diff options
Diffstat (limited to 'arch')
448 files changed, 6704 insertions, 5352 deletions
diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h index 1f8c729..52cd2a4 100644 --- a/arch/alpha/include/asm/thread_info.h +++ b/arch/alpha/include/asm/thread_info.h @@ -95,8 +95,6 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define TS_POLLING 0x0010 /* idle task polling need_resched, skip sending interrupt */ -#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING) - #ifndef __ASSEMBLY__ #define HAVE_SET_RESTORE_SIGMASK 1 static inline void set_restore_sigmask(void) diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 63d27fb..a3fd8a2 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -46,25 +46,6 @@ void (*pm_power_off)(void) = machine_power_off; EXPORT_SYMBOL(pm_power_off); -void -cpu_idle(void) -{ - current_thread_info()->status |= TS_POLLING; - - while (1) { - /* FIXME -- EV6 and LCA45 know how to power down - the CPU. */ - - rcu_idle_enter(); - while (!need_resched()) - cpu_relax(); - - rcu_idle_exit(); - schedule_preempt_disabled(); - } -} - - struct halt_info { int mode; char *restart_cmd; diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 9603bc2..7b60834 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -167,8 +167,7 @@ smp_callin(void) cpuid, current, current->active_mm)); preempt_disable(); - /* Do nothing. */ - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } /* Wait until hwrpb->txrdy is clear for cpu. Return -1 on timeout. */ diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index 1383f86..1d4aabf 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -185,7 +185,6 @@ nautilus_machine_check(unsigned long vector, unsigned long la_ptr) mb(); } -extern void free_reserved_mem(void *, void *); extern void pcibios_claim_one_bus(struct pci_bus *); static struct resource irongate_io = { @@ -239,8 +238,8 @@ nautilus_init_pci(void) if (pci_mem < memtop) memtop = pci_mem; if (memtop > alpha_mv.min_mem_address) { - free_reserved_mem(__va(alpha_mv.min_mem_address), - __va(memtop)); + free_reserved_area((unsigned long)__va(alpha_mv.min_mem_address), + (unsigned long)__va(memtop), 0, NULL); printk("nautilus_init_pci: %ldk freed\n", (memtop - alpha_mv.min_mem_address) >> 10); } diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 1ad6ca7..0ba85ee 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -31,6 +31,7 @@ #include <asm/console.h> #include <asm/tlb.h> #include <asm/setup.h> +#include <asm/sections.h> extern void die_if_kernel(char *,struct pt_regs *,long); @@ -281,8 +282,6 @@ printk_memory_info(void) { unsigned long codesize, reservedpages, datasize, initsize, tmp; extern int page_is_ram(unsigned long) __init; - extern char _text, _etext, _data, _edata; - extern char __init_begin, __init_end; /* printk all informations */ reservedpages = 0; @@ -318,32 +317,15 @@ mem_init(void) #endif /* CONFIG_DISCONTIGMEM */ void -free_reserved_mem(void *start, void *end) -{ - void *__start = start; - for (; __start < end; __start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(__start)); - init_page_count(virt_to_page(__start)); - free_page((long)__start); - totalram_pages++; - } -} - -void free_initmem(void) { - extern char __init_begin, __init_end; - - free_reserved_mem(&__init_begin, &__init_end); - printk ("Freeing unused kernel memory: %ldk freed\n", - (&__init_end - &__init_begin) >> 10); + free_initmem_default(0); } #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_mem((void *)start, (void *)end); - printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10); + free_reserved_area(start, end, 0, "initrd"); } #endif diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c index 3973ae3..3388504 100644 --- a/arch/alpha/mm/numa.c +++ b/arch/alpha/mm/numa.c @@ -17,6 +17,7 @@ #include <asm/hwrpb.h> #include <asm/pgalloc.h> +#include <asm/sections.h> pg_data_t node_data[MAX_NUMNODES]; EXPORT_SYMBOL(node_data); @@ -325,8 +326,6 @@ void __init mem_init(void) { unsigned long codesize, reservedpages, datasize, initsize, pfn; extern int page_is_ram(unsigned long) __init; - extern char _text, _etext, _data, _edata; - extern char __init_begin, __init_end; unsigned long nid, i; high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 0a7531d..cad6685 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -41,37 +41,12 @@ SYSCALL_DEFINE0(arc_gettls) return task_thread_info(current)->thr_ptr; } -static inline void arch_idle(void) +void arch_cpu_idle(void) { /* sleep, but enable all interrupts before committing */ __asm__("sleep 0x3"); } -void cpu_idle(void) -{ - /* Since we SLEEP in idle loop, TIF_POLLING_NRFLAG can't be set */ - - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - -doze: - local_irq_disable(); - if (!need_resched()) { - arch_idle(); - goto doze; - } else { - local_irq_enable(); - } - - rcu_idle_exit(); - tick_nohz_idle_exit(); - - schedule_preempt_disabled(); - } -} - asmlinkage void ret_from_fork(void); /* Layout of Child kernel mode stack as setup at the end of this function is diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 3af3e06..5c7fd60 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -141,7 +141,7 @@ void __cpuinit start_kernel_secondary(void) local_irq_enable(); preempt_disable(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } /* diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index caf797d..727d479 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -144,37 +144,18 @@ void __init mem_init(void) PAGES_TO_KB(reserved_pages)); } -static void __init free_init_pages(const char *what, unsigned long begin, - unsigned long end) -{ - unsigned long addr; - - pr_info("Freeing %s: %ldk [%lx] to [%lx]\n", - what, TO_KB(end - begin), begin, end); - - /* need to check that the page we free is not a partial page */ - for (addr = begin; addr + PAGE_SIZE <= end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } -} - /* * free_initmem: Free all the __init memory. */ void __init_refok free_initmem(void) { - free_init_pages("unused kernel memory", - (unsigned long)__init_begin, - (unsigned long)__init_end); + free_initmem_default(0); } #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_init_pages("initrd memory", start, end); + free_reserved_area(start, end, 0, "initrd"); } #endif diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 1cacda4..a39e321 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -15,6 +15,7 @@ config ARM select GENERIC_IRQ_SHOW select GENERIC_PCI_IOMAP select GENERIC_SMP_IDLE_THREAD + select GENERIC_IDLE_POLL_SETUP select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HARDIRQS_SW_RESEND @@ -549,6 +550,8 @@ config ARCH_IXP4XX select GENERIC_CLOCKEVENTS select MIGHT_HAVE_PCI select NEED_MACH_IO_H + select USB_EHCI_BIG_ENDIAN_MMIO + select USB_EHCI_BIG_ENDIAN_DESC help Support for Intel's IXP4XX (XScale) family of processors. diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi index cb7bcc5..39253b9 100644 --- a/arch/arm/boot/dts/at91sam9260.dtsi +++ b/arch/arm/boot/dts/at91sam9260.dtsi @@ -322,6 +322,24 @@ }; }; + spi0 { + pinctrl_spi0: spi0-0 { + atmel,pins = + <0 0 0x1 0x0 /* PA0 periph A SPI0_MISO pin */ + 0 1 0x1 0x0 /* PA1 periph A SPI0_MOSI pin */ + 0 2 0x1 0x0>; /* PA2 periph A SPI0_SPCK pin */ + }; + }; + + spi1 { + pinctrl_spi1: spi1-0 { + atmel,pins = + <1 0 0x1 0x0 /* PB0 periph A SPI1_MISO pin */ + 1 1 0x1 0x0 /* PB1 periph A SPI1_MOSI pin */ + 1 2 0x1 0x0>; /* PB2 periph A SPI1_SPCK pin */ + }; + }; + pioA: gpio@fffff400 { compatible = "atmel,at91rm9200-gpio"; reg = <0xfffff400 0x200>; @@ -471,6 +489,28 @@ status = "disabled"; }; + spi0: spi@fffc8000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "atmel,at91rm9200-spi"; + reg = <0xfffc8000 0x200>; + interrupts = <12 4 3>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi0>; + status = "disabled"; + }; + + spi1: spi@fffcc000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "atmel,at91rm9200-spi"; + reg = <0xfffcc000 0x200>; + interrupts = <13 4 3>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi1>; + status = "disabled"; + }; + adc0: adc@fffe0000 { compatible = "atmel,at91sam9260-adc"; reg = <0xfffe0000 0x100>; diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi index 271d4de..94b58ab 100644 --- a/arch/arm/boot/dts/at91sam9263.dtsi +++ b/arch/arm/boot/dts/at91sam9263.dtsi @@ -303,6 +303,24 @@ }; }; + spi0 { + pinctrl_spi0: spi0-0 { + atmel,pins = + <0 0 0x2 0x0 /* PA0 periph B SPI0_MISO pin */ + 0 1 0x2 0x0 /* PA1 periph B SPI0_MOSI pin */ + 0 2 0x2 0x0>; /* PA2 periph B SPI0_SPCK pin */ + }; + }; + + spi1 { + pinctrl_spi1: spi1-0 { + atmel,pins = + <1 12 0x1 0x0 /* PB12 periph A SPI1_MISO pin */ + 1 13 0x1 0x0 /* PB13 periph A SPI1_MOSI pin */ + 1 14 0x1 0x0>; /* PB14 periph A SPI1_SPCK pin */ + }; + }; + pioA: gpio@fffff200 { compatible = "atmel,at91rm9200-gpio"; reg = <0xfffff200 0x200>; @@ -462,6 +480,28 @@ reg = <0xfffffd40 0x10>; status = "disabled"; }; + + spi0: spi@fffa4000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "atmel,at91rm9200-spi"; + reg = <0xfffa4000 0x200>; + interrupts = <14 4 3>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi0>; + status = "disabled"; + }; + + spi1: spi@fffa8000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "atmel,at91rm9200-spi"; + reg = <0xfffa8000 0x200>; + interrupts = <15 4 3>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi1>; + status = "disabled"; + }; }; nand0: nand@40000000 { diff --git a/arch/arm/boot/dts/at91sam9263ek.dts b/arch/arm/boot/dts/at91sam9263ek.dts index 1eb0872..a14e424 100644 --- a/arch/arm/boot/dts/at91sam9263ek.dts +++ b/arch/arm/boot/dts/at91sam9263ek.dts @@ -79,6 +79,16 @@ }; }; }; + + spi0: spi@fffa4000 { + status = "okay"; + cs-gpios = <&pioA 5 0>, <0>, <0>, <0>; + mtd_dataflash@0 { + compatible = "atmel,at45", "atmel,dataflash"; + spi-max-frequency = <50000000>; + reg = <0>; + }; + }; }; nand0: nand@40000000 { diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi index da15e83..23d1f46 100644 --- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi +++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi @@ -96,6 +96,16 @@ status = "okay"; pinctrl-0 = <&pinctrl_ssc0_tx>; }; + + spi0: spi@fffc8000 { + status = "okay"; + cs-gpios = <0>, <&pioC 11 0>, <0>, <0>; + mtd_dataflash@0 { + compatible = "atmel,at45", "atmel,dataflash"; + spi-max-frequency = <50000000>; + reg = <1>; + }; + }; }; nand0: nand@40000000 { diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi index 6b1d4ca..cfdf429 100644 --- a/arch/arm/boot/dts/at91sam9g45.dtsi +++ b/arch/arm/boot/dts/at91sam9g45.dtsi @@ -322,6 +322,24 @@ }; }; + spi0 { + pinctrl_spi0: spi0-0 { + atmel,pins = + <1 0 0x1 0x0 /* PB0 periph A SPI0_MISO pin */ + 1 1 0x1 0x0 /* PB1 periph A SPI0_MOSI pin */ + 1 2 0x1 0x0>; /* PB2 periph A SPI0_SPCK pin */ + }; + }; + + spi1 { + pinctrl_spi1: spi1-0 { + atmel,pins = + <1 14 0x1 0x0 /* PB14 periph A SPI1_MISO pin */ + 1 15 0x1 0x0 /* PB15 periph A SPI1_MOSI pin */ + 1 16 0x1 0x0>; /* PB16 periph A SPI1_SPCK pin */ + }; + }; + pioA: gpio@fffff200 { compatible = "atmel,at91rm9200-gpio"; reg = <0xfffff200 0x200>; @@ -531,6 +549,28 @@ reg = <0xfffffd40 0x10>; status = "disabled"; }; + + spi0: spi@fffa4000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "atmel,at91rm9200-spi"; + reg = <0xfffa4000 0x200>; + interrupts = <14 4 3>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi0>; + status = "disabled"; + }; + + spi1: spi@fffa8000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "atmel,at91rm9200-spi"; + reg = <0xfffa8000 0x200>; + interrupts = <15 4 3>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi1>; + status = "disabled"; + }; }; nand0: nand@40000000 { diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts index 20c3191..92c52a7 100644 --- a/arch/arm/boot/dts/at91sam9m10g45ek.dts +++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts @@ -102,6 +102,16 @@ }; }; }; + + spi0: spi@fffa4000{ + status = "okay"; + cs-gpios = <&pioB 3 0>, <0>, <0>, <0>; + mtd_dataflash@0 { + compatible = "atmel,at45", "atmel,dataflash"; + spi-max-frequency = <13000000>; + reg = <0>; + }; + }; }; nand0: nand@40000000 { diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi index 7750f98..b2961f1 100644 --- a/arch/arm/boot/dts/at91sam9n12.dtsi +++ b/arch/arm/boot/dts/at91sam9n12.dtsi @@ -261,6 +261,24 @@ }; }; + spi0 { + pinctrl_spi0: spi0-0 { + atmel,pins = + <0 11 0x1 0x0 /* PA11 periph A SPI0_MISO pin */ + 0 12 0x1 0x0 /* PA12 periph A SPI0_MOSI pin */ + 0 13 0x1 0x0>; /* PA13 periph A SPI0_SPCK pin */ + }; + }; + + spi1 { + pinctrl_spi1: spi1-0 { + atmel,pins = + <0 21 0x2 0x0 /* PA21 periph B SPI1_MISO pin */ + 0 22 0x2 0x0 /* PA22 periph B SPI1_MOSI pin */ + 0 23 0x2 0x0>; /* PA23 periph B SPI1_SPCK pin */ + }; + }; + pioA: gpio@fffff400 { compatible = "atmel,at91sam9x5-gpio", "atmel,at91rm9200-gpio"; reg = <0xfffff400 0x200>; @@ -373,6 +391,28 @@ #size-cells = <0>; status = "disabled"; }; + + spi0: spi@f0000000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "atmel,at91rm9200-spi"; + reg = <0xf0000000 0x100>; + interrupts = <13 4 3>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi0>; + status = "disabled"; + }; + + spi1: spi@f0004000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "atmel,at91rm9200-spi"; + reg = <0xf0004000 0x100>; + interrupts = <14 4 3>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi1>; + status = "disabled"; + }; }; nand0: nand@40000000 { diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts index d400f8d..34c842b 100644 --- a/arch/arm/boot/dts/at91sam9n12ek.dts +++ b/arch/arm/boot/dts/at91sam9n12ek.dts @@ -67,6 +67,16 @@ }; }; }; + + spi0: spi@f0000000 { + status = "okay"; + cs-gpios = <&pioA 14 0>, <0>, <0>, <0>; + m25p80@0 { + compatible = "atmel,at25df321a"; + spi-max-frequency = <50000000>; + reg = <0>; + }; + }; }; nand0: nand@40000000 { diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi index a98c0d5..347b438 100644 --- a/arch/arm/boot/dts/at91sam9x5.dtsi +++ b/arch/arm/boot/dts/at91sam9x5.dtsi @@ -343,6 +343,24 @@ }; }; + spi0 { + pinctrl_spi0: spi0-0 { + atmel,pins = + <0 11 0x1 0x0 /* PA11 periph A SPI0_MISO pin */ + 0 12 0x1 0x0 /* PA12 periph A SPI0_MOSI pin */ + 0 13 0x1 0x0>; /* PA13 periph A SPI0_SPCK pin */ + }; + }; + + spi1 { + pinctrl_spi1: spi1-0 { + atmel,pins = + <0 21 0x2 0x0 /* PA21 periph B SPI1_MISO pin */ + 0 22 0x2 0x0 /* PA22 periph B SPI1_MOSI pin */ + 0 23 0x2 0x0>; /* PA23 periph B SPI1_SPCK pin */ + }; + }; + pioA: gpio@fffff400 { compatible = "atmel,at91sam9x5-gpio", "atmel,at91rm9200-gpio"; reg = <0xfffff400 0x200>; @@ -529,6 +547,28 @@ trigger-value = <0x6>; }; }; + + spi0: spi@f0000000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "atmel,at91rm9200-spi"; + reg = <0xf0000000 0x100>; + interrupts = <13 4 3>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi0>; + status = "disabled"; + }; + + spi1: spi@f0004000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "atmel,at91rm9200-spi"; + reg = <0xf0004000 0x100>; + interrupts = <14 4 3>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi1>; + status = "disabled"; + }; }; nand0: nand@40000000 { diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi index 8a7cf1d..09f5e66 100644 --- a/arch/arm/boot/dts/at91sam9x5ek.dtsi +++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi @@ -84,6 +84,16 @@ }; }; }; + + spi0: spi@f0000000 { + status = "okay"; + cs-gpios = <&pioA 14 0>, <0>, <0>, <0>; + m25p80@0 { + compatible = "atmel,at25df321a"; + spi-max-frequency = <50000000>; + reg = <0>; + }; + }; }; usb0: ohci@00600000 { diff --git a/arch/arm/boot/dts/msm8660-surf.dts b/arch/arm/boot/dts/msm8660-surf.dts index 31f2157..67f8670 100644 --- a/arch/arm/boot/dts/msm8660-surf.dts +++ b/arch/arm/boot/dts/msm8660-surf.dts @@ -38,4 +38,10 @@ <0x19c00000 0x1000>; interrupts = <0 195 0x0>; }; + + qcom,ssbi@500000 { + compatible = "qcom,ssbi"; + reg = <0x500000 0x1000>; + qcom,controller-type = "pmic-arbiter"; + }; }; diff --git a/arch/arm/boot/dts/msm8960-cdp.dts b/arch/arm/boot/dts/msm8960-cdp.dts index 9e621b5..c9b09a8 100644 --- a/arch/arm/boot/dts/msm8960-cdp.dts +++ b/arch/arm/boot/dts/msm8960-cdp.dts @@ -38,4 +38,10 @@ <0x16400000 0x1000>; interrupts = <0 154 0x0>; }; + + qcom,ssbi@500000 { + compatible = "qcom,ssbi"; + reg = <0x500000 0x1000>; + qcom,controller-type = "pmic-arbiter"; + }; }; diff --git a/arch/arm/boot/dts/spear1310.dtsi b/arch/arm/boot/dts/spear1310.dtsi index 1513c19..122ae94 100644 --- a/arch/arm/boot/dts/spear1310.dtsi +++ b/arch/arm/boot/dts/spear1310.dtsi @@ -89,7 +89,7 @@ pinmux: pinmux@e0700000 { compatible = "st,spear1310-pinmux"; reg = <0xe0700000 0x1000>; - #gpio-range-cells = <2>; + #gpio-range-cells = <3>; }; apb { @@ -212,7 +212,7 @@ interrupt-controller; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&pinmux 0 246>; + gpio-ranges = <&pinmux 0 0 246>; status = "disabled"; st-plgpio,ngpio = <246>; diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi index 34da11a..c511c47 100644 --- a/arch/arm/boot/dts/spear1340.dtsi +++ b/arch/arm/boot/dts/spear1340.dtsi @@ -63,7 +63,7 @@ pinmux: pinmux@e0700000 { compatible = "st,spear1340-pinmux"; reg = <0xe0700000 0x1000>; - #gpio-range-cells = <2>; + #gpio-range-cells = <3>; }; pwm: pwm@e0180000 { @@ -127,7 +127,7 @@ interrupt-controller; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&pinmux 0 252>; + gpio-ranges = <&pinmux 0 0 252>; status = "disabled"; st-plgpio,ngpio = <250>; diff --git a/arch/arm/boot/dts/spear310.dtsi b/arch/arm/boot/dts/spear310.dtsi index ab45b8c..9537208 100644 --- a/arch/arm/boot/dts/spear310.dtsi +++ b/arch/arm/boot/dts/spear310.dtsi @@ -25,7 +25,7 @@ pinmux: pinmux@b4000000 { compatible = "st,spear310-pinmux"; reg = <0xb4000000 0x1000>; - #gpio-range-cells = <2>; + #gpio-range-cells = <3>; }; fsmc: flash@44000000 { @@ -102,7 +102,7 @@ interrupt-controller; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&pinmux 0 102>; + gpio-ranges = <&pinmux 0 0 102>; status = "disabled"; st-plgpio,ngpio = <102>; diff --git a/arch/arm/boot/dts/spear320.dtsi b/arch/arm/boot/dts/spear320.dtsi index caa5520..ffea342 100644 --- a/arch/arm/boot/dts/spear320.dtsi +++ b/arch/arm/boot/dts/spear320.dtsi @@ -24,7 +24,7 @@ pinmux: pinmux@b3000000 { compatible = "st,spear320-pinmux"; reg = <0xb3000000 0x1000>; - #gpio-range-cells = <2>; + #gpio-range-cells = <3>; }; clcd@90000000 { @@ -130,7 +130,7 @@ interrupt-controller; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&pinmux 0 102>; + gpio-ranges = <&pinmux 0 0 102>; status = "disabled"; st-plgpio,ngpio = <102>; diff --git a/arch/arm/boot/dts/vt8500-bv07.dts b/arch/arm/boot/dts/vt8500-bv07.dts index 567cf4e..877b33a 100644 --- a/arch/arm/boot/dts/vt8500-bv07.dts +++ b/arch/arm/boot/dts/vt8500-bv07.dts @@ -11,26 +11,22 @@ / { model = "Benign BV07 Netbook"; +}; - /* - * Display node is based on Sascha Hauer's patch on dri-devel. - * Added a bpp property to calculate the size of the framebuffer - * until the binding is formalized. - */ - display: display@0 { - modes { - mode0: mode@0 { - hactive = <800>; - vactive = <480>; - hback-porch = <88>; - hfront-porch = <40>; - hsync-len = <0>; - vback-porch = <32>; - vfront-porch = <11>; - vsync-len = <1>; - clock = <0>; /* unused but required */ - bpp = <16>; /* non-standard but required */ - }; +&fb { + bits-per-pixel = <16>; + display-timings { + native-mode = <&timing0>; + timing0: 800x480 { + clock-frequency = <0>; /* unused but required */ + hactive = <800>; + vactive = <480>; + hfront-porch = <40>; + hback-porch = <88>; + hsync-len = <0>; + vback-porch = <32>; + vfront-porch = <11>; + vsync-len = <1>; }; }; }; diff --git a/arch/arm/boot/dts/vt8500.dtsi b/arch/arm/boot/dts/vt8500.dtsi index cf31ced..68c8dc6 100644 --- a/arch/arm/boot/dts/vt8500.dtsi +++ b/arch/arm/boot/dts/vt8500.dtsi @@ -98,12 +98,10 @@ interrupts = <43>; }; - fb@d800e400 { + fb: fb@d8050800 { compatible = "via,vt8500-fb"; reg = <0xd800e400 0x400>; interrupts = <12>; - display = <&display>; - default-mode = <&mode0>; }; ge_rops@d8050400 { diff --git a/arch/arm/boot/dts/wm8505-ref.dts b/arch/arm/boot/dts/wm8505-ref.dts index fd4e248..edd2cec 100644 --- a/arch/arm/boot/dts/wm8505-ref.dts +++ b/arch/arm/boot/dts/wm8505-ref.dts @@ -11,26 +11,22 @@ / { model = "Wondermedia WM8505 Netbook"; +}; - /* - * Display node is based on Sascha Hauer's patch on dri-devel. - * Added a bpp property to calculate the size of the framebuffer - * until the binding is formalized. - */ - display: display@0 { - modes { - mode0: mode@0 { - hactive = <800>; - vactive = <480>; - hback-porch = <88>; - hfront-porch = <40>; - hsync-len = <0>; - vback-porch = <32>; - vfront-porch = <11>; - vsync-len = <1>; - clock = <0>; /* unused but required */ - bpp = <32>; /* non-standard but required */ - }; +&fb { + bits-per-pixel = <32>; + display-timings { + native-mode = <&timing0>; + timing0: 800x480 { + clock-frequency = <0>; /* unused but required */ + hactive = <800>; + vactive = <480>; + hfront-porch = <40>; + hback-porch = <88>; + hsync-len = <0>; + vback-porch = <32>; + vfront-porch = <11>; + vsync-len = <1>; }; }; }; diff --git a/arch/arm/boot/dts/wm8505.dtsi b/arch/arm/boot/dts/wm8505.dtsi index e74a1c0..bcf668d 100644 --- a/arch/arm/boot/dts/wm8505.dtsi +++ b/arch/arm/boot/dts/wm8505.dtsi @@ -128,11 +128,9 @@ interrupts = <0>; }; - fb@d8050800 { + fb: fb@d8050800 { compatible = "wm,wm8505-fb"; reg = <0xd8050800 0x200>; - display = <&display>; - default-mode = <&mode0>; }; ge_rops@d8050400 { diff --git a/arch/arm/boot/dts/wm8650-mid.dts b/arch/arm/boot/dts/wm8650-mid.dts index cefd938..61671a0 100644 --- a/arch/arm/boot/dts/wm8650-mid.dts +++ b/arch/arm/boot/dts/wm8650-mid.dts @@ -11,26 +11,24 @@ / { model = "Wondermedia WM8650-MID Tablet"; +}; + +&fb { + bits-per-pixel = <16>; - /* - * Display node is based on Sascha Hauer's patch on dri-devel. - * Added a bpp property to calculate the size of the framebuffer - * until the binding is formalized. - */ - display: display@0 { - modes { - mode0: mode@0 { - hactive = <800>; - vactive = <480>; - hback-porch = <88>; - hfront-porch = <40>; - hsync-len = <0>; - vback-porch = <32>; - vfront-porch = <11>; - vsync-len = <1>; - clock = <0>; /* unused but required */ - bpp = <16>; /* non-standard but required */ - }; + display-timings { + native-mode = <&timing0>; + timing0: 800x480 { + clock-frequency = <0>; /* unused but required */ + hactive = <800>; + vactive = <480>; + hfront-porch = <40>; + hback-porch = <88>; + hsync-len = <0>; + vback-porch = <32>; + vfront-porch = <11>; + vsync-len = <1>; }; }; }; + diff --git a/arch/arm/boot/dts/wm8650.dtsi b/arch/arm/boot/dts/wm8650.dtsi index db3c0a1..9313407 100644 --- a/arch/arm/boot/dts/wm8650.dtsi +++ b/arch/arm/boot/dts/wm8650.dtsi @@ -128,11 +128,9 @@ interrupts = <43>; }; - fb@d8050800 { + fb: fb@d8050800 { compatible = "wm,wm8505-fb"; reg = <0xd8050800 0x200>; - display = <&display>; - default-mode = <&mode0>; }; ge_rops@d8050400 { diff --git a/arch/arm/boot/dts/wm8850-w70v2.dts b/arch/arm/boot/dts/wm8850-w70v2.dts index fcc660c..32d2253 100644 --- a/arch/arm/boot/dts/wm8850-w70v2.dts +++ b/arch/arm/boot/dts/wm8850-w70v2.dts @@ -15,28 +15,6 @@ / { model = "Wondermedia WM8850-W70v2 Tablet"; - /* - * Display node is based on Sascha Hauer's patch on dri-devel. - * Added a bpp property to calculate the size of the framebuffer - * until the binding is formalized. - */ - display: display@0 { - modes { - mode0: mode@0 { - hactive = <800>; - vactive = <480>; - hback-porch = <88>; - hfront-porch = <40>; - hsync-len = <0>; - vback-porch = <32>; - vfront-porch = <11>; - vsync-len = <1>; - clock = <0>; /* unused but required */ - bpp = <16>; /* non-standard but required */ - }; - }; - }; - backlight { compatible = "pwm-backlight"; pwms = <&pwm 0 50000 1>; /* duty inverted */ @@ -45,3 +23,21 @@ default-brightness-level = <5>; }; }; + +&fb { + bits-per-pixel = <16>; + display-timings { + native-mode = <&timing0>; + timing0: 800x480 { + clock-frequency = <0>; /* unused but required */ + hactive = <800>; + vactive = <480>; + hfront-porch = <40>; + hback-porch = <88>; + hsync-len = <0>; + vback-porch = <32>; + vfront-porch = <11>; + vsync-len = <1>; + }; + }; +}; diff --git a/arch/arm/boot/dts/wm8850.dtsi b/arch/arm/boot/dts/wm8850.dtsi index e8cbfdc..7149cd1 100644 --- a/arch/arm/boot/dts/wm8850.dtsi +++ b/arch/arm/boot/dts/wm8850.dtsi @@ -135,11 +135,9 @@ }; }; - fb@d8051700 { + fb: fb@d8051700 { compatible = "wm,wm8505-fb"; reg = <0xd8051700 0x200>; - display = <&display>; - default-mode = <&mode0>; }; ge_rops@d8050400 { diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index e36b010..088d6c1 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -188,6 +188,7 @@ CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_MXC=y CONFIG_USB_CHIPIDEA=y CONFIG_USB_CHIPIDEA_HOST=y +CONFIG_USB_PHY=y CONFIG_USB_MXS_PHY=y CONFIG_USB_STORAGE=y CONFIG_MMC=y diff --git a/arch/arm/configs/lpc32xx_defconfig b/arch/arm/configs/lpc32xx_defconfig index 92386b2..afa7249 100644 --- a/arch/arm/configs/lpc32xx_defconfig +++ b/arch/arm/configs/lpc32xx_defconfig @@ -134,6 +134,7 @@ CONFIG_SND_DEBUG_VERBOSE=y # CONFIG_SND_SPI is not set CONFIG_SND_SOC=y CONFIG_USB=y +CONFIG_USB_PHY=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_STORAGE=y CONFIG_USB_GADGET=y diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig index 6a99e30..87924d6 100644 --- a/arch/arm/configs/mxs_defconfig +++ b/arch/arm/configs/mxs_defconfig @@ -120,6 +120,7 @@ CONFIG_USB_EHCI_HCD=y CONFIG_USB_CHIPIDEA=y CONFIG_USB_CHIPIDEA_HOST=y CONFIG_USB_STORAGE=y +CONFIG_USB_PHY=y CONFIG_USB_MXS_PHY=y CONFIG_MMC=y CONFIG_MMC_MXS=y diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig index 42eab9a..7e0ebb6 100644 --- a/arch/arm/configs/omap1_defconfig +++ b/arch/arm/configs/omap1_defconfig @@ -195,6 +195,7 @@ CONFIG_SND_SOC=y CONFIG_SND_OMAP_SOC=y # CONFIG_USB_HID is not set CONFIG_USB=y +CONFIG_USB_PHY=y CONFIG_USB_DEBUG=y CONFIG_USB_DEVICEFS=y # CONFIG_USB_DEVICE_CLASS is not set diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h index cca9f15..ea289e1 100644 --- a/arch/arm/include/asm/glue-cache.h +++ b/arch/arm/include/asm/glue-cache.h @@ -19,14 +19,6 @@ #undef _CACHE #undef MULTI_CACHE -#if defined(CONFIG_CPU_CACHE_V3) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE v3 -# endif -#endif - #if defined(CONFIG_CPU_CACHE_V4) # ifdef _CACHE # define MULTI_CACHE 1 diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h index 02fe2fb..ed94b1a 100644 --- a/arch/arm/include/asm/hardware/iop3xx.h +++ b/arch/arm/include/asm/hardware/iop3xx.h @@ -37,7 +37,7 @@ extern int iop3xx_get_init_atu(void); * IOP3XX processor registers */ #define IOP3XX_PERIPHERAL_PHYS_BASE 0xffffe000 -#define IOP3XX_PERIPHERAL_VIRT_BASE 0xfeffe000 +#define IOP3XX_PERIPHERAL_VIRT_BASE 0xfedfe000 #define IOP3XX_PERIPHERAL_SIZE 0x00002000 #define IOP3XX_PERIPHERAL_UPPER_PA (IOP3XX_PERIPHERAL_PHYS_BASE +\ IOP3XX_PERIPHERAL_SIZE - 1) diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 6ef8afd..86b8fe3 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -111,7 +111,7 @@ #define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */ #define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */ #define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ -#define L_PTE_S2_RDWR (_AT(pteval_t, 2) << 6) /* HAP[2:1] */ +#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ /* * Hyp-mode PL2 PTE definitions for LPAE. diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 80d6fc4..9bcd262 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -61,6 +61,15 @@ extern void __pgd_error(const char *file, int line, pgd_t); #define FIRST_USER_ADDRESS PAGE_SIZE /* + * Use TASK_SIZE as the ceiling argument for free_pgtables() and + * free_pgd_range() to avoid freeing the modules pmd when LPAE is enabled (pmd + * page shared between user and kernel). + */ +#ifdef CONFIG_ARM_LPAE +#define USER_PGTABLES_CEILING TASK_SIZE +#endif + +/* * The pgprot_* and protection_map entries will be fixed up in runtime * to include the cachable and bufferable bits based on memory policy, * as well as any architecture dependent bits like global/ASID and SMP diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h index 5a85f14..21a23e3 100644 --- a/arch/arm/include/asm/system_misc.h +++ b/arch/arm/include/asm/system_misc.h @@ -21,9 +21,6 @@ extern void (*arm_pm_idle)(void); extern unsigned int user_debug; -extern void disable_hlt(void); -extern void enable_hlt(void); - #endif /* !__ASSEMBLY__ */ #endif /* __ASM_ARM_SYSTEM_MISC_H */ diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 9e9c041..ab865e6 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -14,7 +14,6 @@ #include <asm/glue.h> -#define TLB_V3_PAGE (1 << 0) #define TLB_V4_U_PAGE (1 << 1) #define TLB_V4_D_PAGE (1 << 2) #define TLB_V4_I_PAGE (1 << 3) @@ -22,7 +21,6 @@ #define TLB_V6_D_PAGE (1 << 5) #define TLB_V6_I_PAGE (1 << 6) -#define TLB_V3_FULL (1 << 8) #define TLB_V4_U_FULL (1 << 9) #define TLB_V4_D_FULL (1 << 10) #define TLB_V4_I_FULL (1 << 11) @@ -52,7 +50,6 @@ * ============= * * We have the following to choose from: - * v3 - ARMv3 * v4 - ARMv4 without write buffer * v4wb - ARMv4 with write buffer without I TLB flush entry instruction * v4wbi - ARMv4 with write buffer with I TLB flush entry instruction @@ -330,7 +327,6 @@ static inline void local_flush_tlb_all(void) if (tlb_flag(TLB_WB)) dsb(); - tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero); @@ -351,9 +347,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm) if (tlb_flag(TLB_WB)) dsb(); - if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { + if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) { - tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero); @@ -385,9 +380,8 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) if (tlb_flag(TLB_WB)) dsb(); - if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && + if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { - tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr); tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr); @@ -418,7 +412,6 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr) if (tlb_flag(TLB_WB)) dsb(); - tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr); tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr); diff --git a/arch/arm/kernel/early_printk.c b/arch/arm/kernel/early_printk.c index 85aa2b2..4307653 100644 --- a/arch/arm/kernel/early_printk.c +++ b/arch/arm/kernel/early_printk.c @@ -29,28 +29,17 @@ static void early_console_write(struct console *con, const char *s, unsigned n) early_write(s, n); } -static struct console early_console = { +static struct console early_console_dev = { .name = "earlycon", .write = early_console_write, .flags = CON_PRINTBUFFER | CON_BOOT, .index = -1, }; -asmlinkage void early_printk(const char *fmt, ...) -{ - char buf[512]; - int n; - va_list ap; - - va_start(ap, fmt); - n = vscnprintf(buf, sizeof(buf), fmt, ap); - early_write(buf, n); - va_end(ap); -} - static int __init setup_early_printk(char *buf) { - register_console(&early_console); + early_console = &early_console_dev; + register_console(&early_console_dev); return 0; } diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 5dc1aa6..1fd749e 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -1043,7 +1043,7 @@ static int dbg_cpu_pm_notify(struct notifier_block *self, unsigned long action, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata dbg_cpu_pm_nb = { +static struct notifier_block dbg_cpu_pm_nb = { .notifier_call = dbg_cpu_pm_notify, }; diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 146157d..8c3094d 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -253,7 +253,10 @@ validate_event(struct pmu_hw_events *hw_events, struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct pmu *leader_pmu = event->group_leader->pmu; - if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF) + if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF) + return 1; + + if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec) return 1; return armpmu->get_event_idx(hw_events, event) >= 0; diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 047d3e4..c9a5e2c 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -57,38 +57,6 @@ static const char *isa_modes[] = { "ARM" , "Thumb" , "Jazelle", "ThumbEE" }; -static volatile int hlt_counter; - -void disable_hlt(void) -{ - hlt_counter++; -} - -EXPORT_SYMBOL(disable_hlt); - -void enable_hlt(void) -{ - hlt_counter--; - BUG_ON(hlt_counter < 0); -} - -EXPORT_SYMBOL(enable_hlt); - -static int __init nohlt_setup(char *__unused) -{ - hlt_counter = 1; - return 1; -} - -static int __init hlt_setup(char *__unused) -{ - hlt_counter = 0; - return 1; -} - -__setup("nohlt", nohlt_setup); -__setup("hlt", hlt_setup); - extern void call_with_stack(void (*fn)(void *), void *arg, void *sp); typedef void (*phys_reset_t)(unsigned long); @@ -172,54 +140,38 @@ static void default_idle(void) local_irq_enable(); } -/* - * The idle thread. - * We always respect 'hlt_counter' to prevent low power idle. - */ -void cpu_idle(void) +void arch_cpu_idle_prepare(void) { local_fiq_enable(); +} - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - ledtrig_cpu(CPU_LED_IDLE_START); - while (!need_resched()) { -#ifdef CONFIG_HOTPLUG_CPU - if (cpu_is_offline(smp_processor_id())) - cpu_die(); +void arch_cpu_idle_enter(void) +{ + ledtrig_cpu(CPU_LED_IDLE_START); +#ifdef CONFIG_PL310_ERRATA_769419 + wmb(); #endif +} - /* - * We need to disable interrupts here - * to ensure we don't miss a wakeup call. - */ - local_irq_disable(); -#ifdef CONFIG_PL310_ERRATA_769419 - wmb(); +void arch_cpu_idle_exit(void) +{ + ledtrig_cpu(CPU_LED_IDLE_END); +} + +#ifdef CONFIG_HOTPLUG_CPU +void arch_cpu_idle_dead(void) +{ + cpu_die(); +} #endif - if (hlt_counter) { - local_irq_enable(); - cpu_relax(); - } else if (!need_resched()) { - stop_critical_timings(); - if (cpuidle_idle_call()) - default_idle(); - start_critical_timings(); - /* - * default_idle functions must always - * return with IRQs enabled. - */ - WARN_ON(irqs_disabled()); - } else - local_irq_enable(); - } - ledtrig_cpu(CPU_LED_IDLE_END); - rcu_idle_exit(); - tick_nohz_idle_exit(); - schedule_preempt_disabled(); - } + +/* + * Called from the core idle loop. + */ +void arch_cpu_idle(void) +{ + if (cpuidle_idle_call()) + default_idle(); } static char reboot_mode = 'h'; diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c index bd6f56b..59d2adb 100644 --- a/arch/arm/kernel/sched_clock.c +++ b/arch/arm/kernel/sched_clock.c @@ -45,12 +45,12 @@ static u32 notrace jiffy_sched_clock_read(void) static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read; -static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift) +static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) { return (cyc * mult) >> shift; } -static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask) +static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask) { u64 epoch_ns; u32 epoch_cyc; diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index d343a6c..234e339 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -56,7 +56,6 @@ #include <asm/virt.h> #include "atags.h" -#include "tcm.h" #if defined(CONFIG_FPE_NWFPE) || defined(CONFIG_FPE_FASTFPE) @@ -798,8 +797,6 @@ void __init setup_arch(char **cmdline_p) reserve_crashkernel(); - tcm_init(); - #ifdef CONFIG_MULTI_IRQ_HANDLER handle_arch_irq = mdesc->handle_irq; #endif diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 1f2cccc..4619177 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -336,7 +336,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void) /* * OK, it's off to the idle thread for us */ - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } void __init smp_cpus_done(unsigned int max_cpus) diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c index 30ae6bb..f50f19e 100644 --- a/arch/arm/kernel/tcm.c +++ b/arch/arm/kernel/tcm.c @@ -17,7 +17,6 @@ #include <asm/mach/map.h> #include <asm/memory.h> #include <asm/system_info.h> -#include "tcm.h" static struct gen_pool *tcm_pool; static bool dtcm_present; diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 5a93698..c1fe498 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -201,6 +201,7 @@ int kvm_dev_ioctl_check_extension(long ext) break; case KVM_CAP_ARM_SET_DEVICE_ADDR: r = 1; + break; case KVM_CAP_NR_VCPUS: r = num_online_cpus(); break; diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 4ea9a98..7bed755 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -79,11 +79,11 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, u32 val; int cpu; - cpu = get_cpu(); - if (!p->is_write) return read_from_write_only(vcpu, p); + cpu = get_cpu(); + cpumask_setall(&vcpu->arch.require_dcache_flush); cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush); diff --git a/arch/arm/mach-at91/at91sam9260.c b/arch/arm/mach-at91/at91sam9260.c index b67cd53..44199bc 100644 --- a/arch/arm/mach-at91/at91sam9260.c +++ b/arch/arm/mach-at91/at91sam9260.c @@ -232,6 +232,8 @@ static struct clk_lookup periph_clocks_lookups[] = { CLKDEV_CON_DEV_ID("t2_clk", "fffdc000.timer", &tc5_clk), CLKDEV_CON_DEV_ID("hclk", "500000.ohci", &ohci_clk), CLKDEV_CON_DEV_ID("mci_clk", "fffa8000.mmc", &mmc_clk), + CLKDEV_CON_DEV_ID("spi_clk", "fffc8000.spi", &spi0_clk), + CLKDEV_CON_DEV_ID("spi_clk", "fffcc000.spi", &spi1_clk), /* fake hclk clock */ CLKDEV_CON_DEV_ID("hclk", "at91_ohci", &ohci_clk), CLKDEV_CON_ID("pioA", &pioA_clk), diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c index d3addee..2ec5efe 100644 --- a/arch/arm/mach-at91/at91sam9g45.c +++ b/arch/arm/mach-at91/at91sam9g45.c @@ -262,6 +262,8 @@ static struct clk_lookup periph_clocks_lookups[] = { CLKDEV_CON_DEV_ID("mci_clk", "fffd0000.mmc", &mmc1_clk), CLKDEV_CON_DEV_ID(NULL, "fff84000.i2c", &twi0_clk), CLKDEV_CON_DEV_ID(NULL, "fff88000.i2c", &twi1_clk), + CLKDEV_CON_DEV_ID("spi_clk", "fffa4000.spi", &spi0_clk), + CLKDEV_CON_DEV_ID("spi_clk", "fffa8000.spi", &spi1_clk), /* fake hclk clock */ CLKDEV_CON_DEV_ID("hclk", "at91_ohci", &uhphs_clk), CLKDEV_CON_DEV_ID(NULL, "fffff200.gpio", &pioA_clk), diff --git a/arch/arm/mach-at91/at91sam9n12.c b/arch/arm/mach-at91/at91sam9n12.c index 5dfc8fd..ccd0783 100644 --- a/arch/arm/mach-at91/at91sam9n12.c +++ b/arch/arm/mach-at91/at91sam9n12.c @@ -172,6 +172,8 @@ static struct clk_lookup periph_clocks_lookups[] = { CLKDEV_CON_DEV_ID("dma_clk", "ffffec00.dma-controller", &dma_clk), CLKDEV_CON_DEV_ID(NULL, "f8010000.i2c", &twi0_clk), CLKDEV_CON_DEV_ID(NULL, "f8014000.i2c", &twi1_clk), + CLKDEV_CON_DEV_ID("spi_clk", "f0000000.spi", &spi0_clk), + CLKDEV_CON_DEV_ID("spi_clk", "f0004000.spi", &spi1_clk), CLKDEV_CON_DEV_ID(NULL, "fffff400.gpio", &pioAB_clk), CLKDEV_CON_DEV_ID(NULL, "fffff600.gpio", &pioAB_clk), CLKDEV_CON_DEV_ID(NULL, "fffff800.gpio", &pioCD_clk), diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c index 44a9a62..a200d8a 100644 --- a/arch/arm/mach-at91/at91sam9x5.c +++ b/arch/arm/mach-at91/at91sam9x5.c @@ -237,6 +237,8 @@ static struct clk_lookup periph_clocks_lookups[] = { CLKDEV_CON_DEV_ID(NULL, "f8010000.i2c", &twi0_clk), CLKDEV_CON_DEV_ID(NULL, "f8014000.i2c", &twi1_clk), CLKDEV_CON_DEV_ID(NULL, "f8018000.i2c", &twi2_clk), + CLKDEV_CON_DEV_ID("spi_clk", "f0000000.spi", &spi0_clk), + CLKDEV_CON_DEV_ID("spi_clk", "f0004000.spi", &spi1_clk), CLKDEV_CON_DEV_ID(NULL, "fffff400.gpio", &pioAB_clk), CLKDEV_CON_DEV_ID(NULL, "fffff600.gpio", &pioAB_clk), CLKDEV_CON_DEV_ID(NULL, "fffff800.gpio", &pioCD_clk), diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig index bf02471..f112895 100644 --- a/arch/arm/mach-bcm/Kconfig +++ b/arch/arm/mach-bcm/Kconfig @@ -6,6 +6,7 @@ config ARCH_BCM select ARM_ERRATA_764369 if SMP select ARM_GIC select CPU_V7 + select CLKSRC_OF select GENERIC_CLOCKEVENTS select GENERIC_TIME select GPIO_BCM diff --git a/arch/arm/mach-bcm/board_bcm.c b/arch/arm/mach-bcm/board_bcm.c index f0f9aba..2595935 100644 --- a/arch/arm/mach-bcm/board_bcm.c +++ b/arch/arm/mach-bcm/board_bcm.c @@ -16,14 +16,11 @@ #include <linux/device.h> #include <linux/platform_device.h> #include <linux/irqchip.h> +#include <linux/clocksource.h> #include <asm/mach/arch.h> #include <asm/mach/time.h> -static void timer_init(void) -{ -} - static void __init board_init(void) { @@ -35,7 +32,7 @@ static const char * const bcm11351_dt_compat[] = { "bcm,bcm11351", NULL, }; DT_MACHINE_START(BCM11351_DT, "Broadcom Application Processor") .init_irq = irqchip_init, - .init_time = timer_init, + .init_time = clocksource_of_init, .init_machine = board_init, .dt_compat = bcm11351_dt_compat, MACHINE_END diff --git a/arch/arm/mach-exynos/mach-universal_c210.c b/arch/arm/mach-exynos/mach-universal_c210.c index 497fcb7..d28c7fb 100644 --- a/arch/arm/mach-exynos/mach-universal_c210.c +++ b/arch/arm/mach-exynos/mach-universal_c210.c @@ -97,6 +97,19 @@ static struct s3c2410_uartcfg universal_uartcfgs[] __initdata = { static struct regulator_consumer_supply max8952_consumer = REGULATOR_SUPPLY("vdd_arm", NULL); +static struct regulator_init_data universal_max8952_reg_data = { + .constraints = { + .name = "VARM_1.2V", + .min_uV = 770000, + .max_uV = 1400000, + .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE, + .always_on = 1, + .boot_on = 1, + }, + .num_consumer_supplies = 1, + .consumer_supplies = &max8952_consumer, +}; + static struct max8952_platform_data universal_max8952_pdata __initdata = { .gpio_vid0 = EXYNOS4_GPX0(3), .gpio_vid1 = EXYNOS4_GPX0(4), @@ -105,19 +118,7 @@ static struct max8952_platform_data universal_max8952_pdata __initdata = { .dvs_mode = { 48, 32, 28, 18 }, /* 1.25, 1.20, 1.05, 0.95V */ .sync_freq = 0, /* default: fastest */ .ramp_speed = 0, /* default: fastest */ - - .reg_data = { - .constraints = { - .name = "VARM_1.2V", - .min_uV = 770000, - .max_uV = 1400000, - .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE, - .always_on = 1, - .boot_on = 1, - }, - .num_consumer_supplies = 1, - .consumer_supplies = &max8952_consumer, - }, + .reg_data = &universal_max8952_reg_data, }; static struct regulator_consumer_supply lp3974_buck1_consumer = diff --git a/arch/arm/mach-exynos/setup-usb-phy.c b/arch/arm/mach-exynos/setup-usb-phy.c index b81cc56..6af4066 100644 --- a/arch/arm/mach-exynos/setup-usb-phy.c +++ b/arch/arm/mach-exynos/setup-usb-phy.c @@ -204,9 +204,9 @@ static int exynos4210_usb_phy1_exit(struct platform_device *pdev) int s5p_usb_phy_init(struct platform_device *pdev, int type) { - if (type == S5P_USB_PHY_DEVICE) + if (type == USB_PHY_TYPE_DEVICE) return exynos4210_usb_phy0_init(pdev); - else if (type == S5P_USB_PHY_HOST) + else if (type == USB_PHY_TYPE_HOST) return exynos4210_usb_phy1_init(pdev); return -EINVAL; @@ -214,9 +214,9 @@ int s5p_usb_phy_init(struct platform_device *pdev, int type) int s5p_usb_phy_exit(struct platform_device *pdev, int type) { - if (type == S5P_USB_PHY_DEVICE) + if (type == USB_PHY_TYPE_DEVICE) return exynos4210_usb_phy0_exit(pdev); - else if (type == S5P_USB_PHY_HOST) + else if (type == USB_PHY_TYPE_HOST) return exynos4210_usb_phy1_exit(pdev); return -EINVAL; diff --git a/arch/arm/mach-gemini/idle.c b/arch/arm/mach-gemini/idle.c index 92bbd6b..87dff4f 100644 --- a/arch/arm/mach-gemini/idle.c +++ b/arch/arm/mach-gemini/idle.c @@ -13,9 +13,11 @@ static void gemini_idle(void) * will never wakeup... Acctualy it is not very good to enable * interrupts first since scheduler can miss a tick, but there is * no other way around this. Platforms that needs it for power saving - * should call enable_hlt() in init code, since by default it is + * should enable it in init code, since by default it is * disabled. */ + + /* FIXME: Enabling interrupts here is racy! */ local_irq_enable(); cpu_do_idle(); } diff --git a/arch/arm/mach-gemini/irq.c b/arch/arm/mach-gemini/irq.c index 020852d..6d8f6d1 100644 --- a/arch/arm/mach-gemini/irq.c +++ b/arch/arm/mach-gemini/irq.c @@ -15,6 +15,8 @@ #include <linux/stddef.h> #include <linux/list.h> #include <linux/sched.h> +#include <linux/cpu.h> + #include <asm/irq.h> #include <asm/mach/irq.h> #include <asm/system_misc.h> @@ -77,7 +79,7 @@ void __init gemini_init_irq(void) * Disable the idle handler by default since it is buggy * For more info see arch/arm/mach-gemini/idle.c */ - disable_hlt(); + cpu_idle_poll_ctrl(true); request_resource(&iomem_resource, &irq_resource); diff --git a/arch/arm/mach-highbank/hotplug.c b/arch/arm/mach-highbank/hotplug.c index f30c528..890cae2 100644 --- a/arch/arm/mach-highbank/hotplug.c +++ b/arch/arm/mach-highbank/hotplug.c @@ -28,13 +28,11 @@ extern void secondary_startup(void); */ void __ref highbank_cpu_die(unsigned int cpu) { - flush_cache_all(); - highbank_set_cpu_jump(cpu, phys_to_virt(0)); - highbank_set_core_pwr(); - cpu_do_idle(); + flush_cache_louis(); + highbank_set_core_pwr(); - /* We should never return from idle */ - panic("highbank: cpu %d unexpectedly exit from shutdown\n", cpu); + while (1) + cpu_do_idle(); } diff --git a/arch/arm/mach-imx/clk-busy.c b/arch/arm/mach-imx/clk-busy.c index 1ab91b5..85b728c 100644 --- a/arch/arm/mach-imx/clk-busy.c +++ b/arch/arm/mach-imx/clk-busy.c @@ -169,7 +169,7 @@ struct clk *imx_clk_busy_mux(const char *name, void __iomem *reg, u8 shift, busy->mux.reg = reg; busy->mux.shift = shift; - busy->mux.width = width; + busy->mux.mask = BIT(width) - 1; busy->mux.lock = &imx_ccm_lock; busy->mux_ops = &clk_mux_ops; diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c index 1dbeb7c..6600cff 100644 --- a/arch/arm/mach-ixp4xx/common.c +++ b/arch/arm/mach-ixp4xx/common.c @@ -29,6 +29,7 @@ #include <linux/io.h> #include <linux/export.h> #include <linux/gpio.h> +#include <linux/cpu.h> #include <mach/udc.h> #include <mach/hardware.h> @@ -239,7 +240,7 @@ void __init ixp4xx_init_irq(void) * ixp4xx does not implement the XScale PWRMODE register * so it must not call cpu_do_idle(). */ - disable_hlt(); + cpu_idle_poll_ctrl(true); /* Route all sources to IRQ instead of FIQ */ *IXP4XX_ICLR = 0x0; diff --git a/arch/arm/mach-mmp/aspenite.c b/arch/arm/mach-mmp/aspenite.c index 9f64d56..76901f4 100644 --- a/arch/arm/mach-mmp/aspenite.c +++ b/arch/arm/mach-mmp/aspenite.c @@ -223,13 +223,7 @@ static struct pxa27x_keypad_platform_data aspenite_keypad_info __initdata = { }; #if defined(CONFIG_USB_EHCI_MV) -static char *pxa168_sph_clock_name[] = { - [0] = "PXA168-USBCLK", -}; - static struct mv_usb_platform_data pxa168_sph_pdata = { - .clknum = 1, - .clkname = pxa168_sph_clock_name, .mode = MV_USB_MODE_HOST, .phy_init = pxa_usb_phy_init, .phy_deinit = pxa_usb_phy_deinit, diff --git a/arch/arm/mach-mmp/ttc_dkb.c b/arch/arm/mach-mmp/ttc_dkb.c index 22a9058..6528a5f 100644 --- a/arch/arm/mach-mmp/ttc_dkb.c +++ b/arch/arm/mach-mmp/ttc_dkb.c @@ -162,13 +162,7 @@ static struct i2c_board_info ttc_dkb_i2c_info[] = { #ifdef CONFIG_USB_SUPPORT #if defined(CONFIG_USB_MV_UDC) || defined(CONFIG_USB_EHCI_MV_U2O) -static char *pxa910_usb_clock_name[] = { - [0] = "U2OCLK", -}; - static struct mv_usb_platform_data ttc_usb_pdata = { - .clknum = 1, - .clkname = pxa910_usb_clock_name, .vbus = NULL, .mode = MV_USB_MODE_OTG, .otg_force_a_bus_req = 1, diff --git a/arch/arm/mach-omap1/pm.c b/arch/arm/mach-omap1/pm.c index 7a7690a..db37f49 100644 --- a/arch/arm/mach-omap1/pm.c +++ b/arch/arm/mach-omap1/pm.c @@ -43,6 +43,7 @@ #include <linux/module.h> #include <linux/io.h> #include <linux/atomic.h> +#include <linux/cpu.h> #include <asm/fncpy.h> #include <asm/system_misc.h> @@ -584,8 +585,7 @@ static void omap_pm_init_proc(void) static int omap_pm_prepare(void) { /* We cannot sleep in idle until we have resumed */ - disable_hlt(); - + cpu_idle_poll_ctrl(true); return 0; } @@ -621,7 +621,7 @@ static int omap_pm_enter(suspend_state_t state) static void omap_pm_finish(void) { - enable_hlt(); + cpu_idle_poll_ctrl(false); } diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index a202a47..e512253 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -138,6 +138,7 @@ #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/bootmem.h> +#include <linux/cpu.h> #include <asm/system_misc.h> @@ -2157,7 +2158,7 @@ static int _enable(struct omap_hwmod *oh) if (soc_ops.enable_module) soc_ops.enable_module(oh); if (oh->flags & HWMOD_BLOCK_WFI) - disable_hlt(); + cpu_idle_poll_ctrl(true); if (soc_ops.update_context_lost) soc_ops.update_context_lost(oh); @@ -2221,7 +2222,7 @@ static int _idle(struct omap_hwmod *oh) _del_initiator_dep(oh, mpu_oh); if (oh->flags & HWMOD_BLOCK_WFI) - enable_hlt(); + cpu_idle_poll_ctrl(false); if (soc_ops.disable_module) soc_ops.disable_module(oh); @@ -2331,7 +2332,7 @@ static int _shutdown(struct omap_hwmod *oh) _del_initiator_dep(oh, mpu_oh); /* XXX what about the other system initiators here? dma, dsp */ if (oh->flags & HWMOD_BLOCK_WFI) - enable_hlt(); + cpu_idle_poll_ctrl(false); if (soc_ops.disable_module) soc_ops.disable_module(oh); _disable_clocks(oh); diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c index 9e05765..eaba9dc 100644 --- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c @@ -2714,16 +2714,22 @@ static struct omap_ocp2scp_dev ocp2scp_dev_attr[] = { { } }; -static struct omap_hwmod_opt_clk ocp2scp_usb_phy_opt_clks[] = { - { .role = "48mhz", .clk = "ocp2scp_usb_phy_phy_48m" }, -}; - /* ocp2scp_usb_phy */ static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = { .name = "ocp2scp_usb_phy", .class = &omap44xx_ocp2scp_hwmod_class, .clkdm_name = "l3_init_clkdm", - .main_clk = "func_48m_fclk", + /* + * ocp2scp_usb_phy_phy_48m is provided by the OMAP4 PRCM IP + * block as an "optional clock," and normally should never be + * specified as the main_clk for an OMAP IP block. However it + * turns out that this clock is actually the main clock for + * the ocp2scp_usb_phy IP block: + * http://lists.infradead.org/pipermail/linux-arm-kernel/2012-September/119943.html + * So listing ocp2scp_usb_phy_phy_48m as a main_clk here seems + * to be the best workaround. + */ + .main_clk = "ocp2scp_usb_phy_phy_48m", .prcm = { .omap4 = { .clkctrl_offs = OMAP4_CM_L3INIT_USBPHYOCP2SCP_CLKCTRL_OFFSET, @@ -2732,8 +2738,6 @@ static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = { }, }, .dev_attr = ocp2scp_dev_attr, - .opt_clks = ocp2scp_usb_phy_opt_clks, - .opt_clks_cnt = ARRAY_SIZE(ocp2scp_usb_phy_opt_clks), }; /* diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c index 673a4c1..dec5533 100644 --- a/arch/arm/mach-omap2/pm.c +++ b/arch/arm/mach-omap2/pm.c @@ -218,7 +218,7 @@ static int omap_pm_enter(suspend_state_t suspend_state) static int omap_pm_begin(suspend_state_t state) { - disable_hlt(); + cpu_idle_poll_ctrl(true); if (cpu_is_omap34xx()) omap_prcm_irq_prepare(); return 0; @@ -226,8 +226,7 @@ static int omap_pm_begin(suspend_state_t state) static void omap_pm_end(void) { - enable_hlt(); - return; + cpu_idle_poll_ctrl(false); } static void omap_pm_finish(void) diff --git a/arch/arm/mach-orion5x/board-dt.c b/arch/arm/mach-orion5x/board-dt.c index 35a8014..94fbb81 100644 --- a/arch/arm/mach-orion5x/board-dt.c +++ b/arch/arm/mach-orion5x/board-dt.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/of.h> #include <linux/of_platform.h> +#include <linux/cpu.h> #include <asm/system_misc.h> #include <asm/mach/arch.h> #include <mach/orion5x.h> @@ -52,7 +53,7 @@ static void __init orion5x_dt_init(void) */ if (dev == MV88F5281_DEV_ID && rev == MV88F5281_REV_D0) { printk(KERN_INFO "Orion: Applying 5281 D0 WFI workaround.\n"); - disable_hlt(); + cpu_idle_poll_ctrl(true); } if (of_machine_is_compatible("lacie,ethernet-disk-mini-v2")) diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c index d068f14..ad71c8a 100644 --- a/arch/arm/mach-orion5x/common.c +++ b/arch/arm/mach-orion5x/common.c @@ -293,7 +293,7 @@ void __init orion5x_init(void) */ if (dev == MV88F5281_DEV_ID && rev == MV88F5281_REV_D0) { printk(KERN_INFO "Orion: Applying 5281 D0 WFI workaround.\n"); - disable_hlt(); + cpu_idle_poll_ctrl(true); } /* diff --git a/arch/arm/mach-s3c24xx/clock-s3c2440.c b/arch/arm/mach-s3c24xx/clock-s3c2440.c index 04b87ec..1069b56 100644 --- a/arch/arm/mach-s3c24xx/clock-s3c2440.c +++ b/arch/arm/mach-s3c24xx/clock-s3c2440.c @@ -123,6 +123,11 @@ static struct clk s3c2440_clk_ac97 = { .ctrlbit = S3C2440_CLKCON_AC97, }; +#define S3C24XX_VA_UART0 (S3C_VA_UART) +#define S3C24XX_VA_UART1 (S3C_VA_UART + 0x4000 ) +#define S3C24XX_VA_UART2 (S3C_VA_UART + 0x8000 ) +#define S3C24XX_VA_UART3 (S3C_VA_UART + 0xC000 ) + static unsigned long s3c2440_fclk_n_getrate(struct clk *clk) { unsigned long ucon0, ucon1, ucon2, divisor; diff --git a/arch/arm/mach-s3c24xx/common.c b/arch/arm/mach-s3c24xx/common.c index 6bcf87f..92e6094 100644 --- a/arch/arm/mach-s3c24xx/common.c +++ b/arch/arm/mach-s3c24xx/common.c @@ -239,6 +239,11 @@ void __init s3c24xx_init_io(struct map_desc *mach_desc, int size) /* Serial port registrations */ +#define S3C2410_PA_UART0 (S3C24XX_PA_UART) +#define S3C2410_PA_UART1 (S3C24XX_PA_UART + 0x4000 ) +#define S3C2410_PA_UART2 (S3C24XX_PA_UART + 0x8000 ) +#define S3C2443_PA_UART3 (S3C24XX_PA_UART + 0xC000 ) + static struct resource s3c2410_uart0_resource[] = { [0] = DEFINE_RES_MEM(S3C2410_PA_UART0, SZ_16K), [1] = DEFINE_RES_NAMED(IRQ_S3CUART_RX0, \ diff --git a/arch/arm/mach-s3c64xx/setup-usb-phy.c b/arch/arm/mach-s3c64xx/setup-usb-phy.c index c8174d9..ca960bd 100644 --- a/arch/arm/mach-s3c64xx/setup-usb-phy.c +++ b/arch/arm/mach-s3c64xx/setup-usb-phy.c @@ -76,7 +76,7 @@ static int s3c_usb_otgphy_exit(struct platform_device *pdev) int s5p_usb_phy_init(struct platform_device *pdev, int type) { - if (type == S5P_USB_PHY_DEVICE) + if (type == USB_PHY_TYPE_DEVICE) return s3c_usb_otgphy_init(pdev); return -EINVAL; @@ -84,7 +84,7 @@ int s5p_usb_phy_init(struct platform_device *pdev, int type) int s5p_usb_phy_exit(struct platform_device *pdev, int type) { - if (type == S5P_USB_PHY_DEVICE) + if (type == USB_PHY_TYPE_DEVICE) return s3c_usb_otgphy_exit(pdev); return -EINVAL; diff --git a/arch/arm/mach-s5pv210/setup-usb-phy.c b/arch/arm/mach-s5pv210/setup-usb-phy.c index 356a090..b2ee533 100644 --- a/arch/arm/mach-s5pv210/setup-usb-phy.c +++ b/arch/arm/mach-s5pv210/setup-usb-phy.c @@ -80,7 +80,7 @@ static int s5pv210_usb_otgphy_exit(struct platform_device *pdev) int s5p_usb_phy_init(struct platform_device *pdev, int type) { - if (type == S5P_USB_PHY_DEVICE) + if (type == USB_PHY_TYPE_DEVICE) return s5pv210_usb_otgphy_init(pdev); return -EINVAL; @@ -88,7 +88,7 @@ int s5p_usb_phy_init(struct platform_device *pdev, int type) int s5p_usb_phy_exit(struct platform_device *pdev, int type) { - if (type == S5P_USB_PHY_DEVICE) + if (type == USB_PHY_TYPE_DEVICE) return s5pv210_usb_otgphy_exit(pdev); return -EINVAL; diff --git a/arch/arm/mach-shark/core.c b/arch/arm/mach-shark/core.c index b63dec8..1535557 100644 --- a/arch/arm/mach-shark/core.c +++ b/arch/arm/mach-shark/core.c @@ -10,6 +10,7 @@ #include <linux/sched.h> #include <linux/serial_8250.h> #include <linux/io.h> +#include <linux/cpu.h> #include <asm/setup.h> #include <asm/mach-types.h> @@ -130,7 +131,7 @@ static void __init shark_timer_init(void) static void shark_init_early(void) { - disable_hlt(); + cpu_idle_poll_ctrl(true); } MACHINE_START(SHARK, "Shark") diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c index f2ec077..ff8b7ba 100644 --- a/arch/arm/mach-shmobile/board-armadillo800eva.c +++ b/arch/arm/mach-shmobile/board-armadillo800eva.c @@ -169,7 +169,7 @@ static int usbhsf_get_id(struct platform_device *pdev) return USBHS_GADGET; } -static void usbhsf_power_ctrl(struct platform_device *pdev, +static int usbhsf_power_ctrl(struct platform_device *pdev, void __iomem *base, int enable) { struct usbhsf_private *priv = usbhsf_get_priv(pdev); @@ -223,6 +223,8 @@ static void usbhsf_power_ctrl(struct platform_device *pdev, clk_disable(priv->pci); /* usb work around */ clk_disable(priv->usb24); /* usb work around */ } + + return 0; } static int usbhsf_get_vbus(struct platform_device *pdev) @@ -239,7 +241,7 @@ static irqreturn_t usbhsf_interrupt(int irq, void *data) return IRQ_HANDLED; } -static void usbhsf_hardware_exit(struct platform_device *pdev) +static int usbhsf_hardware_exit(struct platform_device *pdev) { struct usbhsf_private *priv = usbhsf_get_priv(pdev); @@ -264,6 +266,8 @@ static void usbhsf_hardware_exit(struct platform_device *pdev) priv->usbh_base = NULL; free_irq(IRQ7, pdev); + + return 0; } static int usbhsf_hardware_init(struct platform_device *pdev) diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c index 7f3a6b7..a385f57 100644 --- a/arch/arm/mach-shmobile/board-kzm9g.c +++ b/arch/arm/mach-shmobile/board-kzm9g.c @@ -155,12 +155,14 @@ static int usbhs_get_vbus(struct platform_device *pdev) return !((1 << 7) & __raw_readw(priv->cr2)); } -static void usbhs_phy_reset(struct platform_device *pdev) +static int usbhs_phy_reset(struct platform_device *pdev) { struct usbhs_private *priv = usbhs_get_priv(pdev); /* init phy */ __raw_writew(0x8a0a, priv->cr2); + + return 0; } static int usbhs_get_id(struct platform_device *pdev) @@ -202,7 +204,7 @@ static int usbhs_hardware_init(struct platform_device *pdev) return 0; } -static void usbhs_hardware_exit(struct platform_device *pdev) +static int usbhs_hardware_exit(struct platform_device *pdev) { struct usbhs_private *priv = usbhs_get_priv(pdev); @@ -210,6 +212,8 @@ static void usbhs_hardware_exit(struct platform_device *pdev) __raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->phy); free_irq(IRQ15, pdev); + + return 0; } static u32 usbhs_pipe_cfg[] = { diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c index db968a5..979237c 100644 --- a/arch/arm/mach-shmobile/board-mackerel.c +++ b/arch/arm/mach-shmobile/board-mackerel.c @@ -596,12 +596,14 @@ static int usbhs_get_vbus(struct platform_device *pdev) return usbhs_is_connected(usbhs_get_priv(pdev)); } -static void usbhs_phy_reset(struct platform_device *pdev) +static int usbhs_phy_reset(struct platform_device *pdev) { struct usbhs_private *priv = usbhs_get_priv(pdev); /* init phy */ __raw_writew(0x8a0a, priv->usbcrcaddr); + + return 0; } static int usbhs0_get_id(struct platform_device *pdev) @@ -628,11 +630,13 @@ static int usbhs0_hardware_init(struct platform_device *pdev) return 0; } -static void usbhs0_hardware_exit(struct platform_device *pdev) +static int usbhs0_hardware_exit(struct platform_device *pdev) { struct usbhs_private *priv = usbhs_get_priv(pdev); cancel_delayed_work_sync(&priv->work); + + return 0; } static struct usbhs_private usbhs0_private = { @@ -735,7 +739,7 @@ static int usbhs1_hardware_init(struct platform_device *pdev) return 0; } -static void usbhs1_hardware_exit(struct platform_device *pdev) +static int usbhs1_hardware_exit(struct platform_device *pdev) { struct usbhs_private *priv = usbhs_get_priv(pdev); @@ -743,6 +747,8 @@ static void usbhs1_hardware_exit(struct platform_device *pdev) __raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->usbphyaddr); free_irq(IRQ8, pdev); + + return 0; } static int usbhs1_get_id(struct platform_device *pdev) diff --git a/arch/arm/mach-shmobile/suspend.c b/arch/arm/mach-shmobile/suspend.c index 47d83f7..5d92b5d 100644 --- a/arch/arm/mach-shmobile/suspend.c +++ b/arch/arm/mach-shmobile/suspend.c @@ -12,6 +12,8 @@ #include <linux/suspend.h> #include <linux/module.h> #include <linux/err.h> +#include <linux/cpu.h> + #include <asm/io.h> #include <asm/system_misc.h> @@ -23,13 +25,13 @@ static int shmobile_suspend_default_enter(suspend_state_t suspend_state) static int shmobile_suspend_begin(suspend_state_t state) { - disable_hlt(); + cpu_idle_poll_ctrl(true); return 0; } static void shmobile_suspend_end(void) { - enable_hlt(); + cpu_idle_poll_ctrl(false); } struct platform_suspend_ops shmobile_suspend_ops = { diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig index d1c4893..dbc653e 100644 --- a/arch/arm/mach-tegra/Kconfig +++ b/arch/arm/mach-tegra/Kconfig @@ -18,8 +18,8 @@ config ARCH_TEGRA_2x_SOC select PL310_ERRATA_727915 if CACHE_L2X0 select PL310_ERRATA_769419 if CACHE_L2X0 select USB_ARCH_HAS_EHCI if USB_SUPPORT - select USB_ULPI if USB - select USB_ULPI_VIEWPORT if USB_SUPPORT + select USB_ULPI if USB_PHY + select USB_ULPI_VIEWPORT if USB_PHY help Support for NVIDIA Tegra AP20 and T20 processors, based on the ARM CortexA9MP CPU and the ARM PL310 L2 cache controller @@ -37,8 +37,8 @@ config ARCH_TEGRA_3x_SOC select PINCTRL_TEGRA30 select PL310_ERRATA_769419 if CACHE_L2X0 select USB_ARCH_HAS_EHCI if USB_SUPPORT - select USB_ULPI if USB - select USB_ULPI_VIEWPORT if USB_SUPPORT + select USB_ULPI if USB_PHY + select USB_ULPI_VIEWPORT if USB_PHY help Support for NVIDIA Tegra T30 processor family, based on the ARM CortexA9MP CPU and the ARM PL310 L2 cache controller diff --git a/arch/arm/mach-ux500/board-mop500-regulators.c b/arch/arm/mach-ux500/board-mop500-regulators.c index 2a17bc5..ff3c9f0 100644 --- a/arch/arm/mach-ux500/board-mop500-regulators.c +++ b/arch/arm/mach-ux500/board-mop500-regulators.c @@ -5,6 +5,7 @@ * * Authors: Sundar Iyer <sundar.iyer@stericsson.com> * Bengt Jonsson <bengt.g.jonsson@stericsson.com> + * Daniel Willerud <daniel.willerud@stericsson.com> * * MOP500 board specific initialization for regulators */ @@ -12,6 +13,7 @@ #include <linux/regulator/machine.h> #include <linux/regulator/ab8500.h> #include "board-mop500-regulators.h" +#include "id.h" static struct regulator_consumer_supply gpio_en_3v3_consumers[] = { REGULATOR_SUPPLY("vdd33a", "smsc911x.0"), @@ -53,21 +55,37 @@ struct regulator_init_data tps61052_regulator = { }; static struct regulator_consumer_supply ab8500_vaux1_consumers[] = { - /* External displays, connector on board 2v5 power supply */ - REGULATOR_SUPPLY("vaux12v5", "mcde.0"), + /* Main display, u8500 R3 uib */ + REGULATOR_SUPPLY("vddi", "mcde_disp_sony_acx424akp.0"), + /* Main display, u8500 uib and ST uib */ + REGULATOR_SUPPLY("vdd1", "samsung_s6d16d0.0"), + /* Secondary display, ST uib */ + REGULATOR_SUPPLY("vdd1", "samsung_s6d16d0.1"), /* SFH7741 proximity sensor */ REGULATOR_SUPPLY("vcc", "gpio-keys.0"), /* BH1780GLS ambient light sensor */ REGULATOR_SUPPLY("vcc", "2-0029"), /* lsm303dlh accelerometer */ - REGULATOR_SUPPLY("vdd", "3-0018"), + REGULATOR_SUPPLY("vdd", "2-0018"), + /* lsm303dlhc accelerometer */ + REGULATOR_SUPPLY("vdd", "2-0019"), /* lsm303dlh magnetometer */ - REGULATOR_SUPPLY("vdd", "3-001e"), + REGULATOR_SUPPLY("vdd", "2-001e"), /* Rohm BU21013 Touchscreen devices */ REGULATOR_SUPPLY("avdd", "3-005c"), REGULATOR_SUPPLY("avdd", "3-005d"), /* Synaptics RMI4 Touchscreen device */ REGULATOR_SUPPLY("vdd", "3-004b"), + /* L3G4200D Gyroscope device */ + REGULATOR_SUPPLY("vdd", "2-0068"), + /* Ambient light sensor device */ + REGULATOR_SUPPLY("vdd", "3-0029"), + /* Pressure sensor device */ + REGULATOR_SUPPLY("vdd", "2-005c"), + /* Cypress TrueTouch Touchscreen device */ + REGULATOR_SUPPLY("vcpin", "spi8.0"), + /* Camera device */ + REGULATOR_SUPPLY("vaux12v5", "mmio_camera"), }; static struct regulator_consumer_supply ab8500_vaux2_consumers[] = { @@ -75,18 +93,50 @@ static struct regulator_consumer_supply ab8500_vaux2_consumers[] = { REGULATOR_SUPPLY("vmmc", "sdi4"), /* AB8500 audio codec */ REGULATOR_SUPPLY("vcc-N2158", "ab8500-codec.0"), + /* AB8500 accessory detect 1 */ + REGULATOR_SUPPLY("vcc-N2158", "ab8500-acc-det.0"), + /* AB8500 Tv-out device */ + REGULATOR_SUPPLY("vcc-N2158", "mcde_tv_ab8500.4"), + /* AV8100 HDMI device */ + REGULATOR_SUPPLY("vcc-N2158", "av8100_hdmi.3"), }; static struct regulator_consumer_supply ab8500_vaux3_consumers[] = { + REGULATOR_SUPPLY("v-SD-STM", "stm"), /* External MMC slot power */ REGULATOR_SUPPLY("vmmc", "sdi0"), }; +static struct regulator_consumer_supply ab8505_vaux4_consumers[] = { +}; + +static struct regulator_consumer_supply ab8505_vaux5_consumers[] = { +}; + +static struct regulator_consumer_supply ab8505_vaux6_consumers[] = { +}; + +static struct regulator_consumer_supply ab8505_vaux8_consumers[] = { + /* AB8500 audio codec device */ + REGULATOR_SUPPLY("v-aux8", NULL), +}; + +static struct regulator_consumer_supply ab8505_vadc_consumers[] = { + /* Internal general-purpose ADC */ + REGULATOR_SUPPLY("vddadc", "ab8500-gpadc.0"), + /* ADC for charger */ + REGULATOR_SUPPLY("vddadc", "ab8500-charger.0"), +}; + static struct regulator_consumer_supply ab8500_vtvout_consumers[] = { /* TV-out DENC supply */ REGULATOR_SUPPLY("vtvout", "ab8500-denc.0"), /* Internal general-purpose ADC */ REGULATOR_SUPPLY("vddadc", "ab8500-gpadc.0"), + /* ADC for charger */ + REGULATOR_SUPPLY("vddadc", "ab8500-charger.0"), + /* AB8500 Tv-out device */ + REGULATOR_SUPPLY("vtvout", "mcde_tv_ab8500.4"), }; static struct regulator_consumer_supply ab8500_vaud_consumers[] = { @@ -114,77 +164,90 @@ static struct regulator_consumer_supply ab8500_vintcore_consumers[] = { REGULATOR_SUPPLY("v-intcore", NULL), /* USB Transceiver */ REGULATOR_SUPPLY("vddulpivio18", "ab8500-usb.0"), + /* Handled by abx500 clk driver */ + REGULATOR_SUPPLY("v-intcore", "abx500-clk.0"), +}; + +static struct regulator_consumer_supply ab8505_usb_consumers[] = { + /* HS USB OTG physical interface */ + REGULATOR_SUPPLY("v-ape", NULL), }; static struct regulator_consumer_supply ab8500_vana_consumers[] = { - /* External displays, connector on board, 1v8 power supply */ - REGULATOR_SUPPLY("vsmps2", "mcde.0"), + /* DB8500 DSI */ + REGULATOR_SUPPLY("vdddsi1v2", "mcde"), + REGULATOR_SUPPLY("vdddsi1v2", "b2r2_core"), + REGULATOR_SUPPLY("vdddsi1v2", "b2r2_1_core"), + REGULATOR_SUPPLY("vdddsi1v2", "dsilink.0"), + REGULATOR_SUPPLY("vdddsi1v2", "dsilink.1"), + REGULATOR_SUPPLY("vdddsi1v2", "dsilink.2"), + /* DB8500 CSI */ + REGULATOR_SUPPLY("vddcsi1v2", "mmio_camera"), }; /* ab8500 regulator register initialization */ -struct ab8500_regulator_reg_init -ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS] = { +static struct ab8500_regulator_reg_init ab8500_reg_init[] = { /* * VanaRequestCtrl = HP/LP depending on VxRequest * VextSupply1RequestCtrl = HP/LP depending on VxRequest */ - INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL2, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL2, 0xf0, 0x00), /* * VextSupply2RequestCtrl = HP/LP depending on VxRequest * VextSupply3RequestCtrl = HP/LP depending on VxRequest * Vaux1RequestCtrl = HP/LP depending on VxRequest * Vaux2RequestCtrl = HP/LP depending on VxRequest */ - INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL3, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL3, 0xff, 0x00), /* * Vaux3RequestCtrl = HP/LP depending on VxRequest * SwHPReq = Control through SWValid disabled */ - INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL4, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL4, 0x07, 0x00), /* * VanaSysClkReq1HPValid = disabled * Vaux1SysClkReq1HPValid = disabled * Vaux2SysClkReq1HPValid = disabled * Vaux3SysClkReq1HPValid = disabled */ - INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID1, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID1, 0xe8, 0x00), /* * VextSupply1SysClkReq1HPValid = disabled * VextSupply2SysClkReq1HPValid = disabled * VextSupply3SysClkReq1HPValid = SysClkReq1 controlled */ - INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID2, 0x40), + INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID2, 0x70, 0x40), /* * VanaHwHPReq1Valid = disabled * Vaux1HwHPreq1Valid = disabled * Vaux2HwHPReq1Valid = disabled * Vaux3HwHPReqValid = disabled */ - INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID1, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID1, 0xe8, 0x00), /* * VextSupply1HwHPReq1Valid = disabled * VextSupply2HwHPReq1Valid = disabled * VextSupply3HwHPReq1Valid = disabled */ - INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID2, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID2, 0x07, 0x00), /* * VanaHwHPReq2Valid = disabled * Vaux1HwHPReq2Valid = disabled * Vaux2HwHPReq2Valid = disabled * Vaux3HwHPReq2Valid = disabled */ - INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID1, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID1, 0xe8, 0x00), /* * VextSupply1HwHPReq2Valid = disabled * VextSupply2HwHPReq2Valid = disabled * VextSupply3HwHPReq2Valid = HWReq2 controlled */ - INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID2, 0x04), + INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID2, 0x07, 0x04), /* * VanaSwHPReqValid = disabled * Vaux1SwHPReqValid = disabled */ - INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID1, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID1, 0xa0, 0x00), /* * Vaux2SwHPReqValid = disabled * Vaux3SwHPReqValid = disabled @@ -192,7 +255,7 @@ ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS] = { * VextSupply2SwHPReqValid = disabled * VextSupply3SwHPReqValid = disabled */ - INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID2, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID2, 0x1f, 0x00), /* * SysClkReq2Valid1 = SysClkReq2 controlled * SysClkReq3Valid1 = disabled @@ -202,7 +265,7 @@ ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS] = { * SysClkReq7Valid1 = disabled * SysClkReq8Valid1 = disabled */ - INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID1, 0x2a), + INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID1, 0xfe, 0x2a), /* * SysClkReq2Valid2 = disabled * SysClkReq3Valid2 = disabled @@ -212,7 +275,7 @@ ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS] = { * SysClkReq7Valid2 = disabled * SysClkReq8Valid2 = disabled */ - INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID2, 0x20), + INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID2, 0xfe, 0x20), /* * VTVoutEna = disabled * Vintcore12Ena = disabled @@ -220,66 +283,62 @@ ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS] = { * Vintcore12LP = inactive (HP) * VTVoutLP = inactive (HP) */ - INIT_REGULATOR_REGISTER(AB8500_REGUMISC1, 0x10), + INIT_REGULATOR_REGISTER(AB8500_REGUMISC1, 0xfe, 0x10), /* * VaudioEna = disabled * VdmicEna = disabled * Vamic1Ena = disabled * Vamic2Ena = disabled */ - INIT_REGULATOR_REGISTER(AB8500_VAUDIOSUPPLY, 0x00), + INIT_REGULATOR_REGISTER(AB8500_VAUDIOSUPPLY, 0x1e, 0x00), /* * Vamic1_dzout = high-Z when Vamic1 is disabled * Vamic2_dzout = high-Z when Vamic2 is disabled */ - INIT_REGULATOR_REGISTER(AB8500_REGUCTRL1VAMIC, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUCTRL1VAMIC, 0x03, 0x00), /* - * VPll = Hw controlled + * VPll = Hw controlled (NOTE! PRCMU bits) * VanaRegu = force off */ - INIT_REGULATOR_REGISTER(AB8500_VPLLVANAREGU, 0x02), + INIT_REGULATOR_REGISTER(AB8500_VPLLVANAREGU, 0x0f, 0x02), /* * VrefDDREna = disabled * VrefDDRSleepMode = inactive (no pulldown) */ - INIT_REGULATOR_REGISTER(AB8500_VREFDDR, 0x00), + INIT_REGULATOR_REGISTER(AB8500_VREFDDR, 0x03, 0x00), /* - * VextSupply1Regu = HW control - * VextSupply2Regu = HW control - * VextSupply3Regu = HW control + * VextSupply1Regu = force LP + * VextSupply2Regu = force OFF + * VextSupply3Regu = force HP (-> STBB2=LP and TPS=LP) * ExtSupply2Bypass = ExtSupply12LPn ball is 0 when Ena is 0 * ExtSupply3Bypass = ExtSupply3LPn ball is 0 when Ena is 0 */ - INIT_REGULATOR_REGISTER(AB8500_EXTSUPPLYREGU, 0x2a), + INIT_REGULATOR_REGISTER(AB8500_EXTSUPPLYREGU, 0xff, 0x13), /* * Vaux1Regu = force HP * Vaux2Regu = force off */ - INIT_REGULATOR_REGISTER(AB8500_VAUX12REGU, 0x01), + INIT_REGULATOR_REGISTER(AB8500_VAUX12REGU, 0x0f, 0x01), /* - * Vaux3regu = force off + * Vaux3Regu = force off */ - INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3REGU, 0x00), + INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3REGU, 0x03, 0x00), /* - * Vsmps1 = 1.15V + * Vaux1Sel = 2.8 V */ - INIT_REGULATOR_REGISTER(AB8500_VSMPS1SEL1, 0x24), - /* - * Vaux1Sel = 2.5 V - */ - INIT_REGULATOR_REGISTER(AB8500_VAUX1SEL, 0x08), + INIT_REGULATOR_REGISTER(AB8500_VAUX1SEL, 0x0f, 0x0C), /* * Vaux2Sel = 2.9 V */ - INIT_REGULATOR_REGISTER(AB8500_VAUX2SEL, 0x0d), + INIT_REGULATOR_REGISTER(AB8500_VAUX2SEL, 0x0f, 0x0d), /* * Vaux3Sel = 2.91 V */ - INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3SEL, 0x07), + INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3SEL, 0x07, 0x07), /* * VextSupply12LP = disabled (no LP) */ - INIT_REGULATOR_REGISTER(AB8500_REGUCTRL2SPARE, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUCTRL2SPARE, 0x01, 0x00), /* * Vaux1Disch = short discharge time * Vaux2Disch = short discharge time @@ -288,33 +347,26 @@ ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS] = { * VTVoutDisch = short discharge time * VaudioDisch = short discharge time */ - INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH, 0xfc, 0x00), /* * VanaDisch = short discharge time * VdmicPullDownEna = pulldown disabled when Vdmic is disabled * VdmicDisch = short discharge time */ - INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH2, 0x00), + INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH2, 0x16, 0x00), }; /* AB8500 regulators */ -struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = { +static struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = { /* supplies to the display/camera */ [AB8500_LDO_AUX1] = { .constraints = { .name = "V-DISPLAY", - .min_uV = 2500000, - .max_uV = 2900000, + .min_uV = 2800000, + .max_uV = 3300000, .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | REGULATOR_CHANGE_STATUS, .boot_on = 1, /* display is on at boot */ - /* - * This voltage cannot be disabled right now because - * it is somehow affecting the external MMC - * functionality, though that typically will use - * AUX3. - */ - .always_on = 1, }, .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux1_consumers), .consumer_supplies = ab8500_vaux1_consumers, @@ -326,7 +378,10 @@ struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = { .min_uV = 1100000, .max_uV = 3300000, .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | - REGULATOR_CHANGE_STATUS, + REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_MODE, + .valid_modes_mask = REGULATOR_MODE_NORMAL | + REGULATOR_MODE_IDLE, }, .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux2_consumers), .consumer_supplies = ab8500_vaux2_consumers, @@ -338,7 +393,10 @@ struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = { .min_uV = 1100000, .max_uV = 3300000, .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | - REGULATOR_CHANGE_STATUS, + REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_MODE, + .valid_modes_mask = REGULATOR_MODE_NORMAL | + REGULATOR_MODE_IDLE, }, .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux3_consumers), .consumer_supplies = ab8500_vaux3_consumers, @@ -392,18 +450,614 @@ struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = { [AB8500_LDO_INTCORE] = { .constraints = { .name = "V-INTCORE", - .valid_ops_mask = REGULATOR_CHANGE_STATUS, + .min_uV = 1250000, + .max_uV = 1350000, + .input_uV = 1800000, + .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | + REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_MODE | + REGULATOR_CHANGE_DRMS, + .valid_modes_mask = REGULATOR_MODE_NORMAL | + REGULATOR_MODE_IDLE, }, .num_consumer_supplies = ARRAY_SIZE(ab8500_vintcore_consumers), .consumer_supplies = ab8500_vintcore_consumers, }, - /* supply for U8500 CSI/DSI, VANA LDO */ + /* supply for U8500 CSI-DSI, VANA LDO */ [AB8500_LDO_ANA] = { .constraints = { - .name = "V-CSI/DSI", + .name = "V-CSI-DSI", .valid_ops_mask = REGULATOR_CHANGE_STATUS, }, .num_consumer_supplies = ARRAY_SIZE(ab8500_vana_consumers), .consumer_supplies = ab8500_vana_consumers, }, }; + +/* supply for VextSupply3 */ +static struct regulator_consumer_supply ab8500_ext_supply3_consumers[] = { + /* SIM supply for 3 V SIM cards */ + REGULATOR_SUPPLY("vinvsim", "sim-detect.0"), +}; + +/* extended configuration for VextSupply2, only used for HREFP_V20 boards */ +static struct ab8500_ext_regulator_cfg ab8500_ext_supply2 = { + .hwreq = true, +}; + +/* + * AB8500 external regulators + */ +static struct regulator_init_data ab8500_ext_regulators[] = { + /* fixed Vbat supplies VSMPS1_EXT_1V8 */ + [AB8500_EXT_SUPPLY1] = { + .constraints = { + .name = "ab8500-ext-supply1", + .min_uV = 1800000, + .max_uV = 1800000, + .initial_mode = REGULATOR_MODE_IDLE, + .boot_on = 1, + .always_on = 1, + }, + }, + /* fixed Vbat supplies VSMPS2_EXT_1V36 and VSMPS5_EXT_1V15 */ + [AB8500_EXT_SUPPLY2] = { + .constraints = { + .name = "ab8500-ext-supply2", + .min_uV = 1360000, + .max_uV = 1360000, + }, + }, + /* fixed Vbat supplies VSMPS3_EXT_3V4 and VSMPS4_EXT_3V4 */ + [AB8500_EXT_SUPPLY3] = { + .constraints = { + .name = "ab8500-ext-supply3", + .min_uV = 3400000, + .max_uV = 3400000, + .valid_ops_mask = REGULATOR_CHANGE_STATUS, + .boot_on = 1, + }, + .num_consumer_supplies = + ARRAY_SIZE(ab8500_ext_supply3_consumers), + .consumer_supplies = ab8500_ext_supply3_consumers, + }, +}; + +/* ab8505 regulator register initialization */ +static struct ab8500_regulator_reg_init ab8505_reg_init[] = { + /* + * VarmRequestCtrl + * VsmpsCRequestCtrl + * VsmpsARequestCtrl + * VsmpsBRequestCtrl + */ + INIT_REGULATOR_REGISTER(AB8505_REGUREQUESTCTRL1, 0x00, 0x00), + /* + * VsafeRequestCtrl + * VpllRequestCtrl + * VanaRequestCtrl = HP/LP depending on VxRequest + */ + INIT_REGULATOR_REGISTER(AB8505_REGUREQUESTCTRL2, 0x30, 0x00), + /* + * Vaux1RequestCtrl = HP/LP depending on VxRequest + * Vaux2RequestCtrl = HP/LP depending on VxRequest + */ + INIT_REGULATOR_REGISTER(AB8505_REGUREQUESTCTRL3, 0xf0, 0x00), + /* + * Vaux3RequestCtrl = HP/LP depending on VxRequest + * SwHPReq = Control through SWValid disabled + */ + INIT_REGULATOR_REGISTER(AB8505_REGUREQUESTCTRL4, 0x07, 0x00), + /* + * VsmpsASysClkReq1HPValid + * VsmpsBSysClkReq1HPValid + * VsafeSysClkReq1HPValid + * VanaSysClkReq1HPValid = disabled + * VpllSysClkReq1HPValid + * Vaux1SysClkReq1HPValid = disabled + * Vaux2SysClkReq1HPValid = disabled + * Vaux3SysClkReq1HPValid = disabled + */ + INIT_REGULATOR_REGISTER(AB8505_REGUSYSCLKREQ1HPVALID1, 0xe8, 0x00), + /* + * VsmpsCSysClkReq1HPValid + * VarmSysClkReq1HPValid + * VbbSysClkReq1HPValid + * VsmpsMSysClkReq1HPValid + */ + INIT_REGULATOR_REGISTER(AB8505_REGUSYSCLKREQ1HPVALID2, 0x00, 0x00), + /* + * VsmpsAHwHPReq1Valid + * VsmpsBHwHPReq1Valid + * VsafeHwHPReq1Valid + * VanaHwHPReq1Valid = disabled + * VpllHwHPReq1Valid + * Vaux1HwHPreq1Valid = disabled + * Vaux2HwHPReq1Valid = disabled + * Vaux3HwHPReqValid = disabled + */ + INIT_REGULATOR_REGISTER(AB8505_REGUHWHPREQ1VALID1, 0xe8, 0x00), + /* + * VsmpsMHwHPReq1Valid + */ + INIT_REGULATOR_REGISTER(AB8505_REGUHWHPREQ1VALID2, 0x00, 0x00), + /* + * VsmpsAHwHPReq2Valid + * VsmpsBHwHPReq2Valid + * VsafeHwHPReq2Valid + * VanaHwHPReq2Valid = disabled + * VpllHwHPReq2Valid + * Vaux1HwHPReq2Valid = disabled + * Vaux2HwHPReq2Valid = disabled + * Vaux3HwHPReq2Valid = disabled + */ + INIT_REGULATOR_REGISTER(AB8505_REGUHWHPREQ2VALID1, 0xe8, 0x00), + /* + * VsmpsMHwHPReq2Valid + */ + INIT_REGULATOR_REGISTER(AB8505_REGUHWHPREQ2VALID2, 0x00, 0x00), + /** + * VsmpsCSwHPReqValid + * VarmSwHPReqValid + * VsmpsASwHPReqValid + * VsmpsBSwHPReqValid + * VsafeSwHPReqValid + * VanaSwHPReqValid + * VanaSwHPReqValid = disabled + * VpllSwHPReqValid + * Vaux1SwHPReqValid = disabled + */ + INIT_REGULATOR_REGISTER(AB8505_REGUSWHPREQVALID1, 0xa0, 0x00), + /* + * Vaux2SwHPReqValid = disabled + * Vaux3SwHPReqValid = disabled + * VsmpsMSwHPReqValid + */ + INIT_REGULATOR_REGISTER(AB8505_REGUSWHPREQVALID2, 0x03, 0x00), + /* + * SysClkReq2Valid1 = SysClkReq2 controlled + * SysClkReq3Valid1 = disabled + * SysClkReq4Valid1 = SysClkReq4 controlled + */ + INIT_REGULATOR_REGISTER(AB8505_REGUSYSCLKREQVALID1, 0x0e, 0x0a), + /* + * SysClkReq2Valid2 = disabled + * SysClkReq3Valid2 = disabled + * SysClkReq4Valid2 = disabled + */ + INIT_REGULATOR_REGISTER(AB8505_REGUSYSCLKREQVALID2, 0x0e, 0x00), + /* + * Vaux4SwHPReqValid + * Vaux4HwHPReq2Valid + * Vaux4HwHPReq1Valid + * Vaux4SysClkReq1HPValid + */ + INIT_REGULATOR_REGISTER(AB8505_REGUVAUX4REQVALID, 0x00, 0x00), + /* + * VadcEna = disabled + * VintCore12Ena = disabled + * VintCore12Sel = 1.25 V + * VintCore12LP = inactive (HP) + * VadcLP = inactive (HP) + */ + INIT_REGULATOR_REGISTER(AB8505_REGUMISC1, 0xfe, 0x10), + /* + * VaudioEna = disabled + * Vaux8Ena = disabled + * Vamic1Ena = disabled + * Vamic2Ena = disabled + */ + INIT_REGULATOR_REGISTER(AB8505_VAUDIOSUPPLY, 0x1e, 0x00), + /* + * Vamic1_dzout = high-Z when Vamic1 is disabled + * Vamic2_dzout = high-Z when Vamic2 is disabled + */ + INIT_REGULATOR_REGISTER(AB8505_REGUCTRL1VAMIC, 0x03, 0x00), + /* + * VsmpsARegu + * VsmpsASelCtrl + * VsmpsAAutoMode + * VsmpsAPWMMode + */ + INIT_REGULATOR_REGISTER(AB8505_VSMPSAREGU, 0x00, 0x00), + /* + * VsmpsBRegu + * VsmpsBSelCtrl + * VsmpsBAutoMode + * VsmpsBPWMMode + */ + INIT_REGULATOR_REGISTER(AB8505_VSMPSBREGU, 0x00, 0x00), + /* + * VsafeRegu + * VsafeSelCtrl + * VsafeAutoMode + * VsafePWMMode + */ + INIT_REGULATOR_REGISTER(AB8505_VSAFEREGU, 0x00, 0x00), + /* + * VPll = Hw controlled (NOTE! PRCMU bits) + * VanaRegu = force off + */ + INIT_REGULATOR_REGISTER(AB8505_VPLLVANAREGU, 0x0f, 0x02), + /* + * VextSupply1Regu = force OFF (OTP_ExtSupply12LPnPolarity 1) + * VextSupply2Regu = force OFF (OTP_ExtSupply12LPnPolarity 1) + * VextSupply3Regu = force OFF (OTP_ExtSupply3LPnPolarity 0) + * ExtSupply2Bypass = ExtSupply12LPn ball is 0 when Ena is 0 + * ExtSupply3Bypass = ExtSupply3LPn ball is 0 when Ena is 0 + */ + INIT_REGULATOR_REGISTER(AB8505_EXTSUPPLYREGU, 0xff, 0x30), + /* + * Vaux1Regu = force HP + * Vaux2Regu = force off + */ + INIT_REGULATOR_REGISTER(AB8505_VAUX12REGU, 0x0f, 0x01), + /* + * Vaux3Regu = force off + */ + INIT_REGULATOR_REGISTER(AB8505_VRF1VAUX3REGU, 0x03, 0x00), + /* + * VsmpsASel1 + */ + INIT_REGULATOR_REGISTER(AB8505_VSMPSASEL1, 0x00, 0x00), + /* + * VsmpsASel2 + */ + INIT_REGULATOR_REGISTER(AB8505_VSMPSASEL2, 0x00, 0x00), + /* + * VsmpsASel3 + */ + INIT_REGULATOR_REGISTER(AB8505_VSMPSASEL3, 0x00, 0x00), + /* + * VsmpsBSel1 + */ + INIT_REGULATOR_REGISTER(AB8505_VSMPSBSEL1, 0x00, 0x00), + /* + * VsmpsBSel2 + */ + INIT_REGULATOR_REGISTER(AB8505_VSMPSBSEL2, 0x00, 0x00), + /* + * VsmpsBSel3 + */ + INIT_REGULATOR_REGISTER(AB8505_VSMPSBSEL3, 0x00, 0x00), + /* + * VsafeSel1 + */ + INIT_REGULATOR_REGISTER(AB8505_VSAFESEL1, 0x00, 0x00), + /* + * VsafeSel2 + */ + INIT_REGULATOR_REGISTER(AB8505_VSAFESEL2, 0x00, 0x00), + /* + * VsafeSel3 + */ + INIT_REGULATOR_REGISTER(AB8505_VSAFESEL3, 0x00, 0x00), + /* + * Vaux1Sel = 2.8 V + */ + INIT_REGULATOR_REGISTER(AB8505_VAUX1SEL, 0x0f, 0x0C), + /* + * Vaux2Sel = 2.9 V + */ + INIT_REGULATOR_REGISTER(AB8505_VAUX2SEL, 0x0f, 0x0d), + /* + * Vaux3Sel = 2.91 V + */ + INIT_REGULATOR_REGISTER(AB8505_VRF1VAUX3SEL, 0x07, 0x07), + /* + * Vaux4RequestCtrl + */ + INIT_REGULATOR_REGISTER(AB8505_VAUX4REQCTRL, 0x00, 0x00), + /* + * Vaux4Regu + */ + INIT_REGULATOR_REGISTER(AB8505_VAUX4REGU, 0x00, 0x00), + /* + * Vaux4Sel + */ + INIT_REGULATOR_REGISTER(AB8505_VAUX4SEL, 0x00, 0x00), + /* + * Vaux1Disch = short discharge time + * Vaux2Disch = short discharge time + * Vaux3Disch = short discharge time + * Vintcore12Disch = short discharge time + * VTVoutDisch = short discharge time + * VaudioDisch = short discharge time + */ + INIT_REGULATOR_REGISTER(AB8505_REGUCTRLDISCH, 0xfc, 0x00), + /* + * VanaDisch = short discharge time + * Vaux8PullDownEna = pulldown disabled when Vaux8 is disabled + * Vaux8Disch = short discharge time + */ + INIT_REGULATOR_REGISTER(AB8505_REGUCTRLDISCH2, 0x16, 0x00), + /* + * Vaux4Disch = short discharge time + */ + INIT_REGULATOR_REGISTER(AB8505_REGUCTRLDISCH3, 0x01, 0x00), + /* + * Vaux5Sel + * Vaux5LP + * Vaux5Ena + * Vaux5Disch + * Vaux5DisSfst + * Vaux5DisPulld + */ + INIT_REGULATOR_REGISTER(AB8505_CTRLVAUX5, 0x00, 0x00), + /* + * Vaux6Sel + * Vaux6LP + * Vaux6Ena + * Vaux6DisPulld + */ + INIT_REGULATOR_REGISTER(AB8505_CTRLVAUX6, 0x00, 0x00), +}; + +struct regulator_init_data ab8505_regulators[AB8505_NUM_REGULATORS] = { + /* supplies to the display/camera */ + [AB8505_LDO_AUX1] = { + .constraints = { + .name = "V-DISPLAY", + .min_uV = 2800000, + .max_uV = 3300000, + .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | + REGULATOR_CHANGE_STATUS, + .boot_on = 1, /* display is on at boot */ + }, + .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux1_consumers), + .consumer_supplies = ab8500_vaux1_consumers, + }, + /* supplies to the on-board eMMC */ + [AB8505_LDO_AUX2] = { + .constraints = { + .name = "V-eMMC1", + .min_uV = 1100000, + .max_uV = 3300000, + .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | + REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_MODE, + .valid_modes_mask = REGULATOR_MODE_NORMAL | + REGULATOR_MODE_IDLE, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux2_consumers), + .consumer_supplies = ab8500_vaux2_consumers, + }, + /* supply for VAUX3, supplies to SDcard slots */ + [AB8505_LDO_AUX3] = { + .constraints = { + .name = "V-MMC-SD", + .min_uV = 1100000, + .max_uV = 3300000, + .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | + REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_MODE, + .valid_modes_mask = REGULATOR_MODE_NORMAL | + REGULATOR_MODE_IDLE, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux3_consumers), + .consumer_supplies = ab8500_vaux3_consumers, + }, + /* supply for VAUX4, supplies to NFC and standalone secure element */ + [AB8505_LDO_AUX4] = { + .constraints = { + .name = "V-NFC-SE", + .min_uV = 1100000, + .max_uV = 3300000, + .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | + REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_MODE, + .valid_modes_mask = REGULATOR_MODE_NORMAL | + REGULATOR_MODE_IDLE, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8505_vaux4_consumers), + .consumer_supplies = ab8505_vaux4_consumers, + }, + /* supply for VAUX5, supplies to TBD */ + [AB8505_LDO_AUX5] = { + .constraints = { + .name = "V-AUX5", + .min_uV = 1050000, + .max_uV = 2790000, + .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | + REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_MODE, + .valid_modes_mask = REGULATOR_MODE_NORMAL | + REGULATOR_MODE_IDLE, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8505_vaux5_consumers), + .consumer_supplies = ab8505_vaux5_consumers, + }, + /* supply for VAUX6, supplies to TBD */ + [AB8505_LDO_AUX6] = { + .constraints = { + .name = "V-AUX6", + .min_uV = 1050000, + .max_uV = 2790000, + .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | + REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_MODE, + .valid_modes_mask = REGULATOR_MODE_NORMAL | + REGULATOR_MODE_IDLE, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8505_vaux6_consumers), + .consumer_supplies = ab8505_vaux6_consumers, + }, + /* supply for gpadc, ADC LDO */ + [AB8505_LDO_ADC] = { + .constraints = { + .name = "V-ADC", + .valid_ops_mask = REGULATOR_CHANGE_STATUS, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8505_vadc_consumers), + .consumer_supplies = ab8505_vadc_consumers, + }, + /* supply for ab8500-vaudio, VAUDIO LDO */ + [AB8505_LDO_AUDIO] = { + .constraints = { + .name = "V-AUD", + .valid_ops_mask = REGULATOR_CHANGE_STATUS, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8500_vaud_consumers), + .consumer_supplies = ab8500_vaud_consumers, + }, + /* supply for v-anamic1 VAMic1-LDO */ + [AB8505_LDO_ANAMIC1] = { + .constraints = { + .name = "V-AMIC1", + .valid_ops_mask = REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_MODE, + .valid_modes_mask = REGULATOR_MODE_NORMAL | + REGULATOR_MODE_IDLE, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8500_vamic1_consumers), + .consumer_supplies = ab8500_vamic1_consumers, + }, + /* supply for v-amic2, VAMIC2 LDO, reuse constants for AMIC1 */ + [AB8505_LDO_ANAMIC2] = { + .constraints = { + .name = "V-AMIC2", + .valid_ops_mask = REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_MODE, + .valid_modes_mask = REGULATOR_MODE_NORMAL | + REGULATOR_MODE_IDLE, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8500_vamic2_consumers), + .consumer_supplies = ab8500_vamic2_consumers, + }, + /* supply for v-aux8, VAUX8 LDO */ + [AB8505_LDO_AUX8] = { + .constraints = { + .name = "V-AUX8", + .valid_ops_mask = REGULATOR_CHANGE_STATUS, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8505_vaux8_consumers), + .consumer_supplies = ab8505_vaux8_consumers, + }, + /* supply for v-intcore12, VINTCORE12 LDO */ + [AB8505_LDO_INTCORE] = { + .constraints = { + .name = "V-INTCORE", + .min_uV = 1250000, + .max_uV = 1350000, + .input_uV = 1800000, + .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | + REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_MODE | + REGULATOR_CHANGE_DRMS, + .valid_modes_mask = REGULATOR_MODE_NORMAL | + REGULATOR_MODE_IDLE, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8500_vintcore_consumers), + .consumer_supplies = ab8500_vintcore_consumers, + }, + /* supply for LDO USB */ + [AB8505_LDO_USB] = { + .constraints = { + .name = "V-USB", + .valid_ops_mask = REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_MODE, + .valid_modes_mask = REGULATOR_MODE_NORMAL | + REGULATOR_MODE_IDLE, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8505_usb_consumers), + .consumer_supplies = ab8505_usb_consumers, + }, + /* supply for U8500 CSI-DSI, VANA LDO */ + [AB8505_LDO_ANA] = { + .constraints = { + .name = "V-CSI-DSI", + .valid_ops_mask = REGULATOR_CHANGE_STATUS, + }, + .num_consumer_supplies = ARRAY_SIZE(ab8500_vana_consumers), + .consumer_supplies = ab8500_vana_consumers, + }, +}; + +struct ab8500_regulator_platform_data ab8500_regulator_plat_data = { + .reg_init = ab8500_reg_init, + .num_reg_init = ARRAY_SIZE(ab8500_reg_init), + .regulator = ab8500_regulators, + .num_regulator = ARRAY_SIZE(ab8500_regulators), + .ext_regulator = ab8500_ext_regulators, + .num_ext_regulator = ARRAY_SIZE(ab8500_ext_regulators), +}; + +/* Use the AB8500 init settings for AB8505 as they are the same right now */ +struct ab8500_regulator_platform_data ab8505_regulator_plat_data = { + .reg_init = ab8505_reg_init, + .num_reg_init = ARRAY_SIZE(ab8505_reg_init), + .regulator = ab8505_regulators, + .num_regulator = ARRAY_SIZE(ab8505_regulators), +}; + +static void ab8500_modify_reg_init(int id, u8 mask, u8 value) +{ + int i; + + if (cpu_is_u8520()) { + for (i = ARRAY_SIZE(ab8505_reg_init) - 1; i >= 0; i--) { + if (ab8505_reg_init[i].id == id) { + u8 initval = ab8505_reg_init[i].value; + initval = (initval & ~mask) | (value & mask); + ab8505_reg_init[i].value = initval; + + BUG_ON(mask & ~ab8505_reg_init[i].mask); + return; + } + } + } else { + for (i = ARRAY_SIZE(ab8500_reg_init) - 1; i >= 0; i--) { + if (ab8500_reg_init[i].id == id) { + u8 initval = ab8500_reg_init[i].value; + initval = (initval & ~mask) | (value & mask); + ab8500_reg_init[i].value = initval; + + BUG_ON(mask & ~ab8500_reg_init[i].mask); + return; + } + } + } + + BUG_ON(1); +} + +void mop500_regulator_init(void) +{ + struct regulator_init_data *regulator; + + /* + * Temporarily turn on Vaux2 on 8520 machine + */ + if (cpu_is_u8520()) { + /* Vaux2 initialized to be on */ + ab8500_modify_reg_init(AB8505_VAUX12REGU, 0x0f, 0x05); + } + + /* + * Handle AB8500_EXT_SUPPLY2 on HREFP_V20_V50 boards (do it for + * all HREFP_V20 boards) + */ + if (cpu_is_u8500v20()) { + /* VextSupply2RequestCtrl = HP/OFF depending on VxRequest */ + ab8500_modify_reg_init(AB8500_REGUREQUESTCTRL3, 0x01, 0x01); + + /* VextSupply2SysClkReq1HPValid = SysClkReq1 controlled */ + ab8500_modify_reg_init(AB8500_REGUSYSCLKREQ1HPVALID2, + 0x20, 0x20); + + /* VextSupply2 = force HP at initialization */ + ab8500_modify_reg_init(AB8500_EXTSUPPLYREGU, 0x0c, 0x04); + + /* enable VextSupply2 during platform active */ + regulator = &ab8500_ext_regulators[AB8500_EXT_SUPPLY2]; + regulator->constraints.always_on = 1; + + /* disable VextSupply2 in suspend */ + regulator = &ab8500_ext_regulators[AB8500_EXT_SUPPLY2]; + regulator->constraints.state_mem.disabled = 1; + regulator->constraints.state_standby.disabled = 1; + + /* enable VextSupply2 HW control (used in suspend) */ + regulator->driver_data = (void *)&ab8500_ext_supply2; + } +} diff --git a/arch/arm/mach-ux500/board-mop500-regulators.h b/arch/arm/mach-ux500/board-mop500-regulators.h index 78a0642..9bece38 100644 --- a/arch/arm/mach-ux500/board-mop500-regulators.h +++ b/arch/arm/mach-ux500/board-mop500-regulators.h @@ -14,10 +14,11 @@ #include <linux/regulator/machine.h> #include <linux/regulator/ab8500.h> -extern struct ab8500_regulator_reg_init -ab8500_regulator_reg_init[AB8500_NUM_REGULATOR_REGISTERS]; -extern struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS]; +extern struct ab8500_regulator_platform_data ab8500_regulator_plat_data; +extern struct ab8500_regulator_platform_data ab8505_regulator_plat_data; extern struct regulator_init_data tps61052_regulator; extern struct regulator_init_data gpio_en_3v3_regulator; +void mop500_regulator_init(void); + #endif diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c index 87d2d7b..ce67237 100644 --- a/arch/arm/mach-ux500/board-mop500.c +++ b/arch/arm/mach-ux500/board-mop500.c @@ -199,10 +199,7 @@ static struct platform_device snowball_sbnet_dev = { struct ab8500_platform_data ab8500_platdata = { .irq_base = MOP500_AB8500_IRQ_BASE, - .regulator_reg_init = ab8500_regulator_reg_init, - .num_regulator_reg_init = ARRAY_SIZE(ab8500_regulator_reg_init), - .regulator = ab8500_regulators, - .num_regulator = ARRAY_SIZE(ab8500_regulators), + .regulator = &ab8500_regulator_plat_data, .gpio = &ab8500_gpio_pdata, .codec = &ab8500_codec_pdata, }; diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c index 915683c..c5e20b5 100644 --- a/arch/arm/mach-vexpress/v2m.c +++ b/arch/arm/mach-vexpress/v2m.c @@ -21,6 +21,8 @@ #include <linux/regulator/fixed.h> #include <linux/regulator/machine.h> #include <linux/vexpress.h> +#include <linux/clk-provider.h> +#include <linux/clkdev.h> #include <asm/arch_timer.h> #include <asm/mach-types.h> @@ -433,7 +435,7 @@ static void __init v2m_dt_timer_init(void) { struct device_node *node = NULL; - vexpress_clk_of_init(); + of_clk_init(NULL); do { node = of_find_compatible_node(node, NULL, "arm,sp804"); @@ -441,6 +443,10 @@ static void __init v2m_dt_timer_init(void) if (node) { pr_info("Using SP804 '%s' as a clock & events source\n", node->full_name); + WARN_ON(clk_register_clkdev(of_clk_get_by_name(node, + "timclken1"), "v2m-timer0", "sp804")); + WARN_ON(clk_register_clkdev(of_clk_get_by_name(node, + "timclken2"), "v2m-timer1", "sp804")); v2m_sp804_init(of_iomap(node, 0), irq_of_parse_and_map(node, 0)); } diff --git a/arch/arm/mach-w90x900/dev.c b/arch/arm/mach-w90x900/dev.c index 7abdb96..e65a80a 100644 --- a/arch/arm/mach-w90x900/dev.c +++ b/arch/arm/mach-w90x900/dev.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/platform_device.h> #include <linux/slab.h> +#include <linux/cpu.h> #include <linux/mtd/physmap.h> #include <linux/mtd/mtd.h> @@ -531,7 +532,7 @@ static struct platform_device *nuc900_public_dev[] __initdata = { void __init nuc900_board_init(struct platform_device **device, int size) { - disable_hlt(); + cpu_idle_poll_ctrl(true); platform_add_devices(device, size); platform_add_devices(nuc900_public_dev, ARRAY_SIZE(nuc900_public_dev)); spi_register_board_info(nuc900_spi_board_info, diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 025d173..4045c49 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -43,7 +43,7 @@ config CPU_ARM740T depends on !MMU select CPU_32v4T select CPU_ABRT_LV4T - select CPU_CACHE_V3 # although the core is v4t + select CPU_CACHE_V4 select CPU_CP15_MPU select CPU_PABRT_LEGACY help @@ -469,9 +469,6 @@ config CPU_PABRT_V7 bool # The cache model -config CPU_CACHE_V3 - bool - config CPU_CACHE_V4 bool diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index 4e333fa..9e51be9 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -33,7 +33,6 @@ obj-$(CONFIG_CPU_PABRT_LEGACY) += pabort-legacy.o obj-$(CONFIG_CPU_PABRT_V6) += pabort-v6.o obj-$(CONFIG_CPU_PABRT_V7) += pabort-v7.o -obj-$(CONFIG_CPU_CACHE_V3) += cache-v3.o obj-$(CONFIG_CPU_CACHE_V4) += cache-v4.o obj-$(CONFIG_CPU_CACHE_V4WT) += cache-v4wt.o obj-$(CONFIG_CPU_CACHE_V4WB) += cache-v4wb.o diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index dd3d591..48bc3c0 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -343,6 +343,7 @@ void __init feroceon_l2_init(int __l2_wt_override) outer_cache.inv_range = feroceon_l2_inv_range; outer_cache.clean_range = feroceon_l2_clean_range; outer_cache.flush_range = feroceon_l2_flush_range; + outer_cache.inv_all = l2_inv_all; enable_l2(); diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S deleted file mode 100644 index 8a3fade..0000000 --- a/arch/arm/mm/cache-v3.S +++ /dev/null @@ -1,137 +0,0 @@ -/* - * linux/arch/arm/mm/cache-v3.S - * - * Copyright (C) 1997-2002 Russell king - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/linkage.h> -#include <linux/init.h> -#include <asm/page.h> -#include "proc-macros.S" - -/* - * flush_icache_all() - * - * Unconditionally clean and invalidate the entire icache. - */ -ENTRY(v3_flush_icache_all) - mov pc, lr -ENDPROC(v3_flush_icache_all) - -/* - * flush_user_cache_all() - * - * Invalidate all cache entries in a particular address - * space. - * - * - mm - mm_struct describing address space - */ -ENTRY(v3_flush_user_cache_all) - /* FALLTHROUGH */ -/* - * flush_kern_cache_all() - * - * Clean and invalidate the entire cache. - */ -ENTRY(v3_flush_kern_cache_all) - /* FALLTHROUGH */ - -/* - * flush_user_cache_range(start, end, flags) - * - * Invalidate a range of cache entries in the specified - * address space. - * - * - start - start address (may not be aligned) - * - end - end address (exclusive, may not be aligned) - * - flags - vma_area_struct flags describing address space - */ -ENTRY(v3_flush_user_cache_range) - mov ip, #0 - mcreq p15, 0, ip, c7, c0, 0 @ flush ID cache - mov pc, lr - -/* - * coherent_kern_range(start, end) - * - * Ensure coherency between the Icache and the Dcache in the - * region described by start. If you have non-snooping - * Harvard caches, you need to implement this function. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_coherent_kern_range) - /* FALLTHROUGH */ - -/* - * coherent_user_range(start, end) - * - * Ensure coherency between the Icache and the Dcache in the - * region described by start. If you have non-snooping - * Harvard caches, you need to implement this function. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_coherent_user_range) - mov r0, #0 - mov pc, lr - -/* - * flush_kern_dcache_area(void *page, size_t size) - * - * Ensure no D cache aliasing occurs, either with itself or - * the I cache - * - * - addr - kernel address - * - size - region size - */ -ENTRY(v3_flush_kern_dcache_area) - /* FALLTHROUGH */ - -/* - * dma_flush_range(start, end) - * - * Clean and invalidate the specified virtual address range. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_dma_flush_range) - mov r0, #0 - mcr p15, 0, r0, c7, c0, 0 @ flush ID cache - mov pc, lr - -/* - * dma_unmap_area(start, size, dir) - * - start - kernel virtual start address - * - size - size of region - * - dir - DMA direction - */ -ENTRY(v3_dma_unmap_area) - teq r2, #DMA_TO_DEVICE - bne v3_dma_flush_range - /* FALLTHROUGH */ - -/* - * dma_map_area(start, size, dir) - * - start - kernel virtual start address - * - size - size of region - * - dir - DMA direction - */ -ENTRY(v3_dma_map_area) - mov pc, lr -ENDPROC(v3_dma_unmap_area) -ENDPROC(v3_dma_map_area) - - .globl v3_flush_kern_cache_louis - .equ v3_flush_kern_cache_louis, v3_flush_kern_cache_all - - __INITDATA - - @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S) - define_cache_functions v3 diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S index 43e5d77..a7ba68f 100644 --- a/arch/arm/mm/cache-v4.S +++ b/arch/arm/mm/cache-v4.S @@ -58,7 +58,7 @@ ENTRY(v4_flush_kern_cache_all) ENTRY(v4_flush_user_cache_range) #ifdef CONFIG_CPU_CP15 mov ip, #0 - mcreq p15, 0, ip, c7, c7, 0 @ flush ID cache + mcr p15, 0, ip, c7, c7, 0 @ flush ID cache mov pc, lr #else /* FALLTHROUGH */ diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index ad722f1..9a5cdc0 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -99,6 +99,9 @@ void show_mem(unsigned int filter) printk("Mem-info:\n"); show_free_areas(filter); + if (filter & SHOW_MEM_FILTER_PAGE_COUNT) + return; + for_each_bank (i, mi) { struct membank *bank = &mi->bank[i]; unsigned int pfn1, pfn2; @@ -424,24 +427,6 @@ void __init bootmem_init(void) max_pfn = max_high - PHYS_PFN_OFFSET; } -static inline int free_area(unsigned long pfn, unsigned long end, char *s) -{ - unsigned int pages = 0, size = (end - pfn) << (PAGE_SHIFT - 10); - - for (; pfn < end; pfn++) { - struct page *page = pfn_to_page(pfn); - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - pages++; - } - - if (size && s) - printk(KERN_INFO "Freeing %s memory: %dK\n", s, size); - - return pages; -} - /* * Poison init memory with an undefined instruction (ARM) or a branch to an * undefined instruction (Thumb). @@ -534,6 +519,14 @@ static void __init free_unused_memmap(struct meminfo *mi) #endif } +#ifdef CONFIG_HIGHMEM +static inline void free_area_high(unsigned long pfn, unsigned long end) +{ + for (; pfn < end; pfn++) + free_highmem_page(pfn_to_page(pfn)); +} +#endif + static void __init free_highpages(void) { #ifdef CONFIG_HIGHMEM @@ -569,8 +562,7 @@ static void __init free_highpages(void) if (res_end > end) res_end = end; if (res_start != start) - totalhigh_pages += free_area(start, res_start, - NULL); + free_area_high(start, res_start); start = res_end; if (start == end) break; @@ -578,9 +570,8 @@ static void __init free_highpages(void) /* And now free anything which remains */ if (start < end) - totalhigh_pages += free_area(start, end, NULL); + free_area_high(start, end); } - totalram_pages += totalhigh_pages; #endif } @@ -609,8 +600,7 @@ void __init mem_init(void) #ifdef CONFIG_SA1111 /* now that our DMA memory is actually so designated, we can free it */ - totalram_pages += free_area(PHYS_PFN_OFFSET, - __phys_to_pfn(__pa(swapper_pg_dir)), NULL); + free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL); #endif free_highpages(); @@ -738,16 +728,12 @@ void free_initmem(void) extern char __tcm_start, __tcm_end; poison_init_mem(&__tcm_start, &__tcm_end - &__tcm_start); - totalram_pages += free_area(__phys_to_pfn(__pa(&__tcm_start)), - __phys_to_pfn(__pa(&__tcm_end)), - "TCM link"); + free_reserved_area(&__tcm_start, &__tcm_end, 0, "TCM link"); #endif poison_init_mem(__init_begin, __init_end - __init_begin); if (!machine_is_integrator() && !machine_is_cintegrator()) - totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)), - __phys_to_pfn(__pa(__init_end)), - "init"); + free_initmem_default(0); } #ifdef CONFIG_BLK_DEV_INITRD @@ -758,9 +744,7 @@ void free_initrd_mem(unsigned long start, unsigned long end) { if (!keep_initrd) { poison_init_mem((void *)start, PAGE_ALIGN(end) - start); - totalram_pages += free_area(__phys_to_pfn(__pa(start)), - __phys_to_pfn(__pa(end)), - "initrd"); + free_reserved_area(start, end, 0, "initrd"); } } diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 7897894..a84ff76 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -34,6 +34,7 @@ #include <asm/mach/pci.h> #include "mm.h" +#include "tcm.h" /* * empty_zero_page is a special page that is used for @@ -1277,6 +1278,7 @@ void __init paging_init(struct machine_desc *mdesc) dma_contiguous_remap(); devicemaps_init(mdesc); kmap_init(); + tcm_init(); top_pmd = pmd_off_k(0xffff0000); diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S index dc5de5d..fde2d2a 100644 --- a/arch/arm/mm/proc-arm740.S +++ b/arch/arm/mm/proc-arm740.S @@ -77,24 +77,27 @@ __arm740_setup: mcr p15, 0, r0, c6, c0 @ set area 0, default ldr r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM - ldr r1, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB) - mov r2, #10 @ 11 is the minimum (4KB) -1: add r2, r2, #1 @ area size *= 2 - mov r1, r1, lsr #1 + ldr r3, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB) + mov r4, #10 @ 11 is the minimum (4KB) +1: add r4, r4, #1 @ area size *= 2 + movs r3, r3, lsr #1 bne 1b @ count not zero r-shift - orr r0, r0, r2, lsl #1 @ the area register value + orr r0, r0, r4, lsl #1 @ the area register value orr r0, r0, #1 @ set enable bit mcr p15, 0, r0, c6, c1 @ set area 1, RAM ldr r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH - ldr r1, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB) - mov r2, #10 @ 11 is the minimum (4KB) -1: add r2, r2, #1 @ area size *= 2 - mov r1, r1, lsr #1 + ldr r3, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB) + cmp r3, #0 + moveq r0, #0 + beq 2f + mov r4, #10 @ 11 is the minimum (4KB) +1: add r4, r4, #1 @ area size *= 2 + movs r3, r3, lsr #1 bne 1b @ count not zero r-shift - orr r0, r0, r2, lsl #1 @ the area register value + orr r0, r0, r4, lsl #1 @ the area register value orr r0, r0, #1 @ set enable bit - mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH +2: mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH mov r0, #0x06 mcr p15, 0, r0, c2, c0 @ Region 1&2 cacheable @@ -137,13 +140,14 @@ __arm740_proc_info: .long 0x41807400 .long 0xfffffff0 .long 0 + .long 0 b __arm740_setup .long cpu_arch_name .long cpu_elf_name - .long HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT + .long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT .long cpu_arm740_name .long arm740_processor_functions .long 0 .long 0 - .long v3_cache_fns @ cache model + .long v4_cache_fns @ cache model .size __arm740_proc_info, . - __arm740_proc_info diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 2c3b942..2556cf1 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -387,7 +387,7 @@ ENTRY(cpu_arm920_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm920_suspend_size .equ cpu_arm920_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_arm920_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index f1803f7..344c8a5 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -402,7 +402,7 @@ ENTRY(cpu_arm926_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm926_suspend_size .equ cpu_arm926_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_arm926_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S index 82f9cdc..0b60dd3 100644 --- a/arch/arm/mm/proc-mohawk.S +++ b/arch/arm/mm/proc-mohawk.S @@ -350,7 +350,7 @@ ENTRY(cpu_mohawk_set_pte_ext) .globl cpu_mohawk_suspend_size .equ cpu_mohawk_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_mohawk_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 3aa0da1..d92dfd0 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -172,7 +172,7 @@ ENTRY(cpu_sa1100_set_pte_ext) .globl cpu_sa1100_suspend_size .equ cpu_sa1100_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_sa1100_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c3, c0, 0 @ domain ID diff --git a/arch/arm/mm/proc-syms.c b/arch/arm/mm/proc-syms.c index 3e6210b..054b491 100644 --- a/arch/arm/mm/proc-syms.c +++ b/arch/arm/mm/proc-syms.c @@ -17,7 +17,9 @@ #ifndef MULTI_CPU EXPORT_SYMBOL(cpu_dcache_clean_area); +#ifdef CONFIG_MMU EXPORT_SYMBOL(cpu_set_pte_ext); +#endif #else EXPORT_SYMBOL(processor); #endif diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index bcaaa8d..5c07ee4 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -138,7 +138,7 @@ ENTRY(cpu_v6_set_pte_ext) /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */ .globl cpu_v6_suspend_size .equ cpu_v6_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v6_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index eb93d64..e8efd83 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -413,7 +413,7 @@ ENTRY(cpu_xsc3_set_pte_ext) .globl cpu_xsc3_suspend_size .equ cpu_xsc3_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_xsc3_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index 2551036..e766f88 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -528,7 +528,7 @@ ENTRY(cpu_xscale_set_pte_ext) .globl cpu_xscale_suspend_size .equ cpu_xscale_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_xscale_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/kernel/tcm.h b/arch/arm/mm/tcm.h index 8015ad4..8015ad4 100644 --- a/arch/arm/kernel/tcm.h +++ b/arch/arm/mm/tcm.h diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c index 51afedd..03db14d 100644 --- a/arch/arm/plat-samsung/devs.c +++ b/arch/arm/plat-samsung/devs.c @@ -10,6 +10,7 @@ * published by the Free Software Foundation. */ +#include <linux/amba/pl330.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/interrupt.h> @@ -1552,6 +1553,9 @@ void __init s3c64xx_spi0_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, pd.num_cs = num_cs; pd.src_clk_nr = src_clk_nr; pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi0_cfg_gpio; +#ifdef CONFIG_PL330_DMA + pd.filter = pl330_filter; +#endif s3c_set_platdata(&pd, sizeof(pd), &s3c64xx_device_spi0); } @@ -1590,6 +1594,9 @@ void __init s3c64xx_spi1_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, pd.num_cs = num_cs; pd.src_clk_nr = src_clk_nr; pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi1_cfg_gpio; +#ifdef CONFIG_PL330_DMA + pd.filter = pl330_filter; +#endif s3c_set_platdata(&pd, sizeof(pd), &s3c64xx_device_spi1); } @@ -1628,6 +1635,9 @@ void __init s3c64xx_spi2_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, pd.num_cs = num_cs; pd.src_clk_nr = src_clk_nr; pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi2_cfg_gpio; +#ifdef CONFIG_PL330_DMA + pd.filter = pl330_filter; +#endif s3c_set_platdata(&pd, sizeof(pd), &s3c64xx_device_spi2); } diff --git a/arch/arm/plat-samsung/include/plat/fb.h b/arch/arm/plat-samsung/include/plat/fb.h index b885322..9ae5072 100644 --- a/arch/arm/plat-samsung/include/plat/fb.h +++ b/arch/arm/plat-samsung/include/plat/fb.h @@ -15,55 +15,7 @@ #ifndef __PLAT_S3C_FB_H #define __PLAT_S3C_FB_H __FILE__ -/* S3C_FB_MAX_WIN - * Set to the maximum number of windows that any of the supported hardware - * can use. Since the platform data uses this for an array size, having it - * set to the maximum of any version of the hardware can do is safe. - */ -#define S3C_FB_MAX_WIN (5) - -/** - * struct s3c_fb_pd_win - per window setup data - * @xres : The window X size. - * @yres : The window Y size. - * @virtual_x: The virtual X size. - * @virtual_y: The virtual Y size. - */ -struct s3c_fb_pd_win { - unsigned short default_bpp; - unsigned short max_bpp; - unsigned short xres; - unsigned short yres; - unsigned short virtual_x; - unsigned short virtual_y; -}; - -/** - * struct s3c_fb_platdata - S3C driver platform specific information - * @setup_gpio: Setup the external GPIO pins to the right state to transfer - * the data from the display system to the connected display - * device. - * @vidcon0: The base vidcon0 values to control the panel data format. - * @vidcon1: The base vidcon1 values to control the panel data output. - * @vtiming: Video timing when connected to a RGB type panel. - * @win: The setup data for each hardware window, or NULL for unused. - * @display_mode: The LCD output display mode. - * - * The platform data supplies the video driver with all the information - * it requires to work with the display(s) attached to the machine. It - * controls the initial mode, the number of display windows (0 is always - * the base framebuffer) that are initialised etc. - * - */ -struct s3c_fb_platdata { - void (*setup_gpio)(void); - - struct s3c_fb_pd_win *win[S3C_FB_MAX_WIN]; - struct fb_videomode *vtiming; - - u32 vidcon0; - u32 vidcon1; -}; +#include <linux/platform_data/video_s3c.h> /** * s3c_fb_set_platdata() - Setup the FB device with platform data. diff --git a/arch/arm/plat-samsung/include/plat/regs-serial.h b/arch/arm/plat-samsung/include/plat/regs-serial.h index 29c26a8..f05f2af 100644 --- a/arch/arm/plat-samsung/include/plat/regs-serial.h +++ b/arch/arm/plat-samsung/include/plat/regs-serial.h @@ -1,281 +1 @@ -/* arch/arm/plat-samsung/include/plat/regs-serial.h - * - * From linux/include/asm-arm/hardware/serial_s3c2410.h - * - * Internal header file for Samsung S3C2410 serial ports (UART0-2) - * - * Copyright (C) 2002 Shane Nay (shane@minirl.com) - * - * Additional defines, Copyright 2003 Simtec Electronics (linux@simtec.co.uk) - * - * Adapted from: - * - * Internal header file for MX1ADS serial ports (UART1 & 2) - * - * Copyright (C) 2002 Shane Nay (shane@minirl.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA -*/ - -#ifndef __ASM_ARM_REGS_SERIAL_H -#define __ASM_ARM_REGS_SERIAL_H - -#define S3C24XX_VA_UART0 (S3C_VA_UART) -#define S3C24XX_VA_UART1 (S3C_VA_UART + 0x4000 ) -#define S3C24XX_VA_UART2 (S3C_VA_UART + 0x8000 ) -#define S3C24XX_VA_UART3 (S3C_VA_UART + 0xC000 ) - -#define S3C2410_PA_UART0 (S3C24XX_PA_UART) -#define S3C2410_PA_UART1 (S3C24XX_PA_UART + 0x4000 ) -#define S3C2410_PA_UART2 (S3C24XX_PA_UART + 0x8000 ) -#define S3C2443_PA_UART3 (S3C24XX_PA_UART + 0xC000 ) - -#define S3C2410_URXH (0x24) -#define S3C2410_UTXH (0x20) -#define S3C2410_ULCON (0x00) -#define S3C2410_UCON (0x04) -#define S3C2410_UFCON (0x08) -#define S3C2410_UMCON (0x0C) -#define S3C2410_UBRDIV (0x28) -#define S3C2410_UTRSTAT (0x10) -#define S3C2410_UERSTAT (0x14) -#define S3C2410_UFSTAT (0x18) -#define S3C2410_UMSTAT (0x1C) - -#define S3C2410_LCON_CFGMASK ((0xF<<3)|(0x3)) - -#define S3C2410_LCON_CS5 (0x0) -#define S3C2410_LCON_CS6 (0x1) -#define S3C2410_LCON_CS7 (0x2) -#define S3C2410_LCON_CS8 (0x3) -#define S3C2410_LCON_CSMASK (0x3) - -#define S3C2410_LCON_PNONE (0x0) -#define S3C2410_LCON_PEVEN (0x5 << 3) -#define S3C2410_LCON_PODD (0x4 << 3) -#define S3C2410_LCON_PMASK (0x7 << 3) - -#define S3C2410_LCON_STOPB (1<<2) -#define S3C2410_LCON_IRM (1<<6) - -#define S3C2440_UCON_CLKMASK (3<<10) -#define S3C2440_UCON_CLKSHIFT (10) -#define S3C2440_UCON_PCLK (0<<10) -#define S3C2440_UCON_UCLK (1<<10) -#define S3C2440_UCON_PCLK2 (2<<10) -#define S3C2440_UCON_FCLK (3<<10) -#define S3C2443_UCON_EPLL (3<<10) - -#define S3C6400_UCON_CLKMASK (3<<10) -#define S3C6400_UCON_CLKSHIFT (10) -#define S3C6400_UCON_PCLK (0<<10) -#define S3C6400_UCON_PCLK2 (2<<10) -#define S3C6400_UCON_UCLK0 (1<<10) -#define S3C6400_UCON_UCLK1 (3<<10) - -#define S3C2440_UCON2_FCLK_EN (1<<15) -#define S3C2440_UCON0_DIVMASK (15 << 12) -#define S3C2440_UCON1_DIVMASK (15 << 12) -#define S3C2440_UCON2_DIVMASK (7 << 12) -#define S3C2440_UCON_DIVSHIFT (12) - -#define S3C2412_UCON_CLKMASK (3<<10) -#define S3C2412_UCON_CLKSHIFT (10) -#define S3C2412_UCON_UCLK (1<<10) -#define S3C2412_UCON_USYSCLK (3<<10) -#define S3C2412_UCON_PCLK (0<<10) -#define S3C2412_UCON_PCLK2 (2<<10) - -#define S3C2410_UCON_CLKMASK (1 << 10) -#define S3C2410_UCON_CLKSHIFT (10) -#define S3C2410_UCON_UCLK (1<<10) -#define S3C2410_UCON_SBREAK (1<<4) - -#define S3C2410_UCON_TXILEVEL (1<<9) -#define S3C2410_UCON_RXILEVEL (1<<8) -#define S3C2410_UCON_TXIRQMODE (1<<2) -#define S3C2410_UCON_RXIRQMODE (1<<0) -#define S3C2410_UCON_RXFIFO_TOI (1<<7) -#define S3C2443_UCON_RXERR_IRQEN (1<<6) -#define S3C2443_UCON_LOOPBACK (1<<5) - -#define S3C2410_UCON_DEFAULT (S3C2410_UCON_TXILEVEL | \ - S3C2410_UCON_RXILEVEL | \ - S3C2410_UCON_TXIRQMODE | \ - S3C2410_UCON_RXIRQMODE | \ - S3C2410_UCON_RXFIFO_TOI) - -#define S3C2410_UFCON_FIFOMODE (1<<0) -#define S3C2410_UFCON_TXTRIG0 (0<<6) -#define S3C2410_UFCON_RXTRIG8 (1<<4) -#define S3C2410_UFCON_RXTRIG12 (2<<4) - -/* S3C2440 FIFO trigger levels */ -#define S3C2440_UFCON_RXTRIG1 (0<<4) -#define S3C2440_UFCON_RXTRIG8 (1<<4) -#define S3C2440_UFCON_RXTRIG16 (2<<4) -#define S3C2440_UFCON_RXTRIG32 (3<<4) - -#define S3C2440_UFCON_TXTRIG0 (0<<6) -#define S3C2440_UFCON_TXTRIG16 (1<<6) -#define S3C2440_UFCON_TXTRIG32 (2<<6) -#define S3C2440_UFCON_TXTRIG48 (3<<6) - -#define S3C2410_UFCON_RESETBOTH (3<<1) -#define S3C2410_UFCON_RESETTX (1<<2) -#define S3C2410_UFCON_RESETRX (1<<1) - -#define S3C2410_UFCON_DEFAULT (S3C2410_UFCON_FIFOMODE | \ - S3C2410_UFCON_TXTRIG0 | \ - S3C2410_UFCON_RXTRIG8 ) - -#define S3C2410_UMCOM_AFC (1<<4) -#define S3C2410_UMCOM_RTS_LOW (1<<0) - -#define S3C2412_UMCON_AFC_63 (0<<5) /* same as s3c2443 */ -#define S3C2412_UMCON_AFC_56 (1<<5) -#define S3C2412_UMCON_AFC_48 (2<<5) -#define S3C2412_UMCON_AFC_40 (3<<5) -#define S3C2412_UMCON_AFC_32 (4<<5) -#define S3C2412_UMCON_AFC_24 (5<<5) -#define S3C2412_UMCON_AFC_16 (6<<5) -#define S3C2412_UMCON_AFC_8 (7<<5) - -#define S3C2410_UFSTAT_TXFULL (1<<9) -#define S3C2410_UFSTAT_RXFULL (1<<8) -#define S3C2410_UFSTAT_TXMASK (15<<4) -#define S3C2410_UFSTAT_TXSHIFT (4) -#define S3C2410_UFSTAT_RXMASK (15<<0) -#define S3C2410_UFSTAT_RXSHIFT (0) - -/* UFSTAT S3C2443 same as S3C2440 */ -#define S3C2440_UFSTAT_TXFULL (1<<14) -#define S3C2440_UFSTAT_RXFULL (1<<6) -#define S3C2440_UFSTAT_TXSHIFT (8) -#define S3C2440_UFSTAT_RXSHIFT (0) -#define S3C2440_UFSTAT_TXMASK (63<<8) -#define S3C2440_UFSTAT_RXMASK (63) - -#define S3C2410_UTRSTAT_TXE (1<<2) -#define S3C2410_UTRSTAT_TXFE (1<<1) -#define S3C2410_UTRSTAT_RXDR (1<<0) - -#define S3C2410_UERSTAT_OVERRUN (1<<0) -#define S3C2410_UERSTAT_FRAME (1<<2) -#define S3C2410_UERSTAT_BREAK (1<<3) -#define S3C2443_UERSTAT_PARITY (1<<1) - -#define S3C2410_UERSTAT_ANY (S3C2410_UERSTAT_OVERRUN | \ - S3C2410_UERSTAT_FRAME | \ - S3C2410_UERSTAT_BREAK) - -#define S3C2410_UMSTAT_CTS (1<<0) -#define S3C2410_UMSTAT_DeltaCTS (1<<2) - -#define S3C2443_DIVSLOT (0x2C) - -/* S3C64XX interrupt registers. */ -#define S3C64XX_UINTP 0x30 -#define S3C64XX_UINTSP 0x34 -#define S3C64XX_UINTM 0x38 - -#define S3C64XX_UINTM_RXD (0) -#define S3C64XX_UINTM_TXD (2) -#define S3C64XX_UINTM_RXD_MSK (1 << S3C64XX_UINTM_RXD) -#define S3C64XX_UINTM_TXD_MSK (1 << S3C64XX_UINTM_TXD) - -/* Following are specific to S5PV210 */ -#define S5PV210_UCON_CLKMASK (1<<10) -#define S5PV210_UCON_CLKSHIFT (10) -#define S5PV210_UCON_PCLK (0<<10) -#define S5PV210_UCON_UCLK (1<<10) - -#define S5PV210_UFCON_TXTRIG0 (0<<8) -#define S5PV210_UFCON_TXTRIG4 (1<<8) -#define S5PV210_UFCON_TXTRIG8 (2<<8) -#define S5PV210_UFCON_TXTRIG16 (3<<8) -#define S5PV210_UFCON_TXTRIG32 (4<<8) -#define S5PV210_UFCON_TXTRIG64 (5<<8) -#define S5PV210_UFCON_TXTRIG128 (6<<8) -#define S5PV210_UFCON_TXTRIG256 (7<<8) - -#define S5PV210_UFCON_RXTRIG1 (0<<4) -#define S5PV210_UFCON_RXTRIG4 (1<<4) -#define S5PV210_UFCON_RXTRIG8 (2<<4) -#define S5PV210_UFCON_RXTRIG16 (3<<4) -#define S5PV210_UFCON_RXTRIG32 (4<<4) -#define S5PV210_UFCON_RXTRIG64 (5<<4) -#define S5PV210_UFCON_RXTRIG128 (6<<4) -#define S5PV210_UFCON_RXTRIG256 (7<<4) - -#define S5PV210_UFSTAT_TXFULL (1<<24) -#define S5PV210_UFSTAT_RXFULL (1<<8) -#define S5PV210_UFSTAT_TXMASK (255<<16) -#define S5PV210_UFSTAT_TXSHIFT (16) -#define S5PV210_UFSTAT_RXMASK (255<<0) -#define S5PV210_UFSTAT_RXSHIFT (0) - -#define S3C2410_UCON_CLKSEL0 (1 << 0) -#define S3C2410_UCON_CLKSEL1 (1 << 1) -#define S3C2410_UCON_CLKSEL2 (1 << 2) -#define S3C2410_UCON_CLKSEL3 (1 << 3) - -/* Default values for s5pv210 UCON and UFCON uart registers */ -#define S5PV210_UCON_DEFAULT (S3C2410_UCON_TXILEVEL | \ - S3C2410_UCON_RXILEVEL | \ - S3C2410_UCON_TXIRQMODE | \ - S3C2410_UCON_RXIRQMODE | \ - S3C2410_UCON_RXFIFO_TOI | \ - S3C2443_UCON_RXERR_IRQEN) - -#define S5PV210_UFCON_DEFAULT (S3C2410_UFCON_FIFOMODE | \ - S5PV210_UFCON_TXTRIG4 | \ - S5PV210_UFCON_RXTRIG4) - -#ifndef __ASSEMBLY__ - -/* configuration structure for per-machine configurations for the - * serial port - * - * the pointer is setup by the machine specific initialisation from the - * arch/arm/mach-s3c2410/ directory. -*/ - -struct s3c2410_uartcfg { - unsigned char hwport; /* hardware port number */ - unsigned char unused; - unsigned short flags; - upf_t uart_flags; /* default uart flags */ - unsigned int clk_sel; - - unsigned int has_fracval; - - unsigned long ucon; /* value of ucon for port */ - unsigned long ulcon; /* value of ulcon for port */ - unsigned long ufcon; /* value of ufcon for port */ -}; - -/* s3c24xx_uart_devs - * - * this is exported from the core as we cannot use driver_register(), - * or platform_add_device() before the console_initcall() -*/ - -extern struct platform_device *s3c24xx_uart_devs[4]; - -#endif /* __ASSEMBLY__ */ - -#endif /* __ASM_ARM_REGS_SERIAL_H */ - +#include <linux/serial_s3c.h> diff --git a/arch/arm/plat-samsung/include/plat/usb-phy.h b/arch/arm/plat-samsung/include/plat/usb-phy.h index 959bcdb..ab34dfa 100644 --- a/arch/arm/plat-samsung/include/plat/usb-phy.h +++ b/arch/arm/plat-samsung/include/plat/usb-phy.h @@ -11,10 +11,7 @@ #ifndef __PLAT_SAMSUNG_USB_PHY_H #define __PLAT_SAMSUNG_USB_PHY_H __FILE__ -enum s5p_usb_phy_type { - S5P_USB_PHY_DEVICE, - S5P_USB_PHY_HOST, -}; +#include <linux/usb/samsung_usb_phy.h> extern int s5p_usb_phy_init(struct platform_device *pdev, int type); extern int s5p_usb_phy_exit(struct platform_device *pdev, int type); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 0337cdb..83a0ad5 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -84,11 +84,15 @@ EXPORT_SYMBOL_GPL(pm_power_off); void (*pm_restart)(const char *cmd); EXPORT_SYMBOL_GPL(pm_restart); +void arch_cpu_idle_prepare(void) +{ + local_fiq_enable(); +} /* * This is our default idle handler. */ -static void default_idle(void) +void arch_cpu_idle(void) { /* * This should do all the clock switching and wait for interrupt @@ -98,43 +102,6 @@ static void default_idle(void) local_irq_enable(); } -/* - * The idle thread. - * We always respect 'hlt_counter' to prevent low power idle. - */ -void cpu_idle(void) -{ - local_fiq_enable(); - - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - while (!need_resched()) { - /* - * We need to disable interrupts here to ensure - * we don't miss a wakeup call. - */ - local_irq_disable(); - if (!need_resched()) { - stop_critical_timings(); - default_idle(); - start_critical_timings(); - /* - * default_idle functions should always return - * with IRQs enabled. - */ - WARN_ON(irqs_disabled()); - } else { - local_irq_enable(); - } - } - rcu_idle_exit(); - tick_nohz_idle_exit(); - schedule_preempt_disabled(); - } -} - void machine_shutdown(void) { #ifdef CONFIG_SMP diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index bdd3459..261445c 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -216,7 +216,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void) /* * OK, it's off to the idle thread for us */ - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } void __init smp_cpus_done(unsigned int max_cpus) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 800aac3..f497ca7 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -197,24 +197,6 @@ void __init bootmem_init(void) max_pfn = max_low_pfn = max; } -static inline int free_area(unsigned long pfn, unsigned long end, char *s) -{ - unsigned int pages = 0, size = (end - pfn) << (PAGE_SHIFT - 10); - - for (; pfn < end; pfn++) { - struct page *page = pfn_to_page(pfn); - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - pages++; - } - - if (size && s) - pr_info("Freeing %s memory: %dK\n", s, size); - - return pages; -} - /* * Poison init memory with an undefined instruction (0x0). */ @@ -405,9 +387,7 @@ void __init mem_init(void) void free_initmem(void) { poison_init_mem(__init_begin, __init_end - __init_begin); - totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)), - __phys_to_pfn(__pa(__init_end)), - "init"); + free_initmem_default(0); } #ifdef CONFIG_BLK_DEV_INITRD @@ -418,9 +398,7 @@ void free_initrd_mem(unsigned long start, unsigned long end) { if (!keep_initrd) { poison_init_mem((void *)start, PAGE_ALIGN(end) - start); - totalram_pages += free_area(__phys_to_pfn(__pa(start)), - __phys_to_pfn(__pa(end)), - "initrd"); + free_reserved_area(start, end, 0, "initrd"); } } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 70b8cd4..eeecc9c 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -391,17 +391,14 @@ int kern_addr_valid(unsigned long addr) } #ifdef CONFIG_SPARSEMEM_VMEMMAP #ifdef CONFIG_ARM64_64K_PAGES -int __meminit vmemmap_populate(struct page *start_page, - unsigned long size, int node) +int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { - return vmemmap_populate_basepages(start_page, size, node); + return vmemmap_populate_basepages(start, end, node); } #else /* !CONFIG_ARM64_64K_PAGES */ -int __meminit vmemmap_populate(struct page *start_page, - unsigned long size, int node) +int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { - unsigned long addr = (unsigned long)start_page; - unsigned long end = (unsigned long)(start_page + size); + unsigned long addr = start; unsigned long next; pgd_t *pgd; pud_t *pud; @@ -434,7 +431,7 @@ int __meminit vmemmap_populate(struct page *start_page, return 0; } #endif /* CONFIG_ARM64_64K_PAGES */ -void vmemmap_free(struct page *memmap, unsigned long nr_pages) +void vmemmap_free(unsigned long start, unsigned long end) { } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h index cf60d0a..fc6483f 100644 --- a/arch/avr32/include/asm/io.h +++ b/arch/avr32/include/asm/io.h @@ -165,6 +165,10 @@ BUILDIO_IOPORT(l, u32) #define readw_be __raw_readw #define readl_be __raw_readl +#define writeb_relaxed writeb +#define writew_relaxed writew +#define writel_relaxed writel + #define writeb_be __raw_writeb #define writew_be __raw_writew #define writel_be __raw_writel diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index fd78f58..073c3c2 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -30,18 +30,9 @@ EXPORT_SYMBOL(pm_power_off); * This file handles the architecture-dependent parts of process handling.. */ -void cpu_idle(void) +void arch_cpu_idle(void) { - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - while (!need_resched()) - cpu_idle_sleep(); - rcu_idle_exit(); - tick_nohz_idle_exit(); - schedule_preempt_disabled(); - } + cpu_enter_idle(); } void machine_halt(void) diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c index 05ad291..869a1c6 100644 --- a/arch/avr32/kernel/time.c +++ b/arch/avr32/kernel/time.c @@ -12,6 +12,7 @@ #include <linux/irq.h> #include <linux/kernel.h> #include <linux/time.h> +#include <linux/cpu.h> #include <asm/sysreg.h> @@ -87,13 +88,17 @@ static void comparator_mode(enum clock_event_mode mode, pr_debug("%s: start\n", evdev->name); /* FALLTHROUGH */ case CLOCK_EVT_MODE_RESUME: - cpu_disable_idle_sleep(); + /* + * If we're using the COUNT and COMPARE registers we + * need to force idle poll. + */ + cpu_idle_poll_ctrl(true); break; case CLOCK_EVT_MODE_UNUSED: case CLOCK_EVT_MODE_SHUTDOWN: sysreg_write(COMPARE, 0); pr_debug("%s: stop\n", evdev->name); - cpu_enable_idle_sleep(); + cpu_idle_poll_ctrl(false); break; default: BUG(); diff --git a/arch/avr32/mach-at32ap/include/mach/pm.h b/arch/avr32/mach-at32ap/include/mach/pm.h index 979b355..f29ff2c 100644 --- a/arch/avr32/mach-at32ap/include/mach/pm.h +++ b/arch/avr32/mach-at32ap/include/mach/pm.h @@ -21,30 +21,6 @@ extern void cpu_enter_idle(void); extern void cpu_enter_standby(unsigned long sdramc_base); -extern bool disable_idle_sleep; - -static inline void cpu_disable_idle_sleep(void) -{ - disable_idle_sleep = true; -} - -static inline void cpu_enable_idle_sleep(void) -{ - disable_idle_sleep = false; -} - -static inline void cpu_idle_sleep(void) -{ - /* - * If we're using the COUNT and COMPARE registers for - * timekeeping, we can't use the IDLE state. - */ - if (disable_idle_sleep) - cpu_relax(); - else - cpu_enter_idle(); -} - void intc_set_suspend_handler(unsigned long offset); #endif diff --git a/arch/avr32/mach-at32ap/pm-at32ap700x.S b/arch/avr32/mach-at32ap/pm-at32ap700x.S index f868f4c..1c8e4e6 100644 --- a/arch/avr32/mach-at32ap/pm-at32ap700x.S +++ b/arch/avr32/mach-at32ap/pm-at32ap700x.S @@ -18,13 +18,6 @@ /* Same as 0xfff00000 but fits in a 21 bit signed immediate */ #define PM_BASE -0x100000 - .section .bss, "wa", @nobits - .global disable_idle_sleep - .type disable_idle_sleep, @object -disable_idle_sleep: - .int 4 - .size disable_idle_sleep, . - disable_idle_sleep - /* Keep this close to the irq handlers */ .section .irq.text, "ax", @progbits diff --git a/arch/avr32/mm/init.c b/arch/avr32/mm/init.c index 2798c2d..e66e840 100644 --- a/arch/avr32/mm/init.c +++ b/arch/avr32/mm/init.c @@ -146,34 +146,14 @@ void __init mem_init(void) initsize >> 10); } -static inline void free_area(unsigned long addr, unsigned long end, char *s) -{ - unsigned int size = (end - addr) >> 10; - - for (; addr < end; addr += PAGE_SIZE) { - struct page *page = virt_to_page(addr); - ClearPageReserved(page); - init_page_count(page); - free_page(addr); - totalram_pages++; - } - - if (size && s) - printk(KERN_INFO "Freeing %s memory: %dK (%lx - %lx)\n", - s, size, end - (size << 10), end); -} - void free_initmem(void) { - free_area((unsigned long)__init_begin, (unsigned long)__init_end, - "init"); + free_initmem_default(0); } #ifdef CONFIG_BLK_DEV_INITRD - void free_initrd_mem(unsigned long start, unsigned long end) { - free_area(start, end, "initrd"); + free_reserved_area(start, end, 0, "initrd"); } - #endif diff --git a/arch/blackfin/kernel/early_printk.c b/arch/blackfin/kernel/early_printk.c index 84ed837..61fbd2d 100644 --- a/arch/blackfin/kernel/early_printk.c +++ b/arch/blackfin/kernel/early_printk.c @@ -25,8 +25,6 @@ extern struct console *bfin_earlyserial_init(unsigned int port, extern struct console *bfin_jc_early_init(void); #endif -static struct console *early_console; - /* Default console */ #define DEFAULT_PORT 0 #define DEFAULT_CFLAG CS8|B57600 diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index 9782c03..4aa5545 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -46,15 +46,14 @@ EXPORT_SYMBOL(pm_power_off); * The idle loop on BFIN */ #ifdef CONFIG_IDLE_L1 -static void default_idle(void)__attribute__((l1_text)); -void cpu_idle(void)__attribute__((l1_text)); +void arch_cpu_idle(void)__attribute__((l1_text)); #endif /* * This is our default idle handler. We need to disable * interrupts here to ensure we don't miss a wakeup call. */ -static void default_idle(void) +void arch_cpu_idle(void) { #ifdef CONFIG_IPIPE ipipe_suspend_domain(); @@ -66,31 +65,12 @@ static void default_idle(void) hard_local_irq_enable(); } -/* - * The idle thread. We try to conserve power, while trying to keep - * overall latency low. The architecture specific idle is passed - * a value to indicate the level of "idleness" of the system. - */ -void cpu_idle(void) -{ - /* endless idle loop with no priority at all */ - while (1) { - #ifdef CONFIG_HOTPLUG_CPU - if (cpu_is_offline(smp_processor_id())) - cpu_die(); -#endif - tick_nohz_idle_enter(); - rcu_idle_enter(); - while (!need_resched()) - default_idle(); - rcu_idle_exit(); - tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); - } +void arch_cpu_idle_dead(void) +{ + cpu_die(); } +#endif /* * Do necessary setup to start up a newly executed thread. diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index bb61ae4..1bc2ce6 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -335,7 +335,7 @@ void __cpuinit secondary_start_kernel(void) */ calibrate_delay(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } void __init smp_prepare_boot_cpu(void) diff --git a/arch/blackfin/mm/init.c b/arch/blackfin/mm/init.c index 9cb8553..82d01a7 100644 --- a/arch/blackfin/mm/init.c +++ b/arch/blackfin/mm/init.c @@ -103,7 +103,7 @@ void __init mem_init(void) max_mapnr = num_physpages = MAP_NR(high_memory); printk(KERN_DEBUG "Kernel managed physical pages: %lu\n", num_physpages); - /* This will put all memory onto the freelists. */ + /* This will put all low memory onto the freelists. */ totalram_pages = free_all_bootmem(); reservedpages = 0; @@ -129,24 +129,11 @@ void __init mem_init(void) initk, codek, datak, DMA_UNCACHED_REGION >> 10, (reservedpages << (PAGE_SHIFT-10))); } -static void __init free_init_pages(const char *what, unsigned long begin, unsigned long end) -{ - unsigned long addr; - /* next to check that the page we free is not a partial page */ - for (addr = begin; addr + PAGE_SIZE <= end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } - printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10); -} - #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { #ifndef CONFIG_MPU - free_init_pages("initrd memory", start, end); + free_reserved_area(start, end, 0, "initrd"); #endif } #endif @@ -154,10 +141,7 @@ void __init free_initrd_mem(unsigned long start, unsigned long end) void __init_refok free_initmem(void) { #if defined CONFIG_RAMKERNEL && !defined CONFIG_MPU - free_init_pages("unused kernel memory", - (unsigned long)(&__init_begin), - (unsigned long)(&__init_end)); - + free_initmem_default(0); if (memory_start == (unsigned long)(&__init_end)) memory_start = (unsigned long)(&__init_begin); #endif diff --git a/arch/c6x/kernel/process.c b/arch/c6x/kernel/process.c index 6434df4..57d2ea8 100644 --- a/arch/c6x/kernel/process.c +++ b/arch/c6x/kernel/process.c @@ -33,7 +33,7 @@ extern asmlinkage void ret_from_kernel_thread(void); void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); -static void c6x_idle(void) +void arch_cpu_idle(void) { unsigned long tmp; @@ -49,32 +49,6 @@ static void c6x_idle(void) : "=b"(tmp)); } -/* - * The idle loop for C64x - */ -void cpu_idle(void) -{ - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - while (1) { - local_irq_disable(); - if (need_resched()) { - local_irq_enable(); - break; - } - c6x_idle(); /* enables local irqs */ - } - rcu_idle_exit(); - tick_nohz_idle_exit(); - - preempt_enable_no_resched(); - schedule(); - preempt_disable(); - } -} - static void halt_loop(void) { printk(KERN_EMERG "System Halted, OK to turn off power\n"); diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c index 89395f0..a9fcd89 100644 --- a/arch/c6x/mm/init.c +++ b/arch/c6x/mm/init.c @@ -77,37 +77,11 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - int pages = 0; - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - pages++; - } - printk(KERN_INFO "Freeing initrd memory: %luk freed\n", - (pages * PAGE_SIZE) >> 10); + free_reserved_area(start, end, 0, "initrd"); } #endif void __init free_initmem(void) { - unsigned long addr; - - /* - * The following code should be cool even if these sections - * are not page aligned. - */ - addr = PAGE_ALIGN((unsigned long)(__init_begin)); - - /* next to check that the page we free is not a partial page */ - for (; addr + PAGE_SIZE < (unsigned long)(__init_end); - addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } - printk(KERN_INFO "Freeing unused kernel memory: %dK freed\n", - (int) ((addr - PAGE_ALIGN((long) &__init_begin)) >> 10)); + free_initmem_default(0); } diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c index b101875..2ba23c1 100644 --- a/arch/cris/arch-v10/kernel/process.c +++ b/arch/cris/arch-v10/kernel/process.c @@ -30,8 +30,9 @@ void etrax_gpio_wake_up_check(void); /* drivers/gpio.c */ void default_idle(void) { #ifdef CONFIG_ETRAX_GPIO - etrax_gpio_wake_up_check(); + etrax_gpio_wake_up_check(); #endif + local_irq_enable(); } /* diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c index 2b23ef0..57451fa 100644 --- a/arch/cris/arch-v32/kernel/process.c +++ b/arch/cris/arch-v32/kernel/process.c @@ -20,18 +20,12 @@ extern void stop_watchdog(void); -extern int cris_hlt_counter; - /* We use this if we don't have any better idle routine. */ void default_idle(void) { - local_irq_disable(); - if (!need_resched() && !cris_hlt_counter) { - /* Halt until exception. */ - __asm__ volatile("ei \n\t" - "halt "); - } - local_irq_enable(); + /* Halt until exception. */ + __asm__ volatile("ei \n\t" + "halt "); } /* diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c index 04a16ed..cdd1202 100644 --- a/arch/cris/arch-v32/kernel/smp.c +++ b/arch/cris/arch-v32/kernel/smp.c @@ -145,8 +145,6 @@ smp_boot_one_cpu(int cpuid, struct task_struct idle) * specific stuff such as the local timer and the MMU. */ void __init smp_callin(void) { - extern void cpu_idle(void); - int cpu = cpu_now_booting; reg_intr_vect_rw_mask vect_mask = {0}; @@ -170,7 +168,7 @@ void __init smp_callin(void) local_irq_enable(); set_cpu_online(cpu, true); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } /* Stop execution on this CPU.*/ diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h index 675823f..c0a29b9 100644 --- a/arch/cris/include/asm/processor.h +++ b/arch/cris/include/asm/processor.h @@ -65,13 +65,6 @@ static inline void release_thread(struct task_struct *dead_task) #define cpu_relax() barrier() -/* - * disable hlt during certain critical i/o operations - */ -#define HAVE_DISABLE_HLT -void disable_hlt(void); -void enable_hlt(void); - void default_idle(void); #endif /* __ASM_CRIS_PROCESSOR_H */ diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c index 104ff4d..b78498e 100644 --- a/arch/cris/kernel/process.c +++ b/arch/cris/kernel/process.c @@ -29,59 +29,14 @@ //#define DEBUG -/* - * The hlt_counter, disable_hlt and enable_hlt is just here as a hook if - * there would ever be a halt sequence (for power save when idle) with - * some largish delay when halting or resuming *and* a driver that can't - * afford that delay. The hlt_counter would then be checked before - * executing the halt sequence, and the driver marks the unhaltable - * region by enable_hlt/disable_hlt. - */ - -int cris_hlt_counter=0; - -void disable_hlt(void) -{ - cris_hlt_counter++; -} - -EXPORT_SYMBOL(disable_hlt); - -void enable_hlt(void) -{ - cris_hlt_counter--; -} - -EXPORT_SYMBOL(enable_hlt); - extern void default_idle(void); void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ - -void cpu_idle (void) +void arch_cpu_idle(void) { - /* endless idle loop with no priority at all */ - while (1) { - rcu_idle_enter(); - while (!need_resched()) { - /* - * Mark this as an RCU critical section so that - * synchronize_kernel() in the unload path waits - * for our completion. - */ - default_idle(); - } - rcu_idle_exit(); - schedule_preempt_disabled(); - } + default_idle(); } void hard_reset_now (void); diff --git a/arch/cris/mm/init.c b/arch/cris/mm/init.c index d72ab58..9ac8094 100644 --- a/arch/cris/mm/init.c +++ b/arch/cris/mm/init.c @@ -12,12 +12,10 @@ #include <linux/init.h> #include <linux/bootmem.h> #include <asm/tlb.h> +#include <asm/sections.h> unsigned long empty_zero_page; -extern char _stext, _edata, _etext; /* From linkerscript */ -extern char __init_begin, __init_end; - void __init mem_init(void) { @@ -67,15 +65,5 @@ mem_init(void) void free_initmem(void) { - unsigned long addr; - - addr = (unsigned long)(&__init_begin); - for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } - printk (KERN_INFO "Freeing unused kernel memory: %luk freed\n", - (unsigned long)((&__init_end - &__init_begin) >> 10)); + free_initmem_default(0); } diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c index 23916b2..5d40aeb77 100644 --- a/arch/frv/kernel/process.c +++ b/arch/frv/kernel/process.c @@ -59,29 +59,12 @@ static void core_sleep_idle(void) mb(); } -void (*idle)(void) = core_sleep_idle; - -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle(void) +void arch_cpu_idle(void) { - /* endless idle loop with no priority at all */ - while (1) { - rcu_idle_enter(); - while (!need_resched()) { - check_pgt_cache(); - - if (!frv_dma_inprogress && idle) - idle(); - } - rcu_idle_exit(); - - schedule_preempt_disabled(); - } + if (!frv_dma_inprogress) + core_sleep_idle(); + else + local_irq_enable(); } void machine_restart(char * __unused) diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c index 92e97b0..dee354f 100644 --- a/arch/frv/mm/init.c +++ b/arch/frv/mm/init.c @@ -122,7 +122,7 @@ void __init mem_init(void) #endif int codek = 0, datak = 0; - /* this will put all memory onto the freelists */ + /* this will put all low memory onto the freelists */ totalram_pages = free_all_bootmem(); #ifdef CONFIG_MMU @@ -131,14 +131,8 @@ void __init mem_init(void) datapages++; #ifdef CONFIG_HIGHMEM - for (pfn = num_physpages - 1; pfn >= num_mappedpages; pfn--) { - struct page *page = &mem_map[pfn]; - - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - totalram_pages++; - } + for (pfn = num_physpages - 1; pfn >= num_mappedpages; pfn--) + free_highmem_page(&mem_map[pfn]); #endif codek = ((unsigned long) &_etext - (unsigned long) &_stext) >> 10; @@ -168,21 +162,7 @@ void __init mem_init(void) void free_initmem(void) { #if defined(CONFIG_RAMKERNEL) && !defined(CONFIG_PROTECT_KERNEL) - unsigned long start, end, addr; - - start = PAGE_ALIGN((unsigned long) &__init_begin); /* round up */ - end = ((unsigned long) &__init_end) & PAGE_MASK; /* round down */ - - /* next to check that the page we free is not a partial page */ - for (addr = start; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } - - printk("Freeing unused kernel memory: %ldKiB freed (0x%lx - 0x%lx)\n", - (end - start) >> 10, start, end); + free_initmem_default(0); #endif } /* end free_initmem() */ @@ -193,14 +173,6 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - int pages = 0; - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - pages++; - } - printk("Freeing initrd memory: %dKiB freed\n", (pages * PAGE_SIZE) >> 10); + free_reserved_area(start, end, 0, "initrd"); } /* end free_initrd_mem() */ #endif diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index b609f63..a17d2cd 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -53,40 +53,13 @@ asmlinkage void ret_from_kernel_thread(void); * The idle loop on an H8/300.. */ #if !defined(CONFIG_H8300H_SIM) && !defined(CONFIG_H8S_SIM) -static void default_idle(void) +void arch_cpu_idle(void) { - local_irq_disable(); - if (!need_resched()) { - local_irq_enable(); - /* XXX: race here! What if need_resched() gets set now? */ - __asm__("sleep"); - } else - local_irq_enable(); -} -#else -static void default_idle(void) -{ - cpu_relax(); + local_irq_enable(); + /* XXX: race here! What if need_resched() gets set now? */ + __asm__("sleep"); } #endif -void (*idle)(void) = default_idle; - -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle(void) -{ - while (1) { - rcu_idle_enter(); - while (!need_resched()) - idle(); - rcu_idle_exit(); - schedule_preempt_disabled(); - } -} void machine_restart(char * __unused) { diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c index 981e250..ff349d7 100644 --- a/arch/h8300/mm/init.c +++ b/arch/h8300/mm/init.c @@ -139,7 +139,7 @@ void __init mem_init(void) start_mem = PAGE_ALIGN(start_mem); max_mapnr = num_physpages = MAP_NR(high_memory); - /* this will put all memory onto the freelists */ + /* this will put all low memory onto the freelists */ totalram_pages = free_all_bootmem(); codek = (_etext - _stext) >> 10; @@ -161,15 +161,7 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - int pages = 0; - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - pages++; - } - printk ("Freeing initrd memory: %dk freed\n", pages); + free_reserved_area(start, end, 0, "initrd"); } #endif @@ -177,23 +169,7 @@ void free_initmem(void) { #ifdef CONFIG_RAMKERNEL - unsigned long addr; -/* - * the following code should be cool even if these sections - * are not page aligned. - */ - addr = PAGE_ALIGN((unsigned long)(__init_begin)); - /* next to check that the page we free is not a partial page */ - for (; addr + PAGE_SIZE < (unsigned long)__init_end; addr +=PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } - printk(KERN_INFO "Freeing unused kernel memory: %ldk freed (0x%x - 0x%x)\n", - (addr - PAGE_ALIGN((long) __init_begin)) >> 10, - (int)(PAGE_ALIGN((unsigned long)__init_begin)), - (int)(addr - PAGE_SIZE)); + free_initmem_default(0); #endif } diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index 06ae9ff..9b948c6 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -51,28 +51,11 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) * If hardware or VM offer wait termination even though interrupts * are disabled. */ -static void default_idle(void) +void arch_cpu_idle(void) { __vmwait(); -} - -void (*idle_sleep)(void) = default_idle; - -void cpu_idle(void) -{ - while (1) { - tick_nohz_idle_enter(); - local_irq_disable(); - while (!need_resched()) { - idle_sleep(); - /* interrupts wake us up, but aren't serviced */ - local_irq_enable(); /* service interrupt */ - local_irq_disable(); - } - local_irq_enable(); - tick_nohz_idle_exit(); - schedule(); - } + /* interrupts wake us up, but irqs are still disabled */ + local_irq_enable(); } /* diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c index 8e095df..0e364ca 100644 --- a/arch/hexagon/kernel/smp.c +++ b/arch/hexagon/kernel/smp.c @@ -184,7 +184,7 @@ void __cpuinit start_secondary(void) local_irq_enable(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 9a02f71..e7e55a0 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -187,7 +187,7 @@ config IA64_DIG config IA64_DIG_VTD bool "DIG+Intel+IOMMU" - select DMAR + select INTEL_IOMMU select PCI_MSI config IA64_HP_ZX1 diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c index da2f319..e70cade 100644 --- a/arch/ia64/hp/sim/simserial.c +++ b/arch/ia64/hp/sim/simserial.c @@ -142,8 +142,7 @@ static void transmit_chars(struct tty_struct *tty, struct serial_state *info, goto out; } - if (info->xmit.head == info->xmit.tail || tty->stopped || - tty->hw_stopped) { + if (info->xmit.head == info->xmit.tail || tty->stopped) { #ifdef SIMSERIAL_DEBUG printk("transmit_chars: head=%d, tail=%d, stopped=%d\n", info->xmit.head, info->xmit.tail, tty->stopped); @@ -181,7 +180,7 @@ static void rs_flush_chars(struct tty_struct *tty) struct serial_state *info = tty->driver_data; if (info->xmit.head == info->xmit.tail || tty->stopped || - tty->hw_stopped || !info->xmit.buf) + !info->xmit.buf) return; transmit_chars(tty, info, NULL); @@ -217,7 +216,7 @@ static int rs_write(struct tty_struct * tty, * Hey, we transmit directly from here in our case */ if (CIRC_CNT(info->xmit.head, info->xmit.tail, SERIAL_XMIT_SIZE) && - !tty->stopped && !tty->hw_stopped) + !tty->stopped) transmit_chars(tty, info, NULL); return ret; @@ -325,14 +324,6 @@ static int rs_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) #define RELEVANT_IFLAG(iflag) (iflag & (IGNBRK|BRKINT|IGNPAR|PARMRK|INPCK)) -static void rs_set_termios(struct tty_struct *tty, struct ktermios *old_termios) -{ - /* Handle turning off CRTSCTS */ - if ((old_termios->c_cflag & CRTSCTS) && - !(tty->termios.c_cflag & CRTSCTS)) { - tty->hw_stopped = 0; - } -} /* * This routine will shutdown a serial port; interrupts are disabled, and * DTR is dropped if the hangup on close termio flag is on. @@ -481,7 +472,6 @@ static const struct tty_operations hp_ops = { .throttle = rs_throttle, .unthrottle = rs_unthrottle, .send_xchar = rs_send_xchar, - .set_termios = rs_set_termios, .hangup = rs_hangup, .proc_fops = &rs_proc_fops, }; diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h index d2bf1fd..76acbcd 100644 --- a/arch/ia64/include/asm/futex.h +++ b/arch/ia64/include/asm/futex.h @@ -106,16 +106,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, return -EFAULT; { - register unsigned long r8 __asm ("r8"); + register unsigned long r8 __asm ("r8") = 0; unsigned long prev; __asm__ __volatile__( " mf;; \n" - " mov %0=r0 \n" " mov ar.ccv=%4;; \n" "[1:] cmpxchg4.acq %1=[%2],%3,ar.ccv \n" " .xdata4 \"__ex_table\", 1b-., 2f-. \n" "[2:]" - : "=r" (r8), "=r" (prev) + : "+r" (r8), "=&r" (prev) : "r" (uaddr), "r" (newval), "rO" ((long) (unsigned) oldval) : "memory"); diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h index 94eaa5b..aa91005 100644 --- a/arch/ia64/include/asm/hugetlb.h +++ b/arch/ia64/include/asm/hugetlb.h @@ -2,6 +2,7 @@ #define _ASM_IA64_HUGETLB_H #include <asm/page.h> +#include <asm-generic/hugetlb.h> void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, diff --git a/arch/ia64/include/asm/irqflags.h b/arch/ia64/include/asm/irqflags.h index 2b68d85..1bf2cf2 100644 --- a/arch/ia64/include/asm/irqflags.h +++ b/arch/ia64/include/asm/irqflags.h @@ -89,6 +89,7 @@ static inline bool arch_irqs_disabled(void) static inline void arch_safe_halt(void) { + arch_local_irq_enable(); ia64_pal_halt_light(); /* PAL_HALT_LIGHT */ } diff --git a/arch/ia64/include/asm/mca.h b/arch/ia64/include/asm/mca.h index 43f96ab..8c70961 100644 --- a/arch/ia64/include/asm/mca.h +++ b/arch/ia64/include/asm/mca.h @@ -143,6 +143,7 @@ extern unsigned long __per_cpu_mca[NR_CPUS]; extern int cpe_vector; extern int ia64_cpe_irq; extern void ia64_mca_init(void); +extern void ia64_mca_irq_init(void); extern void ia64_mca_cpu_init(void *); extern void ia64_os_mca_dispatch(void); extern void ia64_os_mca_dispatch_end(void); diff --git a/arch/ia64/include/asm/numa.h b/arch/ia64/include/asm/numa.h index 2e27ef1..2db0a6c 100644 --- a/arch/ia64/include/asm/numa.h +++ b/arch/ia64/include/asm/numa.h @@ -67,14 +67,13 @@ extern int paddr_to_nid(unsigned long paddr); extern void map_cpu_to_node(int cpu, int nid); extern void unmap_cpu_from_node(int cpu, int nid); - +extern void numa_clear_node(int cpu); #else /* !CONFIG_NUMA */ #define map_cpu_to_node(cpu, nid) do{}while(0) #define unmap_cpu_from_node(cpu, nid) do{}while(0) - #define paddr_to_nid(addr) 0 - +#define numa_clear_node(cpu) do { } while (0) #endif /* CONFIG_NUMA */ #endif /* _ASM_IA64_NUMA_H */ diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index 020d655..cade13d 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -131,8 +131,6 @@ struct thread_info { #define TS_POLLING 1 /* true if in idle loop and not sleeping */ #define TS_RESTORE_SIGMASK 2 /* restore signal mask in do_signal() */ -#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING) - #ifndef __ASSEMBLY__ #define HAVE_SET_RESTORE_SIGMASK 1 static inline void set_restore_sigmask(void) diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S index c4cd45d..abc6dee 100644 --- a/arch/ia64/kernel/fsys.S +++ b/arch/ia64/kernel/fsys.S @@ -90,53 +90,6 @@ ENTRY(fsys_getpid) FSYS_RETURN END(fsys_getpid) -ENTRY(fsys_getppid) - .prologue - .altrp b6 - .body - add r17=IA64_TASK_GROUP_LEADER_OFFSET,r16 - ;; - ld8 r17=[r17] // r17 = current->group_leader - add r9=TI_FLAGS+IA64_TASK_SIZE,r16 - ;; - - ld4 r9=[r9] - add r17=IA64_TASK_REAL_PARENT_OFFSET,r17 // r17 = ¤t->group_leader->real_parent - ;; - and r9=TIF_ALLWORK_MASK,r9 - -1: ld8 r18=[r17] // r18 = current->group_leader->real_parent - ;; - cmp.ne p8,p0=0,r9 - add r8=IA64_TASK_TGID_OFFSET,r18 // r8 = ¤t->group_leader->real_parent->tgid - ;; - - /* - * The .acq is needed to ensure that the read of tgid has returned its data before - * we re-check "real_parent". - */ - ld4.acq r8=[r8] // r8 = current->group_leader->real_parent->tgid -#ifdef CONFIG_SMP - /* - * Re-read current->group_leader->real_parent. - */ - ld8 r19=[r17] // r19 = current->group_leader->real_parent -(p8) br.spnt.many fsys_fallback_syscall - ;; - cmp.ne p6,p0=r18,r19 // did real_parent change? - mov r19=0 // i must not leak kernel bits... -(p6) br.cond.spnt.few 1b // yes -> redo the read of tgid and the check - ;; - mov r17=0 // i must not leak kernel bits... - mov r18=0 // i must not leak kernel bits... -#else - mov r17=0 // i must not leak kernel bits... - mov r18=0 // i must not leak kernel bits... - mov r19=0 // i must not leak kernel bits... -#endif - FSYS_RETURN -END(fsys_getppid) - ENTRY(fsys_set_tid_address) .prologue .altrp b6 @@ -614,7 +567,7 @@ paravirt_fsyscall_table: data8 0 // chown data8 0 // lseek // 1040 data8 fsys_getpid // getpid - data8 fsys_getppid // getppid + data8 0 // getppid data8 0 // mount data8 0 // umount data8 0 // setuid // 1045 diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index ee33c3a..19f107b 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -76,7 +76,7 @@ * PCI pin -> global system interrupt (GSI) -> IA-64 vector <-> IRQ * * Note: The term "IRQ" is loosely used everywhere in Linux kernel to - * describeinterrupts. Now we use "IRQ" only for Linux IRQ's. ISA IRQ + * describe interrupts. Now we use "IRQ" only for Linux IRQ's. ISA IRQ * (isa_irq) is the only exception in this source code. */ @@ -1010,6 +1010,26 @@ iosapic_check_gsi_range (unsigned int gsi_base, unsigned int ver) return 0; } +static int +iosapic_delete_rte(unsigned int irq, unsigned int gsi) +{ + struct iosapic_rte_info *rte, *temp; + + list_for_each_entry_safe(rte, temp, &iosapic_intr_info[irq].rtes, + rte_list) { + if (rte->iosapic->gsi_base + rte->rte_index == gsi) { + if (rte->refcnt) + return -EBUSY; + + list_del(&rte->rte_list); + kfree(rte); + return 0; + } + } + + return -EINVAL; +} + int iosapic_init(unsigned long phys_addr, unsigned int gsi_base) { int num_rte, err, index; @@ -1069,7 +1089,7 @@ int iosapic_init(unsigned long phys_addr, unsigned int gsi_base) int iosapic_remove(unsigned int gsi_base) { - int index, err = 0; + int i, irq, index, err = 0; unsigned long flags; spin_lock_irqsave(&iosapic_lock, flags); @@ -1087,6 +1107,16 @@ int iosapic_remove(unsigned int gsi_base) goto out; } + for (i = gsi_base; i < gsi_base + iosapic_lists[index].num_rte; i++) { + irq = __gsi_to_irq(i); + if (irq < 0) + continue; + + err = iosapic_delete_rte(irq, i); + if (err) + goto out; + } + iounmap(iosapic_lists[index].addr); iosapic_free(index); out: diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c index ad69606..f2c41828 100644 --- a/arch/ia64/kernel/irq.c +++ b/arch/ia64/kernel/irq.c @@ -23,6 +23,8 @@ #include <linux/interrupt.h> #include <linux/kernel_stat.h> +#include <asm/mca.h> + /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -83,6 +85,12 @@ bool is_affinity_mask_valid(const struct cpumask *cpumask) #endif /* CONFIG_SMP */ +int __init arch_early_irq_init(void) +{ + ia64_mca_irq_init(); + return 0; +} + #ifdef CONFIG_HOTPLUG_CPU unsigned int vectors_in_migration[NR_IRQS]; diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 65bf9cd..d7396db 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -2074,22 +2074,16 @@ ia64_mca_init(void) printk(KERN_INFO "MCA related initialization done\n"); } + /* - * ia64_mca_late_init - * - * Opportunity to setup things that require initialization later - * than ia64_mca_init. Setup a timer to poll for CPEs if the - * platform doesn't support an interrupt driven mechanism. - * - * Inputs : None - * Outputs : Status + * These pieces cannot be done in ia64_mca_init() because it is called before + * early_irq_init() which would wipe out our percpu irq registrations. But we + * cannot leave them until ia64_mca_late_init() because by then all the other + * processors have been brought online and have set their own CMC vectors to + * point at a non-existant action. Called from arch_early_irq_init(). */ -static int __init -ia64_mca_late_init(void) +void __init ia64_mca_irq_init(void) { - if (!mca_init) - return 0; - /* * Configure the CMCI/P vector and handler. Interrupts for CMC are * per-processor, so AP CMC interrupts are setup in smp_callin() (smpboot.c). @@ -2108,6 +2102,23 @@ ia64_mca_late_init(void) /* Setup the CPEI/P handler */ register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction); #endif +} + +/* + * ia64_mca_late_init + * + * Opportunity to setup things that require initialization later + * than ia64_mca_init. Setup a timer to poll for CPEs if the + * platform doesn't support an interrupt driven mechanism. + * + * Inputs : None + * Outputs : Status + */ +static int __init +ia64_mca_late_init(void) +{ + if (!mca_init) + return 0; register_hotcpu_notifier(&mca_cpu_notifier); diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index 9392e02..94f8bf7 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -349,7 +349,7 @@ init_record_index_pools(void) /* - 3 - */ slidx_pool.max_idx = (rec_max_size/sect_min_size) * 2 + 1; - slidx_pool.buffer = (slidx_list_t *) + slidx_pool.buffer = kmalloc(slidx_pool.max_idx * sizeof(slidx_list_t), GFP_KERNEL); return slidx_pool.buffer ? 0 : -ENOMEM; diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 2eda284..9ea25fc 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -42,6 +42,7 @@ #include <linux/completion.h> #include <linux/tracehook.h> #include <linux/slab.h> +#include <linux/cpu.h> #include <asm/errno.h> #include <asm/intrinsics.h> @@ -1322,8 +1323,6 @@ out: } EXPORT_SYMBOL(pfm_unregister_buffer_fmt); -extern void update_pal_halt_status(int); - static int pfm_reserve_session(struct task_struct *task, int is_syswide, unsigned int cpu) { @@ -1371,9 +1370,9 @@ pfm_reserve_session(struct task_struct *task, int is_syswide, unsigned int cpu) cpu)); /* - * disable default_idle() to go to PAL_HALT + * Force idle() into poll mode */ - update_pal_halt_status(0); + cpu_idle_poll_ctrl(true); UNLOCK_PFS(flags); @@ -1430,11 +1429,8 @@ pfm_unreserve_session(pfm_context_t *ctx, int is_syswide, unsigned int cpu) is_syswide, cpu)); - /* - * if possible, enable default_idle() to go into PAL_HALT - */ - if (pfm_sessions.pfs_task_sessions == 0 && pfm_sessions.pfs_sys_sessions == 0) - update_pal_halt_status(1); + /* Undo forced polling. Last session reenables pal_halt */ + cpu_idle_poll_ctrl(false); UNLOCK_PFS(flags); diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 6f7dc8b..a26fc64 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -209,41 +209,13 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall) local_irq_disable(); /* force interrupt disable */ } -static int pal_halt = 1; -static int can_do_pal_halt = 1; - static int __init nohalt_setup(char * str) { - pal_halt = can_do_pal_halt = 0; + cpu_idle_poll_ctrl(true); return 1; } __setup("nohalt", nohalt_setup); -void -update_pal_halt_status(int status) -{ - can_do_pal_halt = pal_halt && status; -} - -/* - * We use this if we don't have any better idle routine.. - */ -void -default_idle (void) -{ - local_irq_enable(); - while (!need_resched()) { - if (can_do_pal_halt) { - local_irq_disable(); - if (!need_resched()) { - safe_halt(); - } - local_irq_enable(); - } else - cpu_relax(); - } -} - #ifdef CONFIG_HOTPLUG_CPU /* We don't actually take CPU down, just spin without interrupts. */ static inline void play_dead(void) @@ -270,47 +242,29 @@ static inline void play_dead(void) } #endif /* CONFIG_HOTPLUG_CPU */ -void __attribute__((noreturn)) -cpu_idle (void) +void arch_cpu_idle_dead(void) +{ + play_dead(); +} + +void arch_cpu_idle(void) { void (*mark_idle)(int) = ia64_mark_idle; - int cpu = smp_processor_id(); - - /* endless idle loop with no priority at all */ - while (1) { - rcu_idle_enter(); - if (can_do_pal_halt) { - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - } else { - current_thread_info()->status |= TS_POLLING; - } - if (!need_resched()) { #ifdef CONFIG_SMP - min_xtp(); + min_xtp(); #endif - rmb(); - if (mark_idle) - (*mark_idle)(1); + rmb(); + if (mark_idle) + (*mark_idle)(1); + + safe_halt(); - default_idle(); - if (mark_idle) - (*mark_idle)(0); + if (mark_idle) + (*mark_idle)(0); #ifdef CONFIG_SMP - normal_xtp(); + normal_xtp(); #endif - } - rcu_idle_exit(); - schedule_preempt_disabled(); - check_pgt_cache(); - if (cpu_is_offline(cpu)) - play_dead(); - } } void diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 500f1e4..8d87168 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -455,7 +455,7 @@ start_secondary (void *unused) preempt_disable(); smp_callin(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); return 0; } diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c index 4332f7e..a7869f8 100644 --- a/arch/ia64/kvm/vtlb.c +++ b/arch/ia64/kvm/vtlb.c @@ -256,7 +256,7 @@ u64 guest_vhpt_lookup(u64 iha, u64 *pte) "srlz.d;;" "ssm psr.i;;" "srlz.d;;" - : "=r"(ret) : "r"(iha), "r"(pte):"memory"); + : "=&r"(ret) : "r"(iha), "r"(pte) : "memory"); return ret; } diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 80dab50..67c59eb 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -47,6 +47,8 @@ void show_mem(unsigned int filter) printk(KERN_INFO "Mem-info:\n"); show_free_areas(filter); printk(KERN_INFO "Node memory in pages:\n"); + if (filter & SHOW_MEM_FILTER_PAGE_COUNT) + return; for_each_online_pgdat(pgdat) { unsigned long present; unsigned long flags; diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index c2e955e..ae4db4b 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -623,6 +623,8 @@ void show_mem(unsigned int filter) printk(KERN_INFO "Mem-info:\n"); show_free_areas(filter); + if (filter & SHOW_MEM_FILTER_PAGE_COUNT) + return; printk(KERN_INFO "Node memory in pages:\n"); for_each_online_pgdat(pgdat) { unsigned long present; @@ -817,13 +819,12 @@ void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat) #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP -int __meminit vmemmap_populate(struct page *start_page, - unsigned long size, int node) +int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { - return vmemmap_populate_basepages(start_page, size, node); + return vmemmap_populate_basepages(start, end, node); } -void vmemmap_free(struct page *memmap, unsigned long nr_pages) +void vmemmap_free(unsigned long start, unsigned long end) { } #endif diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 20bc967..d1fe4b4 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -154,25 +154,14 @@ ia64_init_addr_space (void) void free_initmem (void) { - unsigned long addr, eaddr; - - addr = (unsigned long) ia64_imva(__init_begin); - eaddr = (unsigned long) ia64_imva(__init_end); - while (addr < eaddr) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - ++totalram_pages; - addr += PAGE_SIZE; - } - printk(KERN_INFO "Freeing unused kernel memory: %ldkB freed\n", - (__init_end - __init_begin) >> 10); + free_reserved_area((unsigned long)ia64_imva(__init_begin), + (unsigned long)ia64_imva(__init_end), + 0, "unused kernel"); } void __init free_initrd_mem (unsigned long start, unsigned long end) { - struct page *page; /* * EFI uses 4KB pages while the kernel can use 4KB or bigger. * Thus EFI and the kernel may have different page sizes. It is @@ -213,11 +202,7 @@ free_initrd_mem (unsigned long start, unsigned long end) for (; start < end; start += PAGE_SIZE) { if (!virt_addr_valid(start)) continue; - page = virt_to_page(start); - ClearPageReserved(page); - init_page_count(page); - free_page(start); - ++totalram_pages; + free_reserved_page(virt_to_page(start)); } } diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c index 3dccdd8..43964cd 100644 --- a/arch/ia64/mm/ioremap.c +++ b/arch/ia64/mm/ioremap.c @@ -16,7 +16,7 @@ #include <asm/meminit.h> static inline void __iomem * -__ioremap (unsigned long phys_addr) +__ioremap_uc(unsigned long phys_addr) { return (void __iomem *) (__IA64_UNCACHED_OFFSET | phys_addr); } @@ -24,7 +24,11 @@ __ioremap (unsigned long phys_addr) void __iomem * early_ioremap (unsigned long phys_addr, unsigned long size) { - return __ioremap(phys_addr); + u64 attr; + attr = kern_mem_attribute(phys_addr, size); + if (attr & EFI_MEMORY_WB) + return (void __iomem *) phys_to_virt(phys_addr); + return __ioremap_uc(phys_addr); } void __iomem * @@ -47,7 +51,7 @@ ioremap (unsigned long phys_addr, unsigned long size) if (attr & EFI_MEMORY_WB) return (void __iomem *) phys_to_virt(phys_addr); else if (attr & EFI_MEMORY_UC) - return __ioremap(phys_addr); + return __ioremap_uc(phys_addr); /* * Some chipsets don't support UC access to memory. If @@ -93,7 +97,7 @@ ioremap (unsigned long phys_addr, unsigned long size) return (void __iomem *) (offset + (char __iomem *)addr); } - return __ioremap(phys_addr); + return __ioremap_uc(phys_addr); } EXPORT_SYMBOL(ioremap); @@ -103,7 +107,7 @@ ioremap_nocache (unsigned long phys_addr, unsigned long size) if (kern_mem_attribute(phys_addr, size) & EFI_MEMORY_WB) return NULL; - return __ioremap(phys_addr); + return __ioremap_uc(phys_addr); } EXPORT_SYMBOL(ioremap_nocache); diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index 3efea7d..4248492 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -61,18 +61,36 @@ paddr_to_nid(unsigned long paddr) int __meminit __early_pfn_to_nid(unsigned long pfn) { int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec; + /* + * NOTE: The following SMP-unsafe globals are only used early in boot + * when the kernel is running single-threaded. + */ + static int __meminitdata last_ssec, last_esec; + static int __meminitdata last_nid; + + if (section >= last_ssec && section < last_esec) + return last_nid; for (i = 0; i < num_node_memblks; i++) { ssec = node_memblk[i].start_paddr >> PA_SECTION_SHIFT; esec = (node_memblk[i].start_paddr + node_memblk[i].size + ((1L << PA_SECTION_SHIFT) - 1)) >> PA_SECTION_SHIFT; - if (section >= ssec && section < esec) + if (section >= ssec && section < esec) { + last_ssec = ssec; + last_esec = esec; + last_nid = node_memblk[i].nid; return node_memblk[i].nid; + } } return -1; } +void __cpuinit numa_clear_node(int cpu) +{ + unmap_cpu_from_node(cpu, NUMA_NO_NODE); +} + #ifdef CONFIG_MEMORY_HOTPLUG /* * SRAT information is stored in node_memblk[], then we can use SRAT diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index 60532ab..de1474f 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -15,6 +15,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/pci.h> +#include <linux/pci-acpi.h> #include <linux/init.h> #include <linux/ioport.h> #include <linux/slab.h> @@ -458,6 +459,16 @@ void pcibios_fixup_bus(struct pci_bus *b) platform_pci_fixup_bus(b); } +void pcibios_add_bus(struct pci_bus *bus) +{ + acpi_pci_add_bus(bus); +} + +void pcibios_remove_bus(struct pci_bus *bus) +{ + acpi_pci_remove_bus(bus); +} + void pcibios_set_master (struct pci_dev *dev) { /* No special bus mastering setup handling */ diff --git a/arch/ia64/sn/kernel/tiocx.c b/arch/ia64/sn/kernel/tiocx.c index 14c1711..e35f648 100644 --- a/arch/ia64/sn/kernel/tiocx.c +++ b/arch/ia64/sn/kernel/tiocx.c @@ -490,11 +490,14 @@ static int __init tiocx_init(void) { cnodeid_t cnodeid; int found_tiocx_device = 0; + int err; if (!ia64_platform_is("sn2")) return 0; - bus_register(&tiocx_bus_type); + err = bus_register(&tiocx_bus_type); + if (err) + return err; for (cnodeid = 0; cnodeid < num_cnodes; cnodeid++) { nasid_t nasid; diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index bde899e..e2d0490 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -47,24 +47,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk) void (*pm_power_off)(void) = NULL; EXPORT_SYMBOL(pm_power_off); -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle (void) -{ - /* endless idle loop with no priority at all */ - while (1) { - rcu_idle_enter(); - while (!need_resched()) - cpu_relax(); - rcu_idle_exit(); - schedule_preempt_disabled(); - } -} - void machine_restart(char *__unused) { #if defined(CONFIG_PLAT_MAPPI3) diff --git a/arch/m32r/kernel/smpboot.c b/arch/m32r/kernel/smpboot.c index 13168a7..0ac558a 100644 --- a/arch/m32r/kernel/smpboot.c +++ b/arch/m32r/kernel/smpboot.c @@ -432,7 +432,7 @@ int __init start_secondary(void *unused) */ local_flush_tlb_all(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); return 0; } diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c index 78b660e..ab4cbce 100644 --- a/arch/m32r/mm/init.c +++ b/arch/m32r/mm/init.c @@ -28,10 +28,7 @@ #include <asm/mmu_context.h> #include <asm/setup.h> #include <asm/tlb.h> - -/* References to section boundaries */ -extern char _text, _etext, _edata; -extern char __init_begin, __init_end; +#include <asm/sections.h> pgd_t swapper_pg_dir[1024]; @@ -184,17 +181,7 @@ void __init mem_init(void) *======================================================================*/ void free_initmem(void) { - unsigned long addr; - - addr = (unsigned long)(&__init_begin); - for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } - printk (KERN_INFO "Freeing unused kernel memory: %dk freed\n", \ - (int)(&__init_end - &__init_begin) >> 10); + free_initmem_default(0); } #ifdef CONFIG_BLK_DEV_INITRD @@ -204,13 +191,6 @@ void free_initmem(void) *======================================================================*/ void free_initrd_mem(unsigned long start, unsigned long end) { - unsigned long p; - for (p = start; p < end; p += PAGE_SIZE) { - ClearPageReserved(virt_to_page(p)); - init_page_count(virt_to_page(p)); - free_page(p); - totalram_pages++; - } - printk (KERN_INFO "Freeing initrd memory: %ldk freed\n", (end - start) >> 10); + free_reserved_area(start, end, 0, "initrd"); } #endif diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index d538694..c55ff71 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -51,40 +51,16 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return sw->retpc; } -/* - * The idle loop on an m68k.. - */ -static void default_idle(void) +void arch_cpu_idle(void) { - if (!need_resched()) #if defined(MACH_ATARI_ONLY) - /* block out HSYNC on the atari (falcon) */ - __asm__("stop #0x2200" : : : "cc"); + /* block out HSYNC on the atari (falcon) */ + __asm__("stop #0x2200" : : : "cc"); #else - __asm__("stop #0x2000" : : : "cc"); + __asm__("stop #0x2000" : : : "cc"); #endif } -void (*idle)(void) = default_idle; - -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle(void) -{ - /* endless idle loop with no priority at all */ - while (1) { - rcu_idle_enter(); - while (!need_resched()) - idle(); - rcu_idle_exit(); - schedule_preempt_disabled(); - } -} - void machine_restart(char * __unused) { if (mach_reset) diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 519aad8..1af2ca3 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -110,18 +110,7 @@ void __init paging_init(void) void free_initmem(void) { #ifndef CONFIG_MMU_SUN3 - unsigned long addr; - - addr = (unsigned long) __init_begin; - for (; addr < ((unsigned long) __init_end); addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } - pr_notice("Freeing unused kernel memory: %luk freed (0x%x - 0x%x)\n", - (addr - (unsigned long) __init_begin) >> 10, - (unsigned int) __init_begin, (unsigned int) __init_end); + free_initmem_default(0); #endif /* CONFIG_MMU_SUN3 */ } @@ -213,15 +202,6 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - int pages = 0; - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - pages++; - } - pr_notice("Freeing initrd memory: %dk freed\n", - pages << (PAGE_SHIFT - 10)); + free_reserved_area(start, end, 0, "initrd"); } #endif diff --git a/arch/metag/include/asm/thread_info.h b/arch/metag/include/asm/thread_info.h index 0ecd34d..7c4a330 100644 --- a/arch/metag/include/asm/thread_info.h +++ b/arch/metag/include/asm/thread_info.h @@ -150,6 +150,4 @@ static inline int kstack_end(void *addr) #define _TIF_WORK_MASK (_TIF_ALLWORK_MASK & ~(_TIF_SYSCALL_TRACE | \ _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP)) -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) - #endif /* _ASM_THREAD_INFO_H */ diff --git a/arch/metag/kernel/process.c b/arch/metag/kernel/process.c index c6efe62..dc59235 100644 --- a/arch/metag/kernel/process.c +++ b/arch/metag/kernel/process.c @@ -22,6 +22,7 @@ #include <linux/pm.h> #include <linux/syscalls.h> #include <linux/uaccess.h> +#include <linux/smp.h> #include <asm/core_reg.h> #include <asm/user_gateway.h> #include <asm/tcm.h> @@ -31,7 +32,7 @@ /* * Wait for the next interrupt and enable local interrupts */ -static inline void arch_idle(void) +void arch_cpu_idle(void) { int tmp; @@ -59,36 +60,12 @@ static inline void arch_idle(void) : "r" (get_trigger_mask())); } -void cpu_idle(void) -{ - set_thread_flag(TIF_POLLING_NRFLAG); - - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - - while (!need_resched()) { - /* - * We need to disable interrupts here to ensure we don't - * miss a wakeup call. - */ - local_irq_disable(); - if (!need_resched()) { #ifdef CONFIG_HOTPLUG_CPU - if (cpu_is_offline(smp_processor_id())) - cpu_die(); -#endif - arch_idle(); - } else { - local_irq_enable(); - } - } - - rcu_idle_exit(); - tick_nohz_idle_exit(); - schedule_preempt_disabled(); - } +void arch_cpu_idle_dead(void) +{ + cpu_die(); } +#endif void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c index 4b6d1f14..4de8fc8 100644 --- a/arch/metag/kernel/smp.c +++ b/arch/metag/kernel/smp.c @@ -297,7 +297,7 @@ asmlinkage void secondary_start_kernel(void) /* * OK, it's off to the idle thread for us */ - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } void __init smp_cpus_done(unsigned int max_cpus) diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c index 504a398..d05b845 100644 --- a/arch/metag/mm/init.c +++ b/arch/metag/mm/init.c @@ -380,14 +380,8 @@ void __init mem_init(void) #ifdef CONFIG_HIGHMEM unsigned long tmp; - for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) { - struct page *page = pfn_to_page(tmp); - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - totalhigh_pages++; - } - totalram_pages += totalhigh_pages; + for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) + free_highmem_page(pfn_to_page(tmp)); num_physpages += totalhigh_pages; #endif /* CONFIG_HIGHMEM */ @@ -412,32 +406,15 @@ void __init mem_init(void) return; } -static void free_init_pages(char *what, unsigned long begin, unsigned long end) -{ - unsigned long addr; - - for (addr = begin; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE); - free_page(addr); - totalram_pages++; - } - pr_info("Freeing %s: %luk freed\n", what, (end - begin) >> 10); -} - void free_initmem(void) { - free_init_pages("unused kernel memory", - (unsigned long)(&__init_begin), - (unsigned long)(&__init_end)); + free_initmem_default(POISON_FREE_INITMEM); } #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - end = end & PAGE_MASK; - free_init_pages("initrd memory", start, end); + free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd"); } #endif diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 1323fa2..a827057 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -26,6 +26,7 @@ config MICROBLAZE select GENERIC_CPU_DEVICES select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS + select GENERIC_IDLE_POLL_SETUP select MODULES_USE_ELF_RELA select CLONE_BACKWARDS diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h index 0759153..d6e0ffe 100644 --- a/arch/microblaze/include/asm/processor.h +++ b/arch/microblaze/include/asm/processor.h @@ -22,7 +22,6 @@ extern const struct seq_operations cpuinfo_op; # define cpu_relax() barrier() -# define cpu_sleep() do {} while (0) #define task_pt_regs(tsk) \ (((struct pt_regs *)(THREAD_SIZE + task_stack_page(tsk))) - 1) @@ -160,10 +159,6 @@ unsigned long get_wchan(struct task_struct *p); # define STACK_TOP TASK_SIZE # define STACK_TOP_MAX STACK_TOP -void disable_hlt(void); -void enable_hlt(void); -void default_idle(void); - #ifdef CONFIG_DEBUG_FS extern struct dentry *of_debugfs_root; #endif diff --git a/arch/microblaze/include/asm/setup.h b/arch/microblaze/include/asm/setup.h index 0e0b0a5..f05df56 100644 --- a/arch/microblaze/include/asm/setup.h +++ b/arch/microblaze/include/asm/setup.h @@ -46,7 +46,6 @@ void machine_shutdown(void); void machine_halt(void); void machine_power_off(void); -void free_init_pages(char *what, unsigned long begin, unsigned long end); extern void *alloc_maybe_bootmem(size_t size, gfp_t mask); extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h index 008f304..de26ea6 100644 --- a/arch/microblaze/include/asm/thread_info.h +++ b/arch/microblaze/include/asm/thread_info.h @@ -182,7 +182,6 @@ static inline bool test_and_clear_restore_sigmask(void) ti->status &= ~TS_RESTORE_SIGMASK; return true; } -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) #endif #endif /* __KERNEL__ */ diff --git a/arch/microblaze/kernel/early_printk.c b/arch/microblaze/kernel/early_printk.c index 60dcacc..365f2d5 100644 --- a/arch/microblaze/kernel/early_printk.c +++ b/arch/microblaze/kernel/early_printk.c @@ -21,7 +21,6 @@ #include <asm/setup.h> #include <asm/prom.h> -static u32 early_console_initialized; static u32 base_addr; #ifdef CONFIG_SERIAL_UARTLITE_CONSOLE @@ -109,27 +108,11 @@ static struct console early_serial_uart16550_console = { }; #endif /* CONFIG_SERIAL_8250_CONSOLE */ -static struct console *early_console; - -void early_printk(const char *fmt, ...) -{ - char buf[512]; - int n; - va_list ap; - - if (early_console_initialized) { - va_start(ap, fmt); - n = vscnprintf(buf, 512, fmt, ap); - early_console->write(early_console, buf, n); - va_end(ap); - } -} - int __init setup_early_printk(char *opt) { int version = 0; - if (early_console_initialized) + if (early_console) return 1; base_addr = of_early_console(&version); @@ -159,7 +142,6 @@ int __init setup_early_printk(char *opt) } register_console(early_console); - early_console_initialized = 1; return 0; } return 1; @@ -169,7 +151,7 @@ int __init setup_early_printk(char *opt) * only for early console because of performance degression */ void __init remap_early_printk(void) { - if (!early_console_initialized || !early_console) + if (!early_console) return; pr_info("early_printk_console remapping from 0x%x to ", base_addr); base_addr = (u32) ioremap(base_addr, PAGE_SIZE); @@ -194,9 +176,9 @@ void __init remap_early_printk(void) void __init disable_early_printk(void) { - if (!early_console_initialized || !early_console) + if (!early_console) return; pr_warn("disabling early console\n"); unregister_console(early_console); - early_console_initialized = 0; + early_console = NULL; } diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index fa0ea60..7cce2e9 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -44,71 +44,6 @@ void show_regs(struct pt_regs *regs) void (*pm_power_off)(void) = NULL; EXPORT_SYMBOL(pm_power_off); -static int hlt_counter = 1; - -void disable_hlt(void) -{ - hlt_counter++; -} -EXPORT_SYMBOL(disable_hlt); - -void enable_hlt(void) -{ - hlt_counter--; -} -EXPORT_SYMBOL(enable_hlt); - -static int __init nohlt_setup(char *__unused) -{ - hlt_counter = 1; - return 1; -} -__setup("nohlt", nohlt_setup); - -static int __init hlt_setup(char *__unused) -{ - hlt_counter = 0; - return 1; -} -__setup("hlt", hlt_setup); - -void default_idle(void) -{ - if (likely(hlt_counter)) { - local_irq_disable(); - stop_critical_timings(); - cpu_relax(); - start_critical_timings(); - local_irq_enable(); - } else { - clear_thread_flag(TIF_POLLING_NRFLAG); - smp_mb__after_clear_bit(); - local_irq_disable(); - while (!need_resched()) - cpu_sleep(); - local_irq_enable(); - set_thread_flag(TIF_POLLING_NRFLAG); - } -} - -void cpu_idle(void) -{ - set_thread_flag(TIF_POLLING_NRFLAG); - - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - while (!need_resched()) - default_idle(); - rcu_idle_exit(); - tick_nohz_idle_exit(); - - schedule_preempt_disabled(); - check_pgt_cache(); - } -} - void flush_thread(void) { } diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 8f8b367..4ec137d 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -82,13 +82,9 @@ static unsigned long highmem_setup(void) /* FIXME not sure about */ if (memblock_is_reserved(pfn << PAGE_SHIFT)) continue; - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - totalhigh_pages++; + free_highmem_page(page); reservedpages++; } - totalram_pages += totalhigh_pages; pr_info("High memory: %luk\n", totalhigh_pages << (PAGE_SHIFT-10)); @@ -236,40 +232,16 @@ void __init setup_memory(void) paging_init(); } -void free_init_pages(char *what, unsigned long begin, unsigned long end) -{ - unsigned long addr; - - for (addr = begin; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } - pr_info("Freeing %s: %ldk freed\n", what, (end - begin) >> 10); -} - #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - int pages = 0; - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - pages++; - } - pr_notice("Freeing initrd memory: %dk freed\n", - (int)(pages * (PAGE_SIZE / 1024))); + free_reserved_area(start, end, 0, "initrd"); } #endif void free_initmem(void) { - free_init_pages("unused kernel memory", - (unsigned long)(&__init_begin), - (unsigned long)(&__init_end)); + free_initmem_default(0); } void __init mem_init(void) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 51244bf..3a7b395 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -404,6 +404,8 @@ config PMC_MSP select IRQ_CPU select SERIAL_8250 select SERIAL_8250_CONSOLE + select USB_EHCI_BIG_ENDIAN_MMIO + select USB_EHCI_BIG_ENDIAN_DESC help This adds support for the PMC-Sierra family of Multi-Service Processor System-On-A-Chips. These parts include a number @@ -1433,6 +1435,7 @@ config CPU_CAVIUM_OCTEON select CPU_SUPPORTS_HUGEPAGES select LIBFDT select USE_OF + select USB_EHCI_BIG_ENDIAN_MMIO help The Cavium Octeon processor is a highly integrated chip containing many ethernet hardware widgets for networking tasks. The processor diff --git a/arch/mips/bcm63xx/dev-spi.c b/arch/mips/bcm63xx/dev-spi.c index f1c9c3e..e97fd60 100644 --- a/arch/mips/bcm63xx/dev-spi.c +++ b/arch/mips/bcm63xx/dev-spi.c @@ -85,20 +85,9 @@ static struct platform_device bcm63xx_spi_device = { int __init bcm63xx_spi_register(void) { - struct clk *periph_clk; - if (BCMCPU_IS_6328() || BCMCPU_IS_6345()) return -ENODEV; - periph_clk = clk_get(NULL, "periph"); - if (IS_ERR(periph_clk)) { - pr_err("unable to get periph clock\n"); - return -ENODEV; - } - - /* Set bus frequency */ - spi_pdata.speed_hz = clk_get_rate(periph_clk); - spi_resources[0].start = bcm63xx_regset_address(RSET_SPI); spi_resources[0].end = spi_resources[0].start; spi_resources[1].start = bcm63xx_get_irq_number(IRQ_SPI); diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h index ef99db9..fe0d15d 100644 --- a/arch/mips/include/asm/hugetlb.h +++ b/arch/mips/include/asm/hugetlb.h @@ -10,6 +10,7 @@ #define __ASM_HUGETLB_H #include <asm/page.h> +#include <asm-generic/hugetlb.h> static inline int is_hugepage_only_range(struct mm_struct *mm, diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h index c9bae13..b0184cf 100644 --- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h +++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h @@ -13,7 +13,6 @@ struct bcm63xx_spi_pdata { unsigned int msg_ctl_width; int bus_num; int num_chipselect; - u32 speed_hz; }; enum bcm63xx_regs_spi { diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index 99fc547..eab99e5 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -31,7 +31,7 @@ #define PAGE_SHIFT 16 #endif #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE - 1)) +#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1)) #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT #define HPAGE_SHIFT (PAGE_SHIFT + PAGE_SHIFT - 3) diff --git a/arch/mips/kernel/early_printk.c b/arch/mips/kernel/early_printk.c index 9e6440e..505cb77 100644 --- a/arch/mips/kernel/early_printk.c +++ b/arch/mips/kernel/early_printk.c @@ -7,7 +7,9 @@ * Copyright (C) 2007 MIPS Technologies, Inc. * written by Ralf Baechle (ralf@linux-mips.org) */ +#include <linux/kernel.h> #include <linux/console.h> +#include <linux/printk.h> #include <linux/init.h> #include <asm/setup.h> @@ -24,20 +26,18 @@ static void early_console_write(struct console *con, const char *s, unsigned n) } } -static struct console early_console = { +static struct console early_console_prom = { .name = "early", .write = early_console_write, .flags = CON_PRINTBUFFER | CON_BOOT, .index = -1 }; -static int early_console_initialized __initdata; - void __init setup_early_printk(void) { - if (early_console_initialized) + if (early_console) return; - early_console_initialized = 1; + early_console = &early_console_prom; - register_console(&early_console); + register_console(&early_console_prom); } diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 3be4405..cfc742d 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -41,44 +41,26 @@ #include <asm/inst.h> #include <asm/stacktrace.h> -/* - * The idle thread. There's no useful work to be done, so just try to conserve - * power and have a low exit latency (ie sit in a loop waiting for somebody to - * say that they'd like to reschedule) - */ -void __noreturn cpu_idle(void) +#ifdef CONFIG_HOTPLUG_CPU +void arch_cpu_idle_dead(void) { - int cpu; - - /* CPU is going idle. */ - cpu = smp_processor_id(); + /* What the heck is this check doing ? */ + if (!cpu_isset(smp_processor_id(), cpu_callin_map)) + play_dead(); +} +#endif - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - while (!need_resched() && cpu_online(cpu)) { +void arch_cpu_idle(void) +{ #ifdef CONFIG_MIPS_MT_SMTC - extern void smtc_idle_loop_hook(void); + extern void smtc_idle_loop_hook(void); - smtc_idle_loop_hook(); + smtc_idle_loop_hook(); #endif - - if (cpu_wait) { - /* Don't trace irqs off for idle */ - stop_critical_timings(); - (*cpu_wait)(); - start_critical_timings(); - } - } -#ifdef CONFIG_HOTPLUG_CPU - if (!cpu_online(cpu) && !cpu_isset(cpu, cpu_callin_map)) - play_dead(); -#endif - rcu_idle_exit(); - tick_nohz_idle_exit(); - schedule_preempt_disabled(); - } + if (cpu_wait) + (*cpu_wait)(); + else + local_irq_enable(); } asmlinkage void ret_from_fork(void); diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 66bf4e2..aee04af 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -139,7 +139,7 @@ asmlinkage __cpuinit void start_secondary(void) WARN_ON_ONCE(!irqs_disabled()); mp_ops->smp_finish(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } /* diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 6792925..3d0346d 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -77,10 +77,9 @@ EXPORT_SYMBOL_GPL(empty_zero_page); /* * Not static inline because used by IP27 special magic initialization code */ -unsigned long setup_zero_pages(void) +void setup_zero_pages(void) { - unsigned int order; - unsigned long size; + unsigned int order, i; struct page *page; if (cpu_has_vce) @@ -94,15 +93,10 @@ unsigned long setup_zero_pages(void) page = virt_to_page((void *)empty_zero_page); split_page(page, order); - while (page < virt_to_page((void *)(empty_zero_page + (PAGE_SIZE << order)))) { - SetPageReserved(page); - page++; - } - - size = PAGE_SIZE << order; - zero_page_mask = (size - 1) & PAGE_MASK; + for (i = 0; i < (1 << order); i++, page++) + mark_page_reserved(page); - return 1UL << order; + zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK; } #ifdef CONFIG_MIPS_MT_SMTC @@ -380,7 +374,7 @@ void __init mem_init(void) high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); totalram_pages += free_all_bootmem(); - totalram_pages -= setup_zero_pages(); /* Setup zeroed pages. */ + setup_zero_pages(); /* Setup zeroed pages. */ reservedpages = ram = 0; for (tmp = 0; tmp < max_low_pfn; tmp++) @@ -399,12 +393,8 @@ void __init mem_init(void) SetPageReserved(page); continue; } - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - totalhigh_pages++; + free_highmem_page(page); } - totalram_pages += totalhigh_pages; num_physpages += totalhigh_pages; #endif @@ -440,11 +430,8 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end) struct page *page = pfn_to_page(pfn); void *addr = phys_to_virt(PFN_PHYS(pfn)); - ClearPageReserved(page); - init_page_count(page); memset(addr, POISON_FREE_INITMEM, PAGE_SIZE); - __free_page(page); - totalram_pages++; + free_reserved_page(page); } printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10); } @@ -452,18 +439,14 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_init_pages("initrd memory", - virt_to_phys((void *)start), - virt_to_phys((void *)end)); + free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd"); } #endif void __init_refok free_initmem(void) { prom_free_prom_memory(); - free_init_pages("unused kernel memory", - __pa_symbol(&__init_begin), - __pa_symbol(&__init_end)); + free_initmem_default(POISON_FREE_INITMEM); } #ifndef CONFIG_MIPS_PGD_C0_CONTEXT diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index 0872f12..594e60d 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -115,7 +115,6 @@ static void pcibios_scanbus(struct pci_controller *hose) pci_bus_assign_resources(bus); pci_enable_bridges(bus); } - bus->dev.of_node = hose->of_node; } } @@ -169,6 +168,13 @@ void pci_load_of_ranges(struct pci_controller *hose, struct device_node *node) } } } + +struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + + return of_node_get(hose->of_node); +} #endif static DEFINE_MUTEX(pci_scan_mutex); diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index 3505d08..5f2bddb 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -457,7 +457,7 @@ void __init prom_free_prom_memory(void) /* We got nothing to free here ... */ } -extern unsigned long setup_zero_pages(void); +extern void setup_zero_pages(void); void __init paging_init(void) { @@ -492,7 +492,7 @@ void __init mem_init(void) totalram_pages += free_all_bootmem_node(NODE_DATA(node)); } - totalram_pages -= setup_zero_pages(); /* This comes from node 0 */ + setup_zero_pages(); /* This comes from node 0 */ codesize = (unsigned long) &_etext - (unsigned long) &_text; datasize = (unsigned long) &_edata - (unsigned long) &_etext; diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h index f90062b..224b426 100644 --- a/arch/mn10300/include/asm/thread_info.h +++ b/arch/mn10300/include/asm/thread_info.h @@ -165,8 +165,6 @@ void arch_release_thread_info(struct thread_info *ti); #define _TIF_WORK_MASK 0x0000FFFE /* work to do on interrupt/exception return */ #define _TIF_ALLWORK_MASK 0x0000FFFF /* work to do on any return to u-space */ -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) - #endif /* __KERNEL__ */ #endif /* _ASM_THREAD_INFO_H */ diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 84f4e97..2da39fb 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -50,77 +50,19 @@ unsigned long thread_saved_pc(struct task_struct *tsk) void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); -#if !defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) -/* - * we use this if we don't have any better idle routine - */ -static void default_idle(void) -{ - local_irq_disable(); - if (!need_resched()) - safe_halt(); - else - local_irq_enable(); -} - -#else /* !CONFIG_SMP || CONFIG_HOTPLUG_CPU */ /* * On SMP it's slightly faster (but much more power-consuming!) * to poll the ->work.need_resched flag instead of waiting for the * cross-CPU IPI to arrive. Use this option with caution. + * + * tglx: No idea why this depends on HOTPLUG_CPU !?! */ -static inline void poll_idle(void) -{ - int oldval; - - local_irq_enable(); - - /* - * Deal with another CPU just having chosen a thread to - * run here: - */ - oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED); - - if (!oldval) { - set_thread_flag(TIF_POLLING_NRFLAG); - while (!need_resched()) - cpu_relax(); - clear_thread_flag(TIF_POLLING_NRFLAG); - } else { - set_need_resched(); - } -} -#endif /* !CONFIG_SMP || CONFIG_HOTPLUG_CPU */ - -/* - * the idle thread - * - there's no useful work to be done, so just try to conserve power and have - * a low exit latency (ie sit in a loop waiting for somebody to say that - * they'd like to reschedule) - */ -void cpu_idle(void) +#if !defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) +void arch_cpu_idle(void) { - /* endless idle loop with no priority at all */ - for (;;) { - rcu_idle_enter(); - while (!need_resched()) { - void (*idle)(void); - - smp_rmb(); - if (!idle) { -#if defined(CONFIG_SMP) && !defined(CONFIG_HOTPLUG_CPU) - idle = poll_idle; -#else /* CONFIG_SMP && !CONFIG_HOTPLUG_CPU */ - idle = default_idle; -#endif /* CONFIG_SMP && !CONFIG_HOTPLUG_CPU */ - } - idle(); - } - rcu_idle_exit(); - - schedule_preempt_disabled(); - } + safe_halt(); } +#endif void release_segments(struct mm_struct *mm) { diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c index 5d7e152..a17f9c9 100644 --- a/arch/mn10300/kernel/smp.c +++ b/arch/mn10300/kernel/smp.c @@ -675,7 +675,7 @@ int __init start_secondary(void *unused) #ifdef CONFIG_GENERIC_CLOCKEVENTS init_clockevents(); #endif - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); return 0; } @@ -935,8 +935,6 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) int timeout; #ifdef CONFIG_HOTPLUG_CPU - if (num_online_cpus() == 1) - disable_hlt(); if (sleep_mode[cpu]) run_wakeup_cpu(cpu); #endif /* CONFIG_HOTPLUG_CPU */ @@ -1003,9 +1001,6 @@ int __cpu_disable(void) void __cpu_die(unsigned int cpu) { run_sleep_cpu(cpu); - - if (num_online_cpus() == 1) - enable_hlt(); } #ifdef CONFIG_MN10300_CACHE_ENABLED diff --git a/arch/mn10300/mm/init.c b/arch/mn10300/mm/init.c index e57e5bc..5a8ace6 100644 --- a/arch/mn10300/mm/init.c +++ b/arch/mn10300/mm/init.c @@ -139,30 +139,11 @@ void __init mem_init(void) } /* - * - */ -void free_init_pages(char *what, unsigned long begin, unsigned long end) -{ - unsigned long addr; - - for (addr = begin; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - memset((void *) addr, 0xcc, PAGE_SIZE); - free_page(addr); - totalram_pages++; - } - printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10); -} - -/* * recycle memory containing stuff only required for initialisation */ void free_initmem(void) { - free_init_pages("unused kernel memory", - (unsigned long) &__init_begin, - (unsigned long) &__init_end); + free_initmem_default(POISON_FREE_INITMEM); } /* @@ -171,6 +152,6 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_init_pages("initrd memory", start, end); + free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd"); } #endif diff --git a/arch/openrisc/include/asm/thread_info.h b/arch/openrisc/include/asm/thread_info.h index 07f3212..d797acc 100644 --- a/arch/openrisc/include/asm/thread_info.h +++ b/arch/openrisc/include/asm/thread_info.h @@ -128,8 +128,6 @@ register struct thread_info *current_thread_info_reg asm("r10"); /* For OpenRISC, this is anything in the LSW other than syscall trace */ #define _TIF_WORK_MASK (0xff & ~(_TIF_SYSCALL_TRACE|_TIF_SINGLESTEP)) -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) - #endif /* __KERNEL__ */ #endif /* _ASM_THREAD_INFO_H */ diff --git a/arch/openrisc/kernel/Makefile b/arch/openrisc/kernel/Makefile index 35f92ce..ec6d9d3 100644 --- a/arch/openrisc/kernel/Makefile +++ b/arch/openrisc/kernel/Makefile @@ -4,7 +4,7 @@ extra-y := head.o vmlinux.lds -obj-y := setup.o idle.o or32_ksyms.o process.o dma.o \ +obj-y := setup.o or32_ksyms.o process.o dma.o \ traps.o time.o irq.o entry.o ptrace.o signal.o \ sys_call_table.o diff --git a/arch/openrisc/kernel/idle.c b/arch/openrisc/kernel/idle.c deleted file mode 100644 index 5e8a3b6..0000000 --- a/arch/openrisc/kernel/idle.c +++ /dev/null @@ -1,73 +0,0 @@ -/* - * OpenRISC idle.c - * - * Linux architectural port borrowing liberally from similar works of - * others. All original copyrights apply as per the original source - * declaration. - * - * Modifications for the OpenRISC architecture: - * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> - * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> - * - * 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. - * - * Idle daemon for or32. Idle daemon will handle any action - * that needs to be taken when the system becomes idle. - */ - -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/smp.h> -#include <linux/stddef.h> -#include <linux/unistd.h> -#include <linux/ptrace.h> -#include <linux/slab.h> -#include <linux/tick.h> - -#include <asm/pgtable.h> -#include <asm/uaccess.h> -#include <asm/io.h> -#include <asm/processor.h> -#include <asm/mmu.h> -#include <asm/cache.h> -#include <asm/pgalloc.h> - -void (*powersave) (void) = NULL; - -void cpu_idle(void) -{ - set_thread_flag(TIF_POLLING_NRFLAG); - - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - - while (!need_resched()) { - check_pgt_cache(); - rmb(); - - clear_thread_flag(TIF_POLLING_NRFLAG); - - local_irq_disable(); - /* Don't trace irqs off for idle */ - stop_critical_timings(); - if (!need_resched() && powersave != NULL) - powersave(); - start_critical_timings(); - local_irq_enable(); - set_thread_flag(TIF_POLLING_NRFLAG); - } - - rcu_idle_exit(); - tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); - } -} diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index e7fdc50..b3cbc67 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -43,6 +43,7 @@ #include <asm/kmap_types.h> #include <asm/fixmap.h> #include <asm/tlbflush.h> +#include <asm/sections.h> int mem_init_done; @@ -201,9 +202,6 @@ void __init paging_init(void) /* References to section boundaries */ -extern char _stext, _etext, _edata, __bss_start, _end; -extern char __init_begin, __init_end; - static int __init free_pages_init(void) { int reservedpages, pfn; @@ -263,30 +261,11 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - printk(KERN_INFO "Freeing initrd memory: %ldk freed\n", - (end - start) >> 10); - - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - } + free_reserved_area(start, end, 0, "initrd"); } #endif void free_initmem(void) { - unsigned long addr; - - addr = (unsigned long)(&__init_begin); - for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } - printk(KERN_INFO "Freeing unused kernel memory: %luk freed\n", - ((unsigned long)&__init_end - - (unsigned long)&__init_begin) >> 10); + free_initmem_default(0); } diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 01d95e2..113e282 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -65,8 +65,10 @@ ifndef CONFIG_FUNCTION_TRACER endif # Use long jumps instead of long branches (needed if your linker fails to -# link a too big vmlinux executable) -cflags-$(CONFIG_MLONGCALLS) += -mlong-calls +# link a too big vmlinux executable). Not enabled for building modules. +ifdef CONFIG_MLONGCALLS +KBUILD_CFLAGS_KERNEL += -mlong-calls +endif # select which processor to optimise for cflags-$(CONFIG_PA7100) += -march=1.1 -mschedule=7100 diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 79f694f..f0e2784 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -140,7 +140,10 @@ static inline void *kmap(struct page *page) return page_address(page); } -#define kunmap(page) kunmap_parisc(page_address(page)) +static inline void kunmap(struct page *page) +{ + kunmap_parisc(page_address(page)); +} static inline void *kmap_atomic(struct page *page) { diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 7df49fa..1e40d7f 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -16,6 +16,8 @@ #include <asm/processor.h> #include <asm/cache.h> +extern spinlock_t pa_dbit_lock; + /* * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel * memory. For the return value to be meaningful, ADDR must be >= @@ -44,8 +46,11 @@ extern void purge_tlb_entries(struct mm_struct *, unsigned long); #define set_pte_at(mm, addr, ptep, pteval) \ do { \ + unsigned long flags; \ + spin_lock_irqsave(&pa_dbit_lock, flags); \ set_pte(ptep, pteval); \ purge_tlb_entries(mm, addr); \ + spin_unlock_irqrestore(&pa_dbit_lock, flags); \ } while (0) #endif /* !__ASSEMBLY__ */ @@ -435,48 +440,46 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *); static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { -#ifdef CONFIG_SMP + pte_t pte; + unsigned long flags; + if (!pte_young(*ptep)) return 0; - return test_and_clear_bit(xlate_pabit(_PAGE_ACCESSED_BIT), &pte_val(*ptep)); -#else - pte_t pte = *ptep; - if (!pte_young(pte)) + + spin_lock_irqsave(&pa_dbit_lock, flags); + pte = *ptep; + if (!pte_young(pte)) { + spin_unlock_irqrestore(&pa_dbit_lock, flags); return 0; - set_pte_at(vma->vm_mm, addr, ptep, pte_mkold(pte)); + } + set_pte(ptep, pte_mkold(pte)); + purge_tlb_entries(vma->vm_mm, addr); + spin_unlock_irqrestore(&pa_dbit_lock, flags); return 1; -#endif } -extern spinlock_t pa_dbit_lock; - struct mm_struct; static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t old_pte; + unsigned long flags; - spin_lock(&pa_dbit_lock); + spin_lock_irqsave(&pa_dbit_lock, flags); old_pte = *ptep; pte_clear(mm,addr,ptep); - spin_unlock(&pa_dbit_lock); + purge_tlb_entries(mm, addr); + spin_unlock_irqrestore(&pa_dbit_lock, flags); return old_pte; } static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { -#ifdef CONFIG_SMP - unsigned long new, old; - - do { - old = pte_val(*ptep); - new = pte_val(pte_wrprotect(__pte (old))); - } while (cmpxchg((unsigned long *) ptep, old, new) != old); + unsigned long flags; + spin_lock_irqsave(&pa_dbit_lock, flags); + set_pte(ptep, pte_wrprotect(*ptep)); purge_tlb_entries(mm, addr); -#else - pte_t old_pte = *ptep; - set_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); -#endif + spin_unlock_irqrestore(&pa_dbit_lock, flags); } #define pte_same(A,B) (pte_val(A) == pte_val(B)) diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h index d1fb79a..6182832 100644 --- a/arch/parisc/include/asm/thread_info.h +++ b/arch/parisc/include/asm/thread_info.h @@ -77,8 +77,6 @@ struct thread_info { #define _TIF_SYSCALL_TRACE_MASK (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | \ _TIF_BLOCKSTEP) -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) - #endif /* __KERNEL__ */ #endif /* _ASM_PARISC_THREAD_INFO_H */ diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 4ba2c93..e0a8235 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -181,30 +181,24 @@ struct exception_data { #if !defined(CONFIG_64BIT) #define __put_kernel_asm64(__val,ptr) do { \ - u64 __val64 = (u64)(__val); \ - u32 hi = (__val64) >> 32; \ - u32 lo = (__val64) & 0xffffffff; \ __asm__ __volatile__ ( \ "\n1:\tstw %2,0(%1)" \ - "\n2:\tstw %3,4(%1)\n\t" \ + "\n2:\tstw %R2,4(%1)\n\t" \ ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_2)\ ASM_EXCEPTIONTABLE_ENTRY(2b,fixup_put_user_skip_1)\ : "=r"(__pu_err) \ - : "r"(ptr), "r"(hi), "r"(lo), "0"(__pu_err) \ + : "r"(ptr), "r"(__val), "0"(__pu_err) \ : "r1"); \ } while (0) #define __put_user_asm64(__val,ptr) do { \ - u64 __val64 = (u64)(__val); \ - u32 hi = (__val64) >> 32; \ - u32 lo = (__val64) & 0xffffffff; \ __asm__ __volatile__ ( \ "\n1:\tstw %2,0(%%sr3,%1)" \ - "\n2:\tstw %3,4(%%sr3,%1)\n\t" \ + "\n2:\tstw %R2,4(%%sr3,%1)\n\t" \ ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_2)\ ASM_EXCEPTIONTABLE_ENTRY(2b,fixup_put_user_skip_1)\ : "=r"(__pu_err) \ - : "r"(ptr), "r"(hi), "r"(lo), "0"(__pu_err) \ + : "r"(ptr), "r"(__val), "0"(__pu_err) \ : "r1"); \ } while (0) diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 4b12890..83ded26 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -421,14 +421,11 @@ void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) /* Note: purge_tlb_entries can be called at startup with no context. */ - /* Disable preemption while we play with %sr1. */ - preempt_disable(); - mtsp(mm->context, 1); purge_tlb_start(flags); + mtsp(mm->context, 1); pdtlb(addr); pitlb(addr); purge_tlb_end(flags); - preempt_enable(); } EXPORT_SYMBOL(purge_tlb_entries); diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 6795dc6..568b2c6 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -120,11 +120,13 @@ extern void __ashrdi3(void); extern void __ashldi3(void); extern void __lshrdi3(void); extern void __muldi3(void); +extern void __ucmpdi2(void); EXPORT_SYMBOL(__ashrdi3); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__lshrdi3); EXPORT_SYMBOL(__muldi3); +EXPORT_SYMBOL(__ucmpdi2); asmlinkage void * __canonicalize_funcptr_for_compare(void *); EXPORT_SYMBOL(__canonicalize_funcptr_for_compare); diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index d135072..55f92b6 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -59,28 +59,6 @@ #include <asm/unwind.h> #include <asm/sections.h> -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle(void) -{ - set_thread_flag(TIF_POLLING_NRFLAG); - - /* endless idle loop with no priority at all */ - while (1) { - rcu_idle_enter(); - while (!need_resched()) - barrier(); - rcu_idle_exit(); - schedule_preempt_disabled(); - check_pgt_cache(); - } -} - - #define COMMAND_GLOBAL F_EXTEND(0xfffe0030) #define CMD_RESET 5 /* reset any module */ diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 6266730..fd1bb15 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -329,7 +329,7 @@ void __init smp_callin(void) local_irq_enable(); /* Interrupts have been off until now */ - cpu_idle(); /* Wait for timer to schedule some work */ + cpu_startup_entry(CPUHP_ONLINE); /* NOTREACHED */ panic("smp_callin() AAAAaaaaahhhh....\n"); diff --git a/arch/parisc/lib/Makefile b/arch/parisc/lib/Makefile index 5f2e690..5651536 100644 --- a/arch/parisc/lib/Makefile +++ b/arch/parisc/lib/Makefile @@ -2,6 +2,7 @@ # Makefile for parisc-specific library files # -lib-y := lusercopy.o bitops.o checksum.o io.o memset.o fixup.o memcpy.o +lib-y := lusercopy.o bitops.o checksum.o io.o memset.o fixup.o memcpy.o \ + ucmpdi2.o obj-y := iomap.o diff --git a/arch/parisc/lib/ucmpdi2.c b/arch/parisc/lib/ucmpdi2.c new file mode 100644 index 0000000..149c016 --- /dev/null +++ b/arch/parisc/lib/ucmpdi2.c @@ -0,0 +1,25 @@ +#include <linux/module.h> + +union ull_union { + unsigned long long ull; + struct { + unsigned int high; + unsigned int low; + } ui; +}; + +int __ucmpdi2(unsigned long long a, unsigned long long b) +{ + union ull_union au = {.ull = a}; + union ull_union bu = {.ull = b}; + + if (au.ui.high < bu.ui.high) + return 0; + else if (au.ui.high > bu.ui.high) + return 2; + if (au.ui.low < bu.ui.low) + return 0; + else if (au.ui.low > bu.ui.low) + return 2; + return 1; +} diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 3ac462d..157b931 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -505,7 +505,6 @@ static void __init map_pages(unsigned long start_vaddr, void free_initmem(void) { - unsigned long addr; unsigned long init_begin = (unsigned long)__init_begin; unsigned long init_end = (unsigned long)__init_end; @@ -533,19 +532,10 @@ void free_initmem(void) * pages are no-longer executable */ flush_icache_range(init_begin, init_end); - for (addr = init_begin; addr < init_end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - num_physpages++; - totalram_pages++; - } + num_physpages += free_initmem_default(0); /* set up a new led state on systems shipped LED State panel */ pdc_chassis_send_status(PDC_CHASSIS_DIRECT_BCOMPLETE); - - printk(KERN_INFO "Freeing unused kernel memory: %luk freed\n", - (init_end - init_begin) >> 10); } @@ -697,6 +687,8 @@ void show_mem(unsigned int filter) printk(KERN_INFO "Mem-info:\n"); show_free_areas(filter); + if (filter & SHOW_MEM_FILTER_PAGE_COUNT) + return; #ifndef CONFIG_DISCONTIGMEM i = max_mapnr; while (i-- > 0) { @@ -1107,15 +1099,6 @@ void flush_tlb_all(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - if (start >= end) - return; - printk(KERN_INFO "Freeing initrd memory: %ldk freed\n", (end - start) >> 10); - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - num_physpages++; - totalram_pages++; - } + num_physpages += free_reserved_area(start, end, 0, "initrd"); } #endif diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 62e11a3..4fcbd6b 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -3,6 +3,7 @@ #ifdef CONFIG_HUGETLB_PAGE #include <asm/page.h> +#include <asm-generic/hugetlb.h> extern struct kmem_cache *hugepte_cache; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 406b7b9..8ceea14 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -182,8 +182,6 @@ static inline bool test_thread_local_flags(unsigned int flags) #define is_32bit_task() (1) #endif -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) - #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h index b532060..2301602 100644 --- a/arch/powerpc/include/asm/uprobes.h +++ b/arch/powerpc/include/asm/uprobes.h @@ -51,4 +51,5 @@ extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data); extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs); +extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs); #endif /* _ASM_UPROBES_H */ diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index b3ba516..9ec3fe1 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -150,10 +150,7 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end) if (addr <= rtas_end && ((addr + PAGE_SIZE) > rtas_start)) continue; - ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT)); - init_page_count(pfn_to_page(addr >> PAGE_SHIFT)); - free_page((unsigned long)__va(addr)); - totalram_pages++; + free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT)); } } #endif diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 256c5bf..04d69c4 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -304,7 +304,7 @@ syscall_exit_work: subi r12,r12,TI_FLAGS 4: /* Anything else left to do? */ - SET_DEFAULT_THREAD_PPR(r3, r9) /* Set thread.ppr = 3 */ + SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */ andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) beq .ret_from_except_lite @@ -657,7 +657,7 @@ resume_kernel: /* Clear _TIF_EMULATE_STACK_STORE flag */ lis r11,_TIF_EMULATE_STACK_STORE@h addi r5,r9,TI_FLAGS - ldarx r4,0,r5 +0: ldarx r4,0,r5 andc r4,r4,r11 stdcx. r4,0,r5 bne- 0b diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 06c8202..2230fd0 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -1045,10 +1045,7 @@ static void fadump_release_memory(unsigned long begin, unsigned long end) if (addr <= ra_end && ((addr + PAGE_SIZE) > ra_start)) continue; - ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT)); - init_page_count(pfn_to_page(addr >> PAGE_SHIFT)); - free_page((unsigned long)__va(addr)); - totalram_pages++; + free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT)); } } diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index ea78761..939ea7e 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -33,11 +33,6 @@ #include <asm/runlatch.h> #include <asm/smp.h> -#ifdef CONFIG_HOTPLUG_CPU -#define cpu_should_die() cpu_is_offline(smp_processor_id()) -#else -#define cpu_should_die() 0 -#endif unsigned long cpuidle_disable = IDLE_NO_OVERRIDE; EXPORT_SYMBOL(cpuidle_disable); @@ -50,64 +45,38 @@ static int __init powersave_off(char *arg) } __setup("powersave=off", powersave_off); -/* - * The body of the idle task. - */ -void cpu_idle(void) +#ifdef CONFIG_HOTPLUG_CPU +void arch_cpu_idle_dead(void) { - set_thread_flag(TIF_POLLING_NRFLAG); - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - - while (!need_resched() && !cpu_should_die()) { - ppc64_runlatch_off(); - - if (ppc_md.power_save) { - clear_thread_flag(TIF_POLLING_NRFLAG); - /* - * smp_mb is so clearing of TIF_POLLING_NRFLAG - * is ordered w.r.t. need_resched() test. - */ - smp_mb(); - local_irq_disable(); - - /* Don't trace irqs off for idle */ - stop_critical_timings(); - - /* check again after disabling irqs */ - if (!need_resched() && !cpu_should_die()) - ppc_md.power_save(); - - start_critical_timings(); - - /* Some power_save functions return with - * interrupts enabled, some don't. - */ - if (irqs_disabled()) - local_irq_enable(); - set_thread_flag(TIF_POLLING_NRFLAG); - - } else { - /* - * Go into low thread priority and possibly - * low power mode. - */ - HMT_low(); - HMT_very_low(); - } - } + sched_preempt_enable_no_resched(); + cpu_die(); +} +#endif - HMT_medium(); - ppc64_runlatch_on(); - rcu_idle_exit(); - tick_nohz_idle_exit(); - if (cpu_should_die()) { - sched_preempt_enable_no_resched(); - cpu_die(); - } - schedule_preempt_disabled(); +void arch_cpu_idle(void) +{ + ppc64_runlatch_off(); + + if (ppc_md.power_save) { + ppc_md.power_save(); + /* + * Some power_save functions return with + * interrupts enabled, some don't. + */ + if (irqs_disabled()) + local_irq_enable(); + } else { + local_irq_enable(); + /* + * Go into low thread priority and possibly + * low power mode. + */ + HMT_low(); + HMT_very_low(); } + + HMT_medium(); + ppc64_runlatch_on(); } int powersave_nap; diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index a61b133..6782221 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -756,12 +756,7 @@ static __init void kvm_free_tmp(void) end = (ulong)&kvm_tmp[ARRAY_SIZE(kvm_tmp)] & PAGE_MASK; /* Free the tmp space we don't need */ - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - } + free_reserved_area(start, end, 0, NULL); } static int __init kvm_guest_init(void) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 59dd545..16e77a8 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -555,10 +555,12 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new) new->thread.regs->msr |= (MSR_FP | new->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(&new->thread); new->thread.regs->msr |= MSR_VEC; } +#endif /* We may as well turn on VSX too since all the state is restored now */ if (msr & MSR_VSX) new->thread.regs->msr |= MSR_VSX; diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 3acb28e..95068bf 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -866,10 +866,12 @@ static long restore_tm_user_regs(struct pt_regs *regs, do_load_up_transact_fpu(¤t->thread); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(¤t->thread); regs->msr |= MSR_VEC; } +#endif return 0; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 995f854..c179428 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -522,10 +522,12 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, do_load_up_transact_fpu(¤t->thread); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(¤t->thread); regs->msr |= MSR_VEC; } +#endif return err; } diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 76bd9da..ee7ac5e 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -669,7 +669,7 @@ __cpuinit void start_secondary(void *unused) local_irq_enable(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); BUG(); } diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 84dbace..2da67e7 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -309,6 +309,7 @@ _GLOBAL(tm_recheckpoint) or r5, r6, r5 /* Set MSR.FP+.VSX/.VEC */ mtmsr r5 +#ifdef CONFIG_ALTIVEC /* FP and VEC registers: These are recheckpointed from thread.fpr[] * and thread.vr[] respectively. The thread.transact_fpr[] version * is more modern, and will be loaded subsequently by any FPUnavailable @@ -323,6 +324,7 @@ _GLOBAL(tm_recheckpoint) REST_32VRS(0, r5, r3) /* r5 scratch, r3 THREAD ptr */ ld r5, THREAD_VRSAVE(r3) mtspr SPRN_VRSAVE, r5 +#endif dont_restore_vec: andi. r0, r4, MSR_FP diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index f974849..13b8670 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -156,15 +156,13 @@ static struct console udbg_console = { .index = 0, }; -static int early_console_initialized; - /* * Called by setup_system after ppc_md->probe and ppc_md->early_init. * Call it again after setting udbg_putc in ppc_md->setup_arch. */ void __init register_early_udbg_console(void) { - if (early_console_initialized) + if (early_console) return; if (!udbg_putc) @@ -174,7 +172,7 @@ void __init register_early_udbg_console(void) printk(KERN_INFO "early console immortal !\n"); udbg_console.flags &= ~CON_BOOT; } - early_console_initialized = 1; + early_console = &udbg_console; register_console(&udbg_console); } diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c index bc77834..59f419b 100644 --- a/arch/powerpc/kernel/uprobes.c +++ b/arch/powerpc/kernel/uprobes.c @@ -31,6 +31,16 @@ #define UPROBE_TRAP_NR UINT_MAX /** + * is_trap_insn - check if the instruction is a trap variant + * @insn: instruction to be checked. + * Returns true if @insn is a trap variant. + */ +bool is_trap_insn(uprobe_opcode_t *insn) +{ + return (is_trap(*insn)); +} + +/** * arch_uprobe_analyze_insn * @mm: the probed address space. * @arch_uprobe: the probepoint information. @@ -43,12 +53,6 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, if (addr & 0x03) return -EINVAL; - /* - * We currently don't support a uprobe on an already - * existing breakpoint instruction underneath - */ - if (is_trap(auprobe->ainsn)) - return -ENOTSUPP; return 0; } @@ -188,3 +192,16 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) return false; } + +unsigned long +arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs) +{ + unsigned long orig_ret_vaddr; + + orig_ret_vaddr = regs->link; + + /* Replace the return addr with trampoline addr */ + regs->link = trampoline_vaddr; + + return orig_ret_vaddr; +} diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 41cefd4..33db48a 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -26,17 +26,20 @@ #define E500_PID_NUM 3 #define E500_TLB_NUM 2 -#define E500_TLB_VALID 1 -#define E500_TLB_BITMAP 2 +/* entry is mapped somewhere in host TLB */ +#define E500_TLB_VALID (1 << 0) +/* TLB1 entry is mapped by host TLB1, tracked by bitmaps */ +#define E500_TLB_BITMAP (1 << 1) +/* TLB1 entry is mapped by host TLB0 */ #define E500_TLB_TLB0 (1 << 2) struct tlbe_ref { - pfn_t pfn; - unsigned int flags; /* E500_TLB_* */ + pfn_t pfn; /* valid only for TLB0, except briefly */ + unsigned int flags; /* E500_TLB_* */ }; struct tlbe_priv { - struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */ + struct tlbe_ref ref; }; #ifdef CONFIG_KVM_E500V2 @@ -63,17 +66,6 @@ struct kvmppc_vcpu_e500 { unsigned int gtlb_nv[E500_TLB_NUM]; - /* - * information associated with each host TLB entry -- - * TLB1 only for now. If/when guest TLB1 entries can be - * mapped with host TLB0, this will be used for that too. - * - * We don't want to use this for guest TLB0 because then we'd - * have the overhead of doing the translation again even if - * the entry is still in the guest TLB (e.g. we swapped out - * and back, and our host TLB entries got evicted). - */ - struct tlbe_ref *tlb_refs[E500_TLB_NUM]; unsigned int host_tlb1_nv; u32 svr; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index a222edf..1c6a9d72 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -193,8 +193,11 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref; /* Don't bother with unmapped entries */ - if (!(ref->flags & E500_TLB_VALID)) - return; + if (!(ref->flags & E500_TLB_VALID)) { + WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), + "%s: flags %x\n", __func__, ref->flags); + WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]); + } if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) { u64 tmp = vcpu_e500->g2h_tlb1_map[esel]; @@ -248,7 +251,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, pfn_t pfn) { ref->pfn = pfn; - ref->flags = E500_TLB_VALID; + ref->flags |= E500_TLB_VALID; if (tlbe_is_writable(gtlbe)) kvm_set_pfn_dirty(pfn); @@ -257,6 +260,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) { if (ref->flags & E500_TLB_VALID) { + /* FIXME: don't log bogus pfn for TLB1 */ trace_kvm_booke206_ref_release(ref->pfn, ref->flags); ref->flags = 0; } @@ -274,36 +278,23 @@ static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500) static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500) { - int tlbsel = 0; - int i; - - for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->gtlb_priv[tlbsel][i].ref; - kvmppc_e500_ref_release(ref); - } -} - -static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500) -{ - int stlbsel = 1; + int tlbsel; int i; - kvmppc_e500_tlbil_all(vcpu_e500); - - for (i = 0; i < host_tlb_params[stlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->tlb_refs[stlbsel][i]; - kvmppc_e500_ref_release(ref); + for (tlbsel = 0; tlbsel <= 1; tlbsel++) { + for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { + struct tlbe_ref *ref = + &vcpu_e500->gtlb_priv[tlbsel][i].ref; + kvmppc_e500_ref_release(ref); + } } - - clear_tlb_privs(vcpu_e500); } void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); - clear_tlb_refs(vcpu_e500); + kvmppc_e500_tlbil_all(vcpu_e500); + clear_tlb_privs(vcpu_e500); clear_tlb1_bitmap(vcpu_e500); } @@ -458,8 +449,6 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); } - /* Drop old ref and setup new one. */ - kvmppc_e500_ref_release(ref); kvmppc_e500_ref_setup(ref, gtlbe, pfn); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, @@ -507,14 +496,15 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size())) vcpu_e500->host_tlb1_nv = 0; - vcpu_e500->tlb_refs[1][sesel] = *ref; - vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; if (vcpu_e500->h2g_tlb1_rmap[sesel]) { - unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel]; + unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel] - 1; vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel); } - vcpu_e500->h2g_tlb1_rmap[sesel] = esel; + + vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; + vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; + vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1; + WARN_ON(!(ref->flags & E500_TLB_VALID)); return sesel; } @@ -526,13 +516,12 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, struct kvm_book3e_206_tlb_entry *stlbe, int esel) { - struct tlbe_ref ref; + struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref; int sesel; int r; - ref.flags = 0; r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, - &ref); + ref); if (r) return r; @@ -544,7 +533,7 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, } /* Otherwise map into TLB1 */ - sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, &ref, esel); + sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel); write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel); return 0; @@ -565,7 +554,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, case 0: priv = &vcpu_e500->gtlb_priv[tlbsel][esel]; - /* Triggers after clear_tlb_refs or on initial mapping */ + /* Triggers after clear_tlb_privs or on initial mapping */ if (!(priv->ref.flags & E500_TLB_VALID)) { kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe); } else { @@ -665,35 +654,16 @@ int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500) host_tlb_params[0].entries / host_tlb_params[0].ways; host_tlb_params[1].sets = 1; - vcpu_e500->tlb_refs[0] = - kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries, - GFP_KERNEL); - if (!vcpu_e500->tlb_refs[0]) - goto err; - - vcpu_e500->tlb_refs[1] = - kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries, - GFP_KERNEL); - if (!vcpu_e500->tlb_refs[1]) - goto err; - vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) * host_tlb_params[1].entries, GFP_KERNEL); if (!vcpu_e500->h2g_tlb1_rmap) - goto err; + return -EINVAL; return 0; - -err: - kfree(vcpu_e500->tlb_refs[0]); - kfree(vcpu_e500->tlb_refs[1]); - return -EINVAL; } void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500) { kfree(vcpu_e500->h2g_tlb1_rmap); - kfree(vcpu_e500->tlb_refs[0]); - kfree(vcpu_e500->tlb_refs[1]); } diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 1f89d26..2f4baa0 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -108,6 +108,8 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr) { } +static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu); + void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); @@ -136,8 +138,11 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) mtspr(SPRN_GDEAR, vcpu->arch.shared->dar); mtspr(SPRN_GESR, vcpu->arch.shared->esr); - if (vcpu->arch.oldpir != mfspr(SPRN_PIR)) + if (vcpu->arch.oldpir != mfspr(SPRN_PIR) || + __get_cpu_var(last_vcpu_on_cpu) != vcpu) { kvmppc_e500_tlbil_all(vcpu_e500); + __get_cpu_var(last_vcpu_on_cpu) = vcpu; + } kvmppc_load_guest_fp(vcpu); } diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 7e2246f..5a535b7 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -263,19 +263,14 @@ static __meminit void vmemmap_list_populate(unsigned long phys, vmemmap_list = vmem_back; } -int __meminit vmemmap_populate(struct page *start_page, - unsigned long nr_pages, int node) +int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { - unsigned long start = (unsigned long)start_page; - unsigned long end = (unsigned long)(start_page + nr_pages); unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; /* Align to the page size of the linear mapping. */ start = _ALIGN_DOWN(start, page_size); - pr_debug("vmemmap_populate page %p, %ld pages, node %d\n", - start_page, nr_pages, node); - pr_debug(" -> map %lx..%lx\n", start, end); + pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node); for (; start < end; start += page_size) { void *p; @@ -298,7 +293,7 @@ int __meminit vmemmap_populate(struct page *start_page, return 0; } -void vmemmap_free(struct page *memmap, unsigned long nr_pages) +void vmemmap_free(unsigned long start, unsigned long end) { } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index f1f7409..cd76c45 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -352,13 +352,9 @@ void __init mem_init(void) struct page *page = pfn_to_page(pfn); if (memblock_is_reserved(paddr)) continue; - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - totalhigh_pages++; + free_highmem_page(page); reservedpages--; } - totalram_pages += totalhigh_pages; printk(KERN_DEBUG "High memory: %luk\n", totalhigh_pages << (PAGE_SHIFT-10)); } @@ -405,39 +401,14 @@ void __init mem_init(void) void free_initmem(void) { - unsigned long addr; - ppc_md.progress = ppc_printk_progress; - - addr = (unsigned long)__init_begin; - for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) { - memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE); - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } - pr_info("Freeing unused kernel memory: %luk freed\n", - ((unsigned long)__init_end - - (unsigned long)__init_begin) >> 10); + free_initmem_default(POISON_FREE_INITMEM); } #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - if (start >= end) - return; - - start = _ALIGN_DOWN(start, PAGE_SIZE); - end = _ALIGN_UP(end, PAGE_SIZE); - pr_info("Freeing initrd memory: %ldk freed\n", (end - start) >> 10); - - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - } + free_reserved_area(start, end, 0, "initrd"); } #endif diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index bba87ca..fa33c54 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -22,6 +22,7 @@ #include <linux/pfn.h> #include <linux/cpuset.h> #include <linux/node.h> +#include <linux/slab.h> #include <asm/sparsemem.h> #include <asm/prom.h> #include <asm/smp.h> @@ -62,14 +63,11 @@ static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS]; */ static void __init setup_node_to_cpumask_map(void) { - unsigned int node, num = 0; + unsigned int node; /* setup nr_node_ids if not done yet */ - if (nr_node_ids == MAX_NUMNODES) { - for_each_node_mask(node, node_possible_map) - num = node; - nr_node_ids = num + 1; - } + if (nr_node_ids == MAX_NUMNODES) + setup_nr_node_ids(); /* allocate the map */ for (node = 0; node < nr_node_ids; node++) diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index 0effe9f..7be9336 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -274,6 +274,8 @@ config 440EPX select IBM_EMAC_EMAC4 select IBM_EMAC_RGMII select IBM_EMAC_ZMII + select USB_EHCI_BIG_ENDIAN_MMIO + select USB_EHCI_BIG_ENDIAN_DESC config 440GRX bool diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig index c169998..381a592 100644 --- a/arch/powerpc/platforms/512x/Kconfig +++ b/arch/powerpc/platforms/512x/Kconfig @@ -7,6 +7,8 @@ config PPC_MPC512x select PPC_PCI_CHOICE select FSL_PCI if PCI select ARCH_WANT_OPTIONAL_GPIOLIB + select USB_EHCI_BIG_ENDIAN_MMIO + select USB_EHCI_BIG_ENDIAN_DESC config MPC5121_ADS bool "Freescale MPC5121E ADS" diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c index d30235b..db6ac38 100644 --- a/arch/powerpc/platforms/512x/mpc512x_shared.c +++ b/arch/powerpc/platforms/512x/mpc512x_shared.c @@ -172,12 +172,9 @@ static struct fsl_diu_shared_fb __attribute__ ((__aligned__(8))) diu_shared_fb; static inline void mpc512x_free_bootmem(struct page *page) { - __ClearPageReserved(page); BUG_ON(PageTail(page)); BUG_ON(atomic_read(&page->_count) > 1); - atomic_set(&page->_count, 1); - __free_page(page); - totalram_pages++; + free_reserved_page(page); } void mpc512x_release_bootmem(void) diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 2372c60..9a432de 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -72,6 +72,7 @@ unsigned long memory_block_size_bytes(void) return get_memblock_size(); } +#ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { unsigned long start, start_pfn; @@ -153,6 +154,17 @@ static int pseries_remove_memory(struct device_node *np) ret = pseries_remove_memblock(base, lmb_size); return ret; } +#else +static inline int pseries_remove_memblock(unsigned long base, + unsigned int memblock_size) +{ + return -EOPNOTSUPP; +} +static inline int pseries_remove_memory(struct device_node *np) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_MEMORY_HOTREMOVE */ static int pseries_add_memory(struct device_node *np) { diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index eb8fb62..bda6ba6 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -375,19 +375,6 @@ config PACK_STACK Say Y if you are unsure. -config SMALL_STACK - def_bool n - prompt "Use 8kb for kernel stack instead of 16kb" - depends on PACK_STACK && 64BIT && !LOCKDEP - help - If you say Y here and the compiler supports the -mkernel-backchain - option the kernel will use a smaller kernel stack size. The reduced - size is 8kb instead of 16kb. This allows to run more threads on a - system and reduces the pressure on the memory management for higher - order page allocations. - - Say N if you are unsure. - config CHECK_STACK def_bool y prompt "Detect kernel stack overflow" diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 7e3ce78..a7d68a4 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -55,22 +55,12 @@ cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls ifeq ($(call cc-option-yn,-mkernel-backchain),y) cflags-$(CONFIG_PACK_STACK) += -mkernel-backchain -D__PACK_STACK aflags-$(CONFIG_PACK_STACK) += -D__PACK_STACK -cflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK -aflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK -ifdef CONFIG_SMALL_STACK -STACK_SIZE := $(shell echo $$(($(STACK_SIZE)/2)) ) -endif endif # new style option for packed stacks ifeq ($(call cc-option-yn,-mpacked-stack),y) cflags-$(CONFIG_PACK_STACK) += -mpacked-stack -D__PACK_STACK aflags-$(CONFIG_PACK_STACK) += -D__PACK_STACK -cflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK -aflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK -ifdef CONFIG_SMALL_STACK -STACK_SIZE := $(shell echo $$(($(STACK_SIZE)/2)) ) -endif endif ifeq ($(call cc-option-yn,-mstack-size=8192 -mstack-guard=128),y) diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index 9fd4a40..bb5dd49 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -105,9 +105,7 @@ void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df) int hypfs_dbfs_init(void) { dbfs_dir = debugfs_create_dir("s390_hypfs", NULL); - if (IS_ERR(dbfs_dir)) - return PTR_ERR(dbfs_dir); - return 0; + return PTR_RET(dbfs_dir); } void hypfs_dbfs_exit(void) diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 1542293..4d8604e 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -61,8 +61,6 @@ extern const char _sb_findmap[]; #ifndef CONFIG_64BIT -#define __BITOPS_ALIGN 3 -#define __BITOPS_WORDSIZE 32 #define __BITOPS_OR "or" #define __BITOPS_AND "nr" #define __BITOPS_XOR "xr" @@ -81,8 +79,6 @@ extern const char _sb_findmap[]; #else /* CONFIG_64BIT */ -#define __BITOPS_ALIGN 7 -#define __BITOPS_WORDSIZE 64 #define __BITOPS_OR "ogr" #define __BITOPS_AND "ngr" #define __BITOPS_XOR "xgr" @@ -101,8 +97,7 @@ extern const char _sb_findmap[]; #endif /* CONFIG_64BIT */ -#define __BITOPS_WORDS(bits) (((bits)+__BITOPS_WORDSIZE-1)/__BITOPS_WORDSIZE) -#define __BITOPS_BARRIER() asm volatile("" : : : "memory") +#define __BITOPS_WORDS(bits) (((bits) + BITS_PER_LONG - 1) / BITS_PER_LONG) #ifdef CONFIG_SMP /* @@ -114,9 +109,9 @@ static inline void set_bit_cs(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr; /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; + addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3; /* make OR mask */ - mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1)); + mask = 1UL << (nr & (BITS_PER_LONG - 1)); /* Do the atomic update. */ __BITOPS_LOOP(old, new, addr, mask, __BITOPS_OR); } @@ -130,9 +125,9 @@ static inline void clear_bit_cs(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr; /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; + addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3; /* make AND mask */ - mask = ~(1UL << (nr & (__BITOPS_WORDSIZE - 1))); + mask = ~(1UL << (nr & (BITS_PER_LONG - 1))); /* Do the atomic update. */ __BITOPS_LOOP(old, new, addr, mask, __BITOPS_AND); } @@ -146,9 +141,9 @@ static inline void change_bit_cs(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr; /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; + addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3; /* make XOR mask */ - mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1)); + mask = 1UL << (nr & (BITS_PER_LONG - 1)); /* Do the atomic update. */ __BITOPS_LOOP(old, new, addr, mask, __BITOPS_XOR); } @@ -163,12 +158,12 @@ test_and_set_bit_cs(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr; /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; + addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3; /* make OR/test mask */ - mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1)); + mask = 1UL << (nr & (BITS_PER_LONG - 1)); /* Do the atomic update. */ __BITOPS_LOOP(old, new, addr, mask, __BITOPS_OR); - __BITOPS_BARRIER(); + barrier(); return (old & mask) != 0; } @@ -182,12 +177,12 @@ test_and_clear_bit_cs(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr; /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; + addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3; /* make AND/test mask */ - mask = ~(1UL << (nr & (__BITOPS_WORDSIZE - 1))); + mask = ~(1UL << (nr & (BITS_PER_LONG - 1))); /* Do the atomic update. */ __BITOPS_LOOP(old, new, addr, mask, __BITOPS_AND); - __BITOPS_BARRIER(); + barrier(); return (old ^ new) != 0; } @@ -201,12 +196,12 @@ test_and_change_bit_cs(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr; /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; + addr += (nr ^ (nr & (BITS_PER_LONG - 1))) >> 3; /* make XOR/test mask */ - mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1)); + mask = 1UL << (nr & (BITS_PER_LONG - 1)); /* Do the atomic update. */ __BITOPS_LOOP(old, new, addr, mask, __BITOPS_XOR); - __BITOPS_BARRIER(); + barrier(); return (old & mask) != 0; } #endif /* CONFIG_SMP */ @@ -218,7 +213,7 @@ static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long addr; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); asm volatile( " oc %O0(1,%R0),%1" : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" ); @@ -229,7 +224,7 @@ __constant_set_bit(const unsigned long nr, volatile unsigned long *ptr) { unsigned long addr; - addr = ((unsigned long) ptr) + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = ((unsigned long) ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); *(unsigned char *) addr |= 1 << (nr & 7); } @@ -246,7 +241,7 @@ __clear_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long addr; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); asm volatile( " nc %O0(1,%R0),%1" : "=Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) : "cc" ); @@ -257,7 +252,7 @@ __constant_clear_bit(const unsigned long nr, volatile unsigned long *ptr) { unsigned long addr; - addr = ((unsigned long) ptr) + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = ((unsigned long) ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); *(unsigned char *) addr &= ~(1 << (nr & 7)); } @@ -273,7 +268,7 @@ static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long addr; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); asm volatile( " xc %O0(1,%R0),%1" : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" ); @@ -284,7 +279,7 @@ __constant_change_bit(const unsigned long nr, volatile unsigned long *ptr) { unsigned long addr; - addr = ((unsigned long) ptr) + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = ((unsigned long) ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); *(unsigned char *) addr ^= 1 << (nr & 7); } @@ -302,7 +297,7 @@ test_and_set_bit_simple(unsigned long nr, volatile unsigned long *ptr) unsigned long addr; unsigned char ch; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); ch = *(unsigned char *) addr; asm volatile( " oc %O0(1,%R0),%1" @@ -321,7 +316,7 @@ test_and_clear_bit_simple(unsigned long nr, volatile unsigned long *ptr) unsigned long addr; unsigned char ch; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); ch = *(unsigned char *) addr; asm volatile( " nc %O0(1,%R0),%1" @@ -340,7 +335,7 @@ test_and_change_bit_simple(unsigned long nr, volatile unsigned long *ptr) unsigned long addr; unsigned char ch; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); ch = *(unsigned char *) addr; asm volatile( " xc %O0(1,%R0),%1" @@ -376,7 +371,7 @@ static inline int __test_bit(unsigned long nr, const volatile unsigned long *ptr unsigned long addr; unsigned char ch; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); + addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); ch = *(volatile unsigned char *) addr; return (ch >> (nr & 7)) & 1; } @@ -384,7 +379,7 @@ static inline int __test_bit(unsigned long nr, const volatile unsigned long *ptr static inline int __constant_test_bit(unsigned long nr, const volatile unsigned long *addr) { return (((volatile char *) addr) - [(nr^(__BITOPS_WORDSIZE-8))>>3] & (1<<(nr&7))) != 0; + [(nr^(BITS_PER_LONG-8))>>3] & (1<<(nr&7))) != 0; } #define test_bit(nr,addr) \ @@ -693,18 +688,18 @@ static inline int find_next_bit_left(const unsigned long *addr, if (offset >= size) return size; - bit = offset & (__BITOPS_WORDSIZE - 1); + bit = offset & (BITS_PER_LONG - 1); offset -= bit; size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; + p = addr + offset / BITS_PER_LONG; if (bit) { set = __flo_word(0, *p & (~0UL << bit)); if (set >= size) return size + offset; - if (set < __BITOPS_WORDSIZE) + if (set < BITS_PER_LONG) return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; + offset += BITS_PER_LONG; + size -= BITS_PER_LONG; p++; } return offset + find_first_bit_left(p, size); @@ -736,22 +731,22 @@ static inline int find_next_zero_bit (const unsigned long * addr, if (offset >= size) return size; - bit = offset & (__BITOPS_WORDSIZE - 1); + bit = offset & (BITS_PER_LONG - 1); offset -= bit; size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; + p = addr + offset / BITS_PER_LONG; if (bit) { /* - * __ffz_word returns __BITOPS_WORDSIZE + * __ffz_word returns BITS_PER_LONG * if no zero bit is present in the word. */ set = __ffz_word(bit, *p >> bit); if (set >= size) return size + offset; - if (set < __BITOPS_WORDSIZE) + if (set < BITS_PER_LONG) return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; + offset += BITS_PER_LONG; + size -= BITS_PER_LONG; p++; } return offset + find_first_zero_bit(p, size); @@ -773,22 +768,22 @@ static inline int find_next_bit (const unsigned long * addr, if (offset >= size) return size; - bit = offset & (__BITOPS_WORDSIZE - 1); + bit = offset & (BITS_PER_LONG - 1); offset -= bit; size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; + p = addr + offset / BITS_PER_LONG; if (bit) { /* - * __ffs_word returns __BITOPS_WORDSIZE + * __ffs_word returns BITS_PER_LONG * if no one bit is present in the word. */ set = __ffs_word(0, *p & (~0UL << bit)); if (set >= size) return size + offset; - if (set < __BITOPS_WORDSIZE) + if (set < BITS_PER_LONG) return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; + offset += BITS_PER_LONG; + size -= BITS_PER_LONG; p++; } return offset + find_first_bit(p, size); @@ -843,22 +838,22 @@ static inline int find_next_zero_bit_le(void *vaddr, unsigned long size, if (offset >= size) return size; - bit = offset & (__BITOPS_WORDSIZE - 1); + bit = offset & (BITS_PER_LONG - 1); offset -= bit; size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; + p = addr + offset / BITS_PER_LONG; if (bit) { /* - * s390 version of ffz returns __BITOPS_WORDSIZE + * s390 version of ffz returns BITS_PER_LONG * if no zero bit is present in the word. */ set = __ffz_word(bit, __load_ulong_le(p, 0) >> bit); if (set >= size) return size + offset; - if (set < __BITOPS_WORDSIZE) + if (set < BITS_PER_LONG) return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; + offset += BITS_PER_LONG; + size -= BITS_PER_LONG; p++; } return offset + find_first_zero_bit_le(p, size); @@ -885,22 +880,22 @@ static inline int find_next_bit_le(void *vaddr, unsigned long size, if (offset >= size) return size; - bit = offset & (__BITOPS_WORDSIZE - 1); + bit = offset & (BITS_PER_LONG - 1); offset -= bit; size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; + p = addr + offset / BITS_PER_LONG; if (bit) { /* - * s390 version of ffz returns __BITOPS_WORDSIZE + * s390 version of ffz returns BITS_PER_LONG * if no zero bit is present in the word. */ set = __ffs_word(0, __load_ulong_le(p, 0) & (~0UL << bit)); if (set >= size) return size + offset; - if (set < __BITOPS_WORDSIZE) + if (set < BITS_PER_LONG) return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; + offset += BITS_PER_LONG; + size -= BITS_PER_LONG; p++; } return offset + find_first_bit_le(p, size); diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h index e606161..f201af8 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -220,7 +220,8 @@ extern void ccw_device_get_id(struct ccw_device *, struct ccw_dev_id *); #define to_ccwdrv(n) container_of(n, struct ccw_driver, driver) extern struct ccw_device *ccw_device_probe_console(void); -extern int ccw_device_force_console(void); +extern void ccw_device_wait_idle(struct ccw_device *); +extern int ccw_device_force_console(struct ccw_device *); int ccw_device_siosl(struct ccw_device *); diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index ad2b924..ffb8989 100644 --- a/arch/s390/include/asm/cio.h +++ b/arch/s390/include/asm/cio.h @@ -296,8 +296,6 @@ static inline int ccw_dev_id_is_equal(struct ccw_dev_id *dev_id1, return 0; } -extern void wait_cons_dev(void); - extern void css_schedule_reprobe(void); extern void reipl_ccw_dev(struct ccw_dev_id *id); diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index f8c6df6..c1e7c64 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -70,6 +70,22 @@ typedef u32 compat_ulong_t; typedef u64 compat_u64; typedef u32 compat_uptr_t; +typedef struct { + u32 mask; + u32 addr; +} __aligned(8) psw_compat_t; + +typedef struct { + psw_compat_t psw; + u32 gprs[NUM_GPRS]; + u32 acrs[NUM_ACRS]; + u32 orig_gpr2; +} s390_compat_regs; + +typedef struct { + u32 gprs_high[NUM_GPRS]; +} s390_compat_regs_high; + struct compat_timespec { compat_time_t tv_sec; s32 tv_nsec; @@ -124,18 +140,33 @@ struct compat_flock64 { }; struct compat_statfs { - s32 f_type; - s32 f_bsize; - s32 f_blocks; - s32 f_bfree; - s32 f_bavail; - s32 f_files; - s32 f_ffree; + u32 f_type; + u32 f_bsize; + u32 f_blocks; + u32 f_bfree; + u32 f_bavail; + u32 f_files; + u32 f_ffree; + compat_fsid_t f_fsid; + u32 f_namelen; + u32 f_frsize; + u32 f_flags; + u32 f_spare[4]; +}; + +struct compat_statfs64 { + u32 f_type; + u32 f_bsize; + u64 f_blocks; + u64 f_bfree; + u64 f_bavail; + u64 f_files; + u64 f_ffree; compat_fsid_t f_fsid; - s32 f_namelen; - s32 f_frsize; - s32 f_flags; - s32 f_spare[5]; + u32 f_namelen; + u32 f_frsize; + u32 f_flags; + u32 f_spare[4]; }; #define COMPAT_RLIM_OLD_INFINITY 0x7fffffff @@ -248,8 +279,6 @@ static inline int is_compat_task(void) return is_32bit_task(); } -#endif - static inline void __user *arch_compat_alloc_user_space(long len) { unsigned long stack; @@ -260,6 +289,8 @@ static inline void __user *arch_compat_alloc_user_space(long len) return (void __user *) (stack - len); } +#endif + struct compat_ipc64_perm { compat_key_t key; __compat_uid32_t uid; diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 1bfdf24..78f4f87 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -119,6 +119,8 @@ */ #include <asm/ptrace.h> +#include <asm/compat.h> +#include <asm/syscall.h> #include <asm/user.h> typedef s390_fp_regs elf_fpregset_t; @@ -180,18 +182,31 @@ extern unsigned long elf_hwcap; extern char elf_platform[]; #define ELF_PLATFORM (elf_platform) -#ifdef CONFIG_64BIT +#ifndef CONFIG_COMPAT +#define SET_PERSONALITY(ex) \ +do { \ + set_personality(PER_LINUX | \ + (current->personality & (~PER_MASK))); \ + current_thread_info()->sys_call_table = \ + (unsigned long) &sys_call_table; \ +} while (0) +#else /* CONFIG_COMPAT */ #define SET_PERSONALITY(ex) \ do { \ if (personality(current->personality) != PER_LINUX32) \ set_personality(PER_LINUX | \ (current->personality & ~PER_MASK)); \ - if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \ + if ((ex).e_ident[EI_CLASS] == ELFCLASS32) { \ set_thread_flag(TIF_31BIT); \ - else \ + current_thread_info()->sys_call_table = \ + (unsigned long) &sys_call_table_emu; \ + } else { \ clear_thread_flag(TIF_31BIT); \ + current_thread_info()->sys_call_table = \ + (unsigned long) &sys_call_table; \ + } \ } while (0) -#endif /* CONFIG_64BIT */ +#endif /* CONFIG_COMPAT */ #define STACK_RND_MASK 0x7ffUL diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index 593753e..bd90359 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -114,7 +114,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, #define huge_ptep_set_wrprotect(__mm, __addr, __ptep) \ ({ \ pte_t __pte = huge_ptep_get(__ptep); \ - if (pte_write(__pte)) { \ + if (huge_pte_write(__pte)) { \ huge_ptep_invalidate(__mm, __addr, __ptep); \ set_huge_pte_at(__mm, __addr, __ptep, \ huge_pte_wrprotect(__pte)); \ @@ -127,4 +127,58 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, huge_ptep_invalidate(vma->vm_mm, address, ptep); } +static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) +{ + pte_t pte; + pmd_t pmd; + + pmd = mk_pmd_phys(page_to_phys(page), pgprot); + pte_val(pte) = pmd_val(pmd); + return pte; +} + +static inline int huge_pte_write(pte_t pte) +{ + pmd_t pmd; + + pmd_val(pmd) = pte_val(pte); + return pmd_write(pmd); +} + +static inline int huge_pte_dirty(pte_t pte) +{ + /* No dirty bit in the segment table entry. */ + return 0; +} + +static inline pte_t huge_pte_mkwrite(pte_t pte) +{ + pmd_t pmd; + + pmd_val(pmd) = pte_val(pte); + pte_val(pte) = pmd_val(pmd_mkwrite(pmd)); + return pte; +} + +static inline pte_t huge_pte_mkdirty(pte_t pte) +{ + /* No dirty bit in the segment table entry. */ + return pte; +} + +static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) +{ + pmd_t pmd; + + pmd_val(pmd) = pte_val(pte); + pte_val(pte) = pmd_val(pmd_modify(pmd, newprot)); + return pte; +} + +static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pmd_clear((pmd_t *) ptep); +} + #endif /* _ASM_S390_HUGETLB_H */ diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index 27cb321..379d96e 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -50,10 +50,6 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr); #define ioremap_nocache(addr, size) ioremap(addr, size) #define ioremap_wc ioremap_nocache -/* TODO: s390 cannot support io_remap_pfn_range... */ -#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ - remap_pfn_range(vma, vaddr, pfn, size, prot) - static inline void __iomem *ioremap(unsigned long offset, unsigned long size) { return (void __iomem *) offset; diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 05333b7..6c18012 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -140,6 +140,7 @@ static inline bool zdev_enabled(struct zpci_dev *zdev) struct zpci_dev *zpci_alloc_device(void); int zpci_create_device(struct zpci_dev *); int zpci_enable_device(struct zpci_dev *); +int zpci_disable_device(struct zpci_dev *); void zpci_stop_device(struct zpci_dev *); void zpci_free_device(struct zpci_dev *); int zpci_scan_device(struct zpci_dev *); diff --git a/arch/s390/include/asm/pci_debug.h b/arch/s390/include/asm/pci_debug.h index 6bbec42..1ca5d10 100644 --- a/arch/s390/include/asm/pci_debug.h +++ b/arch/s390/include/asm/pci_debug.h @@ -7,14 +7,11 @@ extern debug_info_t *pci_debug_msg_id; extern debug_info_t *pci_debug_err_id; #ifdef CONFIG_PCI_DEBUG -#define zpci_dbg(fmt, args...) \ - do { \ - if (pci_debug_msg_id->level >= 2) \ - debug_sprintf_event(pci_debug_msg_id, 2, fmt , ## args);\ - } while (0) +#define zpci_dbg(imp, fmt, args...) \ + debug_sprintf_event(pci_debug_msg_id, imp, fmt, ##args) #else /* !CONFIG_PCI_DEBUG */ -#define zpci_dbg(fmt, args...) do { } while (0) +#define zpci_dbg(imp, fmt, args...) do { } while (0) #endif #define zpci_err(text...) \ diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h index 1486a98..e6a2bdd 100644 --- a/arch/s390/include/asm/pci_insn.h +++ b/arch/s390/include/asm/pci_insn.h @@ -1,10 +1,6 @@ #ifndef _ASM_S390_PCI_INSN_H #define _ASM_S390_PCI_INSN_H -#include <linux/delay.h> - -#define ZPCI_INSN_BUSY_DELAY 1 /* 1 microsecond */ - /* Load/Store status codes */ #define ZPCI_PCI_ST_FUNC_NOT_ENABLED 4 #define ZPCI_PCI_ST_FUNC_IN_ERR 8 @@ -82,199 +78,12 @@ struct zpci_fib { u64 reserved7; } __packed; -/* Modify PCI Function Controls */ -static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status) -{ - u8 cc; - - asm volatile ( - " .insn rxy,0xe300000000d0,%[req],%[fib]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [req] "+d" (req), [fib] "+Q" (*fib) - : : "cc"); - *status = req >> 24 & 0xff; - return cc; -} - -static inline int mpcifc_instr(u64 req, struct zpci_fib *fib) -{ - u8 cc, status; - - do { - cc = __mpcifc(req, fib, &status); - if (cc == 2) - msleep(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) - printk_once(KERN_ERR "%s: error cc: %d status: %d\n", - __func__, cc, status); - return (cc) ? -EIO : 0; -} - -/* Refresh PCI Translations */ -static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status) -{ - register u64 __addr asm("2") = addr; - register u64 __range asm("3") = range; - u8 cc; - - asm volatile ( - " .insn rre,0xb9d30000,%[fn],%[addr]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [fn] "+d" (fn) - : [addr] "d" (__addr), "d" (__range) - : "cc"); - *status = fn >> 24 & 0xff; - return cc; -} - -static inline int rpcit_instr(u64 fn, u64 addr, u64 range) -{ - u8 cc, status; - - do { - cc = __rpcit(fn, addr, range, &status); - if (cc == 2) - udelay(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) - printk_once(KERN_ERR "%s: error cc: %d status: %d dma_addr: %Lx size: %Lx\n", - __func__, cc, status, addr, range); - return (cc) ? -EIO : 0; -} - -/* Store PCI function controls */ -static inline u8 __stpcifc(u32 handle, u8 space, struct zpci_fib *fib, u8 *status) -{ - u64 fn = (u64) handle << 32 | space << 16; - u8 cc; - - asm volatile ( - " .insn rxy,0xe300000000d4,%[fn],%[fib]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [fn] "+d" (fn), [fib] "=m" (*fib) - : : "cc"); - *status = fn >> 24 & 0xff; - return cc; -} - -/* Set Interruption Controls */ -static inline void sic_instr(u16 ctl, char *unused, u8 isc) -{ - asm volatile ( - " .insn rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n" - : : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused)); -} - -/* PCI Load */ -static inline u8 __pcilg(u64 *data, u64 req, u64 offset, u8 *status) -{ - register u64 __req asm("2") = req; - register u64 __offset asm("3") = offset; - u64 __data; - u8 cc; - - asm volatile ( - " .insn rre,0xb9d20000,%[data],%[req]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [data] "=d" (__data), [req] "+d" (__req) - : "d" (__offset) - : "cc"); - *status = __req >> 24 & 0xff; - *data = __data; - return cc; -} - -static inline int pcilg_instr(u64 *data, u64 req, u64 offset) -{ - u8 cc, status; - - do { - cc = __pcilg(data, req, offset, &status); - if (cc == 2) - udelay(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) { - printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", - __func__, cc, status, req, offset); - /* TODO: on IO errors set data to 0xff... - * here or in users of pcilg (le conversion)? - */ - } - return (cc) ? -EIO : 0; -} - -/* PCI Store */ -static inline u8 __pcistg(u64 data, u64 req, u64 offset, u8 *status) -{ - register u64 __req asm("2") = req; - register u64 __offset asm("3") = offset; - u8 cc; - - asm volatile ( - " .insn rre,0xb9d00000,%[data],%[req]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [req] "+d" (__req) - : "d" (__offset), [data] "d" (data) - : "cc"); - *status = __req >> 24 & 0xff; - return cc; -} - -static inline int pcistg_instr(u64 data, u64 req, u64 offset) -{ - u8 cc, status; - - do { - cc = __pcistg(data, req, offset, &status); - if (cc == 2) - udelay(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) - printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", - __func__, cc, status, req, offset); - return (cc) ? -EIO : 0; -} - -/* PCI Store Block */ -static inline u8 __pcistb(const u64 *data, u64 req, u64 offset, u8 *status) -{ - u8 cc; - - asm volatile ( - " .insn rsy,0xeb00000000d0,%[req],%[offset],%[data]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [req] "+d" (req) - : [offset] "d" (offset), [data] "Q" (*data) - : "cc"); - *status = req >> 24 & 0xff; - return cc; -} - -static inline int pcistb_instr(const u64 *data, u64 req, u64 offset) -{ - u8 cc, status; - - do { - cc = __pcistb(data, req, offset, &status); - if (cc == 2) - udelay(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - if (cc) - printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", - __func__, cc, status, req, offset); - return (cc) ? -EIO : 0; -} +int s390pci_mod_fc(u64 req, struct zpci_fib *fib); +int s390pci_refresh_trans(u64 fn, u64 addr, u64 range); +int s390pci_load(u64 *data, u64 req, u64 offset); +int s390pci_store(u64 data, u64 req, u64 offset); +int s390pci_store_block(const u64 *data, u64 req, u64 offset); +void set_irq_ctrl(u16 ctl, char *unused, u8 isc); #endif diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index 5fd81f3..83a9caa 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -36,7 +36,7 @@ static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr) \ u64 data; \ int rc; \ \ - rc = pcilg_instr(&data, req, ZPCI_OFFSET(addr)); \ + rc = s390pci_load(&data, req, ZPCI_OFFSET(addr)); \ if (rc) \ data = -1ULL; \ return (RETTYPE) data; \ @@ -50,7 +50,7 @@ static inline void zpci_write_##VALTYPE(VALTYPE val, \ u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH); \ u64 data = (VALTYPE) val; \ \ - pcistg_instr(data, req, ZPCI_OFFSET(addr)); \ + s390pci_store(data, req, ZPCI_OFFSET(addr)); \ } zpci_read(8, u64) @@ -83,15 +83,18 @@ static inline int zpci_write_single(u64 req, const u64 *data, u64 offset, u8 len val = 0; /* let FW report error */ break; } - return pcistg_instr(val, req, offset); + return s390pci_store(val, req, offset); } static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len) { u64 data; - u8 cc; + int cc; + + cc = s390pci_load(&data, req, offset); + if (cc) + goto out; - cc = pcilg_instr(&data, req, offset); switch (len) { case 1: *((u8 *) dst) = (u8) data; @@ -106,12 +109,13 @@ static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len) *((u64 *) dst) = (u64) data; break; } +out: return cc; } static inline int zpci_write_block(u64 req, const u64 *data, u64 offset) { - return pcistb_instr(data, req, offset); + return s390pci_store_block(data, req, offset); } static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 4a54431..b462291 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -57,6 +57,10 @@ extern unsigned long zero_page_mask; (((unsigned long)(vaddr)) &zero_page_mask)))) #define __HAVE_COLOR_ZERO_PAGE +/* TODO: s390 cannot support io_remap_pfn_range... */ +#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ + remap_pfn_range(vma, vaddr, pfn, size, prot) + #endif /* !__ASSEMBLY__ */ /* @@ -420,6 +424,13 @@ extern unsigned long MODULES_END; #define __S110 PAGE_RW #define __S111 PAGE_RW +/* + * Segment entry (large page) protection definitions. + */ +#define SEGMENT_NONE __pgprot(_HPAGE_TYPE_NONE) +#define SEGMENT_RO __pgprot(_HPAGE_TYPE_RO) +#define SEGMENT_RW __pgprot(_HPAGE_TYPE_RW) + static inline int mm_exclusive(struct mm_struct *mm) { return likely(mm == current->active_mm && @@ -760,6 +771,8 @@ void gmap_disable(struct gmap *gmap); int gmap_map_segment(struct gmap *gmap, unsigned long from, unsigned long to, unsigned long length); int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len); +unsigned long __gmap_translate(unsigned long address, struct gmap *); +unsigned long gmap_translate(unsigned long address, struct gmap *); unsigned long __gmap_fault(unsigned long address, struct gmap *); unsigned long gmap_fault(unsigned long address, struct gmap *); void gmap_discard(unsigned long from, unsigned long to, struct gmap *); @@ -908,26 +921,6 @@ static inline pte_t pte_mkspecial(pte_t pte) #ifdef CONFIG_HUGETLB_PAGE static inline pte_t pte_mkhuge(pte_t pte) { - /* - * PROT_NONE needs to be remapped from the pte type to the ste type. - * The HW invalid bit is also different for pte and ste. The pte - * invalid bit happens to be the same as the ste _SEGMENT_ENTRY_LARGE - * bit, so we don't have to clear it. - */ - if (pte_val(pte) & _PAGE_INVALID) { - if (pte_val(pte) & _PAGE_SWT) - pte_val(pte) |= _HPAGE_TYPE_NONE; - pte_val(pte) |= _SEGMENT_ENTRY_INV; - } - /* - * Clear SW pte bits, there are no SW bits in a segment table entry. - */ - pte_val(pte) &= ~(_PAGE_SWT | _PAGE_SWX | _PAGE_SWC | - _PAGE_SWR | _PAGE_SWW); - /* - * Also set the change-override bit because we don't need dirty bit - * tracking for hugetlbfs pages. - */ pte_val(pte) |= (_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO); return pte; } @@ -1272,31 +1265,7 @@ static inline void __pmd_idte(unsigned long address, pmd_t *pmdp) } } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - -#define SEGMENT_NONE __pgprot(_HPAGE_TYPE_NONE) -#define SEGMENT_RO __pgprot(_HPAGE_TYPE_RO) -#define SEGMENT_RW __pgprot(_HPAGE_TYPE_RW) - -#define __HAVE_ARCH_PGTABLE_DEPOSIT -extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable); - -#define __HAVE_ARCH_PGTABLE_WITHDRAW -extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm); - -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT; -} - -static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, pmd_t entry) -{ - if (!(pmd_val(entry) & _SEGMENT_ENTRY_INV) && MACHINE_HAS_EDAT1) - pmd_val(entry) |= _SEGMENT_ENTRY_CO; - *pmdp = entry; -} - +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE) static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot) { /* @@ -1317,10 +1286,11 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) return pmd; } -static inline pmd_t pmd_mkhuge(pmd_t pmd) +static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot) { - pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE; - return pmd; + pmd_t __pmd; + pmd_val(__pmd) = physpage + massage_pgprot_pmd(pgprot); + return __pmd; } static inline pmd_t pmd_mkwrite(pmd_t pmd) @@ -1330,6 +1300,34 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd) pmd_val(pmd) &= ~_SEGMENT_ENTRY_RO; return pmd; } +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLB_PAGE */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + +#define __HAVE_ARCH_PGTABLE_DEPOSIT +extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable); + +#define __HAVE_ARCH_PGTABLE_WITHDRAW +extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm); + +static inline int pmd_trans_splitting(pmd_t pmd) +{ + return pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT; +} + +static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t entry) +{ + if (!(pmd_val(entry) & _SEGMENT_ENTRY_INV) && MACHINE_HAS_EDAT1) + pmd_val(entry) |= _SEGMENT_ENTRY_CO; + *pmdp = entry; +} + +static inline pmd_t pmd_mkhuge(pmd_t pmd) +{ + pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE; + return pmd; +} static inline pmd_t pmd_wrprotect(pmd_t pmd) { @@ -1426,13 +1424,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, } } -static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot) -{ - pmd_t __pmd; - pmd_val(__pmd) = physpage + massage_pgprot_pmd(pgprot); - return __pmd; -} - #define pfn_pmd(pfn, pgprot) mk_pmd_phys(__pa((pfn) << PAGE_SHIFT), (pgprot)) #define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 94e749c..6b49987 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -161,7 +161,8 @@ extern unsigned long thread_saved_pc(struct task_struct *t); extern void show_code(struct pt_regs *regs); extern void print_fn_code(unsigned char *code, unsigned long len); -extern int insn_to_mnemonic(unsigned char *instruction, char buf[8]); +extern int insn_to_mnemonic(unsigned char *instruction, char *buf, + unsigned int len); unsigned long get_wchan(struct task_struct *p); #define task_pt_regs(tsk) ((struct pt_regs *) \ diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 3ee5da3..559512a 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -9,9 +9,7 @@ #include <uapi/asm/ptrace.h> #ifndef __ASSEMBLY__ -#ifndef __s390x__ -#else /* __s390x__ */ -#endif /* __s390x__ */ + extern long psw_kernel_bits; extern long psw_user_bits; @@ -77,8 +75,6 @@ struct per_struct_kernel { #define PER_CONTROL_SUSPENSION 0x00400000UL #define PER_CONTROL_ALTERATION 0x00200000UL -#ifdef __s390x__ -#endif /* __s390x__ */ /* * These are defined as per linux/ptrace.h, which see. */ diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index fe7b997..cd29d2f 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -23,6 +23,7 @@ * type here is what we want [need] for both 32 bit and 64 bit systems. */ extern const unsigned int sys_call_table[]; +extern const unsigned int sys_call_table_emu[]; static inline long syscall_get_nr(struct task_struct *task, struct pt_regs *regs) diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 9e2cfe0..eb5f64d 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -14,13 +14,8 @@ #define THREAD_ORDER 1 #define ASYNC_ORDER 1 #else /* CONFIG_64BIT */ -#ifndef __SMALL_STACK #define THREAD_ORDER 2 #define ASYNC_ORDER 2 -#else -#define THREAD_ORDER 1 -#define ASYNC_ORDER 1 -#endif #endif /* CONFIG_64BIT */ #define THREAD_SIZE (PAGE_SIZE << THREAD_ORDER) @@ -41,6 +36,7 @@ struct thread_info { struct task_struct *task; /* main task structure */ struct exec_domain *exec_domain; /* execution domain */ unsigned long flags; /* low level flags */ + unsigned long sys_call_table; /* System call table address */ unsigned int cpu; /* current CPU */ int preempt_count; /* 0 => preemptable, <0 => BUG */ struct restart_block restart_block; diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h index a5ca214..3aa9f1e 100644 --- a/arch/s390/include/uapi/asm/ptrace.h +++ b/arch/s390/include/uapi/asm/ptrace.h @@ -215,12 +215,6 @@ typedef struct unsigned long addr; } __attribute__ ((aligned(8))) psw_t; -typedef struct -{ - __u32 mask; - __u32 addr; -} __attribute__ ((aligned(8))) psw_compat_t; - #ifndef __s390x__ #define PSW_MASK_PER 0x40000000UL @@ -295,20 +289,6 @@ typedef struct unsigned long orig_gpr2; } s390_regs; -typedef struct -{ - psw_compat_t psw; - __u32 gprs[NUM_GPRS]; - __u32 acrs[NUM_ACRS]; - __u32 orig_gpr2; -} s390_compat_regs; - -typedef struct -{ - __u32 gprs_high[NUM_GPRS]; -} s390_compat_regs_high; - - /* * Now for the user space program event recording (trace) definitions. * The following structures are used only for the ptrace interface, don't diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h index 5acca0a..a61d538 100644 --- a/arch/s390/include/uapi/asm/statfs.h +++ b/arch/s390/include/uapi/asm/statfs.h @@ -7,9 +7,6 @@ #ifndef _S390_STATFS_H #define _S390_STATFS_H -#ifndef __s390x__ -#include <asm-generic/statfs.h> -#else /* * We can't use <asm-generic/statfs.h> because in 64-bit mode * we mix ints of different sizes in our struct statfs. @@ -21,49 +18,33 @@ typedef __kernel_fsid_t fsid_t; #endif struct statfs { - int f_type; - int f_bsize; - long f_blocks; - long f_bfree; - long f_bavail; - long f_files; - long f_ffree; + unsigned int f_type; + unsigned int f_bsize; + unsigned long f_blocks; + unsigned long f_bfree; + unsigned long f_bavail; + unsigned long f_files; + unsigned long f_ffree; __kernel_fsid_t f_fsid; - int f_namelen; - int f_frsize; - int f_flags; - int f_spare[4]; + unsigned int f_namelen; + unsigned int f_frsize; + unsigned int f_flags; + unsigned int f_spare[4]; }; struct statfs64 { - int f_type; - int f_bsize; - long f_blocks; - long f_bfree; - long f_bavail; - long f_files; - long f_ffree; + unsigned int f_type; + unsigned int f_bsize; + unsigned long f_blocks; + unsigned long f_bfree; + unsigned long f_bavail; + unsigned long f_files; + unsigned long f_ffree; __kernel_fsid_t f_fsid; - int f_namelen; - int f_frsize; - int f_flags; - int f_spare[4]; + unsigned int f_namelen; + unsigned int f_frsize; + unsigned int f_flags; + unsigned int f_spare[4]; }; -struct compat_statfs64 { - __u32 f_type; - __u32 f_bsize; - __u64 f_blocks; - __u64 f_bfree; - __u64 f_bavail; - __u64 f_files; - __u64 f_ffree; - __kernel_fsid_t f_fsid; - __u32 f_namelen; - __u32 f_frsize; - __u32 f_flags; - __u32 f_spare[4]; -}; - -#endif /* __s390x__ */ #endif diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 2ac311e..1386fca 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -14,16 +14,25 @@ endif CFLAGS_smp.o := -Wno-nonnull # +# Disable tailcall optimizations for stack / callchain walking functions +# since this might generate broken code when accessing register 15 and +# passing its content to other functions. +# +CFLAGS_stacktrace.o += -fno-optimize-sibling-calls +CFLAGS_dumpstack.o += -fno-optimize-sibling-calls + +# # Pass UTS_MACHINE for user_regset definition # CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w -obj-y := bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o \ - processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o \ - debug.o irq.o ipl.o dis.o diag.o mem_detect.o sclp.o vdso.o \ - sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o +obj-y := bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o +obj-y += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o +obj-y += debug.o irq.o ipl.o dis.o diag.o mem_detect.o sclp.o vdso.o +obj-y += sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o +obj-y += dumpstack.o obj-y += $(if $(CONFIG_64BIT),entry64.o,entry.o) obj-y += $(if $(CONFIG_64BIT),reipl64.o,reipl.o) diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index fface87..7a82f9f 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -35,6 +35,7 @@ int main(void) DEFINE(__TI_task, offsetof(struct thread_info, task)); DEFINE(__TI_domain, offsetof(struct thread_info, exec_domain)); DEFINE(__TI_flags, offsetof(struct thread_info, flags)); + DEFINE(__TI_sysc_table, offsetof(struct thread_info, sys_call_table)); DEFINE(__TI_cpu, offsetof(struct thread_info, cpu)); DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count)); DEFINE(__TI_user_timer, offsetof(struct thread_info, user_timer)); diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 6de049f..c439ac9 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -362,6 +362,7 @@ static int setup_frame32(int sig, struct k_sigaction *ka, /* set extra registers only for synchronous signals */ regs->gprs[4] = regs->int_code & 127; regs->gprs[5] = regs->int_parm_long; + regs->gprs[6] = task_thread_info(current)->last_break; } /* Place signal number on stack to allow backtrace from handler. */ @@ -421,6 +422,7 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, regs->gprs[2] = map_signal(sig); regs->gprs[3] = (__force __u64) &frame->info; regs->gprs[4] = (__force __u64) &frame->uc; + regs->gprs[5] = task_thread_info(current)->last_break; return 0; give_sigsegv: diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 3ad5e95..7f4a4a8 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -1696,14 +1696,15 @@ static struct insn *find_insn(unsigned char *code) * insn_to_mnemonic - decode an s390 instruction * @instruction: instruction to decode * @buf: buffer to fill with mnemonic + * @len: length of buffer * * Decode the instruction at @instruction and store the corresponding - * mnemonic into @buf. + * mnemonic into @buf of length @len. * @buf is left unchanged if the instruction could not be decoded. * Returns: * %0 on success, %-ENOENT if the instruction was not found. */ -int insn_to_mnemonic(unsigned char *instruction, char buf[8]) +int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len) { struct insn *insn; @@ -1711,10 +1712,10 @@ int insn_to_mnemonic(unsigned char *instruction, char buf[8]) if (!insn) return -ENOENT; if (insn->name[0] == '\0') - snprintf(buf, 8, "%s", + snprintf(buf, len, "%s", long_insn_name[(int) insn->name[1]]); else - snprintf(buf, 8, "%.5s", insn->name); + snprintf(buf, len, "%.5s", insn->name); return 0; } EXPORT_SYMBOL_GPL(insn_to_mnemonic); diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c new file mode 100644 index 0000000..03dce39 --- /dev/null +++ b/arch/s390/kernel/dumpstack.c @@ -0,0 +1,236 @@ +/* + * Stack dumping functions + * + * Copyright IBM Corp. 1999, 2013 + */ + +#include <linux/kallsyms.h> +#include <linux/hardirq.h> +#include <linux/kprobes.h> +#include <linux/utsname.h> +#include <linux/export.h> +#include <linux/kdebug.h> +#include <linux/ptrace.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <asm/processor.h> +#include <asm/debug.h> +#include <asm/ipl.h> + +#ifndef CONFIG_64BIT +#define LONG "%08lx " +#define FOURLONG "%08lx %08lx %08lx %08lx\n" +static int kstack_depth_to_print = 12; +#else /* CONFIG_64BIT */ +#define LONG "%016lx " +#define FOURLONG "%016lx %016lx %016lx %016lx\n" +static int kstack_depth_to_print = 20; +#endif /* CONFIG_64BIT */ + +/* + * For show_trace we have tree different stack to consider: + * - the panic stack which is used if the kernel stack has overflown + * - the asynchronous interrupt stack (cpu related) + * - the synchronous kernel stack (process related) + * The stack trace can start at any of the three stack and can potentially + * touch all of them. The order is: panic stack, async stack, sync stack. + */ +static unsigned long +__show_trace(unsigned long sp, unsigned long low, unsigned long high) +{ + struct stack_frame *sf; + struct pt_regs *regs; + + while (1) { + sp = sp & PSW_ADDR_INSN; + if (sp < low || sp > high - sizeof(*sf)) + return sp; + sf = (struct stack_frame *) sp; + printk("([<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); + print_symbol("%s)\n", sf->gprs[8] & PSW_ADDR_INSN); + /* Follow the backchain. */ + while (1) { + low = sp; + sp = sf->back_chain & PSW_ADDR_INSN; + if (!sp) + break; + if (sp <= low || sp > high - sizeof(*sf)) + return sp; + sf = (struct stack_frame *) sp; + printk(" [<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); + print_symbol("%s\n", sf->gprs[8] & PSW_ADDR_INSN); + } + /* Zero backchain detected, check for interrupt frame. */ + sp = (unsigned long) (sf + 1); + if (sp <= low || sp > high - sizeof(*regs)) + return sp; + regs = (struct pt_regs *) sp; + printk(" [<%016lx>] ", regs->psw.addr & PSW_ADDR_INSN); + print_symbol("%s\n", regs->psw.addr & PSW_ADDR_INSN); + low = sp; + sp = regs->gprs[15]; + } +} + +static void show_trace(struct task_struct *task, unsigned long *stack) +{ + register unsigned long __r15 asm ("15"); + unsigned long sp; + + sp = (unsigned long) stack; + if (!sp) + sp = task ? task->thread.ksp : __r15; + printk("Call Trace:\n"); +#ifdef CONFIG_CHECK_STACK + sp = __show_trace(sp, S390_lowcore.panic_stack - 4096, + S390_lowcore.panic_stack); +#endif + sp = __show_trace(sp, S390_lowcore.async_stack - ASYNC_SIZE, + S390_lowcore.async_stack); + if (task) + __show_trace(sp, (unsigned long) task_stack_page(task), + (unsigned long) task_stack_page(task) + THREAD_SIZE); + else + __show_trace(sp, S390_lowcore.thread_info, + S390_lowcore.thread_info + THREAD_SIZE); + if (!task) + task = current; + debug_show_held_locks(task); +} + +void show_stack(struct task_struct *task, unsigned long *sp) +{ + register unsigned long *__r15 asm ("15"); + unsigned long *stack; + int i; + + if (!sp) + stack = task ? (unsigned long *) task->thread.ksp : __r15; + else + stack = sp; + + for (i = 0; i < kstack_depth_to_print; i++) { + if (((addr_t) stack & (THREAD_SIZE-1)) == 0) + break; + if ((i * sizeof(long) % 32) == 0) + printk("%s ", i == 0 ? "" : "\n"); + printk(LONG, *stack++); + } + printk("\n"); + show_trace(task, sp); +} + +static void show_last_breaking_event(struct pt_regs *regs) +{ +#ifdef CONFIG_64BIT + printk("Last Breaking-Event-Address:\n"); + printk(" [<%016lx>] ", regs->args[0] & PSW_ADDR_INSN); + print_symbol("%s\n", regs->args[0] & PSW_ADDR_INSN); +#endif +} + +/* + * The architecture-independent dump_stack generator + */ +void dump_stack(void) +{ + printk("CPU: %d %s %s %.*s\n", + task_thread_info(current)->cpu, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + printk("Process %s (pid: %d, task: %p, ksp: %p)\n", + current->comm, current->pid, current, + (void *) current->thread.ksp); + show_stack(NULL, NULL); +} +EXPORT_SYMBOL(dump_stack); + +static inline int mask_bits(struct pt_regs *regs, unsigned long bits) +{ + return (regs->psw.mask & bits) / ((~bits + 1) & bits); +} + +void show_registers(struct pt_regs *regs) +{ + char *mode; + + mode = user_mode(regs) ? "User" : "Krnl"; + printk("%s PSW : %p %p", + mode, (void *) regs->psw.mask, + (void *) regs->psw.addr); + print_symbol(" (%s)\n", regs->psw.addr & PSW_ADDR_INSN); + printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x " + "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER), + mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO), + mask_bits(regs, PSW_MASK_EXT), mask_bits(regs, PSW_MASK_KEY), + mask_bits(regs, PSW_MASK_MCHECK), mask_bits(regs, PSW_MASK_WAIT), + mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC), + mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM)); +#ifdef CONFIG_64BIT + printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA)); +#endif + printk("\n%s GPRS: " FOURLONG, mode, + regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]); + printk(" " FOURLONG, + regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]); + printk(" " FOURLONG, + regs->gprs[8], regs->gprs[9], regs->gprs[10], regs->gprs[11]); + printk(" " FOURLONG, + regs->gprs[12], regs->gprs[13], regs->gprs[14], regs->gprs[15]); + show_code(regs); +} + +void show_regs(struct pt_regs *regs) +{ + printk("CPU: %d %s %s %.*s\n", + task_thread_info(current)->cpu, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + printk("Process %s (pid: %d, task: %p, ksp: %p)\n", + current->comm, current->pid, current, + (void *) current->thread.ksp); + show_registers(regs); + /* Show stack backtrace if pt_regs is from kernel mode */ + if (!user_mode(regs)) + show_trace(NULL, (unsigned long *) regs->gprs[15]); + show_last_breaking_event(regs); +} + +static DEFINE_SPINLOCK(die_lock); + +void die(struct pt_regs *regs, const char *str) +{ + static int die_counter; + + oops_enter(); + lgr_info_log(); + debug_stop_all(); + console_verbose(); + spin_lock_irq(&die_lock); + bust_spinlocks(1); + printk("%s: %04x [#%d] ", str, regs->int_code & 0xffff, ++die_counter); +#ifdef CONFIG_PREEMPT + printk("PREEMPT "); +#endif +#ifdef CONFIG_SMP + printk("SMP "); +#endif +#ifdef CONFIG_DEBUG_PAGEALLOC + printk("DEBUG_PAGEALLOC"); +#endif + printk("\n"); + notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV); + print_modules(); + show_regs(regs); + bust_spinlocks(0); + add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); + spin_unlock_irq(&die_lock); + if (in_interrupt()) + panic("Fatal exception in interrupt"); + if (panic_on_oops) + panic("Fatal exception: panic_on_oops"); + oops_exit(); + do_exit(SIGSEGV); +} diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 94feff7..4d5e6f8 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -45,6 +45,7 @@ _TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT +STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE #define BASED(name) name-system_call(%r13) @@ -97,10 +98,10 @@ STACK_SIZE = 1 << STACK_SHIFT sra %r14,\shift jnz 1f CHECK_STACK 1<<\shift,\savearea + ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: l %r15,\stack # load target stack -2: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) .endm .macro ADD64 high,low,timer @@ -150,7 +151,7 @@ ENTRY(__switch_to) l %r4,__THREAD_info(%r2) # get thread_info of prev l %r5,__THREAD_info(%r3) # get thread_info of next lr %r15,%r5 - ahi %r15,STACK_SIZE # end of kernel stack of next + ahi %r15,STACK_INIT # end of kernel stack of next st %r3,__LC_CURRENT # store task struct of next st %r5,__LC_THREAD_INFO # store thread info of next st %r15,__LC_KERNEL_STACK # store end of kernel stack @@ -178,7 +179,6 @@ sysc_stm: l %r13,__LC_SVC_NEW_PSW+4 sysc_per: l %r15,__LC_KERNEL_STACK - ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs sysc_vtime: UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER @@ -188,6 +188,7 @@ sysc_vtime: mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC sysc_do_svc: oi __TI_flags+3(%r12),_TIF_SYSCALL + l %r10,__TI_sysc_table(%r12) # 31 bit system call table lh %r8,__PT_INT_CODE+2(%r11) sla %r8,2 # shift and test for svc0 jnz sysc_nr_ok @@ -198,7 +199,6 @@ sysc_do_svc: lr %r8,%r1 sla %r8,2 sysc_nr_ok: - l %r10,BASED(.Lsys_call_table) # 31 bit system call table xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) st %r2,__PT_ORIG_GPR2(%r11) st %r7,STACK_FRAME_OVERHEAD(%r15) @@ -359,11 +359,11 @@ ENTRY(pgm_check_handler) tm __LC_PGM_ILC+3,0x80 # check for per exception jnz pgm_svcper # -> single stepped svc 0: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC + ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER l %r15,__LC_KERNEL_STACK -2: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_SAVE_AREA_SYNC stm %r8,%r9,__PT_PSW(%r11) @@ -485,7 +485,6 @@ io_work: # io_work_user: l %r1,__LC_KERNEL_STACK - ahi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) @@ -646,7 +645,6 @@ mcck_skip: tm __PT_PSW+1(%r11),0x01 # returning to user ? jno mcck_return l %r1,__LC_KERNEL_STACK # switch to kernel stack - ahi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r15) @@ -674,6 +672,7 @@ mcck_panic: sra %r14,PAGE_SHIFT jz 0f l %r15,__LC_PANIC_STACK + j mcck_skip 0: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j mcck_skip @@ -714,12 +713,10 @@ ENTRY(restart_int_handler) */ stack_overflow: l %r15,__LC_PANIC_STACK # change to panic stack - ahi %r15,-__PT_SIZE # create pt_regs - stm %r0,%r7,__PT_R0(%r15) - stm %r8,%r9,__PT_PSW(%r15) + la %r11,STACK_FRAME_OVERHEAD(%r15) + stm %r0,%r7,__PT_R0(%r11) + stm %r8,%r9,__PT_PSW(%r11) mvc __PT_R8(32,%r11),0(%r14) - lr %r15,%r11 - ahi %r15,-STACK_FRAME_OVERHEAD l %r1,BASED(1f) xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) lr %r2,%r11 # pass pointer to pt_regs @@ -799,15 +796,14 @@ cleanup_system_call: mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER # set up saved register 11 l %r15,__LC_KERNEL_STACK - ahi %r15,-__PT_SIZE - st %r15,12(%r11) # r11 pt_regs pointer + la %r9,STACK_FRAME_OVERHEAD(%r15) + st %r9,12(%r11) # r11 pt_regs pointer # fill pt_regs - mvc __PT_R8(32,%r15),__LC_SAVE_AREA_SYNC - stm %r0,%r7,__PT_R0(%r15) - mvc __PT_PSW(8,%r15),__LC_SVC_OLD_PSW - mvc __PT_INT_CODE(4,%r15),__LC_SVC_ILC + mvc __PT_R8(32,%r9),__LC_SAVE_AREA_SYNC + stm %r0,%r7,__PT_R0(%r9) + mvc __PT_PSW(8,%r9),__LC_SVC_OLD_PSW + mvc __PT_INT_CODE(4,%r9),__LC_SVC_ILC # setup saved register 15 - ahi %r15,-STACK_FRAME_OVERHEAD st %r15,28(%r11) # r15 stack pointer # set new psw address and exit l %r9,BASED(cleanup_table+4) # sysc_do_svc + 0x80000000 @@ -910,7 +906,6 @@ cleanup_idle_wait: .Ltrace_enter: .long do_syscall_trace_enter .Ltrace_exit: .long do_syscall_trace_exit .Lschedule_tail: .long schedule_tail -.Lsys_call_table: .long sys_call_table .Lsysc_per: .long sysc_per + 0x80000000 #ifdef CONFIG_TRACE_IRQFLAGS .Lhardirqs_on: .long trace_hardirqs_on_caller diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index c3a736a..aa0ab02 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -7,6 +7,7 @@ #include <asm/cputime.h> extern void *restart_stack; +extern unsigned long suspend_zero_pages; void system_call(void); void pgm_check_handler(void); diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 2e6d60c..4c17eec 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -39,6 +39,7 @@ __PT_R15 = __PT_GPRS + 120 STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT +STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING | _TIF_PER_TRAP ) @@ -124,10 +125,10 @@ _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) srag %r14,%r14,\shift jnz 1f CHECK_STACK 1<<\shift,\savearea + aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: lg %r15,\stack # load target stack -2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) .endm .macro UPDATE_VTIME scratch,enter_timer @@ -177,7 +178,7 @@ ENTRY(__switch_to) lg %r4,__THREAD_info(%r2) # get thread_info of prev lg %r5,__THREAD_info(%r3) # get thread_info of next lgr %r15,%r5 - aghi %r15,STACK_SIZE # end of kernel stack of next + aghi %r15,STACK_INIT # end of kernel stack of next stg %r3,__LC_CURRENT # store task struct of next stg %r5,__LC_THREAD_INFO # store thread info of next stg %r15,__LC_KERNEL_STACK # store end of kernel stack @@ -203,10 +204,8 @@ sysc_stmg: stmg %r8,%r15,__LC_SAVE_AREA_SYNC lg %r10,__LC_LAST_BREAK lg %r12,__LC_THREAD_INFO - larl %r13,system_call sysc_per: lg %r15,__LC_KERNEL_STACK - aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs sysc_vtime: UPDATE_VTIME %r13,__LC_SYNC_ENTER_TIMER @@ -217,6 +216,7 @@ sysc_vtime: mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC sysc_do_svc: oi __TI_flags+7(%r12),_TIF_SYSCALL + lg %r10,__TI_sysc_table(%r12) # address of system call table llgh %r8,__PT_INT_CODE+2(%r11) slag %r8,%r8,2 # shift and test for svc 0 jnz sysc_nr_ok @@ -227,13 +227,6 @@ sysc_do_svc: sth %r1,__PT_INT_CODE+2(%r11) slag %r8,%r1,2 sysc_nr_ok: - larl %r10,sys_call_table # 64 bit system call table -#ifdef CONFIG_COMPAT - tm __TI_flags+5(%r12),(_TIF_31BIT>>16) - jno sysc_noemu - larl %r10,sys_call_table_emu # 31 bit system call table -sysc_noemu: -#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) stg %r2,__PT_ORIG_GPR2(%r11) stg %r7,STACK_FRAME_OVERHEAD(%r15) @@ -389,6 +382,7 @@ ENTRY(pgm_check_handler) tm __LC_PGM_ILC+3,0x80 # check for per exception jnz pgm_svcper # -> single stepped svc 0: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC + aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: UPDATE_VTIME %r14,__LC_SYNC_ENTER_TIMER LAST_BREAK %r14 @@ -398,8 +392,7 @@ ENTRY(pgm_check_handler) tm __LC_PGM_ILC+2,0x02 # check for transaction abort jz 2f mvc __THREAD_trap_tdb(256,%r14),0(%r13) -2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC stmg %r8,%r9,__PT_PSW(%r11) @@ -526,7 +519,6 @@ io_work: # io_work_user: lg %r1,__LC_KERNEL_STACK - aghi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) @@ -688,7 +680,6 @@ mcck_skip: tm __PT_PSW+1(%r11),0x01 # returning to user ? jno mcck_return lg %r1,__LC_KERNEL_STACK # switch to kernel stack - aghi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) @@ -755,14 +746,12 @@ ENTRY(restart_int_handler) * Setup a pt_regs so that show_trace can provide a good call trace. */ stack_overflow: - lg %r11,__LC_PANIC_STACK # change to panic stack - aghi %r11,-__PT_SIZE # create pt_regs + lg %r15,__LC_PANIC_STACK # change to panic stack + la %r11,STACK_FRAME_OVERHEAD(%r15) stmg %r0,%r7,__PT_R0(%r11) stmg %r8,%r9,__PT_PSW(%r11) mvc __PT_R8(64,%r11),0(%r14) stg %r10,__PT_ORIG_GPR2(%r11) # store last break to orig_gpr2 - lgr %r15,%r11 - aghi %r15,-STACK_FRAME_OVERHEAD xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs jg kernel_stack_overflow @@ -846,15 +835,14 @@ cleanup_system_call: mvc __TI_last_break(8,%r12),16(%r11) 0: # set up saved register r11 lg %r15,__LC_KERNEL_STACK - aghi %r15,-__PT_SIZE - stg %r15,24(%r11) # r11 pt_regs pointer + la %r9,STACK_FRAME_OVERHEAD(%r15) + stg %r9,24(%r11) # r11 pt_regs pointer # fill pt_regs - mvc __PT_R8(64,%r15),__LC_SAVE_AREA_SYNC - stmg %r0,%r7,__PT_R0(%r15) - mvc __PT_PSW(16,%r15),__LC_SVC_OLD_PSW - mvc __PT_INT_CODE(4,%r15),__LC_SVC_ILC + mvc __PT_R8(64,%r9),__LC_SAVE_AREA_SYNC + stmg %r0,%r7,__PT_R0(%r9) + mvc __PT_PSW(16,%r9),__LC_SVC_OLD_PSW + mvc __PT_INT_CODE(4,%r9),__LC_SVC_ILC # setup saved register r15 - aghi %r15,-STACK_FRAME_OVERHEAD stg %r15,56(%r11) # r15 stack pointer # set new psw address and exit larl %r9,sysc_do_svc @@ -1011,6 +999,7 @@ sys_call_table: #ifdef CONFIG_COMPAT #define SYSCALL(esa,esame,emu) .long emu + .globl sys_call_table_emu sys_call_table_emu: #include "syscalls.S" #undef SYSCALL diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index b3de277..ac21781 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -13,6 +13,7 @@ #include <linux/reboot.h> #include <linux/ftrace.h> #include <linux/debug_locks.h> +#include <linux/suspend.h> #include <asm/cio.h> #include <asm/setup.h> #include <asm/pgtable.h> @@ -67,6 +68,35 @@ void setup_regs(void) memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area)); } +/* + * PM notifier callback for kdump + */ +static int machine_kdump_pm_cb(struct notifier_block *nb, unsigned long action, + void *ptr) +{ + switch (action) { + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + if (crashk_res.start) + crash_map_reserved_pages(); + break; + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + if (crashk_res.start) + crash_unmap_reserved_pages(); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static int __init machine_kdump_pm_init(void) +{ + pm_notifier(machine_kdump_pm_cb, 0); + return 0; +} +arch_initcall(machine_kdump_pm_init); #endif /* diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 536d645..2bc3edd 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -61,18 +61,8 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return sf->gprs[8]; } -/* - * The idle loop on a S390... - */ -static void default_idle(void) +void arch_cpu_idle(void) { - if (cpu_is_offline(smp_processor_id())) - cpu_die(); - local_irq_disable(); - if (need_resched()) { - local_irq_enable(); - return; - } local_mcck_disable(); if (test_thread_flag(TIF_MCCK_PENDING)) { local_mcck_enable(); @@ -83,19 +73,15 @@ static void default_idle(void) vtime_stop_cpu(); } -void cpu_idle(void) +void arch_cpu_idle_exit(void) { - for (;;) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - while (!need_resched() && !test_thread_flag(TIF_MCCK_PENDING)) - default_idle(); - rcu_idle_exit(); - tick_nohz_idle_exit(); - if (test_thread_flag(TIF_MCCK_PENDING)) - s390_handle_mcck(); - schedule_preempt_disabled(); - } + if (test_thread_flag(TIF_MCCK_PENDING)) + s390_handle_mcck(); +} + +void arch_cpu_idle_dead(void) +{ + cpu_die(); } extern void __kprobes kernel_thread_starter(void); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 2926885..0f419c5 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -377,11 +377,14 @@ static void __init setup_lowcore(void) PSW_MASK_DAT | PSW_MASK_MCHECK; lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler; lc->clock_comparator = -1ULL; - lc->kernel_stack = ((unsigned long) &init_thread_union) + THREAD_SIZE; + lc->kernel_stack = ((unsigned long) &init_thread_union) + + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->async_stack = (unsigned long) - __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0) + ASYNC_SIZE; + __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0) + + ASYNC_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->panic_stack = (unsigned long) - __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0) + PAGE_SIZE; + __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0) + + PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->current_task = (unsigned long) init_thread_union.thread_info.task; lc->thread_info = (unsigned long) &init_thread_union; lc->machine_flags = S390_lowcore.machine_flags; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 549c9d1..8074cb4 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -181,8 +181,10 @@ static int __cpuinit pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) lc = pcpu->lowcore; memcpy(lc, &S390_lowcore, 512); memset((char *) lc + 512, 0, sizeof(*lc) - 512); - lc->async_stack = pcpu->async_stack + ASYNC_SIZE; - lc->panic_stack = pcpu->panic_stack + PAGE_SIZE; + lc->async_stack = pcpu->async_stack + ASYNC_SIZE + - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); + lc->panic_stack = pcpu->panic_stack + PAGE_SIZE + - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->cpu_nr = cpu; #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) { @@ -253,7 +255,8 @@ static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk) struct _lowcore *lc = pcpu->lowcore; struct thread_info *ti = task_thread_info(tsk); - lc->kernel_stack = (unsigned long) task_stack_page(tsk) + THREAD_SIZE; + lc->kernel_stack = (unsigned long) task_stack_page(tsk) + + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->thread_info = (unsigned long) task_thread_info(tsk); lc->current_task = (unsigned long) tsk; lc->user_timer = ti->user_timer; @@ -711,8 +714,7 @@ static void __cpuinit smp_start_secondary(void *cpuvoid) set_cpu_online(smp_processor_id(), true); inc_irq_stat(CPU_RST); local_irq_enable(); - /* cpu_idle will call schedule for us */ - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } /* Upping and downing of CPUs */ @@ -810,8 +812,10 @@ void __init smp_prepare_boot_cpu(void) pcpu->state = CPU_STATE_CONFIGURED; pcpu->address = boot_cpu_address; pcpu->lowcore = (struct _lowcore *)(unsigned long) store_prefix(); - pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE; - pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE; + pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE + + STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); + pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE + + STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); S390_lowcore.percpu_offset = __per_cpu_offset[0]; smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN); set_cpu_present(0, true); diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c index aa1494d..c479d2f 100644 --- a/arch/s390/kernel/suspend.c +++ b/arch/s390/kernel/suspend.c @@ -41,6 +41,7 @@ struct page_key_data { static struct page_key_data *page_key_data; static struct page_key_data *page_key_rp, *page_key_wp; static unsigned long page_key_rx, page_key_wx; +unsigned long suspend_zero_pages; /* * For each page in the hibernation image one additional byte is @@ -149,6 +150,36 @@ int pfn_is_nosave(unsigned long pfn) return 0; } +/* + * PM notifier callback for suspend + */ +static int suspend_pm_cb(struct notifier_block *nb, unsigned long action, + void *ptr) +{ + switch (action) { + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + suspend_zero_pages = __get_free_pages(GFP_KERNEL, LC_ORDER); + if (!suspend_zero_pages) + return NOTIFY_BAD; + break; + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + free_pages(suspend_zero_pages, LC_ORDER); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static int __init suspend_pm_init(void) +{ + pm_notifier(suspend_pm_cb, 0); + return 0; +} +arch_initcall(suspend_pm_init); + void save_processor_state(void) { /* swsusp_arch_suspend() actually saves all cpu register contents. diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index d4ca4e0..c487be4 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -36,8 +36,8 @@ ENTRY(swsusp_arch_suspend) /* Store prefix register on stack */ stpx __SF_EMPTY(%r15) - /* Save prefix register contents for lowcore */ - llgf %r4,__SF_EMPTY(%r15) + /* Save prefix register contents for lowcore copy */ + llgf %r10,__SF_EMPTY(%r15) /* Get pointer to save area */ lghi %r1,0x1000 @@ -91,7 +91,18 @@ ENTRY(swsusp_arch_suspend) xc __SF_EMPTY(4,%r15),__SF_EMPTY(%r15) spx __SF_EMPTY(%r15) + /* Save absolute zero pages */ + larl %r2,suspend_zero_pages + lg %r2,0(%r2) + lghi %r4,0 + lghi %r3,2*PAGE_SIZE + lghi %r5,2*PAGE_SIZE +1: mvcle %r2,%r4,0 + jo 1b + + /* Copy lowcore to absolute zero lowcore */ lghi %r2,0 + lgr %r4,%r10 lghi %r3,2*PAGE_SIZE lghi %r5,2*PAGE_SIZE 1: mvcle %r2,%r4,0 @@ -248,8 +259,20 @@ restore_registers: /* Load old stack */ lg %r15,0x2f8(%r13) + /* Save prefix register */ + mvc __SF_EMPTY(4,%r15),0x318(%r13) + + /* Restore absolute zero pages */ + lghi %r2,0 + larl %r4,suspend_zero_pages + lg %r4,0(%r4) + lghi %r3,2*PAGE_SIZE + lghi %r5,2*PAGE_SIZE +1: mvcle %r2,%r4,0 + jo 1b + /* Restore prefix register */ - spx 0x318(%r13) + spx __SF_EMPTY(%r15) /* Activate DAT */ stosm __SF_EMPTY(%r15),0x04 diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 13dd63f..c576232 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -12,49 +12,16 @@ * 'Traps.c' handles hardware traps and faults after we have saved some * state in 'asm.s'. */ -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> +#include <linux/kprobes.h> +#include <linux/kdebug.h> +#include <linux/module.h> #include <linux/ptrace.h> -#include <linux/timer.h> +#include <linux/sched.h> #include <linux/mm.h> -#include <linux/smp.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/seq_file.h> -#include <linux/delay.h> -#include <linux/module.h> -#include <linux/kdebug.h> -#include <linux/kallsyms.h> -#include <linux/reboot.h> -#include <linux/kprobes.h> -#include <linux/bug.h> -#include <linux/utsname.h> -#include <asm/uaccess.h> -#include <asm/io.h> -#include <linux/atomic.h> -#include <asm/mathemu.h> -#include <asm/cpcmd.h> -#include <asm/lowcore.h> -#include <asm/debug.h> -#include <asm/ipl.h> #include "entry.h" int show_unhandled_signals = 1; -#define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; }) - -#ifndef CONFIG_64BIT -#define LONG "%08lx " -#define FOURLONG "%08lx %08lx %08lx %08lx\n" -static int kstack_depth_to_print = 12; -#else /* CONFIG_64BIT */ -#define LONG "%016lx " -#define FOURLONG "%016lx %016lx %016lx %016lx\n" -static int kstack_depth_to_print = 20; -#endif /* CONFIG_64BIT */ - static inline void __user *get_trap_ip(struct pt_regs *regs) { #ifdef CONFIG_64BIT @@ -72,215 +39,6 @@ static inline void __user *get_trap_ip(struct pt_regs *regs) #endif } -/* - * For show_trace we have tree different stack to consider: - * - the panic stack which is used if the kernel stack has overflown - * - the asynchronous interrupt stack (cpu related) - * - the synchronous kernel stack (process related) - * The stack trace can start at any of the three stack and can potentially - * touch all of them. The order is: panic stack, async stack, sync stack. - */ -static unsigned long -__show_trace(unsigned long sp, unsigned long low, unsigned long high) -{ - struct stack_frame *sf; - struct pt_regs *regs; - - while (1) { - sp = sp & PSW_ADDR_INSN; - if (sp < low || sp > high - sizeof(*sf)) - return sp; - sf = (struct stack_frame *) sp; - printk("([<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); - print_symbol("%s)\n", sf->gprs[8] & PSW_ADDR_INSN); - /* Follow the backchain. */ - while (1) { - low = sp; - sp = sf->back_chain & PSW_ADDR_INSN; - if (!sp) - break; - if (sp <= low || sp > high - sizeof(*sf)) - return sp; - sf = (struct stack_frame *) sp; - printk(" [<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); - print_symbol("%s\n", sf->gprs[8] & PSW_ADDR_INSN); - } - /* Zero backchain detected, check for interrupt frame. */ - sp = (unsigned long) (sf + 1); - if (sp <= low || sp > high - sizeof(*regs)) - return sp; - regs = (struct pt_regs *) sp; - printk(" [<%016lx>] ", regs->psw.addr & PSW_ADDR_INSN); - print_symbol("%s\n", regs->psw.addr & PSW_ADDR_INSN); - low = sp; - sp = regs->gprs[15]; - } -} - -static void show_trace(struct task_struct *task, unsigned long *stack) -{ - register unsigned long __r15 asm ("15"); - unsigned long sp; - - sp = (unsigned long) stack; - if (!sp) - sp = task ? task->thread.ksp : __r15; - printk("Call Trace:\n"); -#ifdef CONFIG_CHECK_STACK - sp = __show_trace(sp, S390_lowcore.panic_stack - 4096, - S390_lowcore.panic_stack); -#endif - sp = __show_trace(sp, S390_lowcore.async_stack - ASYNC_SIZE, - S390_lowcore.async_stack); - if (task) - __show_trace(sp, (unsigned long) task_stack_page(task), - (unsigned long) task_stack_page(task) + THREAD_SIZE); - else - __show_trace(sp, S390_lowcore.thread_info, - S390_lowcore.thread_info + THREAD_SIZE); - if (!task) - task = current; - debug_show_held_locks(task); -} - -void show_stack(struct task_struct *task, unsigned long *sp) -{ - register unsigned long * __r15 asm ("15"); - unsigned long *stack; - int i; - - if (!sp) - stack = task ? (unsigned long *) task->thread.ksp : __r15; - else - stack = sp; - - for (i = 0; i < kstack_depth_to_print; i++) { - if (((addr_t) stack & (THREAD_SIZE-1)) == 0) - break; - if ((i * sizeof(long) % 32) == 0) - printk("%s ", i == 0 ? "" : "\n"); - printk(LONG, *stack++); - } - printk("\n"); - show_trace(task, sp); -} - -static void show_last_breaking_event(struct pt_regs *regs) -{ -#ifdef CONFIG_64BIT - printk("Last Breaking-Event-Address:\n"); - printk(" [<%016lx>] ", regs->args[0] & PSW_ADDR_INSN); - print_symbol("%s\n", regs->args[0] & PSW_ADDR_INSN); -#endif -} - -/* - * The architecture-independent dump_stack generator - */ -void dump_stack(void) -{ - printk("CPU: %d %s %s %.*s\n", - task_thread_info(current)->cpu, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - printk("Process %s (pid: %d, task: %p, ksp: %p)\n", - current->comm, current->pid, current, - (void *) current->thread.ksp); - show_stack(NULL, NULL); -} -EXPORT_SYMBOL(dump_stack); - -static inline int mask_bits(struct pt_regs *regs, unsigned long bits) -{ - return (regs->psw.mask & bits) / ((~bits + 1) & bits); -} - -void show_registers(struct pt_regs *regs) -{ - char *mode; - - mode = user_mode(regs) ? "User" : "Krnl"; - printk("%s PSW : %p %p", - mode, (void *) regs->psw.mask, - (void *) regs->psw.addr); - print_symbol(" (%s)\n", regs->psw.addr & PSW_ADDR_INSN); - printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x " - "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER), - mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO), - mask_bits(regs, PSW_MASK_EXT), mask_bits(regs, PSW_MASK_KEY), - mask_bits(regs, PSW_MASK_MCHECK), mask_bits(regs, PSW_MASK_WAIT), - mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC), - mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM)); -#ifdef CONFIG_64BIT - printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA)); -#endif - printk("\n%s GPRS: " FOURLONG, mode, - regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]); - printk(" " FOURLONG, - regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]); - printk(" " FOURLONG, - regs->gprs[8], regs->gprs[9], regs->gprs[10], regs->gprs[11]); - printk(" " FOURLONG, - regs->gprs[12], regs->gprs[13], regs->gprs[14], regs->gprs[15]); - - show_code(regs); -} - -void show_regs(struct pt_regs *regs) -{ - printk("CPU: %d %s %s %.*s\n", - task_thread_info(current)->cpu, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - printk("Process %s (pid: %d, task: %p, ksp: %p)\n", - current->comm, current->pid, current, - (void *) current->thread.ksp); - show_registers(regs); - /* Show stack backtrace if pt_regs is from kernel mode */ - if (!user_mode(regs)) - show_trace(NULL, (unsigned long *) regs->gprs[15]); - show_last_breaking_event(regs); -} - -static DEFINE_SPINLOCK(die_lock); - -void die(struct pt_regs *regs, const char *str) -{ - static int die_counter; - - oops_enter(); - lgr_info_log(); - debug_stop_all(); - console_verbose(); - spin_lock_irq(&die_lock); - bust_spinlocks(1); - printk("%s: %04x [#%d] ", str, regs->int_code & 0xffff, ++die_counter); -#ifdef CONFIG_PREEMPT - printk("PREEMPT "); -#endif -#ifdef CONFIG_SMP - printk("SMP "); -#endif -#ifdef CONFIG_DEBUG_PAGEALLOC - printk("DEBUG_PAGEALLOC"); -#endif - printk("\n"); - notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV); - print_modules(); - show_regs(regs); - bust_spinlocks(0); - add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - spin_unlock_irq(&die_lock); - if (in_interrupt()) - panic("Fatal exception in interrupt"); - if (panic_on_oops) - panic("Fatal exception: panic_on_oops"); - oops_exit(); - do_exit(SIGSEGV); -} - static inline void report_user_fault(struct pt_regs *regs, int signr) { if ((task_pid_nr(current) > 1) && !show_unhandled_signals) diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index a0042ac..3fb0935 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -158,8 +158,6 @@ void __kprobes vtime_stop_cpu(void) unsigned long psw_mask; trace_hardirqs_on(); - /* Don't trace preempt off for idle. */ - stop_critical_timings(); /* Wait for external, I/O or machine check interrupt. */ psw_mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_DAT | @@ -169,9 +167,6 @@ void __kprobes vtime_stop_cpu(void) /* Call the assembler magic in entry.S */ psw_idle(idle, psw_mask); - /* Reenable preemption tracer. */ - start_critical_timings(); - /* Account time spent with enabled wait psw loaded as idle time. */ idle->sequence++; smp_wmb(); diff --git a/arch/s390/kvm/trace.h b/arch/s390/kvm/trace.h index 2b29e62..53252d2 100644 --- a/arch/s390/kvm/trace.h +++ b/arch/s390/kvm/trace.h @@ -117,7 +117,7 @@ TRACE_EVENT(kvm_s390_intercept_instruction, __entry->instruction, insn_to_mnemonic((unsigned char *) &__entry->instruction, - __entry->insn) ? + __entry->insn, sizeof(__entry->insn)) ? "unknown" : __entry->insn) ); diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 479e942..9d84a1f 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -458,12 +458,10 @@ static int __init cmm_init(void) if (rc) goto out_pm; cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread"); - rc = IS_ERR(cmm_thread_ptr) ? PTR_ERR(cmm_thread_ptr) : 0; - if (rc) - goto out_kthread; - return 0; + if (!IS_ERR(cmm_thread_ptr)) + return 0; -out_kthread: + rc = PTR_ERR(cmm_thread_ptr); unregister_pm_notifier(&cmm_power_notifier); out_pm: unregister_oom_notifier(&cmm_oom_nb); diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 2fb9e63..047c3e4 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -395,8 +395,13 @@ void __kprobes do_protection_exception(struct pt_regs *regs) int fault; trans_exc_code = regs->int_parm_long; - /* Protection exception is suppressing, decrement psw address. */ - regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16); + /* + * Protection exceptions are suppressing, decrement psw address. + * The exception to this rule are aborted transactions, for these + * the PSW already points to the correct location. + */ + if (!(regs->int_code & 0x200)) + regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16); /* * Check for low-address protection. This needs to be treated * as a special case because the translation exception code diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 532525e..121089d 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -39,7 +39,7 @@ int arch_prepare_hugepage(struct page *page) if (!ptep) return -ENOMEM; - pte = mk_pte(page, PAGE_RW); + pte_val(pte) = addr; for (i = 0; i < PTRS_PER_PTE; i++) { set_pte_at(&init_mm, addr + i * PAGE_SIZE, ptep + i, pte); pte_val(pte) += PAGE_SIZE; diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 49ce6bb..0b09b23 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -42,11 +42,10 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE))); unsigned long empty_zero_page, zero_page_mask; EXPORT_SYMBOL(empty_zero_page); -static unsigned long __init setup_zero_pages(void) +static void __init setup_zero_pages(void) { struct cpuid cpu_id; unsigned int order; - unsigned long size; struct page *page; int i; @@ -63,10 +62,18 @@ static unsigned long __init setup_zero_pages(void) break; case 0x2097: /* z10 */ case 0x2098: /* z10 */ - default: + case 0x2817: /* z196 */ + case 0x2818: /* z196 */ order = 2; break; + case 0x2827: /* zEC12 */ + default: + order = 5; + break; } + /* Limit number of empty zero pages for small memory sizes */ + if (order > 2 && totalram_pages <= 16384) + order = 2; empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); if (!empty_zero_page) @@ -75,14 +82,11 @@ static unsigned long __init setup_zero_pages(void) page = virt_to_page((void *) empty_zero_page); split_page(page, order); for (i = 1 << order; i > 0; i--) { - SetPageReserved(page); + mark_page_reserved(page); page++; } - size = PAGE_SIZE << order; - zero_page_mask = (size - 1) & PAGE_MASK; - - return 1UL << order; + zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK; } /* @@ -139,7 +143,7 @@ void __init mem_init(void) /* this will put all low memory onto the freelists */ totalram_pages += free_all_bootmem(); - totalram_pages -= setup_zero_pages(); /* Setup zeroed pages. */ + setup_zero_pages(); /* Setup zeroed pages. */ reservedpages = 0; @@ -158,34 +162,15 @@ void __init mem_init(void) PFN_ALIGN((unsigned long)&_eshared) - 1); } -void free_init_pages(char *what, unsigned long begin, unsigned long end) -{ - unsigned long addr = begin; - - if (begin >= end) - return; - for (; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - memset((void *)(addr & PAGE_MASK), POISON_FREE_INITMEM, - PAGE_SIZE); - free_page(addr); - totalram_pages++; - } - printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); -} - void free_initmem(void) { - free_init_pages("unused kernel memory", - (unsigned long)&__init_begin, - (unsigned long)&__init_end); + free_initmem_default(0); } #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_init_pages("initrd memory", start, end); + free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd"); } #endif diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index d21040e..80adfbf 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -9,31 +9,25 @@ #include <asm/pgtable.h> #include <asm/page.h> +static inline unsigned long sske_frame(unsigned long addr, unsigned char skey) +{ + asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],9,0" + : [addr] "+a" (addr) : [skey] "d" (skey)); + return addr; +} + void storage_key_init_range(unsigned long start, unsigned long end) { - unsigned long boundary, function, size; + unsigned long boundary, size; while (start < end) { - if (MACHINE_HAS_EDAT2) { - /* set storage keys for a 2GB frame */ - function = 0x22000 | PAGE_DEFAULT_KEY; - size = 1UL << 31; - boundary = (start + size) & ~(size - 1); - if (boundary <= end) { - do { - start = pfmf(function, start); - } while (start < boundary); - continue; - } - } if (MACHINE_HAS_EDAT1) { /* set storage keys for a 1MB frame */ - function = 0x21000 | PAGE_DEFAULT_KEY; size = 1UL << 20; boundary = (start + size) & ~(size - 1); if (boundary <= end) { do { - start = pfmf(function, start); + start = sske_frame(start, PAGE_DEFAULT_KEY); } while (start < boundary); continue; } diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index ae44d2a..bd954e9 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -379,75 +379,183 @@ out_unmap: } EXPORT_SYMBOL_GPL(gmap_map_segment); -/* - * this function is assumed to be called with mmap_sem held - */ -unsigned long __gmap_fault(unsigned long address, struct gmap *gmap) +static unsigned long *gmap_table_walk(unsigned long address, struct gmap *gmap) { - unsigned long *table, vmaddr, segment; - struct mm_struct *mm; - struct gmap_pgtable *mp; - struct gmap_rmap *rmap; - struct vm_area_struct *vma; - struct page *page; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + unsigned long *table; - current->thread.gmap_addr = address; - mm = gmap->mm; - /* Walk the gmap address space page table */ table = gmap->table + ((address >> 53) & 0x7ff); if (unlikely(*table & _REGION_ENTRY_INV)) - return -EFAULT; + return ERR_PTR(-EFAULT); table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 42) & 0x7ff); if (unlikely(*table & _REGION_ENTRY_INV)) - return -EFAULT; + return ERR_PTR(-EFAULT); table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 31) & 0x7ff); if (unlikely(*table & _REGION_ENTRY_INV)) - return -EFAULT; + return ERR_PTR(-EFAULT); table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 20) & 0x7ff); + return table; +} + +/** + * __gmap_translate - translate a guest address to a user space address + * @address: guest address + * @gmap: pointer to guest mapping meta data structure + * + * Returns user space address which corresponds to the guest address or + * -EFAULT if no such mapping exists. + * This function does not establish potentially missing page table entries. + * The mmap_sem of the mm that belongs to the address space must be held + * when this function gets called. + */ +unsigned long __gmap_translate(unsigned long address, struct gmap *gmap) +{ + unsigned long *segment_ptr, vmaddr, segment; + struct gmap_pgtable *mp; + struct page *page; + current->thread.gmap_addr = address; + segment_ptr = gmap_table_walk(address, gmap); + if (IS_ERR(segment_ptr)) + return PTR_ERR(segment_ptr); /* Convert the gmap address to an mm address. */ - segment = *table; - if (likely(!(segment & _SEGMENT_ENTRY_INV))) { + segment = *segment_ptr; + if (!(segment & _SEGMENT_ENTRY_INV)) { page = pfn_to_page(segment >> PAGE_SHIFT); mp = (struct gmap_pgtable *) page->index; return mp->vmaddr | (address & ~PMD_MASK); } else if (segment & _SEGMENT_ENTRY_RO) { vmaddr = segment & _SEGMENT_ENTRY_ORIGIN; - vma = find_vma(mm, vmaddr); - if (!vma || vma->vm_start > vmaddr) - return -EFAULT; - - /* Walk the parent mm page table */ - pgd = pgd_offset(mm, vmaddr); - pud = pud_alloc(mm, pgd, vmaddr); - if (!pud) - return -ENOMEM; - pmd = pmd_alloc(mm, pud, vmaddr); - if (!pmd) - return -ENOMEM; - if (!pmd_present(*pmd) && - __pte_alloc(mm, vma, pmd, vmaddr)) - return -ENOMEM; - /* pmd now points to a valid segment table entry. */ - rmap = kmalloc(sizeof(*rmap), GFP_KERNEL|__GFP_REPEAT); - if (!rmap) - return -ENOMEM; - /* Link gmap segment table entry location to page table. */ - page = pmd_page(*pmd); - mp = (struct gmap_pgtable *) page->index; - rmap->entry = table; - spin_lock(&mm->page_table_lock); + return vmaddr | (address & ~PMD_MASK); + } + return -EFAULT; +} +EXPORT_SYMBOL_GPL(__gmap_translate); + +/** + * gmap_translate - translate a guest address to a user space address + * @address: guest address + * @gmap: pointer to guest mapping meta data structure + * + * Returns user space address which corresponds to the guest address or + * -EFAULT if no such mapping exists. + * This function does not establish potentially missing page table entries. + */ +unsigned long gmap_translate(unsigned long address, struct gmap *gmap) +{ + unsigned long rc; + + down_read(&gmap->mm->mmap_sem); + rc = __gmap_translate(address, gmap); + up_read(&gmap->mm->mmap_sem); + return rc; +} +EXPORT_SYMBOL_GPL(gmap_translate); + +static int gmap_connect_pgtable(unsigned long segment, + unsigned long *segment_ptr, + struct gmap *gmap) +{ + unsigned long vmaddr; + struct vm_area_struct *vma; + struct gmap_pgtable *mp; + struct gmap_rmap *rmap; + struct mm_struct *mm; + struct page *page; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + + mm = gmap->mm; + vmaddr = segment & _SEGMENT_ENTRY_ORIGIN; + vma = find_vma(mm, vmaddr); + if (!vma || vma->vm_start > vmaddr) + return -EFAULT; + /* Walk the parent mm page table */ + pgd = pgd_offset(mm, vmaddr); + pud = pud_alloc(mm, pgd, vmaddr); + if (!pud) + return -ENOMEM; + pmd = pmd_alloc(mm, pud, vmaddr); + if (!pmd) + return -ENOMEM; + if (!pmd_present(*pmd) && + __pte_alloc(mm, vma, pmd, vmaddr)) + return -ENOMEM; + /* pmd now points to a valid segment table entry. */ + rmap = kmalloc(sizeof(*rmap), GFP_KERNEL|__GFP_REPEAT); + if (!rmap) + return -ENOMEM; + /* Link gmap segment table entry location to page table. */ + page = pmd_page(*pmd); + mp = (struct gmap_pgtable *) page->index; + rmap->entry = segment_ptr; + spin_lock(&mm->page_table_lock); + if (*segment_ptr == segment) { list_add(&rmap->list, &mp->mapper); - spin_unlock(&mm->page_table_lock); /* Set gmap segment table entry to page table. */ - *table = pmd_val(*pmd) & PAGE_MASK; - return vmaddr | (address & ~PMD_MASK); + *segment_ptr = pmd_val(*pmd) & PAGE_MASK; + rmap = NULL; + } + spin_unlock(&mm->page_table_lock); + kfree(rmap); + return 0; +} + +static void gmap_disconnect_pgtable(struct mm_struct *mm, unsigned long *table) +{ + struct gmap_rmap *rmap, *next; + struct gmap_pgtable *mp; + struct page *page; + int flush; + + flush = 0; + spin_lock(&mm->page_table_lock); + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + list_for_each_entry_safe(rmap, next, &mp->mapper, list) { + *rmap->entry = + _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr; + list_del(&rmap->list); + kfree(rmap); + flush = 1; + } + spin_unlock(&mm->page_table_lock); + if (flush) + __tlb_flush_global(); +} + +/* + * this function is assumed to be called with mmap_sem held + */ +unsigned long __gmap_fault(unsigned long address, struct gmap *gmap) +{ + unsigned long *segment_ptr, segment; + struct gmap_pgtable *mp; + struct page *page; + int rc; + + current->thread.gmap_addr = address; + segment_ptr = gmap_table_walk(address, gmap); + if (IS_ERR(segment_ptr)) + return -EFAULT; + /* Convert the gmap address to an mm address. */ + while (1) { + segment = *segment_ptr; + if (!(segment & _SEGMENT_ENTRY_INV)) { + /* Page table is present */ + page = pfn_to_page(segment >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + return mp->vmaddr | (address & ~PMD_MASK); + } + if (!(segment & _SEGMENT_ENTRY_RO)) + /* Nothing mapped in the gmap address space. */ + break; + rc = gmap_connect_pgtable(segment, segment_ptr, gmap); + if (rc) + return rc; } return -EFAULT; } @@ -511,29 +619,6 @@ void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap) } EXPORT_SYMBOL_GPL(gmap_discard); -void gmap_unmap_notifier(struct mm_struct *mm, unsigned long *table) -{ - struct gmap_rmap *rmap, *next; - struct gmap_pgtable *mp; - struct page *page; - int flush; - - flush = 0; - spin_lock(&mm->page_table_lock); - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); - mp = (struct gmap_pgtable *) page->index; - list_for_each_entry_safe(rmap, next, &mp->mapper, list) { - *rmap->entry = - _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr; - list_del(&rmap->list); - kfree(rmap); - flush = 1; - } - spin_unlock(&mm->page_table_lock); - if (flush) - __tlb_flush_global(); -} - static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, unsigned long vmaddr) { @@ -586,8 +671,8 @@ static inline void page_table_free_pgste(unsigned long *table) { } -static inline void gmap_unmap_notifier(struct mm_struct *mm, - unsigned long *table) +static inline void gmap_disconnect_pgtable(struct mm_struct *mm, + unsigned long *table) { } @@ -653,7 +738,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) unsigned int bit, mask; if (mm_has_pgste(mm)) { - gmap_unmap_notifier(mm, table); + gmap_disconnect_pgtable(mm, table); return page_table_free_pgste(table); } /* Free 1K/2K page table fragment of a 4K page */ @@ -696,7 +781,7 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table) mm = tlb->mm; if (mm_has_pgste(mm)) { - gmap_unmap_notifier(mm, table); + gmap_disconnect_pgtable(mm, table); table = (unsigned long *) (__pa(table) | FRAG_MASK); tlb_remove_table(tlb, table); return; diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index ffab84d..3583705 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -191,19 +191,16 @@ static void vmem_remove_range(unsigned long start, unsigned long size) /* * Add a backed mem_map array to the virtual mem_map array. */ -int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) +int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { - unsigned long address, start_addr, end_addr; + unsigned long address = start; pgd_t *pg_dir; pud_t *pu_dir; pmd_t *pm_dir; pte_t *pt_dir; int ret = -ENOMEM; - start_addr = (unsigned long) start; - end_addr = (unsigned long) (start + nr); - - for (address = start_addr; address < end_addr;) { + for (address = start; address < end;) { pg_dir = pgd_offset_k(address); if (pgd_none(*pg_dir)) { pu_dir = vmem_pud_alloc(); @@ -262,14 +259,14 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) } address += PAGE_SIZE; } - memset(start, 0, nr * sizeof(struct page)); + memset((void *)start, 0, end - start); ret = 0; out: - flush_tlb_kernel_range(start_addr, end_addr); + flush_tlb_kernel_range(start, end); return ret; } -void vmemmap_free(struct page *memmap, unsigned long nr_pages) +void vmemmap_free(unsigned long start, unsigned long end) { } diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 0972e91..82f165f 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -747,10 +747,9 @@ void bpf_jit_compile(struct sk_filter *fp) if (!bpf_jit_enable) return; - addrs = kmalloc(fp->len * sizeof(*addrs), GFP_KERNEL); + addrs = kcalloc(fp->len, sizeof(*addrs), GFP_KERNEL); if (addrs == NULL) return; - memset(addrs, 0, fp->len * sizeof(*addrs)); memset(&jit, 0, sizeof(cjit)); memset(&cjit, 0, sizeof(cjit)); diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 584b936..ffeb17c 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -440,6 +440,7 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops) switch (id.machine) { case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break; case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break; + case 0x2827: ops->cpu_type = "s390/zEC12"; break; default: return -ENODEV; } } diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile index f0f426a..086a2e3 100644 --- a/arch/s390/pci/Makefile +++ b/arch/s390/pci/Makefile @@ -2,5 +2,5 @@ # Makefile for the s390 PCI subsystem. # -obj-$(CONFIG_PCI) += pci.o pci_dma.o pci_clp.o pci_msi.o \ - pci_sysfs.o pci_event.o pci_debug.o +obj-$(CONFIG_PCI) += pci.o pci_dma.o pci_clp.o pci_msi.o pci_sysfs.o \ + pci_event.o pci_debug.o pci_insn.o diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 27b4c17..e6f15b5 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -99,9 +99,6 @@ static int __read_mostly aisb_max; static struct kmem_cache *zdev_irq_cache; static struct kmem_cache *zdev_fmb_cache; -debug_info_t *pci_debug_msg_id; -debug_info_t *pci_debug_err_id; - static inline int irq_to_msi_nr(unsigned int irq) { return irq & ZPCI_MSI_MASK; @@ -179,7 +176,7 @@ static int zpci_register_airq(struct zpci_dev *zdev, unsigned int aisb, fib->aisb = (u64) bucket->aisb + aisb / 8; fib->aisbo = aisb & ZPCI_MSI_MASK; - rc = mpcifc_instr(req, fib); + rc = s390pci_mod_fc(req, fib); pr_debug("%s mpcifc returned noi: %d\n", __func__, fib->noi); free_page((unsigned long) fib); @@ -209,7 +206,7 @@ static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args fib->iota = args->iota; fib->fmb_addr = args->fmb_addr; - rc = mpcifc_instr(req, fib); + rc = s390pci_mod_fc(req, fib); free_page((unsigned long) fib); return rc; } @@ -249,10 +246,9 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev) if (zdev->fmb) return -EINVAL; - zdev->fmb = kmem_cache_alloc(zdev_fmb_cache, GFP_KERNEL); + zdev->fmb = kmem_cache_zalloc(zdev_fmb_cache, GFP_KERNEL); if (!zdev->fmb) return -ENOMEM; - memset(zdev->fmb, 0, sizeof(*zdev->fmb)); WARN_ON((u64) zdev->fmb & 0xf); args.fmb_addr = virt_to_phys(zdev->fmb); @@ -284,12 +280,12 @@ static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len) u64 data; int rc; - rc = pcilg_instr(&data, req, offset); - data = data << ((8 - len) * 8); - data = le64_to_cpu(data); - if (!rc) + rc = s390pci_load(&data, req, offset); + if (!rc) { + data = data << ((8 - len) * 8); + data = le64_to_cpu(data); *val = (u32) data; - else + } else *val = 0xffffffff; return rc; } @@ -302,7 +298,7 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len) data = cpu_to_le64(data); data = data >> ((8 - len) * 8); - rc = pcistg_instr(data, req, offset); + rc = s390pci_store(data, req, offset); return rc; } @@ -409,20 +405,28 @@ static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { struct zpci_dev *zdev = get_zdev_by_bus(bus); + int ret; if (!zdev || devfn != ZPCI_DEVFN) - return 0; - return zpci_cfg_load(zdev, where, val, size); + ret = -ENODEV; + else + ret = zpci_cfg_load(zdev, where, val, size); + + return ret; } static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { struct zpci_dev *zdev = get_zdev_by_bus(bus); + int ret; if (!zdev || devfn != ZPCI_DEVFN) - return 0; - return zpci_cfg_store(zdev, where, val, size); + ret = -ENODEV; + else + ret = zpci_cfg_store(zdev, where, val, size); + + return ret; } static struct pci_ops pci_root_ops = { @@ -474,7 +478,7 @@ scan: } /* enable interrupts again */ - sic_instr(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); + set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); /* check again to not lose initiative */ rmb(); @@ -596,19 +600,6 @@ static void zpci_map_resources(struct zpci_dev *zdev) } }; -static void zpci_unmap_resources(struct pci_dev *pdev) -{ - resource_size_t len; - int i; - - for (i = 0; i < PCI_BAR_COUNT; i++) { - len = pci_resource_len(pdev, i); - if (!len) - continue; - pci_iounmap(pdev, (void *) pdev->resource[i].start); - } -}; - struct zpci_dev *zpci_alloc_device(void) { struct zpci_dev *zdev; @@ -636,32 +627,6 @@ void zpci_free_device(struct zpci_dev *zdev) kfree(zdev); } -/* Called on removal of pci_dev, leaves zpci and bus device */ -static void zpci_remove_device(struct pci_dev *pdev) -{ - struct zpci_dev *zdev = get_zdev(pdev); - - dev_info(&pdev->dev, "Removing device %u\n", zdev->domain); - zdev->state = ZPCI_FN_STATE_CONFIGURED; - zpci_dma_exit_device(zdev); - zpci_fmb_disable_device(zdev); - zpci_sysfs_remove_device(&pdev->dev); - zpci_unmap_resources(pdev); - list_del(&zdev->entry); /* can be called from init */ - zdev->pdev = NULL; -} - -static void zpci_scan_devices(void) -{ - struct zpci_dev *zdev; - - mutex_lock(&zpci_list_lock); - list_for_each_entry(zdev, &zpci_list, entry) - if (zdev->state == ZPCI_FN_STATE_CONFIGURED) - zpci_scan_device(zdev); - mutex_unlock(&zpci_list_lock); -} - /* * Too late for any s390 specific setup, since interrupts must be set up * already which requires DMA setup too and the pci scan will access the @@ -688,12 +653,6 @@ int pcibios_enable_device(struct pci_dev *pdev, int mask) return 0; } -void pcibios_disable_device(struct pci_dev *pdev) -{ - zpci_remove_device(pdev); - pdev->sysdata = NULL; -} - int pcibios_add_platform_entries(struct pci_dev *pdev) { return zpci_sysfs_add_device(&pdev->dev); @@ -789,7 +748,7 @@ static int __init zpci_irq_init(void) spin_lock_init(&bucket->lock); /* set summary to 1 to be called every time for the ISC */ *zpci_irq_si = 1; - sic_instr(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); + set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); return 0; out_ai: @@ -872,7 +831,19 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry) spin_unlock(&zpci_iomap_lock); } -static int zpci_create_device_bus(struct zpci_dev *zdev) +int pcibios_add_device(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = get_zdev(pdev); + + zdev->pdev = pdev; + zpci_debug_init_device(zdev); + zpci_fmb_enable_device(zdev); + zpci_map_resources(zdev); + + return 0; +} + +static int zpci_scan_bus(struct zpci_dev *zdev) { struct resource *res; LIST_HEAD(resources); @@ -909,8 +880,8 @@ static int zpci_create_device_bus(struct zpci_dev *zdev) pci_add_resource(&resources, res); } - zdev->bus = pci_create_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops, - zdev, &resources); + zdev->bus = pci_scan_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops, + zdev, &resources); if (!zdev->bus) return -EIO; @@ -959,6 +930,13 @@ out: } EXPORT_SYMBOL_GPL(zpci_enable_device); +int zpci_disable_device(struct zpci_dev *zdev) +{ + zpci_dma_exit_device(zdev); + return clp_disable_fh(zdev); +} +EXPORT_SYMBOL_GPL(zpci_disable_device); + int zpci_create_device(struct zpci_dev *zdev) { int rc; @@ -967,9 +945,16 @@ int zpci_create_device(struct zpci_dev *zdev) if (rc) goto out; - rc = zpci_create_device_bus(zdev); + if (zdev->state == ZPCI_FN_STATE_CONFIGURED) { + rc = zpci_enable_device(zdev); + if (rc) + goto out_free; + + zdev->state = ZPCI_FN_STATE_ONLINE; + } + rc = zpci_scan_bus(zdev); if (rc) - goto out_bus; + goto out_disable; mutex_lock(&zpci_list_lock); list_add_tail(&zdev->entry, &zpci_list); @@ -977,21 +962,12 @@ int zpci_create_device(struct zpci_dev *zdev) hotplug_ops->create_slot(zdev); mutex_unlock(&zpci_list_lock); - if (zdev->state == ZPCI_FN_STATE_STANDBY) - return 0; - - rc = zpci_enable_device(zdev); - if (rc) - goto out_start; return 0; -out_start: - mutex_lock(&zpci_list_lock); - list_del(&zdev->entry); - if (hotplug_ops) - hotplug_ops->remove_slot(zdev); - mutex_unlock(&zpci_list_lock); -out_bus: +out_disable: + if (zdev->state == ZPCI_FN_STATE_ONLINE) + zpci_disable_device(zdev); +out_free: zpci_free_domain(zdev); out: return rc; @@ -1016,15 +992,9 @@ int zpci_scan_device(struct zpci_dev *zdev) goto out; } - zpci_debug_init_device(zdev); - zpci_fmb_enable_device(zdev); - zpci_map_resources(zdev); pci_bus_add_devices(zdev->bus); - /* now that pdev was added to the bus mark it as used */ - zdev->state = ZPCI_FN_STATE_ONLINE; return 0; - out: zpci_dma_exit_device(zdev); clp_disable_fh(zdev); @@ -1087,13 +1057,13 @@ void zpci_deregister_hp_ops(void) } EXPORT_SYMBOL_GPL(zpci_deregister_hp_ops); -unsigned int s390_pci_probe = 1; +unsigned int s390_pci_probe; EXPORT_SYMBOL_GPL(s390_pci_probe); char * __init pcibios_setup(char *str) { - if (!strcmp(str, "off")) { - s390_pci_probe = 0; + if (!strcmp(str, "on")) { + s390_pci_probe = 1; return NULL; } return str; @@ -1138,7 +1108,6 @@ static int __init pci_base_init(void) if (rc) goto out_find; - zpci_scan_devices(); return 0; out_find: diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index f339fe2f..bd34359 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <linux/delay.h> #include <linux/pci.h> +#include <asm/pci_debug.h> #include <asm/pci_clp.h> /* @@ -144,6 +145,7 @@ int clp_add_pci_device(u32 fid, u32 fh, int configured) struct zpci_dev *zdev; int rc; + zpci_dbg(3, "add fid:%x, fh:%x, c:%d\n", fid, fh, configured); zdev = zpci_alloc_device(); if (IS_ERR(zdev)) return PTR_ERR(zdev); @@ -204,8 +206,8 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command) if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) *fh = rrb->response.fh; else { - pr_err("Set PCI FN failed with response: %x cc: %d\n", - rrb->response.hdr.rsp, rc); + zpci_dbg(0, "SPF fh:%x, cc:%d, resp:%x\n", *fh, rc, + rrb->response.hdr.rsp); rc = -EIO; } clp_free_block(rrb); @@ -221,6 +223,8 @@ int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as) if (!rc) /* Success -> store enabled handle in zdev */ zdev->fh = fh; + + zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc); return rc; } @@ -237,9 +241,8 @@ int clp_disable_fh(struct zpci_dev *zdev) if (!rc) /* Success -> store disabled handle in zdev */ zdev->fh = fh; - else - dev_err(&zdev->pdev->dev, - "Failed to disable fn handle: 0x%x\n", fh); + + zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc); return rc; } diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c index a5d07bc..771b823 100644 --- a/arch/s390/pci/pci_debug.c +++ b/arch/s390/pci/pci_debug.c @@ -11,12 +11,17 @@ #include <linux/kernel.h> #include <linux/seq_file.h> #include <linux/debugfs.h> +#include <linux/export.h> #include <linux/pci.h> #include <asm/debug.h> #include <asm/pci_dma.h> static struct dentry *debugfs_root; +debug_info_t *pci_debug_msg_id; +EXPORT_SYMBOL_GPL(pci_debug_msg_id); +debug_info_t *pci_debug_err_id; +EXPORT_SYMBOL_GPL(pci_debug_err_id); static char *pci_perf_names[] = { /* hardware counters */ @@ -168,7 +173,6 @@ int __init zpci_debug_init(void) return -EINVAL; debug_register_view(pci_debug_msg_id, &debug_sprintf_view); debug_set_level(pci_debug_msg_id, 3); - zpci_dbg("Debug view initialized\n"); /* error log */ pci_debug_err_id = debug_register("pci_error", 2, 1, 16); @@ -176,7 +180,6 @@ int __init zpci_debug_init(void) return -EINVAL; debug_register_view(pci_debug_err_id, &debug_hex_ascii_view); debug_set_level(pci_debug_err_id, 6); - zpci_err("Debug view initialized\n"); debugfs_root = debugfs_create_dir("pci", NULL); return 0; diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index a547419..f8e69d5 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -169,8 +169,9 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, * needs to be redone! */ goto no_refresh; - rc = rpcit_instr((u64) zdev->fh << 32, start_dma_addr, - nr_pages * PAGE_SIZE); + + rc = s390pci_refresh_trans((u64) zdev->fh << 32, start_dma_addr, + nr_pages * PAGE_SIZE); no_refresh: spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags); @@ -268,8 +269,6 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, int flags = ZPCI_PTE_VALID; dma_addr_t dma_addr; - WARN_ON_ONCE(offset > PAGE_SIZE); - /* This rounds up number of pages based on size and offset */ nr_pages = iommu_num_pages(pa, size, PAGE_SIZE); iommu_page_index = dma_alloc_iommu(zdev, nr_pages); @@ -291,7 +290,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, if (!dma_update_trans(zdev, pa, dma_addr, size, flags)) { atomic64_add(nr_pages, (atomic64_t *) &zdev->fmb->mapped_pages); - return dma_addr + offset; + return dma_addr + (offset & ~PAGE_MASK); } out_free: diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c new file mode 100644 index 0000000..22eeb9d --- /dev/null +++ b/arch/s390/pci/pci_insn.c @@ -0,0 +1,202 @@ +/* + * s390 specific pci instructions + * + * Copyright IBM Corp. 2013 + */ + +#include <linux/export.h> +#include <linux/errno.h> +#include <linux/delay.h> +#include <asm/pci_insn.h> +#include <asm/processor.h> + +#define ZPCI_INSN_BUSY_DELAY 1 /* 1 microsecond */ + +/* Modify PCI Function Controls */ +static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status) +{ + u8 cc; + + asm volatile ( + " .insn rxy,0xe300000000d0,%[req],%[fib]\n" + " ipm %[cc]\n" + " srl %[cc],28\n" + : [cc] "=d" (cc), [req] "+d" (req), [fib] "+Q" (*fib) + : : "cc"); + *status = req >> 24 & 0xff; + return cc; +} + +int s390pci_mod_fc(u64 req, struct zpci_fib *fib) +{ + u8 cc, status; + + do { + cc = __mpcifc(req, fib, &status); + if (cc == 2) + msleep(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d\n", + __func__, cc, status); + return (cc) ? -EIO : 0; +} + +/* Refresh PCI Translations */ +static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status) +{ + register u64 __addr asm("2") = addr; + register u64 __range asm("3") = range; + u8 cc; + + asm volatile ( + " .insn rre,0xb9d30000,%[fn],%[addr]\n" + " ipm %[cc]\n" + " srl %[cc],28\n" + : [cc] "=d" (cc), [fn] "+d" (fn) + : [addr] "d" (__addr), "d" (__range) + : "cc"); + *status = fn >> 24 & 0xff; + return cc; +} + +int s390pci_refresh_trans(u64 fn, u64 addr, u64 range) +{ + u8 cc, status; + + do { + cc = __rpcit(fn, addr, range, &status); + if (cc == 2) + udelay(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d dma_addr: %Lx size: %Lx\n", + __func__, cc, status, addr, range); + return (cc) ? -EIO : 0; +} + +/* Set Interruption Controls */ +void set_irq_ctrl(u16 ctl, char *unused, u8 isc) +{ + asm volatile ( + " .insn rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n" + : : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused)); +} + +/* PCI Load */ +static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status) +{ + register u64 __req asm("2") = req; + register u64 __offset asm("3") = offset; + int cc = -ENXIO; + u64 __data; + + asm volatile ( + " .insn rre,0xb9d20000,%[data],%[req]\n" + "0: ipm %[cc]\n" + " srl %[cc],28\n" + "1:\n" + EX_TABLE(0b, 1b) + : [cc] "+d" (cc), [data] "=d" (__data), [req] "+d" (__req) + : "d" (__offset) + : "cc"); + *status = __req >> 24 & 0xff; + if (!cc) + *data = __data; + + return cc; +} + +int s390pci_load(u64 *data, u64 req, u64 offset) +{ + u8 status; + int cc; + + do { + cc = __pcilg(data, req, offset, &status); + if (cc == 2) + udelay(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", + __func__, cc, status, req, offset); + return (cc > 0) ? -EIO : cc; +} +EXPORT_SYMBOL_GPL(s390pci_load); + +/* PCI Store */ +static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status) +{ + register u64 __req asm("2") = req; + register u64 __offset asm("3") = offset; + int cc = -ENXIO; + + asm volatile ( + " .insn rre,0xb9d00000,%[data],%[req]\n" + "0: ipm %[cc]\n" + " srl %[cc],28\n" + "1:\n" + EX_TABLE(0b, 1b) + : [cc] "+d" (cc), [req] "+d" (__req) + : "d" (__offset), [data] "d" (data) + : "cc"); + *status = __req >> 24 & 0xff; + return cc; +} + +int s390pci_store(u64 data, u64 req, u64 offset) +{ + u8 status; + int cc; + + do { + cc = __pcistg(data, req, offset, &status); + if (cc == 2) + udelay(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", + __func__, cc, status, req, offset); + return (cc > 0) ? -EIO : cc; +} +EXPORT_SYMBOL_GPL(s390pci_store); + +/* PCI Store Block */ +static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status) +{ + int cc = -ENXIO; + + asm volatile ( + " .insn rsy,0xeb00000000d0,%[req],%[offset],%[data]\n" + "0: ipm %[cc]\n" + " srl %[cc],28\n" + "1:\n" + EX_TABLE(0b, 1b) + : [cc] "+d" (cc), [req] "+d" (req) + : [offset] "d" (offset), [data] "Q" (*data) + : "cc"); + *status = req >> 24 & 0xff; + return cc; +} + +int s390pci_store_block(const u64 *data, u64 req, u64 offset) +{ + u8 status; + int cc; + + do { + cc = __pcistb(data, req, offset, &status); + if (cc == 2) + udelay(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", + __func__, cc, status, req, offset); + return (cc > 0) ? -EIO : cc; +} +EXPORT_SYMBOL_GPL(s390pci_store_block); diff --git a/arch/s390/pci/pci_msi.c b/arch/s390/pci/pci_msi.c index 0297931..b097aed 100644 --- a/arch/s390/pci/pci_msi.c +++ b/arch/s390/pci/pci_msi.c @@ -18,8 +18,9 @@ /* mapping of irq numbers to msi_desc */ static struct hlist_head *msi_hash; -static unsigned int msihash_shift = 6; -#define msi_hashfn(nr) hash_long(nr, msihash_shift) +static const unsigned int msi_hash_bits = 8; +#define MSI_HASH_BUCKETS (1U << msi_hash_bits) +#define msi_hashfn(nr) hash_long(nr, msi_hash_bits) static DEFINE_SPINLOCK(msi_map_lock); @@ -74,6 +75,7 @@ int zpci_setup_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi, map->irq = nr; map->msi = msi; zdev->msi_map[nr & ZPCI_MSI_MASK] = map; + INIT_HLIST_NODE(&map->msi_chain); pr_debug("%s hashing irq: %u to bucket nr: %llu\n", __func__, nr, msi_hashfn(nr)); @@ -125,11 +127,11 @@ int __init zpci_msihash_init(void) { unsigned int i; - msi_hash = kmalloc(256 * sizeof(*msi_hash), GFP_KERNEL); + msi_hash = kmalloc(MSI_HASH_BUCKETS * sizeof(*msi_hash), GFP_KERNEL); if (!msi_hash) return -ENOMEM; - for (i = 0; i < (1U << msihash_shift); i++) + for (i = 0; i < MSI_HASH_BUCKETS; i++) INIT_HLIST_HEAD(&msi_hash[i]); return 0; } diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c index 7956846..f4c6d02 100644 --- a/arch/score/kernel/process.c +++ b/arch/score/kernel/process.c @@ -41,24 +41,6 @@ void machine_halt(void) {} /* If or when software machine-power-off is implemented, add code here. */ void machine_power_off(void) {} -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void __noreturn cpu_idle(void) -{ - /* endless idle loop with no priority at all */ - while (1) { - rcu_idle_enter(); - while (!need_resched()) - barrier(); - rcu_idle_exit(); - schedule_preempt_disabled(); - } -} - void ret_from_fork(void); void ret_from_kernel_thread(void); diff --git a/arch/score/mm/init.c b/arch/score/mm/init.c index cee6bce..1592aad 100644 --- a/arch/score/mm/init.c +++ b/arch/score/mm/init.c @@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(empty_zero_page); static struct kcore_list kcore_mem, kcore_vmalloc; -static unsigned long setup_zero_page(void) +static void setup_zero_page(void) { struct page *page; @@ -52,9 +52,7 @@ static unsigned long setup_zero_page(void) panic("Oh boy, that early out of memory?"); page = virt_to_page((void *) empty_zero_page); - SetPageReserved(page); - - return 1UL; + mark_page_reserved(page); } #ifndef CONFIG_NEED_MULTIPLE_NODES @@ -84,7 +82,7 @@ void __init mem_init(void) high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); totalram_pages += free_all_bootmem(); - totalram_pages -= setup_zero_page(); /* Setup zeroed pages. */ + setup_zero_page(); /* Setup zeroed pages. */ reservedpages = 0; for (tmp = 0; tmp < max_low_pfn; tmp++) @@ -109,37 +107,16 @@ void __init mem_init(void) } #endif /* !CONFIG_NEED_MULTIPLE_NODES */ -static void free_init_pages(const char *what, unsigned long begin, unsigned long end) -{ - unsigned long pfn; - - for (pfn = PFN_UP(begin); pfn < PFN_DOWN(end); pfn++) { - struct page *page = pfn_to_page(pfn); - void *addr = phys_to_virt(PFN_PHYS(pfn)); - - ClearPageReserved(page); - init_page_count(page); - memset(addr, POISON_FREE_INITMEM, PAGE_SIZE); - __free_page(page); - totalram_pages++; - } - printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10); -} - #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_init_pages("initrd memory", - virt_to_phys((void *) start), - virt_to_phys((void *) end)); + free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd"); } #endif void __init_refok free_initmem(void) { - free_init_pages("unused kernel memory", - __pa(&__init_begin), - __pa(&__init_end)); + free_initmem_default(POISON_FREE_INITMEM); } unsigned long pgd_current; diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 5e85963..1ea597c 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -33,6 +33,7 @@ config SUPERH select GENERIC_ATOMIC64 select GENERIC_IRQ_SHOW select GENERIC_SMP_IDLE_THREAD + select GENERIC_IDLE_POLL_SETUP select GENERIC_CLOCKEVENTS select GENERIC_CMOS_UPDATE if SH_SH03 || SH_DREAMCAST select GENERIC_STRNCPY_FROM_USER @@ -148,9 +149,6 @@ config ARCH_HAS_ILOG2_U32 config ARCH_HAS_ILOG2_U64 def_bool n -config ARCH_HAS_DEFAULT_IDLE - def_bool y - config NO_IOPORT def_bool !PCI depends on !SH_CAYMAN && !SH_SH4202_MICRODEV && !SH_SHMIN && \ diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index aaff767..764530c 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -254,11 +254,13 @@ static int usbhs_get_id(struct platform_device *pdev) return gpio_get_value(GPIO_PTB3); } -static void usbhs_phy_reset(struct platform_device *pdev) +static int usbhs_phy_reset(struct platform_device *pdev) { /* enable vbus if HOST */ if (!gpio_get_value(GPIO_PTB3)) gpio_set_value(GPIO_PTB5, 1); + + return 0; } static struct renesas_usbhs_platform_info usbhs_info = { diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c index c2c85f6..a162a7f 100644 --- a/arch/sh/drivers/pci/pcie-sh7786.c +++ b/arch/sh/drivers/pci/pcie-sh7786.c @@ -35,7 +35,7 @@ static unsigned int nr_ports; static struct sh7786_pcie_hwops { int (*core_init)(void); - async_func_ptr *port_init_hw; + async_func_t port_init_hw; } *sh7786_pcie_hwops; static struct resource sh7786_pci0_resources[] = { diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h index b3808c7..699255d 100644 --- a/arch/sh/include/asm/hugetlb.h +++ b/arch/sh/include/asm/hugetlb.h @@ -3,6 +3,7 @@ #include <asm/cacheflush.h> #include <asm/page.h> +#include <asm-generic/hugetlb.h> static inline int is_hugepage_only_range(struct mm_struct *mm, diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h index 7d5ac4e..45a9366 100644 --- a/arch/sh/include/asm/thread_info.h +++ b/arch/sh/include/asm/thread_info.h @@ -207,8 +207,6 @@ static inline bool test_and_clear_restore_sigmask(void) return true; } -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) - #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 3d5a1b3..2ea4483 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -24,98 +24,24 @@ static void (*sh_idle)(void); -static int hlt_counter; - -static int __init nohlt_setup(char *__unused) -{ - hlt_counter = 1; - return 1; -} -__setup("nohlt", nohlt_setup); - -static int __init hlt_setup(char *__unused) -{ - hlt_counter = 0; - return 1; -} -__setup("hlt", hlt_setup); - -static inline int hlt_works(void) -{ - return !hlt_counter; -} - -/* - * On SMP it's slightly faster (but much more power-consuming!) - * to poll the ->work.need_resched flag instead of waiting for the - * cross-CPU IPI to arrive. Use this option with caution. - */ -static void poll_idle(void) +void default_idle(void) { + set_bl_bit(); local_irq_enable(); - while (!need_resched()) - cpu_relax(); + /* Isn't this racy ? */ + cpu_sleep(); + clear_bl_bit(); } -void default_idle(void) +void arch_cpu_idle_dead(void) { - if (hlt_works()) { - clear_thread_flag(TIF_POLLING_NRFLAG); - smp_mb__after_clear_bit(); - - set_bl_bit(); - if (!need_resched()) { - local_irq_enable(); - cpu_sleep(); - } else - local_irq_enable(); - - set_thread_flag(TIF_POLLING_NRFLAG); - clear_bl_bit(); - } else - poll_idle(); + play_dead(); } -/* - * The idle thread. There's no useful work to be done, so just try to conserve - * power and have a low exit latency (ie sit in a loop waiting for somebody to - * say that they'd like to reschedule) - */ -void cpu_idle(void) +void arch_cpu_idle(void) { - unsigned int cpu = smp_processor_id(); - - set_thread_flag(TIF_POLLING_NRFLAG); - - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - - while (!need_resched()) { - check_pgt_cache(); - rmb(); - - if (cpu_is_offline(cpu)) - play_dead(); - - local_irq_disable(); - /* Don't trace irqs off for idle */ - stop_critical_timings(); - if (cpuidle_idle_call()) - sh_idle(); - /* - * Sanity check to ensure that sh_idle() returns - * with IRQs enabled - */ - WARN_ON(irqs_disabled()); - start_critical_timings(); - } - - rcu_idle_exit(); - tick_nohz_idle_exit(); - schedule_preempt_disabled(); - } + if (cpuidle_idle_call()) + sh_idle(); } void __init select_idle_routine(void) @@ -123,13 +49,8 @@ void __init select_idle_routine(void) /* * If a platform has set its own idle routine, leave it alone. */ - if (sh_idle) - return; - - if (hlt_works()) + if (!sh_idle) sh_idle = default_idle; - else - sh_idle = poll_idle; } void stop_this_cpu(void *unused) diff --git a/arch/sh/kernel/sh_bios.c b/arch/sh/kernel/sh_bios.c index 47475cc..fe584e5 100644 --- a/arch/sh/kernel/sh_bios.c +++ b/arch/sh/kernel/sh_bios.c @@ -104,6 +104,7 @@ void sh_bios_vbr_reload(void) ); } +#ifdef CONFIG_EARLY_PRINTK /* * Print a string through the BIOS */ @@ -144,8 +145,6 @@ static struct console bios_console = { .index = -1, }; -static struct console *early_console; - static int __init setup_early_printk(char *buf) { int keep_early = 0; @@ -170,3 +169,4 @@ static int __init setup_early_printk(char *buf) return 0; } early_param("earlyprintk", setup_early_printk); +#endif diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index 2062aa8..4569645 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -203,7 +203,7 @@ asmlinkage void __cpuinit start_secondary(void) set_cpu_online(cpu, true); per_cpu(cpu_state, cpu) = CPU_ONLINE; - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } extern struct { diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 1057940..20f9ead 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -417,15 +417,13 @@ void __init mem_init(void) for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); - unsigned long node_pages = 0; void *node_high_memory; num_physpages += pgdat->node_present_pages; if (pgdat->node_spanned_pages) - node_pages = free_all_bootmem_node(pgdat); + totalram_pages += free_all_bootmem_node(pgdat); - totalram_pages += node_pages; node_high_memory = (void *)__va((pgdat->node_start_pfn + pgdat->node_spanned_pages) << @@ -501,31 +499,13 @@ void __init mem_init(void) void free_initmem(void) { - unsigned long addr; - - addr = (unsigned long)(&__init_begin); - for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - free_page(addr); - totalram_pages++; - } - printk("Freeing unused kernel memory: %ldk freed\n", - ((unsigned long)&__init_end - - (unsigned long)&__init_begin) >> 10); + free_initmem_default(0); } #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - unsigned long p; - for (p = start; p < end; p += PAGE_SIZE) { - ClearPageReserved(virt_to_page(p)); - init_page_count(virt_to_page(p)); - free_page(p); - totalram_pages++; - } - printk("Freeing initrd memory: %ldk freed\n", (end - start) >> 10); + free_reserved_area(start, end, 0, "initrd"); } #endif diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 3d361f2..66dc562 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -407,6 +407,8 @@ config SERIAL_CONSOLE config SPARC_LEON bool "Sparc Leon processor family" depends on SPARC32 + select USB_EHCI_BIG_ENDIAN_MMIO + select USB_EHCI_BIG_ENDIAN_DESC ---help--- If you say Y here if you are running on a SPARC-LEON processor. The LEON processor is a synthesizable VHDL model of the diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index e26d430..ff18e3c 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -2,11 +2,16 @@ generic-y += clkdev.h +generic-y += cputime.h generic-y += div64.h +generic-y += emergency-restart.h generic-y += exec.h generic-y += local64.h +generic-y += mutex.h generic-y += irq_regs.h generic-y += local.h generic-y += module.h +generic-y += serial.h generic-y += trace_clock.h +generic-y += types.h generic-y += word-at-a-time.h diff --git a/arch/sparc/include/asm/cputime.h b/arch/sparc/include/asm/cputime.h deleted file mode 100644 index 1a642b8..0000000 --- a/arch/sparc/include/asm/cputime.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __SPARC_CPUTIME_H -#define __SPARC_CPUTIME_H - -#include <asm-generic/cputime.h> - -#endif /* __SPARC_CPUTIME_H */ diff --git a/arch/sparc/include/asm/emergency-restart.h b/arch/sparc/include/asm/emergency-restart.h deleted file mode 100644 index 108d8c4..0000000 --- a/arch/sparc/include/asm/emergency-restart.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_EMERGENCY_RESTART_H -#define _ASM_EMERGENCY_RESTART_H - -#include <asm-generic/emergency-restart.h> - -#endif /* _ASM_EMERGENCY_RESTART_H */ diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index 7eb57d2..e4cab46 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -2,6 +2,7 @@ #define _ASM_SPARC64_HUGETLB_H #include <asm/page.h> +#include <asm-generic/hugetlb.h> void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, diff --git a/arch/sparc/include/asm/mutex.h b/arch/sparc/include/asm/mutex.h deleted file mode 100644 index 458c1f7..0000000 --- a/arch/sparc/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include <asm-generic/mutex-dec.h> diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 08fcce9..7619f2f 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -915,6 +915,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma, return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot); } +#include <asm/tlbflush.h> #include <asm-generic/pgtable.h> /* We provide our own get_unmapped_area to cope with VA holes and diff --git a/arch/sparc/include/asm/serial.h b/arch/sparc/include/asm/serial.h deleted file mode 100644 index f90d61c..0000000 --- a/arch/sparc/include/asm/serial.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __SPARC_SERIAL_H -#define __SPARC_SERIAL_H - -#define BASE_BAUD ( 1843200 / 16 ) - -#endif /* __SPARC_SERIAL_H */ diff --git a/arch/sparc/include/asm/smp_32.h b/arch/sparc/include/asm/smp_32.h index b73da3c..3c8917f 100644 --- a/arch/sparc/include/asm/smp_32.h +++ b/arch/sparc/include/asm/smp_32.h @@ -36,7 +36,6 @@ typedef void (*smpfunc_t)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); void cpu_panic(void); -extern void smp4m_irq_rotate(int cpu); /* * General functions that each host system must provide. @@ -46,7 +45,6 @@ void sun4m_init_smp(void); void sun4d_init_smp(void); void smp_callin(void); -void smp_boot_cpus(void); void smp_store_cpu_info(int); void smp_resched_interrupt(void); @@ -107,9 +105,6 @@ extern int hard_smp_processor_id(void); #define raw_smp_processor_id() (current_thread_info()->cpu) -#define prof_multiplier(__cpu) cpu_data(__cpu).multiplier -#define prof_counter(__cpu) cpu_data(__cpu).counter - void smp_setup_cpu_possible_map(void); #endif /* !(__ASSEMBLY__) */ diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h index cad36f5..c7de332 100644 --- a/arch/sparc/include/asm/switch_to_64.h +++ b/arch/sparc/include/asm/switch_to_64.h @@ -18,8 +18,7 @@ do { \ * and 2 stores in this critical code path. -DaveM */ #define switch_to(prev, next, last) \ -do { flush_tlb_pending(); \ - save_and_clear_fpu(); \ +do { save_and_clear_fpu(); \ /* If you are tempted to conditionalize the following */ \ /* so that ASI is only written if it changes, think again. */ \ __asm__ __volatile__("wr %%g0, %0, %%asi" \ diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h index 25849ae..dd38075 100644 --- a/arch/sparc/include/asm/thread_info_32.h +++ b/arch/sparc/include/asm/thread_info_32.h @@ -132,8 +132,6 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define _TIF_DO_NOTIFY_RESUME_MASK (_TIF_NOTIFY_RESUME | \ _TIF_SIGPENDING) -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) - #endif /* __KERNEL__ */ #endif /* _ASM_THREAD_INFO_H */ diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h index 269bd92..d5e5042 100644 --- a/arch/sparc/include/asm/thread_info_64.h +++ b/arch/sparc/include/asm/thread_info_64.h @@ -256,8 +256,6 @@ static inline bool test_and_clear_restore_sigmask(void) return true; } -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) - #define thread32_stack_is_64bit(__SP) (((__SP) & 0x1) != 0) #define test_thread_64bit_stack(__SP) \ ((test_thread_flag(TIF_32BIT) && !thread32_stack_is_64bit(__SP)) ? \ diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h index 2ef4634..f0d6a97 100644 --- a/arch/sparc/include/asm/tlbflush_64.h +++ b/arch/sparc/include/asm/tlbflush_64.h @@ -11,24 +11,40 @@ struct tlb_batch { struct mm_struct *mm; unsigned long tlb_nr; + unsigned long active; unsigned long vaddrs[TLB_BATCH_NR]; }; extern void flush_tsb_kernel_range(unsigned long start, unsigned long end); extern void flush_tsb_user(struct tlb_batch *tb); +extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr); /* TLB flush operations. */ -extern void flush_tlb_pending(void); +static inline void flush_tlb_mm(struct mm_struct *mm) +{ +} + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ +} + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ +} + +#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE -#define flush_tlb_range(vma,start,end) \ - do { (void)(start); flush_tlb_pending(); } while (0) -#define flush_tlb_page(vma,addr) flush_tlb_pending() -#define flush_tlb_mm(mm) flush_tlb_pending() +extern void flush_tlb_pending(void); +extern void arch_enter_lazy_mmu_mode(void); +extern void arch_leave_lazy_mmu_mode(void); +#define arch_flush_lazy_mmu_mode() do {} while (0) /* Local cpu only. */ extern void __flush_tlb_all(void); - +extern void __flush_tlb_page(unsigned long context, unsigned long vaddr); extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end); #ifndef CONFIG_SMP @@ -38,15 +54,24 @@ do { flush_tsb_kernel_range(start,end); \ __flush_tlb_kernel_range(start,end); \ } while (0) +static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) +{ + __flush_tlb_page(CTX_HWBITS(mm->context), vaddr); +} + #else /* CONFIG_SMP */ extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end); +extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr); #define flush_tlb_kernel_range(start, end) \ do { flush_tsb_kernel_range(start,end); \ smp_flush_tlb_kernel_range(start, end); \ } while (0) +#define global_flush_tlb_page(mm, vaddr) \ + smp_flush_tlb_page(mm, vaddr) + #endif /* ! CONFIG_SMP */ #endif /* _SPARC64_TLBFLUSH_H */ diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild index ce175af..b5843ee 100644 --- a/arch/sparc/include/uapi/asm/Kbuild +++ b/arch/sparc/include/uapi/asm/Kbuild @@ -44,7 +44,6 @@ header-y += swab.h header-y += termbits.h header-y += termios.h header-y += traps.h -header-y += types.h header-y += uctx.h header-y += unistd.h header-y += utrap.h diff --git a/arch/sparc/include/uapi/asm/types.h b/arch/sparc/include/uapi/asm/types.h deleted file mode 100644 index 383d156..0000000 --- a/arch/sparc/include/uapi/asm/types.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef _SPARC_TYPES_H -#define _SPARC_TYPES_H -/* - * This file is never included by application software unless - * explicitly requested (e.g., via linux/types.h) in which case the - * application is Linux specific so (user-) name space pollution is - * not a major issue. However, for interoperability, libraries still - * need to be careful to avoid a name clashes. - */ - -#if defined(__sparc__) - -#include <asm-generic/int-ll64.h> - -#endif /* defined(__sparc__) */ - -#endif /* defined(_SPARC_TYPES_H) */ diff --git a/arch/sparc/kernel/hvtramp.S b/arch/sparc/kernel/hvtramp.S index 9365432..605c960 100644 --- a/arch/sparc/kernel/hvtramp.S +++ b/arch/sparc/kernel/hvtramp.S @@ -128,8 +128,7 @@ hv_cpu_startup: call smp_callin nop - call cpu_idle - mov 0, %o0 + call cpu_panic nop diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index 62eede1..c852410 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -64,23 +64,12 @@ extern void fpsave(unsigned long *, unsigned long *, void *, unsigned long *); struct task_struct *last_task_used_math = NULL; struct thread_info *current_set[NR_CPUS]; -/* - * the idle loop on a Sparc... ;) - */ -void cpu_idle(void) +/* Idle loop support. */ +void arch_cpu_idle(void) { - set_thread_flag(TIF_POLLING_NRFLAG); - - /* endless idle loop with no priority at all */ - for (;;) { - while (!need_resched()) { - if (sparc_idle) - (*sparc_idle)(); - else - cpu_relax(); - } - schedule_preempt_disabled(); - } + if (sparc_idle) + (*sparc_idle)(); + local_irq_enable(); } /* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */ diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index cdb80b2..9fbf0d1 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -52,20 +52,17 @@ #include "kstack.h" -static void sparc64_yield(int cpu) +/* Idle loop support on sparc64. */ +void arch_cpu_idle(void) { if (tlb_type != hypervisor) { touch_nmi_watchdog(); - return; - } - - clear_thread_flag(TIF_POLLING_NRFLAG); - smp_mb__after_clear_bit(); - - while (!need_resched() && !cpu_is_offline(cpu)) { + } else { unsigned long pstate; - /* Disable interrupts. */ + /* The sun4v sleeping code requires that we have PSTATE.IE cleared over + * the cpu sleep hypervisor call. + */ __asm__ __volatile__( "rdpr %%pstate, %0\n\t" "andn %0, %1, %0\n\t" @@ -73,7 +70,7 @@ static void sparc64_yield(int cpu) : "=&r" (pstate) : "i" (PSTATE_IE)); - if (!need_resched() && !cpu_is_offline(cpu)) + if (!need_resched() && !cpu_is_offline(smp_processor_id())) sun4v_cpu_yield(); /* Re-enable interrupts. */ @@ -84,36 +81,16 @@ static void sparc64_yield(int cpu) : "=&r" (pstate) : "i" (PSTATE_IE)); } - - set_thread_flag(TIF_POLLING_NRFLAG); + local_irq_enable(); } -/* The idle loop on sparc64. */ -void cpu_idle(void) -{ - int cpu = smp_processor_id(); - - set_thread_flag(TIF_POLLING_NRFLAG); - - while(1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - - while (!need_resched() && !cpu_is_offline(cpu)) - sparc64_yield(cpu); - - rcu_idle_exit(); - tick_nohz_idle_exit(); - #ifdef CONFIG_HOTPLUG_CPU - if (cpu_is_offline(cpu)) { - sched_preempt_enable_no_resched(); - cpu_play_dead(); - } -#endif - schedule_preempt_disabled(); - } +void arch_cpu_idle_dead() +{ + sched_preempt_enable_no_resched(); + cpu_play_dead(); } +#endif #ifdef CONFIG_COMPAT static void show_regwindow32(struct pt_regs *regs) diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c index 9e7e6d7..e3f2b81 100644 --- a/arch/sparc/kernel/smp_32.c +++ b/arch/sparc/kernel/smp_32.c @@ -369,7 +369,7 @@ void __cpuinit sparc_start_secondary(void *arg) local_irq_enable(); wmb(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); /* We should never reach here! */ BUG(); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 537eb66..77539ed 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -127,6 +127,8 @@ void __cpuinit smp_callin(void) /* idle thread is expected to have preempt disabled */ preempt_disable(); + + cpu_startup_entry(CPUHP_ONLINE); } void cpu_panic(void) @@ -849,7 +851,7 @@ void smp_tsb_sync(struct mm_struct *mm) } extern unsigned long xcall_flush_tlb_mm; -extern unsigned long xcall_flush_tlb_pending; +extern unsigned long xcall_flush_tlb_page; extern unsigned long xcall_flush_tlb_kernel_range; extern unsigned long xcall_fetch_glob_regs; extern unsigned long xcall_fetch_glob_pmu; @@ -1074,23 +1076,56 @@ local_flush_and_out: put_cpu(); } +struct tlb_pending_info { + unsigned long ctx; + unsigned long nr; + unsigned long *vaddrs; +}; + +static void tlb_pending_func(void *info) +{ + struct tlb_pending_info *t = info; + + __flush_tlb_pending(t->ctx, t->nr, t->vaddrs); +} + void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs) { u32 ctx = CTX_HWBITS(mm->context); + struct tlb_pending_info info; int cpu = get_cpu(); + info.ctx = ctx; + info.nr = nr; + info.vaddrs = vaddrs; + if (mm == current->mm && atomic_read(&mm->mm_users) == 1) cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); else - smp_cross_call_masked(&xcall_flush_tlb_pending, - ctx, nr, (unsigned long) vaddrs, - mm_cpumask(mm)); + smp_call_function_many(mm_cpumask(mm), tlb_pending_func, + &info, 1); __flush_tlb_pending(ctx, nr, vaddrs); put_cpu(); } +void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) +{ + unsigned long context = CTX_HWBITS(mm->context); + int cpu = get_cpu(); + + if (mm == current->mm && atomic_read(&mm->mm_users) == 1) + cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); + else + smp_cross_call_masked(&xcall_flush_tlb_page, + context, vaddr, 0, + mm_cpumask(mm)); + __flush_tlb_page(context, vaddr); + + put_cpu(); +} + void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end) { start &= PAGE_MASK; diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S index da1b781..2e973a2 100644 --- a/arch/sparc/kernel/trampoline_64.S +++ b/arch/sparc/kernel/trampoline_64.S @@ -407,8 +407,7 @@ after_lock_tlb: call smp_callin nop - call cpu_idle - mov 0, %o0 + call cpu_panic nop 1: b,a,pt %xcc, 1b diff --git a/arch/sparc/lib/bitext.c b/arch/sparc/lib/bitext.c index 48d00e7..8ec4e9c 100644 --- a/arch/sparc/lib/bitext.c +++ b/arch/sparc/lib/bitext.c @@ -119,11 +119,7 @@ void bit_map_clear(struct bit_map *t, int offset, int len) void bit_map_init(struct bit_map *t, unsigned long *map, int size) { - - if ((size & 07) != 0) - BUG(); - memset(map, 0, size>>3); - + bitmap_zero(map, size); memset(t, 0, sizeof *t); spin_lock_init(&t->lock); t->map = map; diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index 48e0c03..4490c39 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -282,14 +282,8 @@ static void map_high_region(unsigned long start_pfn, unsigned long end_pfn) printk("mapping high region %08lx - %08lx\n", start_pfn, end_pfn); #endif - for (tmp = start_pfn; tmp < end_pfn; tmp++) { - struct page *page = pfn_to_page(tmp); - - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - totalhigh_pages++; - } + for (tmp = start_pfn; tmp < end_pfn; tmp++) + free_highmem_page(pfn_to_page(tmp)); } void __init mem_init(void) @@ -347,8 +341,6 @@ void __init mem_init(void) map_high_region(start_pfn, end_pfn); } - totalram_pages += totalhigh_pages; - codepages = (((unsigned long) &_etext) - ((unsigned long)&_start)); codepages = PAGE_ALIGN(codepages) >> PAGE_SHIFT; datapages = (((unsigned long) &_edata) - ((unsigned long)&_etext)); diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 1588d33..6ac99d6 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2181,10 +2181,9 @@ unsigned long vmemmap_table[VMEMMAP_SIZE]; static long __meminitdata addr_start, addr_end; static int __meminitdata node_start; -int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) +int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, + int node) { - unsigned long vstart = (unsigned long) start; - unsigned long vend = (unsigned long) (start + nr); unsigned long phys_start = (vstart - VMEMMAP_BASE); unsigned long phys_end = (vend - VMEMMAP_BASE); unsigned long addr = phys_start & VMEMMAP_CHUNK_MASK; @@ -2236,7 +2235,7 @@ void __meminit vmemmap_populate_print_last(void) } } -void vmemmap_free(struct page *memmap, unsigned long nr_pages) +void vmemmap_free(unsigned long start, unsigned long end) { } diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c index 0f4f719..28f96f2 100644 --- a/arch/sparc/mm/iommu.c +++ b/arch/sparc/mm/iommu.c @@ -34,7 +34,7 @@ #define IOMMU_RNGE IOMMU_RNGE_256MB #define IOMMU_START 0xF0000000 #define IOMMU_WINSIZE (256*1024*1024U) -#define IOMMU_NPTES (IOMMU_WINSIZE/PAGE_SIZE) /* 64K PTEs, 265KB */ +#define IOMMU_NPTES (IOMMU_WINSIZE/PAGE_SIZE) /* 64K PTEs, 256KB */ #define IOMMU_ORDER 6 /* 4096 * (1<<6) */ /* srmmu.c */ diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index c38bb72..036c279 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -280,7 +280,9 @@ static void __init srmmu_nocache_init(void) SRMMU_NOCACHE_ALIGN_MAX, 0UL); memset(srmmu_nocache_pool, 0, srmmu_nocache_size); - srmmu_nocache_bitmap = __alloc_bootmem(bitmap_bits >> 3, SMP_CACHE_BYTES, 0UL); + srmmu_nocache_bitmap = + __alloc_bootmem(BITS_TO_LONGS(bitmap_bits) * sizeof(long), + SMP_CACHE_BYTES, 0UL); bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits); srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE); diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index ba6ae7f..83d89bc 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch, tlb_batch); void flush_tlb_pending(void) { struct tlb_batch *tb = &get_cpu_var(tlb_batch); + struct mm_struct *mm = tb->mm; - if (tb->tlb_nr) { - flush_tsb_user(tb); + if (!tb->tlb_nr) + goto out; - if (CTX_VALID(tb->mm->context)) { + flush_tsb_user(tb); + + if (CTX_VALID(mm->context)) { + if (tb->tlb_nr == 1) { + global_flush_tlb_page(mm, tb->vaddrs[0]); + } else { #ifdef CONFIG_SMP smp_flush_tlb_pending(tb->mm, tb->tlb_nr, &tb->vaddrs[0]); @@ -37,12 +43,30 @@ void flush_tlb_pending(void) tb->tlb_nr, &tb->vaddrs[0]); #endif } - tb->tlb_nr = 0; } + tb->tlb_nr = 0; + +out: put_cpu_var(tlb_batch); } +void arch_enter_lazy_mmu_mode(void) +{ + struct tlb_batch *tb = &__get_cpu_var(tlb_batch); + + tb->active = 1; +} + +void arch_leave_lazy_mmu_mode(void) +{ + struct tlb_batch *tb = &__get_cpu_var(tlb_batch); + + if (tb->tlb_nr) + flush_tlb_pending(); + tb->active = 0; +} + static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, bool exec) { @@ -60,6 +84,12 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, nr = 0; } + if (!tb->active) { + global_flush_tlb_page(mm, vaddr); + flush_tsb_user_page(mm, vaddr); + goto out; + } + if (nr == 0) tb->mm = mm; @@ -68,6 +98,7 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, if (nr >= TLB_BATCH_NR) flush_tlb_pending(); +out: put_cpu_var(tlb_batch); } diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 428982b..2cc3bce 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -7,11 +7,10 @@ #include <linux/preempt.h> #include <linux/slab.h> #include <asm/page.h> -#include <asm/tlbflush.h> -#include <asm/tlb.h> -#include <asm/mmu_context.h> #include <asm/pgtable.h> +#include <asm/mmu_context.h> #include <asm/tsb.h> +#include <asm/tlb.h> #include <asm/oplib.h> extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; @@ -46,23 +45,27 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end) } } -static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, - unsigned long tsb, unsigned long nentries) +static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v, + unsigned long hash_shift, + unsigned long nentries) { - unsigned long i; + unsigned long tag, ent, hash; - for (i = 0; i < tb->tlb_nr; i++) { - unsigned long v = tb->vaddrs[i]; - unsigned long tag, ent, hash; + v &= ~0x1UL; + hash = tsb_hash(v, hash_shift, nentries); + ent = tsb + (hash * sizeof(struct tsb)); + tag = (v >> 22UL); - v &= ~0x1UL; + tsb_flush(ent, tag); +} - hash = tsb_hash(v, hash_shift, nentries); - ent = tsb + (hash * sizeof(struct tsb)); - tag = (v >> 22UL); +static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, + unsigned long tsb, unsigned long nentries) +{ + unsigned long i; - tsb_flush(ent, tag); - } + for (i = 0; i < tb->tlb_nr; i++) + __flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries); } void flush_tsb_user(struct tlb_batch *tb) @@ -90,6 +93,30 @@ void flush_tsb_user(struct tlb_batch *tb) spin_unlock_irqrestore(&mm->context.lock, flags); } +void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr) +{ + unsigned long nentries, base, flags; + + spin_lock_irqsave(&mm->context.lock, flags); + + base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; + nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries); + +#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) + if (mm->context.tsb_block[MM_TSB_HUGE].tsb) { + base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb; + nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries); + } +#endif + spin_unlock_irqrestore(&mm->context.lock, flags); +} + #define HV_PGSZ_IDX_BASE HV_PGSZ_IDX_8K #define HV_PGSZ_MASK_BASE HV_PGSZ_MASK_8K diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S index f8e13d4..432aa0c 100644 --- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -53,6 +53,33 @@ __flush_tlb_mm: /* 18 insns */ nop .align 32 + .globl __flush_tlb_page +__flush_tlb_page: /* 22 insns */ + /* %o0 = context, %o1 = vaddr */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, %pstate + mov SECONDARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + stxa %o0, [%o4] ASI_DMMU + andcc %o1, 1, %g0 + andn %o1, 1, %o3 + be,pn %icc, 1f + or %o3, 0x10, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +1: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + retl + wrpr %g7, 0x0, %pstate + nop + nop + nop + nop + + .align 32 .globl __flush_tlb_pending __flush_tlb_pending: /* 26 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ @@ -203,6 +230,31 @@ __cheetah_flush_tlb_mm: /* 19 insns */ retl wrpr %g7, 0x0, %pstate +__cheetah_flush_tlb_page: /* 22 insns */ + /* %o0 = context, %o1 = vaddr */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, 0x0, %pstate + wrpr %g0, 1, %tl + mov PRIMARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + srlx %g2, CTX_PGSZ1_NUC_SHIFT, %o3 + sllx %o3, CTX_PGSZ1_NUC_SHIFT, %o3 + or %o0, %o3, %o0 /* Preserve nucleus page size fields */ + stxa %o0, [%o4] ASI_DMMU + andcc %o1, 1, %g0 + be,pn %icc, 1f + andn %o1, 1, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +1: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + wrpr %g0, 0, %tl + retl + wrpr %g7, 0x0, %pstate + __cheetah_flush_tlb_pending: /* 27 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ rdpr %pstate, %g7 @@ -269,6 +321,20 @@ __hypervisor_flush_tlb_mm: /* 10 insns */ retl nop +__hypervisor_flush_tlb_page: /* 11 insns */ + /* %o0 = context, %o1 = vaddr */ + mov %o0, %g2 + mov %o1, %o0 /* ARG0: vaddr + IMMU-bit */ + mov %g2, %o1 /* ARG1: mmu context */ + mov HV_MMU_ALL, %o2 /* ARG2: flags */ + srlx %o0, PAGE_SHIFT, %o0 + sllx %o0, PAGE_SHIFT, %o0 + ta HV_MMU_UNMAP_ADDR_TRAP + brnz,pn %o0, __hypervisor_tlb_tl0_error + mov HV_MMU_UNMAP_ADDR_TRAP, %o1 + retl + nop + __hypervisor_flush_tlb_pending: /* 16 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ sllx %o1, 3, %g1 @@ -339,6 +405,13 @@ cheetah_patch_cachetlbops: call tlb_patch_one mov 19, %o2 + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__cheetah_flush_tlb_page), %o1 + or %o1, %lo(__cheetah_flush_tlb_page), %o1 + call tlb_patch_one + mov 22, %o2 + sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__cheetah_flush_tlb_pending), %o1 @@ -397,10 +470,9 @@ xcall_flush_tlb_mm: /* 21 insns */ nop nop - .globl xcall_flush_tlb_pending -xcall_flush_tlb_pending: /* 21 insns */ - /* %g5=context, %g1=nr, %g7=vaddrs[] */ - sllx %g1, 3, %g1 + .globl xcall_flush_tlb_page +xcall_flush_tlb_page: /* 17 insns */ + /* %g5=context, %g1=vaddr */ mov PRIMARY_CONTEXT, %g4 ldxa [%g4] ASI_DMMU, %g2 srlx %g2, CTX_PGSZ1_NUC_SHIFT, %g4 @@ -408,20 +480,16 @@ xcall_flush_tlb_pending: /* 21 insns */ or %g5, %g4, %g5 mov PRIMARY_CONTEXT, %g4 stxa %g5, [%g4] ASI_DMMU -1: sub %g1, (1 << 3), %g1 - ldx [%g7 + %g1], %g5 - andcc %g5, 0x1, %g0 + andcc %g1, 0x1, %g0 be,pn %icc, 2f - - andn %g5, 0x1, %g5 + andn %g1, 0x1, %g5 stxa %g0, [%g5] ASI_IMMU_DEMAP 2: stxa %g0, [%g5] ASI_DMMU_DEMAP membar #Sync - brnz,pt %g1, 1b - nop stxa %g2, [%g4] ASI_DMMU retry nop + nop .globl xcall_flush_tlb_kernel_range xcall_flush_tlb_kernel_range: /* 25 insns */ @@ -656,15 +724,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */ membar #Sync retry - .globl __hypervisor_xcall_flush_tlb_pending -__hypervisor_xcall_flush_tlb_pending: /* 21 insns */ - /* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */ - sllx %g1, 3, %g1 + .globl __hypervisor_xcall_flush_tlb_page +__hypervisor_xcall_flush_tlb_page: /* 17 insns */ + /* %g5=ctx, %g1=vaddr */ mov %o0, %g2 mov %o1, %g3 mov %o2, %g4 -1: sub %g1, (1 << 3), %g1 - ldx [%g7 + %g1], %o0 /* ARG0: virtual address */ + mov %g1, %o0 /* ARG0: virtual address */ mov %g5, %o1 /* ARG1: mmu context */ mov HV_MMU_ALL, %o2 /* ARG2: flags */ srlx %o0, PAGE_SHIFT, %o0 @@ -673,8 +739,6 @@ __hypervisor_xcall_flush_tlb_pending: /* 21 insns */ mov HV_MMU_UNMAP_ADDR_TRAP, %g6 brnz,a,pn %o0, __hypervisor_tlb_xcall_error mov %o0, %g5 - brnz,pt %g1, 1b - nop mov %g2, %o0 mov %g3, %o1 mov %g4, %o2 @@ -757,6 +821,13 @@ hypervisor_patch_cachetlbops: call tlb_patch_one mov 10, %o2 + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__hypervisor_flush_tlb_page), %o1 + or %o1, %lo(__hypervisor_flush_tlb_page), %o1 + call tlb_patch_one + mov 11, %o2 + sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__hypervisor_flush_tlb_pending), %o1 @@ -788,12 +859,12 @@ hypervisor_patch_cachetlbops: call tlb_patch_one mov 21, %o2 - sethi %hi(xcall_flush_tlb_pending), %o0 - or %o0, %lo(xcall_flush_tlb_pending), %o0 - sethi %hi(__hypervisor_xcall_flush_tlb_pending), %o1 - or %o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1 + sethi %hi(xcall_flush_tlb_page), %o0 + or %o0, %lo(xcall_flush_tlb_page), %o0 + sethi %hi(__hypervisor_xcall_flush_tlb_page), %o1 + or %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1 call tlb_patch_one - mov 21, %o2 + mov 17, %o2 sethi %hi(xcall_flush_tlb_kernel_range), %o0 or %o0, %lo(xcall_flush_tlb_kernel_range), %o0 diff --git a/arch/tile/include/asm/hugetlb.h b/arch/tile/include/asm/hugetlb.h index 0f885af..3257733 100644 --- a/arch/tile/include/asm/hugetlb.h +++ b/arch/tile/include/asm/hugetlb.h @@ -16,6 +16,7 @@ #define _ASM_TILE_HUGETLB_H #include <asm/page.h> +#include <asm-generic/hugetlb.h> static inline int is_hugepage_only_range(struct mm_struct *mm, diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h index e9c670d..ccc8ef3 100644 --- a/arch/tile/include/asm/thread_info.h +++ b/arch/tile/include/asm/thread_info.h @@ -153,8 +153,6 @@ extern void _cpu_idle(void); #define TS_POLLING 0x0004 /* in idle loop but not sleeping */ #define TS_RESTORE_SIGMASK 0x0008 /* restore signal mask in do_signal */ -#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING) - #ifndef __ASSEMBLY__ #define HAVE_SET_RESTORE_SIGMASK 1 static inline void set_restore_sigmask(void) diff --git a/arch/tile/kernel/early_printk.c b/arch/tile/kernel/early_printk.c index afb9c9a..34d72a1 100644 --- a/arch/tile/kernel/early_printk.c +++ b/arch/tile/kernel/early_printk.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/string.h> #include <linux/irqflags.h> +#include <linux/printk.h> #include <asm/setup.h> #include <hv/hypervisor.h> @@ -33,25 +34,8 @@ static struct console early_hv_console = { }; /* Direct interface for emergencies */ -static struct console *early_console = &early_hv_console; -static int early_console_initialized; static int early_console_complete; -static void early_vprintk(const char *fmt, va_list ap) -{ - char buf[512]; - int n = vscnprintf(buf, sizeof(buf), fmt, ap); - early_console->write(early_console, buf, n); -} - -void early_printk(const char *fmt, ...) -{ - va_list ap; - va_start(ap, fmt); - early_vprintk(fmt, ap); - va_end(ap); -} - void early_panic(const char *fmt, ...) { va_list ap; @@ -69,14 +53,13 @@ static int __initdata keep_early; static int __init setup_early_printk(char *str) { - if (early_console_initialized) + if (early_console) return 1; if (str != NULL && strncmp(str, "keep", 4) == 0) keep_early = 1; early_console = &early_hv_console; - early_console_initialized = 1; register_console(early_console); return 0; @@ -85,12 +68,12 @@ static int __init setup_early_printk(char *str) void __init disable_early_printk(void) { early_console_complete = 1; - if (!early_console_initialized || !early_console) + if (!early_console) return; if (!keep_early) { early_printk("disabling early console\n"); unregister_console(early_console); - early_console_initialized = 0; + early_console = NULL; } else { early_printk("keeping early console\n"); } @@ -98,7 +81,7 @@ void __init disable_early_printk(void) void warn_early_printk(void) { - if (early_console_complete || early_console_initialized) + if (early_console_complete || early_console) return; early_printk("\ Machine shutting down before console output is fully initialized.\n\ diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index caf93ae..80b2a18 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -40,13 +40,11 @@ #include <arch/abi.h> #include <arch/sim_def.h> - /* * Use the (x86) "idle=poll" option to prefer low latency when leaving the * idle loop over low power while in the idle loop, e.g. if we have * one thread per core and we want to get threads out of futex waits fast. */ -static int no_idle_nap; static int __init idle_setup(char *str) { if (!str) @@ -54,64 +52,19 @@ static int __init idle_setup(char *str) if (!strcmp(str, "poll")) { pr_info("using polling idle threads.\n"); - no_idle_nap = 1; - } else if (!strcmp(str, "halt")) - no_idle_nap = 0; - else - return -1; - - return 0; + cpu_idle_poll_ctrl(true); + return 0; + } else if (!strcmp(str, "halt")) { + return 0; + } + return -1; } early_param("idle", idle_setup); -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle(void) +void arch_cpu_idle(void) { - int cpu = smp_processor_id(); - - - current_thread_info()->status |= TS_POLLING; - - if (no_idle_nap) { - while (1) { - while (!need_resched()) - cpu_relax(); - schedule(); - } - } - - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - while (!need_resched()) { - if (cpu_is_offline(cpu)) - BUG(); /* no HOTPLUG_CPU */ - - local_irq_disable(); - __get_cpu_var(irq_stat).idle_timestamp = jiffies; - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - - if (!need_resched()) - _cpu_idle(); - else - local_irq_enable(); - current_thread_info()->status |= TS_POLLING; - } - rcu_idle_exit(); - tick_nohz_idle_exit(); - schedule_preempt_disabled(); - } + __get_cpu_var(irq_stat).idle_timestamp = jiffies; + _cpu_idle(); } /* diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c index e686c5a..44bab29 100644 --- a/arch/tile/kernel/smpboot.c +++ b/arch/tile/kernel/smpboot.c @@ -207,9 +207,7 @@ void __cpuinit online_secondary(void) /* Set up tile-timer clock-event device on this cpu */ setup_tile_timer(); - preempt_enable(); - - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c index b3b4972..dfd63ce 100644 --- a/arch/tile/mm/pgtable.c +++ b/arch/tile/mm/pgtable.c @@ -592,12 +592,7 @@ void iounmap(volatile void __iomem *addr_in) in parallel. Reuse of the virtual address is prevented by leaving it in the global lists until we're done with it. cpa takes care of the direct mappings. */ - read_lock(&vmlist_lock); - for (p = vmlist; p; p = p->next) { - if (p->addr == addr) - break; - } - read_unlock(&vmlist_lock); + p = find_vm_area((void *)addr); if (!p) { pr_err("iounmap: bad address %p\n", addr); diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c index 80b47cb..acbe6c6 100644 --- a/arch/um/drivers/chan_kern.c +++ b/arch/um/drivers/chan_kern.c @@ -568,11 +568,7 @@ void chan_interrupt(struct line *line, int irq) reactivate_fd(chan->fd, irq); if (err == -EIO) { if (chan->primary) { - struct tty_struct *tty = tty_port_tty_get(&line->port); - if (tty != NULL) { - tty_hangup(tty); - tty_kref_put(tty); - } + tty_port_tty_hangup(&line->port, false); if (line->chan_out != chan) close_one_chan(line->chan_out, 1); } diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index be541cf..8035145 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -248,7 +248,6 @@ static irqreturn_t line_write_interrupt(int irq, void *data) { struct chan *chan = data; struct line *line = chan->line; - struct tty_struct *tty; int err; /* @@ -267,12 +266,7 @@ static irqreturn_t line_write_interrupt(int irq, void *data) } spin_unlock(&line->lock); - tty = tty_port_tty_get(&line->port); - if (tty == NULL) - return IRQ_NONE; - - tty_wakeup(tty); - tty_kref_put(tty); + tty_port_tty_wakeup(&line->port); return IRQ_HANDLED; } diff --git a/arch/um/kernel/early_printk.c b/arch/um/kernel/early_printk.c index 49480f0..4a0800b 100644 --- a/arch/um/kernel/early_printk.c +++ b/arch/um/kernel/early_printk.c @@ -16,7 +16,7 @@ static void early_console_write(struct console *con, const char *s, unsigned int um_early_printk(s, n); } -static struct console early_console = { +static struct console early_console_dev = { .name = "earlycon", .write = early_console_write, .flags = CON_BOOT, @@ -25,8 +25,10 @@ static struct console early_console = { static int __init setup_early_printk(char *buf) { - register_console(&early_console); - + if (!early_console) { + early_console = &early_console_dev; + register_console(&early_console_dev); + } return 0; } diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 5abcbfb..9df292b 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -42,17 +42,12 @@ static unsigned long brk_end; static void setup_highmem(unsigned long highmem_start, unsigned long highmem_len) { - struct page *page; unsigned long highmem_pfn; int i; highmem_pfn = __pa(highmem_start) >> PAGE_SHIFT; - for (i = 0; i < highmem_len >> PAGE_SHIFT; i++) { - page = &mem_map[highmem_pfn + i]; - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - } + for (i = 0; i < highmem_len >> PAGE_SHIFT; i++) + free_highmem_page(&mem_map[highmem_pfn + i]); } #endif @@ -73,18 +68,13 @@ void __init mem_init(void) totalram_pages = free_all_bootmem(); max_low_pfn = totalram_pages; #ifdef CONFIG_HIGHMEM - totalhigh_pages = highmem >> PAGE_SHIFT; - totalram_pages += totalhigh_pages; + setup_highmem(end_iomem, highmem); #endif num_physpages = totalram_pages; max_pfn = totalram_pages; printk(KERN_INFO "Memory: %luk available\n", nr_free_pages() << (PAGE_SHIFT-10)); kmalloc_ok = 1; - -#ifdef CONFIG_HIGHMEM - setup_highmem(end_iomem, highmem); -#endif } /* @@ -254,15 +244,7 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - if (start < end) - printk(KERN_INFO "Freeing initrd memory: %ldk freed\n", - (end - start) >> 10); - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - } + free_reserved_area(start, end, 0, "initrd"); } #endif diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index b462b13..bbcef52 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -210,33 +210,14 @@ void initial_thread_cb(void (*proc)(void *), void *arg) kmalloc_ok = save_kmalloc_ok; } -void default_idle(void) +void arch_cpu_idle(void) { unsigned long long nsecs; - while (1) { - /* endless idle loop with no priority at all */ - - /* - * although we are an idle CPU, we do not want to - * get into the scheduler unnecessarily. - */ - if (need_resched()) - schedule(); - - tick_nohz_idle_enter(); - rcu_idle_enter(); - nsecs = disable_timer(); - idle_sleep(nsecs); - rcu_idle_exit(); - tick_nohz_idle_exit(); - } -} - -void cpu_idle(void) -{ cpu_tasks[current_thread_info()->cpu].pid = os_getpid(); - default_idle(); + nsecs = disable_timer(); + idle_sleep(nsecs); + local_irq_enable(); } int __cant_sleep(void) { diff --git a/arch/unicore32/kernel/early_printk.c b/arch/unicore32/kernel/early_printk.c index 3922255..9be0d5d 100644 --- a/arch/unicore32/kernel/early_printk.c +++ b/arch/unicore32/kernel/early_printk.c @@ -33,21 +33,17 @@ static struct console early_ocd_console = { .index = -1, }; -/* Direct interface for emergencies */ -static struct console *early_console = &early_ocd_console; - -static int __initdata keep_early; - static int __init setup_early_printk(char *buf) { - if (!buf) + int keep_early; + + if (!buf || early_console) return 0; if (strstr(buf, "keep")) keep_early = 1; - if (!strncmp(buf, "ocd", 3)) - early_console = &early_ocd_console; + early_console = &early_ocd_console; if (keep_early) early_console->flags &= ~CON_BOOT; diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c index 872d7e2..7fab86d 100644 --- a/arch/unicore32/kernel/process.c +++ b/arch/unicore32/kernel/process.c @@ -45,25 +45,10 @@ static const char * const processor_modes[] = { "UK18", "UK19", "UK1A", "EXTN", "UK1C", "UK1D", "UK1E", "SUSR" }; -void cpu_idle(void) +void arch_cpu_idle(void) { - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - while (!need_resched()) { - local_irq_disable(); - stop_critical_timings(); - cpu_do_idle(); - local_irq_enable(); - start_critical_timings(); - } - rcu_idle_exit(); - tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); - } + cpu_do_idle(); + local_irq_enable(); } static char reboot_mode = 'h'; diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c index de186bd..63df12d 100644 --- a/arch/unicore32/mm/init.c +++ b/arch/unicore32/mm/init.c @@ -66,6 +66,9 @@ void show_mem(unsigned int filter) printk(KERN_DEFAULT "Mem-info:\n"); show_free_areas(filter); + if (filter & SHOW_MEM_FILTER_PAGE_COUNT) + return; + for_each_bank(i, mi) { struct membank *bank = &mi->bank[i]; unsigned int pfn1, pfn2; @@ -313,24 +316,6 @@ void __init bootmem_init(void) max_pfn = max_high - PHYS_PFN_OFFSET; } -static inline int free_area(unsigned long pfn, unsigned long end, char *s) -{ - unsigned int pages = 0, size = (end - pfn) << (PAGE_SHIFT - 10); - - for (; pfn < end; pfn++) { - struct page *page = pfn_to_page(pfn); - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - pages++; - } - - if (size && s) - printk(KERN_INFO "Freeing %s memory: %dK\n", s, size); - - return pages; -} - static inline void free_memmap(unsigned long start_pfn, unsigned long end_pfn) { @@ -404,9 +389,9 @@ void __init mem_init(void) max_mapnr = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map; - /* this will put all unused low memory onto the freelists */ free_unused_memmap(&meminfo); + /* this will put all unused low memory onto the freelists */ totalram_pages += free_all_bootmem(); reserved_pages = free_pages = 0; @@ -491,9 +476,7 @@ void __init mem_init(void) void free_initmem(void) { - totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)), - __phys_to_pfn(__pa(__init_end)), - "init"); + free_initmem_default(0); } #ifdef CONFIG_BLK_DEV_INITRD @@ -503,9 +486,7 @@ static int keep_initrd; void free_initrd_mem(unsigned long start, unsigned long end) { if (!keep_initrd) - totalram_pages += free_area(__phys_to_pfn(__pa(start)), - __phys_to_pfn(__pa(end)), - "initrd"); + free_reserved_area(start, end, 0, "initrd"); } static int __init keepinitrd_setup(char *__unused) diff --git a/arch/unicore32/mm/ioremap.c b/arch/unicore32/mm/ioremap.c index b7a6055..13068ee 100644 --- a/arch/unicore32/mm/ioremap.c +++ b/arch/unicore32/mm/ioremap.c @@ -235,7 +235,7 @@ EXPORT_SYMBOL(__uc32_ioremap_cached); void __uc32_iounmap(volatile void __iomem *io_addr) { void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr); - struct vm_struct **p, *tmp; + struct vm_struct *vm; /* * If this is a section based mapping we need to handle it @@ -244,17 +244,10 @@ void __uc32_iounmap(volatile void __iomem *io_addr) * all the mappings before the area can be reclaimed * by someone else. */ - write_lock(&vmlist_lock); - for (p = &vmlist ; (tmp = *p) ; p = &tmp->next) { - if ((tmp->flags & VM_IOREMAP) && (tmp->addr == addr)) { - if (tmp->flags & VM_UNICORE_SECTION_MAPPING) { - unmap_area_sections((unsigned long)tmp->addr, - tmp->size); - } - break; - } - } - write_unlock(&vmlist_lock); + vm = find_vm_area(addr); + if (vm && (vm->flags & VM_IOREMAP) && + (vm->flags & VM_UNICORE_SECTION_MAPPING)) + unmap_area_sections((unsigned long)vm->addr, vm->size); vunmap(addr); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 70c0f3d..05b057d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -120,6 +120,7 @@ config X86 select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION select OLD_SIGACTION if X86_32 select COMPAT_OLD_SIGACTION if IA32_EMULATION + select RTC_LIB config INSTRUCTION_DECODER def_bool y @@ -188,9 +189,6 @@ config GENERIC_CALIBRATE_DELAY config ARCH_HAS_CPU_RELAX def_bool y -config ARCH_HAS_DEFAULT_IDLE - def_bool y - config ARCH_HAS_CACHE_LINE_SIZE def_bool y @@ -389,7 +387,7 @@ config X86_NUMACHIP config X86_VSMP bool "ScaleMP vSMP" - select PARAVIRT_GUEST + select HYPERVISOR_GUEST select PARAVIRT depends on X86_64 && PCI depends on X86_EXTENDED_PLATFORM @@ -596,44 +594,17 @@ config SCHED_OMIT_FRAME_POINTER If in doubt, say "Y". -menuconfig PARAVIRT_GUEST - bool "Paravirtualized guest support" - ---help--- - Say Y here to get to see options related to running Linux under - various hypervisors. This option alone does not add any kernel code. - - If you say N, all options in this submenu will be skipped and disabled. - -if PARAVIRT_GUEST - -config PARAVIRT_TIME_ACCOUNTING - bool "Paravirtual steal time accounting" - select PARAVIRT - default n +menuconfig HYPERVISOR_GUEST + bool "Linux guest support" ---help--- - Select this option to enable fine granularity task steal time - accounting. Time spent executing other tasks in parallel with - the current vCPU is discounted from the vCPU power. To account for - that, there can be a small performance impact. - - If in doubt, say N here. - -source "arch/x86/xen/Kconfig" + Say Y here to enable options for running Linux under various hyper- + visors. This option enables basic hypervisor detection and platform + setup. -config KVM_GUEST - bool "KVM Guest support (including kvmclock)" - select PARAVIRT - select PARAVIRT - select PARAVIRT_CLOCK - default y if PARAVIRT_GUEST - ---help--- - This option enables various optimizations for running under the KVM - hypervisor. It includes a paravirtualized clock, so that instead - of relying on a PIT (or probably other) emulation by the - underlying device model, the host provides the guest with - timing infrastructure such as time of day, and system time + If you say N, all options in this submenu will be skipped and + disabled, and Linux guest support won't be built in. -source "arch/x86/lguest/Kconfig" +if HYPERVISOR_GUEST config PARAVIRT bool "Enable paravirtualization code" @@ -643,6 +614,13 @@ config PARAVIRT over full virtualization. However, when run without a hypervisor the kernel is theoretically slower and slightly larger. +config PARAVIRT_DEBUG + bool "paravirt-ops debugging" + depends on PARAVIRT && DEBUG_KERNEL + ---help--- + Enable to debug paravirt_ops internals. Specifically, BUG if + a paravirt_op is missing when it is called. + config PARAVIRT_SPINLOCKS bool "Paravirtualization layer for spinlocks" depends on PARAVIRT && SMP @@ -656,17 +634,38 @@ config PARAVIRT_SPINLOCKS If you are unsure how to answer this question, answer N. -config PARAVIRT_CLOCK - bool +source "arch/x86/xen/Kconfig" -endif +config KVM_GUEST + bool "KVM Guest support (including kvmclock)" + depends on PARAVIRT + select PARAVIRT_CLOCK + default y + ---help--- + This option enables various optimizations for running under the KVM + hypervisor. It includes a paravirtualized clock, so that instead + of relying on a PIT (or probably other) emulation by the + underlying device model, the host provides the guest with + timing infrastructure such as time of day, and system time -config PARAVIRT_DEBUG - bool "paravirt-ops debugging" - depends on PARAVIRT && DEBUG_KERNEL +source "arch/x86/lguest/Kconfig" + +config PARAVIRT_TIME_ACCOUNTING + bool "Paravirtual steal time accounting" + depends on PARAVIRT + default n ---help--- - Enable to debug paravirt_ops internals. Specifically, BUG if - a paravirt_op is missing when it is called. + Select this option to enable fine granularity task steal time + accounting. Time spent executing other tasks in parallel with + the current vCPU is discounted from the vCPU power. To account for + that, there can be a small performance impact. + + If in doubt, say N here. + +config PARAVIRT_CLOCK + bool + +endif #HYPERVISOR_GUEST config NO_BOOTMEM def_bool y @@ -1549,6 +1548,7 @@ config X86_SMAP config EFI bool "EFI runtime service support" depends on ACPI + select UCS2_STRING ---help--- This enables the kernel to use EFI runtime services that are available (such as the EFI variable services). diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index b322f12..16f7383 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -131,7 +131,7 @@ config DOUBLEFAULT config DEBUG_TLBFLUSH bool "Set upper limit of TLB entries to flush one-by-one" - depends on DEBUG_KERNEL && (X86_64 || X86_INVLPG) + depends on DEBUG_KERNEL ---help--- X86-only for now. diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index c205035..35ee62f 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -251,6 +251,51 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size) *size = len; } +static efi_status_t setup_efi_vars(struct boot_params *params) +{ + struct setup_data *data; + struct efi_var_bootdata *efidata; + u64 store_size, remaining_size, var_size; + efi_status_t status; + + if (sys_table->runtime->hdr.revision < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + status = efi_call_phys4((void *)sys_table->runtime->query_variable_info, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, &store_size, + &remaining_size, &var_size); + + if (status != EFI_SUCCESS) + return status; + + status = efi_call_phys3(sys_table->boottime->allocate_pool, + EFI_LOADER_DATA, sizeof(*efidata), &efidata); + + if (status != EFI_SUCCESS) + return status; + + efidata->data.type = SETUP_EFI_VARS; + efidata->data.len = sizeof(struct efi_var_bootdata) - + sizeof(struct setup_data); + efidata->data.next = 0; + efidata->store_size = store_size; + efidata->remaining_size = remaining_size; + efidata->max_var_size = var_size; + + if (data) + data->next = (unsigned long)efidata; + else + params->hdr.setup_data = (unsigned long)efidata; + +} + static efi_status_t setup_efi_pci(struct boot_params *params) { efi_pci_io_protocol *pci; @@ -1157,6 +1202,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table, setup_graphics(boot_params); + setup_efi_vars(boot_params); + setup_efi_pci(boot_params); status = efi_call_phys3(sys_table->boottime->allocate_pool, diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index c1d383d..16f24e6 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -52,7 +52,7 @@ ENTRY(startup_32) jnz 1f cli - movl $(__KERNEL_DS), %eax + movl $(__BOOT_DS), %eax movl %eax, %ds movl %eax, %es movl %eax, %ss diff --git a/arch/x86/include/asm/context_tracking.h b/arch/x86/include/asm/context_tracking.h index 1616562..1fe4970 100644 --- a/arch/x86/include/asm/context_tracking.h +++ b/arch/x86/include/asm/context_tracking.h @@ -1,31 +1,10 @@ #ifndef _ASM_X86_CONTEXT_TRACKING_H #define _ASM_X86_CONTEXT_TRACKING_H -#ifndef __ASSEMBLY__ -#include <linux/context_tracking.h> -#include <asm/ptrace.h> - -static inline void exception_enter(struct pt_regs *regs) -{ - user_exit(); -} - -static inline void exception_exit(struct pt_regs *regs) -{ -#ifdef CONFIG_CONTEXT_TRACKING - if (user_mode(regs)) - user_enter(); -#endif -} - -#else /* __ASSEMBLY__ */ - #ifdef CONFIG_CONTEXT_TRACKING # define SCHEDULE_USER call schedule_user #else # define SCHEDULE_USER call schedule #endif -#endif /* !__ASSEMBLY__ */ - #endif diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 93fe929..398f7cb 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -9,6 +9,7 @@ #endif #define NCAPINTS 10 /* N 32-bit words worth of info */ +#define NBUGINTS 1 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used @@ -100,6 +101,7 @@ #define X86_FEATURE_AMD_DCM (3*32+27) /* multi-node processor */ #define X86_FEATURE_APERFMPERF (3*32+28) /* APERFMPERF */ #define X86_FEATURE_EAGER_FPU (3*32+29) /* "eagerfpu" Non lazy FPU restore */ +#define X86_FEATURE_NONSTOP_TSC_S3 (3*32+30) /* TSC doesn't stop in S3 state */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ #define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */ @@ -168,6 +170,7 @@ #define X86_FEATURE_TOPOEXT (6*32+22) /* topology extensions CPUID leafs */ #define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */ #define X86_FEATURE_PERFCTR_NB (6*32+24) /* NB performance counter extensions */ +#define X86_FEATURE_PERFCTR_L2 (6*32+28) /* L2 performance counter extensions */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -216,6 +219,17 @@ #define X86_FEATURE_ADX (9*32+19) /* The ADCX and ADOX instructions */ #define X86_FEATURE_SMAP (9*32+20) /* Supervisor Mode Access Prevention */ +/* + * BUG word(s) + */ +#define X86_BUG(x) (NCAPINTS*32 + (x)) + +#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ +#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ +#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ +#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* AMD Erratum 383 */ +#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* AMD Erratum 400 */ + #if defined(__KERNEL__) && !defined(__ASSEMBLY__) #include <asm/asm.h> @@ -311,6 +325,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) #define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE) #define cpu_has_perfctr_nb boot_cpu_has(X86_FEATURE_PERFCTR_NB) +#define cpu_has_perfctr_l2 boot_cpu_has(X86_FEATURE_PERFCTR_L2) #define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8) #define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) #define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) @@ -401,6 +416,13 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) #define static_cpu_has(bit) boot_cpu_has(bit) #endif +#define cpu_has_bug(c, bit) cpu_has(c, (bit)) +#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) +#define clear_cpu_bug(c, bit) clear_cpu_cap(c, (bit)); + +#define static_cpu_has_bug(bit) static_cpu_has((bit)) +#define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit)) + #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */ #endif /* _ASM_X86_CPUFEATURE_H */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 60c89f3..2fb5d58 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -102,6 +102,13 @@ extern void efi_call_phys_epilog(void); extern void efi_unmap_memmap(void); extern void efi_memory_uc(u64 addr, unsigned long size); +struct efi_var_bootdata { + struct setup_data data; + u64 store_size; + u64 remaining_size; + u64 max_var_size; +}; + #ifdef CONFIG_EFI static inline bool efi_is_native(void) diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index a09c285..0dc7d9e 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -104,12 +104,7 @@ enum fixed_addresses { FIX_LI_PCIA, /* Lithium PCI Bridge A */ FIX_LI_PCIB, /* Lithium PCI Bridge B */ #endif -#ifdef CONFIG_X86_F00F_BUG - FIX_F00F_IDT, /* Virtual mapping for IDT */ -#endif -#ifdef CONFIG_X86_CYCLONE_TIMER - FIX_CYCLONE_TIMER, /*cyclone timer register*/ -#endif + FIX_RO_IDT, /* Virtual mapping for read-only IDT */ #ifdef CONFIG_X86_32 FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index bdd35db..a809121 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -2,6 +2,7 @@ #define _ASM_X86_HUGETLB_H #include <asm/page.h> +#include <asm-generic/hugetlb.h> static inline int is_hugepage_only_range(struct mm_struct *mm, diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 86095ed..2d4b5e6 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -20,13 +20,11 @@ #ifndef _ASM_X86_HYPERVISOR_H #define _ASM_X86_HYPERVISOR_H +#ifdef CONFIG_HYPERVISOR_GUEST + #include <asm/kvm_para.h> #include <asm/xen/hypervisor.h> -extern void init_hypervisor(struct cpuinfo_x86 *c); -extern void init_hypervisor_platform(void); -extern bool hypervisor_x2apic_available(void); - /* * x86 hypervisor information */ @@ -55,4 +53,12 @@ extern const struct hypervisor_x86 x86_hyper_ms_hyperv; extern const struct hypervisor_x86 x86_hyper_xen_hvm; extern const struct hypervisor_x86 x86_hyper_kvm; -#endif +extern void init_hypervisor(struct cpuinfo_x86 *c); +extern void init_hypervisor_platform(void); +extern bool hypervisor_x2apic_available(void); +#else +static inline void init_hypervisor(struct cpuinfo_x86 *c) { } +static inline void init_hypervisor_platform(void) { } +static inline bool hypervisor_x2apic_available(void) { return false; } +#endif /* CONFIG_HYPERVISOR_GUEST */ +#endif /* _ASM_X86_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 9264802..cb75028 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -137,11 +137,11 @@ static inline unsigned long long native_read_pmc(int counter) * pointer indirection), this allows gcc to optimize better */ -#define rdmsr(msr, val1, val2) \ +#define rdmsr(msr, low, high) \ do { \ u64 __val = native_read_msr((msr)); \ - (void)((val1) = (u32)__val); \ - (void)((val2) = (u32)(__val >> 32)); \ + (void)((low) = (u32)__val); \ + (void)((high) = (u32)(__val >> 32)); \ } while (0) static inline void wrmsr(unsigned msr, unsigned low, unsigned high) @@ -162,12 +162,12 @@ static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high) } /* rdmsr with exception handling */ -#define rdmsr_safe(msr, p1, p2) \ +#define rdmsr_safe(msr, low, high) \ ({ \ int __err; \ u64 __val = native_read_msr_safe((msr), &__err); \ - (*p1) = (u32)__val; \ - (*p2) = (u32)(__val >> 32); \ + (*low) = (u32)__val; \ + (*high) = (u32)(__val >> 32); \ __err; \ }) @@ -208,7 +208,7 @@ do { \ #define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val), \ (u32)((val) >> 32)) -#define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2)) +#define write_tsc(low, high) wrmsr(MSR_IA32_TSC, (low), (high)) #define write_rdtscp_aux(val) wrmsr(MSR_TSC_AUX, (val), 0) diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 8b491e6..6c896fb 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -48,6 +48,5 @@ * arch/x86/kernel/head_64.S), and it is mapped here: */ #define KERNEL_IMAGE_SIZE (512 * 1024 * 1024) -#define KERNEL_IMAGE_START _AC(0xffffffff80000000, UL) #endif /* _ASM_X86_PAGE_64_DEFS_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 7361e47..cfdc9ee 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -262,10 +262,6 @@ static inline void set_ldt(const void *addr, unsigned entries) { PVOP_VCALL2(pv_cpu_ops.set_ldt, addr, entries); } -static inline void store_gdt(struct desc_ptr *dtr) -{ - PVOP_VCALL1(pv_cpu_ops.store_gdt, dtr); -} static inline void store_idt(struct desc_ptr *dtr) { PVOP_VCALL1(pv_cpu_ops.store_idt, dtr); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index b3b0ec1..0db1fca 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -123,7 +123,7 @@ struct pv_cpu_ops { void (*load_tr_desc)(void); void (*load_gdt)(const struct desc_ptr *); void (*load_idt)(const struct desc_ptr *); - void (*store_gdt)(struct desc_ptr *); + /* store_gdt has been removed. */ void (*store_idt)(struct desc_ptr *); void (*set_ldt)(const void *desc, unsigned entries); unsigned long (*store_tr)(void); diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index 4f7e67e..85e13cc 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -24,45 +24,45 @@ #define ARCH_P4_CNTRVAL_MASK ((1ULL << ARCH_P4_CNTRVAL_BITS) - 1) #define ARCH_P4_UNFLAGGED_BIT ((1ULL) << (ARCH_P4_CNTRVAL_BITS - 1)) -#define P4_ESCR_EVENT_MASK 0x7e000000U +#define P4_ESCR_EVENT_MASK 0x7e000000ULL #define P4_ESCR_EVENT_SHIFT 25 -#define P4_ESCR_EVENTMASK_MASK 0x01fffe00U +#define P4_ESCR_EVENTMASK_MASK 0x01fffe00ULL #define P4_ESCR_EVENTMASK_SHIFT 9 -#define P4_ESCR_TAG_MASK 0x000001e0U +#define P4_ESCR_TAG_MASK 0x000001e0ULL #define P4_ESCR_TAG_SHIFT 5 -#define P4_ESCR_TAG_ENABLE 0x00000010U -#define P4_ESCR_T0_OS 0x00000008U -#define P4_ESCR_T0_USR 0x00000004U -#define P4_ESCR_T1_OS 0x00000002U -#define P4_ESCR_T1_USR 0x00000001U +#define P4_ESCR_TAG_ENABLE 0x00000010ULL +#define P4_ESCR_T0_OS 0x00000008ULL +#define P4_ESCR_T0_USR 0x00000004ULL +#define P4_ESCR_T1_OS 0x00000002ULL +#define P4_ESCR_T1_USR 0x00000001ULL #define P4_ESCR_EVENT(v) ((v) << P4_ESCR_EVENT_SHIFT) #define P4_ESCR_EMASK(v) ((v) << P4_ESCR_EVENTMASK_SHIFT) #define P4_ESCR_TAG(v) ((v) << P4_ESCR_TAG_SHIFT) -#define P4_CCCR_OVF 0x80000000U -#define P4_CCCR_CASCADE 0x40000000U -#define P4_CCCR_OVF_PMI_T0 0x04000000U -#define P4_CCCR_OVF_PMI_T1 0x08000000U -#define P4_CCCR_FORCE_OVF 0x02000000U -#define P4_CCCR_EDGE 0x01000000U -#define P4_CCCR_THRESHOLD_MASK 0x00f00000U +#define P4_CCCR_OVF 0x80000000ULL +#define P4_CCCR_CASCADE 0x40000000ULL +#define P4_CCCR_OVF_PMI_T0 0x04000000ULL +#define P4_CCCR_OVF_PMI_T1 0x08000000ULL +#define P4_CCCR_FORCE_OVF 0x02000000ULL +#define P4_CCCR_EDGE 0x01000000ULL +#define P4_CCCR_THRESHOLD_MASK 0x00f00000ULL #define P4_CCCR_THRESHOLD_SHIFT 20 -#define P4_CCCR_COMPLEMENT 0x00080000U -#define P4_CCCR_COMPARE 0x00040000U -#define P4_CCCR_ESCR_SELECT_MASK 0x0000e000U +#define P4_CCCR_COMPLEMENT 0x00080000ULL +#define P4_CCCR_COMPARE 0x00040000ULL +#define P4_CCCR_ESCR_SELECT_MASK 0x0000e000ULL #define P4_CCCR_ESCR_SELECT_SHIFT 13 -#define P4_CCCR_ENABLE 0x00001000U -#define P4_CCCR_THREAD_SINGLE 0x00010000U -#define P4_CCCR_THREAD_BOTH 0x00020000U -#define P4_CCCR_THREAD_ANY 0x00030000U -#define P4_CCCR_RESERVED 0x00000fffU +#define P4_CCCR_ENABLE 0x00001000ULL +#define P4_CCCR_THREAD_SINGLE 0x00010000ULL +#define P4_CCCR_THREAD_BOTH 0x00020000ULL +#define P4_CCCR_THREAD_ANY 0x00030000ULL +#define P4_CCCR_RESERVED 0x00000fffULL #define P4_CCCR_THRESHOLD(v) ((v) << P4_CCCR_THRESHOLD_SHIFT) #define P4_CCCR_ESEL(v) ((v) << P4_CCCR_ESCR_SELECT_SHIFT) #define P4_GEN_ESCR_EMASK(class, name, bit) \ - class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT) + class##__##name = ((1ULL << bit) << P4_ESCR_EVENTMASK_SHIFT) #define P4_ESCR_EMASK_BIT(class, name) class##__##name /* @@ -107,7 +107,7 @@ * P4_PEBS_CONFIG_MASK and related bits on * modification.) */ -#define P4_CONFIG_ALIASABLE (1 << 9) +#define P4_CONFIG_ALIASABLE (1ULL << 9) /* * The bits we allow to pass for RAW events @@ -784,17 +784,17 @@ enum P4_ESCR_EMASKS { * Note we have UOP and PEBS bits reserved for now * just in case if we will need them once */ -#define P4_PEBS_CONFIG_ENABLE (1 << 7) -#define P4_PEBS_CONFIG_UOP_TAG (1 << 8) -#define P4_PEBS_CONFIG_METRIC_MASK 0x3f -#define P4_PEBS_CONFIG_MASK 0xff +#define P4_PEBS_CONFIG_ENABLE (1ULL << 7) +#define P4_PEBS_CONFIG_UOP_TAG (1ULL << 8) +#define P4_PEBS_CONFIG_METRIC_MASK 0x3FLL +#define P4_PEBS_CONFIG_MASK 0xFFLL /* * mem: Only counters MSR_IQ_COUNTER4 (16) and * MSR_IQ_COUNTER5 (17) are allowed for PEBS sampling */ -#define P4_PEBS_ENABLE 0x02000000U -#define P4_PEBS_ENABLE_UOP_TAG 0x01000000U +#define P4_PEBS_ENABLE 0x02000000ULL +#define P4_PEBS_ENABLE_UOP_TAG 0x01000000ULL #define p4_config_unpack_metric(v) (((u64)(v)) & P4_PEBS_CONFIG_METRIC_MASK) #define p4_config_unpack_pebs(v) (((u64)(v)) & P4_PEBS_CONFIG_MASK) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 567b5d0..e642300 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -351,7 +351,6 @@ static inline void update_page_count(int level, unsigned long pages) { } * as a pte too. */ extern pte_t *lookup_address(unsigned long address, unsigned int *level); -extern int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase); extern phys_addr_t slow_virt_to_phys(void *__address); #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 3270116..22224b3 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -91,9 +91,6 @@ struct cpuinfo_x86 { /* Problems on some 486Dx4's and old 386's: */ char hard_math; char rfu; - char fdiv_bug; - char f00f_bug; - char coma_bug; char pad0; #else /* Number of 4K pages in DTLB/ITLB combined(in pages): */ @@ -107,7 +104,7 @@ struct cpuinfo_x86 { __u32 extended_cpuid_level; /* Maximum supported CPUID level, -1=no CPUID: */ int cpuid_level; - __u32 x86_capability[NCAPINTS]; + __u32 x86_capability[NCAPINTS + NBUGINTS]; char x86_vendor_id[16]; char x86_model_id[64]; /* in KB - valid for CPUS which support this call: */ @@ -973,26 +970,6 @@ unsigned long calc_aperfmperf_ratio(struct aperfmperf *old, return ratio; } -/* - * AMD errata checking - */ -#ifdef CONFIG_CPU_SUP_AMD -extern const int amd_erratum_383[]; -extern const int amd_erratum_400[]; -extern bool cpu_has_amd_erratum(const int *); - -#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } -#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } -#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ - ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) -#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) -#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) -#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) - -#else -#define cpu_has_amd_erratum(x) (false) -#endif /* CONFIG_CPU_SUP_AMD */ - extern unsigned long arch_align_stack(unsigned long sp); extern void free_init_pages(char *what, unsigned long begin, unsigned long end); diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 487055c..f6064b7 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -15,7 +15,6 @@ struct saved_context { unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; bool misc_enable_saved; - struct desc_ptr gdt; struct desc_ptr idt; u16 ldt; u16 tss; diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 09b0bf1..97b84e0 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -25,9 +25,6 @@ struct saved_context { u64 misc_enable; bool misc_enable_saved; unsigned long efer; - u16 gdt_pad; - u16 gdt_limit; - unsigned long gdt_base; u16 idt_pad; u16 idt_limit; unsigned long idt_base; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 2cd056e..a1df6e8 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -241,8 +241,6 @@ static inline struct thread_info *current_thread_info(void) skip sending interrupt */ #define TS_RESTORE_SIGMASK 0x0008 /* restore signal mask in do_signal() */ -#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING) - #ifndef __ASSEMBLY__ #define HAVE_SET_RESTORE_SIGMASK 1 static inline void set_restore_sigmask(void) diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index 8ff8be7..6e51979 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -55,4 +55,5 @@ extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data); extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs); +extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs); #endif /* _ASM_UPROBES_H */ diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index c15ddaf..0874424 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -6,6 +6,7 @@ #define SETUP_E820_EXT 1 #define SETUP_DTB 2 #define SETUP_PCI 3 +#define SETUP_EFI_VARS 4 /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index 7a060f4..b575788 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -72,6 +72,7 @@ #define MSR_IA32_PEBS_ENABLE 0x000003f1 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 +#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 #define MSR_MTRRfix64K_00000 0x00000250 #define MSR_MTRRfix16K_80000 0x00000258 @@ -195,6 +196,10 @@ #define MSR_AMD64_IBSBRTARGET 0xc001103b #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +/* Fam 16h MSRs */ +#define MSR_F16H_L2I_PERF_CTL 0xc0010230 +#define MSR_F16H_L2I_PERF_CTR 0xc0010231 + /* Fam 15h MSRs */ #define MSR_F15H_PERF_CTL 0xc0010200 #define MSR_F15H_PERF_CTR 0xc0010201 diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 0532f5d..b44577b 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -46,7 +46,7 @@ int acpi_suspend_lowlevel(void) header->pmode_behavior = 0; #ifndef CONFIG_64BIT - store_gdt((struct desc_ptr *)&header->pmode_gdt); + native_store_gdt((struct desc_ptr *)&header->pmode_gdt); if (!rdmsr_safe(MSR_EFER, &header->pmode_efer_low, diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index 13ab720..d1daa66 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -1,4 +1,4 @@ - .section .text..page_aligned + .text #include <linux/linkage.h> #include <asm/segment.h> #include <asm/page_types.h> @@ -18,7 +18,6 @@ wakeup_pmode_return: movw %ax, %gs # reload the gdt, as we need the full 32 bit address - lgdt saved_gdt lidt saved_idt lldt saved_ldt ljmp $(__KERNEL_CS), $1f @@ -44,7 +43,6 @@ bogus_magic: save_registers: - sgdt saved_gdt sidt saved_idt sldt saved_ldt str saved_tss @@ -93,7 +91,6 @@ ENTRY(saved_magic) .long 0 ENTRY(saved_eip) .long 0 # saved registers -saved_gdt: .long 0,0 saved_idt: .long 0,0 saved_ldt: .long 0 saved_tss: .long 0 diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ef5ccca..c15cf9a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -271,7 +271,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start, replacement = (u8 *)&a->repl_offset + a->repl_offset; BUG_ON(a->replacementlen > a->instrlen); BUG_ON(a->instrlen > sizeof(insnbuf)); - BUG_ON(a->cpuid >= NCAPINTS*32); + BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32); if (!boot_cpu_has(a->cpuid)) continue; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index f1d0a14..3048ded 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -25,7 +25,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { }; EXPORT_SYMBOL(amd_nb_misc_ids); -static struct pci_device_id amd_nb_link_ids[] = { +static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, {} diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index d5fd66f..fd972a3 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -87,7 +87,7 @@ static u32 __init allocate_aperture(void) */ addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR, aper_size, aper_size); - if (!addr || addr + aper_size > GART_MAX_ADDR) { + if (!addr) { printk(KERN_ERR "Cannot allocate aperture memory hole (%lx,%uK)\n", addr, aper_size>>10); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index a0e067d..b0684e4 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -14,7 +14,6 @@ CFLAGS_common.o := $(nostackp) obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += proc.o capflags.o powerflags.o common.o -obj-y += vmware.o hypervisor.o mshyperv.o obj-y += rdrand.o obj-y += match.o @@ -31,7 +30,7 @@ obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o ifdef CONFIG_PERF_EVENTS -obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o +obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o perf_event_amd_uncore.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o @@ -42,11 +41,13 @@ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o perf_event_amd_ibs.o +obj-$(CONFIG_HYPERVISOR_GUEST) += vmware.o hypervisor.o mshyperv.o + quiet_cmd_mkcapflags = MKCAP $@ - cmd_mkcapflags = $(PERL) $(srctree)/$(src)/mkcapflags.pl $< $@ + cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $< $@ cpufeature = $(src)/../../include/asm/cpufeature.h targets += capflags.c -$(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.pl FORCE +$(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE $(call if_changed,mkcapflags) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index fa96eb0..5013a48 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -20,11 +20,11 @@ static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { - struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); u32 gprs[8] = { 0 }; int err; - WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__); + WARN_ONCE((boot_cpu_data.x86 != 0xf), + "%s should only be used on K8!\n", __func__); gprs[1] = msr; gprs[7] = 0x9c5a203a; @@ -38,10 +38,10 @@ static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) { - struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); u32 gprs[8] = { 0 }; - WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__); + WARN_ONCE((boot_cpu_data.x86 != 0xf), + "%s should only be used on K8!\n", __func__); gprs[0] = (u32)val; gprs[1] = msr; @@ -192,11 +192,11 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) /* Athlon 660/661 is valid. */ if ((c->x86_model == 6) && ((c->x86_mask == 0) || (c->x86_mask == 1))) - goto valid_k7; + return; /* Duron 670 is valid */ if ((c->x86_model == 7) && (c->x86_mask == 0)) - goto valid_k7; + return; /* * Athlon 662, Duron 671, and Athlon >model 7 have capability @@ -209,7 +209,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) ((c->x86_model == 7) && (c->x86_mask >= 1)) || (c->x86_model > 7)) if (cpu_has_mp) - goto valid_k7; + return; /* If we get here, not a certified SMP capable AMD system. */ @@ -220,9 +220,6 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) WARN_ONCE(1, "WARNING: This combination of AMD" " processors is not suitable for SMP.\n"); add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE); - -valid_k7: - ; } static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) @@ -513,6 +510,10 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) #endif } +static const int amd_erratum_383[]; +static const int amd_erratum_400[]; +static bool cpu_has_amd_erratum(const int *erratum); + static void __cpuinit init_amd(struct cpuinfo_x86 *c) { u32 dummy; @@ -727,8 +728,14 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) rdmsrl_safe(MSR_AMD64_BU_CFG2, &value); value &= ~(1ULL << 24); wrmsrl_safe(MSR_AMD64_BU_CFG2, value); + + if (cpu_has_amd_erratum(amd_erratum_383)) + set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); } + if (cpu_has_amd_erratum(amd_erratum_400)) + set_cpu_bug(c, X86_BUG_AMD_APIC_C1E); + rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); } @@ -847,8 +854,7 @@ cpu_dev_register(amd_cpu_dev); * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that * have an OSVW id assigned, which it takes as first argument. Both take a * variable number of family-specific model-stepping ranges created by - * AMD_MODEL_RANGE(). Each erratum also has to be declared as extern const - * int[] in arch/x86/include/asm/processor.h. + * AMD_MODEL_RANGE(). * * Example: * @@ -858,16 +864,22 @@ cpu_dev_register(amd_cpu_dev); * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0)); */ -const int amd_erratum_400[] = +#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } +#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } +#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ + ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) +#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) +#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) +#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) + +static const int amd_erratum_400[] = AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); -EXPORT_SYMBOL_GPL(amd_erratum_400); -const int amd_erratum_383[] = +static const int amd_erratum_383[] = AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); -EXPORT_SYMBOL_GPL(amd_erratum_383); -bool cpu_has_amd_erratum(const int *erratum) +static bool cpu_has_amd_erratum(const int *erratum) { struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info); int osvw_id = *erratum++; @@ -908,5 +920,3 @@ bool cpu_has_amd_erratum(const int *erratum) return false; } - -EXPORT_SYMBOL_GPL(cpu_has_amd_erratum); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index af6455e..4112be9 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -59,7 +59,7 @@ static void __init check_fpu(void) * trap_init() enabled FXSR and company _before_ testing for FP * problems here. * - * Test for the divl bug.. + * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug */ __asm__("fninit\n\t" "fldl %1\n\t" @@ -75,26 +75,12 @@ static void __init check_fpu(void) kernel_fpu_end(); - boot_cpu_data.fdiv_bug = fdiv_bug; - if (boot_cpu_data.fdiv_bug) + if (fdiv_bug) { + set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV); pr_warn("Hmm, FPU with FDIV bug\n"); + } } -/* - * Check whether we are able to run this kernel safely on SMP. - * - * - i386 is no longer supported. - * - In order to run on anything without a TSC, we need to be - * compiled for a i486. - */ - -static void __init check_config(void) -{ - if (boot_cpu_data.x86 < 4) - panic("Kernel requires i486+ for 'invlpg' and other features"); -} - - void __init check_bugs(void) { identify_boot_cpu(); @@ -102,7 +88,17 @@ void __init check_bugs(void) pr_info("CPU: "); print_cpu_info(&boot_cpu_data); #endif - check_config(); + + /* + * Check whether we are able to run this kernel safely on SMP. + * + * - i386 is no longer supported. + * - In order to run on anything without a TSC, we need to be + * compiled for a i486. + */ + if (boot_cpu_data.x86 < 4) + panic("Kernel requires i486+ for 'invlpg' and other features"); + init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d814772..22018f7 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -920,6 +920,10 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) /* AND the already accumulated flags with these */ for (i = 0; i < NCAPINTS; i++) boot_cpu_data.x86_capability[i] &= c->x86_capability[i]; + + /* OR, i.e. replicate the bug flags */ + for (i = NCAPINTS; i < NCAPINTS + NBUGINTS; i++) + c->x86_capability[i] |= boot_cpu_data.x86_capability[i]; } /* Init Machine Check Exception if available. */ diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 4fbd384..d048d5c 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -249,7 +249,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) /* Emulate MTRRs using Cyrix's ARRs. */ set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); /* 6x86's contain this bug */ - c->coma_bug = 1; + set_cpu_bug(c, X86_BUG_COMA); break; case 4: /* MediaGX/GXm or Geode GXM/GXLV/GX1 */ @@ -317,7 +317,8 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) /* Enable MMX extensions (App note 108) */ setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1); } else { - c->coma_bug = 1; /* 6x86MX, it has the bug. */ + /* A 6x86MX - it has the bug. */ + set_cpu_bug(c, X86_BUG_COMA); } tmp = (!(dir0_lsn & 7) || dir0_lsn & 1) ? 2 : 0; Cx86_cb[tmp] = cyrix_model_mult2[dir0_lsn & 7]; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 1905ce9..9b0c441 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -96,6 +96,18 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) sched_clock_stable = 1; } + /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ + if (c->x86 == 6) { + switch (c->x86_model) { + case 0x27: /* Penwell */ + case 0x35: /* Cloverview */ + set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3); + break; + default: + break; + } + } + /* * There is a known erratum on Pentium III and Core Solo * and Core Duo CPUs. @@ -164,20 +176,6 @@ int __cpuinit ppro_with_ram_bug(void) return 0; } -#ifdef CONFIG_X86_F00F_BUG -static void __cpuinit trap_init_f00f_bug(void) -{ - __set_fixmap(FIX_F00F_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO); - - /* - * Update the IDT descriptor and reload the IDT so that - * it uses the read-only mapped virtual address. - */ - idt_descr.address = fix_to_virt(FIX_F00F_IDT); - load_idt(&idt_descr); -} -#endif - static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) { /* calling is from identify_secondary_cpu() ? */ @@ -206,16 +204,14 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) /* * All current models of Pentium and Pentium with MMX technology CPUs * have the F0 0F bug, which lets nonprivileged users lock up the - * system. - * Note that the workaround only should be initialized once... + * system. Announce that the fault handler will be checking for it. */ - c->f00f_bug = 0; + clear_cpu_bug(c, X86_BUG_F00F); if (!paravirt_enabled() && c->x86 == 5) { static int f00f_workaround_enabled; - c->f00f_bug = 1; + set_cpu_bug(c, X86_BUG_F00F); if (!f00f_workaround_enabled) { - trap_init_f00f_bug(); printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n"); f00f_workaround_enabled = 1; } diff --git a/arch/x86/kernel/cpu/mkcapflags.pl b/arch/x86/kernel/cpu/mkcapflags.pl deleted file mode 100644 index 091972e..0000000 --- a/arch/x86/kernel/cpu/mkcapflags.pl +++ /dev/null @@ -1,48 +0,0 @@ -#!/usr/bin/perl -w -# -# Generate the x86_cap_flags[] array from include/asm-x86/cpufeature.h -# - -($in, $out) = @ARGV; - -open(IN, "< $in\0") or die "$0: cannot open: $in: $!\n"; -open(OUT, "> $out\0") or die "$0: cannot create: $out: $!\n"; - -print OUT "#ifndef _ASM_X86_CPUFEATURE_H\n"; -print OUT "#include <asm/cpufeature.h>\n"; -print OUT "#endif\n"; -print OUT "\n"; -print OUT "const char * const x86_cap_flags[NCAPINTS*32] = {\n"; - -%features = (); -$err = 0; - -while (defined($line = <IN>)) { - if ($line =~ /^\s*\#\s*define\s+(X86_FEATURE_(\S+))\s+(.*)$/) { - $macro = $1; - $feature = "\L$2"; - $tail = $3; - if ($tail =~ /\/\*\s*\"([^"]*)\".*\*\//) { - $feature = "\L$1"; - } - - next if ($feature eq ''); - - if ($features{$feature}++) { - print STDERR "$in: duplicate feature name: $feature\n"; - $err++; - } - printf OUT "\t%-32s = \"%s\",\n", "[$macro]", $feature; - } -} -print OUT "};\n"; - -close(IN); -close(OUT); - -if ($err) { - unlink($out); - exit(1); -} - -exit(0); diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh new file mode 100644 index 0000000..2bf6165 --- /dev/null +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -0,0 +1,41 @@ +#!/bin/sh +# +# Generate the x86_cap_flags[] array from include/asm/cpufeature.h +# + +IN=$1 +OUT=$2 + +TABS="$(printf '\t\t\t\t\t')" +trap 'rm "$OUT"' EXIT + +( + echo "#ifndef _ASM_X86_CPUFEATURE_H" + echo "#include <asm/cpufeature.h>" + echo "#endif" + echo "" + echo "const char * const x86_cap_flags[NCAPINTS*32] = {" + + # Iterate through any input lines starting with #define X86_FEATURE_ + sed -n -e 's/\t/ /g' -e 's/^ *# *define *X86_FEATURE_//p' $IN | + while read i + do + # Name is everything up to the first whitespace + NAME="$(echo "$i" | sed 's/ .*//')" + + # If the /* comment */ starts with a quote string, grab that. + VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')" + [ -z "$VALUE" ] && VALUE="\"$NAME\"" + [ "$VALUE" == '""' ] && continue + + # Name is uppercase, VALUE is all lowercase + VALUE="$(echo "$VALUE" | tr A-Z a-z)" + + TABCOUNT=$(( ( 5*8 - 14 - $(echo "$NAME" | wc -c) ) / 8 )) + printf "\t[%s]%.*s = %s,\n" \ + "X86_FEATURE_$NAME" "$TABCOUNT" "$TABS" "$VALUE" + done + echo "};" +) > $OUT + +trap - EXIT diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index a7d26d8..8f4be53 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -35,13 +35,6 @@ static bool __init ms_hyperv_platform(void) if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) return false; - /* - * Xen emulates Hyper-V to support enlightened Windows. - * Check to see first if we are on a Xen Hypervisor. - */ - if (xen_cpuid_base()) - return false; - cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); @@ -82,12 +75,6 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); -#if IS_ENABLED(CONFIG_HYPERV) - /* - * Setup the IDT for hypervisor callback. - */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); -#endif } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { @@ -103,6 +90,11 @@ static irq_handler_t vmbus_isr; void hv_register_vmbus_handler(int irq, irq_handler_t handler) { + /* + * Setup the IDT for hypervisor callback. + */ + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); + vmbus_irq = irq; vmbus_isr = handler; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index bf0f01a..1025f3c 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -180,8 +180,9 @@ static void release_pmc_hardware(void) {} static bool check_hw_exists(void) { - u64 val, val_new = ~0; - int i, reg, ret = 0; + u64 val, val_fail, val_new= ~0; + int i, reg, reg_fail, ret = 0; + int bios_fail = 0; /* * Check to see if the BIOS enabled any of the counters, if so @@ -192,8 +193,11 @@ static bool check_hw_exists(void) ret = rdmsrl_safe(reg, &val); if (ret) goto msr_fail; - if (val & ARCH_PERFMON_EVENTSEL_ENABLE) - goto bios_fail; + if (val & ARCH_PERFMON_EVENTSEL_ENABLE) { + bios_fail = 1; + val_fail = val; + reg_fail = reg; + } } if (x86_pmu.num_counters_fixed) { @@ -202,8 +206,11 @@ static bool check_hw_exists(void) if (ret) goto msr_fail; for (i = 0; i < x86_pmu.num_counters_fixed; i++) { - if (val & (0x03 << i*4)) - goto bios_fail; + if (val & (0x03 << i*4)) { + bios_fail = 1; + val_fail = val; + reg_fail = reg; + } } } @@ -221,14 +228,13 @@ static bool check_hw_exists(void) if (ret || val != val_new) goto msr_fail; - return true; - -bios_fail: /* * We still allow the PMU driver to operate: */ - printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n"); - printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val); + if (bios_fail) { + printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n"); + printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg_fail, val_fail); + } return true; @@ -1316,9 +1322,16 @@ static struct attribute_group x86_pmu_format_group = { */ static void __init filter_events(struct attribute **attrs) { + struct device_attribute *d; + struct perf_pmu_events_attr *pmu_attr; int i, j; for (i = 0; attrs[i]; i++) { + d = (struct device_attribute *)attrs[i]; + pmu_attr = container_of(d, struct perf_pmu_events_attr, attr); + /* str trumps id */ + if (pmu_attr->event_str) + continue; if (x86_pmu.event_map(i)) continue; @@ -1330,22 +1343,45 @@ static void __init filter_events(struct attribute **attrs) } } -static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, +/* Merge two pointer arrays */ +static __init struct attribute **merge_attr(struct attribute **a, struct attribute **b) +{ + struct attribute **new; + int j, i; + + for (j = 0; a[j]; j++) + ; + for (i = 0; b[i]; i++) + j++; + j++; + + new = kmalloc(sizeof(struct attribute *) * j, GFP_KERNEL); + if (!new) + return NULL; + + j = 0; + for (i = 0; a[i]; i++) + new[j++] = a[i]; + for (i = 0; b[i]; i++) + new[j++] = b[i]; + new[j] = NULL; + + return new; +} + +ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { struct perf_pmu_events_attr *pmu_attr = \ container_of(attr, struct perf_pmu_events_attr, attr); - u64 config = x86_pmu.event_map(pmu_attr->id); - return x86_pmu.events_sysfs_show(page, config); -} -#define EVENT_VAR(_id) event_attr_##_id -#define EVENT_PTR(_id) &event_attr_##_id.attr.attr + /* string trumps id */ + if (pmu_attr->event_str) + return sprintf(page, "%s", pmu_attr->event_str); -#define EVENT_ATTR(_name, _id) \ - PMU_EVENT_ATTR(_name, EVENT_VAR(_id), PERF_COUNT_HW_##_id, \ - events_sysfs_show) + return x86_pmu.events_sysfs_show(page, config); +} EVENT_ATTR(cpu-cycles, CPU_CYCLES ); EVENT_ATTR(instructions, INSTRUCTIONS ); @@ -1459,16 +1495,27 @@ static int __init init_hw_perf_events(void) unconstrained = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1, - 0, x86_pmu.num_counters, 0); + 0, x86_pmu.num_counters, 0, 0); x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ x86_pmu_format_group.attrs = x86_pmu.format_attrs; + if (x86_pmu.event_attrs) + x86_pmu_events_group.attrs = x86_pmu.event_attrs; + if (!x86_pmu.events_sysfs_show) x86_pmu_events_group.attrs = &empty_attrs; else filter_events(x86_pmu_events_group.attrs); + if (x86_pmu.cpu_events) { + struct attribute **tmp; + + tmp = merge_attr(x86_pmu_events_group.attrs, x86_pmu.cpu_events); + if (!WARN_ON(!tmp)) + x86_pmu_events_group.attrs = tmp; + } + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu.num_counters); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 7f5c75c..ba9aadf 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -46,6 +46,7 @@ enum extra_reg_type { EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ EXTRA_REG_LBR = 2, /* lbr_select */ + EXTRA_REG_LDLAT = 3, /* ld_lat_threshold */ EXTRA_REG_MAX /* number of entries needed */ }; @@ -59,7 +60,13 @@ struct event_constraint { u64 cmask; int weight; int overlap; + int flags; }; +/* + * struct event_constraint flags + */ +#define PERF_X86_EVENT_PEBS_LDLAT 0x1 /* ld+ldlat data address sampling */ +#define PERF_X86_EVENT_PEBS_ST 0x2 /* st data address sampling */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -170,16 +177,17 @@ struct cpu_hw_events { void *kfree_on_online; }; -#define __EVENT_CONSTRAINT(c, n, m, w, o) {\ +#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\ { .idxmsk64 = (n) }, \ .code = (c), \ .cmask = (m), \ .weight = (w), \ .overlap = (o), \ + .flags = f, \ } #define EVENT_CONSTRAINT(c, n, m) \ - __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0) + __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0) /* * The overlap flag marks event constraints with overlapping counter @@ -203,7 +211,7 @@ struct cpu_hw_events { * and its counter masks must be kept at a minimum. */ #define EVENT_CONSTRAINT_OVERLAP(c, n, m) \ - __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1) + __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1, 0) /* * Constraint on the Event code. @@ -231,6 +239,14 @@ struct cpu_hw_events { #define INTEL_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) +#define INTEL_PLD_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT) + +#define INTEL_PST_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST) + #define EVENT_CONSTRAINT_END \ EVENT_CONSTRAINT(0, 0, 0) @@ -260,12 +276,22 @@ struct extra_reg { .msr = (ms), \ .config_mask = (m), \ .valid_mask = (vm), \ - .idx = EXTRA_REG_##i \ + .idx = EXTRA_REG_##i, \ } #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx) +#define INTEL_UEVENT_EXTRA_REG(event, msr, vm, idx) \ + EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT | \ + ARCH_PERFMON_EVENTSEL_UMASK, vm, idx) + +#define INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(c) \ + INTEL_UEVENT_EXTRA_REG(c, \ + MSR_PEBS_LD_LAT_THRESHOLD, \ + 0xffff, \ + LDLAT) + #define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0) union perf_capabilities { @@ -355,8 +381,10 @@ struct x86_pmu { */ int attr_rdpmc; struct attribute **format_attrs; + struct attribute **event_attrs; ssize_t (*events_sysfs_show)(char *page, u64 config); + struct attribute **cpu_events; /* * CPU Hotplug hooks @@ -421,6 +449,23 @@ do { \ #define ERF_NO_HT_SHARING 1 #define ERF_HAS_RSP_1 2 +#define EVENT_VAR(_id) event_attr_##_id +#define EVENT_PTR(_id) &event_attr_##_id.attr.attr + +#define EVENT_ATTR(_name, _id) \ +static struct perf_pmu_events_attr EVENT_VAR(_id) = { \ + .attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \ + .id = PERF_COUNT_HW_##_id, \ + .event_str = NULL, \ +}; + +#define EVENT_ATTR_STR(_name, v, str) \ +static struct perf_pmu_events_attr event_attr_##v = { \ + .attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \ + .id = 0, \ + .event_str = str, \ +}; + extern struct x86_pmu x86_pmu __read_mostly; DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events); @@ -628,6 +673,9 @@ int p6_pmu_init(void); int knc_pmu_init(void); +ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page); + #else /* CONFIG_CPU_SUP_INTEL */ static inline void reserve_ds_buffers(void) diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index dfdab42..7e28d94 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -132,14 +132,11 @@ static u64 amd_pmu_event_map(int hw_event) return amd_perfmon_event_map[hw_event]; } -static struct event_constraint *amd_nb_event_constraint; - /* * Previously calculated offsets */ static unsigned int event_offsets[X86_PMC_IDX_MAX] __read_mostly; static unsigned int count_offsets[X86_PMC_IDX_MAX] __read_mostly; -static unsigned int rdpmc_indexes[X86_PMC_IDX_MAX] __read_mostly; /* * Legacy CPUs: @@ -147,14 +144,10 @@ static unsigned int rdpmc_indexes[X86_PMC_IDX_MAX] __read_mostly; * * CPUs with core performance counter extensions: * 6 counters starting at 0xc0010200 each offset by 2 - * - * CPUs with north bridge performance counter extensions: - * 4 additional counters starting at 0xc0010240 each offset by 2 - * (indexed right above either one of the above core counters) */ static inline int amd_pmu_addr_offset(int index, bool eventsel) { - int offset, first, base; + int offset; if (!index) return index; @@ -167,23 +160,7 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) if (offset) return offset; - if (amd_nb_event_constraint && - test_bit(index, amd_nb_event_constraint->idxmsk)) { - /* - * calculate the offset of NB counters with respect to - * base eventsel or perfctr - */ - - first = find_first_bit(amd_nb_event_constraint->idxmsk, - X86_PMC_IDX_MAX); - - if (eventsel) - base = MSR_F15H_NB_PERF_CTL - x86_pmu.eventsel; - else - base = MSR_F15H_NB_PERF_CTR - x86_pmu.perfctr; - - offset = base + ((index - first) << 1); - } else if (!cpu_has_perfctr_core) + if (!cpu_has_perfctr_core) offset = index; else offset = index << 1; @@ -196,36 +173,6 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) return offset; } -static inline int amd_pmu_rdpmc_index(int index) -{ - int ret, first; - - if (!index) - return index; - - ret = rdpmc_indexes[index]; - - if (ret) - return ret; - - if (amd_nb_event_constraint && - test_bit(index, amd_nb_event_constraint->idxmsk)) { - /* - * according to the mnual, ECX value of the NB counters is - * the index of the NB counter (0, 1, 2 or 3) plus 6 - */ - - first = find_first_bit(amd_nb_event_constraint->idxmsk, - X86_PMC_IDX_MAX); - ret = index - first + 6; - } else - ret = index; - - rdpmc_indexes[index] = ret; - - return ret; -} - static int amd_core_hw_config(struct perf_event *event) { if (event->attr.exclude_host && event->attr.exclude_guest) @@ -245,34 +192,6 @@ static int amd_core_hw_config(struct perf_event *event) } /* - * NB counters do not support the following event select bits: - * Host/Guest only - * Counter mask - * Invert counter mask - * Edge detect - * OS/User mode - */ -static int amd_nb_hw_config(struct perf_event *event) -{ - /* for NB, we only allow system wide counting mode */ - if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) - return -EINVAL; - - if (event->attr.exclude_user || event->attr.exclude_kernel || - event->attr.exclude_host || event->attr.exclude_guest) - return -EINVAL; - - event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR | - ARCH_PERFMON_EVENTSEL_OS); - - if (event->hw.config & ~(AMD64_RAW_EVENT_MASK_NB | - ARCH_PERFMON_EVENTSEL_INT)) - return -EINVAL; - - return 0; -} - -/* * AMD64 events are detected based on their event codes. */ static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc) @@ -285,11 +204,6 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc) return (hwc->config & 0xe0) == 0xe0; } -static inline int amd_is_perfctr_nb_event(struct hw_perf_event *hwc) -{ - return amd_nb_event_constraint && amd_is_nb_event(hwc); -} - static inline int amd_has_nb(struct cpu_hw_events *cpuc) { struct amd_nb *nb = cpuc->amd_nb; @@ -315,9 +229,6 @@ static int amd_pmu_hw_config(struct perf_event *event) if (event->attr.type == PERF_TYPE_RAW) event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK; - if (amd_is_perfctr_nb_event(&event->hw)) - return amd_nb_hw_config(event); - return amd_core_hw_config(event); } @@ -341,19 +252,6 @@ static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc, } } -static void amd_nb_interrupt_hw_config(struct hw_perf_event *hwc) -{ - int core_id = cpu_data(smp_processor_id()).cpu_core_id; - - /* deliver interrupts only to this core */ - if (hwc->config & ARCH_PERFMON_EVENTSEL_INT) { - hwc->config |= AMD64_EVENTSEL_INT_CORE_ENABLE; - hwc->config &= ~AMD64_EVENTSEL_INT_CORE_SEL_MASK; - hwc->config |= (u64)(core_id) << - AMD64_EVENTSEL_INT_CORE_SEL_SHIFT; - } -} - /* * AMD64 NorthBridge events need special treatment because * counter access needs to be synchronized across all cores @@ -441,9 +339,6 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev if (new == -1) return &emptyconstraint; - if (amd_is_perfctr_nb_event(hwc)) - amd_nb_interrupt_hw_config(hwc); - return &nb->event_constraints[new]; } @@ -543,8 +438,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) if (!(amd_has_nb(cpuc) && amd_is_nb_event(&event->hw))) return &unconstrained; - return __amd_get_nb_event_constraints(cpuc, event, - amd_nb_event_constraint); + return __amd_get_nb_event_constraints(cpuc, event, NULL); } static void amd_put_event_constraints(struct cpu_hw_events *cpuc, @@ -643,9 +537,6 @@ static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT_OVERLAP(0, 0x09, static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0); static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0); -static struct event_constraint amd_NBPMC96 = EVENT_CONSTRAINT(0, 0x3C0, 0); -static struct event_constraint amd_NBPMC74 = EVENT_CONSTRAINT(0, 0xF0, 0); - static struct event_constraint * amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event) { @@ -711,8 +602,8 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev return &amd_f15_PMC20; } case AMD_EVENT_NB: - return __amd_get_nb_event_constraints(cpuc, event, - amd_nb_event_constraint); + /* moved to perf_event_amd_uncore.c */ + return &emptyconstraint; default: return &emptyconstraint; } @@ -738,7 +629,6 @@ static __initconst const struct x86_pmu amd_pmu = { .eventsel = MSR_K7_EVNTSEL0, .perfctr = MSR_K7_PERFCTR0, .addr_offset = amd_pmu_addr_offset, - .rdpmc_index = amd_pmu_rdpmc_index, .event_map = amd_pmu_event_map, .max_events = ARRAY_SIZE(amd_perfmon_event_map), .num_counters = AMD64_NUM_COUNTERS, @@ -790,23 +680,6 @@ static int setup_perfctr_core(void) return 0; } -static int setup_perfctr_nb(void) -{ - if (!cpu_has_perfctr_nb) - return -ENODEV; - - x86_pmu.num_counters += AMD64_NUM_COUNTERS_NB; - - if (cpu_has_perfctr_core) - amd_nb_event_constraint = &amd_NBPMC96; - else - amd_nb_event_constraint = &amd_NBPMC74; - - printk(KERN_INFO "perf: AMD northbridge performance counters detected\n"); - - return 0; -} - __init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ @@ -817,7 +690,6 @@ __init int amd_pmu_init(void) setup_event_constraints(); setup_perfctr_core(); - setup_perfctr_nb(); /* Events are common for all AMDs */ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c new file mode 100644 index 0000000..c0c661a --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c @@ -0,0 +1,547 @@ +/* + * Copyright (C) 2013 Advanced Micro Devices, Inc. + * + * Author: Jacob Shin <jacob.shin@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/perf_event.h> +#include <linux/percpu.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/cpu.h> +#include <linux/cpumask.h> + +#include <asm/cpufeature.h> +#include <asm/perf_event.h> +#include <asm/msr.h> + +#define NUM_COUNTERS_NB 4 +#define NUM_COUNTERS_L2 4 +#define MAX_COUNTERS NUM_COUNTERS_NB + +#define RDPMC_BASE_NB 6 +#define RDPMC_BASE_L2 10 + +#define COUNTER_SHIFT 16 + +struct amd_uncore { + int id; + int refcnt; + int cpu; + int num_counters; + int rdpmc_base; + u32 msr_base; + cpumask_t *active_mask; + struct pmu *pmu; + struct perf_event *events[MAX_COUNTERS]; + struct amd_uncore *free_when_cpu_online; +}; + +static struct amd_uncore * __percpu *amd_uncore_nb; +static struct amd_uncore * __percpu *amd_uncore_l2; + +static struct pmu amd_nb_pmu; +static struct pmu amd_l2_pmu; + +static cpumask_t amd_nb_active_mask; +static cpumask_t amd_l2_active_mask; + +static bool is_nb_event(struct perf_event *event) +{ + return event->pmu->type == amd_nb_pmu.type; +} + +static bool is_l2_event(struct perf_event *event) +{ + return event->pmu->type == amd_l2_pmu.type; +} + +static struct amd_uncore *event_to_amd_uncore(struct perf_event *event) +{ + if (is_nb_event(event) && amd_uncore_nb) + return *per_cpu_ptr(amd_uncore_nb, event->cpu); + else if (is_l2_event(event) && amd_uncore_l2) + return *per_cpu_ptr(amd_uncore_l2, event->cpu); + + return NULL; +} + +static void amd_uncore_read(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 prev, new; + s64 delta; + + /* + * since we do not enable counter overflow interrupts, + * we do not have to worry about prev_count changing on us + */ + + prev = local64_read(&hwc->prev_count); + rdpmcl(hwc->event_base_rdpmc, new); + local64_set(&hwc->prev_count, new); + delta = (new << COUNTER_SHIFT) - (prev << COUNTER_SHIFT); + delta >>= COUNTER_SHIFT; + local64_add(delta, &event->count); +} + +static void amd_uncore_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + + if (flags & PERF_EF_RELOAD) + wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count)); + + hwc->state = 0; + wrmsrl(hwc->config_base, (hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE)); + perf_event_update_userpage(event); +} + +static void amd_uncore_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + + wrmsrl(hwc->config_base, hwc->config); + hwc->state |= PERF_HES_STOPPED; + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + amd_uncore_read(event); + hwc->state |= PERF_HES_UPTODATE; + } +} + +static int amd_uncore_add(struct perf_event *event, int flags) +{ + int i; + struct amd_uncore *uncore = event_to_amd_uncore(event); + struct hw_perf_event *hwc = &event->hw; + + /* are we already assigned? */ + if (hwc->idx != -1 && uncore->events[hwc->idx] == event) + goto out; + + for (i = 0; i < uncore->num_counters; i++) { + if (uncore->events[i] == event) { + hwc->idx = i; + goto out; + } + } + + /* if not, take the first available counter */ + hwc->idx = -1; + for (i = 0; i < uncore->num_counters; i++) { + if (cmpxchg(&uncore->events[i], NULL, event) == NULL) { + hwc->idx = i; + break; + } + } + +out: + if (hwc->idx == -1) + return -EBUSY; + + hwc->config_base = uncore->msr_base + (2 * hwc->idx); + hwc->event_base = uncore->msr_base + 1 + (2 * hwc->idx); + hwc->event_base_rdpmc = uncore->rdpmc_base + hwc->idx; + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + if (flags & PERF_EF_START) + amd_uncore_start(event, PERF_EF_RELOAD); + + return 0; +} + +static void amd_uncore_del(struct perf_event *event, int flags) +{ + int i; + struct amd_uncore *uncore = event_to_amd_uncore(event); + struct hw_perf_event *hwc = &event->hw; + + amd_uncore_stop(event, PERF_EF_UPDATE); + + for (i = 0; i < uncore->num_counters; i++) { + if (cmpxchg(&uncore->events[i], event, NULL) == event) + break; + } + + hwc->idx = -1; +} + +static int amd_uncore_event_init(struct perf_event *event) +{ + struct amd_uncore *uncore; + struct hw_perf_event *hwc = &event->hw; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* + * NB and L2 counters (MSRs) are shared across all cores that share the + * same NB / L2 cache. Interrupts can be directed to a single target + * core, however, event counts generated by processes running on other + * cores cannot be masked out. So we do not support sampling and + * per-thread events. + */ + if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) + return -EINVAL; + + /* NB and L2 counters do not have usr/os/guest/host bits */ + if (event->attr.exclude_user || event->attr.exclude_kernel || + event->attr.exclude_host || event->attr.exclude_guest) + return -EINVAL; + + /* and we do not enable counter overflow interrupts */ + hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB; + hwc->idx = -1; + + if (event->cpu < 0) + return -EINVAL; + + uncore = event_to_amd_uncore(event); + if (!uncore) + return -ENODEV; + + /* + * since request can come in to any of the shared cores, we will remap + * to a single common cpu. + */ + event->cpu = uncore->cpu; + + return 0; +} + +static ssize_t amd_uncore_attr_show_cpumask(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int n; + cpumask_t *active_mask; + struct pmu *pmu = dev_get_drvdata(dev); + + if (pmu->type == amd_nb_pmu.type) + active_mask = &amd_nb_active_mask; + else if (pmu->type == amd_l2_pmu.type) + active_mask = &amd_l2_active_mask; + else + return 0; + + n = cpulist_scnprintf(buf, PAGE_SIZE - 2, active_mask); + buf[n++] = '\n'; + buf[n] = '\0'; + return n; +} +static DEVICE_ATTR(cpumask, S_IRUGO, amd_uncore_attr_show_cpumask, NULL); + +static struct attribute *amd_uncore_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group amd_uncore_attr_group = { + .attrs = amd_uncore_attrs, +}; + +PMU_FORMAT_ATTR(event, "config:0-7,32-35"); +PMU_FORMAT_ATTR(umask, "config:8-15"); + +static struct attribute *amd_uncore_format_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + NULL, +}; + +static struct attribute_group amd_uncore_format_group = { + .name = "format", + .attrs = amd_uncore_format_attr, +}; + +static const struct attribute_group *amd_uncore_attr_groups[] = { + &amd_uncore_attr_group, + &amd_uncore_format_group, + NULL, +}; + +static struct pmu amd_nb_pmu = { + .attr_groups = amd_uncore_attr_groups, + .name = "amd_nb", + .event_init = amd_uncore_event_init, + .add = amd_uncore_add, + .del = amd_uncore_del, + .start = amd_uncore_start, + .stop = amd_uncore_stop, + .read = amd_uncore_read, +}; + +static struct pmu amd_l2_pmu = { + .attr_groups = amd_uncore_attr_groups, + .name = "amd_l2", + .event_init = amd_uncore_event_init, + .add = amd_uncore_add, + .del = amd_uncore_del, + .start = amd_uncore_start, + .stop = amd_uncore_stop, + .read = amd_uncore_read, +}; + +static struct amd_uncore * __cpuinit amd_uncore_alloc(unsigned int cpu) +{ + return kzalloc_node(sizeof(struct amd_uncore), GFP_KERNEL, + cpu_to_node(cpu)); +} + +static void __cpuinit amd_uncore_cpu_up_prepare(unsigned int cpu) +{ + struct amd_uncore *uncore; + + if (amd_uncore_nb) { + uncore = amd_uncore_alloc(cpu); + uncore->cpu = cpu; + uncore->num_counters = NUM_COUNTERS_NB; + uncore->rdpmc_base = RDPMC_BASE_NB; + uncore->msr_base = MSR_F15H_NB_PERF_CTL; + uncore->active_mask = &amd_nb_active_mask; + uncore->pmu = &amd_nb_pmu; + *per_cpu_ptr(amd_uncore_nb, cpu) = uncore; + } + + if (amd_uncore_l2) { + uncore = amd_uncore_alloc(cpu); + uncore->cpu = cpu; + uncore->num_counters = NUM_COUNTERS_L2; + uncore->rdpmc_base = RDPMC_BASE_L2; + uncore->msr_base = MSR_F16H_L2I_PERF_CTL; + uncore->active_mask = &amd_l2_active_mask; + uncore->pmu = &amd_l2_pmu; + *per_cpu_ptr(amd_uncore_l2, cpu) = uncore; + } +} + +static struct amd_uncore * +__cpuinit amd_uncore_find_online_sibling(struct amd_uncore *this, + struct amd_uncore * __percpu *uncores) +{ + unsigned int cpu; + struct amd_uncore *that; + + for_each_online_cpu(cpu) { + that = *per_cpu_ptr(uncores, cpu); + + if (!that) + continue; + + if (this == that) + continue; + + if (this->id == that->id) { + that->free_when_cpu_online = this; + this = that; + break; + } + } + + this->refcnt++; + return this; +} + +static void __cpuinit amd_uncore_cpu_starting(unsigned int cpu) +{ + unsigned int eax, ebx, ecx, edx; + struct amd_uncore *uncore; + + if (amd_uncore_nb) { + uncore = *per_cpu_ptr(amd_uncore_nb, cpu); + cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); + uncore->id = ecx & 0xff; + + uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_nb); + *per_cpu_ptr(amd_uncore_nb, cpu) = uncore; + } + + if (amd_uncore_l2) { + unsigned int apicid = cpu_data(cpu).apicid; + unsigned int nshared; + + uncore = *per_cpu_ptr(amd_uncore_l2, cpu); + cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx); + nshared = ((eax >> 14) & 0xfff) + 1; + uncore->id = apicid - (apicid % nshared); + + uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2); + *per_cpu_ptr(amd_uncore_l2, cpu) = uncore; + } +} + +static void __cpuinit uncore_online(unsigned int cpu, + struct amd_uncore * __percpu *uncores) +{ + struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu); + + kfree(uncore->free_when_cpu_online); + uncore->free_when_cpu_online = NULL; + + if (cpu == uncore->cpu) + cpumask_set_cpu(cpu, uncore->active_mask); +} + +static void __cpuinit amd_uncore_cpu_online(unsigned int cpu) +{ + if (amd_uncore_nb) + uncore_online(cpu, amd_uncore_nb); + + if (amd_uncore_l2) + uncore_online(cpu, amd_uncore_l2); +} + +static void __cpuinit uncore_down_prepare(unsigned int cpu, + struct amd_uncore * __percpu *uncores) +{ + unsigned int i; + struct amd_uncore *this = *per_cpu_ptr(uncores, cpu); + + if (this->cpu != cpu) + return; + + /* this cpu is going down, migrate to a shared sibling if possible */ + for_each_online_cpu(i) { + struct amd_uncore *that = *per_cpu_ptr(uncores, i); + + if (cpu == i) + continue; + + if (this == that) { + perf_pmu_migrate_context(this->pmu, cpu, i); + cpumask_clear_cpu(cpu, that->active_mask); + cpumask_set_cpu(i, that->active_mask); + that->cpu = i; + break; + } + } +} + +static void __cpuinit amd_uncore_cpu_down_prepare(unsigned int cpu) +{ + if (amd_uncore_nb) + uncore_down_prepare(cpu, amd_uncore_nb); + + if (amd_uncore_l2) + uncore_down_prepare(cpu, amd_uncore_l2); +} + +static void __cpuinit uncore_dead(unsigned int cpu, + struct amd_uncore * __percpu *uncores) +{ + struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu); + + if (cpu == uncore->cpu) + cpumask_clear_cpu(cpu, uncore->active_mask); + + if (!--uncore->refcnt) + kfree(uncore); + *per_cpu_ptr(amd_uncore_nb, cpu) = NULL; +} + +static void __cpuinit amd_uncore_cpu_dead(unsigned int cpu) +{ + if (amd_uncore_nb) + uncore_dead(cpu, amd_uncore_nb); + + if (amd_uncore_l2) + uncore_dead(cpu, amd_uncore_l2); +} + +static int __cpuinit +amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action, + void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + amd_uncore_cpu_up_prepare(cpu); + break; + + case CPU_STARTING: + amd_uncore_cpu_starting(cpu); + break; + + case CPU_ONLINE: + amd_uncore_cpu_online(cpu); + break; + + case CPU_DOWN_PREPARE: + amd_uncore_cpu_down_prepare(cpu); + break; + + case CPU_UP_CANCELED: + case CPU_DEAD: + amd_uncore_cpu_dead(cpu); + break; + + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block amd_uncore_cpu_notifier_block __cpuinitdata = { + .notifier_call = amd_uncore_cpu_notifier, + .priority = CPU_PRI_PERF + 1, +}; + +static void __init init_cpu_already_online(void *dummy) +{ + unsigned int cpu = smp_processor_id(); + + amd_uncore_cpu_starting(cpu); + amd_uncore_cpu_online(cpu); +} + +static int __init amd_uncore_init(void) +{ + unsigned int cpu; + int ret = -ENODEV; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return -ENODEV; + + if (!cpu_has_topoext) + return -ENODEV; + + if (cpu_has_perfctr_nb) { + amd_uncore_nb = alloc_percpu(struct amd_uncore *); + perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1); + + printk(KERN_INFO "perf: AMD NB counters detected\n"); + ret = 0; + } + + if (cpu_has_perfctr_l2) { + amd_uncore_l2 = alloc_percpu(struct amd_uncore *); + perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1); + + printk(KERN_INFO "perf: AMD L2I counters detected\n"); + ret = 0; + } + + if (ret) + return -ENODEV; + + get_online_cpus(); + /* init cpus already online before registering for hotplug notifier */ + for_each_online_cpu(cpu) { + amd_uncore_cpu_up_prepare(cpu); + smp_call_function_single(cpu, init_cpu_already_online, NULL, 1); + } + + register_cpu_notifier(&amd_uncore_cpu_notifier_block); + put_online_cpus(); + + return 0; +} +device_initcall(amd_uncore_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index dab7580..ffd6050 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -81,6 +81,7 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly = static struct extra_reg intel_nehalem_extra_regs[] __read_mostly = { INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b), EVENT_EXTRA_END }; @@ -108,6 +109,8 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ + INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ + INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ EVENT_CONSTRAINT_END }; @@ -136,6 +139,7 @@ static struct extra_reg intel_westmere_extra_regs[] __read_mostly = { INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b), EVENT_EXTRA_END }; @@ -153,11 +157,34 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly = }; static struct extra_reg intel_snb_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + EVENT_EXTRA_END +}; + +static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), EVENT_EXTRA_END }; +EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); +EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); +EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); + +struct attribute *nhm_events_attrs[] = { + EVENT_PTR(mem_ld_nhm), + NULL, +}; + +struct attribute *snb_events_attrs[] = { + EVENT_PTR(mem_ld_snb), + EVENT_PTR(mem_st_snb), + NULL, +}; + static u64 intel_pmu_event_map(int hw_event) { return intel_perfmon_event_map[hw_event]; @@ -1392,8 +1419,11 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) if (x86_pmu.event_constraints) { for_each_event_constraint(c, x86_pmu.event_constraints) { - if ((event->hw.config & c->cmask) == c->code) + if ((event->hw.config & c->cmask) == c->code) { + /* hw.flags zeroed at initialization */ + event->hw.flags |= c->flags; return c; + } } } @@ -1438,6 +1468,7 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc, static void intel_put_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { + event->hw.flags = 0; intel_put_shared_regs_event_constraints(cpuc, event); } @@ -1761,6 +1792,8 @@ static void intel_pmu_flush_branch_stack(void) PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); +PMU_FORMAT_ATTR(ldlat, "config1:0-15"); + static struct attribute *intel_arch3_formats_attr[] = { &format_attr_event.attr, &format_attr_umask.attr, @@ -1771,6 +1804,7 @@ static struct attribute *intel_arch3_formats_attr[] = { &format_attr_cmask.attr, &format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */ + &format_attr_ldlat.attr, /* PEBS load latency */ NULL, }; @@ -2031,6 +2065,8 @@ __init int intel_pmu_init(void) x86_pmu.enable_all = intel_pmu_nhm_enable_all; x86_pmu.extra_regs = intel_nehalem_extra_regs; + x86_pmu.cpu_events = nhm_events_attrs; + /* UOPS_ISSUED.STALLED_CYCLES */ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); @@ -2074,6 +2110,8 @@ __init int intel_pmu_init(void) x86_pmu.extra_regs = intel_westmere_extra_regs; x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.cpu_events = nhm_events_attrs; + /* UOPS_ISSUED.STALLED_CYCLES */ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); @@ -2097,11 +2135,16 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_snb_event_constraints; x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - x86_pmu.extra_regs = intel_snb_extra_regs; + if (boot_cpu_data.x86_model == 45) + x86_pmu.extra_regs = intel_snbep_extra_regs; + else + x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; x86_pmu.er_flags |= ERF_NO_HT_SHARING; + x86_pmu.cpu_events = snb_events_attrs; + /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); @@ -2123,11 +2166,16 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_ivb_event_constraints; x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - x86_pmu.extra_regs = intel_snb_extra_regs; + if (boot_cpu_data.x86_model == 62) + x86_pmu.extra_regs = intel_snbep_extra_regs; + else + x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; x86_pmu.er_flags |= ERF_NO_HT_SHARING; + x86_pmu.cpu_events = snb_events_attrs; + /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 26830f3..60250f6 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -24,6 +24,130 @@ struct pebs_record_32 { */ +union intel_x86_pebs_dse { + u64 val; + struct { + unsigned int ld_dse:4; + unsigned int ld_stlb_miss:1; + unsigned int ld_locked:1; + unsigned int ld_reserved:26; + }; + struct { + unsigned int st_l1d_hit:1; + unsigned int st_reserved1:3; + unsigned int st_stlb_miss:1; + unsigned int st_locked:1; + unsigned int st_reserved2:26; + }; +}; + + +/* + * Map PEBS Load Latency Data Source encodings to generic + * memory data source information + */ +#define P(a, b) PERF_MEM_S(a, b) +#define OP_LH (P(OP, LOAD) | P(LVL, HIT)) +#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) + +static const u64 pebs_data_source[] = { + P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ + OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */ + OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ + OP_LH | P(LVL, L2) | P(SNOOP, NONE), /* 0x03: L2 hit */ + OP_LH | P(LVL, L3) | P(SNOOP, NONE), /* 0x04: L3 hit */ + OP_LH | P(LVL, L3) | P(SNOOP, MISS), /* 0x05: L3 hit, snoop miss */ + OP_LH | P(LVL, L3) | P(SNOOP, HIT), /* 0x06: L3 hit, snoop hit */ + OP_LH | P(LVL, L3) | P(SNOOP, HITM), /* 0x07: L3 hit, snoop hitm */ + OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HIT), /* 0x08: L3 miss snoop hit */ + OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/ + OP_LH | P(LVL, LOC_RAM) | P(SNOOP, HIT), /* 0x0a: L3 miss, shared */ + OP_LH | P(LVL, REM_RAM1) | P(SNOOP, HIT), /* 0x0b: L3 miss, shared */ + OP_LH | P(LVL, LOC_RAM) | SNOOP_NONE_MISS,/* 0x0c: L3 miss, excl */ + OP_LH | P(LVL, REM_RAM1) | SNOOP_NONE_MISS,/* 0x0d: L3 miss, excl */ + OP_LH | P(LVL, IO) | P(SNOOP, NONE), /* 0x0e: I/O */ + OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */ +}; + +static u64 precise_store_data(u64 status) +{ + union intel_x86_pebs_dse dse; + u64 val = P(OP, STORE) | P(SNOOP, NA) | P(LVL, L1) | P(TLB, L2); + + dse.val = status; + + /* + * bit 4: TLB access + * 1 = stored missed 2nd level TLB + * + * so it either hit the walker or the OS + * otherwise hit 2nd level TLB + */ + if (dse.st_stlb_miss) + val |= P(TLB, MISS); + else + val |= P(TLB, HIT); + + /* + * bit 0: hit L1 data cache + * if not set, then all we know is that + * it missed L1D + */ + if (dse.st_l1d_hit) + val |= P(LVL, HIT); + else + val |= P(LVL, MISS); + + /* + * bit 5: Locked prefix + */ + if (dse.st_locked) + val |= P(LOCK, LOCKED); + + return val; +} + +static u64 load_latency_data(u64 status) +{ + union intel_x86_pebs_dse dse; + u64 val; + int model = boot_cpu_data.x86_model; + int fam = boot_cpu_data.x86; + + dse.val = status; + + /* + * use the mapping table for bit 0-3 + */ + val = pebs_data_source[dse.ld_dse]; + + /* + * Nehalem models do not support TLB, Lock infos + */ + if (fam == 0x6 && (model == 26 || model == 30 + || model == 31 || model == 46)) { + val |= P(TLB, NA) | P(LOCK, NA); + return val; + } + /* + * bit 4: TLB access + * 0 = did not miss 2nd level TLB + * 1 = missed 2nd level TLB + */ + if (dse.ld_stlb_miss) + val |= P(TLB, MISS) | P(TLB, L2); + else + val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2); + + /* + * bit 5: locked prefix + */ + if (dse.ld_locked) + val |= P(LOCK, LOCKED); + + return val; +} + struct pebs_record_core { u64 flags, ip; u64 ax, bx, cx, dx; @@ -365,7 +489,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { }; struct event_constraint intel_nehalem_pebs_event_constraints[] = { - INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */ @@ -380,7 +504,7 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = { }; struct event_constraint intel_westmere_pebs_event_constraints[] = { - INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */ @@ -400,7 +524,8 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */ + INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ + INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -414,7 +539,8 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */ + INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ + INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -431,8 +557,10 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) if (x86_pmu.pebs_constraints) { for_each_event_constraint(c, x86_pmu.pebs_constraints) { - if ((event->hw.config & c->cmask) == c->code) + if ((event->hw.config & c->cmask) == c->code) { + event->hw.flags |= c->flags; return c; + } } } @@ -447,6 +575,11 @@ void intel_pmu_pebs_enable(struct perf_event *event) hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; cpuc->pebs_enabled |= 1ULL << hwc->idx; + + if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) + cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32); + else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) + cpuc->pebs_enabled |= 1ULL << 63; } void intel_pmu_pebs_disable(struct perf_event *event) @@ -559,20 +692,51 @@ static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *__pebs) { /* - * We cast to pebs_record_core since that is a subset of - * both formats and we don't use the other fields in this - * routine. + * We cast to pebs_record_nhm to get the load latency data + * if extra_reg MSR_PEBS_LD_LAT_THRESHOLD used */ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct pebs_record_core *pebs = __pebs; + struct pebs_record_nhm *pebs = __pebs; struct perf_sample_data data; struct pt_regs regs; + u64 sample_type; + int fll, fst; if (!intel_pmu_save_and_restart(event)) return; + fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT; + fst = event->hw.flags & PERF_X86_EVENT_PEBS_ST; + perf_sample_data_init(&data, 0, event->hw.last_period); + data.period = event->hw.last_period; + sample_type = event->attr.sample_type; + + /* + * if PEBS-LL or PreciseStore + */ + if (fll || fst) { + if (sample_type & PERF_SAMPLE_ADDR) + data.addr = pebs->dla; + + /* + * Use latency for weight (only avail with PEBS-LL) + */ + if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) + data.weight = pebs->lat; + + /* + * data.data_src encodes the data source + */ + if (sample_type & PERF_SAMPLE_DATA_SRC) { + if (fll) + data.data_src.val = load_latency_data(pebs->dse); + else + data.data_src.val = precise_store_data(pebs->dse); + } + } + /* * We use the interrupt regs as a base because the PEBS record * does not contain a full regs set, specifically it seems to diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index b43200d..d0f9e5a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -17,6 +17,9 @@ static struct event_constraint constraint_fixed = static struct event_constraint constraint_empty = EVENT_CONSTRAINT(0, 0, 0); +#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ + ((1ULL << (n)) - 1))) + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); @@ -31,9 +34,13 @@ DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7"); DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15"); DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23"); @@ -110,6 +117,21 @@ static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_even reg1->alloc = 0; } +static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) +{ + struct intel_uncore_extra_reg *er; + unsigned long flags; + u64 config; + + er = &box->shared_regs[idx]; + + raw_spin_lock_irqsave(&er->lock, flags); + config = er->config; + raw_spin_unlock_irqrestore(&er->lock, flags); + + return config; +} + /* Sandy Bridge-EP uncore support */ static struct intel_uncore_type snbep_uncore_cbox; static struct intel_uncore_type snbep_uncore_pcu; @@ -205,7 +227,7 @@ static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct p struct hw_perf_event_extra *reg1 = &hwc->extra_reg; if (reg1->idx != EXTRA_REG_NONE) - wrmsrl(reg1->reg, reg1->config); + wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0)); wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); } @@ -226,29 +248,6 @@ static void snbep_uncore_msr_init_box(struct intel_uncore_box *box) wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT); } -static int snbep_uncore_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - - if (box->pmu->type == &snbep_uncore_cbox) { - reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + - SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; - reg1->config = event->attr.config1 & - SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK; - } else { - if (box->pmu->type == &snbep_uncore_pcu) { - reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; - reg1->config = event->attr.config1 & SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK; - } else { - return 0; - } - } - reg1->idx = 0; - - return 0; -} - static struct attribute *snbep_uncore_formats_attr[] = { &format_attr_event.attr, &format_attr_umask.attr, @@ -345,16 +344,16 @@ static struct attribute_group snbep_uncore_qpi_format_group = { .attrs = snbep_uncore_qpi_formats_attr, }; +#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT() \ + .init_box = snbep_uncore_msr_init_box, \ + .disable_box = snbep_uncore_msr_disable_box, \ + .enable_box = snbep_uncore_msr_enable_box, \ + .disable_event = snbep_uncore_msr_disable_event, \ + .enable_event = snbep_uncore_msr_enable_event, \ + .read_counter = uncore_msr_read_counter + static struct intel_uncore_ops snbep_uncore_msr_ops = { - .init_box = snbep_uncore_msr_init_box, - .disable_box = snbep_uncore_msr_disable_box, - .enable_box = snbep_uncore_msr_enable_box, - .disable_event = snbep_uncore_msr_disable_event, - .enable_event = snbep_uncore_msr_enable_event, - .read_counter = uncore_msr_read_counter, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, - .hw_config = snbep_uncore_hw_config, + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), }; static struct intel_uncore_ops snbep_uncore_pci_ops = { @@ -372,6 +371,7 @@ static struct event_constraint snbep_uncore_cbox_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x04, 0x3), UNCORE_EVENT_CONSTRAINT(0x05, 0x3), UNCORE_EVENT_CONSTRAINT(0x07, 0x3), + UNCORE_EVENT_CONSTRAINT(0x09, 0x3), UNCORE_EVENT_CONSTRAINT(0x11, 0x1), UNCORE_EVENT_CONSTRAINT(0x12, 0x3), UNCORE_EVENT_CONSTRAINT(0x13, 0x3), @@ -421,6 +421,14 @@ static struct event_constraint snbep_uncore_r3qpi_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x24, 0x3), UNCORE_EVENT_CONSTRAINT(0x25, 0x3), UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2a, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2b, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), UNCORE_EVENT_CONSTRAINT(0x30, 0x3), UNCORE_EVENT_CONSTRAINT(0x31, 0x3), UNCORE_EVENT_CONSTRAINT(0x32, 0x3), @@ -428,6 +436,8 @@ static struct event_constraint snbep_uncore_r3qpi_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x34, 0x3), UNCORE_EVENT_CONSTRAINT(0x36, 0x3), UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), EVENT_CONSTRAINT_END }; @@ -446,6 +456,145 @@ static struct intel_uncore_type snbep_uncore_ubox = { .format_group = &snbep_uncore_ubox_format_group, }; +static struct extra_reg snbep_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2), + EVENT_EXTRA_END +}; + +static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + int i; + + if (uncore_box_is_fake(box)) + return; + + for (i = 0; i < 5; i++) { + if (reg1->alloc & (0x1 << i)) + atomic_sub(1 << (i * 6), &er->ref); + } + reg1->alloc = 0; +} + +static struct event_constraint * +__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event, + u64 (*cbox_filter_mask)(int fields)) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + int i, alloc = 0; + unsigned long flags; + u64 mask; + + if (reg1->idx == EXTRA_REG_NONE) + return NULL; + + raw_spin_lock_irqsave(&er->lock, flags); + for (i = 0; i < 5; i++) { + if (!(reg1->idx & (0x1 << i))) + continue; + if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) + continue; + + mask = cbox_filter_mask(0x1 << i); + if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) || + !((reg1->config ^ er->config) & mask)) { + atomic_add(1 << (i * 6), &er->ref); + er->config &= ~mask; + er->config |= reg1->config & mask; + alloc |= (0x1 << i); + } else { + break; + } + } + raw_spin_unlock_irqrestore(&er->lock, flags); + if (i < 5) + goto fail; + + if (!uncore_box_is_fake(box)) + reg1->alloc |= alloc; + + return 0; +fail: + for (; i >= 0; i--) { + if (alloc & (0x1 << i)) + atomic_sub(1 << (i * 6), &er->ref); + } + return &constraint_empty; +} + +static u64 snbep_cbox_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x4) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC; + + return mask; +} + +static struct event_constraint * +snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask); +} + +static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + + SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static struct intel_uncore_ops snbep_uncore_cbox_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_cbox_hw_config, + .get_constraint = snbep_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + static struct intel_uncore_type snbep_uncore_cbox = { .name = "cbox", .num_counters = 4, @@ -458,10 +607,104 @@ static struct intel_uncore_type snbep_uncore_cbox = { .msr_offset = SNBEP_CBO_MSR_OFFSET, .num_shared_regs = 1, .constraints = snbep_uncore_cbox_constraints, - .ops = &snbep_uncore_msr_ops, + .ops = &snbep_uncore_cbox_ops, .format_group = &snbep_uncore_cbox_format_group, }; +static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + u64 config = reg1->config; + + if (new_idx > reg1->idx) + config <<= 8 * (new_idx - reg1->idx); + else + config >>= 8 * (reg1->idx - new_idx); + + if (modify) { + hwc->config += new_idx - reg1->idx; + reg1->config = config; + reg1->idx = new_idx; + } + return config; +} + +static struct event_constraint * +snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + unsigned long flags; + int idx = reg1->idx; + u64 mask, config1 = reg1->config; + bool ok = false; + + if (reg1->idx == EXTRA_REG_NONE || + (!uncore_box_is_fake(box) && reg1->alloc)) + return NULL; +again: + mask = 0xff << (idx * 8); + raw_spin_lock_irqsave(&er->lock, flags); + if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) || + !((config1 ^ er->config) & mask)) { + atomic_add(1 << (idx * 8), &er->ref); + er->config &= ~mask; + er->config |= config1 & mask; + ok = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + if (!ok) { + idx = (idx + 1) % 4; + if (idx != reg1->idx) { + config1 = snbep_pcu_alter_er(event, idx, false); + goto again; + } + return &constraint_empty; + } + + if (!uncore_box_is_fake(box)) { + if (idx != reg1->idx) + snbep_pcu_alter_er(event, idx, true); + reg1->alloc = 1; + } + return NULL; +} + +static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + + if (uncore_box_is_fake(box) || !reg1->alloc) + return; + + atomic_sub(1 << (reg1->idx * 8), &er->ref); + reg1->alloc = 0; +} + +static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK; + + if (ev_sel >= 0xb && ev_sel <= 0xe) { + reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; + reg1->idx = ev_sel - 0xb; + reg1->config = event->attr.config1 & (0xff << reg1->idx); + } + return 0; +} + +static struct intel_uncore_ops snbep_uncore_pcu_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + static struct intel_uncore_type snbep_uncore_pcu = { .name = "pcu", .num_counters = 4, @@ -472,7 +715,7 @@ static struct intel_uncore_type snbep_uncore_pcu = { .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, .num_shared_regs = 1, - .ops = &snbep_uncore_msr_ops, + .ops = &snbep_uncore_pcu_ops, .format_group = &snbep_uncore_pcu_format_group, }; @@ -544,55 +787,63 @@ static struct intel_uncore_type snbep_uncore_r3qpi = { SNBEP_UNCORE_PCI_COMMON_INIT(), }; +enum { + SNBEP_PCI_UNCORE_HA, + SNBEP_PCI_UNCORE_IMC, + SNBEP_PCI_UNCORE_QPI, + SNBEP_PCI_UNCORE_R2PCIE, + SNBEP_PCI_UNCORE_R3QPI, +}; + static struct intel_uncore_type *snbep_pci_uncores[] = { - &snbep_uncore_ha, - &snbep_uncore_imc, - &snbep_uncore_qpi, - &snbep_uncore_r2pcie, - &snbep_uncore_r3qpi, + [SNBEP_PCI_UNCORE_HA] = &snbep_uncore_ha, + [SNBEP_PCI_UNCORE_IMC] = &snbep_uncore_imc, + [SNBEP_PCI_UNCORE_QPI] = &snbep_uncore_qpi, + [SNBEP_PCI_UNCORE_R2PCIE] = &snbep_uncore_r2pcie, + [SNBEP_PCI_UNCORE_R3QPI] = &snbep_uncore_r3qpi, NULL, }; static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = { { /* Home Agent */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), - .driver_data = (unsigned long)&snbep_uncore_ha, + .driver_data = SNBEP_PCI_UNCORE_HA, }, { /* MC Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), - .driver_data = (unsigned long)&snbep_uncore_imc, + .driver_data = SNBEP_PCI_UNCORE_IMC, }, { /* MC Channel 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), - .driver_data = (unsigned long)&snbep_uncore_imc, + .driver_data = SNBEP_PCI_UNCORE_IMC, }, { /* MC Channel 2 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), - .driver_data = (unsigned long)&snbep_uncore_imc, + .driver_data = SNBEP_PCI_UNCORE_IMC, }, { /* MC Channel 3 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), - .driver_data = (unsigned long)&snbep_uncore_imc, + .driver_data = SNBEP_PCI_UNCORE_IMC, }, { /* QPI Port 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), - .driver_data = (unsigned long)&snbep_uncore_qpi, + .driver_data = SNBEP_PCI_UNCORE_QPI, }, { /* QPI Port 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), - .driver_data = (unsigned long)&snbep_uncore_qpi, + .driver_data = SNBEP_PCI_UNCORE_QPI, }, - { /* P2PCIe */ + { /* R2PCIe */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), - .driver_data = (unsigned long)&snbep_uncore_r2pcie, + .driver_data = SNBEP_PCI_UNCORE_R2PCIE, }, { /* R3QPI Link 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), - .driver_data = (unsigned long)&snbep_uncore_r3qpi, + .driver_data = SNBEP_PCI_UNCORE_R3QPI, }, { /* R3QPI Link 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), - .driver_data = (unsigned long)&snbep_uncore_r3qpi, + .driver_data = SNBEP_PCI_UNCORE_R3QPI, }, { /* end: all zeroes */ } }; @@ -605,7 +856,7 @@ static struct pci_driver snbep_uncore_pci_driver = { /* * build pci bus to socket mapping */ -static int snbep_pci2phy_map_init(void) +static int snbep_pci2phy_map_init(int devid) { struct pci_dev *ubox_dev = NULL; int i, bus, nodeid; @@ -614,9 +865,7 @@ static int snbep_pci2phy_map_init(void) while (1) { /* find the UBOX device */ - ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, - PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX, - ubox_dev); + ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev); if (!ubox_dev) break; bus = ubox_dev->bus->number; @@ -639,7 +888,7 @@ static int snbep_pci2phy_map_init(void) break; } } - }; + } if (ubox_dev) pci_dev_put(ubox_dev); @@ -648,6 +897,440 @@ static int snbep_pci2phy_map_init(void) } /* end of Sandy Bridge-EP uncore support */ +/* IvyTown uncore support */ +static void ivt_uncore_msr_init_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + if (msr) + wrmsrl(msr, IVT_PMON_BOX_CTL_INT); +} + +static void ivt_uncore_pci_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + + pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVT_PMON_BOX_CTL_INT); +} + +#define IVT_UNCORE_MSR_OPS_COMMON_INIT() \ + .init_box = ivt_uncore_msr_init_box, \ + .disable_box = snbep_uncore_msr_disable_box, \ + .enable_box = snbep_uncore_msr_enable_box, \ + .disable_event = snbep_uncore_msr_disable_event, \ + .enable_event = snbep_uncore_msr_enable_event, \ + .read_counter = uncore_msr_read_counter + +static struct intel_uncore_ops ivt_uncore_msr_ops = { + IVT_UNCORE_MSR_OPS_COMMON_INIT(), +}; + +static struct intel_uncore_ops ivt_uncore_pci_ops = { + .init_box = ivt_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_uncore_pci_enable_event, + .read_counter = snbep_uncore_pci_read_counter, +}; + +#define IVT_UNCORE_PCI_COMMON_INIT() \ + .perf_ctr = SNBEP_PCI_PMON_CTR0, \ + .event_ctl = SNBEP_PCI_PMON_CTL0, \ + .event_mask = IVT_PMON_RAW_EVENT_MASK, \ + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ + .ops = &ivt_uncore_pci_ops, \ + .format_group = &ivt_uncore_format_group + +static struct attribute *ivt_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute *ivt_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute *ivt_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid.attr, + &format_attr_filter_link.attr, + &format_attr_filter_state2.attr, + &format_attr_filter_nid2.attr, + &format_attr_filter_opc2.attr, + NULL, +}; + +static struct attribute *ivt_uncore_pcu_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_thresh5.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge.attr, + &format_attr_filter_band0.attr, + &format_attr_filter_band1.attr, + &format_attr_filter_band2.attr, + &format_attr_filter_band3.attr, + NULL, +}; + +static struct attribute *ivt_uncore_qpi_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group ivt_uncore_format_group = { + .name = "format", + .attrs = ivt_uncore_formats_attr, +}; + +static struct attribute_group ivt_uncore_ubox_format_group = { + .name = "format", + .attrs = ivt_uncore_ubox_formats_attr, +}; + +static struct attribute_group ivt_uncore_cbox_format_group = { + .name = "format", + .attrs = ivt_uncore_cbox_formats_attr, +}; + +static struct attribute_group ivt_uncore_pcu_format_group = { + .name = "format", + .attrs = ivt_uncore_pcu_formats_attr, +}; + +static struct attribute_group ivt_uncore_qpi_format_group = { + .name = "format", + .attrs = ivt_uncore_qpi_formats_attr, +}; + +static struct intel_uncore_type ivt_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNBEP_U_MSR_PMON_CTR0, + .event_ctl = SNBEP_U_MSR_PMON_CTL0, + .event_mask = IVT_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &ivt_uncore_msr_ops, + .format_group = &ivt_uncore_ubox_format_group, +}; + +static struct extra_reg ivt_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8), + EVENT_EXTRA_END +}; + +static u64 ivt_cbox_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= IVT_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= IVT_CB0_MSR_PMON_BOX_FILTER_LINK; + if (fields & 0x4) + mask |= IVT_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= IVT_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x10) + mask |= IVT_CB0_MSR_PMON_BOX_FILTER_OPC; + + return mask; +} + +static struct event_constraint * +ivt_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, ivt_cbox_filter_mask); +} + +static int ivt_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = ivt_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + + SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & ivt_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void ivt_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + u64 filter = uncore_shared_reg_config(box, 0); + wrmsrl(reg1->reg, filter & 0xffffffff); + wrmsrl(reg1->reg + 6, filter >> 32); + } + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops ivt_uncore_cbox_ops = { + .init_box = ivt_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = ivt_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = ivt_cbox_hw_config, + .get_constraint = ivt_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type ivt_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 15, + .perf_ctr_bits = 44, + .event_ctl = SNBEP_C0_MSR_PMON_CTL0, + .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, + .event_mask = IVT_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = SNBEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = snbep_uncore_cbox_constraints, + .ops = &ivt_uncore_cbox_ops, + .format_group = &ivt_uncore_cbox_format_group, +}; + +static struct intel_uncore_ops ivt_uncore_pcu_ops = { + IVT_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + +static struct intel_uncore_type ivt_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, + .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, + .event_mask = IVT_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &ivt_uncore_pcu_ops, + .format_group = &ivt_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *ivt_msr_uncores[] = { + &ivt_uncore_ubox, + &ivt_uncore_cbox, + &ivt_uncore_pcu, + NULL, +}; + +static struct intel_uncore_type ivt_uncore_ha = { + .name = "ha", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + IVT_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type ivt_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + IVT_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type ivt_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = IVT_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &ivt_uncore_pci_ops, + .format_group = &ivt_uncore_qpi_format_group, +}; + +static struct intel_uncore_type ivt_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r2pcie_constraints, + IVT_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type ivt_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 2, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r3qpi_constraints, + IVT_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + IVT_PCI_UNCORE_HA, + IVT_PCI_UNCORE_IMC, + IVT_PCI_UNCORE_QPI, + IVT_PCI_UNCORE_R2PCIE, + IVT_PCI_UNCORE_R3QPI, +}; + +static struct intel_uncore_type *ivt_pci_uncores[] = { + [IVT_PCI_UNCORE_HA] = &ivt_uncore_ha, + [IVT_PCI_UNCORE_IMC] = &ivt_uncore_imc, + [IVT_PCI_UNCORE_QPI] = &ivt_uncore_qpi, + [IVT_PCI_UNCORE_R2PCIE] = &ivt_uncore_r2pcie, + [IVT_PCI_UNCORE_R3QPI] = &ivt_uncore_r3qpi, + NULL, +}; + +static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = { + { /* Home Agent 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30), + .driver_data = IVT_PCI_UNCORE_HA, + }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38), + .driver_data = IVT_PCI_UNCORE_HA, + }, + { /* MC0 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC0 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC0 Channel 4 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC1 Channel 4 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), + .driver_data = IVT_PCI_UNCORE_QPI, + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33), + .driver_data = IVT_PCI_UNCORE_QPI, + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a), + .driver_data = IVT_PCI_UNCORE_QPI, + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34), + .driver_data = IVT_PCI_UNCORE_R2PCIE, + }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36), + .driver_data = IVT_PCI_UNCORE_R3QPI, + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37), + .driver_data = IVT_PCI_UNCORE_R3QPI, + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), + .driver_data = IVT_PCI_UNCORE_R3QPI, + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver ivt_uncore_pci_driver = { + .name = "ivt_uncore", + .id_table = ivt_uncore_pci_ids, +}; +/* end of IvyTown uncore support */ + /* Sandy Bridge uncore support */ static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) { @@ -808,9 +1491,6 @@ static struct intel_uncore_type *nhm_msr_uncores[] = { /* end of Nehalem uncore support */ /* Nehalem-EX uncore support */ -#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ - ((1ULL << (n)) - 1))) - DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5"); DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7"); DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63"); @@ -1161,7 +1841,7 @@ static struct extra_reg nhmex_uncore_mbox_extra_regs[] = { }; /* Nehalem-EX or Westmere-EX ? */ -bool uncore_nhmex; +static bool uncore_nhmex; static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config) { @@ -1239,7 +1919,7 @@ static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx) atomic_sub(1 << (idx * 8), &er->ref); } -u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) +static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) { struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &hwc->extra_reg; @@ -1554,7 +2234,7 @@ static struct intel_uncore_type nhmex_uncore_mbox = { .format_group = &nhmex_uncore_mbox_format_group, }; -void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) +static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &hwc->extra_reg; @@ -1724,21 +2404,6 @@ static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event return 0; } -static u64 nhmex_rbox_shared_reg_config(struct intel_uncore_box *box, int idx) -{ - struct intel_uncore_extra_reg *er; - unsigned long flags; - u64 config; - - er = &box->shared_regs[idx]; - - raw_spin_lock_irqsave(&er->lock, flags); - config = er->config; - raw_spin_unlock_irqrestore(&er->lock, flags); - - return config; -} - static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -1759,7 +2424,7 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per case 2: case 3: wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port), - nhmex_rbox_shared_reg_config(box, 2 + (idx / 6) * 5)); + uncore_shared_reg_config(box, 2 + (idx / 6) * 5)); break; case 4: wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port), @@ -2285,7 +2950,7 @@ out: return ret; } -int uncore_pmu_event_init(struct perf_event *event) +static int uncore_pmu_event_init(struct perf_event *event) { struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; @@ -2438,7 +3103,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type) type->unconstrainted = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1, - 0, type->num_counters, 0); + 0, type->num_counters, 0, 0); for (i = 0; i < type->num_boxes; i++) { pmus[i].func_id = -1; @@ -2556,6 +3221,8 @@ static void uncore_pci_remove(struct pci_dev *pdev) if (WARN_ON_ONCE(phys_id != box->phys_id)) return; + pci_set_drvdata(pdev, NULL); + raw_spin_lock(&uncore_box_lock); list_del(&box->list); raw_spin_unlock(&uncore_box_lock); @@ -2574,11 +3241,7 @@ static void uncore_pci_remove(struct pci_dev *pdev) static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - struct intel_uncore_type *type; - - type = (struct intel_uncore_type *)id->driver_data; - - return uncore_pci_add(type, pdev); + return uncore_pci_add(pci_uncores[id->driver_data], pdev); } static int __init uncore_pci_init(void) @@ -2587,12 +3250,19 @@ static int __init uncore_pci_init(void) switch (boot_cpu_data.x86_model) { case 45: /* Sandy Bridge-EP */ - ret = snbep_pci2phy_map_init(); + ret = snbep_pci2phy_map_init(0x3ce0); if (ret) return ret; pci_uncores = snbep_pci_uncores; uncore_pci_driver = &snbep_uncore_pci_driver; break; + case 62: /* IvyTown */ + ret = snbep_pci2phy_map_init(0x0e1e); + if (ret) + return ret; + pci_uncores = ivt_pci_uncores; + uncore_pci_driver = &ivt_uncore_pci_driver; + break; default: return 0; } @@ -2622,6 +3292,21 @@ static void __init uncore_pci_exit(void) } } +/* CPU hot plug/unplug are serialized by cpu_add_remove_lock mutex */ +static LIST_HEAD(boxes_to_free); + +static void __cpuinit uncore_kfree_boxes(void) +{ + struct intel_uncore_box *box; + + while (!list_empty(&boxes_to_free)) { + box = list_entry(boxes_to_free.next, + struct intel_uncore_box, list); + list_del(&box->list); + kfree(box); + } +} + static void __cpuinit uncore_cpu_dying(int cpu) { struct intel_uncore_type *type; @@ -2636,7 +3321,7 @@ static void __cpuinit uncore_cpu_dying(int cpu) box = *per_cpu_ptr(pmu->box, cpu); *per_cpu_ptr(pmu->box, cpu) = NULL; if (box && atomic_dec_and_test(&box->refcnt)) - kfree(box); + list_add(&box->list, &boxes_to_free); } } } @@ -2666,8 +3351,11 @@ static int __cpuinit uncore_cpu_starting(int cpu) if (exist && exist->phys_id == phys_id) { atomic_inc(&exist->refcnt); *per_cpu_ptr(pmu->box, cpu) = exist; - kfree(box); - box = NULL; + if (box) { + list_add(&box->list, + &boxes_to_free); + box = NULL; + } break; } } @@ -2806,6 +3494,10 @@ static int case CPU_DYING: uncore_cpu_dying(cpu); break; + case CPU_ONLINE: + case CPU_DEAD: + uncore_kfree_boxes(); + break; default: break; } @@ -2871,6 +3563,12 @@ static int __init uncore_cpu_init(void) nhmex_uncore_cbox.num_boxes = max_cores; msr_uncores = nhmex_msr_uncores; break; + case 62: /* IvyTown */ + if (ivt_uncore_cbox.num_boxes > max_cores) + ivt_uncore_cbox.num_boxes = max_cores; + msr_uncores = ivt_msr_uncores; + break; + default: return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index e68a455..f952891 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -76,7 +76,7 @@ #define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00 #define SNBEP_PMON_CTL_RST (1 << 17) #define SNBEP_PMON_CTL_EDGE_DET (1 << 18) -#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) /* only for QPI */ +#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) #define SNBEP_PMON_CTL_EN (1 << 22) #define SNBEP_PMON_CTL_INVERT (1 << 23) #define SNBEP_PMON_CTL_TRESH_MASK 0xff000000 @@ -148,9 +148,20 @@ #define SNBEP_C0_MSR_PMON_CTL0 0xd10 #define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04 #define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14 -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK 0xfffffc1f #define SNBEP_CBO_MSR_OFFSET 0x20 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID 0x1f +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID 0x3fc00 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE 0x7c0000 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC 0xff800000 + +#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) { \ + .event = (e), \ + .msr = SNBEP_C0_MSR_PMON_BOX_FILTER, \ + .config_mask = (m), \ + .idx = (i) \ +} + /* SNB-EP PCU register */ #define SNBEP_PCU_MSR_PMON_CTR0 0xc36 #define SNBEP_PCU_MSR_PMON_CTL0 0xc30 @@ -160,6 +171,55 @@ #define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc #define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd +/* IVT event control */ +#define IVT_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ + SNBEP_PMON_BOX_CTL_RST_CTRS) +#define IVT_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_TRESH_MASK) +/* IVT Ubox */ +#define IVT_U_MSR_PMON_GLOBAL_CTL 0xc00 +#define IVT_U_PMON_GLOBAL_FRZ_ALL (1 << 31) +#define IVT_U_PMON_GLOBAL_UNFRZ_ALL (1 << 29) + +#define IVT_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_U_MSR_PMON_CTL_TRESH_MASK) +/* IVT Cbo */ +#define IVT_CBO_MSR_PMON_RAW_EVENT_MASK (IVT_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +#define IVT_CB0_MSR_PMON_BOX_FILTER_TID (0x1fULL << 0) +#define IVT_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 5) +#define IVT_CB0_MSR_PMON_BOX_FILTER_STATE (0x3fULL << 17) +#define IVT_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32) +#define IVT_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52) +#define IVT_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61) +#define IVT_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62) +#define IVT_CB0_MSR_PMON_BOX_FILTER_IOSC (0x1ULL << 63) + +/* IVT home agent */ +#define IVT_HA_PCI_PMON_CTL_Q_OCC_RST (1 << 16) +#define IVT_HA_PCI_PMON_RAW_EVENT_MASK \ + (IVT_PMON_RAW_EVENT_MASK | \ + IVT_HA_PCI_PMON_CTL_Q_OCC_RST) +/* IVT PCU */ +#define IVT_PCU_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) +/* IVT QPI */ +#define IVT_QPI_PCI_PMON_RAW_EVENT_MASK \ + (IVT_PMON_RAW_EVENT_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT) + /* NHM-EX event control */ #define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff #define NHMEX_PMON_CTL_UMASK_MASK 0x0000ff00 diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c index 4b7731b..838fa87 100644 --- a/arch/x86/kernel/cpu/perf_event_knc.c +++ b/arch/x86/kernel/cpu/perf_event_knc.c @@ -17,7 +17,7 @@ static const u64 knc_perfmon_event_map[] = [PERF_COUNT_HW_BRANCH_MISSES] = 0x002b, }; -static __initconst u64 knc_hw_cache_event_ids +static const u64 __initconst knc_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -284,7 +284,7 @@ static struct attribute *intel_knc_formats_attr[] = { NULL, }; -static __initconst struct x86_pmu knc_pmu = { +static const struct x86_pmu knc_pmu __initconst = { .name = "knc", .handle_irq = knc_pmu_handle_irq, .disable_all = knc_pmu_disable_all, diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index 92c7e39..3486e66 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -895,8 +895,8 @@ static void p4_pmu_disable_pebs(void) * So at moment let leave metrics turned on forever -- it's * ok for now but need to be revisited! * - * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)0); - * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)0); + * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, 0); + * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, 0); */ } @@ -910,8 +910,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event) * asserted again and again */ (void)wrmsrl_safe(hwc->config_base, - (u64)(p4_config_unpack_cccr(hwc->config)) & - ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED); + p4_config_unpack_cccr(hwc->config) & ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED); } static void p4_pmu_disable_all(void) @@ -957,7 +956,7 @@ static void p4_pmu_enable_event(struct perf_event *event) u64 escr_addr, cccr; bind = &p4_event_bind_map[idx]; - escr_addr = (u64)bind->escr_msr[thread]; + escr_addr = bind->escr_msr[thread]; /* * - we dont support cascaded counters yet diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index 4820c23..b1e2fe1 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -19,7 +19,7 @@ static const u64 p6_perfmon_event_map[] = }; -static u64 p6_hw_cache_event_ids +static const u64 __initconst p6_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index e280253..37a198b 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -34,9 +34,9 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) "fpu_exception\t: %s\n" "cpuid level\t: %d\n" "wp\t\t: %s\n", - c->fdiv_bug ? "yes" : "no", - c->f00f_bug ? "yes" : "no", - c->coma_bug ? "yes" : "no", + static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no", + static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no", + static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no", c->hard_math ? "yes" : "no", c->hard_math ? "yes" : "no", c->cpuid_level, diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault_32.c index 37250fe..155a13f 100644 --- a/arch/x86/kernel/doublefault_32.c +++ b/arch/x86/kernel/doublefault_32.c @@ -20,7 +20,7 @@ static void doublefault_fn(void) struct desc_ptr gdt_desc = {0, 0}; unsigned long gdt, tss; - store_gdt(&gdt_desc); + native_store_gdt(&gdt_desc); gdt = gdt_desc.address; printk(KERN_EMERG "PANIC: double fault, gdt at %08lx [%d bytes]\n", gdt, gdt_desc.size); diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 9b9f18b..d15f575 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -169,25 +169,9 @@ static struct console early_serial_console = { .index = -1, }; -/* Direct interface for emergencies */ -static struct console *early_console = &early_vga_console; -static int __initdata early_console_initialized; - -asmlinkage void early_printk(const char *fmt, ...) -{ - char buf[512]; - int n; - va_list ap; - - va_start(ap, fmt); - n = vscnprintf(buf, sizeof(buf), fmt, ap); - early_console->write(early_console, buf, n); - va_end(ap); -} - static inline void early_console_register(struct console *con, int keep_early) { - if (early_console->index != -1) { + if (con->index != -1) { printk(KERN_CRIT "ERROR: earlyprintk= %s already used\n", con->name); return; @@ -207,9 +191,8 @@ static int __init setup_early_printk(char *buf) if (!buf) return 0; - if (early_console_initialized) + if (early_console) return 0; - early_console_initialized = 1; keep = (strstr(buf, "keep") != NULL); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index c5e403f..101ac1a9 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -144,10 +144,10 @@ void __init x86_64_start_kernel(char * real_mode_data) * Build-time sanity checks on the kernel image and module * area mappings. (these are purely build-time and produce no code) */ - BUILD_BUG_ON(MODULES_VADDR < KERNEL_IMAGE_START); - BUILD_BUG_ON(MODULES_VADDR-KERNEL_IMAGE_START < KERNEL_IMAGE_SIZE); + BUILD_BUG_ON(MODULES_VADDR < __START_KERNEL_map); + BUILD_BUG_ON(MODULES_VADDR - __START_KERNEL_map < KERNEL_IMAGE_SIZE); BUILD_BUG_ON(MODULES_LEN + KERNEL_IMAGE_SIZE > 2*PUD_SIZE); - BUILD_BUG_ON((KERNEL_IMAGE_START & ~PMD_MASK) != 0); + BUILD_BUG_ON((__START_KERNEL_map & ~PMD_MASK) != 0); BUILD_BUG_ON((MODULES_VADDR & ~PMD_MASK) != 0); BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL)); BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) == diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 7bfe318..9895a9a 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -353,7 +353,11 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src) * have given. */ newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest; - BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check. */ + if ((s64) (s32) newdisp != newdisp) { + pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp); + pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", src, dest, insn.displacement.value); + return 0; + } disp = (u8 *) dest + insn_offset_displacement(&insn); *(s32 *) disp = (s32) newdisp; } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b686a90..cd6d9a5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -20,6 +20,7 @@ * Authors: Anthony Liguori <aliguori@us.ibm.com> */ +#include <linux/context_tracking.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/kvm_para.h> @@ -43,7 +44,6 @@ #include <asm/apicdef.h> #include <asm/hypervisor.h> #include <asm/kvm_guest.h> -#include <asm/context_tracking.h> static int kvmapf = 1; @@ -254,16 +254,18 @@ EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason); dotraplinkage void __kprobes do_async_page_fault(struct pt_regs *regs, unsigned long error_code) { + enum ctx_state prev_state; + switch (kvm_read_and_reset_pf_reason()) { default: do_page_fault(regs, error_code); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ - exception_enter(regs); + prev_state = exception_enter(); exit_idle(); kvm_async_pf_task_wait((u32)read_cr2()); - exception_exit(regs); + exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c index 577db84..833d51d 100644 --- a/arch/x86/kernel/microcode_core_early.c +++ b/arch/x86/kernel/microcode_core_early.c @@ -45,9 +45,6 @@ static int __cpuinit x86_vendor(void) u32 eax = 0x00000000; u32 ebx, ecx = 0, edx; - if (!have_cpuid_p()) - return X86_VENDOR_UNKNOWN; - native_cpuid(&eax, &ebx, &ecx, &edx); if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx)) @@ -59,18 +56,45 @@ static int __cpuinit x86_vendor(void) return X86_VENDOR_UNKNOWN; } +static int __cpuinit x86_family(void) +{ + u32 eax = 0x00000001; + u32 ebx, ecx = 0, edx; + int x86; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + x86 = (eax >> 8) & 0xf; + if (x86 == 15) + x86 += (eax >> 20) & 0xff; + + return x86; +} + void __init load_ucode_bsp(void) { - int vendor = x86_vendor(); + int vendor, x86; + + if (!have_cpuid_p()) + return; - if (vendor == X86_VENDOR_INTEL) + vendor = x86_vendor(); + x86 = x86_family(); + + if (vendor == X86_VENDOR_INTEL && x86 >= 6) load_ucode_intel_bsp(); } void __cpuinit load_ucode_ap(void) { - int vendor = x86_vendor(); + int vendor, x86; + + if (!have_cpuid_p()) + return; + + vendor = x86_vendor(); + x86 = x86_family(); - if (vendor == X86_VENDOR_INTEL) + if (vendor == X86_VENDOR_INTEL && x86 >= 6) load_ucode_intel_ap(); } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 8bfb335..cd6de64 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -360,7 +360,6 @@ struct pv_cpu_ops pv_cpu_ops = { .set_ldt = native_set_ldt, .load_gdt = native_load_gdt, .load_idt = native_load_idt, - .store_gdt = native_store_gdt, .store_idt = native_store_idt, .store_tr = native_store_tr, .load_tls = native_load_tls, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 14ae100..14fcf55 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -301,13 +301,7 @@ void exit_idle(void) } #endif -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle(void) +void arch_cpu_idle_prepare(void) { /* * If we're the non-boot CPU, nothing set the stack canary up @@ -317,71 +311,40 @@ void cpu_idle(void) * canaries already on the stack wont ever trigger). */ boot_init_stack_canary(); - current_thread_info()->status |= TS_POLLING; - - while (1) { - tick_nohz_idle_enter(); - - while (!need_resched()) { - rmb(); - - if (cpu_is_offline(smp_processor_id())) - play_dead(); - - /* - * Idle routines should keep interrupts disabled - * from here on, until they go to idle. - * Otherwise, idle callbacks can misfire. - */ - local_touch_nmi(); - local_irq_disable(); - - enter_idle(); - - /* Don't trace irqs off for idle */ - stop_critical_timings(); - - /* enter_idle() needs rcu for notifiers */ - rcu_idle_enter(); +} - if (cpuidle_idle_call()) - x86_idle(); +void arch_cpu_idle_enter(void) +{ + local_touch_nmi(); + enter_idle(); +} - rcu_idle_exit(); - start_critical_timings(); +void arch_cpu_idle_exit(void) +{ + __exit_idle(); +} - /* In many cases the interrupt that ended idle - has already called exit_idle. But some idle - loops can be woken up without interrupt. */ - __exit_idle(); - } +void arch_cpu_idle_dead(void) +{ + play_dead(); +} - tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); - } +/* + * Called from the generic idle code. + */ +void arch_cpu_idle(void) +{ + if (cpuidle_idle_call()) + x86_idle(); } /* - * We use this if we don't have any better - * idle routine.. + * We use this if we don't have any better idle routine.. */ void default_idle(void) { trace_cpu_idle_rcuidle(1, smp_processor_id()); - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - - if (!need_resched()) - safe_halt(); /* enables interrupts racelessly */ - else - local_irq_enable(); - current_thread_info()->status |= TS_POLLING; + safe_halt(); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #ifdef CONFIG_APM_MODULE @@ -411,20 +374,6 @@ void stop_this_cpu(void *dummy) halt(); } -/* - * On SMP it's slightly faster (but much more power-consuming!) - * to poll the ->work.need_resched flag instead of waiting for the - * cross-CPU IPI to arrive. Use this option with caution. - */ -static void poll_idle(void) -{ - trace_cpu_idle_rcuidle(0, smp_processor_id()); - local_irq_enable(); - while (!need_resched()) - cpu_relax(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); -} - bool amd_e400_c1e_detected; EXPORT_SYMBOL(amd_e400_c1e_detected); @@ -489,13 +438,13 @@ static void amd_e400_idle(void) void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP - if (x86_idle == poll_idle && smp_num_siblings > 1) + if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1) pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); #endif - if (x86_idle) + if (x86_idle || boot_option_idle_override == IDLE_POLL) return; - if (cpu_has_amd_erratum(amd_erratum_400)) { + if (cpu_has_bug(c, X86_BUG_AMD_APIC_C1E)) { /* E400: APIC timer interrupt does not wake up CPU from C1e */ pr_info("using AMD E400 aware idle routine\n"); x86_idle = amd_e400_idle; @@ -517,8 +466,8 @@ static int __init idle_setup(char *str) if (!strcmp(str, "poll")) { pr_info("using polling idle threads\n"); - x86_idle = poll_idle; boot_option_idle_override = IDLE_POLL; + cpu_idle_poll_ctrl(true); } else if (!strcmp(str, "halt")) { /* * When the boot option of idle=halt is added, halt is diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 26ee48a..04ee1e2 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -354,18 +354,22 @@ static void ati_force_hpet_resume(void) static u32 ati_ixp4x0_rev(struct pci_dev *dev) { - u32 d; - u8 b; + int err = 0; + u32 d = 0; + u8 b = 0; - pci_read_config_byte(dev, 0xac, &b); + err = pci_read_config_byte(dev, 0xac, &b); b &= ~(1<<5); - pci_write_config_byte(dev, 0xac, b); - pci_read_config_dword(dev, 0x70, &d); + err |= pci_write_config_byte(dev, 0xac, b); + err |= pci_read_config_dword(dev, 0x70, &d); d |= 1<<8; - pci_write_config_dword(dev, 0x70, d); - pci_read_config_dword(dev, 0x8, &d); + err |= pci_write_config_dword(dev, 0x70, d); + err |= pci_read_config_dword(dev, 0x8, &d); d &= 0xff; dev_printk(KERN_DEBUG, &dev->dev, "SB4X0 revision 0x%x\n", d); + + WARN_ON_ONCE(err); + return d; } diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 2e8f3d3..198eb20 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -13,6 +13,7 @@ #include <asm/x86_init.h> #include <asm/time.h> #include <asm/mrst.h> +#include <asm/rtc.h> #ifdef CONFIG_X86_32 /* @@ -36,70 +37,24 @@ EXPORT_SYMBOL(rtc_lock); * nowtime is written into the registers of the CMOS clock, it will * jump to the next second precisely 500 ms later. Check the Motorola * MC146818A or Dallas DS12887 data sheet for details. - * - * BUG: This routine does not handle hour overflow properly; it just - * sets the minutes. Usually you'll only notice that after reboot! */ int mach_set_rtc_mmss(unsigned long nowtime) { - int real_seconds, real_minutes, cmos_minutes; - unsigned char save_control, save_freq_select; - unsigned long flags; + struct rtc_time tm; int retval = 0; - spin_lock_irqsave(&rtc_lock, flags); - - /* tell the clock it's being set */ - save_control = CMOS_READ(RTC_CONTROL); - CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); - - /* stop and reset prescaler */ - save_freq_select = CMOS_READ(RTC_FREQ_SELECT); - CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); - - cmos_minutes = CMOS_READ(RTC_MINUTES); - if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - cmos_minutes = bcd2bin(cmos_minutes); - - /* - * since we're only adjusting minutes and seconds, - * don't interfere with hour overflow. This avoids - * messing with unknown time zones but requires your - * RTC not to be off by more than 15 minutes - */ - real_seconds = nowtime % 60; - real_minutes = nowtime / 60; - /* correct for half hour time zone */ - if (((abs(real_minutes - cmos_minutes) + 15)/30) & 1) - real_minutes += 30; - real_minutes %= 60; - - if (abs(real_minutes - cmos_minutes) < 30) { - if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { - real_seconds = bin2bcd(real_seconds); - real_minutes = bin2bcd(real_minutes); - } - CMOS_WRITE(real_seconds, RTC_SECONDS); - CMOS_WRITE(real_minutes, RTC_MINUTES); + rtc_time_to_tm(nowtime, &tm); + if (!rtc_valid_tm(&tm)) { + retval = set_rtc_time(&tm); + if (retval) + printk(KERN_ERR "%s: RTC write failed with error %d\n", + __FUNCTION__, retval); } else { - printk_once(KERN_NOTICE - "set_rtc_mmss: can't update from %d to %d\n", - cmos_minutes, real_minutes); - retval = -1; + printk(KERN_ERR + "%s: Invalid RTC value: write of %lx to RTC failed\n", + __FUNCTION__, nowtime); + retval = -EINVAL; } - - /* The following flags have to be released exactly in this order, - * otherwise the DS12887 (popular MC146818A clone with integrated - * battery and quartz) will not reset the oscillator and will not - * update precisely 500 ms later. You won't find this mentioned in - * the Dallas Semiconductor data sheets, but who believes data - * sheets anyway ... -- Markus Kuhn - */ - CMOS_WRITE(save_control, RTC_CONTROL); - CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); - - spin_unlock_irqrestore(&rtc_lock, flags); - return retval; } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 90d8cc9..4689855 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -82,7 +82,6 @@ #include <asm/timer.h> #include <asm/i8259.h> #include <asm/sections.h> -#include <asm/dmi.h> #include <asm/io_apic.h> #include <asm/ist.h> #include <asm/setup_arch.h> @@ -173,12 +172,10 @@ static struct resource bss_resource = { /* cpu data as detected by the assembly code in head.S */ struct cpuinfo_x86 new_cpu_data __cpuinitdata = { .wp_works_ok = -1, - .fdiv_bug = -1, }; /* common cpu data for all cpus */ struct cpuinfo_x86 boot_cpu_data __read_mostly = { .wp_works_ok = -1, - .fdiv_bug = -1, }; EXPORT_SYMBOL(boot_cpu_data); @@ -507,11 +504,14 @@ static void __init memblock_x86_reserve_range_setup_data(void) /* * Keep the crash kernel below this limit. On 32 bits earlier kernels * would limit the kernel to the low 512 MiB due to mapping restrictions. + * On 64bit, old kexec-tools need to under 896MiB. */ #ifdef CONFIG_X86_32 -# define CRASH_KERNEL_ADDR_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_LOW_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_HIGH_MAX (512 << 20) #else -# define CRASH_KERNEL_ADDR_MAX MAXMEM +# define CRASH_KERNEL_ADDR_LOW_MAX (896UL<<20) +# define CRASH_KERNEL_ADDR_HIGH_MAX MAXMEM #endif static void __init reserve_crashkernel_low(void) @@ -521,19 +521,35 @@ static void __init reserve_crashkernel_low(void) unsigned long long low_base = 0, low_size = 0; unsigned long total_low_mem; unsigned long long base; + bool auto_set = false; int ret; total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT)); + /* crashkernel=Y,low */ ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base); - if (ret != 0 || low_size <= 0) - return; + if (ret != 0) { + /* + * two parts from lib/swiotlb.c: + * swiotlb size: user specified with swiotlb= or default. + * swiotlb overflow buffer: now is hardcoded to 32k. + * We round it to 8M for other buffers that + * may need to stay low too. + */ + low_size = swiotlb_size_or_default() + (8UL<<20); + auto_set = true; + } else { + /* passed with crashkernel=0,low ? */ + if (!low_size) + return; + } low_base = memblock_find_in_range(low_size, (1ULL<<32), low_size, alignment); if (!low_base) { - pr_info("crashkernel low reservation failed - No suitable area found.\n"); + if (!auto_set) + pr_info("crashkernel low reservation failed - No suitable area found.\n"); return; } @@ -554,14 +570,22 @@ static void __init reserve_crashkernel(void) const unsigned long long alignment = 16<<20; /* 16M */ unsigned long long total_mem; unsigned long long crash_size, crash_base; + bool high = false; int ret; total_mem = memblock_phys_mem_size(); + /* crashkernel=XM */ ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); - if (ret != 0 || crash_size <= 0) - return; + if (ret != 0 || crash_size <= 0) { + /* crashkernel=X,high */ + ret = parse_crashkernel_high(boot_command_line, total_mem, + &crash_size, &crash_base); + if (ret != 0 || crash_size <= 0) + return; + high = true; + } /* 0 means: find the address automatically */ if (crash_base <= 0) { @@ -569,7 +593,9 @@ static void __init reserve_crashkernel(void) * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX */ crash_base = memblock_find_in_range(alignment, - CRASH_KERNEL_ADDR_MAX, crash_size, alignment); + high ? CRASH_KERNEL_ADDR_HIGH_MAX : + CRASH_KERNEL_ADDR_LOW_MAX, + crash_size, alignment); if (!crash_base) { pr_info("crashkernel reservation failed - No suitable area found.\n"); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9f190a2..9c73b51 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -284,7 +284,7 @@ notrace static void __cpuinit start_secondary(void *unused) x86_cpuinit.setup_percpu_clockev(); wmb(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } void __init smp_store_boot_cpu_info(void) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 68bda7a..772e2a8 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/context_tracking.h> #include <linux/interrupt.h> #include <linux/kallsyms.h> #include <linux/spinlock.h> @@ -55,8 +56,7 @@ #include <asm/i387.h> #include <asm/fpu-internal.h> #include <asm/mce.h> -#include <asm/context_tracking.h> - +#include <asm/fixmap.h> #include <asm/mach_traps.h> #ifdef CONFIG_X86_64 @@ -176,34 +176,38 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, #define DO_ERROR(trapnr, signr, str, name) \ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ - exception_enter(regs); \ + enum ctx_state prev_state; \ + \ + prev_state = exception_enter(); \ if (notify_die(DIE_TRAP, str, regs, error_code, \ trapnr, signr) == NOTIFY_STOP) { \ - exception_exit(regs); \ + exception_exit(prev_state); \ return; \ } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, NULL); \ - exception_exit(regs); \ + exception_exit(prev_state); \ } #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ siginfo_t info; \ + enum ctx_state prev_state; \ + \ info.si_signo = signr; \ info.si_errno = 0; \ info.si_code = sicode; \ info.si_addr = (void __user *)siaddr; \ - exception_enter(regs); \ + prev_state = exception_enter(); \ if (notify_die(DIE_TRAP, str, regs, error_code, \ trapnr, signr) == NOTIFY_STOP) { \ - exception_exit(regs); \ + exception_exit(prev_state); \ return; \ } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, &info); \ - exception_exit(regs); \ + exception_exit(prev_state); \ } DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, @@ -226,14 +230,16 @@ DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, /* Runs on IST stack */ dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); if (notify_die(DIE_TRAP, "stack segment", regs, error_code, X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { preempt_conditional_sti(regs); do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); preempt_conditional_cli(regs); } - exception_exit(regs); + exception_exit(prev_state); } dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) @@ -241,7 +247,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) static const char str[] = "double fault"; struct task_struct *tsk = current; - exception_enter(regs); + exception_enter(); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -261,8 +267,9 @@ dotraplinkage void __kprobes do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; + enum ctx_state prev_state; - exception_enter(regs); + prev_state = exception_enter(); conditional_sti(regs); #ifdef CONFIG_X86_32 @@ -300,12 +307,14 @@ do_general_protection(struct pt_regs *regs, long error_code) force_sig(SIGSEGV, tsk); exit: - exception_exit(regs); + exception_exit(prev_state); } /* May run on IST stack. */ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code) { + enum ctx_state prev_state; + #ifdef CONFIG_DYNAMIC_FTRACE /* * ftrace must be first, everything else may cause a recursive crash. @@ -315,7 +324,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co ftrace_int3_handler(regs)) return; #endif - exception_enter(regs); + prev_state = exception_enter(); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) @@ -336,7 +345,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co preempt_conditional_cli(regs); debug_stack_usage_dec(); exit: - exception_exit(regs); + exception_exit(prev_state); } #ifdef CONFIG_X86_64 @@ -393,11 +402,12 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) { struct task_struct *tsk = current; + enum ctx_state prev_state; int user_icebp = 0; unsigned long dr6; int si_code; - exception_enter(regs); + prev_state = exception_enter(); get_debugreg(dr6, 6); @@ -467,7 +477,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_dec(); exit: - exception_exit(regs); + exception_exit(prev_state); } /* @@ -561,17 +571,21 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); math_error(regs, error_code, X86_TRAP_MF); - exception_exit(regs); + exception_exit(prev_state); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); math_error(regs, error_code, X86_TRAP_XF); - exception_exit(regs); + exception_exit(prev_state); } dotraplinkage void @@ -639,7 +653,9 @@ EXPORT_SYMBOL_GPL(math_state_restore); dotraplinkage void __kprobes do_device_not_available(struct pt_regs *regs, long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); BUG_ON(use_eager_fpu()); #ifdef CONFIG_MATH_EMULATION @@ -650,7 +666,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); - exception_exit(regs); + exception_exit(prev_state); return; } #endif @@ -658,15 +674,16 @@ do_device_not_available(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 conditional_sti(regs); #endif - exception_exit(regs); + exception_exit(prev_state); } #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) { siginfo_t info; + enum ctx_state prev_state; - exception_enter(regs); + prev_state = exception_enter(); local_irq_enable(); info.si_signo = SIGILL; @@ -678,7 +695,7 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, &info); } - exception_exit(regs); + exception_exit(prev_state); } #endif @@ -753,6 +770,14 @@ void __init trap_init(void) #endif /* + * Set the IDT descriptor to a fixed read-only location, so that the + * "sidt" instruction will not leak the location of the kernel, and + * to defend the IDT against arbitrary memory write vulnerabilities. + * It will be reloaded in cpu_init() */ + __set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO); + idt_descr.address = fix_to_virt(FIX_RO_IDT); + + /* * Should be a barrier for any external CPU state: */ cpu_init(); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 4b9ea10..098b3cf 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -768,7 +768,8 @@ static cycle_t read_tsc(struct clocksource *cs) static void resume_tsc(struct clocksource *cs) { - clocksource_tsc.cycle_last = 0; + if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) + clocksource_tsc.cycle_last = 0; } static struct clocksource clocksource_tsc = { @@ -939,6 +940,9 @@ static int __init init_tsc_clocksource(void) clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; } + if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) + clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; + /* * Trust the results of the earlier calibration on systems * exporting a reliable TSC. diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 0ba4cfb..2ed8459 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -697,3 +697,32 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) send_sig(SIGTRAP, current, 0); return ret; } + +unsigned long +arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs) +{ + int rasize, ncopied; + unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */ + + rasize = is_ia32_task() ? 4 : 8; + ncopied = copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize); + if (unlikely(ncopied)) + return -1; + + /* check whether address has been already hijacked */ + if (orig_ret_vaddr == trampoline_vaddr) + return orig_ret_vaddr; + + ncopied = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize); + if (likely(!ncopied)) + return orig_ret_vaddr; + + if (ncopied != rasize) { + pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, " + "%%ip=%#lx\n", current->pid, regs->sp, regs->ip); + + force_sig_info(SIGSEGV, SEND_SIG_FORCED, current); + } + + return -1; +} diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 22a1530..10c4f30 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -94,10 +94,6 @@ SECTIONS _text = .; /* bootstrapping code */ HEAD_TEXT -#ifdef CONFIG_X86_32 - . = ALIGN(PAGE_SIZE); - *(.text..page_aligned) -#endif . = ALIGN(8); _stext = .; TEXT_TEXT diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index e1b1ce2..7d39d70 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -555,7 +555,7 @@ static void svm_init_erratum_383(void) int err; u64 val; - if (!cpu_has_amd_erratum(amd_erratum_383)) + if (!static_cpu_has_bug(X86_BUG_AMD_TLB_MMATCH)) return; /* Use _safe variants to not break nested virtualization */ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 6667042..867b810 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2459,7 +2459,7 @@ static int hardware_enable(void *garbage) ept_sync_global(); } - store_gdt(&__get_cpu_var(host_gdt)); + native_store_gdt(&__get_cpu_var(host_gdt)); return 0; } diff --git a/arch/x86/lguest/Kconfig b/arch/x86/lguest/Kconfig index 29043d2..4a0890f 100644 --- a/arch/x86/lguest/Kconfig +++ b/arch/x86/lguest/Kconfig @@ -1,7 +1,6 @@ config LGUEST_GUEST bool "Lguest guest support" - select PARAVIRT - depends on X86_32 + depends on X86_32 && PARAVIRT select TTY select VIRTUALIZATION select VIRTIO diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 2af5df3..e78b8ee 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -61,7 +61,7 @@ ENTRY(csum_partial) testl $3, %esi # Check alignment. jz 2f # Jump if alignment is ok. testl $1, %esi # Check alignment. - jz 10f # Jump if alignment is boundary of 2bytes. + jz 10f # Jump if alignment is boundary of 2 bytes. # buf is odd dec %ecx diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c index b908a59..e78761d 100644 --- a/arch/x86/lib/memcpy_32.c +++ b/arch/x86/lib/memcpy_32.c @@ -26,7 +26,7 @@ void *memmove(void *dest, const void *src, size_t n) char *ret = dest; __asm__ __volatile__( - /* Handle more 16bytes in loop */ + /* Handle more 16 bytes in loop */ "cmp $0x10, %0\n\t" "jb 1f\n\t" @@ -51,7 +51,7 @@ void *memmove(void *dest, const void *src, size_t n) "sub $0x10, %0\n\t" /* - * We gobble 16byts forward in each loop. + * We gobble 16 bytes forward in each loop. */ "3:\n\t" "sub $0x10, %0\n\t" @@ -117,7 +117,7 @@ void *memmove(void *dest, const void *src, size_t n) "sub $0x10, %0\n\t" /* - * We gobble 16byts backward in each loop. + * We gobble 16 bytes backward in each loop. */ "7:\n\t" "sub $0x10, %0\n\t" diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 1c273be..56313a3 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -98,7 +98,7 @@ ENTRY(memcpy) subq $0x20, %rdx /* * At most 3 ALU operations in one cycle, - * so append NOPS in the same 16bytes trunk. + * so append NOPS in the same 16 bytes trunk. */ .p2align 4 .Lcopy_backward_loop: diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index ee16461..65268a6 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -27,7 +27,7 @@ ENTRY(memmove) CFI_STARTPROC - /* Handle more 32bytes in loop */ + /* Handle more 32 bytes in loop */ mov %rdi, %rax cmp $0x20, %rdx jb 1f @@ -56,7 +56,7 @@ ENTRY(memmove) 3: sub $0x20, %rdx /* - * We gobble 32byts forward in each loop. + * We gobble 32 bytes forward in each loop. */ 5: sub $0x20, %rdx @@ -122,7 +122,7 @@ ENTRY(memmove) addq %rdx, %rdi subq $0x20, %rdx /* - * We gobble 32byts backward in each loop. + * We gobble 32 bytes backward in each loop. */ 8: subq $0x20, %rdx diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index 5247d01..2ca15b5 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -130,9 +130,8 @@ int __init amd_numa_init(void) } limit >>= 16; - limit <<= 24; - limit |= (1<<24)-1; limit++; + limit <<= 24; if (limit > end) limit = end; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 0e88336..654be4a 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -13,12 +13,12 @@ #include <linux/perf_event.h> /* perf_sw_event */ #include <linux/hugetlb.h> /* hstate_index_to_shift */ #include <linux/prefetch.h> /* prefetchw */ +#include <linux/context_tracking.h> /* exception_enter(), ... */ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/pgalloc.h> /* pgd_*(), ... */ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ #include <asm/fixmap.h> /* VSYSCALL_START */ -#include <asm/context_tracking.h> /* exception_enter(), ... */ /* * Page fault error code bits: @@ -557,7 +557,7 @@ static int is_f00f_bug(struct pt_regs *regs, unsigned long address) /* * Pentium F0 0F C7 C8 bug workaround: */ - if (boot_cpu_data.f00f_bug) { + if (boot_cpu_has_bug(X86_BUG_F00F)) { nr = (address - idt_descr.address) >> 3; if (nr == 6) { @@ -1224,7 +1224,9 @@ good_area: dotraplinkage void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); __do_page_fault(regs, error_code); - exception_exit(regs); + exception_exit(prev_state); } diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 6f31ee5..252b8f5 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -137,5 +137,4 @@ void __init set_highmem_pages_init(void) add_highpages_with_active_regions(nid, zone_start_pfn, zone_end_pfn); } - totalram_pages += totalhigh_pages; } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 59b7fc4..fdc5dca 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -515,11 +515,8 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end) printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); for (; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE); - free_page(addr); - totalram_pages++; + free_reserved_page(virt_to_page(addr)); } #endif } diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 2d19001..3ac7e31 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -427,14 +427,6 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) pkmap_page_table = pte; } -static void __init add_one_highpage_init(struct page *page) -{ - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - totalhigh_pages++; -} - void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn, unsigned long end_pfn) { @@ -448,7 +440,7 @@ void __init add_highpages_with_active_regions(int nid, start_pfn, end_pfn); for ( ; pfn < e_pfn; pfn++) if (pfn_valid(pfn)) - add_one_highpage_init(pfn_to_page(pfn)); + free_highmem_page(pfn_to_page(pfn)); } } #else diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 474e28f..caad9a0 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1011,14 +1011,12 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct) flush_tlb_all(); } -void __ref vmemmap_free(struct page *memmap, unsigned long nr_pages) +void __ref vmemmap_free(unsigned long start, unsigned long end) { - unsigned long start = (unsigned long)memmap; - unsigned long end = (unsigned long)(memmap + nr_pages); - remove_pagetable(start, end, false); } +#ifdef CONFIG_MEMORY_HOTREMOVE static void __meminit kernel_physical_mapping_remove(unsigned long start, unsigned long end) { @@ -1028,7 +1026,6 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end) remove_pagetable(start, end, true); } -#ifdef CONFIG_MEMORY_HOTREMOVE int __ref arch_remove_memory(u64 start, u64 size) { unsigned long start_pfn = start >> PAGE_SHIFT; @@ -1067,10 +1064,9 @@ void __init mem_init(void) /* clear_bss() already clear the empty_zero_page */ - reservedpages = 0; - - /* this will put all low memory onto the freelists */ register_page_bootmem_info(); + + /* this will put all memory onto the freelists */ totalram_pages = free_all_bootmem(); absent_pages = absent_pages_in_range(0, max_pfn); @@ -1285,18 +1281,17 @@ static long __meminitdata addr_start, addr_end; static void __meminitdata *p_start, *p_end; static int __meminitdata node_start; -int __meminit -vmemmap_populate(struct page *start_page, unsigned long size, int node) +static int __meminit vmemmap_populate_hugepages(unsigned long start, + unsigned long end, int node) { - unsigned long addr = (unsigned long)start_page; - unsigned long end = (unsigned long)(start_page + size); + unsigned long addr; unsigned long next; pgd_t *pgd; pud_t *pud; pmd_t *pmd; - for (; addr < end; addr = next) { - void *p = NULL; + for (addr = start; addr < end; addr = next) { + next = pmd_addr_end(addr, end); pgd = vmemmap_pgd_populate(addr, node); if (!pgd) @@ -1306,31 +1301,14 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node) if (!pud) return -ENOMEM; - if (!cpu_has_pse) { - next = (addr + PAGE_SIZE) & PAGE_MASK; - pmd = vmemmap_pmd_populate(pud, addr, node); - - if (!pmd) - return -ENOMEM; - - p = vmemmap_pte_populate(pmd, addr, node); + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) { + void *p; - if (!p) - return -ENOMEM; - - addr_end = addr + PAGE_SIZE; - p_end = p + PAGE_SIZE; - } else { - next = pmd_addr_end(addr, end); - - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) { + p = vmemmap_alloc_block_buf(PMD_SIZE, node); + if (p) { pte_t entry; - p = vmemmap_alloc_block_buf(PMD_SIZE, node); - if (!p) - return -ENOMEM; - entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL_LARGE); set_pmd(pmd, __pmd(pte_val(entry))); @@ -1347,15 +1325,32 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node) addr_end = addr + PMD_SIZE; p_end = p + PMD_SIZE; - } else - vmemmap_verify((pte_t *)pmd, node, addr, next); + continue; + } + } else if (pmd_large(*pmd)) { + vmemmap_verify((pte_t *)pmd, node, addr, next); + continue; } - + pr_warn_once("vmemmap: falling back to regular page backing\n"); + if (vmemmap_populate_basepages(addr, next, node)) + return -ENOMEM; } - sync_global_pgds((unsigned long)start_page, end - 1); return 0; } +int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) +{ + int err; + + if (cpu_has_pse) + err = vmemmap_populate_hugepages(start, end, node); + else + err = vmemmap_populate_basepages(start, end, node); + if (!err) + sync_global_pgds(start, end - 1); + return err; +} + #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE) void register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long size) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 78fe3f1..9a1e658 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -282,12 +282,7 @@ void iounmap(volatile void __iomem *addr) in parallel. Reuse of the virtual address is prevented by leaving it in the global lists until we're done with it. cpa takes care of the direct mappings. */ - read_lock(&vmlist_lock); - for (p = vmlist; p; p = p->next) { - if (p->addr == (void __force *)addr) - break; - } - read_unlock(&vmlist_lock); + p = find_vm_area((void __force *)addr); if (!p) { printk(KERN_ERR "iounmap: bad address %p\n", addr); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 72fe01e..a71c4e2 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -114,14 +114,11 @@ void numa_clear_node(int cpu) */ void __init setup_node_to_cpumask_map(void) { - unsigned int node, num = 0; + unsigned int node; /* setup nr_node_ids if not done yet */ - if (nr_node_ids == MAX_NUMNODES) { - for_each_node_mask(node, node_possible_map) - num = node; - nr_node_ids = num + 1; - } + if (nr_node_ids == MAX_NUMNODES) + setup_nr_node_ids(); /* allocate the map */ for (node = 0; node < nr_node_ids; node++) diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 0e38951..d0b1773 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -130,13 +130,12 @@ static int pageattr_test(void) } failed += print_split(&sa); - srandom32(100); for (i = 0; i < NTEST; i++) { - unsigned long pfn = random32() % max_pfn_mapped; + unsigned long pfn = prandom_u32() % max_pfn_mapped; addr[i] = (unsigned long)__va(pfn << PAGE_SHIFT); - len[i] = random32() % 100; + len[i] = prandom_u32() % 100; len[i] = min_t(unsigned long, len[i], max_pfn_mapped - pfn - 1); if (len[i] == 0) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index fb4e73e..bb32480 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -542,13 +542,14 @@ out_unlock: return do_split; } -int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase) +static int +__split_large_page(pte_t *kpte, unsigned long address, struct page *base) { + pte_t *pbase = (pte_t *)page_address(base); unsigned long pfn, pfninc = 1; unsigned int i, level; pte_t *tmp; pgprot_t ref_prot; - struct page *base = virt_to_page(pbase); spin_lock(&pgd_lock); /* @@ -633,7 +634,6 @@ int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase) static int split_large_page(pte_t *kpte, unsigned long address) { - pte_t *pbase; struct page *base; if (!debug_pagealloc) @@ -644,8 +644,7 @@ static int split_large_page(pte_t *kpte, unsigned long address) if (!base) return -ENOMEM; - pbase = (pte_t *)page_address(base); - if (__split_large_page(kpte, address, pbase)) + if (__split_large_page(kpte, address, base)) __free_page(base); return 0; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 901177d..305c68b 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -6,6 +6,7 @@ #include <linux/sched.h> #include <linux/pci.h> +#include <linux/pci-acpi.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/dmi.h> @@ -170,6 +171,16 @@ void pcibios_fixup_bus(struct pci_bus *b) pcibios_fixup_device_resources(dev); } +void pcibios_add_bus(struct pci_bus *bus) +{ + acpi_pci_add_bus(bus); +} + +void pcibios_remove_bus(struct pci_bus *bus) +{ + acpi_pci_remove_bus(bus); +} + /* * Only use DMI information to set this if nothing was passed * on the kernel command line (which was parsed earlier). diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 94e7662..4a9be6d 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -177,7 +177,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) goto error; i = 0; list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0, + irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], (type == PCI_CAP_ID_MSIX) ? "pcifront-msi-x" : "pcifront-msi", @@ -244,7 +244,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) dev_dbg(&dev->dev, "xen: msi already bound to pirq=%d\n", pirq); } - irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0, + irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, (type == PCI_CAP_ID_MSIX) ? "msi-x" : "msi", DOMID_SELF); @@ -326,7 +326,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) } ret = xen_bind_pirq_msi_to_irq(dev, msidesc, - map_irq.pirq, map_irq.index, + map_irq.pirq, (type == PCI_CAP_ID_MSIX) ? "msi-x" : "msi", domid); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 5f2ecaf..b55d174 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -41,6 +41,7 @@ #include <linux/io.h> #include <linux/reboot.h> #include <linux/bcd.h> +#include <linux/ucs2_string.h> #include <asm/setup.h> #include <asm/efi.h> @@ -48,9 +49,17 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/x86_init.h> +#include <asm/rtc.h> #define EFI_DEBUG 1 +/* + * There's some additional metadata associated with each + * variable. Intel's reference implementation is 60 bytes - bump that + * to account for potential alignment constraints + */ +#define VAR_METADATA_SIZE 64 + struct efi __read_mostly efi = { .mps = EFI_INVALID_TABLE_ADDR, .acpi = EFI_INVALID_TABLE_ADDR, @@ -69,6 +78,13 @@ struct efi_memory_map memmap; static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; +static u64 efi_var_store_size; +static u64 efi_var_remaining_size; +static u64 efi_var_max_var_size; +static u64 boot_used_size; +static u64 boot_var_size; +static u64 active_size; + unsigned long x86_efi_facility; /* @@ -98,6 +114,15 @@ static int __init setup_add_efi_memmap(char *arg) } early_param("add_efi_memmap", setup_add_efi_memmap); +static bool efi_no_storage_paranoia; + +static int __init setup_storage_paranoia(char *arg) +{ + efi_no_storage_paranoia = true; + return 0; +} +early_param("efi_no_storage_paranoia", setup_storage_paranoia); + static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { @@ -162,8 +187,53 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { - return efi_call_virt3(get_next_variable, - name_size, name, vendor); + efi_status_t status; + static bool finished = false; + static u64 var_size; + + status = efi_call_virt3(get_next_variable, + name_size, name, vendor); + + if (status == EFI_NOT_FOUND) { + finished = true; + if (var_size < boot_used_size) { + boot_var_size = boot_used_size - var_size; + active_size += boot_var_size; + } else { + printk(KERN_WARNING FW_BUG "efi: Inconsistent initial sizes\n"); + } + } + + if (boot_used_size && !finished) { + unsigned long size; + u32 attr; + efi_status_t s; + void *tmp; + + s = virt_efi_get_variable(name, vendor, &attr, &size, NULL); + + if (s != EFI_BUFFER_TOO_SMALL || !size) + return status; + + tmp = kmalloc(size, GFP_ATOMIC); + + if (!tmp) + return status; + + s = virt_efi_get_variable(name, vendor, &attr, &size, tmp); + + if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) { + var_size += size; + var_size += ucs2_strsize(name, 1024); + active_size += size; + active_size += VAR_METADATA_SIZE; + active_size += ucs2_strsize(name, 1024); + } + + kfree(tmp); + } + + return status; } static efi_status_t virt_efi_set_variable(efi_char16_t *name, @@ -172,9 +242,34 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name, unsigned long data_size, void *data) { - return efi_call_virt5(set_variable, - name, vendor, attr, - data_size, data); + efi_status_t status; + u32 orig_attr = 0; + unsigned long orig_size = 0; + + status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size, + NULL); + + if (status != EFI_BUFFER_TOO_SMALL) + orig_size = 0; + + status = efi_call_virt5(set_variable, + name, vendor, attr, + data_size, data); + + if (status == EFI_SUCCESS) { + if (orig_size) { + active_size -= orig_size; + active_size -= ucs2_strsize(name, 1024); + active_size -= VAR_METADATA_SIZE; + } + if (data_size) { + active_size += data_size; + active_size += ucs2_strsize(name, 1024); + active_size += VAR_METADATA_SIZE; + } + } + + return status; } static efi_status_t virt_efi_query_variable_info(u32 attr, @@ -258,10 +353,10 @@ static efi_status_t __init phys_efi_get_time(efi_time_t *tm, int efi_set_rtc_mmss(unsigned long nowtime) { - int real_seconds, real_minutes; efi_status_t status; efi_time_t eft; efi_time_cap_t cap; + struct rtc_time tm; status = efi.get_time(&eft, &cap); if (status != EFI_SUCCESS) { @@ -269,13 +364,20 @@ int efi_set_rtc_mmss(unsigned long nowtime) return -1; } - real_seconds = nowtime % 60; - real_minutes = nowtime / 60; - if (((abs(real_minutes - eft.minute) + 15)/30) & 1) - real_minutes += 30; - real_minutes %= 60; - eft.minute = real_minutes; - eft.second = real_seconds; + rtc_time_to_tm(nowtime, &tm); + if (!rtc_valid_tm(&tm)) { + eft.year = tm.tm_year + 1900; + eft.month = tm.tm_mon + 1; + eft.day = tm.tm_mday; + eft.minute = tm.tm_min; + eft.second = tm.tm_sec; + eft.nanosecond = 0; + } else { + printk(KERN_ERR + "%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n", + __FUNCTION__, nowtime); + return -1; + } status = efi.set_time(&eft); if (status != EFI_SUCCESS) { @@ -682,6 +784,9 @@ void __init efi_init(void) char vendor[100] = "unknown"; int i = 0; void *tmp; + struct setup_data *data; + struct efi_var_bootdata *efi_var_data; + u64 pa_data; #ifdef CONFIG_X86_32 if (boot_params.efi_info.efi_systab_hi || @@ -699,6 +804,22 @@ void __init efi_init(void) if (efi_systab_init(efi_phys.systab)) return; + pa_data = boot_params.hdr.setup_data; + while (pa_data) { + data = early_ioremap(pa_data, sizeof(*efi_var_data)); + if (data->type == SETUP_EFI_VARS) { + efi_var_data = (struct efi_var_bootdata *)data; + + efi_var_store_size = efi_var_data->store_size; + efi_var_remaining_size = efi_var_data->remaining_size; + efi_var_max_var_size = efi_var_data->max_var_size; + } + pa_data = data->next; + early_iounmap(data, sizeof(*efi_var_data)); + } + + boot_used_size = efi_var_store_size - efi_var_remaining_size; + set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); /* @@ -999,3 +1120,48 @@ u64 efi_mem_attributes(unsigned long phys_addr) } return 0; } + +/* + * Some firmware has serious problems when using more than 50% of the EFI + * variable store, i.e. it triggers bugs that can brick machines. Ensure that + * we never use more than this safe limit. + * + * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable + * store. + */ +efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) +{ + efi_status_t status; + u64 storage_size, remaining_size, max_size; + + status = efi.query_variable_info(attributes, &storage_size, + &remaining_size, &max_size); + if (status != EFI_SUCCESS) + return status; + + if (!max_size && remaining_size > size) + printk_once(KERN_ERR FW_BUG "Broken EFI implementation" + " is returning MaxVariableSize=0\n"); + /* + * Some firmware implementations refuse to boot if there's insufficient + * space in the variable store. We account for that by refusing the + * write if permitting it would reduce the available space to under + * 50%. However, some firmware won't reclaim variable space until + * after the used (not merely the actively used) space drops below + * a threshold. We can approximate that case with the value calculated + * above. If both the firmware and our calculations indicate that the + * available space would drop below 50%, refuse the write. + */ + + if (!storage_size || size > remaining_size || + (max_size && size > max_size)) + return EFI_OUT_OF_RESOURCES; + + if (!efi_no_storage_paranoia && + ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) && + (remaining_size - size < storage_size / 2))) + return EFI_OUT_OF_RESOURCES; + + return EFI_SUCCESS; +} +EXPORT_SYMBOL_GPL(efi_query_variable_store); diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index e31bcd8..a0a0a43 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -356,8 +356,7 @@ static int __init sfi_parse_gpio(struct sfi_table_header *table) num = SFI_GET_NUM_ENTRIES(sb, struct sfi_gpio_table_entry); pentry = (struct sfi_gpio_table_entry *)sb->pentry; - gpio_table = (struct sfi_gpio_table_entry *) - kmalloc(num * sizeof(*pentry), GFP_KERNEL); + gpio_table = kmalloc(num * sizeof(*pentry), GFP_KERNEL); if (!gpio_table) return -1; memcpy(gpio_table, pentry, num * sizeof(*pentry)); diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c index 225bd0f..d62b0a3 100644 --- a/arch/x86/platform/mrst/vrtc.c +++ b/arch/x86/platform/mrst/vrtc.c @@ -85,27 +85,35 @@ unsigned long vrtc_get_time(void) return mktime(year, mon, mday, hour, min, sec); } -/* Only care about the minutes and seconds */ int vrtc_set_mmss(unsigned long nowtime) { - int real_sec, real_min; unsigned long flags; - int vrtc_min; - - spin_lock_irqsave(&rtc_lock, flags); - vrtc_min = vrtc_cmos_read(RTC_MINUTES); - - real_sec = nowtime % 60; - real_min = nowtime / 60; - if (((abs(real_min - vrtc_min) + 15)/30) & 1) - real_min += 30; - real_min %= 60; - - vrtc_cmos_write(real_sec, RTC_SECONDS); - vrtc_cmos_write(real_min, RTC_MINUTES); - spin_unlock_irqrestore(&rtc_lock, flags); - - return 0; + struct rtc_time tm; + int year; + int retval = 0; + + rtc_time_to_tm(nowtime, &tm); + if (!rtc_valid_tm(&tm) && tm.tm_year >= 72) { + /* + * tm.year is the number of years since 1900, and the + * vrtc need the years since 1972. + */ + year = tm.tm_year - 72; + spin_lock_irqsave(&rtc_lock, flags); + vrtc_cmos_write(year, RTC_YEAR); + vrtc_cmos_write(tm.tm_mon, RTC_MONTH); + vrtc_cmos_write(tm.tm_mday, RTC_DAY_OF_MONTH); + vrtc_cmos_write(tm.tm_hour, RTC_HOURS); + vrtc_cmos_write(tm.tm_min, RTC_MINUTES); + vrtc_cmos_write(tm.tm_sec, RTC_SECONDS); + spin_unlock_irqrestore(&rtc_lock, flags); + } else { + printk(KERN_ERR + "%s: Invalid vRTC value: write of %lx to vRTC failed\n", + __FUNCTION__, nowtime); + retval = -EINVAL; + } + return retval; } void __init mrst_rtc_init(void) diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c index 74704be..9a2e590 100644 --- a/arch/x86/platform/olpc/olpc-xo1-sci.c +++ b/arch/x86/platform/olpc/olpc-xo1-sci.c @@ -460,7 +460,6 @@ static int setup_power_button(struct platform_device *pdev) static void free_power_button(void) { input_unregister_device(power_button_idev); - input_free_device(power_button_idev); } static int setup_ebook_switch(struct platform_device *pdev) @@ -491,7 +490,6 @@ static int setup_ebook_switch(struct platform_device *pdev) static void free_ebook_switch(void) { input_unregister_device(ebook_switch_idev); - input_free_device(ebook_switch_idev); } static int setup_lid_switch(struct platform_device *pdev) @@ -526,6 +524,7 @@ static int setup_lid_switch(struct platform_device *pdev) err_create_attr: input_unregister_device(lid_switch_idev); + lid_switch_idev = NULL; err_register: input_free_device(lid_switch_idev); return r; @@ -535,7 +534,6 @@ static void free_lid_switch(void) { device_remove_file(&lid_switch_idev->dev, &dev_attr_lid_wake_mode); input_unregister_device(lid_switch_idev); - input_free_device(lid_switch_idev); } static int xo1_sci_probe(struct platform_device *pdev) diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c index 98718f6..5c86786 100644 --- a/arch/x86/platform/uv/uv_time.c +++ b/arch/x86/platform/uv/uv_time.c @@ -159,10 +159,9 @@ static __init int uv_rtc_allocate_timers(void) { int cpu; - blade_info = kmalloc(uv_possible_blades * sizeof(void *), GFP_KERNEL); + blade_info = kzalloc(uv_possible_blades * sizeof(void *), GFP_KERNEL); if (!blade_info) return -ENOMEM; - memset(blade_info, 0, uv_possible_blades * sizeof(void *)); for_each_present_cpu(cpu) { int nid = cpu_to_node(cpu); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 3c68768..6d6e907 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -62,11 +62,9 @@ static void __save_processor_state(struct saved_context *ctxt) * descriptor tables */ #ifdef CONFIG_X86_32 - store_gdt(&ctxt->gdt); store_idt(&ctxt->idt); #else /* CONFIG_X86_64 */ - store_gdt((struct desc_ptr *)&ctxt->gdt_limit); store_idt((struct desc_ptr *)&ctxt->idt_limit); #endif store_tr(ctxt->tr); @@ -135,7 +133,10 @@ static void fix_processor_context(void) { int cpu = smp_processor_id(); struct tss_struct *t = &per_cpu(init_tss, cpu); - +#ifdef CONFIG_X86_64 + struct desc_struct *desc = get_cpu_gdt_table(cpu); + tss_desc tss; +#endif set_tss_desc(cpu, t); /* * This just modifies memory; should not be * necessary. But... This is necessary, because @@ -144,7 +145,9 @@ static void fix_processor_context(void) */ #ifdef CONFIG_X86_64 - get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS].type = 9; + memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc)); + tss.type = 0x9; /* The available 64-bit TSS (see AMD vol 2, pg 91 */ + write_gdt_entry(desc, GDT_ENTRY_TSS, &tss, DESC_TSS); syscall_init(); /* This sets MSR_*STAR and related */ #endif @@ -183,11 +186,9 @@ static void __restore_processor_state(struct saved_context *ctxt) * ltr is done i fix_processor_context(). */ #ifdef CONFIG_X86_32 - load_gdt(&ctxt->gdt); load_idt(&ctxt->idt); #else /* CONFIG_X86_64 */ - load_gdt((const struct desc_ptr *)&ctxt->gdt_limit); load_idt((const struct desc_ptr *)&ctxt->idt_limit); #endif diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile index bae601f..e812034 100644 --- a/arch/x86/tools/Makefile +++ b/arch/x86/tools/Makefile @@ -39,4 +39,5 @@ $(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/ina HOST_EXTRACFLAGS += -I$(srctree)/tools/include hostprogs-y += relocs +relocs-objs := relocs_32.o relocs_64.o relocs_common.o relocs: $(obj)/relocs diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 79d67bd..590be10 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -1,43 +1,36 @@ -#include <stdio.h> -#include <stdarg.h> -#include <stdlib.h> -#include <stdint.h> -#include <string.h> -#include <errno.h> -#include <unistd.h> -#include <elf.h> -#include <byteswap.h> -#define USE_BSD -#include <endian.h> -#include <regex.h> -#include <tools/le_byteshift.h> - -static void die(char *fmt, ...); - -#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) -static Elf32_Ehdr ehdr; -static unsigned long reloc_count, reloc_idx; -static unsigned long *relocs; -static unsigned long reloc16_count, reloc16_idx; -static unsigned long *relocs16; +/* This is included from relocs_32/64.c */ + +#define ElfW(type) _ElfW(ELF_BITS, type) +#define _ElfW(bits, type) __ElfW(bits, type) +#define __ElfW(bits, type) Elf##bits##_##type + +#define Elf_Addr ElfW(Addr) +#define Elf_Ehdr ElfW(Ehdr) +#define Elf_Phdr ElfW(Phdr) +#define Elf_Shdr ElfW(Shdr) +#define Elf_Sym ElfW(Sym) + +static Elf_Ehdr ehdr; + +struct relocs { + uint32_t *offset; + unsigned long count; + unsigned long size; +}; + +static struct relocs relocs16; +static struct relocs relocs32; +static struct relocs relocs64; struct section { - Elf32_Shdr shdr; + Elf_Shdr shdr; struct section *link; - Elf32_Sym *symtab; - Elf32_Rel *reltab; + Elf_Sym *symtab; + Elf_Rel *reltab; char *strtab; }; static struct section *secs; -enum symtype { - S_ABS, - S_REL, - S_SEG, - S_LIN, - S_NSYMTYPES -}; - static const char * const sym_regex_kernel[S_NSYMTYPES] = { /* * Following symbols have been audited. There values are constant and do @@ -49,6 +42,9 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "^(xen_irq_disable_direct_reloc$|" "xen_save_fl_direct_reloc$|" "VDSO|" +#if ELF_BITS == 64 + "__vvar_page|" +#endif "__crc_)", /* @@ -72,6 +68,11 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "__end_rodata|" "__initramfs_start|" "(jiffies|jiffies_64)|" +#if ELF_BITS == 64 + "__per_cpu_load|" + "init_per_cpu__.*|" + "__end_rodata_hpage_align|" +#endif "_end)$" }; @@ -132,15 +133,6 @@ static void regex_init(int use_real_mode) } } -static void die(char *fmt, ...) -{ - va_list ap; - va_start(ap, fmt); - vfprintf(stderr, fmt, ap); - va_end(ap); - exit(1); -} - static const char *sym_type(unsigned type) { static const char *type_name[] = { @@ -198,6 +190,24 @@ static const char *rel_type(unsigned type) { static const char *type_name[] = { #define REL_TYPE(X) [X] = #X +#if ELF_BITS == 64 + REL_TYPE(R_X86_64_NONE), + REL_TYPE(R_X86_64_64), + REL_TYPE(R_X86_64_PC32), + REL_TYPE(R_X86_64_GOT32), + REL_TYPE(R_X86_64_PLT32), + REL_TYPE(R_X86_64_COPY), + REL_TYPE(R_X86_64_GLOB_DAT), + REL_TYPE(R_X86_64_JUMP_SLOT), + REL_TYPE(R_X86_64_RELATIVE), + REL_TYPE(R_X86_64_GOTPCREL), + REL_TYPE(R_X86_64_32), + REL_TYPE(R_X86_64_32S), + REL_TYPE(R_X86_64_16), + REL_TYPE(R_X86_64_PC16), + REL_TYPE(R_X86_64_8), + REL_TYPE(R_X86_64_PC8), +#else REL_TYPE(R_386_NONE), REL_TYPE(R_386_32), REL_TYPE(R_386_PC32), @@ -213,6 +223,7 @@ static const char *rel_type(unsigned type) REL_TYPE(R_386_PC8), REL_TYPE(R_386_16), REL_TYPE(R_386_PC16), +#endif #undef REL_TYPE }; const char *name = "unknown type rel type name"; @@ -240,7 +251,7 @@ static const char *sec_name(unsigned shndx) return name; } -static const char *sym_name(const char *sym_strtab, Elf32_Sym *sym) +static const char *sym_name(const char *sym_strtab, Elf_Sym *sym) { const char *name; name = "<noname>"; @@ -253,15 +264,42 @@ static const char *sym_name(const char *sym_strtab, Elf32_Sym *sym) return name; } +static Elf_Sym *sym_lookup(const char *symname) +{ + int i; + for (i = 0; i < ehdr.e_shnum; i++) { + struct section *sec = &secs[i]; + long nsyms; + char *strtab; + Elf_Sym *symtab; + Elf_Sym *sym; + + if (sec->shdr.sh_type != SHT_SYMTAB) + continue; + nsyms = sec->shdr.sh_size/sizeof(Elf_Sym); + symtab = sec->symtab; + strtab = sec->link->strtab; + + for (sym = symtab; --nsyms >= 0; sym++) { + if (!sym->st_name) + continue; + if (strcmp(symname, strtab + sym->st_name) == 0) + return sym; + } + } + return 0; +} #if BYTE_ORDER == LITTLE_ENDIAN #define le16_to_cpu(val) (val) #define le32_to_cpu(val) (val) +#define le64_to_cpu(val) (val) #endif #if BYTE_ORDER == BIG_ENDIAN #define le16_to_cpu(val) bswap_16(val) #define le32_to_cpu(val) bswap_32(val) +#define le64_to_cpu(val) bswap_64(val) #endif static uint16_t elf16_to_cpu(uint16_t val) @@ -274,6 +312,23 @@ static uint32_t elf32_to_cpu(uint32_t val) return le32_to_cpu(val); } +#define elf_half_to_cpu(x) elf16_to_cpu(x) +#define elf_word_to_cpu(x) elf32_to_cpu(x) + +#if ELF_BITS == 64 +static uint64_t elf64_to_cpu(uint64_t val) +{ + return le64_to_cpu(val); +} +#define elf_addr_to_cpu(x) elf64_to_cpu(x) +#define elf_off_to_cpu(x) elf64_to_cpu(x) +#define elf_xword_to_cpu(x) elf64_to_cpu(x) +#else +#define elf_addr_to_cpu(x) elf32_to_cpu(x) +#define elf_off_to_cpu(x) elf32_to_cpu(x) +#define elf_xword_to_cpu(x) elf32_to_cpu(x) +#endif + static void read_ehdr(FILE *fp) { if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) { @@ -283,8 +338,8 @@ static void read_ehdr(FILE *fp) if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0) { die("No ELF magic\n"); } - if (ehdr.e_ident[EI_CLASS] != ELFCLASS32) { - die("Not a 32 bit executable\n"); + if (ehdr.e_ident[EI_CLASS] != ELF_CLASS) { + die("Not a %d bit executable\n", ELF_BITS); } if (ehdr.e_ident[EI_DATA] != ELFDATA2LSB) { die("Not a LSB ELF executable\n"); @@ -293,36 +348,36 @@ static void read_ehdr(FILE *fp) die("Unknown ELF version\n"); } /* Convert the fields to native endian */ - ehdr.e_type = elf16_to_cpu(ehdr.e_type); - ehdr.e_machine = elf16_to_cpu(ehdr.e_machine); - ehdr.e_version = elf32_to_cpu(ehdr.e_version); - ehdr.e_entry = elf32_to_cpu(ehdr.e_entry); - ehdr.e_phoff = elf32_to_cpu(ehdr.e_phoff); - ehdr.e_shoff = elf32_to_cpu(ehdr.e_shoff); - ehdr.e_flags = elf32_to_cpu(ehdr.e_flags); - ehdr.e_ehsize = elf16_to_cpu(ehdr.e_ehsize); - ehdr.e_phentsize = elf16_to_cpu(ehdr.e_phentsize); - ehdr.e_phnum = elf16_to_cpu(ehdr.e_phnum); - ehdr.e_shentsize = elf16_to_cpu(ehdr.e_shentsize); - ehdr.e_shnum = elf16_to_cpu(ehdr.e_shnum); - ehdr.e_shstrndx = elf16_to_cpu(ehdr.e_shstrndx); + ehdr.e_type = elf_half_to_cpu(ehdr.e_type); + ehdr.e_machine = elf_half_to_cpu(ehdr.e_machine); + ehdr.e_version = elf_word_to_cpu(ehdr.e_version); + ehdr.e_entry = elf_addr_to_cpu(ehdr.e_entry); + ehdr.e_phoff = elf_off_to_cpu(ehdr.e_phoff); + ehdr.e_shoff = elf_off_to_cpu(ehdr.e_shoff); + ehdr.e_flags = elf_word_to_cpu(ehdr.e_flags); + ehdr.e_ehsize = elf_half_to_cpu(ehdr.e_ehsize); + ehdr.e_phentsize = elf_half_to_cpu(ehdr.e_phentsize); + ehdr.e_phnum = elf_half_to_cpu(ehdr.e_phnum); + ehdr.e_shentsize = elf_half_to_cpu(ehdr.e_shentsize); + ehdr.e_shnum = elf_half_to_cpu(ehdr.e_shnum); + ehdr.e_shstrndx = elf_half_to_cpu(ehdr.e_shstrndx); if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN)) { die("Unsupported ELF header type\n"); } - if (ehdr.e_machine != EM_386) { - die("Not for x86\n"); + if (ehdr.e_machine != ELF_MACHINE) { + die("Not for %s\n", ELF_MACHINE_NAME); } if (ehdr.e_version != EV_CURRENT) { die("Unknown ELF version\n"); } - if (ehdr.e_ehsize != sizeof(Elf32_Ehdr)) { + if (ehdr.e_ehsize != sizeof(Elf_Ehdr)) { die("Bad Elf header size\n"); } - if (ehdr.e_phentsize != sizeof(Elf32_Phdr)) { + if (ehdr.e_phentsize != sizeof(Elf_Phdr)) { die("Bad program header entry\n"); } - if (ehdr.e_shentsize != sizeof(Elf32_Shdr)) { + if (ehdr.e_shentsize != sizeof(Elf_Shdr)) { die("Bad section header entry\n"); } if (ehdr.e_shstrndx >= ehdr.e_shnum) { @@ -333,7 +388,7 @@ static void read_ehdr(FILE *fp) static void read_shdrs(FILE *fp) { int i; - Elf32_Shdr shdr; + Elf_Shdr shdr; secs = calloc(ehdr.e_shnum, sizeof(struct section)); if (!secs) { @@ -349,16 +404,16 @@ static void read_shdrs(FILE *fp) if (fread(&shdr, sizeof shdr, 1, fp) != 1) die("Cannot read ELF section headers %d/%d: %s\n", i, ehdr.e_shnum, strerror(errno)); - sec->shdr.sh_name = elf32_to_cpu(shdr.sh_name); - sec->shdr.sh_type = elf32_to_cpu(shdr.sh_type); - sec->shdr.sh_flags = elf32_to_cpu(shdr.sh_flags); - sec->shdr.sh_addr = elf32_to_cpu(shdr.sh_addr); - sec->shdr.sh_offset = elf32_to_cpu(shdr.sh_offset); - sec->shdr.sh_size = elf32_to_cpu(shdr.sh_size); - sec->shdr.sh_link = elf32_to_cpu(shdr.sh_link); - sec->shdr.sh_info = elf32_to_cpu(shdr.sh_info); - sec->shdr.sh_addralign = elf32_to_cpu(shdr.sh_addralign); - sec->shdr.sh_entsize = elf32_to_cpu(shdr.sh_entsize); + sec->shdr.sh_name = elf_word_to_cpu(shdr.sh_name); + sec->shdr.sh_type = elf_word_to_cpu(shdr.sh_type); + sec->shdr.sh_flags = elf_xword_to_cpu(shdr.sh_flags); + sec->shdr.sh_addr = elf_addr_to_cpu(shdr.sh_addr); + sec->shdr.sh_offset = elf_off_to_cpu(shdr.sh_offset); + sec->shdr.sh_size = elf_xword_to_cpu(shdr.sh_size); + sec->shdr.sh_link = elf_word_to_cpu(shdr.sh_link); + sec->shdr.sh_info = elf_word_to_cpu(shdr.sh_info); + sec->shdr.sh_addralign = elf_xword_to_cpu(shdr.sh_addralign); + sec->shdr.sh_entsize = elf_xword_to_cpu(shdr.sh_entsize); if (sec->shdr.sh_link < ehdr.e_shnum) sec->link = &secs[sec->shdr.sh_link]; } @@ -412,12 +467,12 @@ static void read_symtabs(FILE *fp) die("Cannot read symbol table: %s\n", strerror(errno)); } - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) { - Elf32_Sym *sym = &sec->symtab[j]; - sym->st_name = elf32_to_cpu(sym->st_name); - sym->st_value = elf32_to_cpu(sym->st_value); - sym->st_size = elf32_to_cpu(sym->st_size); - sym->st_shndx = elf16_to_cpu(sym->st_shndx); + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Sym); j++) { + Elf_Sym *sym = &sec->symtab[j]; + sym->st_name = elf_word_to_cpu(sym->st_name); + sym->st_value = elf_addr_to_cpu(sym->st_value); + sym->st_size = elf_xword_to_cpu(sym->st_size); + sym->st_shndx = elf_half_to_cpu(sym->st_shndx); } } } @@ -428,7 +483,7 @@ static void read_relocs(FILE *fp) int i,j; for (i = 0; i < ehdr.e_shnum; i++) { struct section *sec = &secs[i]; - if (sec->shdr.sh_type != SHT_REL) { + if (sec->shdr.sh_type != SHT_REL_TYPE) { continue; } sec->reltab = malloc(sec->shdr.sh_size); @@ -445,10 +500,13 @@ static void read_relocs(FILE *fp) die("Cannot read symbol table: %s\n", strerror(errno)); } - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) { - Elf32_Rel *rel = &sec->reltab[j]; - rel->r_offset = elf32_to_cpu(rel->r_offset); - rel->r_info = elf32_to_cpu(rel->r_info); + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { + Elf_Rel *rel = &sec->reltab[j]; + rel->r_offset = elf_addr_to_cpu(rel->r_offset); + rel->r_info = elf_xword_to_cpu(rel->r_info); +#if (SHT_REL_TYPE == SHT_RELA) + rel->r_addend = elf_xword_to_cpu(rel->r_addend); +#endif } } } @@ -457,6 +515,13 @@ static void read_relocs(FILE *fp) static void print_absolute_symbols(void) { int i; + const char *format; + + if (ELF_BITS == 64) + format = "%5d %016"PRIx64" %5"PRId64" %10s %10s %12s %s\n"; + else + format = "%5d %08"PRIx32" %5"PRId32" %10s %10s %12s %s\n"; + printf("Absolute symbols\n"); printf(" Num: Value Size Type Bind Visibility Name\n"); for (i = 0; i < ehdr.e_shnum; i++) { @@ -468,19 +533,19 @@ static void print_absolute_symbols(void) continue; } sym_strtab = sec->link->strtab; - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) { - Elf32_Sym *sym; + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Sym); j++) { + Elf_Sym *sym; const char *name; sym = &sec->symtab[j]; name = sym_name(sym_strtab, sym); if (sym->st_shndx != SHN_ABS) { continue; } - printf("%5d %08x %5d %10s %10s %12s %s\n", + printf(format, j, sym->st_value, sym->st_size, - sym_type(ELF32_ST_TYPE(sym->st_info)), - sym_bind(ELF32_ST_BIND(sym->st_info)), - sym_visibility(ELF32_ST_VISIBILITY(sym->st_other)), + sym_type(ELF_ST_TYPE(sym->st_info)), + sym_bind(ELF_ST_BIND(sym->st_info)), + sym_visibility(ELF_ST_VISIBILITY(sym->st_other)), name); } } @@ -490,14 +555,20 @@ static void print_absolute_symbols(void) static void print_absolute_relocs(void) { int i, printed = 0; + const char *format; + + if (ELF_BITS == 64) + format = "%016"PRIx64" %016"PRIx64" %10s %016"PRIx64" %s\n"; + else + format = "%08"PRIx32" %08"PRIx32" %10s %08"PRIx32" %s\n"; for (i = 0; i < ehdr.e_shnum; i++) { struct section *sec = &secs[i]; struct section *sec_applies, *sec_symtab; char *sym_strtab; - Elf32_Sym *sh_symtab; + Elf_Sym *sh_symtab; int j; - if (sec->shdr.sh_type != SHT_REL) { + if (sec->shdr.sh_type != SHT_REL_TYPE) { continue; } sec_symtab = sec->link; @@ -507,12 +578,12 @@ static void print_absolute_relocs(void) } sh_symtab = sec_symtab->symtab; sym_strtab = sec_symtab->link->strtab; - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) { - Elf32_Rel *rel; - Elf32_Sym *sym; + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { + Elf_Rel *rel; + Elf_Sym *sym; const char *name; rel = &sec->reltab[j]; - sym = &sh_symtab[ELF32_R_SYM(rel->r_info)]; + sym = &sh_symtab[ELF_R_SYM(rel->r_info)]; name = sym_name(sym_strtab, sym); if (sym->st_shndx != SHN_ABS) { continue; @@ -542,10 +613,10 @@ static void print_absolute_relocs(void) printed = 1; } - printf("%08x %08x %10s %08x %s\n", + printf(format, rel->r_offset, rel->r_info, - rel_type(ELF32_R_TYPE(rel->r_info)), + rel_type(ELF_R_TYPE(rel->r_info)), sym->st_value, name); } @@ -555,19 +626,34 @@ static void print_absolute_relocs(void) printf("\n"); } -static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym), - int use_real_mode) +static void add_reloc(struct relocs *r, uint32_t offset) +{ + if (r->count == r->size) { + unsigned long newsize = r->size + 50000; + void *mem = realloc(r->offset, newsize * sizeof(r->offset[0])); + + if (!mem) + die("realloc of %ld entries for relocs failed\n", + newsize); + r->offset = mem; + r->size = newsize; + } + r->offset[r->count++] = offset; +} + +static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel, + Elf_Sym *sym, const char *symname)) { int i; /* Walk through the relocations */ for (i = 0; i < ehdr.e_shnum; i++) { char *sym_strtab; - Elf32_Sym *sh_symtab; + Elf_Sym *sh_symtab; struct section *sec_applies, *sec_symtab; int j; struct section *sec = &secs[i]; - if (sec->shdr.sh_type != SHT_REL) { + if (sec->shdr.sh_type != SHT_REL_TYPE) { continue; } sec_symtab = sec->link; @@ -577,101 +663,281 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym), } sh_symtab = sec_symtab->symtab; sym_strtab = sec_symtab->link->strtab; - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) { - Elf32_Rel *rel; - Elf32_Sym *sym; - unsigned r_type; - const char *symname; - int shn_abs; + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { + Elf_Rel *rel = &sec->reltab[j]; + Elf_Sym *sym = &sh_symtab[ELF_R_SYM(rel->r_info)]; + const char *symname = sym_name(sym_strtab, sym); - rel = &sec->reltab[j]; - sym = &sh_symtab[ELF32_R_SYM(rel->r_info)]; - r_type = ELF32_R_TYPE(rel->r_info); - - shn_abs = sym->st_shndx == SHN_ABS; - - switch (r_type) { - case R_386_NONE: - case R_386_PC32: - case R_386_PC16: - case R_386_PC8: - /* - * NONE can be ignored and and PC relative - * relocations don't need to be adjusted. - */ - break; + process(sec, rel, sym, symname); + } + } +} - case R_386_16: - symname = sym_name(sym_strtab, sym); - if (!use_real_mode) - goto bad; - if (shn_abs) { - if (is_reloc(S_ABS, symname)) - break; - else if (!is_reloc(S_SEG, symname)) - goto bad; - } else { - if (is_reloc(S_LIN, symname)) - goto bad; - else - break; - } - visit(rel, sym); - break; +/* + * The .data..percpu section is a special case for x86_64 SMP kernels. + * It is used to initialize the actual per_cpu areas and to provide + * definitions for the per_cpu variables that correspond to their offsets + * within the percpu area. Since the values of all of the symbols need + * to be offsets from the start of the per_cpu area the virtual address + * (sh_addr) of .data..percpu is 0 in SMP kernels. + * + * This means that: + * + * Relocations that reference symbols in the per_cpu area do not + * need further relocation (since the value is an offset relative + * to the start of the per_cpu area that does not change). + * + * Relocations that apply to the per_cpu area need to have their + * offset adjusted by by the value of __per_cpu_load to make them + * point to the correct place in the loaded image (because the + * virtual address of .data..percpu is 0). + * + * For non SMP kernels .data..percpu is linked as part of the normal + * kernel data and does not require special treatment. + * + */ +static int per_cpu_shndx = -1; +Elf_Addr per_cpu_load_addr; - case R_386_32: - symname = sym_name(sym_strtab, sym); - if (shn_abs) { - if (is_reloc(S_ABS, symname)) - break; - else if (!is_reloc(S_REL, symname)) - goto bad; - } else { - if (use_real_mode && - !is_reloc(S_LIN, symname)) - break; - } - visit(rel, sym); - break; - default: - die("Unsupported relocation type: %s (%d)\n", - rel_type(r_type), r_type); +static void percpu_init(void) +{ + int i; + for (i = 0; i < ehdr.e_shnum; i++) { + ElfW(Sym) *sym; + if (strcmp(sec_name(i), ".data..percpu")) + continue; + + if (secs[i].shdr.sh_addr != 0) /* non SMP kernel */ + return; + + sym = sym_lookup("__per_cpu_load"); + if (!sym) + die("can't find __per_cpu_load\n"); + + per_cpu_shndx = i; + per_cpu_load_addr = sym->st_value; + return; + } +} + +#if ELF_BITS == 64 + +/* + * Check to see if a symbol lies in the .data..percpu section. + * For some as yet not understood reason the "__init_begin" + * symbol which immediately preceeds the .data..percpu section + * also shows up as it it were part of it so we do an explict + * check for that symbol name and ignore it. + */ +static int is_percpu_sym(ElfW(Sym) *sym, const char *symname) +{ + return (sym->st_shndx == per_cpu_shndx) && + strcmp(symname, "__init_begin"); +} + + +static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym, + const char *symname) +{ + unsigned r_type = ELF64_R_TYPE(rel->r_info); + ElfW(Addr) offset = rel->r_offset; + int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname); + + if (sym->st_shndx == SHN_UNDEF) + return 0; + + /* + * Adjust the offset if this reloc applies to the percpu section. + */ + if (sec->shdr.sh_info == per_cpu_shndx) + offset += per_cpu_load_addr; + + switch (r_type) { + case R_X86_64_NONE: + case R_X86_64_PC32: + /* + * NONE can be ignored and PC relative relocations don't + * need to be adjusted. + */ + break; + + case R_X86_64_32: + case R_X86_64_32S: + case R_X86_64_64: + /* + * References to the percpu area don't need to be adjusted. + */ + if (is_percpu_sym(sym, symname)) + break; + + if (shn_abs) { + /* + * Whitelisted absolute symbols do not require + * relocation. + */ + if (is_reloc(S_ABS, symname)) break; - bad: - symname = sym_name(sym_strtab, sym); - die("Invalid %s %s relocation: %s\n", - shn_abs ? "absolute" : "relative", - rel_type(r_type), symname); - } + + die("Invalid absolute %s relocation: %s\n", + rel_type(r_type), symname); + break; } + + /* + * Relocation offsets for 64 bit kernels are output + * as 32 bits and sign extended back to 64 bits when + * the relocations are processed. + * Make sure that the offset will fit. + */ + if ((int32_t)offset != (int64_t)offset) + die("Relocation offset doesn't fit in 32 bits\n"); + + if (r_type == R_X86_64_64) + add_reloc(&relocs64, offset); + else + add_reloc(&relocs32, offset); + break; + + default: + die("Unsupported relocation type: %s (%d)\n", + rel_type(r_type), r_type); + break; } + + return 0; } -static void count_reloc(Elf32_Rel *rel, Elf32_Sym *sym) +#else + +static int do_reloc32(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, + const char *symname) { - if (ELF32_R_TYPE(rel->r_info) == R_386_16) - reloc16_count++; - else - reloc_count++; + unsigned r_type = ELF32_R_TYPE(rel->r_info); + int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname); + + switch (r_type) { + case R_386_NONE: + case R_386_PC32: + case R_386_PC16: + case R_386_PC8: + /* + * NONE can be ignored and PC relative relocations don't + * need to be adjusted. + */ + break; + + case R_386_32: + if (shn_abs) { + /* + * Whitelisted absolute symbols do not require + * relocation. + */ + if (is_reloc(S_ABS, symname)) + break; + + die("Invalid absolute %s relocation: %s\n", + rel_type(r_type), symname); + break; + } + + add_reloc(&relocs32, rel->r_offset); + break; + + default: + die("Unsupported relocation type: %s (%d)\n", + rel_type(r_type), r_type); + break; + } + + return 0; } -static void collect_reloc(Elf32_Rel *rel, Elf32_Sym *sym) +static int do_reloc_real(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, + const char *symname) { - /* Remember the address that needs to be adjusted. */ - if (ELF32_R_TYPE(rel->r_info) == R_386_16) - relocs16[reloc16_idx++] = rel->r_offset; - else - relocs[reloc_idx++] = rel->r_offset; + unsigned r_type = ELF32_R_TYPE(rel->r_info); + int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname); + + switch (r_type) { + case R_386_NONE: + case R_386_PC32: + case R_386_PC16: + case R_386_PC8: + /* + * NONE can be ignored and PC relative relocations don't + * need to be adjusted. + */ + break; + + case R_386_16: + if (shn_abs) { + /* + * Whitelisted absolute symbols do not require + * relocation. + */ + if (is_reloc(S_ABS, symname)) + break; + + if (is_reloc(S_SEG, symname)) { + add_reloc(&relocs16, rel->r_offset); + break; + } + } else { + if (!is_reloc(S_LIN, symname)) + break; + } + die("Invalid %s %s relocation: %s\n", + shn_abs ? "absolute" : "relative", + rel_type(r_type), symname); + break; + + case R_386_32: + if (shn_abs) { + /* + * Whitelisted absolute symbols do not require + * relocation. + */ + if (is_reloc(S_ABS, symname)) + break; + + if (is_reloc(S_REL, symname)) { + add_reloc(&relocs32, rel->r_offset); + break; + } + } else { + if (is_reloc(S_LIN, symname)) + add_reloc(&relocs32, rel->r_offset); + break; + } + die("Invalid %s %s relocation: %s\n", + shn_abs ? "absolute" : "relative", + rel_type(r_type), symname); + break; + + default: + die("Unsupported relocation type: %s (%d)\n", + rel_type(r_type), r_type); + break; + } + + return 0; } +#endif + static int cmp_relocs(const void *va, const void *vb) { - const unsigned long *a, *b; + const uint32_t *a, *b; a = va; b = vb; return (*a == *b)? 0 : (*a > *b)? 1 : -1; } -static int write32(unsigned int v, FILE *f) +static void sort_relocs(struct relocs *r) +{ + qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs); +} + +static int write32(uint32_t v, FILE *f) { unsigned char buf[4]; @@ -679,33 +945,40 @@ static int write32(unsigned int v, FILE *f) return fwrite(buf, 1, 4, f) == 4 ? 0 : -1; } +static int write32_as_text(uint32_t v, FILE *f) +{ + return fprintf(f, "\t.long 0x%08"PRIx32"\n", v) > 0 ? 0 : -1; +} + static void emit_relocs(int as_text, int use_real_mode) { int i; - /* Count how many relocations I have and allocate space for them. */ - reloc_count = 0; - walk_relocs(count_reloc, use_real_mode); - relocs = malloc(reloc_count * sizeof(relocs[0])); - if (!relocs) { - die("malloc of %d entries for relocs failed\n", - reloc_count); - } + int (*write_reloc)(uint32_t, FILE *) = write32; + int (*do_reloc)(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, + const char *symname); + +#if ELF_BITS == 64 + if (!use_real_mode) + do_reloc = do_reloc64; + else + die("--realmode not valid for a 64-bit ELF file"); +#else + if (!use_real_mode) + do_reloc = do_reloc32; + else + do_reloc = do_reloc_real; +#endif - relocs16 = malloc(reloc16_count * sizeof(relocs[0])); - if (!relocs16) { - die("malloc of %d entries for relocs16 failed\n", - reloc16_count); - } /* Collect up the relocations */ - reloc_idx = 0; - walk_relocs(collect_reloc, use_real_mode); + walk_relocs(do_reloc); - if (reloc16_count && !use_real_mode) + if (relocs16.count && !use_real_mode) die("Segment relocations found but --realmode not specified\n"); /* Order the relocations for more efficient processing */ - qsort(relocs, reloc_count, sizeof(relocs[0]), cmp_relocs); - qsort(relocs16, reloc16_count, sizeof(relocs16[0]), cmp_relocs); + sort_relocs(&relocs16); + sort_relocs(&relocs32); + sort_relocs(&relocs64); /* Print the relocations */ if (as_text) { @@ -714,114 +987,60 @@ static void emit_relocs(int as_text, int use_real_mode) */ printf(".section \".data.reloc\",\"a\"\n"); printf(".balign 4\n"); - if (use_real_mode) { - printf("\t.long %lu\n", reloc16_count); - for (i = 0; i < reloc16_count; i++) - printf("\t.long 0x%08lx\n", relocs16[i]); - printf("\t.long %lu\n", reloc_count); - for (i = 0; i < reloc_count; i++) { - printf("\t.long 0x%08lx\n", relocs[i]); - } - } else { - /* Print a stop */ - printf("\t.long 0x%08lx\n", (unsigned long)0); - for (i = 0; i < reloc_count; i++) { - printf("\t.long 0x%08lx\n", relocs[i]); - } - } - - printf("\n"); + write_reloc = write32_as_text; } - else { - if (use_real_mode) { - write32(reloc16_count, stdout); - for (i = 0; i < reloc16_count; i++) - write32(relocs16[i], stdout); - write32(reloc_count, stdout); - /* Now print each relocation */ - for (i = 0; i < reloc_count; i++) - write32(relocs[i], stdout); - } else { + if (use_real_mode) { + write_reloc(relocs16.count, stdout); + for (i = 0; i < relocs16.count; i++) + write_reloc(relocs16.offset[i], stdout); + + write_reloc(relocs32.count, stdout); + for (i = 0; i < relocs32.count; i++) + write_reloc(relocs32.offset[i], stdout); + } else { + if (ELF_BITS == 64) { /* Print a stop */ - write32(0, stdout); + write_reloc(0, stdout); /* Now print each relocation */ - for (i = 0; i < reloc_count; i++) { - write32(relocs[i], stdout); - } + for (i = 0; i < relocs64.count; i++) + write_reloc(relocs64.offset[i], stdout); } + + /* Print a stop */ + write_reloc(0, stdout); + + /* Now print each relocation */ + for (i = 0; i < relocs32.count; i++) + write_reloc(relocs32.offset[i], stdout); } } -static void usage(void) -{ - die("relocs [--abs-syms|--abs-relocs|--text|--realmode] vmlinux\n"); -} +#if ELF_BITS == 64 +# define process process_64 +#else +# define process process_32 +#endif -int main(int argc, char **argv) +void process(FILE *fp, int use_real_mode, int as_text, + int show_absolute_syms, int show_absolute_relocs) { - int show_absolute_syms, show_absolute_relocs; - int as_text, use_real_mode; - const char *fname; - FILE *fp; - int i; - - show_absolute_syms = 0; - show_absolute_relocs = 0; - as_text = 0; - use_real_mode = 0; - fname = NULL; - for (i = 1; i < argc; i++) { - char *arg = argv[i]; - if (*arg == '-') { - if (strcmp(arg, "--abs-syms") == 0) { - show_absolute_syms = 1; - continue; - } - if (strcmp(arg, "--abs-relocs") == 0) { - show_absolute_relocs = 1; - continue; - } - if (strcmp(arg, "--text") == 0) { - as_text = 1; - continue; - } - if (strcmp(arg, "--realmode") == 0) { - use_real_mode = 1; - continue; - } - } - else if (!fname) { - fname = arg; - continue; - } - usage(); - } - if (!fname) { - usage(); - } regex_init(use_real_mode); - fp = fopen(fname, "r"); - if (!fp) { - die("Cannot open %s: %s\n", - fname, strerror(errno)); - } read_ehdr(fp); read_shdrs(fp); read_strtabs(fp); read_symtabs(fp); read_relocs(fp); + if (ELF_BITS == 64) + percpu_init(); if (show_absolute_syms) { print_absolute_symbols(); - goto out; + return; } if (show_absolute_relocs) { print_absolute_relocs(); - goto out; + return; } emit_relocs(as_text, use_real_mode); -out: - fclose(fp); - return 0; } diff --git a/arch/x86/tools/relocs.h b/arch/x86/tools/relocs.h new file mode 100644 index 0000000..07cdb1e --- /dev/null +++ b/arch/x86/tools/relocs.h @@ -0,0 +1,36 @@ +#ifndef RELOCS_H +#define RELOCS_H + +#include <stdio.h> +#include <stdarg.h> +#include <stdlib.h> +#include <stdint.h> +#include <inttypes.h> +#include <string.h> +#include <errno.h> +#include <unistd.h> +#include <elf.h> +#include <byteswap.h> +#define USE_BSD +#include <endian.h> +#include <regex.h> +#include <tools/le_byteshift.h> + +void die(char *fmt, ...); + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +enum symtype { + S_ABS, + S_REL, + S_SEG, + S_LIN, + S_NSYMTYPES +}; + +void process_32(FILE *fp, int use_real_mode, int as_text, + int show_absolute_syms, int show_absolute_relocs); +void process_64(FILE *fp, int use_real_mode, int as_text, + int show_absolute_syms, int show_absolute_relocs); + +#endif /* RELOCS_H */ diff --git a/arch/x86/tools/relocs_32.c b/arch/x86/tools/relocs_32.c new file mode 100644 index 0000000..b2ade2b --- /dev/null +++ b/arch/x86/tools/relocs_32.c @@ -0,0 +1,17 @@ +#include "relocs.h" + +#define ELF_BITS 32 + +#define ELF_MACHINE EM_386 +#define ELF_MACHINE_NAME "i386" +#define SHT_REL_TYPE SHT_REL +#define Elf_Rel ElfW(Rel) + +#define ELF_CLASS ELFCLASS32 +#define ELF_R_SYM(val) ELF32_R_SYM(val) +#define ELF_R_TYPE(val) ELF32_R_TYPE(val) +#define ELF_ST_TYPE(o) ELF32_ST_TYPE(o) +#define ELF_ST_BIND(o) ELF32_ST_BIND(o) +#define ELF_ST_VISIBILITY(o) ELF32_ST_VISIBILITY(o) + +#include "relocs.c" diff --git a/arch/x86/tools/relocs_64.c b/arch/x86/tools/relocs_64.c new file mode 100644 index 0000000..56b61b7 --- /dev/null +++ b/arch/x86/tools/relocs_64.c @@ -0,0 +1,17 @@ +#include "relocs.h" + +#define ELF_BITS 64 + +#define ELF_MACHINE EM_X86_64 +#define ELF_MACHINE_NAME "x86_64" +#define SHT_REL_TYPE SHT_RELA +#define Elf_Rel Elf64_Rela + +#define ELF_CLASS ELFCLASS64 +#define ELF_R_SYM(val) ELF64_R_SYM(val) +#define ELF_R_TYPE(val) ELF64_R_TYPE(val) +#define ELF_ST_TYPE(o) ELF64_ST_TYPE(o) +#define ELF_ST_BIND(o) ELF64_ST_BIND(o) +#define ELF_ST_VISIBILITY(o) ELF64_ST_VISIBILITY(o) + +#include "relocs.c" diff --git a/arch/x86/tools/relocs_common.c b/arch/x86/tools/relocs_common.c new file mode 100644 index 0000000..44d3968 --- /dev/null +++ b/arch/x86/tools/relocs_common.c @@ -0,0 +1,76 @@ +#include "relocs.h" + +void die(char *fmt, ...) +{ + va_list ap; + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + exit(1); +} + +static void usage(void) +{ + die("relocs [--abs-syms|--abs-relocs|--text|--realmode] vmlinux\n"); +} + +int main(int argc, char **argv) +{ + int show_absolute_syms, show_absolute_relocs; + int as_text, use_real_mode; + const char *fname; + FILE *fp; + int i; + unsigned char e_ident[EI_NIDENT]; + + show_absolute_syms = 0; + show_absolute_relocs = 0; + as_text = 0; + use_real_mode = 0; + fname = NULL; + for (i = 1; i < argc; i++) { + char *arg = argv[i]; + if (*arg == '-') { + if (strcmp(arg, "--abs-syms") == 0) { + show_absolute_syms = 1; + continue; + } + if (strcmp(arg, "--abs-relocs") == 0) { + show_absolute_relocs = 1; + continue; + } + if (strcmp(arg, "--text") == 0) { + as_text = 1; + continue; + } + if (strcmp(arg, "--realmode") == 0) { + use_real_mode = 1; + continue; + } + } + else if (!fname) { + fname = arg; + continue; + } + usage(); + } + if (!fname) { + usage(); + } + fp = fopen(fname, "r"); + if (!fp) { + die("Cannot open %s: %s\n", fname, strerror(errno)); + } + if (fread(&e_ident, 1, EI_NIDENT, fp) != EI_NIDENT) { + die("Cannot read %s: %s", fname, strerror(errno)); + } + rewind(fp); + if (e_ident[EI_CLASS] == ELFCLASS64) + process_64(fp, use_real_mode, as_text, + show_absolute_syms, show_absolute_relocs); + else + process_32(fp, use_real_mode, as_text, + show_absolute_syms, show_absolute_relocs); + fclose(fp); + return 0; +} diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 131dacd..1a3c765 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -4,7 +4,7 @@ config XEN bool "Xen guest support" - select PARAVIRT + depends on PARAVIRT select PARAVIRT_CLOCK select XEN_HAVE_PVMMU depends on X86_64 || (X86_32 && X86_PAE && !X86_VISWS) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c8e1c7b..53d4f68 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -31,6 +31,7 @@ #include <linux/pci.h> #include <linux/gfp.h> #include <linux/memblock.h> +#include <linux/edd.h> #include <xen/xen.h> #include <xen/events.h> @@ -1220,7 +1221,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .alloc_ldt = xen_alloc_ldt, .free_ldt = xen_free_ldt, - .store_gdt = native_store_gdt, .store_idt = native_store_idt, .store_tr = xen_store_tr, @@ -1306,6 +1306,55 @@ static const struct machine_ops xen_machine_ops __initconst = { .emergency_restart = xen_emergency_restart, }; +static void __init xen_boot_params_init_edd(void) +{ +#if IS_ENABLED(CONFIG_EDD) + struct xen_platform_op op; + struct edd_info *edd_info; + u32 *mbr_signature; + unsigned nr; + int ret; + + edd_info = boot_params.eddbuf; + mbr_signature = boot_params.edd_mbr_sig_buffer; + + op.cmd = XENPF_firmware_info; + + op.u.firmware_info.type = XEN_FW_DISK_INFO; + for (nr = 0; nr < EDDMAXNR; nr++) { + struct edd_info *info = edd_info + nr; + + op.u.firmware_info.index = nr; + info->params.length = sizeof(info->params); + set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params, + &info->params); + ret = HYPERVISOR_dom0_op(&op); + if (ret) + break; + +#define C(x) info->x = op.u.firmware_info.u.disk_info.x + C(device); + C(version); + C(interface_support); + C(legacy_max_cylinder); + C(legacy_max_head); + C(legacy_sectors_per_track); +#undef C + } + boot_params.eddbuf_entries = nr; + + op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE; + for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) { + op.u.firmware_info.index = nr; + ret = HYPERVISOR_dom0_op(&op); + if (ret) + break; + mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature; + } + boot_params.edd_mbr_sig_buf_entries = nr; +#endif +} + /* * Set up the GDT and segment registers for -fstack-protector. Until * we do this, we have to be careful not to call any stack-protected @@ -1508,6 +1557,8 @@ asmlinkage void __init xen_start_kernel(void) /* Avoid searching for BIOS MP tables */ x86_init.mpparse.find_smp_config = x86_init_noop; x86_init.mpparse.get_smp_config = x86_init_uint_noop; + + xen_boot_params_init_edd(); } #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ @@ -1589,8 +1640,11 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self, switch (action) { case CPU_UP_PREPARE: xen_vcpu_setup(cpu); - if (xen_have_vector_callback) + if (xen_have_vector_callback) { xen_init_lock_cpu(cpu); + if (xen_feature(XENFEAT_hvm_safe_pvclock)) + xen_setup_timer(cpu); + } break; default: break; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index e006c18..fdc3ba2 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -2043,9 +2043,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) switch (idx) { case FIX_BTMAP_END ... FIX_BTMAP_BEGIN: -#ifdef CONFIG_X86_F00F_BUG - case FIX_F00F_IDT: -#endif + case FIX_RO_IDT: #ifdef CONFIG_X86_32 case FIX_WP_TEST: case FIX_VDSO: diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 09ea61d..8ff3799 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -95,7 +95,7 @@ static void __cpuinit cpu_bringup(void) static void __cpuinit cpu_bringup_and_idle(void) { cpu_bringup(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } static int xen_smp_intr_init(unsigned int cpu) @@ -144,6 +144,13 @@ static int xen_smp_intr_init(unsigned int cpu) goto fail; per_cpu(xen_callfuncsingle_irq, cpu) = rc; + /* + * The IRQ worker on PVHVM goes through the native path and uses the + * IPI mechanism. + */ + if (xen_hvm_domain()) + return 0; + callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu); rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR, cpu, @@ -167,6 +174,9 @@ static int xen_smp_intr_init(unsigned int cpu) if (per_cpu(xen_callfuncsingle_irq, cpu) >= 0) unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL); + if (xen_hvm_domain()) + return rc; + if (per_cpu(xen_irq_work, cpu) >= 0) unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); @@ -418,7 +428,7 @@ static int xen_cpu_disable(void) static void xen_cpu_die(unsigned int cpu) { - while (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) { + while (xen_pv_domain() && HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) { current->state = TASK_UNINTERRUPTIBLE; schedule_timeout(HZ/10); } @@ -426,7 +436,8 @@ static void xen_cpu_die(unsigned int cpu) unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL); unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL); unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); + if (!xen_hvm_domain()) + unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); xen_uninit_lock_cpu(cpu); xen_teardown_timer(cpu); } @@ -657,11 +668,7 @@ static int __cpuinit xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle) static void xen_hvm_cpu_die(unsigned int cpu) { - unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); + xen_cpu_die(cpu); native_cpu_die(cpu); } diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index f7a080e..8b54603 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -364,6 +364,16 @@ void __cpuinit xen_init_lock_cpu(int cpu) int irq; const char *name; + WARN(per_cpu(lock_kicker_irq, cpu) > 0, "spinlock on CPU%d exists on IRQ%d!\n", + cpu, per_cpu(lock_kicker_irq, cpu)); + + /* + * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23 + * (xen: disable PV spinlocks on HVM) + */ + if (xen_hvm_domain()) + return; + name = kasprintf(GFP_KERNEL, "spinlock%d", cpu); irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR, cpu, @@ -382,11 +392,26 @@ void __cpuinit xen_init_lock_cpu(int cpu) void xen_uninit_lock_cpu(int cpu) { + /* + * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23 + * (xen: disable PV spinlocks on HVM) + */ + if (xen_hvm_domain()) + return; + unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL); + per_cpu(lock_kicker_irq, cpu) = -1; } void __init xen_init_spinlocks(void) { + /* + * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23 + * (xen: disable PV spinlocks on HVM) + */ + if (xen_hvm_domain()) + return; + BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t)); pv_lock_ops.spin_is_locked = xen_spin_is_locked; diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 0296a95..3d88bfd 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -377,7 +377,7 @@ static const struct clock_event_device xen_vcpuop_clockevent = { static const struct clock_event_device *xen_clockevent = &xen_timerop_clockevent; -static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events); +static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events) = { .irq = -1 }; static irqreturn_t xen_timer_interrupt(int irq, void *dev_id) { @@ -401,6 +401,9 @@ void xen_setup_timer(int cpu) struct clock_event_device *evt; int irq; + evt = &per_cpu(xen_clock_events, cpu); + WARN(evt->irq >= 0, "IRQ%d for CPU%d is already allocated\n", evt->irq, cpu); + printk(KERN_INFO "installing Xen timer for CPU %d\n", cpu); name = kasprintf(GFP_KERNEL, "timer%d", cpu); @@ -413,7 +416,6 @@ void xen_setup_timer(int cpu) IRQF_FORCE_RESUME, name, NULL); - evt = &per_cpu(xen_clock_events, cpu); memcpy(evt, xen_clockevent, sizeof(*evt)); evt->cpumask = cpumask_of(cpu); @@ -426,6 +428,7 @@ void xen_teardown_timer(int cpu) BUG_ON(cpu == 0); evt = &per_cpu(xen_clock_events, cpu); unbind_from_irqhandler(evt->irq, NULL); + evt->irq = -1; } void xen_setup_cpu_clockevents(void) @@ -497,7 +500,11 @@ static void xen_hvm_setup_cpu_clockevents(void) { int cpu = smp_processor_id(); xen_setup_runstate_info(cpu); - xen_setup_timer(cpu); + /* + * xen_setup_timer(cpu) - snprintf is bad in atomic context. Hence + * doing it xen_hvm_cpu_notify (which gets called by smp_init during + * early bootup and also during CPU hotplug events). + */ xen_setup_cpu_clockevents(); } diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 5cd82e9..1c85323 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -105,19 +105,9 @@ void coprocessor_flush_all(struct thread_info *ti) /* * Powermanagement idle function, if any is provided by the platform. */ - -void cpu_idle(void) +void arch_cpu_idle(void) { - local_irq_enable(); - - /* endless idle loop with no priority at all */ - while (1) { - rcu_idle_enter(); - while (!need_resched()) - platform_idle(); - rcu_idle_exit(); - schedule_preempt_disabled(); - } + platform_idle(); } /* diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 7a5156f..bba125b 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -208,32 +208,17 @@ void __init mem_init(void) highmemsize >> 10); } -void -free_reserved_mem(void *start, void *end) -{ - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page((unsigned long)start); - totalram_pages++; - } -} - #ifdef CONFIG_BLK_DEV_INITRD extern int initrd_is_mapped; void free_initrd_mem(unsigned long start, unsigned long end) { - if (initrd_is_mapped) { - free_reserved_mem((void*)start, (void*)end); - printk ("Freeing initrd memory: %ldk freed\n",(end-start)>>10); - } + if (initrd_is_mapped) + free_reserved_area(start, end, 0, "initrd"); } #endif void free_initmem(void) { - free_reserved_mem(__init_begin, __init_end); - printk("Freeing unused kernel memory: %zuk freed\n", - (__init_end - __init_begin) >> 10); + free_initmem_default(0); } |