } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 3a0cd07..f88dfde 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3163,7 +3163,6 @@ sctp_disposition_t sctp_sf_operr_notify(const struct sctp_endpoint *ep, sctp_cmd_seq_t *commands) { struct sctp_chunk *chunk = arg; - struct sctp_ulpevent *ev; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(ep, asoc, type, arg, commands); @@ -3173,21 +3172,10 @@ sctp_disposition_t sctp_sf_operr_notify(const struct sctp_endpoint *ep, return sctp_sf_violation_chunklen(ep, asoc, type, arg, commands); - while (chunk->chunk_end > chunk->skb->data) { - ev = sctp_ulpevent_make_remote_error(asoc, chunk, 0, - GFP_ATOMIC); - if (!ev) - goto nomem; + sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_OPERR, + SCTP_CHUNK(chunk)); - sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, - SCTP_ULPEVENT(ev)); - sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_OPERR, - SCTP_CHUNK(chunk)); - } return SCTP_DISPOSITION_CONSUME; - -nomem: - return SCTP_DISPOSITION_NOMEM; } /* diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 85c9034..bd0a16c 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -380,7 +380,8 @@ static bool is_valid_reg_rule(const struct ieee80211_reg_rule *rule) freq_diff = freq_range->end_freq_khz - freq_range->start_freq_khz; - if (freq_diff <= 0 || freq_range->max_bandwidth_khz > freq_diff) + if (freq_range->end_freq_khz <= freq_range->start_freq_khz || + freq_range->max_bandwidth_khz > freq_diff) return false; return true; diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 0278bc0..e7ded13 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1498,58 +1498,31 @@ static int smack_socket_post_create(struct socket *sock, int family, * looks for host based access restrictions * * This version will only be appropriate for really small - * sets of single label hosts. Because of the masking - * it cannot shortcut out on the first match. There are - * numerious ways to address the problem, but none of them - * have been applied here. + * sets of single label hosts. * * Returns the label of the far end or NULL if it's not special. */ static char *smack_host_label(struct sockaddr_in *sip) { struct smk_netlbladdr *snp; - char *bestlabel = NULL; struct in_addr *siap = &sip->sin_addr; - struct in_addr *liap; - struct in_addr *miap; - struct in_addr bestmask; if (siap->s_addr == 0) return NULL; - bestmask.s_addr = 0; - for (snp = smack_netlbladdrs; snp != NULL; snp = snp->smk_next) { - liap = &snp->smk_host.sin_addr; - miap = &snp->smk_mask; - /* - * If the addresses match after applying the list entry mask - * the entry matches the address. If it doesn't move along to - * the next entry. - */ - if ((liap->s_addr & miap->s_addr) != - (siap->s_addr & miap->s_addr)) - continue; /* - * If the list entry mask identifies a single address - * it can't get any more specific. + * we break after finding the first match because + * the list is sorted from longest to shortest mask + * so we have found the most specific match */ - if (miap->s_addr == 0xffffffff) + if ((&snp->smk_host.sin_addr)->s_addr == + (siap->s_addr & (&snp->smk_mask)->s_addr)) { return snp->smk_label; - /* - * If the list entry mask is less specific than the best - * already found this entry is uninteresting. - */ - if ((miap->s_addr | bestmask.s_addr) == bestmask.s_addr) - continue; - /* - * This is better than any entry found so far. - */ - bestmask.s_addr = miap->s_addr; - bestlabel = snp->smk_label; + } } - return bestlabel; + return NULL; } /** diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index 8e42800..51f0efc 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -650,10 +650,6 @@ static void *netlbladdr_seq_next(struct seq_file *s, void *v, loff_t *pos) return skp; } -/* -#define BEMASK 0x80000000 -*/ -#define BEMASK 0x00000001 #define BEBITS (sizeof(__be32) * 8) /* @@ -663,12 +659,10 @@ static int netlbladdr_seq_show(struct seq_file *s, void *v) { struct smk_netlbladdr *skp = (struct smk_netlbladdr *) v; unsigned char *hp = (char *) &skp->smk_host.sin_addr.s_addr; - __be32 bebits; - int maskn = 0; + int maskn; + u32 temp_mask = be32_to_cpu(skp->smk_mask.s_addr); - for (bebits = BEMASK; bebits != 0; maskn++, bebits <<= 1) - if ((skp->smk_mask.s_addr & bebits) == 0) - break; + for (maskn = 0; temp_mask; temp_mask <<= 1, maskn++); seq_printf(s, "%u.%u.%u.%u/%d %s\n", hp[0], hp[1], hp[2], hp[3], maskn, skp->smk_label); @@ -702,6 +696,42 @@ static int smk_open_netlbladdr(struct inode *inode, struct file *file) } /** + * smk_netlbladdr_insert + * @new : netlabel to insert + * + * This helper insert netlabel in the smack_netlbladdrs list + * sorted by netmask length (longest to smallest) + */ +static void smk_netlbladdr_insert(struct smk_netlbladdr *new) +{ + struct smk_netlbladdr *m; + + if (smack_netlbladdrs == NULL) { + smack_netlbladdrs = new; + return; + } + + /* the comparison '>' is a bit hacky, but works */ + if (new->smk_mask.s_addr > smack_netlbladdrs->smk_mask.s_addr) { + new->smk_next = smack_netlbladdrs; + smack_netlbladdrs = new; + return; + } + for (m = smack_netlbladdrs; m != NULL; m = m->smk_next) { + if (m->smk_next == NULL) { + m->smk_next = new; + return; + } + if (new->smk_mask.s_addr > m->smk_next->smk_mask.s_addr) { + new->smk_next = m->smk_next; + m->smk_next = new; + return; + } + } +} + + +/** * smk_write_netlbladdr - write() for /smack/netlabel * @filp: file pointer, not actually used * @buf: where to get the data from @@ -724,8 +754,9 @@ static ssize_t smk_write_netlbladdr(struct file *file, const char __user *buf, struct netlbl_audit audit_info; struct in_addr mask; unsigned int m; - __be32 bebits = BEMASK; + u32 mask_bits = (1<<31); __be32 nsa; + u32 temp_mask; /* * Must have privilege. @@ -761,10 +792,13 @@ static ssize_t smk_write_netlbladdr(struct file *file, const char __user *buf, if (sp == NULL) return -EINVAL; - for (mask.s_addr = 0; m > 0; m--) { - mask.s_addr |= bebits; - bebits <<= 1; + for (temp_mask = 0; m > 0; m--) { + temp_mask |= mask_bits; + mask_bits >>= 1; } + mask.s_addr = cpu_to_be32(temp_mask); + + newname.sin_addr.s_addr &= mask.s_addr; /* * Only allow one writer at a time. Writes should be * quite rare and small in any case. @@ -772,6 +806,7 @@ static ssize_t smk_write_netlbladdr(struct file *file, const char __user *buf, mutex_lock(&smk_netlbladdr_lock); nsa = newname.sin_addr.s_addr; + /* try to find if the prefix is already in the list */ for (skp = smack_netlbladdrs; skp != NULL; skp = skp->smk_next) if (skp->smk_host.sin_addr.s_addr == nsa && skp->smk_mask.s_addr == mask.s_addr) @@ -787,9 +822,8 @@ static ssize_t smk_write_netlbladdr(struct file *file, const char __user *buf, rc = 0; skp->smk_host.sin_addr.s_addr = newname.sin_addr.s_addr; skp->smk_mask.s_addr = mask.s_addr; - skp->smk_next = smack_netlbladdrs; skp->smk_label = sp; - smack_netlbladdrs = skp; + smk_netlbladdr_insert(skp); } } else { rc = netlbl_cfg_unlbl_static_del(&init_net, NULL, diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 3bc4276..6094344 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -1207,7 +1207,7 @@ static const char *slave_vols[] = { "LFE Playback Volume", "Side Playback Volume", "Headphone Playback Volume", - "Headphone Playback Volume", + "Headphone2 Playback Volume", "Speaker Playback Volume", "External Speaker Playback Volume", "Speaker2 Playback Volume", @@ -1221,7 +1221,7 @@ static const char *slave_sws[] = { "LFE Playback Switch", "Side Playback Switch", "Headphone Playback Switch", - "Headphone Playback Switch", + "Headphone2 Playback Switch", "Speaker Playback Switch", "External Speaker Playback Switch", "Speaker2 Playback Switch", @@ -3516,6 +3516,7 @@ static int stac92xx_parse_auto_config(struct hda_codec *codec, hda_nid_t dig_out if (! spec->autocfg.line_outs) return 0; /* can't find valid pin config */ +#if 0 /* FIXME: temporarily disabled */ /* If we have no real line-out pin and multiple hp-outs, HPs should * be set up as multi-channel outputs. */ @@ -3535,6 +3536,7 @@ static int stac92xx_parse_auto_config(struct hda_codec *codec, hda_nid_t dig_out spec->autocfg.line_out_type = AUTO_PIN_HP_OUT; spec->autocfg.hp_outs = 0; } +#endif /* FIXME: temporarily disabled */ if (spec->autocfg.mono_out_pin) { int dir = get_wcaps(codec, spec->autocfg.mono_out_pin) & (AC_WCAP_OUT_AMP | AC_WCAP_IN_AMP); |