diff options
| author | David S. Miller <davem@davemloft.net> | 2013-05-24 23:48:28 (GMT) |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2013-05-24 23:48:28 (GMT) |
| commit | e6ff4c75f9095f61b3a66c2a78e47b62864022dd (patch) | |
| tree | 425ea9463cbec0b1975b8a33d9a56817143055d0 /arch | |
| parent | ee9c799c231324de681eb21e06d8bf4842768b75 (diff) | |
| parent | 0e255f1c0c9add2f0c920240ac4cadc28ae274c3 (diff) | |
| download | linux-e6ff4c75f9095f61b3a66c2a78e47b62864022dd.tar.xz | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Merge net into net-next because some upcoming net-next changes
build on top of bug fixes that went into net.
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'arch')
150 files changed, 1662 insertions, 956 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index dd0e8eb..a4429bc 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -213,6 +213,9 @@ config USE_GENERIC_SMP_HELPERS config GENERIC_SMP_IDLE_THREAD bool +config GENERIC_IDLE_POLL_SETUP + bool + # Select if arch init_task initializer is different to init/init_task.c config ARCH_INIT_TASK bool diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index d423d58..49d993c 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -38,6 +38,7 @@ config ARM select HAVE_GENERIC_HARDIRQS select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)) select HAVE_IDE if PCI || ISA || PCMCIA + select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZMA select HAVE_KERNEL_LZO @@ -488,7 +489,7 @@ config ARCH_IXP4XX config ARCH_DOVE bool "Marvell Dove" select ARCH_REQUIRE_GPIOLIB - select CPU_V7 + select CPU_PJ4 select GENERIC_CLOCKEVENTS select MIGHT_HAVE_PCI select PINCTRL diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 4737408..1ba358b 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -309,7 +309,7 @@ define archhelp echo ' Image - Uncompressed kernel image (arch/$(ARCH)/boot/Image)' echo '* xipImage - XIP kernel image, if configured (arch/$(ARCH)/boot/xipImage)' echo ' uImage - U-Boot wrapped zImage' - echo ' bootpImage - Combined zImage and initial RAM disk' + echo ' bootpImage - Combined zImage and initial RAM disk' echo ' (supply initrd image via make variable INITRD=<path>)' echo '* dtbs - Build device tree blobs for enabled boards' echo ' install - Install uncompressed kernel' diff --git a/arch/arm/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c index 52b88d8..3caed0d 100644 --- a/arch/arm/common/mcpm_platsmp.c +++ b/arch/arm/common/mcpm_platsmp.c @@ -15,8 +15,6 @@ #include <linux/smp.h> #include <linux/spinlock.h> -#include <linux/irqchip/arm-gic.h> - #include <asm/mcpm.h> #include <asm/smp.h> #include <asm/smp_plat.h> @@ -49,7 +47,6 @@ static int __cpuinit mcpm_boot_secondary(unsigned int cpu, struct task_struct *i static void __cpuinit mcpm_secondary_init(unsigned int cpu) { mcpm_cpu_powered_up(); - gic_secondary_init(0); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig index 7e0ebb6..9940f7b 100644 --- a/arch/arm/configs/omap1_defconfig +++ b/arch/arm/configs/omap1_defconfig @@ -199,7 +199,6 @@ CONFIG_USB_PHY=y CONFIG_USB_DEBUG=y CONFIG_USB_DEVICEFS=y # CONFIG_USB_DEVICE_CLASS is not set -CONFIG_USB_SUSPEND=y CONFIG_USB_MON=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_STORAGE=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index c1ef64b..435d69b 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -204,7 +204,6 @@ CONFIG_USB=y CONFIG_USB_DEBUG=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_DEVICEFS=y -CONFIG_USB_SUSPEND=y CONFIG_USB_MON=y CONFIG_USB_WDM=y CONFIG_USB_STORAGE=y diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h index 7eb18c1..4f009c1 100644 --- a/arch/arm/include/asm/cmpxchg.h +++ b/arch/arm/include/asm/cmpxchg.h @@ -233,15 +233,15 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr, ((__typeof__(*(ptr)))atomic64_cmpxchg(container_of((ptr), \ atomic64_t, \ counter), \ - (unsigned long)(o), \ - (unsigned long)(n))) + (unsigned long long)(o), \ + (unsigned long long)(n))) #define cmpxchg64_local(ptr, o, n) \ ((__typeof__(*(ptr)))local64_cmpxchg(container_of((ptr), \ local64_t, \ a), \ - (unsigned long)(o), \ - (unsigned long)(n))) + (unsigned long long)(o), \ + (unsigned long long)(n))) #endif /* __LINUX_ARM_ARCH__ >= 6 */ diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 47ab905..550d63c 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -251,7 +251,7 @@ void __ref cpu_die(void) * this returns, power and/or clocks can be removed at any point * from this CPU and its cache by platform_cpu_kill(). */ - RCU_NONIDLE(complete(&cpu_died)); + complete(&cpu_died); /* * Ensure that the cache lines associated with that completion are diff --git a/arch/arm/mach-tegra/tegra2_emc.c b/arch/arm/mach-tegra/tegra2_emc.c index 9e8bdfa..31e69a0 100644 --- a/arch/arm/mach-tegra/tegra2_emc.c +++ b/arch/arm/mach-tegra/tegra2_emc.c @@ -307,11 +307,6 @@ static int tegra_emc_probe(struct platform_device *pdev) } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - dev_err(&pdev->dev, "missing register base\n"); - return -ENOMEM; - } - emc_regbase = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(emc_regbase)) return PTR_ERR(emc_regbase); diff --git a/arch/arm/plat-samsung/adc.c b/arch/arm/plat-samsung/adc.c index ca07cb1..79690f2 100644 --- a/arch/arm/plat-samsung/adc.c +++ b/arch/arm/plat-samsung/adc.c @@ -381,11 +381,6 @@ static int s3c_adc_probe(struct platform_device *pdev) } regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!regs) { - dev_err(dev, "failed to find registers\n"); - return -ENXIO; - } - adc->regs = devm_ioremap_resource(dev, regs); if (IS_ERR(adc->regs)) return PTR_ERR(adc->regs); diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index d30042e..13609e0 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -152,11 +152,12 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, } EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range); -static int __init xen_secondary_init(unsigned int cpu) +static void __init xen_percpu_init(void *unused) { struct vcpu_register_vcpu_info info; struct vcpu_info *vcpup; int err; + int cpu = get_cpu(); pr_info("Xen: initializing cpu%d\n", cpu); vcpup = per_cpu_ptr(xen_vcpu_info, cpu); @@ -165,14 +166,10 @@ static int __init xen_secondary_init(unsigned int cpu) info.offset = offset_in_page(vcpup); err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info); - if (err) { - pr_debug("register_vcpu_info failed: err=%d\n", err); - } else { - /* This cpu is using the registered vcpu info, even if - later ones fail to. */ - per_cpu(xen_vcpu, cpu) = vcpup; - } - return 0; + BUG_ON(err); + per_cpu(xen_vcpu, cpu) = vcpup; + + enable_percpu_irq(xen_events_irq, 0); } static void xen_restart(char str, const char *cmd) @@ -208,7 +205,6 @@ static int __init xen_guest_init(void) const char *version = NULL; const char *xen_prefix = "xen,xen-"; struct resource res; - int i; node = of_find_compatible_node(NULL, NULL, "xen,xen"); if (!node) { @@ -265,19 +261,23 @@ static int __init xen_guest_init(void) sizeof(struct vcpu_info)); if (xen_vcpu_info == NULL) return -ENOMEM; - for_each_online_cpu(i) - xen_secondary_init(i); gnttab_init(); if (!xen_initial_domain()) xenbus_probe(NULL); + return 0; +} +core_initcall(xen_guest_init); + +static int __init xen_pm_init(void) +{ pm_power_off = xen_power_off; arm_pm_restart = xen_restart; return 0; } -core_initcall(xen_guest_init); +subsys_initcall(xen_pm_init); static irqreturn_t xen_arm_callback(int irq, void *arg) { @@ -285,11 +285,6 @@ static irqreturn_t xen_arm_callback(int irq, void *arg) return IRQ_HANDLED; } -static __init void xen_percpu_enable_events(void *unused) -{ - enable_percpu_irq(xen_events_irq, 0); -} - static int __init xen_init_events(void) { if (!xen_domain() || xen_events_irq < 0) @@ -303,7 +298,7 @@ static int __init xen_init_events(void) return -EINVAL; } - on_each_cpu(xen_percpu_enable_events, NULL, 0); + on_each_cpu(xen_percpu_init, NULL, 0); return 0; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 48347dc..56b3f6d 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -122,8 +122,6 @@ endmenu menu "Kernel Features" -source "kernel/time/Kconfig" - config ARM64_64K_PAGES bool "Enable 64KB pages support" help diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index c8eedc6..5aceb83 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -82,7 +82,7 @@ .macro enable_dbg_if_not_stepping, tmp mrs \tmp, mdscr_el1 - tbnz \tmp, #1, 9990f + tbnz \tmp, #0, 9990f enable_dbg 9990: .endm diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 0c3ba9f..f4726dc 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -136,8 +136,6 @@ void disable_debug_monitors(enum debug_el el) */ static void clear_os_lock(void *unused) { - asm volatile("msr mdscr_el1, %0" : : "r" (0)); - isb(); asm volatile("msr oslar_el1, %0" : : "r" (0)); isb(); } diff --git a/arch/arm64/kernel/early_printk.c b/arch/arm64/kernel/early_printk.c index ac974f4..fbb6e18 100644 --- a/arch/arm64/kernel/early_printk.c +++ b/arch/arm64/kernel/early_printk.c @@ -95,7 +95,7 @@ static void early_write(struct console *con, const char *s, unsigned n) } } -static struct console early_console = { +static struct console early_console_dev = { .name = "earlycon", .write = early_write, .flags = CON_PRINTBUFFER | CON_BOOT, @@ -145,7 +145,8 @@ static int __init setup_early_printk(char *buf) early_base = early_io_map(paddr, EARLYCON_IOBASE); printch = match->printch; - register_console(&early_console); + early_console = &early_console_dev; + register_console(&early_console_dev); return 0; } diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 6a9a532..add6ea6 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -282,12 +282,13 @@ void __init setup_arch(char **cmdline_p) #endif } -static int __init arm64_of_clk_init(void) +static int __init arm64_device_init(void) { of_clk_init(NULL); + of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); return 0; } -arch_initcall(arm64_of_clk_init); +arch_initcall(arm64_device_init); static DEFINE_PER_CPU(struct cpu, cpu_data); @@ -305,13 +306,6 @@ static int __init topology_init(void) } subsys_initcall(topology_init); -static int __init arm64_device_probe(void) -{ - of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); - return 0; -} -device_initcall(arm64_device_probe); - static const char *hwcap_str[] = { "fp", "asimd", diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index abe69b8..48a3860 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -52,7 +52,7 @@ loop1: add x2, x2, #4 // add 4 (line length offset) mov x4, #0x3ff and x4, x4, x1, lsr #3 // find maximum number on the way size - clz x5, x4 // find bit position of way size increment + clz w5, w4 // find bit position of way size increment mov x7, #0x7fff and x7, x7, x1, lsr #13 // extract max number of the index size loop2: diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index f1d8b9b..a82ae88 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -119,8 +119,7 @@ ENTRY(__cpu_setup) mov x0, #3 << 20 msr cpacr_el1, x0 // Enable FP/ASIMD - mov x0, #1 - msr oslar_el1, x0 // Set the debug OS lock + msr mdscr_el1, xzr // Reset mdscr_el1 tlbi vmalle1is // invalidate I + D TLBs /* * Memory region attributes for LPAE: diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig index bdc3558..549903c 100644 --- a/arch/avr32/Kconfig +++ b/arch/avr32/Kconfig @@ -205,6 +205,11 @@ config ARCH_DISCONTIGMEM_ENABLE config ARCH_SPARSEMEM_ENABLE def_bool n +config NODES_SHIFT + int + default "2" + depends on NEED_MULTIPLE_NODES + source "mm/Kconfig" config OWNERSHIP_TRACE diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild index 4dd4f78..d22af85 100644 --- a/arch/avr32/include/asm/Kbuild +++ b/arch/avr32/include/asm/Kbuild @@ -2,3 +2,4 @@ generic-y += clkdev.h generic-y += exec.h generic-y += trace_clock.h +generic-y += param.h diff --git a/arch/avr32/include/asm/numnodes.h b/arch/avr32/include/asm/numnodes.h deleted file mode 100644 index 0b864d7..0000000 --- a/arch/avr32/include/asm/numnodes.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef __ASM_AVR32_NUMNODES_H -#define __ASM_AVR32_NUMNODES_H - -/* Max 4 nodes */ -#define NODES_SHIFT 2 - -#endif /* __ASM_AVR32_NUMNODES_H */ diff --git a/arch/avr32/include/asm/param.h b/arch/avr32/include/asm/param.h deleted file mode 100644 index 009a167..0000000 --- a/arch/avr32/include/asm/param.h +++ /dev/null @@ -1,9 +0,0 @@ -#ifndef __ASM_AVR32_PARAM_H -#define __ASM_AVR32_PARAM_H - -#include <uapi/asm/param.h> - -# define HZ CONFIG_HZ -# define USER_HZ 100 /* User interfaces are in "ticks" */ -# define CLOCKS_PER_SEC (USER_HZ) /* frequency at which times() counts */ -#endif /* __ASM_AVR32_PARAM_H */ diff --git a/arch/avr32/include/uapi/asm/Kbuild b/arch/avr32/include/uapi/asm/Kbuild index df53e7a..3b85ead 100644 --- a/arch/avr32/include/uapi/asm/Kbuild +++ b/arch/avr32/include/uapi/asm/Kbuild @@ -33,3 +33,4 @@ header-y += termbits.h header-y += termios.h header-y += types.h header-y += unistd.h +generic-y += param.h diff --git a/arch/avr32/include/uapi/asm/param.h b/arch/avr32/include/uapi/asm/param.h deleted file mode 100644 index d28aa5e..0000000 --- a/arch/avr32/include/uapi/asm/param.h +++ /dev/null @@ -1,18 +0,0 @@ -#ifndef _UAPI__ASM_AVR32_PARAM_H -#define _UAPI__ASM_AVR32_PARAM_H - - -#ifndef HZ -# define HZ 100 -#endif - -/* TODO: Should be configurable */ -#define EXEC_PAGESIZE 4096 - -#ifndef NOGROUP -# define NOGROUP (-1) -#endif - -#define MAXHOSTNAMELEN 64 - -#endif /* _UAPI__ASM_AVR32_PARAM_H */ diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c index 596f730..2c94129 100644 --- a/arch/avr32/kernel/module.c +++ b/arch/avr32/kernel/module.c @@ -264,7 +264,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, break; case R_AVR32_GOT18SW: if ((relocation & 0xfffe0003) != 0 - && (relocation & 0xfffc0003) != 0xffff0000) + && (relocation & 0xfffc0000) != 0xfffc0000) return reloc_overflow(module, "R_AVR32_GOT18SW", relocation); relocation >>= 2; diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c index cb0f6af..9edc35f 100644 --- a/arch/mips/alchemy/board-gpr.c +++ b/arch/mips/alchemy/board-gpr.c @@ -31,6 +31,7 @@ #include <linux/i2c.h> #include <linux/i2c-gpio.h> #include <asm/bootinfo.h> +#include <asm/idle.h> #include <asm/reboot.h> #include <asm/mach-au1x00/au1000.h> #include <prom.h> diff --git a/arch/mips/alchemy/common/time.c b/arch/mips/alchemy/common/time.c index 38afb11..93fa586 100644 --- a/arch/mips/alchemy/common/time.c +++ b/arch/mips/alchemy/common/time.c @@ -36,6 +36,7 @@ #include <linux/interrupt.h> #include <linux/spinlock.h> +#include <asm/idle.h> #include <asm/processor.h> #include <asm/time.h> #include <asm/mach-au1x00/au1000.h> diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index a0233a2..8be4e85 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -19,6 +19,7 @@ #include <linux/clk.h> #include <asm/bootinfo.h> +#include <asm/idle.h> #include <asm/time.h> /* for mips_hpt_frequency */ #include <asm/reboot.h> /* for _machine_{restart,halt} */ #include <asm/mips_machine.h> diff --git a/arch/mips/cobalt/reset.c b/arch/mips/cobalt/reset.c index 516b442..4eedd48 100644 --- a/arch/mips/cobalt/reset.c +++ b/arch/mips/cobalt/reset.c @@ -12,6 +12,7 @@ #include <linux/io.h> #include <linux/leds.h> +#include <asm/idle.h> #include <asm/processor.h> #include <cobalt.h> diff --git a/arch/mips/configs/db1000_defconfig b/arch/mips/configs/db1000_defconfig index face9d2..bac26b9 100644 --- a/arch/mips/configs/db1000_defconfig +++ b/arch/mips/configs/db1000_defconfig @@ -228,7 +228,6 @@ CONFIG_HIDRAW=y CONFIG_USB_HID=y CONFIG_USB_SUPPORT=y CONFIG_USB=y -CONFIG_USB_SUSPEND=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_ROOT_HUB_TT=y CONFIG_USB_EHCI_TT_NEWSCHED=y diff --git a/arch/mips/configs/db1235_defconfig b/arch/mips/configs/db1235_defconfig index 14752dd..e2b4ad5 100644 --- a/arch/mips/configs/db1235_defconfig +++ b/arch/mips/configs/db1235_defconfig @@ -344,7 +344,6 @@ CONFIG_UHID=y CONFIG_USB_HIDDEV=y CONFIG_USB=y CONFIG_USB_DYNAMIC_MINORS=y -CONFIG_USB_SUSPEND=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_EHCI_ROOT_HUB_TT=y diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig index b6acd2f..343bebc 100644 --- a/arch/mips/configs/lemote2f_defconfig +++ b/arch/mips/configs/lemote2f_defconfig @@ -300,7 +300,6 @@ CONFIG_USB=y CONFIG_USB_DEVICEFS=y # CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_DYNAMIC_MINORS=y -CONFIG_USB_SUSPEND=y CONFIG_USB_OTG_WHITELIST=y CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y diff --git a/arch/mips/include/asm/clock.h b/arch/mips/include/asm/clock.h index c9456e7..778e32d 100644 --- a/arch/mips/include/asm/clock.h +++ b/arch/mips/include/asm/clock.h @@ -6,8 +6,6 @@ #include <linux/seq_file.h> #include <linux/clk.h> -extern void (*cpu_wait) (void); - struct clk; struct clk_ops { diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h new file mode 100644 index 0000000..d192158 --- /dev/null +++ b/arch/mips/include/asm/idle.h @@ -0,0 +1,23 @@ +#ifndef __ASM_IDLE_H +#define __ASM_IDLE_H + +#include <linux/linkage.h> + +extern void (*cpu_wait)(void); +extern void r4k_wait(void); +extern asmlinkage void __r4k_wait(void); +extern void r4k_wait_irqoff(void); +extern void __pastwait(void); + +static inline int using_rollback_handler(void) +{ + return cpu_wait == r4k_wait; +} + +static inline int address_is_in_r4k_wait_irqoff(unsigned long addr) +{ + return addr >= (unsigned long)r4k_wait_irqoff && + addr < (unsigned long)__pastwait; +} + +#endif /* __ASM_IDLE_H */ diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index 1be1372..b7e5985 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -118,7 +118,7 @@ static inline void set_io_port_base(unsigned long base) */ static inline unsigned long virt_to_phys(volatile const void *address) { - return (unsigned long)address - PAGE_OFFSET + PHYS_OFFSET; + return __pa(address); } /* diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index e68781e..143875c 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -336,7 +336,7 @@ enum emulation_result { #define VPN2_MASK 0xffffe000 #define TLB_IS_GLOBAL(x) (((x).tlb_lo0 & MIPS3_PG_G) && ((x).tlb_lo1 & MIPS3_PG_G)) #define TLB_VPN2(x) ((x).tlb_hi & VPN2_MASK) -#define TLB_ASID(x) (ASID_MASK((x).tlb_hi)) +#define TLB_ASID(x) ((x).tlb_hi & ASID_MASK) #define TLB_IS_VALID(x, va) (((va) & (1 << PAGE_SHIFT)) ? ((x).tlb_lo1 & MIPS3_PG_V) : ((x).tlb_lo0 & MIPS3_PG_V)) struct kvm_mips_tlb { diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h index 1554721..8201160 100644 --- a/arch/mips/include/asm/mmu_context.h +++ b/arch/mips/include/asm/mmu_context.h @@ -67,68 +67,45 @@ extern unsigned long pgd_current[]; TLBMISS_HANDLER_SETUP_PGD(swapper_pg_dir) #endif #endif /* CONFIG_MIPS_PGD_C0_CONTEXT*/ +#if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX) -#define ASID_INC(asid) \ -({ \ - unsigned long __asid = asid; \ - __asm__("1:\taddiu\t%0,1\t\t\t\t# patched\n\t" \ - ".section\t__asid_inc,\"a\"\n\t" \ - ".word\t1b\n\t" \ - ".previous" \ - :"=r" (__asid) \ - :"0" (__asid)); \ - __asid; \ -}) -#define ASID_MASK(asid) \ -({ \ - unsigned long __asid = asid; \ - __asm__("1:\tandi\t%0,%1,0xfc0\t\t\t# patched\n\t" \ - ".section\t__asid_mask,\"a\"\n\t" \ - ".word\t1b\n\t" \ - ".previous" \ - :"=r" (__asid) \ - :"r" (__asid)); \ - __asid; \ -}) -#define ASID_VERSION_MASK \ -({ \ - unsigned long __asid; \ - __asm__("1:\taddiu\t%0,$0,0xff00\t\t\t\t# patched\n\t" \ - ".section\t__asid_version_mask,\"a\"\n\t" \ - ".word\t1b\n\t" \ - ".previous" \ - :"=r" (__asid)); \ - __asid; \ -}) -#define ASID_FIRST_VERSION \ -({ \ - unsigned long __asid = asid; \ - __asm__("1:\tli\t%0,0x100\t\t\t\t# patched\n\t" \ - ".section\t__asid_first_version,\"a\"\n\t" \ - ".word\t1b\n\t" \ - ".previous" \ - :"=r" (__asid)); \ - __asid; \ -}) - -#define ASID_FIRST_VERSION_R3000 0x1000 -#define ASID_FIRST_VERSION_R4000 0x100 -#define ASID_FIRST_VERSION_R8000 0x1000 -#define ASID_FIRST_VERSION_RM9000 0x1000 +#define ASID_INC 0x40 +#define ASID_MASK 0xfc0 + +#elif defined(CONFIG_CPU_R8000) + +#define ASID_INC 0x10 +#define ASID_MASK 0xff0 + +#elif defined(CONFIG_MIPS_MT_SMTC) + +#define ASID_INC 0x1 +extern unsigned long smtc_asid_mask; +#define ASID_MASK (smtc_asid_mask) +#define HW_ASID_MASK 0xff +/* End SMTC/34K debug hack */ +#else /* FIXME: not correct for R6000 */ + +#define ASID_INC 0x1 +#define ASID_MASK 0xff -#ifdef CONFIG_MIPS_MT_SMTC -#define SMTC_HW_ASID_MASK 0xff -extern unsigned int smtc_asid_mask; #endif #define cpu_context(cpu, mm) ((mm)->context.asid[cpu]) -#define cpu_asid(cpu, mm) ASID_MASK(cpu_context((cpu), (mm))) +#define cpu_asid(cpu, mm) (cpu_context((cpu), (mm)) & ASID_MASK) #define asid_cache(cpu) (cpu_data[cpu].asid_cache) static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { } +/* + * All unused by hardware upper bits will be considered + * as a software asid extension. + */ +#define ASID_VERSION_MASK ((unsigned long)~(ASID_MASK|(ASID_MASK-1))) +#define ASID_FIRST_VERSION ((unsigned long)(~ASID_VERSION_MASK) + 1) + #ifndef CONFIG_MIPS_MT_SMTC /* Normal, classic MIPS get_new_mmu_context */ static inline void @@ -137,7 +114,7 @@ get_new_mmu_context(struct mm_struct *mm, unsigned long cpu) extern void kvm_local_flush_tlb_all(void); unsigned long asid = asid_cache(cpu); - if (!ASID_MASK((asid = ASID_INC(asid)))) { + if (! ((asid += ASID_INC) & ASID_MASK) ) { if (cpu_has_vtag_icache) flush_icache_all(); #ifdef CONFIG_VIRTUALIZATION @@ -200,7 +177,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * free up the ASID value for use and flush any old * instances of it from the TLB. */ - oldasid = ASID_MASK(read_c0_entryhi()); + oldasid = (read_c0_entryhi() & ASID_MASK); if(smtc_live_asid[mytlb][oldasid]) { smtc_live_asid[mytlb][oldasid] &= ~(0x1 << cpu); if(smtc_live_asid[mytlb][oldasid] == 0) @@ -211,7 +188,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * having ASID_MASK smaller than the hardware maximum, * make sure no "soft" bits become "hard"... */ - write_c0_entryhi((read_c0_entryhi() & ~SMTC_HW_ASID_MASK) | + write_c0_entryhi((read_c0_entryhi() & ~HW_ASID_MASK) | cpu_asid(cpu, next)); ehb(); /* Make sure it propagates to TCStatus */ evpe(mtflags); @@ -264,15 +241,15 @@ activate_mm(struct mm_struct *prev, struct mm_struct *next) #ifdef CONFIG_MIPS_MT_SMTC /* See comments for similar code above */ mtflags = dvpe(); - oldasid = ASID_MASK(read_c0_entryhi()); + oldasid = read_c0_entryhi() & ASID_MASK; if(smtc_live_asid[mytlb][oldasid]) { smtc_live_asid[mytlb][oldasid] &= ~(0x1 << cpu); if(smtc_live_asid[mytlb][oldasid] == 0) smtc_flush_tlb_asid(oldasid); } /* See comments for similar code above */ - write_c0_entryhi((read_c0_entryhi() & ~SMTC_HW_ASID_MASK) | - cpu_asid(cpu, next)); + write_c0_entryhi((read_c0_entryhi() & ~HW_ASID_MASK) | + cpu_asid(cpu, next)); ehb(); /* Make sure it propagates to TCStatus */ evpe(mtflags); #else @@ -309,14 +286,14 @@ drop_mmu_context(struct mm_struct *mm, unsigned cpu) #ifdef CONFIG_MIPS_MT_SMTC /* See comments for similar code above */ prevvpe = dvpe(); - oldasid = ASID_MASK(read_c0_entryhi()); + oldasid = (read_c0_entryhi() & ASID_MASK); if (smtc_live_asid[mytlb][oldasid]) { smtc_live_asid[mytlb][oldasid] &= ~(0x1 << cpu); if(smtc_live_asid[mytlb][oldasid] == 0) smtc_flush_tlb_asid(oldasid); } /* See comments for similar code above */ - write_c0_entryhi((read_c0_entryhi() & ~SMTC_HW_ASID_MASK) + write_c0_entryhi((read_c0_entryhi() & ~HW_ASID_MASK) | cpu_asid(cpu, mm)); ehb(); /* Make sure it propagates to TCStatus */ evpe(prevvpe); diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index eab99e5..f59552f 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -46,7 +46,6 @@ #endif /* CONFIG_MIPS_HUGE_TLB_SUPPORT */ #include <linux/pfn.h> -#include <asm/io.h> extern void build_clear_page(void); extern void build_copy_page(void); @@ -151,6 +150,7 @@ typedef struct { unsigned long pgprot; } pgprot_t; ((unsigned long)(x) - PAGE_OFFSET + PHYS_OFFSET) #endif #define __va(x) ((void *)((unsigned long)(x) + PAGE_OFFSET - PHYS_OFFSET)) +#include <asm/io.h> /* * RELOC_HIDE was originally added by 6007b903dfe5f1d13e0c711ac2894bdd4a61b1ad @@ -171,14 +171,13 @@ typedef struct { unsigned long pgprot; } pgprot_t; #ifdef CONFIG_FLATMEM -#define pfn_valid(pfn) \ -({ \ - unsigned long __pfn = (pfn); \ - /* avoid <linux/bootmem.h> include hell */ \ - extern unsigned long min_low_pfn; \ - \ - __pfn >= min_low_pfn && __pfn < max_mapnr; \ -}) +static inline int pfn_valid(unsigned long pfn) +{ + /* avoid <linux/mm.h> include hell */ + extern unsigned long max_mapnr; + + return pfn >= ARCH_PFN_OFFSET && pfn < max_mapnr; +} #elif defined(CONFIG_SPARSEMEM) diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index 71686c8..1470b7b 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -28,7 +28,6 @@ /* * System setup and hardware flags.. */ -extern void (*cpu_wait)(void); extern unsigned int vced_count, vcei_count; diff --git a/arch/mips/include/asm/kvm.h b/arch/mips/include/uapi/asm/kvm.h index 85789ea..85789ea 100644 --- a/arch/mips/include/asm/kvm.h +++ b/arch/mips/include/uapi/asm/kvm.h diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h index 16338b8..1dee279 100644 --- a/arch/mips/include/uapi/asm/unistd.h +++ b/arch/mips/include/uapi/asm/unistd.h @@ -694,16 +694,17 @@ #define __NR_process_vm_writev (__NR_Linux + 305) #define __NR_kcmp (__NR_Linux + 306) #define __NR_finit_module (__NR_Linux + 307) +#define __NR_getdents64 (__NR_Linux + 308) /* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 307 +#define __NR_Linux_syscalls 308 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 307 +#define __NR_64_Linux_syscalls 308 #if _MIPS_SIM == _MIPS_SIM_NABI32 diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 6ad9e04..423d871 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -4,7 +4,7 @@ extra-y := head.o vmlinux.lds -obj-y += cpu-probe.o branch.o entry.o genex.o irq.o process.o \ +obj-y += cpu-probe.o branch.o entry.o genex.o idle.o irq.o process.o \ prom.o ptrace.o reset.o setup.o signal.o syscall.o \ time.o topology.o traps.o unaligned.o watch.o vdso.o diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 4bbffdb..c6568bf 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -27,105 +27,6 @@ #include <asm/spram.h> #include <asm/uaccess.h> -/* - * Not all of the MIPS CPUs have the "wait" instruction available. Moreover, - * the implementation of the "wait" feature differs between CPU families. This - * points to the function that implements CPU specific wait. - * The wait instruction stops the pipeline and reduces the power consumption of - * the CPU very much. - */ -void (*cpu_wait)(void); -EXPORT_SYMBOL(cpu_wait); - -static void r3081_wait(void) -{ - unsigned long cfg = read_c0_conf(); - write_c0_conf(cfg | R30XX_CONF_HALT); -} - -static void r39xx_wait(void) -{ - local_irq_disable(); - if (!need_resched()) - write_c0_conf(read_c0_conf() | TX39_CONF_HALT); - local_irq_enable(); -} - -extern void r4k_wait(void); - -/* - * This variant is preferable as it allows testing need_resched and going to - * sleep depending on the outcome atomically. Unfortunately the "It is - * implementation-dependent whether the pipeline restarts when a non-enabled - * interrupt is requested" restriction in the MIPS32/MIPS64 architecture makes - * using this version a gamble. - */ -void r4k_wait_irqoff(void) -{ - local_irq_disable(); - if (!need_resched()) - __asm__(" .set push \n" - " .set mips3 \n" - " wait \n" - " .set pop \n"); - local_irq_enable(); - __asm__(" .globl __pastwait \n" - "__pastwait: \n"); -} - -/* - * The RM7000 variant has to handle erratum 38. The workaround is to not - * have any pending stores when the WAIT instruction is executed. - */ -static void rm7k_wait_irqoff(void) -{ - local_irq_disable(); - if (!need_resched()) - __asm__( - " .set push \n" - " .set mips3 \n" - " .set noat \n" - " mfc0 $1, $12 \n" - " sync \n" - " mtc0 $1, $12 # stalls until W stage \n" - " wait \n" - " mtc0 $1, $12 # stalls until W stage \n" - " .set pop \n"); - local_irq_enable(); -} - -/* - * The Au1xxx wait is available only if using 32khz counter or - * external timer source, but specifically not CP0 Counter. - * alchemy/common/time.c may override cpu_wait! - */ -static void au1k_wait(void) -{ - __asm__(" .set mips3 \n" - " cache 0x14, 0(%0) \n" - " cache 0x14, 32(%0) \n" - " sync \n" - " nop \n" - " wait \n" - " nop \n" - " nop \n" - " nop \n" - " nop \n" - " .set mips0 \n" - : : "r" (au1k_wait)); -} - -static int __initdata nowait; - -static int __init wait_disable(char *s) -{ - nowait = 1; - - return 1; -} - -__setup("nowait", wait_disable); - static int __cpuinitdata mips_fpu_disabled; static int __init fpu_disable(char *s) @@ -150,105 +51,6 @@ static int __init dsp_disable(char *s) __setup("nodsp", dsp_disable); -void __init check_wait(void) -{ - struct cpuinfo_mips *c = ¤t_cpu_data; - - if (nowait) { - printk("Wait instruction disabled.\n"); - return; - } - - switch (c->cputype) { - case CPU_R3081: - case CPU_R3081E: - cpu_wait = r3081_wait; - break; - case CPU_TX3927: - cpu_wait = r39xx_wait; - break; - case CPU_R4200: -/* case CPU_R4300: */ - case CPU_R4600: - case CPU_R4640: - case CPU_R4650: - case CPU_R4700: - case CPU_R5000: - case CPU_R5500: - case CPU_NEVADA: - case CPU_4KC: - case CPU_4KEC: - case CPU_4KSC: - case CPU_5KC: - case CPU_25KF: - case CPU_PR4450: - case CPU_BMIPS3300: - case CPU_BMIPS4350: - case CPU_BMIPS4380: - case CPU_BMIPS5000: - case CPU_CAVIUM_OCTEON: - case CPU_CAVIUM_OCTEON_PLUS: - case CPU_CAVIUM_OCTEON2: - case CPU_JZRISC: - case CPU_LOONGSON1: - case CPU_XLR: - case CPU_XLP: - cpu_wait = r4k_wait; - break; - - case CPU_RM7000: - cpu_wait = rm7k_wait_irqoff; - break; - - case CPU_M14KC: - case CPU_M14KEC: - case CPU_24K: - case CPU_34K: - case CPU_1004K: - cpu_wait = r4k_wait; - if (read_c0_config7() & MIPS_CONF7_WII) - cpu_wait = r4k_wait_irqoff; - break; - - case CPU_74K: - cpu_wait = r4k_wait; - if ((c->processor_id & 0xff) >= PRID_REV_ENCODE_332(2, 1, 0)) - cpu_wait = r4k_wait_irqoff; - break; - - case CPU_TX49XX: - cpu_wait = r4k_wait_irqoff; - break; - case CPU_ALCHEMY: - cpu_wait = au1k_wait; - break; - case CPU_20KC: - /* - * WAIT on Rev1.0 has E1, E2, E3 and E16. - * WAIT on Rev2.0 and Rev3.0 has E16. - * Rev3.1 WAIT is nop, why bother - */ - if ((c->processor_id & 0xff) <= 0x64) - break; - - /* - * Another rev is incremeting c0_count at a reduced clock - * rate while in WAIT mode. So we basically have the choice - * between using the cp0 timer as clocksource or avoiding - * the WAIT instruction. Until more details are known, - * disable the use of WAIT for 20Kc entirely. - cpu_wait = r4k_wait; - */ - break; - case CPU_RM9000: - if ((c->processor_id & 0x00ff) >= 0x40) - cpu_wait = r4k_wait; - break; - default: - break; - } -} - static inline void check_errata(void) { struct cpuinfo_mips *c = ¤t_cpu_data; diff --git a/arch/mips/kernel/crash_dump.c b/arch/mips/kernel/crash_dump.c index 35bed0d..3be9e7b 100644 --- a/arch/mips/kernel/crash_dump.c +++ b/arch/mips/kernel/crash_dump.c @@ -2,6 +2,7 @@ #include <linux/bootmem.h> #include <linux/crash_dump.h> #include <asm/uaccess.h> +#include <linux/slab.h> static int __init parse_savemaxmem(char *p) { diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index 5c2ba9f..31fa856 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -122,7 +122,7 @@ handle_vcei: __FINIT .align 5 /* 32 byte rollback region */ -LEAF(r4k_wait) +LEAF(__r4k_wait) .set push .set noreorder /* start of rollback region */ @@ -146,14 +146,14 @@ LEAF(r4k_wait) jr ra nop .set pop - END(r4k_wait) + END(__r4k_wait) .macro BUILD_ROLLBACK_PROLOGUE handler FEXPORT(rollback_\handler) .set push .set noat MFC0 k0, CP0_EPC - PTR_LA k1, r4k_wait + PTR_LA k1, __r4k_wait ori k0, 0x1f /* 32 byte rollback region */ xori k0, 0x1f bne k0, k1, 9f @@ -493,7 +493,7 @@ NESTED(nmi_handler, PT_SIZE, sp) .set noreorder /* check if TLB contains a entry for EPC */ MFC0 k1, CP0_ENTRYHI - andi k1, 0xff /* ASID_MASK patched at run-time!! */ + andi k1, 0xff /* ASID_MASK */ MFC0 k0, CP0_EPC PTR_SRL k0, _PAGE_SHIFT + 1 PTR_SLL k0, _PAGE_SHIFT + 1 diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c new file mode 100644 index 0000000..3b09b88 --- /dev/null +++ b/arch/mips/kernel/idle.c @@ -0,0 +1,244 @@ +/* + * MIPS idle loop and WAIT instruction support. + * + * Copyright (C) xxxx the Anonymous + * Copyright (C) 1994 - 2006 Ralf Baechle + * Copyright (C) 2003, 2004 Maciej W. Rozycki + * Copyright (C) 2001, 2004, 2011, 2012 MIPS Technologies, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/export.h> +#include <linux/init.h> +#include <linux/irqflags.h> +#include <linux/printk.h> +#include <linux/sched.h> +#include <asm/cpu.h> +#include <asm/cpu-info.h> +#include <asm/idle.h> +#include <asm/mipsregs.h> + +/* + * Not all of the MIPS CPUs have the "wait" instruction available. Moreover, + * the implementation of the "wait" feature differs between CPU families. This + * points to the function that implements CPU specific wait. + * The wait instruction stops the pipeline and reduces the power consumption of + * the CPU very much. + */ +void (*cpu_wait)(void); +EXPORT_SYMBOL(cpu_wait); + +static void r3081_wait(void) +{ + unsigned long cfg = read_c0_conf(); + write_c0_conf(cfg | R30XX_CONF_HALT); + local_irq_enable(); +} + +static void r39xx_wait(void) +{ + if (!need_resched()) + write_c0_conf(read_c0_conf() | TX39_CONF_HALT); + local_irq_enable(); +} + +void r4k_wait(void) +{ + local_irq_enable(); + __r4k_wait(); +} + +/* + * This variant is preferable as it allows testing need_resched and going to + * sleep depending on the outcome atomically. Unfortunately the "It is + * implementation-dependent whether the pipeline restarts when a non-enabled + * interrupt is requested" restriction in the MIPS32/MIPS64 architecture makes + * using this version a gamble. + */ +void r4k_wait_irqoff(void) +{ + if (!need_resched()) + __asm__( + " .set push \n" + " .set mips3 \n" + " wait \n" + " .set pop \n"); + local_irq_enable(); + __asm__( + " .globl __pastwait \n" + "__pastwait: \n"); +} + +/* + * The RM7000 variant has to handle erratum 38. The workaround is to not + * have any pending stores when the WAIT instruction is executed. + */ +static void rm7k_wait_irqoff(void) +{ + if (!need_resched()) + __asm__( + " .set push \n" + " .set mips3 \n" + " .set noat \n" + " mfc0 $1, $12 \n" + " sync \n" + " mtc0 $1, $12 # stalls until W stage \n" + " wait \n" + " mtc0 $1, $12 # stalls until W stage \n" + " .set pop \n"); + local_irq_enable(); +} + +/* + * The Au1xxx wait is available only if using 32khz counter or + * external timer source, but specifically not CP0 Counter. + * alchemy/common/time.c may override cpu_wait! + */ +static void au1k_wait(void) +{ + __asm__( + " .set mips3 \n" + " cache 0x14, 0(%0) \n" + " cache 0x14, 32(%0) \n" + " sync \n" + " nop \n" + " wait \n" + " nop \n" + " nop \n" + " nop \n" + " nop \n" + " .set mips0 \n" + : : "r" (au1k_wait)); + local_irq_enable(); +} + +static int __initdata nowait; + +static int __init wait_disable(char *s) +{ + nowait = 1; + + return 1; +} + +__setup("nowait", wait_disable); + +void __init check_wait(void) +{ + struct cpuinfo_mips *c = ¤t_cpu_data; + + if (nowait) { + printk("Wait instruction disabled.\n"); + return; + } + + switch (c->cputype) { + case CPU_R3081: + case CPU_R3081E: + cpu_wait = r3081_wait; + break; + case CPU_TX3927: + cpu_wait = r39xx_wait; + break; + case CPU_R4200: +/* case CPU_R4300: */ + case CPU_R4600: + case CPU_R4640: + case CPU_R4650: + case CPU_R4700: + case CPU_R5000: + case CPU_R5500: + case CPU_NEVADA: + case CPU_4KC: + case CPU_4KEC: + case CPU_4KSC: + case CPU_5KC: + case CPU_25KF: + case CPU_PR4450: + case CPU_BMIPS3300: + case CPU_BMIPS4350: + case CPU_BMIPS4380: + case CPU_BMIPS5000: + case CPU_CAVIUM_OCTEON: + case CPU_CAVIUM_OCTEON_PLUS: + case CPU_CAVIUM_OCTEON2: + case CPU_JZRISC: + case CPU_LOONGSON1: + case CPU_XLR: + case CPU_XLP: + cpu_wait = r4k_wait; + break; + + case CPU_RM7000: + cpu_wait = rm7k_wait_irqoff; + break; + + case CPU_M14KC: + case CPU_M14KEC: + case CPU_24K: + case CPU_34K: + case CPU_1004K: + cpu_wait = r4k_wait; + if (read_c0_config7() & MIPS_CONF7_WII) + cpu_wait = r4k_wait_irqoff; + break; + + case CPU_74K: + cpu_wait = r4k_wait; + if ((c->processor_id & 0xff) >= PRID_REV_ENCODE_332(2, 1, 0)) + cpu_wait = r4k_wait_irqoff; + break; + + case CPU_TX49XX: + cpu_wait = r4k_wait_irqoff; + break; + case CPU_ALCHEMY: + cpu_wait = au1k_wait; + break; + case CPU_20KC: + /* + * WAIT on Rev1.0 has E1, E2, E3 and E16. + * WAIT on Rev2.0 and Rev3.0 has E16. + * Rev3.1 WAIT is nop, why bother + */ + if ((c->processor_id & 0xff) <= 0x64) + break; + + /* + * Another rev is incremeting c0_count at a reduced clock + * rate while in WAIT mode. So we basically have the choice + * between using the cp0 timer as clocksource or avoiding + * the WAIT instruction. Until more details are known, + * disable the use of WAIT for 20Kc entirely. + cpu_wait = r4k_wait; + */ + break; + case CPU_RM9000: + if ((c->processor_id & 0x00ff) >= 0x40) + cpu_wait = r4k_wait; + break; + default: + break; + } +} + +static void smtc_idle_hook(void) +{ +#ifdef CONFIG_MIPS_MT_SMTC + void smtc_idle_loop_hook(void); + + smtc_idle_loop_hook(); +#endif +} + +void arch_cpu_idle(void) +{ + smtc_idle_hook(); + if (cpu_wait) + cpu_wait(); + else + local_irq_enable(); +} diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c index 12bc4eb..1f8187a 100644 --- a/arch/mips/kernel/kprobes.c +++ b/arch/mips/kernel/kprobes.c @@ -207,7 +207,10 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p) void __kprobes arch_remove_kprobe(struct kprobe *p) { - free_insn_slot(p->ainsn.insn, 0); + if (p->ainsn.insn) { + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; + } } static void save_previous_kprobe(struct kprobe_ctlblk *kcb) diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index a3e4614..acb3437 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -10,6 +10,7 @@ #include <asm/bootinfo.h> #include <asm/cpu.h> #include <asm/cpu-features.h> +#include <asm/idle.h> #include <asm/mipsregs.h> #include <asm/processor.h> #include <asm/prom.h> diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index eb902c1..c6a041d 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -51,19 +51,6 @@ void arch_cpu_idle_dead(void) } #endif -void arch_cpu_idle(void) -{ -#ifdef CONFIG_MIPS_MT_SMTC - extern void smtc_idle_loop_hook(void); - - smtc_idle_loop_hook(); -#endif - if (cpu_wait) - (*cpu_wait)(); - else - local_irq_enable(); -} - asmlinkage void ret_from_fork(void); asmlinkage void ret_from_kernel_thread(void); @@ -224,6 +211,9 @@ struct mips_frame_info { int pc_offset; }; +#define J_TARGET(pc,target) \ + (((unsigned long)(pc) & 0xf0000000) | ((target) << 2)) + static inline int is_ra_save_ins(union mips_instruction *ip) { #ifdef CONFIG_CPU_MICROMIPS @@ -264,7 +254,7 @@ static inline int is_ra_save_ins(union mips_instruction *ip) #endif } -static inline int is_jal_jalr_jr_ins(union mips_instruction *ip) +static inline int is_jump_ins(union mips_instruction *ip) { #ifdef CONFIG_CPU_MICROMIPS /* @@ -288,6 +278,8 @@ static inline int is_jal_jalr_jr_ins(union mips_instruction *ip) return 0; return (((ip->u_format.uimmediate >> 6) & mm_jalr_op) == mm_jalr_op); #else + if (ip->j_format.opcode == j_op) + return 1; if (ip->j_format.opcode == jal_op) return 1; if (ip->r_format.opcode != spec_op) @@ -350,7 +342,7 @@ static int get_frame_info(struct mips_frame_info *info) for (i = 0; i < max_insns; i++, ip++) { - if (is_jal_jalr_jr_ins(ip)) + if (is_jump_ins(ip)) break; if (!info->frame_size) { if (is_sp_move_ins(ip)) @@ -393,15 +385,42 @@ err: static struct mips_frame_info schedule_mfi __read_mostly; +#ifdef CONFIG_KALLSYMS +static unsigned long get___schedule_addr(void) +{ + return kallsyms_lookup_name("__schedule"); +} +#else +static unsigned long get___schedule_addr(void) +{ + union mips_instruction *ip = (void *)schedule; + int max_insns = 8; + int i; + + for (i = 0; i < max_insns; i++, ip++) { + if (ip->j_format.opcode == j_op) + return J_TARGET(ip, ip->j_format.target); + } + return 0; +} +#endif + static int __init frame_info_init(void) { unsigned long size = 0; #ifdef CONFIG_KALLSYMS unsigned long ofs; +#endif + unsigned long addr; + + addr = get___schedule_addr(); + if (!addr) + addr = (unsigned long)schedule; - kallsyms_lookup_size_offset((unsigned long)schedule, &size, &ofs); +#ifdef CONFIG_KALLSYMS + kallsyms_lookup_size_offset(addr, &size, &ofs); #endif - schedule_mfi.func = schedule; + schedule_mfi.func = (void *)addr; schedule_mfi.func_size = size; get_frame_info(&schedule_mfi); diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 36cfd40..97a5909 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -423,4 +423,5 @@ sys_call_table: PTR sys_process_vm_writev /* 5305 */ PTR sys_kcmp PTR sys_finit_module + PTR sys_getdents64 .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index c17619f..6e7862a 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -37,6 +37,7 @@ #include <linux/atomic.h> #include <asm/cpu.h> #include <asm/processor.h> +#include <asm/idle.h> #include <asm/r4k-timer.h> #include <asm/mmu_context.h> #include <asm/time.h> diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index 31d22f3..75a4fd7 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -34,6 +34,7 @@ #include <asm/hardirq.h> #include <asm/hazards.h> #include <asm/irq.h> +#include <asm/idle.h> #include <asm/mmu_context.h> #include <asm/mipsregs.h> #include <asm/cacheflush.h> @@ -111,7 +112,7 @@ static int vpe0limit; static int ipibuffers; static int nostlb; static int asidmask; -unsigned int smtc_asid_mask = 0xff; +unsigned long smtc_asid_mask = 0xff; static int __init vpe0tcs(char *str) { @@ -858,7 +859,6 @@ void smtc_send_ipi(int cpu, int type, unsigned int action) unsigned long flags; int mtflags; unsigned long tcrestart; - extern void r4k_wait_irqoff(void), __pastwait(void); int set_resched_flag = (type == LINUX_SMP_IPI && action == SMP_RESCHEDULE_YOURSELF); @@ -914,8 +914,7 @@ void smtc_send_ipi(int cpu, int type, unsigned int action) */ if (cpu_wait == r4k_wait_irqoff) { tcrestart = read_tc_c0_tcrestart(); - if (tcrestart >= (unsigned long)r4k_wait_irqoff - && tcrestart < (unsigned long)__pastwait) { + if (address_is_in_r4k_wait_irqoff(tcrestart)) { write_tc_c0_tcrestart(__pastwait); tcstatus &= ~TCSTATUS_IXMT; write_tc_c0_tcstatus(tcstatus); @@ -1395,7 +1394,7 @@ void smtc_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu) asid = asid_cache(cpu); do { - if (!ASID_MASK(ASID_INC(asid))) { + if (!((asid += ASID_INC) & ASID_MASK) ) { if (cpu_has_vtag_icache) flush_icache_all(); /* Traverse all online CPUs (hack requires contiguous range) */ @@ -1414,7 +1413,7 @@ void smtc_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu) mips_ihb(); } tcstat = read_tc_c0_tcstatus(); - smtc_live_asid[tlb][ASID_MASK(tcstat)] |= (asiduse)(0x1 << i); + smtc_live_asid[tlb][(tcstat & ASID_MASK)] |= (asiduse)(0x1 << i); if (!prevhalt) write_tc_c0_tchalt(0); } @@ -1423,7 +1422,7 @@ void smtc_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu) asid = ASID_FIRST_VERSION; local_flush_tlb_all(); /* start new asid cycle */ } - } while (smtc_live_asid[tlb][ASID_MASK(asid)]); + } while (smtc_live_asid[tlb][(asid & ASID_MASK)]); /* * SMTC shares the TLB within VPEs and possibly across all VPEs. @@ -1461,7 +1460,7 @@ void smtc_flush_tlb_asid(unsigned long asid) tlb_read(); ehb(); ehi = read_c0_entryhi(); - if (ASID_MASK(ehi) == asid) { + if ((ehi & ASID_MASK) == asid) { /* * Invalidate only entries with specified ASID, * makiing sure all entries differ. diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 77cff1f..e3be670 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -41,6 +41,7 @@ #include <asm/dsp.h> #include <asm/fpu.h> #include <asm/fpu_emulator.h> +#include <asm/idle.h> #include <asm/mipsregs.h> #include <asm/mipsmtregs.h> #include <asm/module.h> @@ -57,7 +58,6 @@ #include <asm/uasm.h> extern void check_wait(void); -extern asmlinkage void r4k_wait(void); extern asmlinkage void rollback_handle_int(void); extern asmlinkage void handle_int(void); extern u32 handle_tlbl[]; @@ -1542,7 +1542,7 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs) extern char except_vec_vi, except_vec_vi_lui; extern char except_vec_vi_ori, except_vec_vi_end; extern char rollback_except_vec_vi; - char *vec_start = (cpu_wait == r4k_wait) ? + char *vec_start = using_rollback_handler() ? &rollback_except_vec_vi : &except_vec_vi; #ifdef CONFIG_MIPS_MT_SMTC /* @@ -1656,7 +1656,6 @@ void __cpuinit per_cpu_trap_init(bool is_boot_cpu) unsigned int cpu = smp_processor_id(); unsigned int status_set = ST0_CU0; unsigned int hwrena = cpu_hwrena_impl_bits; - unsigned long asid = 0; #ifdef CONFIG_MIPS_MT_SMTC int secondaryTC = 0; int bootTC = (cpu == 0); @@ -1740,9 +1739,8 @@ void __cpuinit per_cpu_trap_init(bool is_boot_cpu) } #endif /* CONFIG_MIPS_MT_SMTC */ - asid = ASID_FIRST_VERSION; - cpu_data[cpu].asid_cache = asid; - TLBMISS_HANDLER_SETUP(); + if (!cpu_data[cpu].asid_cache) + cpu_data[cpu].asid_cache = ASID_FIRST_VERSION; atomic_inc(&init_mm.mm_count); current->active_mm = &init_mm; @@ -1814,10 +1812,8 @@ void __init trap_init(void) extern char except_vec4; extern char except_vec3_r4000; unsigned long i; - int rollback; check_wait(); - rollback = (cpu_wait == r4k_wait); #if defined(CONFIG_KGDB) if (kgdb_early_setup) @@ -1894,7 +1890,8 @@ void __init trap_init(void) if (board_be_init) board_be_init(); - set_except_vector(0, rollback ? rollback_handle_int : handle_int); + set_except_vector(0, using_rollback_handler() ? rollback_handle_int + : handle_int); set_except_vector(1, handle_tlbm); set_except_vector(2, handle_tlbl); set_except_vector(3, handle_tlbs); diff --git a/arch/mips/kvm/kvm_mips_emul.c b/arch/mips/kvm/kvm_mips_emul.c index 2b2bac9..4b6274b 100644 --- a/arch/mips/kvm/kvm_mips_emul.c +++ b/arch/mips/kvm/kvm_mips_emul.c @@ -525,16 +525,18 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause, printk("MTCz, cop0->reg[EBASE]: %#lx\n", kvm_read_c0_guest_ebase(cop0)); } else if (rd == MIPS_CP0_TLB_HI && sel == 0) { - uint32_t nasid = ASID_MASK(vcpu->arch.gprs[rt]); + uint32_t nasid = + vcpu->arch.gprs[rt] & ASID_MASK; if ((KSEGX(vcpu->arch.gprs[rt]) != CKSEG0) && - (ASID_MASK(kvm_read_c0_guest_entryhi(cop0)) - != nasid)) { + ((kvm_read_c0_guest_entryhi(cop0) & + ASID_MASK) != nasid)) { kvm_debug ("MTCz, change ASID from %#lx to %#lx\n", - ASID_MASK(kvm_read_c0_guest_entryhi(cop0)), - ASID_MASK(vcpu->arch.gprs[rt])); + kvm_read_c0_guest_entryhi(cop0) & + ASID_MASK, + vcpu->arch.gprs[rt] & ASID_MASK); /* Blow away the shadow host TLBs */ kvm_mips_flush_host_tlb(1); @@ -986,7 +988,8 @@ kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, uint32_t cause, * resulting handler will do the right thing */ index = kvm_mips_guest_tlb_lookup(vcpu, (va & VPN2_MASK) | - ASID_MASK(kvm_read_c0_guest_entryhi(cop0))); + (kvm_read_c0_guest_entryhi + (cop0) & ASID_MASK)); if (index < 0) { vcpu->arch.host_cp0_entryhi = (va & VPN2_MASK); @@ -1151,7 +1154,7 @@ kvm_mips_emulate_tlbmiss_ld(unsigned long cause, uint32_t *opc, struct kvm_vcpu_arch *arch = &vcpu->arch; enum emulation_result er = EMULATE_DONE; unsigned long entryhi = (vcpu->arch. host_cp0_badvaddr & VPN2_MASK) | - ASID_MASK(kvm_read_c0_guest_entryhi(cop0)); + (kvm_read_c0_guest_entryhi(cop0) & ASID_MASK); if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { /* save old pc */ @@ -1198,7 +1201,7 @@ kvm_mips_emulate_tlbinv_ld(unsigned long cause, uint32_t *opc, enum emulation_result er = EMULATE_DONE; unsigned long entryhi = (vcpu->arch.host_cp0_badvaddr & VPN2_MASK) | - ASID_MASK(kvm_read_c0_guest_entryhi(cop0)); + (kvm_read_c0_guest_entryhi(cop0) & ASID_MASK); if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { /* save old pc */ @@ -1243,7 +1246,7 @@ kvm_mips_emulate_tlbmiss_st(unsigned long cause, uint32_t *opc, struct kvm_vcpu_arch *arch = &vcpu->arch; enum emulation_result er = EMULATE_DONE; unsigned long entryhi = (vcpu->arch.host_cp0_badvaddr & VPN2_MASK) | - ASID_MASK(kvm_read_c0_guest_entryhi(cop0)); + (kvm_read_c0_guest_entryhi(cop0) & ASID_MASK); if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { /* save old pc */ @@ -1287,7 +1290,7 @@ kvm_mips_emulate_tlbinv_st(unsigned long cause, uint32_t *opc, struct kvm_vcpu_arch *arch = &vcpu->arch; enum emulation_result er = EMULATE_DONE; unsigned long entryhi = (vcpu->arch.host_cp0_badvaddr & VPN2_MASK) | - ASID_MASK(kvm_read_c0_guest_entryhi(cop0)); + (kvm_read_c0_guest_entryhi(cop0) & ASID_MASK); if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { /* save old pc */ @@ -1356,7 +1359,7 @@ kvm_mips_emulate_tlbmod(unsigned long cause, uint32_t *opc, { struct mips_coproc *cop0 = vcpu->arch.cop0; unsigned long entryhi = (vcpu->arch.host_cp0_badvaddr & VPN2_MASK) | - ASID_MASK(kvm_read_c0_guest_entryhi(cop0)); + (kvm_read_c0_guest_entryhi(cop0) & ASID_MASK); struct kvm_vcpu_arch *arch = &vcpu->arch; enum emulation_result er = EMULATE_DONE; @@ -1783,8 +1786,8 @@ kvm_mips_handle_tlbmiss(unsigned long cause, uint32_t *opc, */ index = kvm_mips_guest_tlb_lookup(vcpu, (va & VPN2_MASK) | - ASID_MASK(kvm_read_c0_guest_entryhi - (vcpu->arch.cop0))); + (kvm_read_c0_guest_entryhi + (vcpu->arch.cop0) & ASID_MASK)); if (index < 0) { if (exccode == T_TLB_LD_MISS) { er = kvm_mips_emulate_tlbmiss_ld(cause, opc, run, vcpu); diff --git a/arch/mips/kvm/kvm_tlb.c b/arch/mips/kvm/kvm_tlb.c index 89511a9..c777dd3 100644 --- a/arch/mips/kvm/kvm_tlb.c +++ b/arch/mips/kvm/kvm_tlb.c @@ -17,6 +17,8 @@ #include <linux/delay.h> #include <linux/module.h> #include <linux/kvm_host.h> +#include <linux/srcu.h> + #include <asm/cpu.h> #include <asm/bootinfo.h> @@ -51,13 +53,13 @@ EXPORT_SYMBOL(kvm_mips_is_error_pfn); uint32_t kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu) { - return ASID_MASK(vcpu->arch.guest_kernel_asid[smp_processor_id()]); + return vcpu->arch.guest_kernel_asid[smp_processor_id()] & ASID_MASK; } uint32_t kvm_mips_get_user_asid(struct kvm_vcpu *vcpu) { - return ASID_MASK(vcpu->arch.guest_user_asid[smp_processor_id()]); + return vcpu->arch.guest_user_asid[smp_processor_id()] & ASID_MASK; } inline uint32_t kvm_mips_get_commpage_asid (struct kvm_vcpu *vcpu) @@ -84,7 +86,7 @@ void kvm_mips_dump_host_tlbs(void) old_pagemask = read_c0_pagemask(); printk("HOST TLBs:\n"); - printk("ASID: %#lx\n", ASID_MASK(read_c0_entryhi())); + printk("ASID: %#lx\n", read_c0_entryhi() & ASID_MASK); for (i = 0; i < current_cpu_data.tlbsize; i++) { write_c0_index(i); @@ -169,21 +171,27 @@ void kvm_mips_dump_shadow_tlbs(struct kvm_vcpu *vcpu) } } -static void kvm_mips_map_page(struct kvm *kvm, gfn_t gfn) +static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn) { + int srcu_idx, err = 0; pfn_t pfn; if (kvm->arch.guest_pmap[gfn] != KVM_INVALID_PAGE) - return; + return 0; + srcu_idx = srcu_read_lock(&kvm->srcu); pfn = kvm_mips_gfn_to_pfn(kvm, gfn); if (kvm_mips_is_error_pfn(pfn)) { - panic("Couldn't get pfn for gfn %#" PRIx64 "!\n", gfn); + kvm_err("Couldn't get pfn for gfn %#" PRIx64 "!\n", gfn); + err = -EFAULT; + goto out; } kvm->arch.guest_pmap[gfn] = pfn; - return; +out: + srcu_read_unlock(&kvm->srcu, srcu_idx); + return err; } /* Translate guest KSEG0 addresses to Host PA */ @@ -207,7 +215,10 @@ unsigned long kvm_mips_translate_guest_kseg0_to_hpa(struct kvm_vcpu *vcpu, gva); return KVM_INVALID_PAGE; } - kvm_mips_map_page(vcpu->kvm, gfn); + + if (kvm_mips_map_page(vcpu->kvm, gfn) < 0) + return KVM_INVALID_ADDR; + return (kvm->arch.guest_pmap[gfn] << PAGE_SHIFT) + offset; } @@ -310,8 +321,11 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr, even = !(gfn & 0x1); vaddr = badvaddr & (PAGE_MASK << 1); - kvm_mips_map_page(vcpu->kvm, gfn); - kvm_mips_map_page(vcpu->kvm, gfn ^ 0x1); + if (kvm_mips_map_page(vcpu->kvm, gfn) < 0) + return -1; + + if (kvm_mips_map_page(vcpu->kvm, gfn ^ 0x1) < 0) + return -1; if (even) { pfn0 = kvm->arch.guest_pmap[gfn]; @@ -389,8 +403,11 @@ kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, pfn0 = 0; pfn1 = 0; } else { - kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo0) >> PAGE_SHIFT); - kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo1) >> PAGE_SHIFT); + if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo0) >> PAGE_SHIFT) < 0) + return -1; + + if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo1) >> PAGE_SHIFT) < 0) + return -1; pfn0 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo0) >> PAGE_SHIFT]; pfn1 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo1) >> PAGE_SHIFT]; @@ -428,7 +445,7 @@ int kvm_mips_guest_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long entryhi) for (i = 0; i < KVM_MIPS_GUEST_TLB_SIZE; i++) { if (((TLB_VPN2(tlb[i]) & ~tlb[i].tlb_mask) == ((entryhi & VPN2_MASK) & ~tlb[i].tlb_mask)) && - (TLB_IS_GLOBAL(tlb[i]) || (TLB_ASID(tlb[i]) == ASID_MASK(entryhi)))) { + (TLB_IS_GLOBAL(tlb[i]) || (TLB_ASID(tlb[i]) == (entryhi & ASID_MASK)))) { index = i; break; } @@ -626,7 +643,7 @@ kvm_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu, { unsigned long asid = asid_cache(cpu); - if (!(ASID_MASK(ASID_INC(asid)))) { + if (!((asid += ASID_INC) & ASID_MASK)) { if (cpu_has_vtag_icache) { flush_icache_all(); } @@ -804,7 +821,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (!newasid) { /* If we preempted while the guest was executing, then reload the pre-empted ASID */ if (current->flags & PF_VCPU) { - write_c0_entryhi(ASID_MASK(vcpu->arch.preempt_entryhi)); + write_c0_entryhi(vcpu->arch. + preempt_entryhi & ASID_MASK); ehb(); } } else { @@ -816,11 +834,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) */ if (current->flags & PF_VCPU) { if (KVM_GUEST_KERNEL_MODE(vcpu)) - write_c0_entryhi(ASID_MASK(vcpu->arch. - guest_kernel_asid[cpu])); + write_c0_entryhi(vcpu->arch. + guest_kernel_asid[cpu] & + ASID_MASK); else - write_c0_entryhi(ASID_MASK(vcpu->arch. - guest_user_asid[cpu])); + write_c0_entryhi(vcpu->arch. + guest_user_asid[cpu] & + ASID_MASK); ehb(); } } @@ -879,7 +899,8 @@ uint32_t kvm_get_inst(uint32_t *opc, struct kvm_vcpu *vcpu) kvm_mips_guest_tlb_lookup(vcpu, ((unsigned long) opc & VPN2_MASK) | - ASID_MASK(kvm_read_c0_guest_entryhi(cop0))); + (kvm_read_c0_guest_entryhi + (cop0) & ASID_MASK)); if (index < 0) { kvm_err ("%s: get_user_failed for %p, vcpu: %p, ASID: %#lx\n", diff --git a/arch/mips/lantiq/xway/gptu.c b/arch/mips/lantiq/xway/gptu.c index 9861c86..850821d 100644 --- a/arch/mips/lantiq/xway/gptu.c +++ b/arch/mips/lantiq/xway/gptu.c @@ -144,10 +144,6 @@ static int gptu_probe(struct platform_device *pdev) } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - dev_err(&pdev->dev, "Failed to get resource\n"); - return -ENOMEM; - } /* remap gptu register range */ gptu_membase = devm_ioremap_resource(&pdev->dev, res); @@ -169,6 +165,8 @@ static int gptu_probe(struct platform_device *pdev) if (((gptu_r32(GPTU_ID) >> 8) & 0xff) != GPTU_MAGIC) { dev_err(&pdev->dev, "Failed to find magic\n"); gptu_hwexit(); + clk_disable(clk); + clk_put(clk); return -ENAVAIL; } diff --git a/arch/mips/lib/dump_tlb.c b/arch/mips/lib/dump_tlb.c index 8a12d00..32b9f21 100644 --- a/arch/mips/lib/dump_tlb.c +++ b/arch/mips/lib/dump_tlb.c @@ -11,7 +11,6 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/tlbdebug.h> -#include <asm/mmu_context.h> static inline const char *msk2str(unsigned int mask) { @@ -56,7 +55,7 @@ static void dump_tlb(int first, int last) s_pagemask = read_c0_pagemask(); s_entryhi = read_c0_entryhi(); s_index = read_c0_index(); - asid = ASID_MASK(s_entryhi); + asid = s_entryhi & 0xff; for (i = first; i <= last; i++) { write_c0_index(i); @@ -86,7 +85,7 @@ static void dump_tlb(int first, int last) printk("va=%0*lx asid=%02lx\n", width, (entryhi & ~0x1fffUL), - ASID_MASK(entryhi)); + entryhi & 0xff); printk("\t[pa=%0*llx c=%d d=%d v=%d g=%d] ", width, (entrylo0 << 6) & PAGE_MASK, c0, diff --git a/arch/mips/lib/r3k_dump_tlb.c b/arch/mips/lib/r3k_dump_tlb.c index 8327698..91615c2 100644 --- a/arch/mips/lib/r3k_dump_tlb.c +++ b/arch/mips/lib/r3k_dump_tlb.c @@ -9,7 +9,6 @@ #include <linux/mm.h> #include <asm/mipsregs.h> -#include <asm/mmu_context.h> #include <asm/page.h> #include <asm/pgtable.h> #include <asm/tlbdebug.h> @@ -22,7 +21,7 @@ static void dump_tlb(int first, int last) unsigned int asid; unsigned long entryhi, entrylo0; - asid = ASID_MASK(read_c0_entryhi()); + asid = read_c0_entryhi() & 0xfc0; for (i = first; i <= last; i++) { write_c0_index(i<<8); @@ -36,7 +35,7 @@ static void dump_tlb(int first, int last) /* Unused entries have a virtual address of KSEG0. */ if ((entryhi & 0xffffe000) != 0x80000000 - && (ASID_MASK(entryhi) == asid)) { + && (entryhi & 0xfc0) == asid) { /* * Only print entries in use */ @@ -45,7 +44,7 @@ static void dump_tlb(int first, int last) printk("va=%08lx asid=%08lx" " [pa=%06lx n=%d d=%d v=%d g=%d]", (entryhi & 0xffffe000), - ASID_MASK(entryhi), + entryhi & 0xfc0, entrylo0 & PAGE_MASK, (entrylo0 & (1 << 11)) ? 1 : 0, (entrylo0 & (1 << 10)) ? 1 : 0, diff --git a/arch/mips/loongson/common/reset.c b/arch/mips/loongson/common/reset.c index 35c8c64..65bfbb5 100644 --- a/arch/mips/loongson/common/reset.c +++ b/arch/mips/loongson/common/reset.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/pm.h> +#include <asm/idle.h> #include <asm/reboot.h> #include <loongson.h> diff --git a/arch/mips/loongson1/common/reset.c b/arch/mips/loongson1/common/reset.c index d4f610f..547f34b 100644 --- a/arch/mips/loongson1/common/reset.c +++ b/arch/mips/loongson1/common/reset.c @@ -9,6 +9,7 @@ #include <linux/io.h> #include <linux/pm.h> +#include <asm/idle.h> #include <asm/reboot.h> #include <loongson1.h> diff --git a/arch/mips/mm/tlb-r3k.c b/arch/mips/mm/tlb-r3k.c index 4a13c15..a63d1ed 100644 --- a/arch/mips/mm/tlb-r3k.c +++ b/arch/mips/mm/tlb-r3k.c @@ -51,7 +51,7 @@ void local_flush_tlb_all(void) #endif local_irq_save(flags); - old_ctx = ASID_MASK(read_c0_entryhi()); + old_ctx = read_c0_entryhi() & ASID_MASK; write_c0_entrylo0(0); entry = r3k_have_wired_reg ? read_c0_wired() : 8; for (; entry < current_cpu_data.tlbsize; entry++) { @@ -87,13 +87,13 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, #ifdef DEBUG_TLB printk("[tlbrange<%lu,0x%08lx,0x%08lx>]", - ASID_MASK(cpu_context(cpu, mm)), start, end); + cpu_context(cpu, mm) & ASID_MASK, start, end); #endif local_irq_save(flags); size = (end - start + (PAGE_SIZE - 1)) >> PAGE_SHIFT; if (size <= current_cpu_data.tlbsize) { - int oldpid = ASID_MASK(read_c0_entryhi()); - int newpid = ASID_MASK(cpu_context(cpu, mm)); + int oldpid = read_c0_entryhi() & ASID_MASK; + int newpid = cpu_context(cpu, mm) & ASID_MASK; start &= PAGE_MASK; end += PAGE_SIZE - 1; @@ -166,10 +166,10 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page) #ifdef DEBUG_TLB printk("[tlbpage<%lu,0x%08lx>]", cpu_context(cpu, vma->vm_mm), page); #endif - newpid = ASID_MASK(cpu_context(cpu, vma->vm_mm)); + newpid = cpu_context(cpu, vma->vm_mm) & ASID_MASK; page &= PAGE_MASK; local_irq_save(flags); - oldpid = ASID_MASK(read_c0_entryhi()); + oldpid = read_c0_entryhi() & ASID_MASK; write_c0_entryhi(page | newpid); BARRIER; tlb_probe(); @@ -197,10 +197,10 @@ void __update_tlb(struct vm_area_struct *vma, unsigned long address, pte_t pte) if (current->active_mm != vma->vm_mm) return; - pid = ASID_MASK(read_c0_entryhi()); + pid = read_c0_entryhi() & ASID_MASK; #ifdef DEBUG_TLB - if ((pid != ASID_MASK(cpu_context(cpu, vma->vm_mm))) || (cpu_context(cpu, vma->vm_mm) == 0)) { + if ((pid != (cpu_context(cpu, vma->vm_mm) & ASID_MASK)) || (cpu_context(cpu, vma->vm_mm) == 0)) { printk("update_mmu_cache: Wheee, bogus tlbpid mmpid=%lu tlbpid=%d\n", (cpu_context(cpu, vma->vm_mm)), pid); } @@ -241,7 +241,7 @@ void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1, local_irq_save(flags); /* Save old context and create impossible VPN2 value */ - old_ctx = ASID_MASK(read_c0_entryhi()); + old_ctx = read_c0_entryhi() & ASID_MASK; old_pagemask = read_c0_pagemask(); w = read_c0_wired(); write_c0_wired(w + 1); @@ -264,7 +264,7 @@ void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1, #endif local_irq_save(flags); - old_ctx = ASID_MASK(read_c0_entryhi()); + old_ctx = read_c0_entryhi() & ASID_MASK; write_c0_entrylo0(entrylo0); write_c0_entryhi(entryhi); write_c0_index(wired); diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 09653b2..c643de4 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -287,7 +287,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte) ENTER_CRITICAL(flags); - pid = ASID_MASK(read_c0_entryhi()); + pid = read_c0_entryhi() & ASID_MASK; address &= (PAGE_MASK << 1); write_c0_entryhi(address | pid); pgdp = pgd_offset(vma->vm_mm, address); diff --git a/arch/mips/mm/tlb-r8k.c b/arch/mips/mm/tlb-r8k.c index 122f920..91c2499 100644 --- a/arch/mips/mm/tlb-r8k.c +++ b/arch/mips/mm/tlb-r8k.c @@ -195,7 +195,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte) if (current->active_mm != vma->vm_mm) return; - pid = ASID_MASK(read_c0_entryhi()); + pid = read_c0_entryhi() & ASID_MASK; local_irq_save(flags); address &= PAGE_MASK; diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 4d46d37..ce9818e 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -29,7 +29,6 @@ #include <linux/init.h> #include <linux/cache.h> -#include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/pgtable.h> #include <asm/war.h> @@ -306,78 +305,6 @@ static struct uasm_reloc relocs[128] __cpuinitdata; static int check_for_high_segbits __cpuinitdata; #endif -static void __cpuinit insn_fixup(unsigned int **start, unsigned int **stop, - unsigned int i_const) -{ - unsigned int **p; - - for (p = start; p < stop; p++) { -#ifndef CONFIG_CPU_MICROMIPS - unsigned int *ip; - - ip = *p; - *ip = (*ip & 0xffff0000) | i_const; -#else - unsigned short *ip; - - ip = ((unsigned short *)((unsigned int)*p - 1)); - if ((*ip & 0xf000) == 0x4000) { - *ip &= 0xfff1; - *ip |= (i_const << 1); - } else if ((*ip & 0xf000) == 0x6000) { - *ip &= 0xfff1; - *ip |= ((i_const >> 2) << 1); - } else { - ip++; - *ip = i_const; - } -#endif - local_flush_icache_range((unsigned long)ip, - (unsigned long)ip + sizeof(*ip)); - } -} - -#define asid_insn_fixup(section, const) \ -do { \ - extern unsigned int *__start_ ## section; \ - extern unsigned int *__stop_ ## section; \ - insn_fixup(&__start_ ## section, &__stop_ ## section, const); \ -} while(0) - -/* - * Caller is assumed to flush the caches before the first context switch. - */ -static void __cpuinit setup_asid(unsigned int inc, unsigned int mask, - unsigned int version_mask, - unsigned int first_version) -{ - extern asmlinkage void handle_ri_rdhwr_vivt(void); - unsigned long *vivt_exc; - -#ifdef CONFIG_CPU_MICROMIPS - /* - * Worst case optimised microMIPS addiu instructions support - * only a 3-bit immediate value. - */ - if(inc > 7) - panic("Invalid ASID increment value!"); -#endif - asid_insn_fixup(__asid_inc, inc); - asid_insn_fixup(__asid_mask, mask); - asid_insn_fixup(__asid_version_mask, version_mask); - asid_insn_fixup(__asid_first_version, first_version); - - /* Patch up the 'handle_ri_rdhwr_vivt' handler. */ - vivt_exc = (unsigned long *) &handle_ri_rdhwr_vivt; -#ifdef CONFIG_CPU_MICROMIPS - vivt_exc = (unsigned long *)((unsigned long) vivt_exc - 1); -#endif - vivt_exc++; - *vivt_exc = (*vivt_exc & ~mask) | mask; - - current_cpu_data.asid_cache = first_version; -} - static int check_for_high_segbits __cpuinitdata; static unsigned int kscratch_used_mask __cpuinitdata; @@ -2256,7 +2183,6 @@ void __cpuinit build_tlb_refill_handler(void) case CPU_TX3922: case CPU_TX3927: #ifndef CONFIG_MIPS_PGD_C0_CONTEXT - setup_asid(0x40, 0xfc0, 0xf000, ASID_FIRST_VERSION_R3000); if (cpu_has_local_ebase) build_r3000_tlb_refill_handler(); if (!run_once) { @@ -2282,11 +2208,6 @@ void __cpuinit build_tlb_refill_handler(void) break; default: -#ifndef CONFIG_MIPS_MT_SMTC - setup_asid(0x1, 0xff, 0xff00, ASID_FIRST_VERSION_R4000); -#else - setup_asid(0x1, smtc_asid_mask, 0xff00, ASID_FIRST_VERSION_R4000); -#endif if (!run_once) { scratch_reg = allocate_kscratch(); #ifdef CONFIG_MIPS_PGD_C0_CONTEXT diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c index af31914..eaa99d2 100644 --- a/arch/mips/netlogic/xlp/setup.c +++ b/arch/mips/netlogic/xlp/setup.c @@ -37,6 +37,7 @@ #include <linux/pm.h> #include <linux/bootmem.h> +#include <asm/idle.h> #include <asm/reboot.h> #include <asm/time.h> #include <asm/bootinfo.h> diff --git a/arch/mips/netlogic/xlr/setup.c b/arch/mips/netlogic/xlr/setup.c index e3e0941..89c8c10 100644 --- a/arch/mips/netlogic/xlr/setup.c +++ b/arch/mips/netlogic/xlr/setup.c @@ -36,6 +36,7 @@ #include <linux/serial_8250.h> #include <linux/pm.h> +#include <asm/idle.h> #include <asm/reboot.h> #include <asm/time.h> #include <asm/bootinfo.h> diff --git a/arch/mips/pmcs-msp71xx/msp_prom.c b/arch/mips/pmcs-msp71xx/msp_prom.c index 0edb89a..1c98975 100644 --- a/arch/mips/pmcs-msp71xx/msp_prom.c +++ b/arch/mips/pmcs-msp71xx/msp_prom.c @@ -83,7 +83,7 @@ static inline unsigned char str2hexnum(unsigned char c) return 0; /* foo */ } -static inline int str2eaddr(unsigned char *ea, unsigned char *str) +int str2eaddr(unsigned char *ea, unsigned char *str) { int index = 0; unsigned char num = 0; diff --git a/arch/mips/pmcs-msp71xx/msp_setup.c b/arch/mips/pmcs-msp71xx/msp_setup.c index 1651cfd..396b296 100644 --- a/arch/mips/pmcs-msp71xx/msp_setup.c +++ b/arch/mips/pmcs-msp71xx/msp_setup.c @@ -12,6 +12,7 @@ #include <asm/bootinfo.h> #include <asm/cacheflush.h> +#include <asm/idle.h> #include <asm/r4kcache.h> #include <asm/reboot.h> #include <asm/smp-ops.h> diff --git a/arch/mips/ralink/dts/rt3050.dtsi b/arch/mips/ralink/dts/rt3050.dtsi index ef7da1e..e3203d4 100644 --- a/arch/mips/ralink/dts/rt3050.dtsi +++ b/arch/mips/ralink/dts/rt3050.dtsi @@ -55,4 +55,14 @@ reg-shift = <2>; }; }; + + usb@101c0000 { + compatible = "ralink,rt3050-usb", "snps,dwc2"; + reg = <0x101c0000 40000>; + + interrupt-parent = <&intc>; + interrupts = <18>; + + status = "disabled"; + }; }; diff --git a/arch/mips/ralink/dts/rt3052_eval.dts b/arch/mips/ralink/dts/rt3052_eval.dts index c18c9a8..0ac73ea 100644 --- a/arch/mips/ralink/dts/rt3052_eval.dts +++ b/arch/mips/ralink/dts/rt3052_eval.dts @@ -43,4 +43,8 @@ reg = <0x50000 0x7b0000>; }; }; + + usb@101c0000 { + status = "ok"; + }; }; diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c index 5364aab..681e7f8 100644 --- a/arch/mips/txx9/generic/setup.c +++ b/arch/mips/txx9/generic/setup.c @@ -26,6 +26,7 @@ #include <linux/slab.h> #include <linux/irq.h> #include <asm/bootinfo.h> +#include <asm/idle.h> #include <asm/time.h> #include <asm/reboot.h> #include <asm/r4kcache.h> diff --git a/arch/mips/vr41xx/common/pmu.c b/arch/mips/vr41xx/common/pmu.c index 70a3f90..d7f7558 100644 --- a/arch/mips/vr41xx/common/pmu.c +++ b/arch/mips/vr41xx/common/pmu.c @@ -27,6 +27,7 @@ #include <asm/cacheflush.h> #include <asm/cpu.h> +#include <asm/idle.h> #include <asm/io.h> #include <asm/processor.h> #include <asm/reboot.h> diff --git a/arch/mips/wrppmc/reset.c b/arch/mips/wrppmc/reset.c index cc5474b..80beb18 100644 --- a/arch/mips/wrppmc/reset.c +++ b/arch/mips/wrppmc/reset.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <asm/cacheflush.h> +#include <asm/idle.h> #include <asm/mipsregs.h> #include <asm/processor.h> diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index cad060f..6507dab 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -245,7 +245,7 @@ config SMP config IRQSTACKS bool "Use separate kernel stacks when processing interrupts" - default n + default y help If you say Y here the kernel will use separate kernel stacks for handling hard and soft interrupts. This can help avoid diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 2f967cc..1976900 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -23,24 +23,21 @@ NM = sh $(srctree)/arch/parisc/nm CHECKFLAGS += -D__hppa__=1 LIBGCC = $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name) -MACHINE := $(shell uname -m) -NATIVE := $(if $(filter parisc%,$(MACHINE)),1,0) - ifdef CONFIG_64BIT UTS_MACHINE := parisc64 CHECKFLAGS += -D__LP64__=1 -m64 -WIDTH := 64 +CC_ARCHES = hppa64 else # 32-bit -WIDTH := +CC_ARCHES = hppa hppa2.0 hppa1.1 endif -# attempt to help out folks who are cross-compiling -ifeq ($(NATIVE),1) -CROSS_COMPILE := hppa$(WIDTH)-linux- -else - ifeq ($(CROSS_COMPILE),) - CROSS_COMPILE := hppa$(WIDTH)-linux-gnu- - endif +ifneq ($(SUBARCH),$(UTS_MACHINE)) + ifeq ($(CROSS_COMPILE),) + CC_SUFFIXES = linux linux-gnu unknown-linux-gnu + CROSS_COMPILE := $(call cc-cross-prefix, \ + $(foreach a,$(CC_ARCHES), \ + $(foreach s,$(CC_SUFFIXES),$(a)-$(s)-))) + endif endif OBJCOPY_FLAGS =-O binary -R .note -R .comment -S diff --git a/arch/parisc/include/asm/hardirq.h b/arch/parisc/include/asm/hardirq.h index 12373c4..c19f713 100644 --- a/arch/parisc/include/asm/hardirq.h +++ b/arch/parisc/include/asm/hardirq.h @@ -11,10 +11,18 @@ #include <linux/threads.h> #include <linux/irq.h> +#ifdef CONFIG_IRQSTACKS +#define __ARCH_HAS_DO_SOFTIRQ +#endif + typedef struct { unsigned int __softirq_pending; #ifdef CONFIG_DEBUG_STACKOVERFLOW unsigned int kernel_stack_usage; +#ifdef CONFIG_IRQSTACKS + unsigned int irq_stack_usage; + unsigned int irq_stack_counter; +#endif #endif #ifdef CONFIG_SMP unsigned int irq_resched_count; @@ -28,6 +36,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); #define __ARCH_IRQ_STAT #define __IRQ_STAT(cpu, member) (irq_stat[cpu].member) #define inc_irq_stat(member) this_cpu_inc(irq_stat.member) +#define __inc_irq_stat(member) __this_cpu_inc(irq_stat.member) #define local_softirq_pending() this_cpu_read(irq_stat.__softirq_pending) #define __ARCH_SET_SOFTIRQ_PENDING diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index 0640155..cfbc439 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -63,10 +63,13 @@ */ #ifdef __KERNEL__ +#include <linux/spinlock_types.h> + #define IRQ_STACK_SIZE (4096 << 2) /* 16k irq stack size */ union irq_stack_union { unsigned long stack[IRQ_STACK_SIZE/sizeof(unsigned long)]; + raw_spinlock_t lock; }; DECLARE_PER_CPU(union irq_stack_union, irq_stack_union); diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index 4bb96ad..ae27cb6 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -452,9 +452,41 @@ L2_ptep \pgd,\pte,\index,\va,\fault .endm + /* Acquire pa_dbit_lock lock. */ + .macro dbit_lock spc,tmp,tmp1 +#ifdef CONFIG_SMP + cmpib,COND(=),n 0,\spc,2f + load32 PA(pa_dbit_lock),\tmp +1: LDCW 0(\tmp),\tmp1 + cmpib,COND(=) 0,\tmp1,1b + nop +2: +#endif + .endm + + /* Release pa_dbit_lock lock without reloading lock address. */ + .macro dbit_unlock0 spc,tmp +#ifdef CONFIG_SMP + or,COND(=) %r0,\spc,%r0 + stw \spc,0(\tmp) +#endif + .endm + + /* Release pa_dbit_lock lock. */ + .macro dbit_unlock1 spc,tmp +#ifdef CONFIG_SMP + load32 PA(pa_dbit_lock),\tmp + dbit_unlock0 \spc,\tmp +#endif + .endm + /* Set the _PAGE_ACCESSED bit of the PTE. Be clever and * don't needlessly dirty the cache line if it was already set */ - .macro update_ptep ptep,pte,tmp,tmp1 + .macro update_ptep spc,ptep,pte,tmp,tmp1 +#ifdef CONFIG_SMP + or,COND(=) %r0,\spc,%r0 + LDREG 0(\ptep),\pte +#endif ldi _PAGE_ACCESSED,\tmp1 or \tmp1,\pte,\tmp and,COND(<>) \tmp1,\pte,%r0 @@ -463,7 +495,11 @@ /* Set the dirty bit (and accessed bit). No need to be * clever, this is only used from the dirty fault */ - .macro update_dirty ptep,pte,tmp + .macro update_dirty spc,ptep,pte,tmp +#ifdef CONFIG_SMP + or,COND(=) %r0,\spc,%r0 + LDREG 0(\ptep),\pte +#endif ldi _PAGE_ACCESSED|_PAGE_DIRTY,\tmp or \tmp,\pte,\pte STREG \pte,0(\ptep) @@ -1111,11 +1147,13 @@ dtlb_miss_20w: L3_ptep ptp,pte,t0,va,dtlb_check_alias_20w - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot idtlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1135,11 +1173,13 @@ nadtlb_miss_20w: L3_ptep ptp,pte,t0,va,nadtlb_check_alias_20w - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot idtlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1161,7 +1201,8 @@ dtlb_miss_11: L2_ptep ptp,pte,t0,va,dtlb_check_alias_11 - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot @@ -1172,6 +1213,7 @@ dtlb_miss_11: idtlbp prot,(%sr1,va) mtsp t0, %sr1 /* Restore sr1 */ + dbit_unlock1 spc,t0 rfir nop @@ -1192,7 +1234,8 @@ nadtlb_miss_11: L2_ptep ptp,pte,t0,va,nadtlb_check_alias_11 - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot @@ -1204,6 +1247,7 @@ nadtlb_miss_11: idtlbp prot,(%sr1,va) mtsp t0, %sr1 /* Restore sr1 */ + dbit_unlock1 spc,t0 rfir nop @@ -1224,13 +1268,15 @@ dtlb_miss_20: L2_ptep ptp,pte,t0,va,dtlb_check_alias_20 - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot f_extend pte,t0 idtlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1250,13 +1296,15 @@ nadtlb_miss_20: L2_ptep ptp,pte,t0,va,nadtlb_check_alias_20 - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot f_extend pte,t0 idtlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1357,11 +1405,13 @@ itlb_miss_20w: L3_ptep ptp,pte,t0,va,itlb_fault - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot iitlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1379,11 +1429,13 @@ naitlb_miss_20w: L3_ptep ptp,pte,t0,va,naitlb_check_alias_20w - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot iitlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1405,7 +1457,8 @@ itlb_miss_11: L2_ptep ptp,pte,t0,va,itlb_fault - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot @@ -1416,6 +1469,7 @@ itlb_miss_11: iitlbp prot,(%sr1,va) mtsp t0, %sr1 /* Restore sr1 */ + dbit_unlock1 spc,t0 rfir nop @@ -1427,7 +1481,8 @@ naitlb_miss_11: L2_ptep ptp,pte,t0,va,naitlb_check_alias_11 - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot @@ -1438,6 +1493,7 @@ naitlb_miss_11: iitlbp prot,(%sr1,va) mtsp t0, %sr1 /* Restore sr1 */ + dbit_unlock1 spc,t0 rfir nop @@ -1459,13 +1515,15 @@ itlb_miss_20: L2_ptep ptp,pte,t0,va,itlb_fault - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot f_extend pte,t0 iitlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1477,13 +1535,15 @@ naitlb_miss_20: L2_ptep ptp,pte,t0,va,naitlb_check_alias_20 - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot f_extend pte,t0 iitlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1507,29 +1567,13 @@ dbit_trap_20w: L3_ptep ptp,pte,t0,va,dbit_fault -#ifdef CONFIG_SMP - cmpib,COND(=),n 0,spc,dbit_nolock_20w - load32 PA(pa_dbit_lock),t0 - -dbit_spin_20w: - LDCW 0(t0),t1 - cmpib,COND(=) 0,t1,dbit_spin_20w - nop - -dbit_nolock_20w: -#endif - update_dirty ptp,pte,t1 + dbit_lock spc,t0,t1 + update_dirty spc,ptp,pte,t1 make_insert_tlb spc,pte,prot idtlbt pte,prot -#ifdef CONFIG_SMP - cmpib,COND(=),n 0,spc,dbit_nounlock_20w - ldi 1,t1 - stw t1,0(t0) - -dbit_nounlock_20w: -#endif + dbit_unlock0 spc,t0 rfir nop @@ -1543,18 +1587,8 @@ dbit_trap_11: L2_ptep ptp,pte,t0,va,dbit_fault -#ifdef CONFIG_SMP - cmpib,COND(=),n 0,spc,dbit_nolock_11 - load32 PA(pa_dbit_lock),t0 - -dbit_spin_11: - LDCW 0(t0),t1 - cmpib,= 0,t1,dbit_spin_11 - nop - -dbit_nolock_11: -#endif - update_dirty ptp,pte,t1 + dbit_lock spc,t0,t1 + update_dirty spc,ptp,pte,t1 make_insert_tlb_11 spc,pte,prot @@ -1565,13 +1599,7 @@ dbit_nolock_11: idtlbp prot,(%sr1,va) mtsp t1, %sr1 /* Restore sr1 */ -#ifdef CONFIG_SMP - cmpib,COND(=),n 0,spc,dbit_nounlock_11 - ldi 1,t1 - stw t1,0(t0) - -dbit_nounlock_11: -#endif + dbit_unlock0 spc,t0 rfir nop @@ -1583,32 +1611,15 @@ dbit_trap_20: L2_ptep ptp,pte,t0,va,dbit_fault -#ifdef CONFIG_SMP - cmpib,COND(=),n 0,spc,dbit_nolock_20 - load32 PA(pa_dbit_lock),t0 - -dbit_spin_20: - LDCW 0(t0),t1 - cmpib,= 0,t1,dbit_spin_20 - nop - -dbit_nolock_20: -#endif - update_dirty ptp,pte,t1 + dbit_lock spc,t0,t1 + update_dirty spc,ptp,pte,t1 make_insert_tlb spc,pte,prot f_extend pte,t1 idtlbt pte,prot - -#ifdef CONFIG_SMP - cmpib,COND(=),n 0,spc,dbit_nounlock_20 - ldi 1,t1 - stw t1,0(t0) - -dbit_nounlock_20: -#endif + dbit_unlock0 spc,t0 rfir nop diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index e255db0..55237a7 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -166,22 +166,32 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%*s: ", prec, "STK"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->kernel_stack_usage); - seq_printf(p, " Kernel stack usage\n"); + seq_puts(p, " Kernel stack usage\n"); +# ifdef CONFIG_IRQSTACKS + seq_printf(p, "%*s: ", prec, "IST"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->irq_stack_usage); + seq_puts(p, " Interrupt stack usage\n"); + seq_printf(p, "%*s: ", prec, "ISC"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->irq_stack_counter); + seq_puts(p, " Interrupt stack usage counter\n"); +# endif #endif #ifdef CONFIG_SMP seq_printf(p, "%*s: ", prec, "RES"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count); - seq_printf(p, " Rescheduling interrupts\n"); + seq_puts(p, " Rescheduling interrupts\n"); seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_call_count); - seq_printf(p, " Function call interrupts\n"); + seq_puts(p, " Function call interrupts\n"); #endif seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count); - seq_printf(p, " TLB shootdowns\n"); + seq_puts(p, " TLB shootdowns\n"); return 0; } @@ -378,6 +388,7 @@ static inline void stack_overflow_check(struct pt_regs *regs) unsigned long sp = regs->gr[30]; unsigned long stack_usage; unsigned int *last_usage; + int cpu = smp_processor_id(); /* if sr7 != 0, we interrupted a userspace process which we do not want * to check for stack overflow. We will only check the kernel stack. */ @@ -386,7 +397,31 @@ static inline void stack_overflow_check(struct pt_regs *regs) /* calculate kernel stack usage */ stack_usage = sp - stack_start; - last_usage = &per_cpu(irq_stat.kernel_stack_usage, smp_processor_id()); +#ifdef CONFIG_IRQSTACKS + if (likely(stack_usage <= THREAD_SIZE)) + goto check_kernel_stack; /* found kernel stack */ + + /* check irq stack usage */ + stack_start = (unsigned long) &per_cpu(irq_stack_union, cpu).stack; + stack_usage = sp - stack_start; + + last_usage = &per_cpu(irq_stat.irq_stack_usage, cpu); + if (unlikely(stack_usage > *last_usage)) + *last_usage = stack_usage; + + if (likely(stack_usage < (IRQ_STACK_SIZE - STACK_MARGIN))) + return; + + pr_emerg("stackcheck: %s will most likely overflow irq stack " + "(sp:%lx, stk bottom-top:%lx-%lx)\n", + current->comm, sp, stack_start, stack_start + IRQ_STACK_SIZE); + goto panic_check; + +check_kernel_stack: +#endif + + /* check kernel stack usage */ + last_usage = &per_cpu(irq_stat.kernel_stack_usage, cpu); if (unlikely(stack_usage > *last_usage)) *last_usage = stack_usage; @@ -398,31 +433,69 @@ static inline void stack_overflow_check(struct pt_regs *regs) "(sp:%lx, stk bottom-top:%lx-%lx)\n", current->comm, sp, stack_start, stack_start + THREAD_SIZE); +#ifdef CONFIG_IRQSTACKS +panic_check: +#endif if (sysctl_panic_on_stackoverflow) panic("low stack detected by irq handler - check messages\n"); #endif } #ifdef CONFIG_IRQSTACKS -DEFINE_PER_CPU(union irq_stack_union, irq_stack_union); +DEFINE_PER_CPU(union irq_stack_union, irq_stack_union) = { + .lock = __RAW_SPIN_LOCK_UNLOCKED((irq_stack_union).lock) + }; static void execute_on_irq_stack(void *func, unsigned long param1) { - unsigned long *irq_stack_start; + union irq_stack_union *union_ptr; unsigned long irq_stack; - int cpu = smp_processor_id(); + raw_spinlock_t *irq_stack_in_use; - irq_stack_start = &per_cpu(irq_stack_union, cpu).stack[0]; - irq_stack = (unsigned long) irq_stack_start; - irq_stack = ALIGN(irq_stack, 16); /* align for stack frame usage */ + union_ptr = &per_cpu(irq_stack_union, smp_processor_id()); + irq_stack = (unsigned long) &union_ptr->stack; + irq_stack = ALIGN(irq_stack + sizeof(irq_stack_union.lock), + 64); /* align for stack frame usage */ - BUG_ON(*irq_stack_start); /* report bug if we were called recursive. */ - *irq_stack_start = 1; + /* We may be called recursive. If we are already using the irq stack, + * just continue to use it. Use spinlocks to serialize + * the irq stack usage. + */ + irq_stack_in_use = &union_ptr->lock; + if (!raw_spin_trylock(irq_stack_in_use)) { + void (*direct_call)(unsigned long p1) = func; + + /* We are using the IRQ stack already. + * Do direct call on current stack. */ + direct_call(param1); + return; + } /* This is where we switch to the IRQ stack. */ call_on_stack(param1, func, irq_stack); - *irq_stack_start = 0; + __inc_irq_stat(irq_stack_counter); + + /* free up irq stack usage. */ + do_raw_spin_unlock(irq_stack_in_use); +} + +asmlinkage void do_softirq(void) +{ + __u32 pending; + unsigned long flags; + + if (in_interrupt()) + return; + + local_irq_save(flags); + + pending = local_softirq_pending(); + + if (pending) + execute_on_irq_stack(__do_softirq, 0); + + local_irq_restore(flags); } #endif /* CONFIG_IRQSTACKS */ diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index ce939ac..1c96564 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -1069,7 +1069,7 @@ void flush_tlb_all(void) { int do_recycle; - inc_irq_stat(irq_tlb_count); + __inc_irq_stat(irq_tlb_count); do_recycle = 0; spin_lock(&sid_lock); if (dirty_space_ids > RECYCLE_THRESHOLD) { @@ -1090,7 +1090,7 @@ void flush_tlb_all(void) #else void flush_tlb_all(void) { - inc_irq_stat(irq_tlb_count); + __inc_irq_stat(irq_tlb_count); spin_lock(&sid_lock); flush_tlb_all_local(NULL); recycle_sids(); diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 5416e28..863d877 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -262,8 +262,31 @@ config PPC_EARLY_DEBUG_OPAL_HVSI Select this to enable early debugging for the PowerNV platform using an "hvsi" console +config PPC_EARLY_DEBUG_MEMCONS + bool "In memory console" + help + Select this to enable early debugging using an in memory console. + This console provides input and output buffers stored within the + kernel BSS and should be safe to select on any system. A debugger + can then be used to read kernel output or send input to the console. endchoice +config PPC_MEMCONS_OUTPUT_SIZE + int "In memory console output buffer size" + depends on PPC_EARLY_DEBUG_MEMCONS + default 4096 + help + Selects the size of the output buffer (in bytes) of the in memory + console. + +config PPC_MEMCONS_INPUT_SIZE + int "In memory console input buffer size" + depends on PPC_EARLY_DEBUG_MEMCONS + default 128 + help + Selects the size of the input buffer (in bytes) of the in memory + console. + config PPC_EARLY_DEBUG_OPAL def_bool y depends on PPC_EARLY_DEBUG_OPAL_RAW || PPC_EARLY_DEBUG_OPAL_HVSI diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index f791962..139a830 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -136,7 +136,6 @@ CONFIG_HID_SMARTJOYPLUS=m CONFIG_USB_HIDDEV=y CONFIG_USB=m CONFIG_USB_ANNOUNCE_NEW_DEVICES=y -CONFIG_USB_SUSPEND=y CONFIG_USB_MON=m CONFIG_USB_EHCI_HCD=m # CONFIG_USB_EHCI_HCD_PPC_OF is not set diff --git a/arch/powerpc/include/asm/context_tracking.h b/arch/powerpc/include/asm/context_tracking.h new file mode 100644 index 0000000..b6f5a33 --- /dev/null +++ b/arch/powerpc/include/asm/context_tracking.h @@ -0,0 +1,10 @@ +#ifndef _ASM_POWERPC_CONTEXT_TRACKING_H +#define _ASM_POWERPC_CONTEXT_TRACKING_H + +#ifdef CONFIG_CONTEXT_TRACKING +#define SCHEDULE_USER bl .schedule_user +#else +#define SCHEDULE_USER bl .schedule +#endif + +#endif diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 0df5464..681bc03 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -52,6 +52,7 @@ #define FW_FEATURE_BEST_ENERGY ASM_CONST(0x0000000080000000) #define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000) #define FW_FEATURE_PRRN ASM_CONST(0x0000000200000000) +#define FW_FEATURE_OPALv3 ASM_CONST(0x0000000400000000) #ifndef __ASSEMBLY__ @@ -69,7 +70,8 @@ enum { FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY | FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN, FW_FEATURE_PSERIES_ALWAYS = 0, - FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2, + FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2 | + FW_FEATURE_OPALv3, FW_FEATURE_POWERNV_ALWAYS = 0, FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1, FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1, diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index d615b28..ba713f1 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -96,11 +96,12 @@ static inline bool arch_irqs_disabled(void) #endif #define hard_irq_disable() do { \ + u8 _was_enabled = get_paca()->soft_enabled; \ __hard_irq_disable(); \ - if (local_paca->soft_enabled) \ - trace_hardirqs_off(); \ get_paca()->soft_enabled = 0; \ get_paca()->irq_happened |= PACA_IRQ_HARD_DIS; \ + if (_was_enabled) \ + trace_hardirqs_off(); \ } while(0) static inline bool lazy_irq_pending(void) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index b6c8b58..cbb9305 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -243,7 +243,8 @@ enum OpalMCE_TlbErrorType { enum OpalThreadStatus { OPAL_THREAD_INACTIVE = 0x0, - OPAL_THREAD_STARTED = 0x1 + OPAL_THREAD_STARTED = 0x1, + OPAL_THREAD_UNAVAILABLE = 0x2 /* opal-v3 */ }; enum OpalPciBusCompare { @@ -563,6 +564,8 @@ extern void opal_nvram_init(void); extern int opal_machine_check(struct pt_regs *regs); +extern void opal_shutdown(void); + #endif /* __ASSEMBLY__ */ #endif /* __OPAL_H */ diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 8b11b5b..2c1d8cb 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -174,6 +174,8 @@ struct pci_dn { /* Get the pointer to a device_node's pci_dn */ #define PCI_DN(dn) ((struct pci_dn *) (dn)->data) +extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev); + extern void * update_dn_pci_info(struct device_node *dn, void *data); static inline int pci_device_from_OF_node(struct device_node *np, diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h index 91acb12..b66ae72 100644 --- a/arch/powerpc/include/asm/pgalloc-64.h +++ b/arch/powerpc/include/asm/pgalloc-64.h @@ -186,7 +186,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, static inline pgtable_t pmd_pgtable(pmd_t pmd) { - return (pgtable_t)(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE); + return (pgtable_t)(pmd_val(pmd) & ~PMD_MASKED_BITS); } static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index d7e67ca..594db6b 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -284,6 +284,12 @@ struct thread_struct { unsigned long ebbrr; unsigned long ebbhr; unsigned long bescr; + unsigned long siar; + unsigned long sdar; + unsigned long sier; + unsigned long mmcr0; + unsigned long mmcr2; + unsigned long mmcra; #endif }; diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h index 3e13e23..d836d94 100644 --- a/arch/powerpc/include/asm/pte-hash64-64k.h +++ b/arch/powerpc/include/asm/pte-hash64-64k.h @@ -47,7 +47,7 @@ * generic accessors and iterators here */ #define __real_pte(e,p) ((real_pte_t) { \ - (e), ((e) & _PAGE_COMBO) ? \ + (e), (pte_val(e) & _PAGE_COMBO) ? \ (pte_val(*((p) + PTRS_PER_PTE))) : 0 }) #define __rpte_to_hidx(r,index) ((pte_val((r).pte) & _PAGE_COMBO) ? \ (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf)) diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index a8bc2bb..34fd704 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -264,6 +264,8 @@ extern void rtas_progress(char *s, unsigned short hex); extern void rtas_initialize(void); extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data); extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data); +extern int rtas_online_cpus_mask(cpumask_var_t cpus); +extern int rtas_offline_cpus_mask(cpumask_var_t cpus); extern int rtas_ibm_suspend_me(struct rtas_args *); struct rtc_time; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 8ceea14..ba7b197 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -97,7 +97,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_PERFMON_CTXSW 6 /* perfmon needs ctxsw calls */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SINGLESTEP 8 /* singlestepping active */ -#define TIF_MEMDIE 9 /* is terminating due to OOM killer */ +#define TIF_NOHZ 9 /* in adaptive nohz mode */ #define TIF_SECCOMP 10 /* secure computing */ #define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */ #define TIF_NOERROR 12 /* Force successful syscall return */ @@ -106,6 +106,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SYSCALL_TRACEPOINT 15 /* syscall tracepoint instrumentation */ #define TIF_EMULATE_STACK_STORE 16 /* Is an instruction emulation for stack store? */ +#define TIF_MEMDIE 17 /* is terminating due to OOM killer */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) @@ -124,8 +125,10 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_UPROBE (1<<TIF_UPROBE) #define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) #define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE) +#define _TIF_NOHZ (1<<TIF_NOHZ) #define _TIF_SYSCALL_T_OR_A (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ - _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT) + _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \ + _TIF_NOHZ) #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ _TIF_NOTIFY_RESUME | _TIF_UPROBE) diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h index 5a7510e..dc59091 100644 --- a/arch/powerpc/include/asm/udbg.h +++ b/arch/powerpc/include/asm/udbg.h @@ -52,6 +52,7 @@ extern void __init udbg_init_40x_realmode(void); extern void __init udbg_init_cpm(void); extern void __init udbg_init_usbgecko(void); extern void __init udbg_init_wsp(void); +extern void __init udbg_init_memcons(void); extern void __init udbg_init_ehv_bc(void); extern void __init udbg_init_ps3gelic(void); extern void __init udbg_init_debug_opal_raw(void); diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index b51a97c..6f16ffa 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -127,6 +127,12 @@ int main(void) DEFINE(THREAD_BESCR, offsetof(struct thread_struct, bescr)); DEFINE(THREAD_EBBHR, offsetof(struct thread_struct, ebbhr)); DEFINE(THREAD_EBBRR, offsetof(struct thread_struct, ebbrr)); + DEFINE(THREAD_SIAR, offsetof(struct thread_struct, siar)); + DEFINE(THREAD_SDAR, offsetof(struct thread_struct, sdar)); + DEFINE(THREAD_SIER, offsetof(struct thread_struct, sier)); + DEFINE(THREAD_MMCR0, offsetof(struct thread_struct, mmcr0)); + DEFINE(THREAD_MMCR2, offsetof(struct thread_struct, mmcr2)); + DEFINE(THREAD_MMCRA, offsetof(struct thread_struct, mmcra)); #endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM DEFINE(PACATMSCRATCH, offsetof(struct paca_struct, tm_scratch)); diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index a283b64..18b5b9c 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -135,8 +135,12 @@ __init_HFSCR: blr __init_TLB: - /* Clear the TLB */ - li r6,128 + /* + * Clear the TLB using the "IS 3" form of tlbiel instruction + * (invalidate by congruence class). P7 has 128 CCs, P8 has 512 + * so we just always do 512 + */ + li r6,512 mtctr r6 li r7,0xc00 /* IS field = 0b11 */ ptesync diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index e514de5..d22e73e 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -439,8 +439,6 @@ ret_from_fork: ret_from_kernel_thread: REST_NVGPRS(r1) bl schedule_tail - li r3,0 - stw r3,0(r1) mtlr r14 mr r3,r15 PPC440EP_ERR42 diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 915fbb4..0e9095e 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -33,6 +33,7 @@ #include <asm/irqflags.h> #include <asm/ftrace.h> #include <asm/hw_irq.h> +#include <asm/context_tracking.h> /* * System calls. @@ -376,8 +377,6 @@ _GLOBAL(ret_from_fork) _GLOBAL(ret_from_kernel_thread) bl .schedule_tail REST_NVGPRS(r1) - li r3,0 - std r3,0(r1) ld r14, 0(r14) mtlr r14 mr r3,r15 @@ -466,6 +465,20 @@ BEGIN_FTR_SECTION std r0, THREAD_EBBHR(r3) mfspr r0, SPRN_EBBRR std r0, THREAD_EBBRR(r3) + + /* PMU registers made user read/(write) by EBB */ + mfspr r0, SPRN_SIAR + std r0, THREAD_SIAR(r3) + mfspr r0, SPRN_SDAR + std r0, THREAD_SDAR(r3) + mfspr r0, SPRN_SIER + std r0, THREAD_SIER(r3) + mfspr r0, SPRN_MMCR0 + std r0, THREAD_MMCR0(r3) + mfspr r0, SPRN_MMCR2 + std r0, THREAD_MMCR2(r3) + mfspr r0, SPRN_MMCRA + std r0, THREAD_MMCRA(r3) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) #endif @@ -561,6 +574,20 @@ BEGIN_FTR_SECTION ld r0, THREAD_EBBRR(r4) mtspr SPRN_EBBRR, r0 + /* PMU registers made user read/(write) by EBB */ + ld r0, THREAD_SIAR(r4) + mtspr SPRN_SIAR, r0 + ld r0, THREAD_SDAR(r4) + mtspr SPRN_SDAR, r0 + ld r0, THREAD_SIER(r4) + mtspr SPRN_SIER, r0 + ld r0, THREAD_MMCR0(r4) + mtspr SPRN_MMCR0, r0 + ld r0, THREAD_MMCR2(r4) + mtspr SPRN_MMCR2, r0 + ld r0, THREAD_MMCRA(r4) + mtspr SPRN_MMCRA, r0 + ld r0,THREAD_TAR(r4) mtspr SPRN_TAR,r0 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) @@ -634,7 +661,7 @@ _GLOBAL(ret_from_except_lite) andi. r0,r4,_TIF_NEED_RESCHED beq 1f bl .restore_interrupts - bl .schedule + SCHEDULE_USER b .ret_from_except_lite 1: bl .save_nvgprs diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 42a756e..645170a 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -489,7 +489,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) */ mfspr r14,SPRN_DBSR /* check single-step/branch taken */ - andis. r15,r14,DBSR_IC@h + andis. r15,r14,(DBSR_IC|DBSR_BT)@h beq+ 1f LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) @@ -500,7 +500,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) bge+ cr1,1f /* here it looks like we got an inappropriate debug exception. */ - lis r14,DBSR_IC@h /* clear the IC event */ + lis r14,(DBSR_IC|DBSR_BT)@h /* clear the event */ rlwinm r11,r11,0,~MSR_DE /* clear DE in the CSRR1 value */ mtspr SPRN_DBSR,r14 mtspr SPRN_CSRR1,r11 @@ -555,7 +555,7 @@ kernel_dbg_exc: */ mfspr r14,SPRN_DBSR /* check single-step/branch taken */ - andis. r15,r14,DBSR_IC@h + andis. r15,r14,(DBSR_IC|DBSR_BT)@h beq+ 1f LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) @@ -566,7 +566,7 @@ kernel_dbg_exc: bge+ cr1,1f /* here it looks like we got an inappropriate debug exception. */ - lis r14,DBSR_IC@h /* clear the IC event */ + lis r14,(DBSR_IC|DBSR_BT)@h /* clear the event */ rlwinm r11,r11,0,~MSR_DE /* clear DE in the DSRR1 value */ mtspr SPRN_DBSR,r14 mtspr SPRN_DSRR1,r11 diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 466a290..611acdf 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -17,6 +17,7 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/cpu.h> +#include <linux/hardirq.h> #include <asm/page.h> #include <asm/current.h> @@ -335,10 +336,13 @@ void default_machine_kexec(struct kimage *image) pr_debug("kexec: Starting switchover sequence.\n"); /* switch to a staticly allocated stack. Based on irq stack code. + * We setup preempt_count to avoid using VMX in memcpy. * XXX: the task struct will likely be invalid once we do the copy! */ kexec_stack.thread_info.task = current_thread_info()->task; kexec_stack.thread_info.flags = 0; + kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET; + kexec_stack.thread_info.cpu = current_thread_info()->cpu; /* We need a static PACA, too; copy this CPU's PACA over and switch to * it. Also poison per_cpu_offset to catch anyone using non-static diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 19e096b..e469f30 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -657,6 +657,17 @@ _GLOBAL(__ucmpdi2) li r3,2 blr +_GLOBAL(__bswapdi2) + rotlwi r9,r4,8 + rotlwi r10,r3,8 + rlwimi r9,r4,24,0,7 + rlwimi r10,r3,24,0,7 + rlwimi r9,r4,24,16,23 + rlwimi r10,r3,24,16,23 + mr r3,r9 + mr r4,r10 + blr + _GLOBAL(abs) srawi r4,r3,31 xor r3,r3,r4 diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 5cfa800..6820e45 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -234,6 +234,17 @@ _GLOBAL(__flush_dcache_icache) isync blr +_GLOBAL(__bswapdi2) + srdi r8,r3,32 + rlwinm r7,r3,8,0xffffffff + rlwimi r7,r3,24,0,7 + rlwinm r9,r8,8,0xffffffff + rlwimi r7,r3,24,16,23 + rlwimi r9,r8,24,0,7 + rlwimi r9,r8,24,16,23 + sldi r7,r7,32 + or r3,r7,r9 + blr #if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) /* diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index f5c5c90..e9acf50 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -359,7 +359,6 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, enum pci_mmap_state mmap_state, int write_combine) { - unsigned long prot = pgprot_val(protection); /* Write combine is always 0 on non-memory space mappings. On * memory space, if the user didn't pass 1, we check for a @@ -376,9 +375,9 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, /* XXX would be nice to have a way to ask for write-through */ if (write_combine) - return pgprot_noncached_wc(prot); + return pgprot_noncached_wc(protection); else - return pgprot_noncached(prot); + return pgprot_noncached(protection); } /* @@ -1521,9 +1520,10 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose, for (i = 0; i < 3; ++i) { res = &hose->mem_resources[i]; if (!res->flags) { - printk(KERN_ERR "PCI: Memory resource 0 not set for " - "host bridge %s (domain %d)\n", - hose->dn->full_name, hose->global_number); + if (i == 0) + printk(KERN_ERR "PCI: Memory resource 0 not set for " + "host bridge %s (domain %d)\n", + hose->dn->full_name, hose->global_number); continue; } offset = hose->mem_offset[i]; diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 873050d..2e86296 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -266,3 +266,13 @@ int pcibus_to_node(struct pci_bus *bus) } EXPORT_SYMBOL(pcibus_to_node); #endif + +static void quirk_radeon_32bit_msi(struct pci_dev *dev) +{ + struct pci_dn *pdn = pci_get_pdn(dev); + + if (pdn) + pdn->force_32bit_msi = 1; +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x68f2, quirk_radeon_32bit_msi); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0xaa68, quirk_radeon_32bit_msi); diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index e7af165..df03844 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -32,6 +32,14 @@ #include <asm/ppc-pci.h> #include <asm/firmware.h> +struct pci_dn *pci_get_pdn(struct pci_dev *pdev) +{ + struct device_node *dn = pci_device_to_OF_node(pdev); + if (!dn) + return NULL; + return PCI_DN(dn); +} + /* * Traverse_func that inits the PCI fields of the device node. * NOTE: this *must* be done before read/write config to the device. diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 78b8766..c296665 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -143,7 +143,8 @@ EXPORT_SYMBOL(__lshrdi3); int __ucmpdi2(unsigned long long, unsigned long long); EXPORT_SYMBOL(__ucmpdi2); #endif - +long long __bswapdi2(long long); +EXPORT_SYMBOL(__bswapdi2); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memmove); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index ceb4e7b..a902723 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -339,6 +339,13 @@ static void set_debug_reg_defaults(struct thread_struct *thread) static void prime_debug_regs(struct thread_struct *thread) { + /* + * We could have inherited MSR_DE from userspace, since + * it doesn't get cleared on exception entry. Make sure + * MSR_DE is clear before we enable any debug events. + */ + mtmsr(mfmsr() & ~MSR_DE); + mtspr(SPRN_IAC1, thread->iac1); mtspr(SPRN_IAC2, thread->iac2); #if CONFIG_PPC_ADV_DEBUG_IACS > 2 @@ -971,6 +978,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, * do some house keeping and then return from the fork or clone * system call, using the stack frame created above. */ + ((unsigned long *)sp)[0] = 0; sp -= sizeof(struct pt_regs); kregs = (struct pt_regs *) sp; sp -= STACK_FRAME_OVERHEAD; diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 3b14d32..98c2fc1 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -32,6 +32,7 @@ #include <trace/syscall.h> #include <linux/hw_breakpoint.h> #include <linux/perf_event.h> +#include <linux/context_tracking.h> #include <asm/uaccess.h> #include <asm/page.h> @@ -1788,6 +1789,8 @@ long do_syscall_trace_enter(struct pt_regs *regs) { long ret = 0; + user_exit(); + secure_computing_strict(regs->gpr[0]); if (test_thread_flag(TIF_SYSCALL_TRACE) && @@ -1832,4 +1835,6 @@ void do_syscall_trace_leave(struct pt_regs *regs) step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, step); + + user_enter(); } diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 1fd6e7b..52add6f 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/capability.h> #include <linux/delay.h> +#include <linux/cpu.h> #include <linux/smp.h> #include <linux/completion.h> #include <linux/cpumask.h> @@ -807,6 +808,95 @@ static void rtas_percpu_suspend_me(void *info) __rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1); } +enum rtas_cpu_state { + DOWN, + UP, +}; + +#ifndef CONFIG_SMP +static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, + cpumask_var_t cpus) +{ + if (!cpumask_empty(cpus)) { + cpumask_clear(cpus); + return -EINVAL; + } else + return 0; +} +#else +/* On return cpumask will be altered to indicate CPUs changed. + * CPUs with states changed will be set in the mask, + * CPUs with status unchanged will be unset in the mask. */ +static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, + cpumask_var_t cpus) +{ + int cpu; + int cpuret = 0; + int ret = 0; + + if (cpumask_empty(cpus)) + return 0; + + for_each_cpu(cpu, cpus) { + switch (state) { + case DOWN: + cpuret = cpu_down(cpu); + break; + case UP: + cpuret = cpu_up(cpu); + break; + } + if (cpuret) { + pr_debug("%s: cpu_%s for cpu#%d returned %d.\n", + __func__, + ((state == UP) ? "up" : "down"), + cpu, cpuret); + if (!ret) + ret = cpuret; + if (state == UP) { + /* clear bits for unchanged cpus, return */ + cpumask_shift_right(cpus, cpus, cpu); + cpumask_shift_left(cpus, cpus, cpu); + break; + } else { + /* clear bit for unchanged cpu, continue */ + cpumask_clear_cpu(cpu, cpus); + } + } + } + + return ret; +} +#endif + +int rtas_online_cpus_mask(cpumask_var_t cpus) +{ + int ret; + + ret = rtas_cpu_state_change_mask(UP, cpus); + + if (ret) { + cpumask_var_t tmp_mask; + + if (!alloc_cpumask_var(&tmp_mask, GFP_TEMPORARY)) + return ret; + + /* Use tmp_mask to preserve cpus mask from first failure */ + cpumask_copy(tmp_mask, cpus); + rtas_offline_cpus_mask(tmp_mask); + free_cpumask_var(tmp_mask); + } + + return ret; +} +EXPORT_SYMBOL(rtas_online_cpus_mask); + +int rtas_offline_cpus_mask(cpumask_var_t cpus) +{ + return rtas_cpu_state_change_mask(DOWN, cpus); +} +EXPORT_SYMBOL(rtas_offline_cpus_mask); + int rtas_ibm_suspend_me(struct rtas_args *args) { long state; @@ -814,6 +904,8 @@ int rtas_ibm_suspend_me(struct rtas_args *args) unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; struct rtas_suspend_me_data data; DECLARE_COMPLETION_ONSTACK(done); + cpumask_var_t offline_mask; + int cpuret; if (!rtas_service_present("ibm,suspend-me")) return -ENOSYS; @@ -837,11 +929,24 @@ int rtas_ibm_suspend_me(struct rtas_args *args) return 0; } + if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY)) + return -ENOMEM; + atomic_set(&data.working, 0); atomic_set(&data.done, 0); atomic_set(&data.error, 0); data.token = rtas_token("ibm,suspend-me"); data.complete = &done; + + /* All present CPUs must be online */ + cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask); + cpuret = rtas_online_cpus_mask(offline_mask); + if (cpuret) { + pr_err("%s: Could not bring present CPUs online.\n", __func__); + atomic_set(&data.error, cpuret); + goto out; + } + stop_topology_update(); /* Call function on all CPUs. One of us will make the @@ -857,6 +962,14 @@ int rtas_ibm_suspend_me(struct rtas_args *args) start_topology_update(); + /* Take down CPUs not online prior to suspend */ + cpuret = rtas_offline_cpus_mask(offline_mask); + if (cpuret) + pr_warn("%s: Could not restore CPUs to offline state.\n", + __func__); + +out: + free_cpumask_var(offline_mask); return atomic_read(&data.error); } #else /* CONFIG_PPC_PSERIES */ diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 5b30224..2f3cdb0 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -89,6 +89,7 @@ /* Array sizes */ #define VALIDATE_BUF_SIZE 4096 +#define VALIDATE_MSG_LEN 256 #define RTAS_MSG_MAXLEN 64 /* Quirk - RTAS requires 4k list length and block size */ @@ -466,7 +467,7 @@ static void validate_flash(struct rtas_validate_flash_t *args_buf) } static int get_validate_flash_msg(struct rtas_validate_flash_t *args_buf, - char *msg) + char *msg, int msglen) { int n; @@ -474,7 +475,8 @@ static int get_validate_flash_msg(struct rtas_validate_flash_t *args_buf, n = sprintf(msg, "%d\n", args_buf->update_results); if ((args_buf->update_results >= VALIDATE_CUR_UNKNOWN) || (args_buf->update_results == VALIDATE_TMP_UPDATE)) - n += sprintf(msg + n, "%s\n", args_buf->buf); + n += snprintf(msg + n, msglen - n, "%s\n", + args_buf->buf); } else { n = sprintf(msg, "%d\n", args_buf->status); } @@ -486,11 +488,11 @@ static ssize_t validate_flash_read(struct file *file, char __user *buf, { struct rtas_validate_flash_t *const args_buf = &rtas_validate_flash_data; - char msg[RTAS_MSG_MAXLEN]; + char msg[VALIDATE_MSG_LEN]; int msglen; mutex_lock(&rtas_validate_flash_mutex); - msglen = get_validate_flash_msg(args_buf, msg); + msglen = get_validate_flash_msg(args_buf, msg, VALIDATE_MSG_LEN); mutex_unlock(&rtas_validate_flash_mutex); return simple_read_from_buffer(buf, count, ppos, msg, msglen); diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index cf12eae..577a8aa 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -13,6 +13,7 @@ #include <linux/signal.h> #include <linux/uprobes.h> #include <linux/key.h> +#include <linux/context_tracking.h> #include <asm/hw_breakpoint.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -24,7 +25,7 @@ * through debug.exception-trace sysctl. */ -int show_unhandled_signals = 0; +int show_unhandled_signals = 1; /* * Allocate space for the signal frame @@ -159,6 +160,8 @@ static int do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) { + user_exit(); + if (thread_info_flags & _TIF_UPROBE) uprobe_notify_resume(regs); @@ -169,4 +172,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); } + + user_enter(); } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 83efa2f..a7a648f 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -35,6 +35,7 @@ #include <linux/kdebug.h> #include <linux/debugfs.h> #include <linux/ratelimit.h> +#include <linux/context_tracking.h> #include <asm/emulated_ops.h> #include <asm/pgtable.h> @@ -667,6 +668,7 @@ int machine_check_generic(struct pt_regs *regs) void machine_check_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); int recover = 0; __get_cpu_var(irq_stat).mce_exceptions++; @@ -683,7 +685,7 @@ void machine_check_exception(struct pt_regs *regs) recover = cur_cpu_spec->machine_check(regs); if (recover > 0) - return; + goto bail; #if defined(CONFIG_8xx) && defined(CONFIG_PCI) /* the qspan pci read routines can cause machine checks -- Cort @@ -693,20 +695,23 @@ void machine_check_exception(struct pt_regs *regs) * -- BenH */ bad_page_fault(regs, regs->dar, SIGBUS); - return; + goto bail; #endif if (debugger_fault_handler(regs)) - return; + goto bail; if (check_io_access(regs)) - return; + goto bail; die("Machine check", regs, SIGBUS); /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) panic("Unrecoverable Machine check"); + +bail: + exception_exit(prev_state); } void SMIException(struct pt_regs *regs) @@ -716,20 +721,29 @@ void SMIException(struct pt_regs *regs) void unknown_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); + printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n", regs->nip, regs->msr, regs->trap); _exception(SIGTRAP, regs, 0, 0); + + exception_exit(prev_state); } void instruction_breakpoint_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); + if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5, 5, SIGTRAP) == NOTIFY_STOP) - return; + goto bail; if (debugger_iabr_match(regs)) - return; + goto bail; _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); + +bail: + exception_exit(prev_state); } void RunModeException(struct pt_regs *regs) @@ -739,15 +753,20 @@ void RunModeException(struct pt_regs *regs) void __kprobes single_step_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); + clear_single_step(regs); if (notify_die(DIE_SSTEP, "single_step", regs, 5, 5, SIGTRAP) == NOTIFY_STOP) - return; + goto bail; if (debugger_sstep(regs)) - return; + goto bail; _exception(SIGTRAP, regs, TRAP_TRACE, regs->nip); + +bail: + exception_exit(prev_state); } /* @@ -1005,6 +1024,7 @@ int is_valid_bugaddr(unsigned long addr) void __kprobes program_check_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); unsigned int reason = get_reason(regs); extern int do_mathemu(struct pt_regs *regs); @@ -1014,26 +1034,26 @@ void __kprobes program_check_exception(struct pt_regs *regs) if (reason & REASON_FP) { /* IEEE FP exception */ parse_fpe(regs); - return; + goto bail; } if (reason & REASON_TRAP) { /* Debugger is first in line to stop recursive faults in * rcu_lock, notify_die, or atomic_notifier_call_chain */ if (debugger_bpt(regs)) - return; + goto bail; /* trap exception */ if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP) == NOTIFY_STOP) - return; + goto bail; if (!(regs->msr & MSR_PR) && /* not user-mode */ report_bug(regs->nip, regs) == BUG_TRAP_TYPE_WARN) { regs->nip += 4; - return; + goto bail; } _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); - return; + goto bail; } #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (reason & REASON_TM) { @@ -1049,7 +1069,7 @@ void __kprobes program_check_exception(struct pt_regs *regs) if (!user_mode(regs) && report_bug(regs->nip, regs) == BUG_TRAP_TYPE_WARN) { regs->nip += 4; - return; + goto bail; } /* If usermode caused this, it's done something illegal and * gets a SIGILL slap on the wrist. We call it an illegal @@ -1059,7 +1079,7 @@ void __kprobes program_check_exception(struct pt_regs *regs) */ if (user_mode(regs)) { _exception(SIGILL, regs, ILL_ILLOPN, regs->nip); - return; + goto bail; } else { printk(KERN_EMERG "Unexpected TM Bad Thing exception " "at %lx (msr 0x%x)\n", regs->nip, reason); @@ -1083,16 +1103,16 @@ void __kprobes program_check_exception(struct pt_regs *regs) switch (do_mathemu(regs)) { case 0: emulate_single_step(regs); - return; + goto bail; case 1: { int code = 0; code = __parse_fpscr(current->thread.fpscr.val); _exception(SIGFPE, regs, code, regs->nip); - return; + goto bail; } case -EFAULT: _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip); - return; + goto bail; } /* fall through on any other errors */ #endif /* CONFIG_MATH_EMULATION */ @@ -1103,10 +1123,10 @@ void __kprobes program_check_exception(struct pt_regs *regs) case 0: regs->nip += 4; emulate_single_step(regs); - return; + goto bail; case -EFAULT: _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip); - return; + goto bail; } } @@ -1114,10 +1134,14 @@ void __kprobes program_check_exception(struct pt_regs *regs) _exception(SIGILL, regs, ILL_PRVOPC, regs->nip); else _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); + +bail: + exception_exit(prev_state); } void alignment_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); int sig, code, fixed = 0; /* We restore the interrupt state now */ @@ -1131,7 +1155,7 @@ void alignment_exception(struct pt_regs *regs) if (fixed == 1) { regs->nip += 4; /* skip over emulated instruction */ emulate_single_step(regs); - return; + goto bail; } /* Operand address was bad */ @@ -1146,6 +1170,9 @@ void alignment_exception(struct pt_regs *regs) _exception(sig, regs, code, regs->dar); else bad_page_fault(regs, regs->dar, sig); + +bail: + exception_exit(prev_state); } void StackOverflow(struct pt_regs *regs) @@ -1174,23 +1201,32 @@ void trace_syscall(struct pt_regs *regs) void kernel_fp_unavailable_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); + printk(KERN_EMERG "Unrecoverable FP Unavailable Exception " "%lx at %lx\n", regs->trap, regs->nip); die("Unrecoverable FP Unavailable Exception", regs, SIGABRT); + + exception_exit(prev_state); } void altivec_unavailable_exception(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); + if (user_mode(regs)) { /* A user program has executed an altivec instruction, but this kernel doesn't support altivec. */ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); - return; + goto bail; } printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception " "%lx at %lx\n", regs->trap, regs->nip); die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT); + +bail: + exception_exit(prev_state); } void vsx_unavailable_exception(struct pt_regs *regs) diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index 13b8670..9d3fdcd 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -64,6 +64,9 @@ void __init udbg_early_init(void) udbg_init_usbgecko(); #elif defined(CONFIG_PPC_EARLY_DEBUG_WSP) udbg_init_wsp(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_MEMCONS) + /* In memory console */ + udbg_init_memcons(); #elif defined(CONFIG_PPC_EARLY_DEBUG_EHV_BC) udbg_init_ehv_bc(); #elif defined(CONFIG_PPC_EARLY_DEBUG_PS3GELIC) diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 229951f..8726779 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -32,6 +32,7 @@ #include <linux/perf_event.h> #include <linux/magic.h> #include <linux/ratelimit.h> +#include <linux/context_tracking.h> #include <asm/firmware.h> #include <asm/page.h> @@ -196,6 +197,7 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault) int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, unsigned long error_code) { + enum ctx_state prev_state = exception_enter(); struct vm_area_struct * vma; struct mm_struct *mm = current->mm; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; @@ -204,6 +206,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, int trap = TRAP(regs); int is_exec = trap == 0x400; int fault; + int rc = 0; #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) /* @@ -230,28 +233,30 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, * look at it */ if (error_code & ICSWX_DSI_UCT) { - int rc = acop_handle_fault(regs, address, error_code); + rc = acop_handle_fault(regs, address, error_code); if (rc) - return rc; + goto bail; } #endif /* CONFIG_PPC_ICSWX */ if (notify_page_fault(regs)) - return 0; + goto bail; if (unlikely(debugger_fault_handler(regs))) - return 0; + goto bail; /* On a kernel SLB miss we can only check for a valid exception entry */ - if (!user_mode(regs) && (address >= TASK_SIZE)) - return SIGSEGV; + if (!user_mode(regs) && (address >= TASK_SIZE)) { + rc = SIGSEGV; + goto bail; + } #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE) || \ defined(CONFIG_PPC_BOOK3S_64)) if (error_code & DSISR_DABRMATCH) { /* breakpoint match */ do_break(regs, address, error_code); - return 0; + goto bail; } #endif @@ -260,8 +265,10 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, local_irq_enable(); if (in_atomic() || mm == NULL) { - if (!user_mode(regs)) - return SIGSEGV; + if (!user_mode(regs)) { + rc = SIGSEGV; + goto bail; + } /* in_atomic() in user mode is really bad, as is current->mm == NULL. */ printk(KERN_EMERG "Page fault in user mode with " @@ -417,9 +424,11 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, flags); if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { - int rc = mm_fault_error(regs, address, fault); + rc = mm_fault_error(regs, address, fault); if (rc >= MM_FAULT_RETURN) - return rc; + goto bail; + else + rc = 0; } /* @@ -454,7 +463,7 @@ good_area: } up_read(&mm->mmap_sem); - return 0; + goto bail; bad_area: up_read(&mm->mmap_sem); @@ -463,7 +472,7 @@ bad_area_nosemaphore: /* User mode accesses cause a SIGSEGV */ if (user_mode(regs)) { _exception(SIGSEGV, regs, code, address); - return 0; + goto bail; } if (is_exec && (error_code & DSISR_PROTFAULT)) @@ -471,7 +480,11 @@ bad_area_nosemaphore: " page (%lx) - exploit attempt? (uid: %d)\n", address, from_kuid(&init_user_ns, current_uid())); - return SIGSEGV; + rc = SIGSEGV; + +bail: + exception_exit(prev_state); + return rc; } diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 88ac0ee..e303a6d 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -33,6 +33,7 @@ #include <linux/init.h> #include <linux/signal.h> #include <linux/memblock.h> +#include <linux/context_tracking.h> #include <asm/processor.h> #include <asm/pgtable.h> @@ -954,6 +955,7 @@ void hash_failure_debug(unsigned long ea, unsigned long access, */ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) { + enum ctx_state prev_state = exception_enter(); pgd_t *pgdir; unsigned long vsid; struct mm_struct *mm; @@ -973,7 +975,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) mm = current->mm; if (! mm) { DBG_LOW(" user region with no mm !\n"); - return 1; + rc = 1; + goto bail; } psize = get_slice_psize(mm, ea); ssize = user_segment_size(ea); @@ -992,19 +995,23 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) /* Not a valid range * Send the problem up to do_page_fault */ - return 1; + rc = 1; + goto bail; } DBG_LOW(" mm=%p, mm->pgdir=%p, vsid=%016lx\n", mm, mm->pgd, vsid); /* Bad address. */ if (!vsid) { DBG_LOW("Bad address!\n"); - return 1; + rc = 1; + goto bail; } /* Get pgdir */ pgdir = mm->pgd; - if (pgdir == NULL) - return 1; + if (pgdir == NULL) { + rc = 1; + goto bail; + } /* Check CPU locality */ tmp = cpumask_of(smp_processor_id()); @@ -1027,7 +1034,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) ptep = find_linux_pte_or_hugepte(pgdir, ea, &hugeshift); if (ptep == NULL || !pte_present(*ptep)) { DBG_LOW(" no PTE !\n"); - return 1; + rc = 1; + goto bail; } /* Add _PAGE_PRESENT to the required access perm */ @@ -1038,13 +1046,16 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) */ if (access & ~pte_val(*ptep)) { DBG_LOW(" no access !\n"); - return 1; + rc = 1; + goto bail; } #ifdef CONFIG_HUGETLB_PAGE - if (hugeshift) - return __hash_page_huge(ea, access, vsid, ptep, trap, local, + if (hugeshift) { + rc = __hash_page_huge(ea, access, vsid, ptep, trap, local, ssize, hugeshift, psize); + goto bail; + } #endif /* CONFIG_HUGETLB_PAGE */ #ifndef CONFIG_PPC_64K_PAGES @@ -1124,6 +1135,9 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) pte_val(*(ptep + PTRS_PER_PTE))); #endif DBG_LOW(" -> rc=%d\n", rc); + +bail: + exception_exit(prev_state); return rc; } EXPORT_SYMBOL_GPL(hash_page); @@ -1259,6 +1273,8 @@ void flush_hash_range(unsigned long number, int local) */ void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc) { + enum ctx_state prev_state = exception_enter(); + if (user_mode(regs)) { #ifdef CONFIG_PPC_SUBPAGE_PROT if (rc == -2) @@ -1268,6 +1284,8 @@ void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc) _exception(SIGBUS, regs, BUS_ADRERR, address); } else bad_page_fault(regs, address, SIGBUS); + + exception_exit(prev_state); } long hpte_insert_repeating(unsigned long hash, unsigned long vpn, diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index c2787bf..a90b9c4 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -215,7 +215,8 @@ static void __meminit vmemmap_create_mapping(unsigned long start, unsigned long phys) { int mapped = htab_bolt_mapping(start, start + page_size, phys, - PAGE_KERNEL, mmu_vmemmap_psize, + pgprot_val(PAGE_KERNEL), + mmu_vmemmap_psize, mmu_kernel_ssize); BUG_ON(mapped < 0); } diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index c627843..426180b 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -13,11 +13,13 @@ #include <linux/perf_event.h> #include <linux/percpu.h> #include <linux/hardirq.h> +#include <linux/uaccess.h> #include <asm/reg.h> #include <asm/pmc.h> #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/ptrace.h> +#include <asm/code-patching.h> #define BHRB_MAX_ENTRIES 32 #define BHRB_TARGET 0x0000000000000002 @@ -100,6 +102,10 @@ static inline int siar_valid(struct pt_regs *regs) return 1; } +static inline void power_pmu_bhrb_enable(struct perf_event *event) {} +static inline void power_pmu_bhrb_disable(struct perf_event *event) {} +void power_pmu_flush_branch_stack(void) {} +static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {} #endif /* CONFIG_PPC32 */ static bool regs_use_siar(struct pt_regs *regs) @@ -308,6 +314,159 @@ static inline int siar_valid(struct pt_regs *regs) return 1; } + +/* Reset all possible BHRB entries */ +static void power_pmu_bhrb_reset(void) +{ + asm volatile(PPC_CLRBHRB); +} + +static void power_pmu_bhrb_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + if (!ppmu->bhrb_nr) + return; + + /* Clear BHRB if we changed task context to avoid data leaks */ + if (event->ctx->task && cpuhw->bhrb_context != event->ctx) { + power_pmu_bhrb_reset(); + cpuhw->bhrb_context = event->ctx; + } + cpuhw->bhrb_users++; +} + +static void power_pmu_bhrb_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + if (!ppmu->bhrb_nr) + return; + + cpuhw->bhrb_users--; + WARN_ON_ONCE(cpuhw->bhrb_users < 0); + + if (!cpuhw->disabled && !cpuhw->bhrb_users) { + /* BHRB cannot be turned off when other + * events are active on the PMU. + */ + + /* avoid stale pointer */ + cpuhw->bhrb_context = NULL; + } +} + +/* Called from ctxsw to prevent one process's branch entries to + * mingle with the other process's entries during context switch. + */ +void power_pmu_flush_branch_stack(void) +{ + if (ppmu->bhrb_nr) + power_pmu_bhrb_reset(); +} +/* Calculate the to address for a branch */ +static __u64 power_pmu_bhrb_to(u64 addr) +{ + unsigned int instr; + int ret; + __u64 target; + + if (is_kernel_addr(addr)) + return branch_target((unsigned int *)addr); + + /* Userspace: need copy instruction here then translate it */ + pagefault_disable(); + ret = __get_user_inatomic(instr, (unsigned int __user *)addr); + if (ret) { + pagefault_enable(); + return 0; + } + pagefault_enable(); + + target = branch_target(&instr); + if ((!target) || (instr & BRANCH_ABSOLUTE)) + return target; + + /* Translate relative branch target from kernel to user address */ + return target - (unsigned long)&instr + addr; +} + +/* Processing BHRB entries */ +void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) +{ + u64 val; + u64 addr; + int r_index, u_index, pred; + + r_index = 0; + u_index = 0; + while (r_index < ppmu->bhrb_nr) { + /* Assembly read function */ + val = read_bhrb(r_index++); + if (!val) + /* Terminal marker: End of valid BHRB entries */ + break; + else { + addr = val & BHRB_EA; + pred = val & BHRB_PREDICTION; + + if (!addr) + /* invalid entry */ + continue; + + /* Branches are read most recent first (ie. mfbhrb 0 is + * the most recent branch). + * There are two types of valid entries: + * 1) a target entry which is the to address of a + * computed goto like a blr,bctr,btar. The next + * entry read from the bhrb will be branch + * corresponding to this target (ie. the actual + * blr/bctr/btar instruction). + * 2) a from address which is an actual branch. If a + * target entry proceeds this, then this is the + * matching branch for that target. If this is not + * following a target entry, then this is a branch + * where the target is given as an immediate field + * in the instruction (ie. an i or b form branch). + * In this case we need to read the instruction from + * memory to determine the target/to address. + */ + + if (val & BHRB_TARGET) { + /* Target branches use two entries + * (ie. computed gotos/XL form) + */ + cpuhw->bhrb_entries[u_index].to = addr; + cpuhw->bhrb_entries[u_index].mispred = pred; + cpuhw->bhrb_entries[u_index].predicted = ~pred; + + /* Get from address in next entry */ + val = read_bhrb(r_index++); + addr = val & BHRB_EA; + if (val & BHRB_TARGET) { + /* Shouldn't have two targets in a + row.. Reset index and try again */ + r_index--; + addr = 0; + } + cpuhw->bhrb_entries[u_index].from = addr; + } else { + /* Branches to immediate field + (ie I or B form) */ + cpuhw->bhrb_entries[u_index].from = addr; + cpuhw->bhrb_entries[u_index].to = + power_pmu_bhrb_to(addr); + cpuhw->bhrb_entries[u_index].mispred = pred; + cpuhw->bhrb_entries[u_index].predicted = ~pred; + } + u_index++; + + } + } + cpuhw->bhrb_stack.nr = u_index; + return; +} + #endif /* CONFIG_PPC64 */ static void perf_event_interrupt(struct pt_regs *regs); @@ -904,47 +1063,6 @@ static int collect_events(struct perf_event *group, int max_count, return n; } -/* Reset all possible BHRB entries */ -static void power_pmu_bhrb_reset(void) -{ - asm volatile(PPC_CLRBHRB); -} - -void power_pmu_bhrb_enable(struct perf_event *event) -{ - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); - - if (!ppmu->bhrb_nr) - return; - - /* Clear BHRB if we changed task context to avoid data leaks */ - if (event->ctx->task && cpuhw->bhrb_context != event->ctx) { - power_pmu_bhrb_reset(); - cpuhw->bhrb_context = event->ctx; - } - cpuhw->bhrb_users++; -} - -void power_pmu_bhrb_disable(struct perf_event *event) -{ - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); - - if (!ppmu->bhrb_nr) - return; - - cpuhw->bhrb_users--; - WARN_ON_ONCE(cpuhw->bhrb_users < 0); - - if (!cpuhw->disabled && !cpuhw->bhrb_users) { - /* BHRB cannot be turned off when other - * events are active on the PMU. - */ - - /* avoid stale pointer */ - cpuhw->bhrb_context = NULL; - } -} - /* * Add a event to the PMU. * If all events are not already frozen, then we disable and @@ -1180,15 +1298,6 @@ int power_pmu_commit_txn(struct pmu *pmu) return 0; } -/* Called from ctxsw to prevent one process's branch entries to - * mingle with the other process's entries during context switch. - */ -void power_pmu_flush_branch_stack(void) -{ - if (ppmu->bhrb_nr) - power_pmu_bhrb_reset(); -} - /* * Return 1 if we might be able to put event on a limited PMC, * or 0 if not. @@ -1458,77 +1567,6 @@ struct pmu power_pmu = { .flush_branch_stack = power_pmu_flush_branch_stack, }; -/* Processing BHRB entries */ -void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) -{ - u64 val; - u64 addr; - int r_index, u_index, target, pred; - - r_index = 0; - u_index = 0; - while (r_index < ppmu->bhrb_nr) { - /* Assembly read function */ - val = read_bhrb(r_index); - - /* Terminal marker: End of valid BHRB entries */ - if (val == 0) { - break; - } else { - /* BHRB field break up */ - addr = val & BHRB_EA; - pred = val & BHRB_PREDICTION; - target = val & BHRB_TARGET; - - /* Probable Missed entry: Not applicable for POWER8 */ - if ((addr == 0) && (target == 0) && (pred == 1)) { - r_index++; - continue; - } - - /* Real Missed entry: Power8 based missed entry */ - if ((addr == 0) && (target == 1) && (pred == 1)) { - r_index++; - continue; - } - - /* Reserved condition: Not a valid entry */ - if ((addr == 0) && (target == 1) && (pred == 0)) { - r_index++; - continue; - } - - /* Is a target address */ - if (val & BHRB_TARGET) { - /* First address cannot be a target address */ - if (r_index == 0) { - r_index++; - continue; - } - - /* Update target address for the previous entry */ - cpuhw->bhrb_entries[u_index - 1].to = addr; - cpuhw->bhrb_entries[u_index - 1].mispred = pred; - cpuhw->bhrb_entries[u_index - 1].predicted = ~pred; - - /* Dont increment u_index */ - r_index++; - } else { - /* Update address, flags for current entry */ - cpuhw->bhrb_entries[u_index].from = addr; - cpuhw->bhrb_entries[u_index].mispred = pred; - cpuhw->bhrb_entries[u_index].predicted = ~pred; - - /* Successfully popullated one entry */ - u_index++; - r_index++; - } - } - } - cpuhw->bhrb_stack.nr = u_index; - return; -} - /* * A counter has overflowed; update its count and record * things if requested. Note that interrupts are hard-disabled diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index a881232..b62aab3 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -128,7 +128,7 @@ config PPC_RTAS_DAEMON config RTAS_PROC bool "Proc interface to RTAS" - depends on PPC_RTAS + depends on PPC_RTAS && PROC_FS default y config RTAS_FLASH diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index d3e840d..c24684c 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -6,6 +6,7 @@ config PPC_POWERNV select PPC_ICP_NATIVE select PPC_P7_NAP select PPC_PCI_CHOICE if EMBEDDED + select EPAPR_BOOT default y config POWERNV_MSI diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index ade4463..628c564 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -15,6 +15,7 @@ #include <linux/of.h> #include <linux/of_platform.h> #include <linux/interrupt.h> +#include <linux/slab.h> #include <asm/opal.h> #include <asm/firmware.h> @@ -28,6 +29,8 @@ struct opal { static struct device_node *opal_node; static DEFINE_SPINLOCK(opal_write_lock); extern u64 opal_mc_secondary_handler[]; +static unsigned int *opal_irqs; +static unsigned int opal_irq_count; int __init early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data) @@ -53,7 +56,11 @@ int __init early_init_dt_scan_opal(unsigned long node, opal.entry, entryp, entrysz); powerpc_firmware_features |= FW_FEATURE_OPAL; - if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) { + if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) { + powerpc_firmware_features |= FW_FEATURE_OPALv2; + powerpc_firmware_features |= FW_FEATURE_OPALv3; + printk("OPAL V3 detected !\n"); + } else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) { powerpc_firmware_features |= FW_FEATURE_OPALv2; printk("OPAL V2 detected !\n"); } else { @@ -144,6 +151,13 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) { len = total_len; rc = opal_console_write(vtermno, &len, data); + + /* Closed or other error drop */ + if (rc != OPAL_SUCCESS && rc != OPAL_BUSY && + rc != OPAL_BUSY_EVENT) { + written = total_len; + break; + } if (rc == OPAL_SUCCESS) { total_len -= len; data += len; @@ -316,6 +330,8 @@ static int __init opal_init(void) irqs = of_get_property(opal_node, "opal-interrupts", &irqlen); pr_debug("opal: Found %d interrupts reserved for OPAL\n", irqs ? (irqlen / 4) : 0); + opal_irq_count = irqlen / 4; + opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL); for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) { unsigned int hwirq = be32_to_cpup(irqs); unsigned int irq = irq_create_mapping(NULL, hwirq); @@ -327,7 +343,19 @@ static int __init opal_init(void) if (rc) pr_warning("opal: Error %d requesting irq %d" " (0x%x)\n", rc, irq, hwirq); + opal_irqs[i] = irq; } return 0; } subsys_initcall(opal_init); + +void opal_shutdown(void) +{ + unsigned int i; + + for (i = 0; i < opal_irq_count; i++) { + if (opal_irqs[i]) + free_irq(opal_irqs[i], 0); + opal_irqs[i] = 0; + } +} diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 1da578b..9c9d15e 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -68,16 +68,6 @@ define_pe_printk_level(pe_err, KERN_ERR); define_pe_printk_level(pe_warn, KERN_WARNING); define_pe_printk_level(pe_info, KERN_INFO); -static struct pci_dn *pnv_ioda_get_pdn(struct pci_dev *dev) -{ - struct device_node *np; - - np = pci_device_to_OF_node(dev); - if (!np) - return NULL; - return PCI_DN(np); -} - static int pnv_ioda_alloc_pe(struct pnv_phb *phb) { unsigned long pe; @@ -110,7 +100,7 @@ static struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct pnv_phb *phb = hose->private_data; - struct pci_dn *pdn = pnv_ioda_get_pdn(dev); + struct pci_dn *pdn = pci_get_pdn(dev); if (!pdn) return NULL; @@ -173,7 +163,7 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) /* Add to all parents PELT-V */ while (parent) { - struct pci_dn *pdn = pnv_ioda_get_pdn(parent); + struct pci_dn *pdn = pci_get_pdn(parent); if (pdn && pdn->pe_number != IODA_INVALID_PE) { rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number, pe->pe_number, OPAL_ADD_PE_TO_DOMAIN); @@ -252,7 +242,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct pnv_phb *phb = hose->private_data; - struct pci_dn *pdn = pnv_ioda_get_pdn(dev); + struct pci_dn *pdn = pci_get_pdn(dev); struct pnv_ioda_pe *pe; int pe_num; @@ -323,7 +313,7 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) struct pci_dev *dev; list_for_each_entry(dev, &bus->devices, bus_list) { - struct pci_dn *pdn = pnv_ioda_get_pdn(dev); + struct pci_dn *pdn = pci_get_pdn(dev); if (pdn == NULL) { pr_warn("%s: No device node associated with device !\n", @@ -436,7 +426,7 @@ static void pnv_pci_ioda_setup_PEs(void) static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev) { - struct pci_dn *pdn = pnv_ioda_get_pdn(pdev); + struct pci_dn *pdn = pci_get_pdn(pdev); struct pnv_ioda_pe *pe; /* @@ -768,6 +758,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, unsigned int is_64, struct msi_msg *msg) { struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev); + struct pci_dn *pdn = pci_get_pdn(dev); struct irq_data *idata; struct irq_chip *ichip; unsigned int xive_num = hwirq - phb->msi_base; @@ -783,6 +774,10 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, if (pe->mve_number < 0) return -ENXIO; + /* Force 32-bit MSI on some broken devices */ + if (pdn && pdn->force_32bit_msi) + is_64 = 0; + /* Assign XIVE to PE */ rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num); if (rc) { @@ -1035,7 +1030,7 @@ static int pnv_pci_enable_device_hook(struct pci_dev *dev) if (!phb->initialized) return 0; - pdn = pnv_ioda_get_pdn(dev); + pdn = pci_get_pdn(dev); if (!pdn || pdn->pe_number == IODA_INVALID_PE) return -EINVAL; @@ -1048,6 +1043,12 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus, return phb->ioda.pe_rmap[(bus->number << 8) | devfn]; } +static void pnv_pci_ioda_shutdown(struct pnv_phb *phb) +{ + opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET, + OPAL_ASSERT_RESET); +} + void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type) { struct pci_controller *hose; @@ -1178,6 +1179,9 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type) /* Setup TCEs */ phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup; + /* Setup shutdown function for kexec */ + phb->shutdown = pnv_pci_ioda_shutdown; + /* Setup MSI support */ pnv_pci_init_ioda_msis(phb); diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 55dfca844..277343c 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -47,6 +47,10 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); struct pnv_phb *phb = hose->private_data; + struct pci_dn *pdn = pci_get_pdn(pdev); + + if (pdn && pdn->force_32bit_msi && !phb->msi32_support) + return -ENODEV; return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV; } @@ -367,7 +371,7 @@ static void pnv_tce_free(struct iommu_table *tbl, long index, long npages) while (npages--) *(tcep++) = 0; - if (tbl->it_type & TCE_PCI_SWINV_CREATE) + if (tbl->it_type & TCE_PCI_SWINV_FREE) pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1); } @@ -450,6 +454,18 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) pnv_pci_dma_fallback_setup(hose, pdev); } +void pnv_pci_shutdown(void) +{ + struct pci_controller *hose; + + list_for_each_entry(hose, &hose_list, list_node) { + struct pnv_phb *phb = hose->private_data; + + if (phb && phb->shutdown) + phb->shutdown(phb); + } +} + /* Fixup wrong class code in p7ioc and p8 root complex */ static void pnv_p7ioc_rc_quirk(struct pci_dev *dev) { diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 48dc4bb..25d76c4 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -86,6 +86,7 @@ struct pnv_phb { void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev); void (*fixup_phb)(struct pci_controller *hose); u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn); + void (*shutdown)(struct pnv_phb *phb); union { struct { @@ -158,4 +159,5 @@ extern void pnv_pci_init_ioda_hub(struct device_node *np); extern void pnv_pci_init_ioda2_phb(struct device_node *np); extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, u64 *startp, u64 *endp); + #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 8a9df7f..a1c6f83 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -9,8 +9,10 @@ static inline void pnv_smp_init(void) { } #ifdef CONFIG_PCI extern void pnv_pci_init(void); +extern void pnv_pci_shutdown(void); #else static inline void pnv_pci_init(void) { } +static inline void pnv_pci_shutdown(void) { } #endif #endif /* _POWERNV_H */ diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index db1ad1c..d4459bf 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -78,7 +78,9 @@ static void pnv_show_cpuinfo(struct seq_file *m) if (root) model = of_get_property(root, "model", NULL); seq_printf(m, "machine\t\t: PowerNV %s\n", model); - if (firmware_has_feature(FW_FEATURE_OPALv2)) + if (firmware_has_feature(FW_FEATURE_OPALv3)) + seq_printf(m, "firmware\t: OPAL v3\n"); + else if (firmware_has_feature(FW_FEATURE_OPALv2)) seq_printf(m, "firmware\t: OPAL v2\n"); else if (firmware_has_feature(FW_FEATURE_OPAL)) seq_printf(m, "firmware\t: OPAL v1\n"); @@ -126,6 +128,17 @@ static void pnv_progress(char *s, unsigned short hex) { } +static void pnv_shutdown(void) +{ + /* Let the PCI code clear up IODA tables */ + pnv_pci_shutdown(); + + /* And unregister all OPAL interrupts so they don't fire + * up while we kexec + */ + opal_shutdown(); +} + #ifdef CONFIG_KEXEC static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) { @@ -187,6 +200,7 @@ define_machine(powernv) { .init_IRQ = pnv_init_IRQ, .show_cpuinfo = pnv_show_cpuinfo, .progress = pnv_progress, + .machine_shutdown = pnv_shutdown, .power_save = power7_idle, .calibrate_decr = generic_calibrate_decr, #ifdef CONFIG_KEXEC diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 6a3ecca..88c9459 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -71,18 +71,68 @@ int pnv_smp_kick_cpu(int nr) BUG_ON(nr < 0 || nr >= NR_CPUS); - /* On OPAL v2 the CPU are still spinning inside OPAL itself, - * get them back now + /* + * If we already started or OPALv2 is not supported, we just + * kick the CPU via the PACA */ - if (!paca[nr].cpu_start && firmware_has_feature(FW_FEATURE_OPALv2)) { - pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu); - rc = opal_start_cpu(pcpu, start_here); + if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPALv2)) + goto kick; + + /* + * At this point, the CPU can either be spinning on the way in + * from kexec or be inside OPAL waiting to be started for the + * first time. OPAL v3 allows us to query OPAL to know if it + * has the CPUs, so we do that + */ + if (firmware_has_feature(FW_FEATURE_OPALv3)) { + uint8_t status; + + rc = opal_query_cpu_status(pcpu, &status); if (rc != OPAL_SUCCESS) { - pr_warn("OPAL Error %ld starting CPU %d\n", + pr_warn("OPAL Error %ld querying CPU %d state\n", rc, nr); return -ENODEV; } + + /* + * Already started, just kick it, probably coming from + * kexec and spinning + */ + if (status == OPAL_THREAD_STARTED) + goto kick; + + /* + * Available/inactive, let's kick it + */ + if (status == OPAL_THREAD_INACTIVE) { + pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", + nr, pcpu); + rc = opal_start_cpu(pcpu, start_here); + if (rc != OPAL_SUCCESS) { + pr_warn("OPAL Error %ld starting CPU %d\n", + rc, nr); + return -ENODEV; + } + } else { + /* + * An unavailable CPU (or any other unknown status) + * shouldn't be started. It should also + * not be in the possible map but currently it can + * happen + */ + pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable" + " (status %d)...\n", nr, pcpu, status); + return -ENODEV; + } + } else { + /* + * On OPAL v2, we just kick it and hope for the best, + * we must not test the error from opal_start_cpu() or + * we would fail to get CPUs from kexec. + */ + opal_start_cpu(pcpu, start_here); } + kick: return smp_generic_kick_cpu(nr); } diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 9a0941b..023b288 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -18,6 +18,7 @@ config PPC_PSERIES select PPC_PCI_CHOICE if EXPERT select ZLIB_DEFLATE select PPC_DOORBELL + select HAVE_CONTEXT_TRACKING default y config PPC_SPLPAR diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 420524e..6d2f0ab 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -26,26 +26,6 @@ static int query_token, change_token; #define RTAS_CHANGE_MSIX_FN 4 #define RTAS_CHANGE_32MSI_FN 5 -static struct pci_dn *get_pdn(struct pci_dev *pdev) -{ - struct device_node *dn; - struct pci_dn *pdn; - - dn = pci_device_to_OF_node(pdev); - if (!dn) { - dev_dbg(&pdev->dev, "rtas_msi: No OF device node\n"); - return NULL; - } - - pdn = PCI_DN(dn); - if (!pdn) { - dev_dbg(&pdev->dev, "rtas_msi: No PCI DN\n"); - return NULL; - } - - return pdn; -} - /* RTAS Helpers */ static int rtas_change_msi(struct pci_dn *pdn, u32 func, u32 num_irqs) @@ -91,7 +71,7 @@ static void rtas_disable_msi(struct pci_dev *pdev) { struct pci_dn *pdn; - pdn = get_pdn(pdev); + pdn = pci_get_pdn(pdev); if (!pdn) return; @@ -152,7 +132,7 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name) struct pci_dn *pdn; const u32 *req_msi; - pdn = get_pdn(pdev); + pdn = pci_get_pdn(pdev); if (!pdn) return -ENODEV; @@ -394,6 +374,23 @@ static int check_msix_entries(struct pci_dev *pdev) return 0; } +static void rtas_hack_32bit_msi_gen2(struct pci_dev *pdev) +{ + u32 addr_hi, addr_lo; + + /* + * We should only get in here for IODA1 configs. This is based on the + * fact that we using RTAS for MSIs, we don't have the 32 bit MSI RTAS + * support, and we are in a PCIe Gen2 slot. + */ + dev_info(&pdev->dev, + "rtas_msi: No 32 bit MSI firmware support, forcing 32 bit MSI\n"); + pci_read_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, &addr_hi); + addr_lo = 0xffff0000 | ((addr_hi >> (48 - 32)) << 4); + pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_LO, addr_lo); + pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, 0); +} + static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) { struct pci_dn *pdn; @@ -401,8 +398,9 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) struct msi_desc *entry; struct msi_msg msg; int nvec = nvec_in; + int use_32bit_msi_hack = 0; - pdn = get_pdn(pdev); + pdn = pci_get_pdn(pdev); if (!pdn) return -ENODEV; @@ -428,15 +426,31 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) */ again: if (type == PCI_CAP_ID_MSI) { - if (pdn->force_32bit_msi) + if (pdn->force_32bit_msi) { rc = rtas_change_msi(pdn, RTAS_CHANGE_32MSI_FN, nvec); - else + if (rc < 0) { + /* + * We only want to run the 32 bit MSI hack below if + * the max bus speed is Gen2 speed + */ + if (pdev->bus->max_bus_speed != PCIE_SPEED_5_0GT) + return rc; + + use_32bit_msi_hack = 1; + } + } else + rc = -1; + + if (rc < 0) rc = rtas_change_msi(pdn, RTAS_CHANGE_MSI_FN, nvec); - if (rc < 0 && !pdn->force_32bit_msi) { + if (rc < 0) { pr_debug("rtas_msi: trying the old firmware call.\n"); rc = rtas_change_msi(pdn, RTAS_CHANGE_FN, nvec); } + + if (use_32bit_msi_hack && rc > 0) + rtas_hack_32bit_msi_gen2(pdev); } else rc = rtas_change_msi(pdn, RTAS_CHANGE_MSIX_FN, nvec); @@ -518,12 +532,3 @@ static int rtas_msi_init(void) } arch_initcall(rtas_msi_init); -static void quirk_radeon(struct pci_dev *dev) -{ - struct pci_dn *pdn = get_pdn(dev); - - if (pdn) - pdn->force_32bit_msi = 1; -} -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x68f2, quirk_radeon); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0xaa68, quirk_radeon); diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 47226e0..5f997e7 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -16,6 +16,7 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/cpu.h> #include <linux/delay.h> #include <linux/suspend.h> #include <linux/stat.h> @@ -126,11 +127,15 @@ static ssize_t store_hibernate(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { + cpumask_var_t offline_mask; int rc; if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY)) + return -ENOMEM; + stream_id = simple_strtoul(buf, NULL, 16); do { @@ -140,15 +145,32 @@ static ssize_t store_hibernate(struct device *dev, } while (rc == -EAGAIN); if (!rc) { + /* All present CPUs must be online */ + cpumask_andnot(offline_mask, cpu_present_mask, + cpu_online_mask); + rc = rtas_online_cpus_mask(offline_mask); + if (rc) { + pr_err("%s: Could not bring present CPUs online.\n", + __func__); + goto out; + } + stop_topology_update(); rc = pm_suspend(PM_SUSPEND_MEM); start_topology_update(); + + /* Take down CPUs not online prior to suspend */ + if (!rtas_offline_cpus_mask(offline_mask)) + pr_warn("%s: Could not restore CPUs to offline " + "state.\n", __func__); } stream_id = 0; if (!rc) rc = count; +out: + free_cpumask_var(offline_mask); return rc; } diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c index 97fe82e..2d3b1dd 100644 --- a/arch/powerpc/platforms/wsp/ics.c +++ b/arch/powerpc/platforms/wsp/ics.c @@ -361,7 +361,7 @@ static int wsp_chip_set_affinity(struct irq_data *d, xive = xive_set_server(xive, get_irq_server(ics, hw_irq)); wsp_ics_set_xive(ics, hw_irq, xive); - return 0; + return IRQ_SET_MASK_OK; } static struct irq_chip wsp_irq_chip = { diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index b0a518e..99464a7 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -64,6 +64,8 @@ endif obj-$(CONFIG_PPC_SCOM) += scom.o +obj-$(CONFIG_PPC_EARLY_DEBUG_MEMCONS) += udbg_memcons.o + subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror obj-$(CONFIG_PPC_XICS) += xics/ diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c index 6e0e100..9cd0e60 100644 --- a/arch/powerpc/sysdev/ehv_pic.c +++ b/arch/powerpc/sysdev/ehv_pic.c @@ -81,7 +81,7 @@ int ehv_pic_set_affinity(struct irq_data *d, const struct cpumask *dest, ev_int_set_config(src, config, prio, cpuid); spin_unlock_irqrestore(&ehv_pic_lock, flags); - return 0; + return IRQ_SET_MASK_OK; } static unsigned int ehv_pic_type_to_vecpri(unsigned int type) diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index ee21b5e..0a13ecb 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -836,7 +836,7 @@ int mpic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, mpic_physmask(mask)); } - return 0; + return IRQ_SET_MASK_OK; } static unsigned int mpic_type_to_vecpri(struct mpic *mpic, unsigned int type) diff --git a/arch/powerpc/sysdev/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c new file mode 100644 index 0000000..ce5a7b4 --- /dev/null +++ b/arch/powerpc/sysdev/udbg_memcons.c @@ -0,0 +1,105 @@ +/* + * A udbg backend which logs messages and reads input from in memory + * buffers. + * + * The console output can be read from memcons_output which is a + * circular buffer whose next write position is stored in memcons.output_pos. + * + * Input may be passed by writing into the memcons_input buffer when it is + * empty. The input buffer is empty when both input_pos == input_start and + * *input_start == '\0'. + * + * Copyright (C) 2003-2005 Anton Blanchard and Milton Miller, IBM Corp + * Copyright (C) 2013 Alistair Popple, IBM Corp + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <asm/barrier.h> +#include <asm/page.h> +#include <asm/processor.h> +#include <asm/udbg.h> + +struct memcons { + char *output_start; + char *output_pos; + char *output_end; + char *input_start; + char *input_pos; + char *input_end; +}; + +static char memcons_output[CONFIG_PPC_MEMCONS_OUTPUT_SIZE]; +static char memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE]; + +struct memcons memcons = { + .output_start = memcons_output, + .output_pos = memcons_output, + .output_end = &memcons_output[CONFIG_PPC_MEMCONS_OUTPUT_SIZE], + .input_start = memcons_input, + .input_pos = memcons_input, + .input_end = &memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE], +}; + +void memcons_putc(char c) +{ + char *new_output_pos; + + *memcons.output_pos = c; + wmb(); + new_output_pos = memcons.output_pos + 1; + if (new_output_pos >= memcons.output_end) + new_output_pos = memcons.output_start; + + memcons.output_pos = new_output_pos; +} + +int memcons_getc_poll(void) +{ + char c; + char *new_input_pos; + + if (*memcons.input_pos) { + c = *memcons.input_pos; + + new_input_pos = memcons.input_pos + 1; + if (new_input_pos >= memcons.input_end) + new_input_pos = memcons.input_start; + else if (*new_input_pos == '\0') + new_input_pos = memcons.input_start; + + *memcons.input_pos = '\0'; + wmb(); + memcons.input_pos = new_input_pos; + return c; + } + + return -1; +} + +int memcons_getc(void) +{ + int c; + + while (1) { + c = memcons_getc_poll(); + if (c == -1) + cpu_relax(); + else + break; + } + + return c; +} + +void udbg_init_memcons(void) +{ + udbg_putc = memcons_putc; + udbg_getc = memcons_getc; + udbg_getc_poll = memcons_getc_poll; +} diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c index f7e8609..39d7221 100644 --- a/arch/powerpc/sysdev/xics/ics-opal.c +++ b/arch/powerpc/sysdev/xics/ics-opal.c @@ -148,7 +148,7 @@ static int ics_opal_set_affinity(struct irq_data *d, __func__, d->irq, hw_irq, server, rc); return -1; } - return 0; + return IRQ_SET_MASK_OK; } static struct irq_chip ics_opal_irq_chip = { diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 2c9789d..da183c5 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -98,7 +98,6 @@ config S390 select CLONE_BACKWARDS2 select GENERIC_CLOCKEVENTS select GENERIC_CPU_DEVICES if !SMP - select GENERIC_KERNEL_THREAD select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL_OLD select HAVE_ALIGNED_STRUCT_PAGE if SLUB diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index b7931fa..bf246da 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -9,11 +9,6 @@ struct dyn_arch_ftrace { }; #define MCOUNT_ADDR ((long)_mcount) -#ifdef CONFIG_64BIT -#define MCOUNT_INSN_SIZE 12 -#else -#define MCOUNT_INSN_SIZE 20 -#endif static inline unsigned long ftrace_call_adjust(unsigned long addr) { @@ -21,4 +16,11 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) } #endif /* __ASSEMBLY__ */ + +#ifdef CONFIG_64BIT +#define MCOUNT_INSN_SIZE 12 +#else +#define MCOUNT_INSN_SIZE 22 +#endif + #endif /* _ASM_S390_FTRACE_H */ diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 75ce9b0..5d64fb7 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -32,7 +32,7 @@ void storage_key_init_range(unsigned long start, unsigned long end); -static unsigned long pfmf(unsigned long function, unsigned long address) +static inline unsigned long pfmf(unsigned long function, unsigned long address) { asm volatile( " .insn rre,0xb9af0000,%[function],%[address]" @@ -44,17 +44,13 @@ static unsigned long pfmf(unsigned long function, unsigned long address) static inline void clear_page(void *page) { - if (MACHINE_HAS_PFMF) { - pfmf(0x10000, (unsigned long)page); - } else { - register unsigned long reg1 asm ("1") = 0; - register void *reg2 asm ("2") = page; - register unsigned long reg3 asm ("3") = 4096; - asm volatile( - " mvcl 2,0" - : "+d" (reg2), "+d" (reg3) : "d" (reg1) - : "memory", "cc"); - } + register unsigned long reg1 asm ("1") = 0; + register void *reg2 asm ("2") = page; + register unsigned long reg3 asm ("3") = 4096; + asm volatile( + " mvcl 2,0" + : "+d" (reg2), "+d" (reg3) : "d" (reg1) + : "memory", "cc"); } static inline void copy_page(void *to, void *from) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 4105b82..0f0de30 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -306,7 +306,7 @@ extern unsigned long MODULES_END; #define RCP_HC_BIT 0x00200000UL #define RCP_GR_BIT 0x00040000UL #define RCP_GC_BIT 0x00020000UL -#define RCP_IN_BIT 0x00008000UL /* IPTE notify bit */ +#define RCP_IN_BIT 0x00002000UL /* IPTE notify bit */ /* User dirty / referenced bit for KVM's migration feature */ #define KVM_UR_BIT 0x00008000UL @@ -374,7 +374,7 @@ extern unsigned long MODULES_END; #define RCP_HC_BIT 0x0020000000000000UL #define RCP_GR_BIT 0x0004000000000000UL #define RCP_GC_BIT 0x0002000000000000UL -#define RCP_IN_BIT 0x0000800000000000UL /* IPTE notify bit */ +#define RCP_IN_BIT 0x0000200000000000UL /* IPTE notify bit */ /* User dirty / referenced bit for KVM's migration feature */ #define KVM_UR_BIT 0x0000800000000000UL diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 7f4a4a8..be87d3e 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -1862,6 +1862,8 @@ void print_fn_code(unsigned char *code, unsigned long len) while (len) { ptr = buffer; opsize = insn_length(*code); + if (opsize > len) + break; ptr += sprintf(ptr, "%p: ", code); for (i = 0; i < opsize; i++) ptr += sprintf(ptr, "%02x", code[i]); diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 78bdf0e..e3043ae 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -16,12 +16,6 @@ #include <trace/syscall.h> #include <asm/asm-offsets.h> -#ifdef CONFIG_64BIT -#define MCOUNT_OFFSET_RET 12 -#else -#define MCOUNT_OFFSET_RET 22 -#endif - #ifdef CONFIG_DYNAMIC_FTRACE void ftrace_disable_code(void); @@ -155,9 +149,10 @@ unsigned long __kprobes prepare_ftrace_return(unsigned long parent, if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; + ip = (ip & PSW_ADDR_INSN) - MCOUNT_INSN_SIZE; if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) goto out; - trace.func = (ip & PSW_ADDR_INSN) - MCOUNT_OFFSET_RET; + trace.func = ip; /* Only trace if the calling function expects to. */ if (!ftrace_graph_entry(&trace)) { current->curr_ret_stack--; diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 4567ce2..08dcf21 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -7,6 +7,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/ftrace.h> .section .kprobes.text, "ax" @@ -33,6 +34,7 @@ ENTRY(ftrace_caller) la %r2,0(%r14) st %r0,__SF_BACKCHAIN(%r15) la %r3,0(%r3) + ahi %r2,-MCOUNT_INSN_SIZE l %r14,0b-0b(%r1) l %r14,0(%r14) basr %r14,%r14 diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S index 1133219..1c52eae 100644 --- a/arch/s390/kernel/mcount64.S +++ b/arch/s390/kernel/mcount64.S @@ -7,6 +7,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/ftrace.h> .section .kprobes.text, "ax" @@ -29,6 +30,7 @@ ENTRY(ftrace_caller) stg %r1,__SF_BACKCHAIN(%r15) lgr %r2,%r14 lg %r3,168(%r15) + aghi %r2,-MCOUNT_INSN_SIZE larl %r14,ftrace_trace_function lg %r14,0(%r14) basr %r14,%r14 diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 8074cb4..05674b6 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -645,7 +645,7 @@ static int __cpuinit __smp_rescan_cpus(struct sclp_cpu_info *info, continue; pcpu = pcpu_devices + cpu; pcpu->address = info->cpu[i].address; - pcpu->state = (cpu >= info->configured) ? + pcpu->state = (i >= info->configured) ? CPU_STATE_STANDBY : CPU_STATE_CONFIGURED; smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); set_cpu_present(cpu, true); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 7805ddc..18dc417 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -677,8 +677,7 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long start, unsigned long len) break; } /* Get the page mapped */ - if (get_user_pages(current, gmap->mm, addr, 1, 1, 0, - NULL, NULL) != 1) { + if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE)) { rc = -EFAULT; break; } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6a154a9..685692c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -108,7 +108,6 @@ config X86 select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) select GENERIC_TIME_VSYSCALL if X86_64 select KTIME_SCALAR if X86_32 - select ALWAYS_USE_PERSISTENT_CLOCK select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HAVE_CONTEXT_TRACKING if X86_64 diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index dab95a8..55b6761 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -34,7 +34,7 @@ extern pgd_t early_level4_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; static unsigned int __initdata next_early_pgt = 2; -pmdval_t __initdata early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); +pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c index d893e8e..2e9e128 100644 --- a/arch/x86/kernel/microcode_intel_early.c +++ b/arch/x86/kernel/microcode_intel_early.c @@ -487,6 +487,7 @@ static inline void show_saved_mc(void) #endif #if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU) +static DEFINE_MUTEX(x86_cpu_microcode_mutex); /* * Save this mc into mc_saved_data. So it will be loaded early when a CPU is * hot added or resumes. @@ -507,7 +508,7 @@ int save_mc_for_early(u8 *mc) * Hold hotplug lock so mc_saved_data is not accessed by a CPU in * hotplug. */ - cpu_hotplug_driver_lock(); + mutex_lock(&x86_cpu_microcode_mutex); mc_saved_count_init = mc_saved_data.mc_saved_count; mc_saved_count = mc_saved_data.mc_saved_count; @@ -544,7 +545,7 @@ int save_mc_for_early(u8 *mc) } out: - cpu_hotplug_driver_unlock(); + mutex_unlock(&x86_cpu_microcode_mutex); return ret; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 607af0d..4e7a37f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -312,6 +312,8 @@ void arch_cpu_idle(void) { if (cpuidle_idle_call()) x86_idle(); + else + local_irq_enable(); } /* @@ -368,9 +370,6 @@ void amd_e400_remove_cpu(int cpu) */ static void amd_e400_idle(void) { - if (need_resched()) - return; - if (!amd_e400_c1e_detected) { u32 lo, hi; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index fdc5dca..eaac174 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -359,7 +359,17 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, } /* - * would have hole in the middle or ends, and only ram parts will be mapped. + * We need to iterate through the E820 memory map and create direct mappings + * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply + * create direct mappings for all pfns from [0 to max_low_pfn) and + * [4GB to max_pfn) because of possible memory holes in high addresses + * that cannot be marked as UC by fixed/variable range MTRRs. + * Depending on the alignment of E820 ranges, this may possibly result + * in using smaller size (i.e. 4K instead of 2M or 1G) page tables. + * + * init_mem_mapping() calls init_range_memory_mapping() with big range. + * That range would have hole in the middle or ends, and only ram parts + * will be mapped in init_range_memory_mapping(). */ static unsigned long __init init_range_memory_mapping( unsigned long r_start, @@ -419,6 +429,13 @@ void __init init_mem_mapping(void) max_pfn_mapped = 0; /* will get exact value next */ min_pfn_mapped = real_end >> PAGE_SHIFT; last_start = start = real_end; + + /* + * We start from the top (end of memory) and go to the bottom. + * The memblock_find_in_range() gets us a block of RAM from the + * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages + * for page table. + */ while (last_start > ISA_END_ADDRESS) { if (last_start > step_size) { start = round_down(last_start - 1, step_size); diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c index 0e0fabf..6eb18c4 100644 --- a/arch/x86/pci/mrst.c +++ b/arch/x86/pci/mrst.c @@ -141,11 +141,6 @@ static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn, */ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg) { - if (bus == 0 && (devfn == PCI_DEVFN(2, 0) - || devfn == PCI_DEVFN(0, 0) - || devfn == PCI_DEVFN(3, 0))) - return 1; - /* This is a workaround for A0 LNC bug where PCI status register does * not have new CAP bit set. can not be written by SW either. * @@ -155,7 +150,10 @@ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg) */ if (reg >= 0x100 || reg == PCI_STATUS || reg == PCI_HEADER_TYPE) return 0; - + if (bus == 0 && (devfn == PCI_DEVFN(2, 0) + || devfn == PCI_DEVFN(0, 0) + || devfn == PCI_DEVFN(3, 0))) + return 1; return 0; /* langwell on others */ } |