diff options
Diffstat (limited to 'arch')
55 files changed, 1284 insertions, 703 deletions
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 9503a4be40f6..63e77e3944ce 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -145,27 +145,24 @@ SYSCALL_DEFINE4(osf_getdirentries, unsigned int, fd, long __user *, basep) { int error; - struct file *file; + struct fd arg = fdget(fd); struct osf_dirent_callback buf; - error = -EBADF; - file = fget(fd); - if (!file) - goto out; + if (!arg.file) + return -EBADF; buf.dirent = dirent; buf.basep = basep; buf.count = count; buf.error = 0; - error = vfs_readdir(file, osf_filldir, &buf); + error = vfs_readdir(arg.file, osf_filldir, &buf); if (error >= 0) error = buf.error; if (count != buf.count) error = count - buf.count; - fput(file); - out: + fdput(arg); return error; } diff --git a/arch/arm/boot/dts/highbank.dts b/arch/arm/boot/dts/highbank.dts index 9fecf1ae777b..0c6fc34821f9 100644 --- a/arch/arm/boot/dts/highbank.dts +++ b/arch/arm/boot/dts/highbank.dts @@ -121,6 +121,10 @@ compatible = "calxeda,hb-ahci"; reg = <0xffe08000 0x10000>; interrupts = <0 83 4>; + calxeda,port-phys = <&combophy5 0 &combophy0 0 + &combophy0 1 &combophy0 2 + &combophy0 3>; + dma-coherent; }; sdhci@ffe0e000 { @@ -306,5 +310,19 @@ reg = <0xfff51000 0x1000>; interrupts = <0 80 4 0 81 4 0 82 4>; }; + + combophy0: combo-phy@fff58000 { + compatible = "calxeda,hb-combophy"; + #phy-cells = <1>; + reg = <0xfff58000 0x1000>; + phydev = <5>; + }; + + combophy5: combo-phy@fff5d000 { + compatible = "calxeda,hb-combophy"; + #phy-cells = <1>; + reg = <0xfff5d000 0x1000>; + phydev = <31>; + }; }; }; diff --git a/arch/arm/configs/sam9_l9260_defconfig b/arch/arm/configs/sam9_l9260_defconfig index ecf2531523a1..b4384af1bea6 100644 --- a/arch/arm/configs/sam9_l9260_defconfig +++ b/arch/arm/configs/sam9_l9260_defconfig @@ -39,7 +39,7 @@ CONFIG_MTD_NAND=y CONFIG_MTD_NAND_ATMEL=y CONFIG_MTD_NAND_PLATFORM=y CONFIG_MTD_UBI=y -CONFIG_MTD_UBI_BEB_RESERVE=3 +CONFIG_MTD_UBI_BEB_LIMIT=25 CONFIG_MTD_UBI_GLUEBI=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h index 05112380dc53..8dcd9c702d90 100644 --- a/arch/arm/include/asm/barrier.h +++ b/arch/arm/include/asm/barrier.h @@ -44,10 +44,9 @@ #define rmb() dsb() #define wmb() mb() #else -#include <asm/memory.h> -#define mb() do { if (arch_is_coherent()) dmb(); else barrier(); } while (0) -#define rmb() do { if (arch_is_coherent()) dmb(); else barrier(); } while (0) -#define wmb() do { if (arch_is_coherent()) dmb(); else barrier(); } while (0) +#define mb() barrier() +#define rmb() barrier() +#define wmb() barrier() #endif #ifndef CONFIG_SMP diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 5c44dcb0987b..23004847bb05 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -13,6 +13,7 @@ #define DMA_ERROR_CODE (~0) extern struct dma_map_ops arm_dma_ops; +extern struct dma_map_ops arm_coherent_dma_ops; static inline struct dma_map_ops *get_dma_ops(struct device *dev) { diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 5f6ddcc56452..73cf03aa981e 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -275,14 +275,6 @@ static inline __deprecated void *bus_to_virt(unsigned long x) #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) #define virt_addr_valid(kaddr) ((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory) -/* - * Optional coherency support. Currently used only by selected - * Intel XSC3-based systems. - */ -#ifndef arch_is_coherent -#define arch_is_coherent() 0 -#endif - #endif #include <asm-generic/memory_model.h> diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index aa4ffe6e5ecf..dea7a925c7e2 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -24,6 +24,7 @@ #include <linux/percpu.h> #include <linux/clockchips.h> #include <linux/completion.h> +#include <linux/cpufreq.h> #include <linux/atomic.h> #include <asm/smp.h> @@ -650,3 +651,56 @@ int setup_profiling_timer(unsigned int multiplier) { return -EINVAL; } + +#ifdef CONFIG_CPU_FREQ + +static DEFINE_PER_CPU(unsigned long, l_p_j_ref); +static DEFINE_PER_CPU(unsigned long, l_p_j_ref_freq); +static unsigned long global_l_p_j_ref; +static unsigned long global_l_p_j_ref_freq; + +static int cpufreq_callback(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct cpufreq_freqs *freq = data; + int cpu = freq->cpu; + + if (freq->flags & CPUFREQ_CONST_LOOPS) + return NOTIFY_OK; + + if (!per_cpu(l_p_j_ref, cpu)) { + per_cpu(l_p_j_ref, cpu) = + per_cpu(cpu_data, cpu).loops_per_jiffy; + per_cpu(l_p_j_ref_freq, cpu) = freq->old; + if (!global_l_p_j_ref) { + global_l_p_j_ref = loops_per_jiffy; + global_l_p_j_ref_freq = freq->old; + } + } + + if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) || + (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) || + (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) { + loops_per_jiffy = cpufreq_scale(global_l_p_j_ref, + global_l_p_j_ref_freq, + freq->new); + per_cpu(cpu_data, cpu).loops_per_jiffy = + cpufreq_scale(per_cpu(l_p_j_ref, cpu), + per_cpu(l_p_j_ref_freq, cpu), + freq->new); + } + return NOTIFY_OK; +} + +static struct notifier_block cpufreq_notifier = { + .notifier_call = cpufreq_callback, +}; + +static int __init register_cpufreq_notifier(void) +{ + return cpufreq_register_notifier(&cpufreq_notifier, + CPUFREQ_TRANSITION_NOTIFIER); +} +core_initcall(register_cpufreq_notifier); + +#endif diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c index af1da34ccf9d..40e36a50304c 100644 --- a/arch/arm/mach-highbank/highbank.c +++ b/arch/arm/mach-highbank/highbank.c @@ -15,6 +15,7 @@ */ #include <linux/clk.h> #include <linux/clkdev.h> +#include <linux/dma-mapping.h> #include <linux/io.h> #include <linux/irq.h> #include <linux/irqdomain.h> @@ -23,6 +24,7 @@ #include <linux/of_platform.h> #include <linux/of_address.h> #include <linux/smp.h> +#include <linux/amba/bus.h> #include <asm/cacheflush.h> #include <asm/smp_plat.h> @@ -149,11 +151,61 @@ static void highbank_power_off(void) cpu_do_idle(); } +static int highbank_platform_notifier(struct notifier_block *nb, + unsigned long event, void *__dev) +{ + struct resource *res; + int reg = -1; + struct device *dev = __dev; + + if (event != BUS_NOTIFY_ADD_DEVICE) + return NOTIFY_DONE; + + if (of_device_is_compatible(dev->of_node, "calxeda,hb-ahci")) + reg = 0xc; + else if (of_device_is_compatible(dev->of_node, "calxeda,hb-sdhci")) + reg = 0x18; + else if (of_device_is_compatible(dev->of_node, "arm,pl330")) + reg = 0x20; + else if (of_device_is_compatible(dev->of_node, "calxeda,hb-xgmac")) { + res = platform_get_resource(to_platform_device(dev), + IORESOURCE_MEM, 0); + if (res) { + if (res->start == 0xfff50000) + reg = 0; + else if (res->start == 0xfff51000) + reg = 4; + } + } + + if (reg < 0) + return NOTIFY_DONE; + + if (of_property_read_bool(dev->of_node, "dma-coherent")) { + writel(0xff31, sregs_base + reg); + set_dma_ops(dev, &arm_coherent_dma_ops); + } else + writel(0, sregs_base + reg); + + return NOTIFY_OK; +} + +static struct notifier_block highbank_amba_nb = { + .notifier_call = highbank_platform_notifier, +}; + +static struct notifier_block highbank_platform_nb = { + .notifier_call = highbank_platform_notifier, +}; + static void __init highbank_init(void) { pm_power_off = highbank_power_off; highbank_pm_init(); + bus_register_notifier(&platform_bus_type, &highbank_platform_nb); + bus_register_notifier(&amba_bustype, &highbank_amba_nb); + of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); } diff --git a/arch/arm/mach-shmobile/Makefile b/arch/arm/mach-shmobile/Makefile index 0df5ae6740c6..fe2c97c179d1 100644 --- a/arch/arm/mach-shmobile/Makefile +++ b/arch/arm/mach-shmobile/Makefile @@ -3,7 +3,7 @@ # # Common objects -obj-y := timer.o console.o clock.o common.o +obj-y := timer.o console.o clock.o # CPU objects obj-$(CONFIG_ARCH_SH7367) += setup-sh7367.o clock-sh7367.o intc-sh7367.o diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c index bc3b5da59e25..790dc68c4312 100644 --- a/arch/arm/mach-shmobile/board-ap4evb.c +++ b/arch/arm/mach-shmobile/board-ap4evb.c @@ -1231,6 +1231,15 @@ static struct i2c_board_info i2c1_devices[] = { #define USCCR1 IOMEM(0xE6058144) static void __init ap4evb_init(void) { + struct pm_domain_device domain_devices[] = { + { "A4LC", &lcdc1_device, }, + { "A4LC", &lcdc_device, }, + { "A4MP", &fsi_device, }, + { "A3SP", &sh_mmcif_device, }, + { "A3SP", &sdhi0_device, }, + { "A3SP", &sdhi1_device, }, + { "A4R", &ceu_device, }, + }; u32 srcr4; struct clk *clk; @@ -1463,14 +1472,8 @@ static void __init ap4evb_init(void) platform_add_devices(ap4evb_devices, ARRAY_SIZE(ap4evb_devices)); - rmobile_add_device_to_domain(&sh7372_pd_a4lc, &lcdc1_device); - rmobile_add_device_to_domain(&sh7372_pd_a4lc, &lcdc_device); - rmobile_add_device_to_domain(&sh7372_pd_a4mp, &fsi_device); - - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sh_mmcif_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sdhi0_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sdhi1_device); - rmobile_add_device_to_domain(&sh7372_pd_a4r, &ceu_device); + rmobile_add_devices_to_domains(domain_devices, + ARRAY_SIZE(domain_devices)); hdmi_init_pm_clock(); fsi_init_pm_clock(); @@ -1485,6 +1488,6 @@ MACHINE_START(AP4EVB, "ap4evb") .init_irq = sh7372_init_irq, .handle_irq = shmobile_handle_irq_intc, .init_machine = ap4evb_init, - .init_late = shmobile_init_late, + .init_late = sh7372_pm_init_late, .timer = &shmobile_timer, MACHINE_END diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c index c6593d394273..2912eab3b967 100644 --- a/arch/arm/mach-shmobile/board-armadillo800eva.c +++ b/arch/arm/mach-shmobile/board-armadillo800eva.c @@ -1209,10 +1209,10 @@ static void __init eva_init(void) eva_clock_init(); - rmobile_add_device_to_domain(&r8a7740_pd_a4lc, &lcdc0_device); - rmobile_add_device_to_domain(&r8a7740_pd_a4lc, &hdmi_lcdc_device); + rmobile_add_device_to_domain("A4LC", &lcdc0_device); + rmobile_add_device_to_domain("A4LC", &hdmi_lcdc_device); if (usb) - rmobile_add_device_to_domain(&r8a7740_pd_a3sp, usb); + rmobile_add_device_to_domain("A3SP", usb); } static void __init eva_earlytimer_init(void) diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c index 62783b5d8813..0c27c810cf99 100644 --- a/arch/arm/mach-shmobile/board-mackerel.c +++ b/arch/arm/mach-shmobile/board-mackerel.c @@ -1412,6 +1412,22 @@ static struct i2c_board_info i2c1_devices[] = { #define USCCR1 IOMEM(0xE6058144) static void __init mackerel_init(void) { + struct pm_domain_device domain_devices[] = { + { "A4LC", &lcdc_device, }, + { "A4LC", &hdmi_lcdc_device, }, + { "A4LC", &meram_device, }, + { "A4MP", &fsi_device, }, + { "A3SP", &usbhs0_device, }, + { "A3SP", &usbhs1_device, }, + { "A3SP", &nand_flash_device, }, + { "A3SP", &sh_mmcif_device, }, + { "A3SP", &sdhi0_device, }, +#if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE) + { "A3SP", &sdhi1_device, }, +#endif + { "A3SP", &sdhi2_device, }, + { "A4R", &ceu_device, }, + }; u32 srcr4; struct clk *clk; @@ -1626,20 +1642,8 @@ static void __init mackerel_init(void) platform_add_devices(mackerel_devices, ARRAY_SIZE(mackerel_devices)); - rmobile_add_device_to_domain(&sh7372_pd_a4lc, &lcdc_device); - rmobile_add_device_to_domain(&sh7372_pd_a4lc, &hdmi_lcdc_device); - rmobile_add_device_to_domain(&sh7372_pd_a4lc, &meram_device); - rmobile_add_device_to_domain(&sh7372_pd_a4mp, &fsi_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &usbhs0_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &usbhs1_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &nand_flash_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sh_mmcif_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sdhi0_device); -#if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE) - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sdhi1_device); -#endif - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sdhi2_device); - rmobile_add_device_to_domain(&sh7372_pd_a4r, &ceu_device); + rmobile_add_devices_to_domains(domain_devices, + ARRAY_SIZE(domain_devices)); hdmi_init_pm_clock(); sh7372_pm_init(); @@ -1653,6 +1657,6 @@ MACHINE_START(MACKEREL, "mackerel") .init_irq = sh7372_init_irq, .handle_irq = shmobile_handle_irq_intc, .init_machine = mackerel_init, - .init_late = shmobile_init_late, + .init_late = sh7372_pm_init_late, .timer = &shmobile_timer, MACHINE_END diff --git a/arch/arm/mach-shmobile/common.c b/arch/arm/mach-shmobile/common.c deleted file mode 100644 index 608aba9d60d7..000000000000 --- a/arch/arm/mach-shmobile/common.c +++ /dev/null @@ -1,24 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - */ -#include <linux/kernel.h> -#include <linux/init.h> -#include <mach/common.h> - -void __init shmobile_init_late(void) -{ - shmobile_suspend_init(); - shmobile_cpuidle_init(); -} diff --git a/arch/arm/mach-shmobile/cpuidle.c b/arch/arm/mach-shmobile/cpuidle.c index 7b541e911ab4..9e050268cde4 100644 --- a/arch/arm/mach-shmobile/cpuidle.c +++ b/arch/arm/mach-shmobile/cpuidle.c @@ -16,51 +16,38 @@ #include <asm/cpuidle.h> #include <asm/io.h> -static void shmobile_enter_wfi(void) +int shmobile_enter_wfi(struct cpuidle_device *dev, struct cpuidle_driver *drv, + int index) { cpu_do_idle(); -} - -void (*shmobile_cpuidle_modes[CPUIDLE_STATE_MAX])(void) = { - shmobile_enter_wfi, /* regular sleep mode */ -}; - -static int shmobile_cpuidle_enter(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) -{ - shmobile_cpuidle_modes[index](); - - return index; + return 0; } static struct cpuidle_device shmobile_cpuidle_dev; -static struct cpuidle_driver shmobile_cpuidle_driver = { +static struct cpuidle_driver shmobile_cpuidle_default_driver = { .name = "shmobile_cpuidle", .owner = THIS_MODULE, .en_core_tk_irqen = 1, .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[0].enter = shmobile_enter_wfi, .safe_state_index = 0, /* C1 */ .state_count = 1, }; -void (*shmobile_cpuidle_setup)(struct cpuidle_driver *drv); +static struct cpuidle_driver *cpuidle_drv = &shmobile_cpuidle_default_driver; + +void shmobile_cpuidle_set_driver(struct cpuidle_driver *drv) +{ + cpuidle_drv = drv; +} int shmobile_cpuidle_init(void) { struct cpuidle_device *dev = &shmobile_cpuidle_dev; - struct cpuidle_driver *drv = &shmobile_cpuidle_driver; - int i; - - for (i = 0; i < CPUIDLE_STATE_MAX; i++) - drv->states[i].enter = shmobile_cpuidle_enter; - - if (shmobile_cpuidle_setup) - shmobile_cpuidle_setup(drv); - cpuidle_register_driver(drv); + cpuidle_register_driver(cpuidle_drv); - dev->state_count = drv->state_count; + dev->state_count = cpuidle_drv->state_count; cpuidle_register_device(dev); return 0; diff --git a/arch/arm/mach-shmobile/include/mach/common.h b/arch/arm/mach-shmobile/include/mach/common.h index f80f9c549393..ed77ab8c9143 100644 --- a/arch/arm/mach-shmobile/include/mach/common.h +++ b/arch/arm/mach-shmobile/include/mach/common.h @@ -13,8 +13,10 @@ extern int shmobile_clk_init(void); extern void shmobile_handle_irq_intc(struct pt_regs *); extern struct platform_suspend_ops shmobile_suspend_ops; struct cpuidle_driver; -extern void (*shmobile_cpuidle_modes[])(void); -extern void (*shmobile_cpuidle_setup)(struct cpuidle_driver *drv); +struct cpuidle_device; +extern int shmobile_enter_wfi(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index); +extern void shmobile_cpuidle_set_driver(struct cpuidle_driver *drv); extern void sh7367_init_irq(void); extern void sh7367_map_io(void); @@ -75,8 +77,6 @@ extern void r8a7740_meram_workaround(void); extern void r8a7779_register_twd(void); -extern void shmobile_init_late(void); - #ifdef CONFIG_SUSPEND int shmobile_suspend_init(void); #else @@ -100,4 +100,10 @@ static inline int shmobile_cpu_is_dead(unsigned int cpu) { return 1; } extern void shmobile_smp_init_cpus(unsigned int ncores); +static inline void shmobile_init_late(void) +{ + shmobile_suspend_init(); + shmobile_cpuidle_init(); +} + #endif /* __ARCH_MACH_COMMON_H */ diff --git a/arch/arm/mach-shmobile/include/mach/pm-rmobile.h b/arch/arm/mach-shmobile/include/mach/pm-rmobile.h index 5a402840fe28..690553a06887 100644 --- a/arch/arm/mach-shmobile/include/mach/pm-rmobile.h +++ b/arch/arm/mach-shmobile/include/mach/pm-rmobile.h @@ -12,6 +12,8 @@ #include <linux/pm_domain.h> +#define DEFAULT_DEV_LATENCY_NS 250000 + struct platform_device; struct rmobile_pm_domain { @@ -29,16 +31,33 @@ struct rmobile_pm_domain *to_rmobile_pd(struct generic_pm_domain *d) return container_of(d, struct rmobile_pm_domain, genpd); } +struct pm_domain_device { + const char *domain_name; + struct platform_device *pdev; +}; + #ifdef CONFIG_PM -extern void rmobile_init_pm_domain(struct rmobile_pm_domain *rmobile_pd); -extern void rmobile_add_device_to_domain(struct rmobile_pm_domain *rmobile_pd, - struct platform_device *pdev); -extern void rmobile_pm_add_subdomain(struct rmobile_pm_domain *rmobile_pd, - struct rmobile_pm_domain *rmobile_sd); +extern void rmobile_init_domains(struct rmobile_pm_domain domains[], int num); +extern void rmobile_add_device_to_domain_td(const char *domain_name, + struct platform_device *pdev, + struct gpd_timing_data *td); + +static inline void rmobile_add_device_to_domain(const char *domain_name, + struct platform_device *pdev) +{ + rmobile_add_device_to_domain_td(domain_name, pdev, NULL); +} + +extern void rmobile_add_devices_to_domains(struct pm_domain_device data[], + int size); #else -#define rmobile_init_pm_domain(pd) do { } while (0) -#define rmobile_add_device_to_domain(pd, pdev) do { } while (0) -#define rmobile_pm_add_subdomain(pd, sd) do { } while (0) + +#define rmobile_init_domains(domains, num) do { } while (0) +#define rmobile_add_device_to_domain_td(name, pdev, td) do { } while (0) +#define rmobile_add_device_to_domain(name, pdev) do { } while (0) + +static inline void rmobile_add_devices_to_domains(struct pm_domain_device d[], + int size) {} #endif /* CONFIG_PM */ #endif /* PM_RMOBILE_H */ diff --git a/arch/arm/mach-shmobile/include/mach/r8a7740.h b/arch/arm/mach-shmobile/include/mach/r8a7740.h index 7143147780df..59d252f4cf97 100644 --- a/arch/arm/mach-shmobile/include/mach/r8a7740.h +++ b/arch/arm/mach-shmobile/include/mach/r8a7740.h @@ -607,9 +607,9 @@ enum { }; #ifdef CONFIG_PM -extern struct rmobile_pm_domain r8a7740_pd_a4s; -extern struct rmobile_pm_domain r8a7740_pd_a3sp; -extern struct rmobile_pm_domain r8a7740_pd_a4lc; +extern void __init r8a7740_init_pm_domains(void); +#else +static inline void r8a7740_init_pm_domains(void) {} #endif /* CONFIG_PM */ #endif /* __ASM_R8A7740_H__ */ diff --git a/arch/arm/mach-shmobile/include/mach/r8a7779.h b/arch/arm/mach-shmobile/include/mach/r8a7779.h index f504c5e81b47..499f52d2a4a1 100644 --- a/arch/arm/mach-shmobile/include/mach/r8a7779.h +++ b/arch/arm/mach-shmobile/include/mach/r8a7779.h @@ -347,17 +347,9 @@ extern int r8a7779_sysc_power_down(struct r8a7779_pm_ch *r8a7779_ch); extern int r8a7779_sysc_power_up(struct r8a7779_pm_ch *r8a7779_ch); #ifdef CONFIG_PM -extern struct r8a7779_pm_domain r8a7779_sh4a; -extern struct r8a7779_pm_domain r8a7779_sgx; -extern struct r8a7779_pm_domain r8a7779_vdp1; -extern struct r8a7779_pm_domain r8a7779_impx3; - -extern void r8a7779_init_pm_domain(struct r8a7779_pm_domain *r8a7779_pd); -extern void r8a7779_add_device_to_domain(struct r8a7779_pm_domain *r8a7779_pd, - struct platform_device *pdev); +extern void __init r8a7779_init_pm_domains(void); #else -#define r8a7779_init_pm_domain(pd) do { } while (0) -#define r8a7779_add_device_to_domain(pd, pdev) do { } while (0) +static inline void r8a7779_init_pm_domains(void) {} #endif /* CONFIG_PM */ extern struct smp_operations r8a7779_smp_ops; diff --git a/arch/arm/mach-shmobile/include/mach/sh7372.h b/arch/arm/mach-shmobile/include/mach/sh7372.h index b59048e6d8fd..eb98b45c5089 100644 --- a/arch/arm/mach-shmobile/include/mach/sh7372.h +++ b/arch/arm/mach-shmobile/include/mach/sh7372.h @@ -478,21 +478,17 @@ extern struct clk sh7372_fsibck_clk; extern struct clk sh7372_fsidiva_clk; extern struct clk sh7372_fsidivb_clk; -#ifdef CONFIG_PM -extern struct rmobile_pm_domain sh7372_pd_a4lc; -extern struct rmobile_pm_domain sh7372_pd_a4mp; -extern struct rmobile_pm_domain sh7372_pd_d4; -extern struct rmobile_pm_domain sh7372_pd_a4r; -extern struct rmobile_pm_domain sh7372_pd_a3rv; -extern struct rmobile_pm_domain sh7372_pd_a3ri; -extern struct rmobile_pm_domain sh7372_pd_a4s; -extern struct rmobile_pm_domain sh7372_pd_a3sp; -extern struct rmobile_pm_domain sh7372_pd_a3sg; -#endif /* CONFIG_PM */ - extern void sh7372_intcs_suspend(void); extern void sh7372_intcs_resume(void); extern void sh7372_intca_suspend(void); extern void sh7372_intca_resume(void); +#ifdef CONFIG_PM +extern void __init sh7372_init_pm_domains(void); +#else +static inline void sh7372_init_pm_domains(void) {} +#endif + +extern void __init sh7372_pm_init_late(void); + #endif /* __ASM_SH7372_H__ */ diff --git a/arch/arm/mach-shmobile/pm-r8a7740.c b/arch/arm/mach-shmobile/pm-r8a7740.c index 893504d012a6..21e5316d2d88 100644 --- a/arch/arm/mach-shmobile/pm-r8a7740.c +++ b/arch/arm/mach-shmobile/pm-r8a7740.c @@ -21,14 +21,6 @@ static int r8a7740_pd_a4s_suspend(void) return -EBUSY; } -struct rmobile_pm_domain r8a7740_pd_a4s = { - .genpd.name = "A4S", - .bit_shift = 10, - .gov = &pm_domain_always_on_gov, - .no_debug = true, - .suspend = r8a7740_pd_a4s_suspend, -}; - static int r8a7740_pd_a3sp_suspend(void) { /* @@ -38,17 +30,31 @@ static int r8a7740_pd_a3sp_suspend(void) return console_suspend_enabled ? 0 : -EBUSY; } -struct rmobile_pm_domain r8a7740_pd_a3sp = { - .genpd.name = "A3SP", - .bit_shift = 11, - .gov = &pm_domain_always_on_gov, - .no_debug = true, - .suspend = r8a7740_pd_a3sp_suspend, +static struct rmobile_pm_domain r8a7740_pm_domains[] = { + { + .genpd.name = "A4S", + .bit_shift = 10, + .gov = &pm_domain_always_on_gov, + .no_debug = true, + .suspend = r8a7740_pd_a4s_suspend, + }, + { + .genpd.name = "A3SP", + .bit_shift = 11, + .gov = &pm_domain_always_on_gov, + .no_debug = true, + .suspend = r8a7740_pd_a3sp_suspend, + }, + { + .genpd.name = "A4LC", + .bit_shift = 1, + }, }; -struct rmobile_pm_domain r8a7740_pd_a4lc = { - .genpd.name = "A4LC", - .bit_shift = 1, -}; +void __init r8a7740_init_pm_domains(void) +{ + rmobile_init_domains(r8a7740_pm_domains, ARRAY_SIZE(r8a7740_pm_domains)); + pm_genpd_add_subdomain_names("A4S", "A3SP"); +} #endif /* CONFIG_PM */ diff --git a/arch/arm/mach-shmobile/pm-r8a7779.c b/arch/arm/mach-shmobile/pm-r8a7779.c index a18a4ae16d2b..d50a8e9b94a4 100644 --- a/arch/arm/mach-shmobile/pm-r8a7779.c +++ b/arch/arm/mach-shmobile/pm-r8a7779.c @@ -183,7 +183,7 @@ static bool pd_active_wakeup(struct device *dev) return true; } -void r8a7779_init_pm_domain(struct r8a7779_pm_domain *r8a7779_pd) +static void r8a7779_init_pm_domain(struct r8a7779_pm_domain *r8a7779_pd) { struct generic_pm_domain *genpd = &r8a7779_pd->genpd; @@ -199,43 +199,44 @@ void r8a7779_init_pm_domain(struct r8a7779_pm_domain *r8a7779_pd) pd_power_up(&r8a7779_pd->genpd); } -void r8a7779_add_device_to_domain(struct r8a7779_pm_domain *r8a7779_pd, - struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - - pm_genpd_add_device(&r8a7779_pd->genpd, dev); - if (pm_clk_no_clocks(dev)) - pm_clk_add(dev, NULL); -} - -struct r8a7779_pm_domain r8a7779_sh4a = { - .ch = { - .chan_offs = 0x80, /* PWRSR1 .. PWRER1 */ - .isr_bit = 16, /* SH4A */ - } -}; - -struct r8a7779_pm_domain r8a7779_sgx = { - .ch = { - .chan_offs = 0xc0, /* PWRSR2 .. PWRER2 */ - .isr_bit = 20, /* SGX */ - } +static struct r8a7779_pm_domain r8a7779_pm_domains[] = { + { + .genpd.name = "SH4A", + .ch = { + .chan_offs = 0x80, /* PWRSR1 .. PWRER1 */ + .isr_bit = 16, /* SH4A */ + }, + }, + { + .genpd.name = "SGX", + .ch = { + .chan_offs = 0xc0, /* PWRSR2 .. PWRER2 */ + .isr_bit = 20, /* SGX */ + }, + }, + { + .genpd.name = "VDP1", + .ch = { + .chan_offs = 0x100, /* PWRSR3 .. PWRER3 */ + .isr_bit = 21, /* VDP */ + }, + }, + { + .genpd.name = "IMPX3", + .ch = { + .chan_offs = 0x140, /* PWRSR4 .. PWRER4 */ + .isr_bit = 24, /* IMP */ + }, + }, }; -struct r8a7779_pm_domain r8a7779_vdp1 = { - .ch = { - .chan_offs = 0x100, /* PWRSR3 .. PWRER3 */ - .isr_bit = 21, /* VDP */ - } -}; +void __init r8a7779_init_pm_domains(void) +{ + int j; -struct r8a7779_pm_domain r8a7779_impx3 = { - .ch = { - .chan_offs = 0x140, /* PWRSR4 .. PWRER4 */ - .isr_bit = 24, /* IMP */ - } -}; + for (j = 0; j < ARRAY_SIZE(r8a7779_pm_domains); j++) + r8a7779_init_pm_domain(&r8a7779_pm_domains[j]); +} #endif /* CONFIG_PM */ diff --git a/arch/arm/mach-shmobile/pm-rmobile.c b/arch/arm/mach-shmobile/pm-rmobile.c index 32e177275e47..1fc05d9453d0 100644 --- a/arch/arm/mach-shmobile/pm-rmobile.c +++ b/arch/arm/mach-shmobile/pm-rmobile.c @@ -134,7 +134,7 @@ static int rmobile_pd_start_dev(struct device *dev) return ret; } -void rmobile_init_pm_domain(struct rmobile_pm_domain *rmobile_pd) +static void rmobile_init_pm_domain(struct rmobile_pm_domain *rmobile_pd) { struct generic_pm_domain *genpd = &rmobile_pd->genpd; struct dev_power_governor *gov = rmobile_pd->gov; @@ -149,19 +149,38 @@ void rmobile_init_pm_domain(struct rmobile_pm_domain *rmobile_pd) __rmobile_pd_power_up(rmobile_pd, false); } -void rmobile_add_device_to_domain(struct rmobile_pm_domain *rmobile_pd, - struct platform_device *pdev) +void rmobile_init_domains(struct rmobile_pm_domain domains[], int num) +{ + int j; + + for (j = 0; j < num; j++) + rmobile_init_pm_domain(&domains[j]); +} + +void rmobile_add_device_to_domain_td(const char *domain_name, + struct platform_device *pdev, + struct gpd_timing_data *td) { struct device *dev = &pdev->dev; - pm_genpd_add_device(&rmobile_pd->genpd, dev); + __pm_genpd_name_add_device(domain_name, dev, td); if (pm_clk_no_clocks(dev)) pm_clk_add(dev, NULL); } -void rmobile_pm_add_subdomain(struct rmobile_pm_domain *rmobile_pd, - struct rmobile_pm_domain *rmobile_sd) +void rmobile_add_devices_to_domains(struct pm_domain_device data[], + int size) { - pm_genpd_add_subdomain(&rmobile_pd->genpd, &rmobile_sd->genpd); + struct gpd_timing_data latencies = { + .stop_latency_ns = DEFAULT_DEV_LATENCY_NS, + .start_latency_ns = DEFAULT_DEV_LATENCY_NS, + .save_state_latency_ns = DEFAULT_DEV_LATENCY_NS, + .restore_state_latency_ns = DEFAULT_DEV_LATENCY_NS, + }; + int j; + + for (j = 0; j < size; j++) + rmobile_add_device_to_domain_td(data[j].domain_name, + data[j].pdev, &latencies); } #endif /* CONFIG_PM */ diff --git a/arch/arm/mach-shmobile/pm-sh7372.c b/arch/arm/mach-shmobile/pm-sh7372.c index 162121842a2b..a0826a48dd08 100644 --- a/arch/arm/mach-shmobile/pm-sh7372.c +++ b/arch/arm/mach-shmobile/pm-sh7372.c @@ -21,6 +21,7 @@ #include <linux/irq.h> #include <linux/bitrev.h> #include <linux/console.h> +#include <asm/cpuidle.h> #include <asm/io.h> #include <asm/tlbflush.h> #include <asm/suspend.h> @@ -72,20 +73,7 @@ #ifdef CONFIG_PM -struct rmobile_pm_domain sh7372_pd_a4lc = { - .genpd.name = "A4LC", - .bit_shift = 1, -}; - -struct rmobile_pm_domain sh7372_pd_a4mp = { - .genpd.name = "A4MP", - .bit_shift = 2, -}; - -struct rmobile_pm_domain sh7372_pd_d4 = { - .genpd.name = "D4", - .bit_shift = 3, -}; +#define PM_DOMAIN_ON_OFF_LATENCY_NS 250000 static int sh7372_a4r_pd_suspend(void) { @@ -94,39 +82,25 @@ static int sh7372_a4r_pd_suspend(void) return 0; } -struct rmobile_pm_domain sh7372_pd_a4r = { - .genpd.name = "A4R", - .bit_shift = 5, - .suspend = sh7372_a4r_pd_suspend, - .resume = sh7372_intcs_resume, -}; +static bool a4s_suspend_ready; -struct rmobile_pm_domain sh7372_pd_a3rv = { - .genpd.name = "A3RV", - .bit_shift = 6, -}; - -struct rmobile_pm_domain sh7372_pd_a3ri = { - .genpd.name = "A3RI", - .bit_shift = 8, -}; - -static int sh7372_pd_a4s_suspend(void) +static int sh7372_a4s_pd_suspend(void) { /* * The A4S domain contains the CPU core and therefore it should - * only be turned off if the CPU is in use. + * only be turned off if the CPU is not in use. This may happen + * during system suspend, when SYSC is going to be used for generating + * resume signals and a4s_suspend_ready is set to let + * sh7372_enter_suspend() know that it can turn A4S off. */ + a4s_suspend_ready = true; return -EBUSY; } -struct rmobile_pm_domain sh7372_pd_a4s = { - .genpd.name = "A4S", - .bit_shift = 10, - .gov = &pm_domain_always_on_gov, - .no_debug = true, - .suspend = sh7372_pd_a4s_suspend, -}; +static void sh7372_a4s_pd_resume(void) +{ + a4s_suspend_ready = false; +} static int sh7372_a3sp_pd_suspend(void) { @@ -137,18 +111,80 @@ static int sh7372_a3sp_pd_suspend(void) return console_suspend_enabled ? 0 : -EBUSY; } -struct rmobile_pm_domain sh7372_pd_a3sp = { - .genpd.name = "A3SP", - .bit_shift = 11, - .gov = &pm_domain_always_on_gov, - .no_debug = true, - .suspend = sh7372_a3sp_pd_suspend, +static struct rmobile_pm_domain sh7372_pm_domains[] = { + { + .genpd.name = "A4LC", + .genpd.power_on_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .genpd.power_off_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .bit_shift = 1, + }, + { + .genpd.name = "A4MP", + .genpd.power_on_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .genpd.power_off_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .bit_shift = 2, + }, + { + .genpd.name = "D4", + .genpd.power_on_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .genpd.power_off_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .bit_shift = 3, + }, + { + .genpd.name = "A4R", + .genpd.power_on_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .genpd.power_off_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .bit_shift = 5, + .suspend = sh7372_a4r_pd_suspend, + .resume = sh7372_intcs_resume, + }, + { + .genpd.name = "A3RV", + .genpd.power_on_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .genpd.power_off_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .bit_shift = 6, + }, + { + .genpd.name = "A3RI", + .genpd.power_on_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .genpd.power_off_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .bit_shift = 8, + }, + { + .genpd.name = "A4S", + .genpd.power_on_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .genpd.power_off_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .bit_shift = 10, + .gov = &pm_domain_always_on_gov, + .no_debug = true, + .suspend = sh7372_a4s_pd_suspend, + .resume = sh7372_a4s_pd_resume, + }, + { + .genpd.name = "A3SP", + .genpd.power_on_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .genpd.power_off_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .bit_shift = 11, + .gov = &pm_domain_always_on_gov, + .no_debug = true, + .suspend = sh7372_a3sp_pd_suspend, + }, + { + .genpd.name = "A3SG", + .genpd.power_on_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .genpd.power_off_latency_ns = PM_DOMAIN_ON_OFF_LATENCY_NS, + .bit_shift = 13, + }, }; -struct rmobile_pm_domain sh7372_pd_a3sg = { - .genpd.name = "A3SG", - .bit_shift = 13, -}; +void __init sh7372_init_pm_domains(void) +{ + rmobile_init_domains(sh7372_pm_domains, ARRAY_SIZE(sh7372_pm_domains)); + pm_genpd_add_subdomain_names("A4LC", "A3RV"); + pm_genpd_add_subdomain_names("A4R", "A4LC"); + pm_genpd_add_subdomain_names("A4S", "A3SG"); + pm_genpd_add_subdomain_names("A4S", "A3SP"); +} #endif /* CONFIG_PM */ @@ -304,6 +340,21 @@ static void sh7372_enter_a3sm_common(int pllc0_on) sh7372_set_reset_vector(__pa(sh7372_resume_core_standby_sysc)); sh7372_enter_sysc(pllc0_on, 1 << 12); } + +static void sh7372_enter_a4s_common(int pllc0_on) +{ + sh7372_intca_suspend(); + sh7372_set_reset_vector(SMFRAM); + sh7372_enter_sysc(pllc0_on, 1 << 10); + sh7372_intca_resume(); +} + +static void sh7372_pm_setup_smfram(void) +{ + memcpy((void *)SMFRAM, sh7372_resume_core_standby_sysc, 0x100); +} +#else +static inline void sh7372_pm_setup_smfram(void) {} #endif /* CONFIG_SUSPEND || CONFIG_CPU_IDLE */ #ifdef CONFIG_CPU_IDLE @@ -313,7 +364,8 @@ static int sh7372_do_idle_core_standby(unsigned long unused) return 0; } -static void sh7372_enter_core_standby(void) +static int sh7372_enter_core_standby(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { sh7372_set_reset_vector(__pa(sh7372_resume_core_standby_sysc)); @@ -324,83 +376,102 @@ static void sh7372_enter_core_standby(void) /* disable reset vector translation */ __raw_writel(0, SBAR); + + return 1; } -static void sh7372_enter_a3sm_pll_on(void) +static int sh7372_enter_a3sm_pll_on(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { sh7372_enter_a3sm_common(1); + return 2; } -static void sh7372_enter_a3sm_pll_off(void) +static int sh7372_enter_a3sm_pll_off(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { sh7372_enter_a3sm_common(0); + return 3; } -static void sh7372_cpuidle_setup(struct cpuidle_driver *drv) +static int sh7372_enter_a4s(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { - struct cpuidle_state *state = &drv->states[drv->state_count]; - - snprintf(state->name, CPUIDLE_NAME_LEN, "C2"); - strncpy(state->desc, "Core Standby Mode", CPUIDLE_DESC_LEN); - state->exit_latency = 10; - state->target_residency = 20 + 10; - state->flags = CPUIDLE_FLAG_TIME_VALID; - shmobile_cpuidle_modes[drv->state_count] = sh7372_enter_core_standby; - drv->state_count++; - - state = &drv->states[drv->state_count]; - snprintf(state->name, CPUIDLE_NAME_LEN, "C3"); - strncpy(state->desc, "A3SM PLL ON", CPUIDLE_DESC_LEN); - state->exit_latency = 20; - state->target_residency = 30 + 20; - state->flags = CPUIDLE_FLAG_TIME_VALID; - shmobile_cpuidle_modes[drv->state_count] = sh7372_enter_a3sm_pll_on; - drv->state_count++; - - state = &drv->states[drv->state_count]; - snprintf(state->name, CPUIDLE_NAME_LEN, "C4"); - strncpy(state->desc, "A3SM PLL OFF", CPUIDLE_DESC_LEN); - state->exit_latency = 120; - state->target_residency = 30 + 120; - state->flags = CPUIDLE_FLAG_TIME_VALID; - shmobile_cpuidle_modes[drv->state_count] = sh7372_enter_a3sm_pll_off; - drv->state_count++; + unsigned long msk, msk2; + + if (!sh7372_sysc_valid(&msk, &msk2)) + return sh7372_enter_a3sm_pll_off(dev, drv, index); + + sh7372_setup_sysc(msk, msk2); + sh7372_enter_a4s_common(0); + return 4; } +static struct cpuidle_driver sh7372_cpuidle_driver = { + .name = "sh7372_cpuidle", + .owner = THIS_MODULE, + .en_core_tk_irqen = 1, + .state_count = 5, + .safe_state_index = 0, /* C1 */ + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[0].enter = shmobile_enter_wfi, + .states[1] = { + .name = "C2", + .desc = "Core Standby Mode", + .exit_latency = 10, + .target_residency = 20 + 10, + .flags = CPUIDLE_FLAG_TIME_VALID, + .enter = sh7372_enter_core_standby, + }, + .states[2] = { + .name = "C3", + .desc = "A3SM PLL ON", + .exit_latency = 20, + .target_residency = 30 + 20, + .flags = CPUIDLE_FLAG_TIME_VALID, + .enter = sh7372_enter_a3sm_pll_on, + }, + .states[3] = { + .name = "C4", + .desc = "A3SM PLL OFF", + .exit_latency = 120, + .target_residency = 30 + 120, + .flags = CPUIDLE_FLAG_TIME_VALID, + .enter = sh7372_enter_a3sm_pll_off, + }, + .states[4] = { + .name = "C5", + .desc = "A4S PLL OFF", + .exit_latency = 240, + .target_residency = 30 + 240, + .flags = CPUIDLE_FLAG_TIME_VALID, + .enter = sh7372_enter_a4s, + .disabled = true, + }, +}; + static void sh7372_cpuidle_init(void) { - shmobile_cpuidle_setup = sh7372_cpuidle_setup; + shmobile_cpuidle_set_driver(&sh7372_cpuidle_driver); } #else static void sh7372_cpuidle_init(void) {} #endif #ifdef CONFIG_SUSPEND -static void sh7372_enter_a4s_common(int pllc0_on) -{ - sh7372_intca_suspend(); - memcpy((void *)SMFRAM, sh7372_resume_core_standby_sysc, 0x100); - sh7372_set_reset_vector(SMFRAM); - sh7372_enter_sysc(pllc0_on, 1 << 10); - sh7372_intca_resume(); -} - static int sh7372_enter_suspend(suspend_state_t suspend_state) { unsigned long msk, msk2; /* check active clocks to determine potential wakeup sources */ - if (sh7372_sysc_valid(&msk, &msk2)) { - if (!console_suspend_enabled && - sh7372_pd_a4s.genpd.status == GPD_STATE_POWER_OFF) { - /* convert INTC mask/sense to SYSC mask/sense */ - sh7372_setup_sysc(msk, msk2); - - /* enter A4S sleep with PLLC0 off */ - pr_debug("entering A4S\n"); - sh7372_enter_a4s_common(0); - return 0; - } + if (sh7372_sysc_valid(&msk, &msk2) && a4s_suspend_ready) { + /* convert INTC mask/sense to SYSC mask/sense */ + sh7372_setup_sysc(msk, msk2); + + /* enter A4S sleep with PLLC0 off */ + pr_debug("entering A4S\n"); + sh7372_enter_a4s_common(0); + return 0; } /* default to enter A3SM sleep with PLLC0 off */ @@ -426,7 +497,7 @@ static int sh7372_pm_notifier_fn(struct notifier_block *notifier, * executed during system suspend and resume, respectively, so * that those functions don't crash while accessing the INTCS. */ - pm_genpd_poweron(&sh7372_pd_a4r.genpd); + pm_genpd_name_poweron("A4R"); break; case PM_POST_SUSPEND: pm_genpd_poweroff_unused(); @@ -455,6 +526,14 @@ void __init sh7372_pm_init(void) /* do not convert A3SM, A3SP, A3SG, A4R power down into A4S */ __raw_writel(0, PDNSEL); + sh7372_pm_setup_smfram(); + sh7372_suspend_init(); sh7372_cpuidle_init(); } + +void __init sh7372_pm_init_late(void) +{ + shmobile_init_late(); + pm_genpd_name_attach_cpuidle("A4S", 4); +} diff --git a/arch/arm/mach-shmobile/setup-r8a7740.c b/arch/arm/mach-shmobile/setup-r8a7740.c index 78948a9dba0e..11bb1d984197 100644 --- a/arch/arm/mach-shmobile/setup-r8a7740.c +++ b/arch/arm/mach-shmobile/setup-r8a7740.c @@ -673,12 +673,7 @@ void __init r8a7740_add_standard_devices(void) r8a7740_i2c_workaround(&i2c0_device); r8a7740_i2c_workaround(&i2c1_device); - /* PM domain */ - rmobile_init_pm_domain(&r8a7740_pd_a4s); - rmobile_init_pm_domain(&r8a7740_pd_a3sp); - rmobile_init_pm_domain(&r8a7740_pd_a4lc); - - rmobile_pm_add_subdomain(&r8a7740_pd_a4s, &r8a7740_pd_a3sp); + r8a7740_init_pm_domains(); /* add devices */ platform_add_devices(r8a7740_early_devices, @@ -688,16 +683,16 @@ void __init r8a7740_add_standard_devices(void) /* add devices to PM domain */ - rmobile_add_device_to_domain(&r8a7740_pd_a3sp, &scif0_device); - rmobile_add_device_to_domain(&r8a7740_pd_a3sp, &scif1_device); - rmobile_add_device_to_domain(&r8a7740_pd_a3sp, &scif2_device); - rmobile_add_device_to_domain(&r8a7740_pd_a3sp, &scif3_device); - rmobile_add_device_to_domain(&r8a7740_pd_a3sp, &scif4_device); - rmobile_add_device_to_domain(&r8a7740_pd_a3sp, &scif5_device); - rmobile_add_device_to_domain(&r8a7740_pd_a3sp, &scif6_device); - rmobile_add_device_to_domain(&r8a7740_pd_a3sp, &scif7_device); - rmobile_add_device_to_domain(&r8a7740_pd_a3sp, &scifb_device); - rmobile_add_device_to_domain(&r8a7740_pd_a3sp, &i2c1_device); + rmobile_add_device_to_domain("A3SP", &scif0_device); + rmobile_add_device_to_domain("A3SP", &scif1_device); + rmobile_add_device_to_domain("A3SP", &scif2_device); + rmobile_add_device_to_domain("A3SP", &scif3_device); + rmobile_add_device_to_domain("A3SP", &scif4_device); + rmobile_add_device_to_domain("A3SP", &scif5_device); + rmobile_add_device_to_domain("A3SP", &scif6_device); + rmobile_add_device_to_domain("A3SP", &scif7_device); + rmobile_add_device_to_domain("A3SP", &scifb_device); + rmobile_add_device_to_domain("A3SP", &i2c1_device); } static void __init r8a7740_earlytimer_init(void) diff --git a/arch/arm/mach-shmobile/setup-r8a7779.c b/arch/arm/mach-shmobile/setup-r8a7779.c index e98e46f6cf55..2917668f0091 100644 --- a/arch/arm/mach-shmobile/setup-r8a7779.c +++ b/arch/arm/mach-shmobile/setup-r8a7779.c @@ -251,10 +251,7 @@ void __init r8a7779_add_standard_devices(void) #endif r8a7779_pm_init(); - r8a7779_init_pm_domain(&r8a7779_sh4a); - r8a7779_init_pm_domain(&r8a7779_sgx); - r8a7779_init_pm_domain(&r8a7779_vdp1); - r8a7779_init_pm_domain(&r8a7779_impx3); + r8a7779_init_pm_domains(); platform_add_devices(r8a7779_early_devices, ARRAY_SIZE(r8a7779_early_devices)); diff --git a/arch/arm/mach-shmobile/setup-sh7372.c b/arch/arm/mach-shmobile/setup-sh7372.c index 838a87be1d5c..a07954fbcd22 100644 --- a/arch/arm/mach-shmobile/setup-sh7372.c +++ b/arch/arm/mach-shmobile/setup-sh7372.c @@ -1001,21 +1001,34 @@ static struct platform_device *sh7372_late_devices[] __initdata = { void __init sh7372_add_standard_devices(void) { - rmobile_init_pm_domain(&sh7372_pd_a4lc); - rmobile_init_pm_domain(&sh7372_pd_a4mp); - rmobile_init_pm_domain(&sh7372_pd_d4); - rmobile_init_pm_domain(&sh7372_pd_a4r); - rmobile_init_pm_domain(&sh7372_pd_a3rv); - rmobile_init_pm_domain(&sh7372_pd_a3ri); - rmobile_init_pm_domain(&sh7372_pd_a4s); - rmobile_init_pm_domain(&sh7372_pd_a3sp); - rmobile_init_pm_domain(&sh7372_pd_a3sg); - - rmobile_pm_add_subdomain(&sh7372_pd_a4lc, &sh7372_pd_a3rv); - rmobile_pm_add_subdomain(&sh7372_pd_a4r, &sh7372_pd_a4lc); - - rmobile_pm_add_subdomain(&sh7372_pd_a4s, &sh7372_pd_a3sg); - rmobile_pm_add_subdomain(&sh7372_pd_a4s, &sh7372_pd_a3sp); + struct pm_domain_device domain_devices[] = { + { "A3RV", &vpu_device, }, + { "A4MP", &spu0_device, }, + { "A4MP", &spu1_device, }, + { "A3SP", &scif0_device, }, + { "A3SP", &scif1_device, }, + { "A3SP", &scif2_device, }, + { "A3SP", &scif3_device, }, + { "A3SP", &scif4_device, }, + { "A3SP", &scif5_device, }, + { "A3SP", &scif6_device, }, + { "A3SP", &iic1_device, }, + { "A3SP", &dma0_device, }, + { "A3SP", &dma1_device, }, + { "A3SP", &dma2_device, }, + { "A3SP", &usb_dma0_device, }, + { "A3SP", &usb_dma1_device, }, + { "A4R", &iic0_device, }, + { "A4R", &veu0_device, }, + { "A4R", &veu1_device, }, + { "A4R", &veu2_device, }, + { "A4R", &veu3_device, }, + { "A4R", &jpu_device, }, + { "A4R", &tmu00_device, }, + { "A4R", &tmu01_device, }, + }; + + sh7372_init_pm_domains(); platform_add_devices(sh7372_early_devices, ARRAY_SIZE(sh7372_early_devices)); @@ -1023,30 +1036,8 @@ void __init sh7372_add_standard_devices(void) platform_add_devices(sh7372_late_devices, ARRAY_SIZE(sh7372_late_devices)); - rmobile_add_device_to_domain(&sh7372_pd_a3rv, &vpu_device); - rmobile_add_device_to_domain(&sh7372_pd_a4mp, &spu0_device); - rmobile_add_device_to_domain(&sh7372_pd_a4mp, &spu1_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif0_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif1_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif2_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif3_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif4_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif5_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif6_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &iic1_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &dma0_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &dma1_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &dma2_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &usb_dma0_device); - rmobile_add_device_to_domain(&sh7372_pd_a3sp, &usb_dma1_device); - rmobile_add_device_to_domain(&sh7372_pd_a4r, &iic0_device); - rmobile_add_device_to_domain(&sh7372_pd_a4r, &veu0_device); - rmobile_add_device_to_domain(&sh7372_pd_a4r, &veu1_device); - rmobile_add_device_to_domain(&sh7372_pd_a4r, &veu2_device); - rmobile_add_device_to_domain(&sh7372_pd_a4r, &veu3_device); - rmobile_add_device_to_domain(&sh7372_pd_a4r, &jpu_device); - rmobile_add_device_to_domain(&sh7372_pd_a4r, &tmu00_device); - rmobile_add_device_to_domain(&sh7372_pd_a4r, &tmu01_device); + rmobile_add_devices_to_domains(domain_devices, + ARRAY_SIZE(domain_devices)); } static void __init sh7372_earlytimer_init(void) diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 13f555d62491..477a2d23ddf1 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -73,11 +73,18 @@ static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - if (!arch_is_coherent() && !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) __dma_page_cpu_to_dev(page, offset, size, dir); return pfn_to_dma(dev, page_to_pfn(page)) + offset; } +static dma_addr_t arm_coherent_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + return pfn_to_dma(dev, page_to_pfn(page)) + offset; +} + /** * arm_dma_unmap_page - unmap a buffer previously mapped through dma_map_page() * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices @@ -96,7 +103,7 @@ static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - if (!arch_is_coherent() && !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)), handle & ~PAGE_MASK, size, dir); } @@ -106,8 +113,7 @@ static void arm_dma_sync_single_for_cpu(struct device *dev, { unsigned int offset = handle & (PAGE_SIZE - 1); struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset)); - if (!arch_is_coherent()) - __dma_page_dev_to_cpu(page, offset, size, dir); + __dma_page_dev_to_cpu(page, offset, size, dir); } static void arm_dma_sync_single_for_device(struct device *dev, @@ -115,8 +121,7 @@ static void arm_dma_sync_single_for_device(struct device *dev, { unsigned int offset = handle & (PAGE_SIZE - 1); struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset)); - if (!arch_is_coherent()) - __dma_page_cpu_to_dev(page, offset, size, dir); + __dma_page_cpu_to_dev(page, offset, size, dir); } static int arm_dma_set_mask(struct device *dev, u64 dma_mask); @@ -138,6 +143,22 @@ struct dma_map_ops arm_dma_ops = { }; EXPORT_SYMBOL(arm_dma_ops); +static void *arm_coherent_dma_alloc(struct device *dev, size_t size, + dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs); +static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, struct dma_attrs *attrs); + +struct dma_map_ops arm_coherent_dma_ops = { + .alloc = arm_coherent_dma_alloc, + .free = arm_coherent_dma_free, + .mmap = arm_dma_mmap, + .get_sgtable = arm_dma_get_sgtable, + .map_page = arm_coherent_dma_map_page, + .map_sg = arm_dma_map_sg, + .set_dma_mask = arm_dma_set_mask, +}; +EXPORT_SYMBOL(arm_coherent_dma_ops); + static u64 get_coherent_dma_mask(struct device *dev) { u64 mask = (u64)arm_dma_limit; @@ -586,7 +607,7 @@ static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp, static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, - gfp_t gfp, pgprot_t prot, const void *caller) + gfp_t gfp, pgprot_t prot, bool is_coherent, const void *caller) { u64 mask = get_coherent_dma_mask(dev); struct page *page; @@ -619,7 +640,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); - if (arch_is_coherent() || nommu()) + if (is_coherent || nommu()) addr = __alloc_simple_buffer(dev, size, gfp, &page); else if (gfp & GFP_ATOMIC) addr = __alloc_from_pool(size, &page); @@ -647,7 +668,20 @@ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, if (dma_alloc_from_coherent(dev, size, handle, &memory)) return memory; - return __dma_alloc(dev, size, handle, gfp, prot, + return __dma_alloc(dev, size, handle, gfp, prot, false, + __builtin_return_address(0)); +} + +static void *arm_coherent_dma_alloc(struct device *dev, size_t size, + dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) +{ + pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel); + void *memory; + + if (dma_alloc_from_coherent(dev, size, handle, &memory)) + return memory; + + return __dma_alloc(dev, size, handle, gfp, prot, true, __builtin_return_address(0)); } @@ -684,8 +718,9 @@ int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, /* * Free a buffer as defined by the above mapping. */ -void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, struct dma_attrs *attrs) +static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, struct dma_attrs *attrs, + bool is_coherent) { struct page *page = pfn_to_page(dma_to_pfn(dev, handle)); @@ -694,7 +729,7 @@ void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, size = PAGE_ALIGN(size); - if (arch_is_coherent() || nommu()) { + if (is_coherent || nommu()) { __dma_free_buffer(page, size); } else if (__free_from_pool(cpu_addr, size)) { return; @@ -710,6 +745,18 @@ void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, } } +void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, struct dma_attrs *attrs) +{ + __arm_dma_free(dev, size, cpu_addr, handle, attrs, false); +} + +static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, struct dma_attrs *attrs) +{ + __arm_dma_free(dev, size, cpu_addr, handle, attrs, true); +} + int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t handle, size_t size, struct dma_attrs *attrs) @@ -1012,11 +1059,12 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, gfp_t if (!pages[i]) goto error; - if (order) + if (order) { split_page(pages[i], order); - j = 1 << order; - while (--j) - pages[i + j] = pages[i] + j; + j = 1 << order; + while (--j) + pages[i + j] = pages[i] + j; + } __dma_clear_buffer(pages[i], PAGE_SIZE << order); i += 1 << order; @@ -1303,7 +1351,8 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt, */ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, size_t size, dma_addr_t *handle, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, struct dma_attrs *attrs, + bool is_coherent) { struct dma_iommu_mapping *mapping = dev->archdata.mapping; dma_addr_t iova, iova_base; @@ -1322,8 +1371,8 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, phys_addr_t phys = page_to_phys(sg_page(s)); unsigned int len = PAGE_ALIGN(s->offset + s->length); - if (!arch_is_coherent() && - !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if (!is_coherent && + !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); ret = iommu_map(mapping->domain, iova, phys, len, 0); @@ -1341,20 +1390,9 @@ fail: return ret; } -/** - * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA - * @dev: valid struct device pointer - * @sg: list of buffers - * @nents: number of buffers to map - * @dir: DMA transfer direction - * - * Map a set of buffers described by scatterlist in streaming mode for DMA. - * The scatter gather list elements are merged together (if possible) and - * tagged with the appropriate dma address and length. They are obtained via - * sg_dma_{address,length}. - */ -int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs) +static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs, + bool is_coherent) { struct scatterlist *s = sg, *dma = sg, *start = sg; int i, count = 0; @@ -1370,7 +1408,7 @@ int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) { if (__map_sg_chunk(dev, start, size, &dma->dma_address, - dir, attrs) < 0) + dir, attrs, is_coherent) < 0) goto bad_mapping; dma->dma_address += offset; @@ -1383,7 +1421,8 @@ int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, } size += s->length; } - if (__map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs) < 0) + if (__map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs, + is_coherent) < 0) goto bad_mapping; dma->dma_address += offset; @@ -1398,17 +1437,44 @@ bad_mapping: } /** - * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg + * arm_coherent_iommu_map_sg - map a set of SG buffers for streaming mode DMA * @dev: valid struct device pointer * @sg: list of buffers - * @nents: number of buffers to unmap (same as was passed to dma_map_sg) - * @dir: DMA transfer direction (same as was passed to dma_map_sg) + * @nents: number of buffers to map + * @dir: DMA transfer direction * - * Unmap a set of streaming mode DMA translations. Again, CPU access - * rules concerning calls here are the same as for dma_unmap_single(). + * Map a set of i/o coherent buffers described by scatterlist in streaming + * mode for DMA. The scatter gather list elements are merged together (if + * possible) and tagged with the appropriate dma address and length. They are + * obtained via sg_dma_{address,length}. */ -void arm_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs) +int arm_coherent_iommu_map_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, struct dma_attrs *attrs) +{ + return __iommu_map_sg(dev, sg, nents, dir, attrs, true); +} + +/** + * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to map + * @dir: DMA transfer direction + * + * Map a set of buffers described by scatterlist in streaming mode for DMA. + * The scatter gather list elements are merged together (if possible) and + * tagged with the appropriate dma address and length. They are obtained via + * sg_dma_{address,length}. + */ +int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, struct dma_attrs *attrs) +{ + return __iommu_map_sg(dev, sg, nents, dir, attrs, false); +} + +static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, struct dma_attrs *attrs, + bool is_coherent) { struct scatterlist *s; int i; @@ -1417,7 +1483,7 @@ void arm_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, if (sg_dma_len(s)) __iommu_remove_mapping(dev, sg_dma_address(s), sg_dma_len(s)); - if (!arch_is_coherent() && + if (!is_coherent && !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) __dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir); @@ -1425,6 +1491,38 @@ void arm_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, } /** + * arm_coherent_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to unmap (same as was passed to dma_map_sg) + * @dir: DMA transfer direction (same as was passed to dma_map_sg) + * + * Unmap a set of streaming mode DMA translations. Again, CPU access + * rules concerning calls here are the same as for dma_unmap_single(). + */ +void arm_coherent_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, struct dma_attrs *attrs) +{ + __iommu_unmap_sg(dev, sg, nents, dir, attrs, true); +} + +/** + * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to unmap (same as was passed to dma_map_sg) + * @dir: DMA transfer direction (same as was passed to dma_map_sg) + * + * Unmap a set of streaming mode DMA translations. Again, CPU access + * rules concerning calls here are the same as for dma_unmap_single(). + */ +void arm_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + __iommu_unmap_sg(dev, sg, nents, dir, attrs, false); +} + +/** * arm_iommu_sync_sg_for_cpu * @dev: valid struct device pointer * @sg: list of buffers @@ -1438,8 +1536,7 @@ void arm_iommu_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int i; for_each_sg(sg, s, nents, i) - if (!arch_is_coherent()) - __dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir); + __dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir); } @@ -1457,22 +1554,21 @@ void arm_iommu_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int i; for_each_sg(sg, s, nents, i) - if (!arch_is_coherent()) - __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); + __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); } /** - * arm_iommu_map_page + * arm_coherent_iommu_map_page * @dev: valid struct device pointer * @page: page that buffer resides in * @offset: offset into page for start of buffer * @size: size of buffer to map * @dir: DMA transfer direction * - * IOMMU aware version of arm_dma_map_page() + * Coherent IOMMU aware version of arm_dma_map_page() */ -static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, +static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { @@ -1480,9 +1576,6 @@ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, dma_addr_t dma_addr; int ret, len = PAGE_ALIGN(size + offset); - if (!arch_is_coherent() && !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) - __dma_page_cpu_to_dev(page, offset, size, dir); - dma_addr = __alloc_iova(mapping, len); if (dma_addr == DMA_ERROR_CODE) return dma_addr; @@ -1498,6 +1591,51 @@ fail: } /** + * arm_iommu_map_page + * @dev: valid struct device pointer + * @page: page that buffer resides in + * @offset: offset into page for start of buffer + * @size: size of buffer to map + * @dir: DMA transfer direction + * + * IOMMU aware version of arm_dma_map_page() + */ +static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + __dma_page_cpu_to_dev(page, offset, size, dir); + + return arm_coherent_iommu_map_page(dev, page, offset, size, dir, attrs); +} + +/** + * arm_coherent_iommu_unmap_page + * @dev: valid struct device pointer + * @handle: DMA address of buffer + * @size: size of buffer (same as passed to dma_map_page) + * @dir: DMA transfer direction (same as passed to dma_map_page) + * + * Coherent IOMMU aware version of arm_dma_unmap_page() + */ +static void arm_coherent_iommu_unmap_page(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + dma_addr_t iova = handle & PAGE_MASK; + int offset = handle & ~PAGE_MASK; + int len = PAGE_ALIGN(size + offset); + + if (!iova) + return; + + iommu_unmap(mapping->domain, iova, len); + __free_iova(mapping, iova, len); +} + +/** * arm_iommu_unmap_page * @dev: valid struct device pointer * @handle: DMA address of buffer @@ -1519,7 +1657,7 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle, if (!iova) return; - if (!arch_is_coherent() && !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) __dma_page_dev_to_cpu(page, offset, size, dir); iommu_unmap(mapping->domain, iova, len); @@ -1537,8 +1675,7 @@ static void arm_iommu_sync_single_for_cpu(struct device *dev, if (!iova) return; - if (!arch_is_coherent()) - __dma_page_dev_to_cpu(page, offset, size, dir); + __dma_page_dev_to_cpu(page, offset, size, dir); } static void arm_iommu_sync_single_for_device(struct device *dev, @@ -1572,6 +1709,19 @@ struct dma_map_ops iommu_ops = { .sync_sg_for_device = arm_iommu_sync_sg_for_device, }; +struct dma_map_ops iommu_coherent_ops = { + .alloc = arm_iommu_alloc_attrs, + .free = arm_iommu_free_attrs, + .mmap = arm_iommu_mmap_attrs, + .get_sgtable = arm_iommu_get_sgtable, + + .map_page = arm_coherent_iommu_map_page, + .unmap_page = arm_coherent_iommu_unmap_page, + + .map_sg = arm_coherent_iommu_map_sg, + .unmap_sg = arm_coherent_iommu_unmap_sg, +}; + /** * arm_iommu_create_mapping * @bus: pointer to the bus holding the client device (for IOMMU calls) @@ -1665,7 +1815,7 @@ int arm_iommu_attach_device(struct device *dev, dev->archdata.mapping = mapping; set_dma_ops(dev, &iommu_ops); - pr_info("Attached IOMMU controller to %s device.\n", dev_name(dev)); + pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev)); return 0; } diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 18144e6a3115..941dfb9e9a78 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -423,17 +423,6 @@ static void __init build_mem_type_table(void) vecs_pgprot = kern_pgprot = user_pgprot = cp->pte; /* - * Enable CPU-specific coherency if supported. - * (Only available on XSC3 at the moment.) - */ - if (arch_is_coherent() && cpu_is_xsc3()) { - mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; - mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; - mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED; - mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; - mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; - } - /* * ARMv6 and above have extended page tables. */ if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) { diff --git a/arch/ia64/include/asm/xen/interface.h b/arch/ia64/include/asm/xen/interface.h index 09d5f7fd9db1..3d52a5bbd857 100644 --- a/arch/ia64/include/asm/xen/interface.h +++ b/arch/ia64/include/asm/xen/interface.h @@ -67,6 +67,10 @@ #define set_xen_guest_handle(hnd, val) do { (hnd).p = val; } while (0) #ifndef __ASSEMBLY__ +/* Explicitly size integers that represent pfns in the public interface + * with Xen so that we could have one ABI that works for 32 and 64 bit + * guests. */ +typedef unsigned long xen_pfn_t; /* Guest handles for primitive C types. */ __DEFINE_GUEST_HANDLE(uchar, unsigned char); __DEFINE_GUEST_HANDLE(uint, unsigned int); @@ -79,7 +83,6 @@ DEFINE_GUEST_HANDLE(void); DEFINE_GUEST_HANDLE(uint64_t); DEFINE_GUEST_HANDLE(uint32_t); -typedef unsigned long xen_pfn_t; DEFINE_GUEST_HANDLE(xen_pfn_t); #define PRI_xen_pfn "lx" #endif @@ -265,6 +268,8 @@ typedef struct xen_callback xen_callback_t; #endif /* !__ASSEMBLY__ */ +#include <asm/pvclock-abi.h> + /* Size of the shared_info area (this is not related to page size). */ #define XSI_SHIFT 14 #define XSI_SIZE (1 << XSI_SHIFT) diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 5a5c22245dee..f388b4e18a37 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2306,7 +2306,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t * partially initialize the vma for the sampling buffer */ vma->vm_mm = mm; - vma->vm_file = filp; + vma->vm_file = get_file(filp); vma->vm_flags = VM_READ| VM_MAYREAD |VM_RESERVED; vma->vm_page_prot = PAGE_READONLY; /* XXX may need to change */ @@ -2345,8 +2345,6 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t goto error; } - get_file(filp); - /* * now insert the vma in the vm list for the process, must be * done with mmap lock held @@ -4782,7 +4780,7 @@ recheck: asmlinkage long sys_perfmonctl (int fd, int cmd, void __user *arg, int count) { - struct file *file = NULL; + struct fd f = {NULL, 0}; pfm_context_t *ctx = NULL; unsigned long flags = 0UL; void *args_k = NULL; @@ -4879,17 +4877,17 @@ restart_args: ret = -EBADF; - file = fget(fd); - if (unlikely(file == NULL)) { + f = fdget(fd); + if (unlikely(f.file == NULL)) { DPRINT(("invalid fd %d\n", fd)); goto error_args; } - if (unlikely(PFM_IS_FILE(file) == 0)) { + if (unlikely(PFM_IS_FILE(f.file) == 0)) { DPRINT(("fd %d not related to perfmon\n", fd)); goto error_args; } - ctx = file->private_data; + ctx = f.file->private_data; if (unlikely(ctx == NULL)) { DPRINT(("no context for fd %d\n", fd)); goto error_args; @@ -4919,8 +4917,8 @@ abort_locked: if (call_made && PFM_CMD_RW_ARG(cmd) && copy_to_user(arg, args_k, base_sz*count)) ret = -EFAULT; error_args: - if (file) - fput(file); + if (f.file) + fdput(f); kfree(args_k); diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c index c71eb6c79897..6785de7bd2a0 100644 --- a/arch/parisc/hpux/fs.c +++ b/arch/parisc/hpux/fs.c @@ -109,33 +109,32 @@ Efault: int hpux_getdents(unsigned int fd, struct hpux_dirent __user *dirent, unsigned int count) { - struct file * file; + struct fd arg; struct hpux_dirent __user * lastdirent; struct getdents_callback buf; - int error = -EBADF; + int error; - file = fget(fd); - if (!file) - goto out; + arg = fdget(fd); + if (!arg.file) + return -EBADF; buf.current_dir = dirent; buf.previous = NULL; buf.count = count; buf.error = 0; - error = vfs_readdir(file, filldir, &buf); + error = vfs_readdir(arg.file, filldir, &buf); if (error >= 0) error = buf.error; lastdirent = buf.previous; if (lastdirent) { - if (put_user(file->f_pos, &lastdirent->d_off)) + if (put_user(arg.file->f_pos, &lastdirent->d_off)) error = -EFAULT; else error = count - buf.count; } - fput(file); -out: + fdput(arg); return error; } diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 559ae1ee6706..840838769853 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -189,7 +189,7 @@ SYSCALL_SPU(getcwd) SYSCALL_SPU(capget) SYSCALL_SPU(capset) COMPAT_SYS(sigaltstack) -SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile) +SYSX_SPU(sys_sendfile,compat_sys_sendfile_wrapper,sys_sendfile) SYSCALL(ni_syscall) SYSCALL(ni_syscall) PPC_SYS(vfork) @@ -229,7 +229,7 @@ COMPAT_SYS_SPU(sched_setaffinity) COMPAT_SYS_SPU(sched_getaffinity) SYSCALL(ni_syscall) SYSCALL(ni_syscall) -SYS32ONLY(sendfile64) +SYSX(sys_ni_syscall,compat_sys_sendfile64_wrapper,sys_sendfile64) COMPAT_SYS_SPU(io_setup) SYSCALL_SPU(io_destroy) COMPAT_SYS_SPU(io_getevents) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index bd377a368611..c683fa350add 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -419,6 +419,7 @@ #define __ARCH_WANT_COMPAT_SYS_TIME #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND #define __ARCH_WANT_SYS_NEWFSTATAT +#define __ARCH_WANT_COMPAT_SYS_SENDFILE #endif /* diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 0794a3017b1b..e144498bcddd 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1624,6 +1624,63 @@ static void __init prom_instantiate_rtas(void) #ifdef CONFIG_PPC64 /* + * Allocate room for and instantiate Stored Measurement Log (SML) + */ +static void __init prom_instantiate_sml(void) +{ + phandle ibmvtpm_node; + ihandle ibmvtpm_inst; + u32 entry = 0, size = 0; + u64 base; + + prom_debug("prom_instantiate_sml: start...\n"); + + ibmvtpm_node = call_prom("finddevice", 1, 1, ADDR("/ibm,vtpm")); + prom_debug("ibmvtpm_node: %x\n", ibmvtpm_node); + if (!PHANDLE_VALID(ibmvtpm_node)) + return; + + ibmvtpm_inst = call_prom("open", 1, 1, ADDR("/ibm,vtpm")); + if (!IHANDLE_VALID(ibmvtpm_inst)) { + prom_printf("opening vtpm package failed (%x)\n", ibmvtpm_inst); + return; + } + + if (call_prom_ret("call-method", 2, 2, &size, + ADDR("sml-get-handover-size"), + ibmvtpm_inst) != 0 || size == 0) { + prom_printf("SML get handover size failed\n"); + return; + } + + base = alloc_down(size, PAGE_SIZE, 0); + if (base == 0) + prom_panic("Could not allocate memory for sml\n"); + + prom_printf("instantiating sml at 0x%x...", base); + + if (call_prom_ret("call-method", 4, 2, &entry, + ADDR("sml-handover"), + ibmvtpm_inst, size, base) != 0 || entry == 0) { + prom_printf("SML handover failed\n"); + return; + } + prom_printf(" done\n"); + + reserve_mem(base, size); + + prom_setprop(ibmvtpm_node, "/ibm,vtpm", "linux,sml-base", + &base, sizeof(base)); + prom_setprop(ibmvtpm_node, "/ibm,vtpm", "linux,sml-size", + &size, sizeof(size)); + + prom_debug("sml base = 0x%x\n", base); + prom_debug("sml size = 0x%x\n", (long)size); + + prom_debug("prom_instantiate_sml: end...\n"); +} + +/* * Allocate room for and initialize TCE tables */ static void __init prom_initialize_tce_table(void) @@ -2916,6 +2973,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, prom_instantiate_opal(); #endif +#ifdef CONFIG_PPC64 + /* instantiate sml */ + prom_instantiate_sml(); +#endif + /* * On non-powermacs, put all CPUs in spin-loops. * diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 81c570633ead..abd1112da54f 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -143,48 +143,17 @@ long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t pt * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) * and the register representation of a signed int (msr in 64-bit mode) is performed. */ -asmlinkage long compat_sys_sendfile(u32 out_fd, u32 in_fd, compat_off_t __user * offset, u32 count) +asmlinkage long compat_sys_sendfile_wrapper(u32 out_fd, u32 in_fd, + compat_off_t __user *offset, u32 count) { - mm_segment_t old_fs = get_fs(); - int ret; - off_t of; - off_t __user *up; - - if (offset && get_user(of, offset)) - return -EFAULT; - - /* The __user pointer cast is valid because of the set_fs() */ - set_fs(KERNEL_DS); - up = offset ? (off_t __user *) &of : NULL; - ret = sys_sendfile((int)out_fd, (int)in_fd, up, count); - set_fs(old_fs); - - if (offset && put_user(of, offset)) - return -EFAULT; - - return ret; + return compat_sys_sendfile((int)out_fd, (int)in_fd, offset, count); } -asmlinkage int compat_sys_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, s32 count) +asmlinkage long compat_sys_sendfile64_wrapper(u32 out_fd, u32 in_fd, + compat_loff_t __user *offset, u32 count) { - mm_segment_t old_fs = get_fs(); - int ret; - loff_t lof; - loff_t __user *up; - - if (offset && get_user(lof, offset)) - return -EFAULT; - - /* The __user pointer cast is valid because of the set_fs() */ - set_fs(KERNEL_DS); - up = offset ? (loff_t __user *) &lof : NULL; - ret = sys_sendfile64(out_fd, in_fd, up, count); - set_fs(old_fs); - - if (offset && put_user(lof, offset)) - return -EFAULT; - - return ret; + return sys_sendfile((int)out_fd, (int)in_fd, + (off_t __user *)offset, count); } long compat_sys_execve(unsigned long a0, unsigned long a1, unsigned long a2, diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c index 714bbfc3162c..db4e638cf408 100644 --- a/arch/powerpc/platforms/cell/spu_syscalls.c +++ b/arch/powerpc/platforms/cell/spu_syscalls.c @@ -69,8 +69,6 @@ SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags, umode_t, mode, int, neighbor_fd) { long ret; - struct file *neighbor; - int fput_needed; struct spufs_calls *calls; calls = spufs_calls_get(); @@ -78,11 +76,11 @@ SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags, return -ENOSYS; if (flags & SPU_CREATE_AFFINITY_SPU) { + struct fd neighbor = fdget(neighbor_fd); ret = -EBADF; - neighbor = fget_light(neighbor_fd, &fput_needed); - if (neighbor) { - ret = calls->create_thread(name, flags, mode, neighbor); - fput_light(neighbor, fput_needed); + if (neighbor.file) { + ret = calls->create_thread(name, flags, mode, neighbor.file); + fdput(neighbor); } } else ret = calls->create_thread(name, flags, mode, NULL); @@ -94,8 +92,7 @@ SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags, asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, __u32 __user *ustatus) { long ret; - struct file *filp; - int fput_needed; + struct fd arg; struct spufs_calls *calls; calls = spufs_calls_get(); @@ -103,10 +100,10 @@ asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, __u32 __user *ustatus) return -ENOSYS; ret = -EBADF; - filp = fget_light(fd, &fput_needed); - if (filp) { - ret = calls->spu_run(filp, unpc, ustatus); - fput_light(filp, fput_needed); + arg = fdget(fd); + if (arg.file) { + ret = calls->spu_run(arg.file, unpc, ustatus); + fdput(arg); } spufs_calls_put(calls); diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index c2c5b078ba80..657e3f233a64 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -106,6 +106,17 @@ static int spufs_ctx_note_size(struct spu_context *ctx, int dfd) return total; } +static int match_context(const void *v, struct file *file, unsigned fd) +{ + struct spu_context *ctx; + if (file->f_op != &spufs_context_fops) + return 0; + ctx = SPUFS_I(file->f_dentry->d_inode)->i_ctx; + if (ctx->flags & SPU_CREATE_NOSCHED) + return 0; + return fd + 1; +} + /* * The additional architecture-specific notes for Cell are various * context files in the spu context. @@ -115,29 +126,18 @@ static int spufs_ctx_note_size(struct spu_context *ctx, int dfd) * internal functionality to dump them without needing to actually * open the files. */ +/* + * descriptor table is not shared, so files can't change or go away. + */ static struct spu_context *coredump_next_context(int *fd) { - struct fdtable *fdt = files_fdtable(current->files); struct file *file; - struct spu_context *ctx = NULL; - - for (; *fd < fdt->max_fds; (*fd)++) { - if (!fd_is_open(*fd, fdt)) - continue; - - file = fcheck(*fd); - - if (!file || file->f_op != &spufs_context_fops) - continue; - - ctx = SPUFS_I(file->f_dentry->d_inode)->i_ctx; - if (ctx->flags & SPU_CREATE_NOSCHED) - continue; - - break; - } - - return ctx; + int n = iterate_fd(current->files, *fd, match_context, NULL); + if (!n) + return NULL; + *fd = n - 1; + file = fcheck(*fd); + return SPUFS_I(file->f_dentry->d_inode)->i_ctx; } int spufs_coredump_extra_notes_size(void) diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 124ec1a55cc9..06ea69bd387a 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -72,8 +72,6 @@ static void hypfs_remove(struct dentry *dentry) struct dentry *parent; parent = dentry->d_parent; - if (!parent || !parent->d_inode) - return; mutex_lock(&parent->d_inode->i_mutex); if (hypfs_positive(dentry)) { if (S_ISDIR(dentry->d_inode->i_mode)) diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h index fb2693464807..d9a677c51926 100644 --- a/arch/sparc/include/asm/unistd.h +++ b/arch/sparc/include/asm/unistd.h @@ -447,6 +447,7 @@ #else #define __ARCH_WANT_COMPAT_SYS_TIME #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND +#define __ARCH_WANT_COMPAT_SYS_SENDFILE #endif /* diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S index d97f3eb72e06..44025f4ba41f 100644 --- a/arch/sparc/kernel/sys32.S +++ b/arch/sparc/kernel/sys32.S @@ -90,7 +90,7 @@ SIGN1(sys32_mkdir, sys_mkdir, %o1) SIGN3(sys32_futex, compat_sys_futex, %o1, %o2, %o5) SIGN1(sys32_sysfs, compat_sys_sysfs, %o0) SIGN2(sys32_sendfile, compat_sys_sendfile, %o0, %o1) -SIGN2(sys32_sendfile64, compat_sys_sendfile64, %o0, %o1) +SIGN2(sys32_sendfile64, sys_sendfile, %o0, %o1) SIGN1(sys32_prctl, sys_prctl, %o0) SIGN1(sys32_sched_rr_get_interval, compat_sys_sched_rr_get_interval, %o0) SIGN2(sys32_waitpid, sys_waitpid, %o0, %o2) diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index f7392336961f..d862499eb01c 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -506,52 +506,6 @@ long compat_sys_fadvise64_64(int fd, advice); } -asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, - compat_off_t __user *offset, - compat_size_t count) -{ - mm_segment_t old_fs = get_fs(); - int ret; - off_t of; - - if (offset && get_user(of, offset)) - return -EFAULT; - - set_fs(KERNEL_DS); - ret = sys_sendfile(out_fd, in_fd, - offset ? (off_t __user *) &of : NULL, - count); - set_fs(old_fs); - - if (offset && put_user(of, offset)) - return -EFAULT; - - return ret; -} - -asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, - compat_loff_t __user *offset, - compat_size_t count) -{ - mm_segment_t old_fs = get_fs(); - int ret; - loff_t lof; - - if (offset && get_user(lof, offset)) - return -EFAULT; - - set_fs(KERNEL_DS); - ret = sys_sendfile64(out_fd, in_fd, - offset ? (loff_t __user *) &lof : NULL, - count); - set_fs(old_fs); - - if (offset && put_user(lof, offset)) - return -EFAULT; - - return ret; -} - /* This is just a version for 32-bit applications which does * not force O_LARGEFILE on. */ diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index c17de0db6736..9efeb6da48bc 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -21,6 +21,9 @@ #include <linux/un.h> #include <linux/workqueue.h> #include <linux/mutex.h> +#include <linux/fs.h> +#include <linux/mount.h> +#include <linux/file.h> #include <asm/uaccess.h> #include <asm/switch_to.h> @@ -118,90 +121,38 @@ void mconsole_log(struct mc_request *req) mconsole_reply(req, "", 0, 0); } -/* This is a more convoluted version of mconsole_proc, which has some stability - * problems; however, we need it fixed, because it is expected that UML users - * mount HPPFS instead of procfs on /proc. And we want mconsole_proc to still - * show the real procfs content, not the ones from hppfs.*/ -#if 0 void mconsole_proc(struct mc_request *req) { struct vfsmount *mnt = current->nsproxy->pid_ns->proc_mnt; - struct file *file; - int n; - char *ptr = req->request.data, *buf; - mm_segment_t old_fs = get_fs(); - - ptr += strlen("proc"); - ptr = skip_spaces(ptr); - - file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY); - if (IS_ERR(file)) { - mconsole_reply(req, "Failed to open file", 1, 0); - goto out; - } - - buf = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (buf == NULL) { - mconsole_reply(req, "Failed to allocate buffer", 1, 0); - goto out_fput; - } - - if (file->f_op->read) { - do { - loff_t pos; - set_fs(KERNEL_DS); - n = vfs_read(file, buf, PAGE_SIZE - 1, &pos); - file_pos_write(file, pos); - set_fs(old_fs); - if (n >= 0) { - buf[n] = '\0'; - mconsole_reply(req, buf, 0, (n > 0)); - } - else { - mconsole_reply(req, "Read of file failed", - 1, 0); - goto out_free; - } - } while (n > 0); - } - else mconsole_reply(req, "", 0, 0); - - out_free: - kfree(buf); - out_fput: - fput(file); - out: ; -} -#endif - -void mconsole_proc(struct mc_request *req) -{ - char path[64]; char *buf; int len; - int fd; + struct file *file; int first_chunk = 1; char *ptr = req->request.data; ptr += strlen("proc"); ptr = skip_spaces(ptr); - snprintf(path, sizeof(path), "/proc/%s", ptr); - fd = sys_open(path, 0, 0); - if (fd < 0) { + file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY); + if (IS_ERR(file)) { mconsole_reply(req, "Failed to open file", 1, 0); - printk(KERN_ERR "open %s: %d\n",path,fd); + printk(KERN_ERR "open /proc/%s: %ld\n", ptr, PTR_ERR(file)); goto out; } buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (buf == NULL) { mconsole_reply(req, "Failed to allocate buffer", 1, 0); - goto out_close; + goto out_fput; } - for (;;) { - len = sys_read(fd, buf, PAGE_SIZE-1); + do { + loff_t pos; + mm_segment_t old_fs = get_fs(); + set_fs(KERNEL_DS); + len = vfs_read(file, buf, PAGE_SIZE - 1, &pos); + set_fs(old_fs); + file->f_pos = pos; if (len < 0) { mconsole_reply(req, "Read of file failed", 1, 0); goto out_free; @@ -211,22 +162,14 @@ void mconsole_proc(struct mc_request *req) mconsole_reply(req, "\n", 0, 1); first_chunk = 0; } - if (len == PAGE_SIZE-1) { - buf[len] = '\0'; - mconsole_reply(req, buf, 0, 1); - } else { - buf[len] = '\0'; - mconsole_reply(req, buf, 0, 0); - break; - } - } - + buf[len] = '\0'; + mconsole_reply(req, buf, 0, (len > 0)); + } while (len > 0); out_free: kfree(buf); - out_close: - sys_close(fd); - out: - /* nothing */; + out_fput: + fput(file); + out: ; } #define UML_MCONSOLE_HELPTEXT \ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 957ec87385af..fbee9714d9ab 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -248,6 +248,9 @@ #define MSR_IA32_PERF_STATUS 0x00000198 #define MSR_IA32_PERF_CTL 0x00000199 +#define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 +#define MSR_AMD_PERF_STATUS 0xc0010063 +#define MSR_AMD_PERF_CTL 0xc0010062 #define MSR_IA32_MPERF 0x000000e7 #define MSR_IA32_APERF 0x000000e8 diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h index cbf0c9d50b92..555f94d3637b 100644 --- a/arch/x86/include/asm/xen/interface.h +++ b/arch/x86/include/asm/xen/interface.h @@ -47,6 +47,10 @@ #endif #ifndef __ASSEMBLY__ +/* Explicitly size integers that represent pfns in the public interface + * with Xen so that on ARM we can have one ABI that works for 32 and 64 + * bit guests. */ +typedef unsigned long xen_pfn_t; /* Guest handles for primitive C types. */ __DEFINE_GUEST_HANDLE(uchar, unsigned char); __DEFINE_GUEST_HANDLE(uint, unsigned int); @@ -57,6 +61,7 @@ DEFINE_GUEST_HANDLE(long); DEFINE_GUEST_HANDLE(void); DEFINE_GUEST_HANDLE(uint64_t); DEFINE_GUEST_HANDLE(uint32_t); +DEFINE_GUEST_HANDLE(xen_pfn_t); #endif #ifndef HYPERVISOR_VIRT_START @@ -121,6 +126,8 @@ struct arch_shared_info { #include "interface_64.h" #endif +#include <asm/pvclock-abi.h> + #ifndef __ASSEMBLY__ /* * The following is all CPU context. Note that the fpu_ctxt block is filled diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h index 1be1ab7d6a41..ee52fcac6f72 100644 --- a/arch/x86/include/asm/xen/swiotlb-xen.h +++ b/arch/x86/include/asm/xen/swiotlb-xen.h @@ -5,10 +5,12 @@ extern int xen_swiotlb; extern int __init pci_xen_swiotlb_detect(void); extern void __init pci_xen_swiotlb_init(void); +extern int pci_xen_swiotlb_init_late(void); #else #define xen_swiotlb (0) static inline int __init pci_xen_swiotlb_detect(void) { return 0; } static inline void __init pci_xen_swiotlb_init(void) { } +static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; } #endif #endif /* _ASM_X86_SWIOTLB_XEN_H */ diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index ec57bd3818a4..7005ced5d1ad 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -6,8 +6,9 @@ #include <xen/xen.h> #include <xen/interface/physdev.h> +#include "xen-ops.h" -unsigned int xen_io_apic_read(unsigned apic, unsigned reg) +static unsigned int xen_io_apic_read(unsigned apic, unsigned reg) { struct physdev_apic apic_op; int ret; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 1fbe75a95f15..2d932c351f91 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -80,6 +80,8 @@ #include "smp.h" #include "multicalls.h" +#include <xen/events.h> + EXPORT_SYMBOL_GPL(hypercall_page); DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); @@ -1288,7 +1290,6 @@ asmlinkage void __init xen_start_kernel(void) { struct physdev_set_iopl set_iopl; int rc; - pgd_t *pgd; if (!xen_start_info) return; @@ -1380,8 +1381,6 @@ asmlinkage void __init xen_start_kernel(void) acpi_numa = -1; #endif - pgd = (pgd_t *)xen_start_info->pt_base; - /* Don't do the full vcpu_info placement stuff until we have a possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; @@ -1390,7 +1389,7 @@ asmlinkage void __init xen_start_kernel(void) early_boot_irqs_disabled = true; xen_raw_console_write("mapping kernel into physical memory\n"); - pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages); + xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, xen_start_info->nr_pages); /* Allocate and initialize top and mid mfn levels for p2m structure */ xen_build_mfn_list_list(); @@ -1441,11 +1440,19 @@ asmlinkage void __init xen_start_kernel(void) const struct dom0_vga_console_info *info = (void *)((char *)xen_start_info + xen_start_info->console.dom0.info_off); + struct xen_platform_op op = { + .cmd = XENPF_firmware_info, + .interface_version = XENPF_INTERFACE_VERSION, + .u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS, + }; xen_init_vga(info, xen_start_info->console.dom0.info_size); xen_start_info->console.domU.mfn = 0; xen_start_info->console.domU.evtchn = 0; + if (HYPERVISOR_dom0_op(&op) == 0) + boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags; + xen_init_apic(); /* Make sure ACS will be enabled */ diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 7a769b7526cb..5a16824cc2b3 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -84,6 +84,7 @@ */ DEFINE_SPINLOCK(xen_reservation_lock); +#ifdef CONFIG_X86_32 /* * Identity map, in addition to plain kernel map. This needs to be * large enough to allocate page table pages to allocate the rest. @@ -91,7 +92,7 @@ DEFINE_SPINLOCK(xen_reservation_lock); */ #define LEVEL1_IDENT_ENTRIES (PTRS_PER_PTE * 4) static RESERVE_BRK_ARRAY(pte_t, level1_ident_pgt, LEVEL1_IDENT_ENTRIES); - +#endif #ifdef CONFIG_X86_64 /* l3 pud for userspace vsyscall mapping */ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; @@ -1176,13 +1177,6 @@ static void xen_exit_mmap(struct mm_struct *mm) static void xen_post_allocator_init(void); -static void __init xen_pagetable_init(void) -{ - paging_init(); - xen_setup_shared_info(); - xen_post_allocator_init(); -} - static __init void xen_mapping_pagetable_reserve(u64 start, u64 end) { /* reserve the range used */ @@ -1197,6 +1191,87 @@ static __init void xen_mapping_pagetable_reserve(u64 start, u64 end) } } +#ifdef CONFIG_X86_64 +static void __init xen_cleanhighmap(unsigned long vaddr, + unsigned long vaddr_end) +{ + unsigned long kernel_end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1; + pmd_t *pmd = level2_kernel_pgt + pmd_index(vaddr); + + /* NOTE: The loop is more greedy than the cleanup_highmap variant. + * We include the PMD passed in on _both_ boundaries. */ + for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE)); + pmd++, vaddr += PMD_SIZE) { + if (pmd_none(*pmd)) + continue; + if (vaddr < (unsigned long) _text || vaddr > kernel_end) + set_pmd(pmd, __pmd(0)); + } + /* In case we did something silly, we should crash in this function + * instead of somewhere later and be confusing. */ + xen_mc_flush(); +} +#endif +static void __init xen_pagetable_init(void) +{ +#ifdef CONFIG_X86_64 + unsigned long size; + unsigned long addr; +#endif + paging_init(); + xen_setup_shared_info(); +#ifdef CONFIG_X86_64 + if (!xen_feature(XENFEAT_auto_translated_physmap)) { + unsigned long new_mfn_list; + + size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); + + /* On 32-bit, we get zero so this never gets executed. */ + new_mfn_list = xen_revector_p2m_tree(); + if (new_mfn_list && new_mfn_list != xen_start_info->mfn_list) { + /* using __ka address and sticking INVALID_P2M_ENTRY! */ + memset((void *)xen_start_info->mfn_list, 0xff, size); + + /* We should be in __ka space. */ + BUG_ON(xen_start_info->mfn_list < __START_KERNEL_map); + addr = xen_start_info->mfn_list; + /* We roundup to the PMD, which means that if anybody at this stage is + * using the __ka address of xen_start_info or xen_start_info->shared_info + * they are in going to crash. Fortunatly we have already revectored + * in xen_setup_kernel_pagetable and in xen_setup_shared_info. */ + size = roundup(size, PMD_SIZE); + xen_cleanhighmap(addr, addr + size); + + size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); + memblock_free(__pa(xen_start_info->mfn_list), size); + /* And revector! Bye bye old array */ + xen_start_info->mfn_list = new_mfn_list; + } else + goto skip; + } + /* At this stage, cleanup_highmap has already cleaned __ka space + * from _brk_limit way up to the max_pfn_mapped (which is the end of + * the ramdisk). We continue on, erasing PMD entries that point to page + * tables - do note that they are accessible at this stage via __va. + * For good measure we also round up to the PMD - which means that if + * anybody is using __ka address to the initial boot-stack - and try + * to use it - they are going to crash. The xen_start_info has been + * taken care of already in xen_setup_kernel_pagetable. */ + addr = xen_start_info->pt_base; + size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE); + + xen_cleanhighmap(addr, addr + size); + xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base)); +#ifdef DEBUG + /* This is superflous and is not neccessary, but you know what + * lets do it. The MODULES_VADDR -> MODULES_END should be clear of + * anything at this stage. */ + xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1); +#endif +skip: +#endif + xen_post_allocator_init(); +} static void xen_write_cr2(unsigned long cr2) { this_cpu_read(xen_vcpu)->arch.cr2 = cr2; @@ -1652,7 +1727,7 @@ static void set_page_prot(void *addr, pgprot_t prot) if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0)) BUG(); } - +#ifdef CONFIG_X86_32 static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) { unsigned pmdidx, pteidx; @@ -1703,7 +1778,7 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) set_page_prot(pmd, PAGE_KERNEL_RO); } - +#endif void __init xen_setup_machphys_mapping(void) { struct xen_machphys_mapping mapping; @@ -1731,7 +1806,20 @@ static void convert_pfn_mfn(void *v) for (i = 0; i < PTRS_PER_PTE; i++) pte[i] = xen_make_pte(pte[i].pte); } - +static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end, + unsigned long addr) +{ + if (*pt_base == PFN_DOWN(__pa(addr))) { + set_page_prot((void *)addr, PAGE_KERNEL); + clear_page((void *)addr); + (*pt_base)++; + } + if (*pt_end == PFN_DOWN(__pa(addr))) { + set_page_prot((void *)addr, PAGE_KERNEL); + clear_page((void *)addr); + (*pt_end)--; + } +} /* * Set up the initial kernel pagetable. * @@ -1743,11 +1831,13 @@ static void convert_pfn_mfn(void *v) * of the physical mapping once some sort of allocator has been set * up. */ -pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, - unsigned long max_pfn) +void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) { pud_t *l3; pmd_t *l2; + unsigned long addr[3]; + unsigned long pt_base, pt_end; + unsigned i; /* max_pfn_mapped is the last pfn mapped in the initial memory * mappings. Considering that on Xen after the kernel mappings we @@ -1755,32 +1845,53 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, * set max_pfn_mapped to the last real pfn mapped. */ max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list)); + pt_base = PFN_DOWN(__pa(xen_start_info->pt_base)); + pt_end = pt_base + xen_start_info->nr_pt_frames; + /* Zap identity mapping */ init_level4_pgt[0] = __pgd(0); /* Pre-constructed entries are in pfn, so convert to mfn */ + /* L4[272] -> level3_ident_pgt + * L4[511] -> level3_kernel_pgt */ convert_pfn_mfn(init_level4_pgt); + + /* L3_i[0] -> level2_ident_pgt */ convert_pfn_mfn(level3_ident_pgt); + /* L3_k[510] -> level2_kernel_pgt + * L3_i[511] -> level2_fixmap_pgt */ convert_pfn_mfn(level3_kernel_pgt); + /* We get [511][511] and have Xen's version of level2_kernel_pgt */ l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd); l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud); - memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD); - memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD); - + addr[0] = (unsigned long)pgd; + addr[1] = (unsigned long)l3; + addr[2] = (unsigned long)l2; + /* Graft it onto L4[272][0]. Note that we creating an aliasing problem: + * Both L4[272][0] and L4[511][511] have entries that point to the same + * L2 (PMD) tables. Meaning that if you modify it in __va space + * it will be also modified in the __ka space! (But if you just + * modify the PMD table to point to other PTE's or none, then you + * are OK - which is what cleanup_highmap does) */ + copy_page(level2_ident_pgt, l2); + /* Graft it onto L4[511][511] */ + copy_page(level2_kernel_pgt, l2); + + /* Get [511][510] and graft that in level2_fixmap_pgt */ l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd); l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud); - memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD); - - /* Set up identity map */ - xen_map_identity_early(level2_ident_pgt, max_pfn); + copy_page(level2_fixmap_pgt, l2); + /* Note that we don't do anything with level1_fixmap_pgt which + * we don't need. */ /* Make pagetable pieces RO */ set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); + set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); @@ -1791,22 +1902,28 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, /* Unpin Xen-provided one */ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); - /* Switch over */ - pgd = init_level4_pgt; - /* * At this stage there can be no user pgd, and no page * structure to attach it to, so make sure we just set kernel * pgd. */ xen_mc_batch(); - __xen_write_cr3(true, __pa(pgd)); + __xen_write_cr3(true, __pa(init_level4_pgt)); xen_mc_issue(PARAVIRT_LAZY_CPU); - memblock_reserve(__pa(xen_start_info->pt_base), - xen_start_info->nr_pt_frames * PAGE_SIZE); + /* We can't that easily rip out L3 and L2, as the Xen pagetables are + * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ... for + * the initial domain. For guests using the toolstack, they are in: + * [L4], [L3], [L2], [L1], [L1], order .. So for dom0 we can only + * rip out the [L4] (pgd), but for guests we shave off three pages. + */ + for (i = 0; i < ARRAY_SIZE(addr); i++) + check_pt_base(&pt_base, &pt_end, addr[i]); - return pgd; + /* Our (by three pages) smaller Xen pagetable that we are using */ + memblock_reserve(PFN_PHYS(pt_base), (pt_end - pt_base) * PAGE_SIZE); + /* Revector the xen_start_info */ + xen_start_info = (struct start_info *)__va(__pa(xen_start_info)); } #else /* !CONFIG_X86_64 */ static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD); @@ -1831,8 +1948,7 @@ static void __init xen_write_cr3_init(unsigned long cr3) */ swapper_kernel_pmd = extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); - memcpy(swapper_kernel_pmd, initial_kernel_pmd, - sizeof(pmd_t) * PTRS_PER_PMD); + copy_page(swapper_kernel_pmd, initial_kernel_pmd); swapper_pg_dir[KERNEL_PGD_BOUNDARY] = __pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT); set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO); @@ -1849,8 +1965,7 @@ static void __init xen_write_cr3_init(unsigned long cr3) pv_mmu_ops.write_cr3 = &xen_write_cr3; } -pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, - unsigned long max_pfn) +void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) { pmd_t *kernel_pmd; @@ -1862,11 +1977,11 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, 512*1024); kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); - memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); + copy_page(initial_kernel_pmd, kernel_pmd); xen_map_identity_early(initial_kernel_pmd, max_pfn); - memcpy(initial_page_table, pgd, sizeof(pgd_t) * PTRS_PER_PGD); + copy_page(initial_page_table, pgd); initial_page_table[KERNEL_PGD_BOUNDARY] = __pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT); @@ -1882,8 +1997,6 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, memblock_reserve(__pa(xen_start_info->pt_base), xen_start_info->nr_pt_frames * PAGE_SIZE); - - return initial_page_table; } #endif /* CONFIG_X86_64 */ @@ -2333,6 +2446,9 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma, unsigned long range; int err = 0; + if (xen_feature(XENFEAT_auto_translated_physmap)) + return -EINVAL; + prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP); BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_RESERVED | VM_IO)) == @@ -2351,8 +2467,8 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma, if (err) goto out; - err = -EFAULT; - if (HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid) < 0) + err = HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid); + if (err < 0) goto out; nr -= batch; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 72213da605f5..95fb2aa5927e 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -22,7 +22,7 @@ * * P2M_PER_PAGE depends on the architecture, as a mfn is always * unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to - * 512 and 1024 entries respectively. + * 512 and 1024 entries respectively. * * In short, these structures contain the Machine Frame Number (MFN) of the PFN. * @@ -139,11 +139,11 @@ * / | ~0, ~0, .... | * | \---------------/ * | - * p2m_missing p2m_missing - * /------------------\ /------------\ - * | [p2m_mid_missing]+---->| ~0, ~0, ~0 | - * | [p2m_mid_missing]+---->| ..., ~0 | - * \------------------/ \------------/ + * p2m_mid_missing p2m_missing + * /-----------------\ /------------\ + * | [p2m_missing] +---->| ~0, ~0, ~0 | + * | [p2m_missing] +---->| ..., ~0 | + * \-----------------/ \------------/ * * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT) */ @@ -396,7 +396,85 @@ void __init xen_build_dynamic_phys_to_machine(void) m2p_override_init(); } +#ifdef CONFIG_X86_64 +#include <linux/bootmem.h> +unsigned long __init xen_revector_p2m_tree(void) +{ + unsigned long va_start; + unsigned long va_end; + unsigned long pfn; + unsigned long pfn_free = 0; + unsigned long *mfn_list = NULL; + unsigned long size; + + va_start = xen_start_info->mfn_list; + /*We copy in increments of P2M_PER_PAGE * sizeof(unsigned long), + * so make sure it is rounded up to that */ + size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); + va_end = va_start + size; + + /* If we were revectored already, don't do it again. */ + if (va_start <= __START_KERNEL_map && va_start >= __PAGE_OFFSET) + return 0; + + mfn_list = alloc_bootmem_align(size, PAGE_SIZE); + if (!mfn_list) { + pr_warn("Could not allocate space for a new P2M tree!\n"); + return xen_start_info->mfn_list; + } + /* Fill it out with INVALID_P2M_ENTRY value */ + memset(mfn_list, 0xFF, size); + + for (pfn = 0; pfn < ALIGN(MAX_DOMAIN_PAGES, P2M_PER_PAGE); pfn += P2M_PER_PAGE) { + unsigned topidx = p2m_top_index(pfn); + unsigned mididx; + unsigned long *mid_p; + + if (!p2m_top[topidx]) + continue; + + if (p2m_top[topidx] == p2m_mid_missing) + continue; + + mididx = p2m_mid_index(pfn); + mid_p = p2m_top[topidx][mididx]; + if (!mid_p) + continue; + if ((mid_p == p2m_missing) || (mid_p == p2m_identity)) + continue; + + if ((unsigned long)mid_p == INVALID_P2M_ENTRY) + continue; + + /* The old va. Rebase it on mfn_list */ + if (mid_p >= (unsigned long *)va_start && mid_p <= (unsigned long *)va_end) { + unsigned long *new; + + if (pfn_free > (size / sizeof(unsigned long))) { + WARN(1, "Only allocated for %ld pages, but we want %ld!\n", + size / sizeof(unsigned long), pfn_free); + return 0; + } + new = &mfn_list[pfn_free]; + + copy_page(new, mid_p); + p2m_top[topidx][mididx] = &mfn_list[pfn_free]; + p2m_top_mfn_p[topidx][mididx] = virt_to_mfn(&mfn_list[pfn_free]); + + pfn_free += P2M_PER_PAGE; + } + /* This should be the leafs allocated for identity from _brk. */ + } + return (unsigned long)mfn_list; + +} +#else +unsigned long __init xen_revector_p2m_tree(void) +{ + return 0; +} +#endif unsigned long get_phys_to_machine(unsigned long pfn) { unsigned topidx, mididx, idx; @@ -430,7 +508,7 @@ static void free_p2m_page(void *p) free_page((unsigned long)p); } -/* +/* * Fully allocate the p2m structure for a given pfn. We need to check * that both the top and mid levels are allocated, and make sure the * parallel mfn tree is kept in sync. We may race with other cpus, so diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c index 967633ad98c4..969570491c39 100644 --- a/arch/x86/xen/pci-swiotlb-xen.c +++ b/arch/x86/xen/pci-swiotlb-xen.c @@ -8,6 +8,14 @@ #include <xen/xen.h> #include <asm/iommu_table.h> + +#include <asm/xen/swiotlb-xen.h> +#ifdef CONFIG_X86_64 +#include <asm/iommu.h> +#include <asm/dma.h> +#endif +#include <linux/export.h> + int xen_swiotlb __read_mostly; static struct dma_map_ops xen_swiotlb_dma_ops = { @@ -34,34 +42,64 @@ static struct dma_map_ops xen_swiotlb_dma_ops = { int __init pci_xen_swiotlb_detect(void) { + if (!xen_pv_domain()) + return 0; + /* If running as PV guest, either iommu=soft, or swiotlb=force will * activate this IOMMU. If running as PV privileged, activate it * irregardless. */ - if ((xen_initial_domain() || swiotlb || swiotlb_force) && - (xen_pv_domain())) + if ((xen_initial_domain() || swiotlb || swiotlb_force)) xen_swiotlb = 1; /* If we are running under Xen, we MUST disable the native SWIOTLB. * Don't worry about swiotlb_force flag activating the native, as * the 'swiotlb' flag is the only one turning it on. */ - if (xen_pv_domain()) - swiotlb = 0; + swiotlb = 0; +#ifdef CONFIG_X86_64 + /* pci_swiotlb_detect_4gb turns on native SWIOTLB if no_iommu == 0 + * (so no iommu=X command line over-writes). + * Considering that PV guests do not want the *native SWIOTLB* but + * only Xen SWIOTLB it is not useful to us so set no_iommu=1 here. + */ + if (max_pfn > MAX_DMA32_PFN) + no_iommu = 1; +#endif return xen_swiotlb; } void __init pci_xen_swiotlb_init(void) { if (xen_swiotlb) { - xen_swiotlb_init(1); + xen_swiotlb_init(1, true /* early */); dma_ops = &xen_swiotlb_dma_ops; /* Make sure ACS will be enabled */ pci_request_acs(); } } + +int pci_xen_swiotlb_init_late(void) +{ + int rc; + + if (xen_swiotlb) + return 0; + + rc = xen_swiotlb_init(1, false /* late */); + if (rc) + return rc; + + dma_ops = &xen_swiotlb_dma_ops; + /* Make sure ACS will be enabled */ + pci_request_acs(); + + return 0; +} +EXPORT_SYMBOL_GPL(pci_xen_swiotlb_init_late); + IOMMU_INIT_FINISH(pci_xen_swiotlb_detect, - 0, + NULL, pci_xen_swiotlb_init, - 0); + NULL); diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c index ffcf2615640b..0a7852483ffe 100644 --- a/arch/x86/xen/platform-pci-unplug.c +++ b/arch/x86/xen/platform-pci-unplug.c @@ -24,6 +24,7 @@ #include <linux/module.h> #include <xen/platform_pci.h> +#include "xen-ops.h" #define XEN_PLATFORM_ERR_MAGIC -1 #define XEN_PLATFORM_ERR_PROTOCOL -2 diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index e2d62d697b5d..8971a26d21ab 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -432,6 +432,24 @@ char * __init xen_memory_setup(void) * - mfn_list * - xen_start_info * See comment above "struct start_info" in <xen/interface/xen.h> + * We tried to make the the memblock_reserve more selective so + * that it would be clear what region is reserved. Sadly we ran + * in the problem wherein on a 64-bit hypervisor with a 32-bit + * initial domain, the pt_base has the cr3 value which is not + * neccessarily where the pagetable starts! As Jan put it: " + * Actually, the adjustment turns out to be correct: The page + * tables for a 32-on-64 dom0 get allocated in the order "first L1", + * "first L2", "first L3", so the offset to the page table base is + * indeed 2. When reading xen/include/public/xen.h's comment + * very strictly, this is not a violation (since there nothing is said + * that the first thing in the page table space is pointed to by + * pt_base; I admit that this seems to be implied though, namely + * do I think that it is implied that the page table space is the + * range [pt_base, pt_base + nt_pt_frames), whereas that + * range here indeed is [pt_base - 2, pt_base - 2 + nt_pt_frames), + * which - without a priori knowledge - the kernel would have + * difficulty to figure out)." - so lets just fall back to the + * easy way and reserve the whole region. */ memblock_reserve(__pa(xen_start_info->mfn_list), xen_start_info->pt_base - xen_start_info->mfn_list); diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c index 1cd7f4d11e29..6722e3733f02 100644 --- a/arch/x86/xen/vga.c +++ b/arch/x86/xen/vga.c @@ -35,6 +35,7 @@ void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size) info->u.text_mode_3.font_height; break; + case XEN_VGATYPE_EFI_LFB: case XEN_VGATYPE_VESA_LFB: if (size < offsetof(struct dom0_vga_console_info, u.vesa_lfb.gbl_caps)) @@ -54,6 +55,12 @@ void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size) screen_info->blue_pos = info->u.vesa_lfb.blue_pos; screen_info->rsvd_size = info->u.vesa_lfb.rsvd_size; screen_info->rsvd_pos = info->u.vesa_lfb.rsvd_pos; + + if (info->video_type == XEN_VGATYPE_EFI_LFB) { + screen_info->orig_video_isVGA = VIDEO_TYPE_EFI; + break; + } + if (size >= offsetof(struct dom0_vga_console_info, u.vesa_lfb.gbl_caps) + sizeof(info->u.vesa_lfb.gbl_caps)) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index aaa7291c9259..7faed5869e5b 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -28,9 +28,61 @@ ENTRY(startup_xen) __FINIT .pushsection .text - .align PAGE_SIZE + .balign PAGE_SIZE ENTRY(hypercall_page) - .skip PAGE_SIZE +#define NEXT_HYPERCALL(x) \ + ENTRY(xen_hypercall_##x) \ + .skip 32 + +NEXT_HYPERCALL(set_trap_table) +NEXT_HYPERCALL(mmu_update) +NEXT_HYPERCALL(set_gdt) +NEXT_HYPERCALL(stack_switch) +NEXT_HYPERCALL(set_callbacks) +NEXT_HYPERCALL(fpu_taskswitch) +NEXT_HYPERCALL(sched_op_compat) +NEXT_HYPERCALL(platform_op) +NEXT_HYPERCALL(set_debugreg) +NEXT_HYPERCALL(get_debugreg) +NEXT_HYPERCALL(update_descriptor) +NEXT_HYPERCALL(ni) +NEXT_HYPERCALL(memory_op) +NEXT_HYPERCALL(multicall) +NEXT_HYPERCALL(update_va_mapping) +NEXT_HYPERCALL(set_timer_op) +NEXT_HYPERCALL(event_channel_op_compat) +NEXT_HYPERCALL(xen_version) +NEXT_HYPERCALL(console_io) +NEXT_HYPERCALL(physdev_op_compat) +NEXT_HYPERCALL(grant_table_op) +NEXT_HYPERCALL(vm_assist) +NEXT_HYPERCALL(update_va_mapping_otherdomain) +NEXT_HYPERCALL(iret) +NEXT_HYPERCALL(vcpu_op) +NEXT_HYPERCALL(set_segment_base) +NEXT_HYPERCALL(mmuext_op) +NEXT_HYPERCALL(xsm_op) +NEXT_HYPERCALL(nmi_op) +NEXT_HYPERCALL(sched_op) +NEXT_HYPERCALL(callback_op) +NEXT_HYPERCALL(xenoprof_op) +NEXT_HYPERCALL(event_channel_op) +NEXT_HYPERCALL(physdev_op) +NEXT_HYPERCALL(hvm_op) +NEXT_HYPERCALL(sysctl) +NEXT_HYPERCALL(domctl) +NEXT_HYPERCALL(kexec_op) +NEXT_HYPERCALL(tmem_op) /* 38 */ +ENTRY(xen_hypercall_rsvr) + .skip 320 +NEXT_HYPERCALL(mca) /* 48 */ +NEXT_HYPERCALL(arch_1) +NEXT_HYPERCALL(arch_2) +NEXT_HYPERCALL(arch_3) +NEXT_HYPERCALL(arch_4) +NEXT_HYPERCALL(arch_5) +NEXT_HYPERCALL(arch_6) + .balign PAGE_SIZE .popsection ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 202d4c150154..bb5a8105ea86 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -27,7 +27,7 @@ void xen_setup_mfn_list_list(void); void xen_setup_shared_info(void); void xen_build_mfn_list_list(void); void xen_setup_machphys_mapping(void); -pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn); +void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn); void xen_reserve_top(void); extern unsigned long xen_max_p2m_pfn; @@ -45,6 +45,7 @@ void xen_hvm_init_shared_info(void); void xen_unplug_emulated_devices(void); void __init xen_build_dynamic_phys_to_machine(void); +unsigned long __init xen_revector_p2m_tree(void); void xen_init_irq_ops(void); void xen_setup_timer(int cpu); |