diff options
Diffstat (limited to 'arch')
131 files changed, 1121 insertions, 838 deletions
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 9bef61b30367..8290b69da202 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -549,6 +549,11 @@ config NUMA Access). This option is for configuring high-end multiprocessor server machines. If in doubt, say N. +config NODES_SHIFT + int + default "7" + depends on NEED_MULTIPLE_NODES + # LARGE_VMALLOC is racy, if you *really* need it then fix it first config ALPHA_LARGE_VMALLOC bool diff --git a/arch/alpha/kernel/alpha_ksyms.c b/arch/alpha/kernel/alpha_ksyms.c index 9d6186d50245..c645c5e14786 100644 --- a/arch/alpha/kernel/alpha_ksyms.c +++ b/arch/alpha/kernel/alpha_ksyms.c @@ -76,7 +76,6 @@ EXPORT_SYMBOL(strncpy); EXPORT_SYMBOL(strnlen); EXPORT_SYMBOL(strncat); EXPORT_SYMBOL(strstr); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strchr); EXPORT_SYMBOL(strrchr); EXPORT_SYMBOL(memcmp); diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index a15e18a00258..558b83368559 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -24,6 +24,7 @@ #include <linux/config.h> /* CONFIG_ALPHA_LCA etc */ #include <linux/mc146818rtc.h> #include <linux/console.h> +#include <linux/cpu.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/string.h> @@ -471,6 +472,22 @@ page_is_ram(unsigned long pfn) return 0; } +static int __init +register_cpus(void) +{ + int i; + + for_each_possible_cpu(i) { + struct cpu *p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + register_cpu(p, i, NULL); + } + return 0; +} + +arch_initcall(register_cpus); + void __init setup_arch(char **cmdline_p) { diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 02c2db08114a..185255416e85 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -439,7 +439,7 @@ setup_smp(void) if ((cpu->flags & 0x1cc) == 0x1cc) { smp_num_probed++; /* Assume here that "whami" == index */ - cpu_set(i, cpu_possible_map); + cpu_set(i, cpu_present_mask); cpu->pal_revision = boot_cpu_palrev; } @@ -450,9 +450,8 @@ setup_smp(void) } } else { smp_num_probed = 1; - cpu_set(boot_cpuid, cpu_possible_map); + cpu_set(boot_cpuid, cpu_present_mask); } - cpu_present_mask = cpumask_of_cpu(boot_cpuid); printk(KERN_INFO "SMP: %d CPUs probed -- cpu_present_mask = %lx\n", smp_num_probed, cpu_possible_map.bits[0]); @@ -488,9 +487,8 @@ void __devinit smp_prepare_boot_cpu(void) { /* - * Mark the boot cpu (current cpu) as both present and online + * Mark the boot cpu (current cpu) as online */ - cpu_set(smp_processor_id(), cpu_present_mask); cpu_set(smp_processor_id(), cpu_online_map); } diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index dc5a9332c915..1dbf6ddb300d 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -512,6 +512,12 @@ config ARCH_DISCONTIGMEM_ENABLE or have huge holes in the physical address space for other reasons. See <file:Documentation/vm/numa> for more. +config NODES_SHIFT + int + default "4" if ARCH_LH7A40X + default "2" + depends on NEED_MULTIPLE_NODES + source "mm/Kconfig" config LEDS diff --git a/arch/arm/boot/compressed/vmlinux.lds.in b/arch/arm/boot/compressed/vmlinux.lds.in index eed616113e47..153a07e7222b 100644 --- a/arch/arm/boot/compressed/vmlinux.lds.in +++ b/arch/arm/boot/compressed/vmlinux.lds.in @@ -18,6 +18,7 @@ SECTIONS _start = .; *(.start) *(.text) + *(.text.*) *(.fixup) *(.gnu.warning) *(.rodata) diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index ee083b3f0522..c49b5d4d7fca 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -101,7 +101,6 @@ EXPORT_SYMBOL(__raw_writesl); /* string / mem functions */ EXPORT_SYMBOL(strchr); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strrchr); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 437528403959..8cff73e668b3 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -322,6 +322,12 @@ static void __init setup_processor(void) sprintf(system_utsname.machine, "%s%c", list->arch_name, ENDIANNESS); sprintf(elf_platform, "%s%c", list->elf_name, ENDIANNESS); elf_hwcap = list->elf_hwcap; +#ifndef CONFIG_ARM_THUMB + elf_hwcap &= ~HWCAP_THUMB; +#endif +#ifndef CONFIG_VFP + elf_hwcap &= ~HWCAP_VFP; +#endif cpu_proc_init(); } diff --git a/arch/arm/mach-omap1/devices.c b/arch/arm/mach-omap1/devices.c index 876c38da14f7..847329cafc5c 100644 --- a/arch/arm/mach-omap1/devices.c +++ b/arch/arm/mach-omap1/devices.c @@ -25,10 +25,6 @@ #include <asm/arch/mux.h> #include <asm/arch/gpio.h> -extern void omap_nop_release(struct device *dev); - -/*-------------------------------------------------------------------------*/ - #if defined(CONFIG_OMAP1610_IR) || defined(CONFIG_OMAP161O_IR_MODULE) static u64 irda_dmamask = 0xffffffff; @@ -37,7 +33,6 @@ static struct platform_device omap1610ir_device = { .name = "omap1610-ir", .id = -1, .dev = { - .release = omap_nop_release, .dma_mask = &irda_dmamask, }, }; @@ -84,9 +79,6 @@ static struct resource rtc_resources[] = { static struct platform_device omap_rtc_device = { .name = "omap_rtc", .id = -1, - .dev = { - .release = omap_nop_release, - }, .num_resources = ARRAY_SIZE(rtc_resources), .resource = rtc_resources, }; @@ -124,9 +116,6 @@ static struct resource sti_resources[] = { static struct platform_device sti_device = { .name = "sti", .id = -1, - .dev = { - .release = omap_nop_release, - }, .num_resources = ARRAY_SIZE(sti_resources), .resource = sti_resources, }; diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c index def9e5370edf..fb7f91da1aad 100644 --- a/arch/arm/mach-omap2/devices.c +++ b/arch/arm/mach-omap2/devices.c @@ -25,10 +25,6 @@ #include <asm/arch/mux.h> #include <asm/arch/gpio.h> -extern void omap_nop_release(struct device *dev); - -/*-------------------------------------------------------------------------*/ - #if defined(CONFIG_I2C_OMAP) || defined(CONFIG_I2C_OMAP_MODULE) #define OMAP2_I2C_BASE2 0x48072000 @@ -49,9 +45,6 @@ static struct resource i2c_resources2[] = { static struct platform_device omap_i2c_device2 = { .name = "i2c_omap", .id = 2, - .dev = { - .release = omap_nop_release, - }, .num_resources = ARRAY_SIZE(i2c_resources2), .resource = i2c_resources2, }; @@ -100,9 +93,6 @@ static struct resource sti_resources[] = { static struct platform_device sti_device = { .name = "sti", .id = -1, - .dev = { - .release = omap_nop_release, - }, .num_resources = ARRAY_SIZE(sti_resources), .resource = sti_resources, }; diff --git a/arch/arm/mach-s3c2410/clock.c b/arch/arm/mach-s3c2410/clock.c index b7f85e6d6b76..6de713ad319a 100644 --- a/arch/arm/mach-s3c2410/clock.c +++ b/arch/arm/mach-s3c2410/clock.c @@ -367,6 +367,8 @@ static int s3c24xx_clkout_setparent(struct clk *clk, struct clk *parent) source = S3C2410_MISCCR_CLK0_UPLL; else if (parent == &clk_f) source = S3C2410_MISCCR_CLK0_FCLK; + else if (parent == &clk_h) + source = S3C2410_MISCCR_CLK0_HCLK; else if (parent == &clk_p) source = S3C2410_MISCCR_CLK0_PCLK; else if (clk == &s3c24xx_clkout0 && parent == &s3c24xx_dclk0) @@ -376,6 +378,8 @@ static int s3c24xx_clkout_setparent(struct clk *clk, struct clk *parent) else return -EINVAL; + clk->parent = parent; + if (clk == &s3c24xx_dclk0) mask = S3C2410_MISCCR_CLK0_MASK; else { diff --git a/arch/arm/mach-s3c2410/common-smdk.c b/arch/arm/mach-s3c2410/common-smdk.c index 36b8291b5e03..f372fbda124e 100644 --- a/arch/arm/mach-s3c2410/common-smdk.c +++ b/arch/arm/mach-s3c2410/common-smdk.c @@ -37,6 +37,7 @@ #include <asm/arch/nand.h> +#include "common-smdk.h" #include "devs.h" #include "pm.h" diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S index 5c4055b62d97..54e3c5bb5186 100644 --- a/arch/arm/mm/cache-v4wb.S +++ b/arch/arm/mm/cache-v4wb.S @@ -10,7 +10,7 @@ #include <linux/config.h> #include <linux/linkage.h> #include <linux/init.h> -#include <asm/hardware.h> +#include <asm/memory.h> #include <asm/page.h> #include "proc-macros.S" @@ -46,6 +46,11 @@ */ #define CACHE_DLIMIT (CACHE_DSIZE * 4) + .data +flush_base: + .long FLUSH_BASE + .text + /* * flush_user_cache_all() * @@ -63,11 +68,21 @@ ENTRY(v4wb_flush_kern_cache_all) mov ip, #0 mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache __flush_whole_cache: - mov r0, #FLUSH_BASE - add r1, r0, #CACHE_DSIZE -1: ldr r2, [r0], #32 - cmp r0, r1 + ldr r3, =flush_base + ldr r1, [r3, #0] + eor r1, r1, #CACHE_DSIZE + str r1, [r3, #0] + add r2, r1, #CACHE_DSIZE +1: ldr r3, [r1], #32 + cmp r1, r2 + blo 1b +#ifdef FLUSH_BASE_MINICACHE + add r2, r2, #FLUSH_BASE_MINICACHE - FLUSH_BASE + sub r1, r2, #512 @ only 512 bytes +1: ldr r3, [r1], #32 + cmp r1, r2 blo 1b +#endif mcr p15, 0, ip, c7, c10, 4 @ drain write buffer mov pc, lr @@ -82,6 +97,7 @@ __flush_whole_cache: * - flags - vma_area_struct flags describing address space */ ENTRY(v4wb_flush_user_cache_range) + mov ip, #0 sub r3, r1, r0 @ calculate total size tst r2, #VM_EXEC @ executable region? mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 88279124317a..9ea1f87a7079 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -20,6 +20,7 @@ #include <asm/mach-types.h> #include <asm/setup.h> +#include <asm/sizes.h> #include <asm/tlb.h> #include <asm/mach/arch.h> @@ -455,14 +456,14 @@ static void __init devicemaps_init(struct machine_desc *mdesc) #ifdef FLUSH_BASE map.pfn = __phys_to_pfn(FLUSH_BASE_PHYS); map.virtual = FLUSH_BASE; - map.length = PGDIR_SIZE; + map.length = SZ_1M; map.type = MT_CACHECLEAN; create_mapping(&map); #endif #ifdef FLUSH_BASE_MINICACHE - map.pfn = __phys_to_pfn(FLUSH_BASE_PHYS + PGDIR_SIZE); + map.pfn = __phys_to_pfn(FLUSH_BASE_PHYS + SZ_1M); map.virtual = FLUSH_BASE_MINICACHE; - map.length = PGDIR_SIZE; + map.length = SZ_1M; map.type = MT_MINICLEAN; create_mapping(&map); #endif diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S index c916a6cae404..a2dd5ae1077d 100644 --- a/arch/arm/mm/proc-sa110.S +++ b/arch/arm/mm/proc-sa110.S @@ -26,22 +26,7 @@ * the cache line size of the I and D cache */ #define DCACHELINESIZE 32 -#define FLUSH_OFFSET 32768 - .macro flush_110_dcache rd, ra, re - ldr \rd, =flush_base - ldr \ra, [\rd] - eor \ra, \ra, #FLUSH_OFFSET - str \ra, [\rd] - add \re, \ra, #16384 @ only necessary for 16k -1001: ldr \rd, [\ra], #DCACHELINESIZE - teq \re, \ra - bne 1001b - .endm - - .data -flush_base: - .long FLUSH_BASE .text /* @@ -145,13 +130,11 @@ ENTRY(cpu_sa110_dcache_clean_area) */ .align 5 ENTRY(cpu_sa110_switch_mm) - flush_110_dcache r3, ip, r1 - mov r1, #0 - mcr p15, 0, r1, c7, c5, 0 @ invalidate I cache - mcr p15, 0, r1, c7, c10, 4 @ drain WB + str lr, [sp, #-4]! + bl v4wb_flush_kern_cache_all @ clears IP mcr p15, 0, r0, c2, c0, 0 @ load page table pointer - mcr p15, 0, r1, c8, c7, 0 @ invalidate I & D TLBs - mov pc, lr + mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs + ldr pc, [sp], #4 /* * cpu_sa110_set_pte(ptep, pte) diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 41f21f2dd8ff..777ad99c1439 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -30,30 +30,6 @@ * the cache line size of the I and D cache */ #define DCACHELINESIZE 32 -#define FLUSH_OFFSET 32768 - - .macro flush_1100_dcache rd, ra, re - ldr \rd, =flush_base - ldr \ra, [\rd] - eor \ra, \ra, #FLUSH_OFFSET - str \ra, [\rd] - add \re, \ra, #8192 @ only necessary for 8k -1001: ldr \rd, [\ra], #DCACHELINESIZE - teq \re, \ra - bne 1001b -#ifdef FLUSH_BASE_MINICACHE - add \ra, \ra, #FLUSH_BASE_MINICACHE - FLUSH_BASE - add \re, \ra, #512 @ only 512 bytes -1002: ldr \rd, [\ra], #DCACHELINESIZE - teq \re, \ra - bne 1002b -#endif - .endm - - .data -flush_base: - .long FLUSH_BASE - .text __INIT @@ -79,9 +55,8 @@ ENTRY(cpu_sa1100_proc_fin) stmfd sp!, {lr} mov ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE msr cpsr_c, ip - flush_1100_dcache r0, r1, r2 @ clean caches - mov r0, #0 - mcr p15, 0, r0, c15, c2, 2 @ Disable clock switching + bl v4wb_flush_kern_cache_all + mcr p15, 0, ip, c15, c2, 2 @ Disable clock switching mrc p15, 0, r0, c1, c0, 0 @ ctrl register bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. @@ -167,14 +142,12 @@ ENTRY(cpu_sa1100_dcache_clean_area) */ .align 5 ENTRY(cpu_sa1100_switch_mm) - flush_1100_dcache r3, ip, r1 - mov ip, #0 - mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache + str lr, [sp, #-4]! + bl v4wb_flush_kern_cache_all @ clears IP mcr p15, 0, ip, c9, c0, 0 @ invalidate RB - mcr p15, 0, ip, c7, c10, 4 @ drain WB mcr p15, 0, r0, c2, c0, 0 @ load page table pointer mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs - mov pc, lr + ldr pc, [sp], #4 /* * cpu_sa1100_set_pte(ptep, pte) diff --git a/arch/arm/plat-omap/clock.c b/arch/arm/plat-omap/clock.c index 06485c193ee3..32ec04c58bcd 100644 --- a/arch/arm/plat-omap/clock.c +++ b/arch/arm/plat-omap/clock.c @@ -58,7 +58,7 @@ struct clk * clk_get(struct device *dev, const char *id) if (p->id == idno && strcmp(id, p->name) == 0 && try_module_get(p->owner)) { clk = p; - break; + goto found; } } @@ -69,6 +69,7 @@ struct clk * clk_get(struct device *dev, const char *id) } } +found: mutex_unlock(&clocks_mutex); return clk; diff --git a/arch/arm/plat-omap/devices.c b/arch/arm/plat-omap/devices.c index 079b67deac0f..5d5d6eb222dd 100644 --- a/arch/arm/plat-omap/devices.c +++ b/arch/arm/plat-omap/devices.c @@ -26,14 +26,6 @@ #include <asm/arch/gpio.h> #include <asm/arch/menelaus.h> - -void omap_nop_release(struct device *dev) -{ - /* Nothing */ -} - -/*-------------------------------------------------------------------------*/ - #if defined(CONFIG_I2C_OMAP) || defined(CONFIG_I2C_OMAP_MODULE) #define OMAP1_I2C_BASE 0xfffb3800 @@ -59,9 +51,6 @@ static struct resource i2c_resources1[] = { static struct platform_device omap_i2c_device1 = { .name = "i2c_omap", .id = 1, - .dev = { - .release = omap_nop_release, - }, .num_resources = ARRAY_SIZE(i2c_resources1), .resource = i2c_resources1, }; @@ -187,7 +176,6 @@ static struct platform_device mmc_omap_device1 = { .name = "mmci-omap", .id = 1, .dev = { - .release = omap_nop_release, .dma_mask = &mmc1_dmamask, .platform_data = &mmc1_conf, }, @@ -217,7 +205,6 @@ static struct platform_device mmc_omap_device2 = { .name = "mmci-omap", .id = 2, .dev = { - .release = omap_nop_release, .dma_mask = &mmc2_dmamask, .platform_data = &mmc2_conf, }, @@ -321,9 +308,6 @@ static struct resource uwire_resources[] = { static struct platform_device omap_uwire_device = { .name = "omap_uwire", .id = -1, - .dev = { - .release = omap_nop_release, - }, .num_resources = ARRAY_SIZE(uwire_resources), .resource = uwire_resources, }; @@ -365,9 +349,6 @@ static struct resource wdt_resources[] = { static struct platform_device omap_wdt_device = { .name = "omap_wdt", .id = -1, - .dev = { - .release = omap_nop_release, - }, .num_resources = ARRAY_SIZE(wdt_resources), .resource = wdt_resources, }; @@ -401,9 +382,6 @@ static struct resource rng_resources[] = { static struct platform_device omap_rng_device = { .name = "omap_rng", .id = -1, - .dev = { - .release = omap_nop_release, - }, .num_resources = ARRAY_SIZE(rng_resources), .resource = rng_resources, }; diff --git a/arch/arm/vfp/vfpdouble.c b/arch/arm/vfp/vfpdouble.c index 9b367a65cb4d..febd115dba28 100644 --- a/arch/arm/vfp/vfpdouble.c +++ b/arch/arm/vfp/vfpdouble.c @@ -588,6 +588,7 @@ static u32 vfp_double_ftosi(int sd, int unused, int dm, u32 fpscr) struct vfp_double vdm; u32 d, exceptions = 0; int rmode = fpscr & FPSCR_RMODE_MASK; + int tm; vfp_double_unpack(&vdm, vfp_get_double(dm)); vfp_double_dump("VDM", &vdm); @@ -595,10 +596,14 @@ static u32 vfp_double_ftosi(int sd, int unused, int dm, u32 fpscr) /* * Do we have denormalised number? */ - if (vfp_double_type(&vdm) & VFP_DENORMAL) + tm = vfp_double_type(&vdm); + if (tm & VFP_DENORMAL) exceptions |= FPSCR_IDC; - if (vdm.exponent >= 1023 + 32) { + if (tm & VFP_NAN) { + d = 0; + exceptions |= FPSCR_IOC; + } else if (vdm.exponent >= 1023 + 32) { d = 0x7fffffff; if (vdm.sign) d = ~d; @@ -1122,9 +1127,9 @@ u32 vfp_double_cpdo(u32 inst, u32 fpscr) { u32 op = inst & FOP_MASK; u32 exceptions = 0; - unsigned int dd = vfp_get_sd(inst); - unsigned int dn = vfp_get_sn(inst); - unsigned int dm = vfp_get_sm(inst); + unsigned int dd = vfp_get_dd(inst); + unsigned int dn = vfp_get_dn(inst); + unsigned int dm = vfp_get_dm(inst); unsigned int vecitr, veclen, vecstride; u32 (*fop)(int, int, s32, u32); @@ -1141,7 +1146,7 @@ u32 vfp_double_cpdo(u32 inst, u32 fpscr) pr_debug("VFP: vecstride=%u veclen=%u\n", vecstride, (veclen >> FPSCR_LENGTH_BIT) + 1); - fop = (op == FOP_EXT) ? fop_extfns[dn] : fop_fns[FOP_TO_IDX(op)]; + fop = (op == FOP_EXT) ? fop_extfns[FEXT_TO_IDX(inst)] : fop_fns[FOP_TO_IDX(op)]; if (!fop) goto invalid; @@ -1149,17 +1154,13 @@ u32 vfp_double_cpdo(u32 inst, u32 fpscr) u32 except; if (op == FOP_EXT) - pr_debug("VFP: itr%d (d%u.%u) = op[%u] (d%u.%u)\n", + pr_debug("VFP: itr%d (d%u) = op[%u] (d%u)\n", vecitr >> FPSCR_LENGTH_BIT, - dd >> 1, dd & 1, dn, - dm >> 1, dm & 1); + dd, dn, dm); else - pr_debug("VFP: itr%d (d%u.%u) = (d%u.%u) op[%u] (d%u.%u)\n", + pr_debug("VFP: itr%d (d%u) = (d%u) op[%u] (d%u)\n", vecitr >> FPSCR_LENGTH_BIT, - dd >> 1, dd & 1, - dn >> 1, dn & 1, - FOP_TO_IDX(op), - dm >> 1, dm & 1); + dd, dn, FOP_TO_IDX(op), dm); except = fop(dd, dn, dm, fpscr); pr_debug("VFP: itr%d: exceptions=%08x\n", diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S index b7ed57e00cd4..a3f65b47aea9 100644 --- a/arch/arm/vfp/vfphw.S +++ b/arch/arm/vfp/vfphw.S @@ -189,11 +189,10 @@ vfp_put_float: .globl vfp_get_double vfp_get_double: - mov r0, r0, lsr #1 add pc, pc, r0, lsl #3 mov r0, r0 .irp dr,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 - mrrc p10, 1, r0, r1, c\dr @ fmrrd r0, r1, d\dr + mrrc p11, 1, r0, r1, c\dr @ fmrrd r0, r1, d\dr mov pc, lr .endr @@ -204,10 +203,9 @@ vfp_get_double: .globl vfp_put_double vfp_put_double: - mov r0, r0, lsr #1 add pc, pc, r0, lsl #3 mov r0, r0 .irp dr,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 - mcrr p10, 1, r1, r2, c\dr @ fmrrd r1, r2, d\dr + mcrr p11, 1, r1, r2, c\dr @ fmdrr r1, r2, d\dr mov pc, lr .endr diff --git a/arch/arm/vfp/vfpsingle.c b/arch/arm/vfp/vfpsingle.c index 14dd696ddeb1..4ac27f193934 100644 --- a/arch/arm/vfp/vfpsingle.c +++ b/arch/arm/vfp/vfpsingle.c @@ -632,6 +632,7 @@ static u32 vfp_single_ftosi(int sd, int unused, s32 m, u32 fpscr) struct vfp_single vsm; u32 d, exceptions = 0; int rmode = fpscr & FPSCR_RMODE_MASK; + int tm; vfp_single_unpack(&vsm, m); vfp_single_dump("VSM", &vsm); @@ -639,10 +640,14 @@ static u32 vfp_single_ftosi(int sd, int unused, s32 m, u32 fpscr) /* * Do we have a denormalised number? */ + tm = vfp_single_type(&vsm); if (vfp_single_type(&vsm) & VFP_DENORMAL) exceptions |= FPSCR_IDC; - if (vsm.exponent >= 127 + 32) { + if (tm & VFP_NAN) { + d = 0; + exceptions |= FPSCR_IOC; + } else if (vsm.exponent >= 127 + 32) { /* * m >= 2^31-2^7: invalid */ @@ -1188,7 +1193,7 @@ u32 vfp_single_cpdo(u32 inst, u32 fpscr) pr_debug("VFP: vecstride=%u veclen=%u\n", vecstride, (veclen >> FPSCR_LENGTH_BIT) + 1); - fop = (op == FOP_EXT) ? fop_extfns[sn] : fop_fns[FOP_TO_IDX(op)]; + fop = (op == FOP_EXT) ? fop_extfns[FEXT_TO_IDX(inst)] : fop_fns[FOP_TO_IDX(op)]; if (!fop) goto invalid; diff --git a/arch/arm26/kernel/armksyms.c b/arch/arm26/kernel/armksyms.c index a6a1b3373444..9d66c27f2724 100644 --- a/arch/arm26/kernel/armksyms.c +++ b/arch/arm26/kernel/armksyms.c @@ -152,7 +152,6 @@ EXPORT_SYMBOL(strncmp); EXPORT_SYMBOL(strchr); EXPORT_SYMBOL(strlen); EXPORT_SYMBOL(strnlen); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strrchr); EXPORT_SYMBOL(strstr); EXPORT_SYMBOL(memset); diff --git a/arch/cris/kernel/crisksyms.c b/arch/cris/kernel/crisksyms.c index de39725da920..d57859053ce7 100644 --- a/arch/cris/kernel/crisksyms.c +++ b/arch/cris/kernel/crisksyms.c @@ -39,7 +39,6 @@ EXPORT_SYMBOL(loops_per_usec); /* String functions */ EXPORT_SYMBOL(memcmp); EXPORT_SYMBOL(memmove); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strstr); EXPORT_SYMBOL(strcpy); EXPORT_SYMBOL(strchr); diff --git a/arch/frv/kernel/entry.S b/arch/frv/kernel/entry.S index 1d21c8d34d8a..a9b59527a741 100644 --- a/arch/frv/kernel/entry.S +++ b/arch/frv/kernel/entry.S @@ -1170,12 +1170,6 @@ __syscall_badsys: # syscall vector table # ############################################################################### -#ifdef CONFIG_MMU -#define __MMU(X) X -#else -#define __MMU(X) sys_ni_syscall -#endif - .section .rodata ALIGN .globl sys_call_table @@ -1305,7 +1299,7 @@ sys_call_table: .long sys_newuname .long sys_ni_syscall /* old "cacheflush" */ .long sys_adjtimex - .long __MMU(sys_mprotect) /* 125 */ + .long sys_mprotect /* 125 */ .long sys_sigprocmask .long sys_ni_syscall /* old "create_module" */ .long sys_init_module @@ -1324,16 +1318,16 @@ sys_call_table: .long sys_getdents .long sys_select .long sys_flock - .long __MMU(sys_msync) + .long sys_msync .long sys_readv /* 145 */ .long sys_writev .long sys_getsid .long sys_fdatasync .long sys_sysctl - .long __MMU(sys_mlock) /* 150 */ - .long __MMU(sys_munlock) - .long __MMU(sys_mlockall) - .long __MMU(sys_munlockall) + .long sys_mlock /* 150 */ + .long sys_munlock + .long sys_mlockall + .long sys_munlockall .long sys_sched_setparam .long sys_sched_getparam /* 155 */ .long sys_sched_setscheduler @@ -1343,7 +1337,7 @@ sys_call_table: .long sys_sched_get_priority_min /* 160 */ .long sys_sched_rr_get_interval .long sys_nanosleep - .long __MMU(sys_mremap) + .long sys_mremap .long sys_setresuid16 .long sys_getresuid16 /* 165 */ .long sys_ni_syscall /* for vm86 */ @@ -1398,8 +1392,8 @@ sys_call_table: .long sys_setfsuid /* 215 */ .long sys_setfsgid .long sys_pivot_root - .long __MMU(sys_mincore) - .long __MMU(sys_madvise) + .long sys_mincore + .long sys_madvise .long sys_getdents64 /* 220 */ .long sys_fcntl64 .long sys_ni_syscall /* reserved for TUX */ @@ -1437,7 +1431,7 @@ sys_call_table: .long sys_epoll_create .long sys_epoll_ctl /* 255 */ .long sys_epoll_wait - .long __MMU(sys_remap_file_pages) + .long sys_remap_file_pages .long sys_set_tid_address .long sys_timer_create .long sys_timer_settime /* 260 */ diff --git a/arch/frv/kernel/frv_ksyms.c b/arch/frv/kernel/frv_ksyms.c index 07c8ffa0dd39..0f273a7aca5a 100644 --- a/arch/frv/kernel/frv_ksyms.c +++ b/arch/frv/kernel/frv_ksyms.c @@ -27,7 +27,6 @@ EXPORT_SYMBOL(__ioremap); EXPORT_SYMBOL(iounmap); EXPORT_SYMBOL(strnlen); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strrchr); EXPORT_SYMBOL(strstr); EXPORT_SYMBOL(strchr); diff --git a/arch/h8300/kernel/h8300_ksyms.c b/arch/h8300/kernel/h8300_ksyms.c index b6cd78c972bb..f8d6dee84781 100644 --- a/arch/h8300/kernel/h8300_ksyms.c +++ b/arch/h8300/kernel/h8300_ksyms.c @@ -25,7 +25,6 @@ extern char h8300_debug_device[]; /* platform dependent support */ EXPORT_SYMBOL(strnlen); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strrchr); EXPORT_SYMBOL(strstr); EXPORT_SYMBOL(strchr); diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index f17bd1d2707e..18ec9fe6deb6 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -53,6 +53,35 @@ source "init/Kconfig" menu "Processor type and features" +config SMP + bool "Symmetric multi-processing support" + ---help--- + This enables support for systems with more than one CPU. If you have + a system with only one CPU, like most personal computers, say N. If + you have a system with more than one CPU, say Y. + + If you say N here, the kernel will run on single and multiprocessor + machines, but will use only one CPU of a multiprocessor machine. If + you say Y here, the kernel will run on many, but not all, + singleprocessor machines. On a singleprocessor machine, the kernel + will run faster if you say N here. + + Note that if you say Y here and choose architecture "586" or + "Pentium" under "Processor family", the kernel will not work on 486 + architectures. Similarly, multiprocessor kernels for the "PPro" + architecture may not work on all Pentium based boards. + + People using multiprocessor machines who say Y here should also say + Y to "Enhanced Real Time Clock Support", below. The "Advanced Power + Management" code will be disabled if you say Y here. + + See also the <file:Documentation/smp.txt>, + <file:Documentation/i386/IO-APIC.txt>, + <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at + <http://www.tldp.org/docs.html#howto>. + + If you don't know what to do here, say N. + choice prompt "Subarchitecture Type" default X86_PC @@ -178,35 +207,6 @@ config HPET_EMULATE_RTC depends on HPET_TIMER && RTC=y default y -config SMP - bool "Symmetric multi-processing support" - ---help--- - This enables support for systems with more than one CPU. If you have - a system with only one CPU, like most personal computers, say N. If - you have a system with more than one CPU, say Y. - - If you say N here, the kernel will run on single and multiprocessor - machines, but will use only one CPU of a multiprocessor machine. If - you say Y here, the kernel will run on many, but not all, - singleprocessor machines. On a singleprocessor machine, the kernel - will run faster if you say N here. - - Note that if you say Y here and choose architecture "586" or - "Pentium" under "Processor family", the kernel will not work on 486 - architectures. Similarly, multiprocessor kernels for the "PPro" - architecture may not work on all Pentium based boards. - - People using multiprocessor machines who say Y here should also say - Y to "Enhanced Real Time Clock Support", below. The "Advanced Power - Management" code will be disabled if you say Y here. - - See also the <file:Documentation/smp.txt>, - <file:Documentation/i386/IO-APIC.txt>, - <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at - <http://www.tldp.org/docs.html#howto>. - - If you don't know what to do here, say N. - config NR_CPUS int "Maximum number of CPUs (2-255)" range 2 255 @@ -522,6 +522,12 @@ config NUMA comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI" depends on X86_SUMMIT && (!HIGHMEM64G || !ACPI) +config NODES_SHIFT + int + default "4" if X86_NUMAQ + default "3" + depends on NEED_MULTIPLE_NODES + config HAVE_ARCH_BOOTMEM_NODE bool depends on NUMA @@ -757,15 +763,6 @@ config HOTPLUG_CPU Say N. -config DOUBLEFAULT - default y - bool "Enable doublefault exception handler" if EMBEDDED - help - This option allows trapping of rare doublefault exceptions that - would otherwise cause a system to silently reboot. Disabling this - option saves about 4k and might cause you much additional grey - hair. - endmenu diff --git a/arch/i386/Kconfig.cpu b/arch/i386/Kconfig.cpu index 79603b3471f9..eb130482ba18 100644 --- a/arch/i386/Kconfig.cpu +++ b/arch/i386/Kconfig.cpu @@ -311,5 +311,5 @@ config X86_OOSTORE config X86_TSC bool - depends on (MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MGEODEGX1) && !X86_NUMAQ + depends on (MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MGEODEGX1 || MGEODE_LX) && !X86_NUMAQ default y diff --git a/arch/i386/boot/video.S b/arch/i386/boot/video.S index 0000a2674537..c9343c3a8082 100644 --- a/arch/i386/boot/video.S +++ b/arch/i386/boot/video.S @@ -97,6 +97,7 @@ #define PARAM_VESAPM_OFF 0x30 #define PARAM_LFB_PAGES 0x32 #define PARAM_VESA_ATTRIB 0x34 +#define PARAM_CAPABILITIES 0x36 /* Define DO_STORE according to CONFIG_VIDEO_RETAIN */ #ifdef CONFIG_VIDEO_RETAIN @@ -233,6 +234,10 @@ mopar_gr: movw 18(%di), %ax movl %eax, %fs:(PARAM_LFB_SIZE) +# store mode capabilities + movl 10(%di), %eax + movl %eax, %fs:(PARAM_CAPABILITIES) + # switching the DAC to 8-bit is for <= 8 bpp only movw %fs:(PARAM_LFB_DEPTH), %ax cmpw $8, %ax diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index 033066176b3e..030a0007a4e0 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -168,7 +168,7 @@ int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size) unsigned long i; int config_size; - if (!phys_addr || !size) + if (!phys_addr || !size || !cpu_has_apic) return -EINVAL; mcfg = (struct acpi_table_mcfg *)__acpi_map_table(phys_addr, size); @@ -215,7 +215,7 @@ static int __init acpi_parse_madt(unsigned long phys_addr, unsigned long size) { struct acpi_table_madt *madt = NULL; - if (!phys_addr || !size) + if (!phys_addr || !size || !cpu_has_apic) return -EINVAL; madt = (struct acpi_table_madt *)__acpi_map_table(phys_addr, size); @@ -693,6 +693,9 @@ static int __init acpi_parse_madt_lapic_entries(void) { int count; + if (!cpu_has_apic) + return -ENODEV; + /* * Note that the LAPIC address is obtained from the MADT (32-bit value) * and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value). @@ -751,6 +754,9 @@ static int __init acpi_parse_madt_ioapic_entries(void) return -ENODEV; } + if (!cpu_has_apic) + return -ENODEV; + /* * if "noapic" boot option, don't look for IO-APICs */ diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index 6273bf74c203..254cee9f0b7b 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -62,6 +62,18 @@ int apic_verbosity; static void apic_pm_activate(void); +int modern_apic(void) +{ + unsigned int lvr, version; + /* AMD systems use old APIC versions, so check the CPU */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD && + boot_cpu_data.x86 >= 0xf) + return 1; + lvr = apic_read(APIC_LVR); + version = GET_APIC_VERSION(lvr); + return version >= 0x14; +} + /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -119,10 +131,7 @@ void enable_NMI_through_LVT0 (void * dummy) int get_physical_broadcast(void) { - unsigned int lvr, version; - lvr = apic_read(APIC_LVR); - version = GET_APIC_VERSION(lvr); - if (!APIC_INTEGRATED(version) || version >= 0x14) + if (modern_apic()) return 0xff; else return 0xf; @@ -349,9 +358,9 @@ int __init verify_local_APIC(void) void __init sync_Arb_IDs(void) { - /* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 */ - unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR)); - if (ver >= 0x14) /* P4 or higher */ + /* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 + And not needed on AMD */ + if (modern_apic()) return; /* * Wait for idle. diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c index 0810f81f2a05..ff2b2154ac1b 100644 --- a/arch/i386/kernel/cpu/amd.c +++ b/arch/i386/kernel/cpu/amd.c @@ -212,8 +212,6 @@ static void __init init_amd(struct cpuinfo_x86 *c) if (cpuid_eax(0x80000000) >= 0x80000008) { c->x86_max_cores = (cpuid_ecx(0x80000008) & 0xff) + 1; - if (c->x86_max_cores & (c->x86_max_cores - 1)) - c->x86_max_cores = 1; } if (cpuid_eax(0x80000000) >= 0x80000007) { diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c index 712a26bd4457..7c0e160a2145 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c @@ -46,7 +46,7 @@ #define PFX "powernow-k8: " #define BFX PFX "BIOS error: " -#define VERSION "version 1.60.1" +#define VERSION "version 1.60.2" #include "powernow-k8.h" /* serialize freq changes */ @@ -55,7 +55,7 @@ static DEFINE_MUTEX(fidvid_mutex); static struct powernow_k8_data *powernow_data[NR_CPUS]; #ifndef CONFIG_SMP -static cpumask_t cpu_core_map[1] = { CPU_MASK_ALL }; +static cpumask_t cpu_core_map[1]; #endif /* Return a frequency in MHz, given an input fid */ @@ -910,6 +910,9 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi unsigned int newstate; int ret = -EIO; + if (!data) + return -EINVAL; + /* only run on specific CPU from here on */ oldmask = current->cpus_allowed; set_cpus_allowed(current, cpumask_of_cpu(pol->cpu)); @@ -969,6 +972,9 @@ static int powernowk8_verify(struct cpufreq_policy *pol) { struct powernow_k8_data *data = powernow_data[pol->cpu]; + if (!data) + return -EINVAL; + return cpufreq_frequency_table_verify(pol, data->powernow_table); } @@ -977,7 +983,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) { struct powernow_k8_data *data; cpumask_t oldmask = CPU_MASK_ALL; - int rc, i; + int rc; if (!cpu_online(pol->cpu)) return -ENODEV; @@ -1063,8 +1069,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) printk("cpu_init done, current fid 0x%x, vid 0x%x\n", data->currfid, data->currvid); - for_each_cpu_mask(i, cpu_core_map[pol->cpu]) - powernow_data[i] = data; + powernow_data[pol->cpu] = data; return 0; @@ -1104,6 +1109,9 @@ static unsigned int powernowk8_get (unsigned int cpu) if (!data) return -EINVAL; + if (!data) + return -EINVAL; + set_cpus_allowed(current, cpumask_of_cpu(cpu)); if (smp_processor_id() != cpu) { printk(KERN_ERR PFX "limiting to CPU %d failed in powernowk8_get\n", cpu); diff --git a/arch/i386/kernel/i386_ksyms.c b/arch/i386/kernel/i386_ksyms.c index 055325056a74..036a9857936f 100644 --- a/arch/i386/kernel/i386_ksyms.c +++ b/arch/i386/kernel/i386_ksyms.c @@ -19,7 +19,6 @@ EXPORT_SYMBOL(__put_user_2); EXPORT_SYMBOL(__put_user_4); EXPORT_SYMBOL(__put_user_8); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strstr); #ifdef CONFIG_SMP diff --git a/arch/i386/kernel/mpparse.c b/arch/i386/kernel/mpparse.c index 8d8aa9d1796d..34d21e21e012 100644 --- a/arch/i386/kernel/mpparse.c +++ b/arch/i386/kernel/mpparse.c @@ -38,12 +38,6 @@ int smp_found_config; unsigned int __initdata maxcpus = NR_CPUS; -#ifdef CONFIG_HOTPLUG_CPU -#define CPU_HOTPLUG_ENABLED (1) -#else -#define CPU_HOTPLUG_ENABLED (0) -#endif - /* * Various Linux-internal data structures created from the * MP-table. @@ -110,21 +104,6 @@ static int __init mpf_checksum(unsigned char *mp, int len) static int mpc_record; static struct mpc_config_translation *translation_table[MAX_MPC_ENTRY] __initdata; -#ifdef CONFIG_X86_NUMAQ -static int MP_valid_apicid(int apicid, int version) -{ - return hweight_long(apicid & 0xf) == 1 && (apicid >> 4) != 0xf; -} -#else -static int MP_valid_apicid(int apicid, int version) -{ - if (version >= 0x14) - return apicid < 0xff; - else - return apicid < 0xf; -} -#endif - static void __devinit MP_processor_info (struct mpc_config_processor *m) { int ver, apicid; @@ -190,12 +169,6 @@ static void __devinit MP_processor_info (struct mpc_config_processor *m) ver = m->mpc_apicver; - if (!MP_valid_apicid(apicid, ver)) { - printk(KERN_WARNING "Processor #%d INVALID. (Max ID: %d).\n", - m->mpc_apicid, MAX_APICS); - return; - } - /* * Validate version */ @@ -225,7 +198,14 @@ static void __devinit MP_processor_info (struct mpc_config_processor *m) cpu_set(num_processors, cpu_possible_map); num_processors++; - if (CPU_HOTPLUG_ENABLED || (num_processors > 8)) { + /* + * Would be preferable to switch to bigsmp when CONFIG_HOTPLUG_CPU=y + * but we need to work other dependencies like SMP_SUSPEND etc + * before this can be done without some confusion. + * if (CPU_HOTPLUG_ENABLED || num_processors > 8) + * - Ashok Raj <ashok.raj@intel.com> + */ + if (num_processors > 8) { switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: if (!APIC_XAPIC(ver)) { @@ -249,6 +229,13 @@ static void __init MP_bus_info (struct mpc_config_bus *m) mpc_oem_bus_info(m, str, translation_table[mpc_record]); + if (m->mpc_busid >= MAX_MP_BUSSES) { + printk(KERN_WARNING "MP table busid value (%d) for bustype %s " + " is too large, max. supported is %d\n", + m->mpc_busid, str, MAX_MP_BUSSES - 1); + return; + } + if (strncmp(str, BUSTYPE_ISA, sizeof(BUSTYPE_ISA)-1) == 0) { mp_bus_id_to_type[m->mpc_busid] = MP_BUS_ISA; } else if (strncmp(str, BUSTYPE_EISA, sizeof(BUSTYPE_EISA)-1) == 0) { diff --git a/arch/i386/kernel/reboot_fixups.c b/arch/i386/kernel/reboot_fixups.c index 10e21a4773dd..99aab41a05b0 100644 --- a/arch/i386/kernel/reboot_fixups.c +++ b/arch/i386/kernel/reboot_fixups.c @@ -51,7 +51,5 @@ void mach_reboot_fixups(void) cur->reboot_fixup(dev); } - - printk(KERN_WARNING "No reboot fixup found for your hardware\n"); } diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index eacc3f0a2ea4..80cb3b2d0997 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -963,6 +963,36 @@ efi_memory_present_wrapper(unsigned long start, unsigned long end, void *arg) return 0; } + /* + * This function checks if the entire range <start,end> is mapped with type. + * + * Note: this function only works correct if the e820 table is sorted and + * not-overlapping, which is the case + */ +int __init +e820_all_mapped(unsigned long start, unsigned long end, unsigned type) +{ + int i; + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + if (type && ei->type != type) + continue; + /* is the region (part) in overlap with the current region ?*/ + if (ei->addr >= end || ei->addr + ei->size <= start) + continue; + /* if the region is at the beginning of <start,end> we move + * start to the end of the region since it's ok until there + */ + if (ei->addr <= start) + start = ei->addr + ei->size; + /* if start is now at or beyond end, we're done, full + * coverage */ + if (start >= end) + return 1; /* we're done */ + } + return 0; +} + /* * Find the highest page frame number we have available */ @@ -1317,8 +1347,8 @@ legacy_init_iomem_resources(struct resource *code_resource, struct resource *dat /* * Request address space for all standard resources * - * This is called just before pcibios_assign_resources(), which is also - * an fs_initcall, but is linked in later (in arch/i386/pci/i386.c). + * This is called just before pcibios_init(), which is also a + * subsys_initcall, but is linked in later (in arch/i386/pci/common.c). */ static int __init request_standard_resources(void) { @@ -1339,7 +1369,7 @@ static int __init request_standard_resources(void) return 0; } -fs_initcall(request_standard_resources); +subsys_initcall(request_standard_resources); static void __init register_memory(void) { diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index e38527994590..2d22f5761b1d 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -365,6 +365,9 @@ void die(const char * str, struct pt_regs * regs, long err) if (++die.lock_owner_depth < 3) { int nl = 0; + unsigned long esp; + unsigned short ss; + handle_BUG(regs); printk(KERN_EMERG "%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter); #ifdef CONFIG_PREEMPT @@ -387,8 +390,19 @@ void die(const char * str, struct pt_regs * regs, long err) printk("\n"); if (notify_die(DIE_OOPS, str, regs, err, current->thread.trap_no, SIGSEGV) != - NOTIFY_STOP) + NOTIFY_STOP) { show_registers(regs); + /* Executive summary in case the oops scrolled away */ + esp = (unsigned long) (®s->esp); + savesegment(ss, ss); + if (user_mode(regs)) { + esp = regs->esp; + ss = regs->xss & 0xffff; + } + printk(KERN_EMERG "EIP: [<%08lx>] ", regs->eip); + print_symbol("%s", regs->eip); + printk(" SS:ESP %04x:%08lx\n", ss, esp); + } else regs = NULL; } else diff --git a/arch/i386/mach-voyager/voyager_cat.c b/arch/i386/mach-voyager/voyager_cat.c index 23967fe658d3..3039539de51e 100644 --- a/arch/i386/mach-voyager/voyager_cat.c +++ b/arch/i386/mach-voyager/voyager_cat.c @@ -106,9 +106,15 @@ voyager_module_t *voyager_cat_list; /* the I/O port assignments for the VIC and QIC */ static struct resource vic_res = { - "Voyager Interrupt Controller", 0xFC00, 0xFC6F }; + .name = "Voyager Interrupt Controller", + .start = 0xFC00, + .end = 0xFC6F +}; static struct resource qic_res = { - "Quad Interrupt Controller", 0xFC70, 0xFCFF }; + .name = "Quad Interrupt Controller", + .start = 0xFC70, + .end = 0xFCFF +}; /* This function is used to pack a data bit stream inside a message. * It writes num_bits of the data buffer in msg starting at start_bit. diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c index 9f66ac582a8b..ae6534ad8161 100644 --- a/arch/i386/mm/init.c +++ b/arch/i386/mm/init.c @@ -651,6 +651,7 @@ void __init mem_init(void) * Specifically, in the case of x86, we will always add * memory to the highmem for now. */ +#ifdef CONFIG_HOTPLUG_MEMORY #ifndef CONFIG_NEED_MULTIPLE_NODES int add_memory(u64 start, u64 size) { @@ -667,6 +668,7 @@ int remove_memory(u64 start, u64 size) return -EINVAL; } #endif +#endif kmem_cache_t *pgd_cache; kmem_cache_t *pmd_cache; diff --git a/arch/i386/pci/direct.c b/arch/i386/pci/direct.c index 99012b93bd12..5d81fb510375 100644 --- a/arch/i386/pci/direct.c +++ b/arch/i386/pci/direct.c @@ -4,6 +4,7 @@ #include <linux/pci.h> #include <linux/init.h> +#include <linux/dmi.h> #include "pci.h" /* @@ -18,8 +19,10 @@ int pci_conf1_read(unsigned int seg, unsigned int bus, { unsigned long flags; - if (!value || (bus > 255) || (devfn > 255) || (reg > 255)) + if ((bus > 255) || (devfn > 255) || (reg > 255)) { + *value = -1; return -EINVAL; + } spin_lock_irqsave(&pci_config_lock, flags); @@ -91,8 +94,10 @@ static int pci_conf2_read(unsigned int seg, unsigned int bus, unsigned long flags; int dev, fn; - if (!value || (bus > 255) || (devfn > 255) || (reg > 255)) + if ((bus > 255) || (devfn > 255) || (reg > 255)) { + *value = -1; return -EINVAL; + } dev = PCI_SLOT(devfn); fn = PCI_FUNC(devfn); @@ -188,6 +193,10 @@ static int __init pci_sanity_check(struct pci_raw_ops *o) if (pci_probe & PCI_NO_CHECKS) return 1; + /* Assume Type 1 works for newer systems. + This handles machines that don't have anything on PCI Bus 0. */ + if (dmi_get_year(DMI_BIOS_DATE) >= 2001) + return 1; for (devfn = 0; devfn < 0x100; devfn++) { if (o->read(0, 0, devfn, PCI_CLASS_DEVICE, 2, &x)) diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c index 613789071f30..6b1ea0c9a570 100644 --- a/arch/i386/pci/mmconfig.c +++ b/arch/i386/pci/mmconfig.c @@ -12,14 +12,20 @@ #include <linux/pci.h> #include <linux/init.h> #include <linux/acpi.h> +#include <asm/e820.h> #include "pci.h" +#define MMCONFIG_APER_SIZE (256*1024*1024) + +/* Assume systems with more busses have correct MCFG */ +#define MAX_CHECK_BUS 16 + #define mmcfg_virt_addr ((void __iomem *) fix_to_virt(FIX_PCIE_MCFG)) /* The base address of the last MMCONFIG device accessed */ static u32 mmcfg_last_accessed_device; -static DECLARE_BITMAP(fallback_slots, 32); +static DECLARE_BITMAP(fallback_slots, MAX_CHECK_BUS*32); /* * Functions for accessing PCI configuration space with MMCONFIG accesses @@ -29,8 +35,8 @@ static u32 get_base_addr(unsigned int seg, int bus, unsigned devfn) int cfg_num = -1; struct acpi_table_mcfg_config *cfg; - if (seg == 0 && bus == 0 && - test_bit(PCI_SLOT(devfn), fallback_slots)) + if (seg == 0 && bus < MAX_CHECK_BUS && + test_bit(PCI_SLOT(devfn) + 32*bus, fallback_slots)) return 0; while (1) { @@ -74,8 +80,10 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus, unsigned long flags; u32 base; - if (!value || (bus > 255) || (devfn > 255) || (reg > 4095)) + if ((bus > 255) || (devfn > 255) || (reg > 4095)) { + *value = -1; return -EINVAL; + } base = get_base_addr(seg, bus, devfn); if (!base) @@ -146,29 +154,34 @@ static struct pci_raw_ops pci_mmcfg = { Normally this can be expressed in the MCFG by not listing them and assigning suitable _SEGs, but this isn't implemented in some BIOS. Instead try to discover all devices on bus 0 that are unreachable using MM - and fallback for them. - We only do this for bus 0/seg 0 */ + and fallback for them. */ static __init void unreachable_devices(void) { - int i; + int i, k; unsigned long flags; - for (i = 0; i < 32; i++) { - u32 val1; - u32 addr; - - pci_conf1_read(0, 0, PCI_DEVFN(i, 0), 0, 4, &val1); - if (val1 == 0xffffffff) - continue; - - /* Locking probably not needed, but safer */ - spin_lock_irqsave(&pci_config_lock, flags); - addr = get_base_addr(0, 0, PCI_DEVFN(i, 0)); - if (addr != 0) - pci_exp_set_dev_base(addr, 0, PCI_DEVFN(i, 0)); - if (addr == 0 || readl((u32 __iomem *)mmcfg_virt_addr) != val1) - set_bit(i, fallback_slots); - spin_unlock_irqrestore(&pci_config_lock, flags); + for (k = 0; k < MAX_CHECK_BUS; k++) { + for (i = 0; i < 32; i++) { + u32 val1; + u32 addr; + + pci_conf1_read(0, k, PCI_DEVFN(i, 0), 0, 4, &val1); + if (val1 == 0xffffffff) + continue; + + /* Locking probably not needed, but safer */ + spin_lock_irqsave(&pci_config_lock, flags); + addr = get_base_addr(0, k, PCI_DEVFN(i, 0)); + if (addr != 0) + pci_exp_set_dev_base(addr, k, PCI_DEVFN(i, 0)); + if (addr == 0 || + readl((u32 __iomem *)mmcfg_virt_addr) != val1) { + set_bit(i, fallback_slots); + printk(KERN_NOTICE + "PCI: No mmconfig possible on %x:%x\n", k, i); + } + spin_unlock_irqrestore(&pci_config_lock, flags); + } } } @@ -183,6 +196,14 @@ void __init pci_mmcfg_init(void) (pci_mmcfg_config[0].base_address == 0)) return; + if (!e820_all_mapped(pci_mmcfg_config[0].base_address, + pci_mmcfg_config[0].base_address + MMCONFIG_APER_SIZE, + E820_RESERVED)) { + printk(KERN_ERR "PCI: BIOS Bug: MCFG area is not E820-reserved\n"); + printk(KERN_ERR "PCI: Not using MMCONFIG.\n"); + return; + } + printk(KERN_INFO "PCI: Using MMCONFIG\n"); raw_pci_ops = &pci_mmcfg; pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF; diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index edffe25a477a..9f40eeff0b5c 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -260,15 +260,6 @@ config NR_CPUS than 64 will cause the use of a CPU mask array, causing a small performance hit. -config IA64_NR_NODES - int "Maximum number of NODEs (256-1024)" if (IA64_SGI_SN2 || IA64_GENERIC) - range 256 1024 - depends on IA64_SGI_SN2 || IA64_GENERIC - default "256" - help - This option specifies the maximum number of nodes in your SSI system. - If in doubt, use the default. - config HOTPLUG_CPU bool "Support for hot-pluggable CPUs (EXPERIMENTAL)" depends on SMP && EXPERIMENTAL @@ -352,6 +343,16 @@ config NUMA Access). This option is for configuring high-end multiprocessor server systems. If in doubt, say N. +config NODES_SHIFT + int "Max num nodes shift(3-10)" + range 3 10 + default "8" + depends on NEED_MULTIPLE_NODES + help + This option specifies the maximum number of nodes in your SSI system. + MAX_NUMNODES will be 2^(This value). + If in doubt, use the default. + # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent. # VIRTUAL_MEM_MAP has been retained for historical reasons. config VIRTUAL_MEM_MAP diff --git a/arch/ia64/kernel/acpi-ext.c b/arch/ia64/kernel/acpi-ext.c index 4a5574ff007b..fff82929d225 100644 --- a/arch/ia64/kernel/acpi-ext.c +++ b/arch/ia64/kernel/acpi-ext.c @@ -1,105 +1,104 @@ /* - * arch/ia64/kernel/acpi-ext.c + * (c) Copyright 2003, 2006 Hewlett-Packard Development Company, L.P. + * Alex Williamson <alex.williamson@hp.com> + * Bjorn Helgaas <bjorn.helgaas@hp.com> * - * Copyright (C) 2003 Hewlett-Packard - * Copyright (C) Alex Williamson - * Copyright (C) Bjorn Helgaas - * - * Vendor specific extensions to ACPI. + * 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/config.h> #include <linux/module.h> #include <linux/types.h> #include <linux/acpi.h> -#include <linux/efi.h> #include <asm/acpi-ext.h> -struct acpi_vendor_descriptor { - u8 guid_id; - efi_guid_t guid; -}; +/* + * Device CSRs that do not appear in PCI config space should be described + * via ACPI. This would normally be done with Address Space Descriptors + * marked as "consumer-only," but old versions of Windows and Linux ignore + * the producer/consumer flag, so HP invented a vendor-defined resource to + * describe the location and size of CSR space. + */ -struct acpi_vendor_info { - struct acpi_vendor_descriptor *descriptor; - u8 *data; - u32 length; +struct acpi_vendor_uuid hp_ccsr_uuid = { + .subtype = 2, + .data = { 0xf9, 0xad, 0xe9, 0x69, 0x4f, 0x92, 0x5f, 0xab, 0xf6, 0x4a, + 0x24, 0xd2, 0x01, 0x37, 0x0e, 0xad }, }; -acpi_status -acpi_vendor_resource_match(struct acpi_resource *resource, void *context) +static acpi_status hp_ccsr_locate(acpi_handle obj, u64 *base, u64 *length) { - struct acpi_vendor_info *info = (struct acpi_vendor_info *)context; - struct acpi_resource_vendor *vendor; - struct acpi_vendor_descriptor *descriptor; - u32 byte_length; - - if (resource->type != ACPI_RESOURCE_TYPE_VENDOR) - return AE_OK; - - vendor = (struct acpi_resource_vendor *)&resource->data; - descriptor = (struct acpi_vendor_descriptor *)vendor->byte_data; - if (vendor->byte_length <= sizeof(*info->descriptor) || - descriptor->guid_id != info->descriptor->guid_id || - efi_guidcmp(descriptor->guid, info->descriptor->guid)) - return AE_OK; - - byte_length = vendor->byte_length - sizeof(struct acpi_vendor_descriptor); - info->data = acpi_os_allocate(byte_length); - if (!info->data) - return AE_NO_MEMORY; - - memcpy(info->data, - vendor->byte_data + sizeof(struct acpi_vendor_descriptor), - byte_length); - info->length = byte_length; - return AE_CTRL_TERMINATE; -} + acpi_status status; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + struct acpi_resource *resource; + struct acpi_resource_vendor_typed *vendor; -acpi_status -acpi_find_vendor_resource(acpi_handle obj, struct acpi_vendor_descriptor * id, - u8 ** data, u32 * byte_length) -{ - struct acpi_vendor_info info; + status = acpi_get_vendor_resource(obj, METHOD_NAME__CRS, &hp_ccsr_uuid, + &buffer); - info.descriptor = id; - info.data = NULL; + resource = buffer.pointer; + vendor = &resource->data.vendor_typed; - acpi_walk_resources(obj, METHOD_NAME__CRS, acpi_vendor_resource_match, - &info); - if (!info.data) - return AE_NOT_FOUND; + if (ACPI_FAILURE(status) || vendor->byte_length < 16) { + status = AE_NOT_FOUND; + goto exit; + } - *data = info.data; - *byte_length = info.length; - return AE_OK; + memcpy(base, vendor->byte_data, sizeof(*base)); + memcpy(length, vendor->byte_data + 8, sizeof(*length)); + + exit: + acpi_os_free(buffer.pointer); + return status; } -struct acpi_vendor_descriptor hp_ccsr_descriptor = { - .guid_id = 2, - .guid = - EFI_GUID(0x69e9adf9, 0x924f, 0xab5f, 0xf6, 0x4a, 0x24, 0xd2, 0x01, - 0x37, 0x0e, 0xad) +struct csr_space { + u64 base; + u64 length; }; -acpi_status hp_acpi_csr_space(acpi_handle obj, u64 * csr_base, u64 * csr_length) +static acpi_status find_csr_space(struct acpi_resource *resource, void *data) { + struct csr_space *space = data; + struct acpi_resource_address64 addr; acpi_status status; - u8 *data; - u32 length; - status = - acpi_find_vendor_resource(obj, &hp_ccsr_descriptor, &data, &length); + status = acpi_resource_to_address64(resource, &addr); + if (ACPI_SUCCESS(status) && + addr.resource_type == ACPI_MEMORY_RANGE && + addr.address_length && + addr.producer_consumer == ACPI_CONSUMER) { + space->base = addr.minimum; + space->length = addr.address_length; + return AE_CTRL_TERMINATE; + } + return AE_OK; /* keep looking */ +} - if (ACPI_FAILURE(status) || length != 16) - return AE_NOT_FOUND; +static acpi_status hp_crs_locate(acpi_handle obj, u64 *base, u64 *length) +{ + struct csr_space space = { 0, 0 }; - memcpy(csr_base, data, sizeof(*csr_base)); - memcpy(csr_length, data + 8, sizeof(*csr_length)); - acpi_os_free(data); + acpi_walk_resources(obj, METHOD_NAME__CRS, find_csr_space, &space); + if (!space.length) + return AE_NOT_FOUND; + *base = space.base; + *length = space.length; return AE_OK; } +acpi_status hp_acpi_csr_space(acpi_handle obj, u64 *csr_base, u64 *csr_length) +{ + acpi_status status; + + status = hp_ccsr_locate(obj, csr_base, csr_length); + if (ACPI_SUCCESS(status)) + return status; + + return hp_crs_locate(obj, csr_base, csr_length); +} EXPORT_SYMBOL(hp_acpi_csr_space); diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index 750e8e7fbdc3..6e16f6b35bd3 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1606,5 +1606,8 @@ sys_call_table: data8 sys_ni_syscall // 1295 reserved for ppoll data8 sys_unshare data8 sys_splice + data8 sys_set_robust_list + data8 sys_get_robust_list + data8 sys_sync_file_range // 1300 .org sys_call_table + 8*NR_syscalls // guard against failures to increase NR_syscalls diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 8963171788d5..5e6fdbe78bcd 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -581,10 +581,12 @@ ia64_mca_rendez_int_handler(int rendez_irq, void *arg, struct pt_regs *regs) { unsigned long flags; int cpu = smp_processor_id(); + struct ia64_mca_notify_die nd = + { .sos = NULL, .monarch_cpu = &monarch_cpu }; /* Mask all interrupts */ local_irq_save(flags); - if (notify_die(DIE_MCA_RENDZVOUS_ENTER, "MCA", regs, 0, 0, 0) + if (notify_die(DIE_MCA_RENDZVOUS_ENTER, "MCA", regs, (long)&nd, 0, 0) == NOTIFY_STOP) ia64_mca_spin(__FUNCTION__); @@ -594,7 +596,7 @@ ia64_mca_rendez_int_handler(int rendez_irq, void *arg, struct pt_regs *regs) */ ia64_sal_mc_rendez(); - if (notify_die(DIE_MCA_RENDZVOUS_PROCESS, "MCA", regs, 0, 0, 0) + if (notify_die(DIE_MCA_RENDZVOUS_PROCESS, "MCA", regs, (long)&nd, 0, 0) == NOTIFY_STOP) ia64_mca_spin(__FUNCTION__); @@ -602,7 +604,7 @@ ia64_mca_rendez_int_handler(int rendez_irq, void *arg, struct pt_regs *regs) while (monarch_cpu != -1) cpu_relax(); /* spin until monarch leaves */ - if (notify_die(DIE_MCA_RENDZVOUS_LEAVE, "MCA", regs, 0, 0, 0) + if (notify_die(DIE_MCA_RENDZVOUS_LEAVE, "MCA", regs, (long)&nd, 0, 0) == NOTIFY_STOP) ia64_mca_spin(__FUNCTION__); @@ -1023,6 +1025,8 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, &sos->proc_state_param; int recover, cpu = smp_processor_id(); task_t *previous_current; + struct ia64_mca_notify_die nd = + { .sos = sos, .monarch_cpu = &monarch_cpu }; oops_in_progress = 1; /* FIXME: make printk NMI/MCA/INIT safe */ console_loglevel = 15; /* make sure printks make it to console */ @@ -1031,7 +1035,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, previous_current = ia64_mca_modify_original_stack(regs, sw, sos, "MCA"); monarch_cpu = cpu; - if (notify_die(DIE_MCA_MONARCH_ENTER, "MCA", regs, 0, 0, 0) + if (notify_die(DIE_MCA_MONARCH_ENTER, "MCA", regs, (long)&nd, 0, 0) == NOTIFY_STOP) ia64_mca_spin(__FUNCTION__); ia64_wait_for_slaves(cpu); @@ -1043,7 +1047,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, * spinning in SAL does not work. */ ia64_mca_wakeup_all(); - if (notify_die(DIE_MCA_MONARCH_PROCESS, "MCA", regs, 0, 0, 0) + if (notify_die(DIE_MCA_MONARCH_PROCESS, "MCA", regs, (long)&nd, 0, 0) == NOTIFY_STOP) ia64_mca_spin(__FUNCTION__); @@ -1064,7 +1068,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, ia64_sal_clear_state_info(SAL_INFO_TYPE_MCA); sos->os_status = IA64_MCA_CORRECTED; } - if (notify_die(DIE_MCA_MONARCH_LEAVE, "MCA", regs, 0, 0, recover) + if (notify_die(DIE_MCA_MONARCH_LEAVE, "MCA", regs, (long)&nd, 0, recover) == NOTIFY_STOP) ia64_mca_spin(__FUNCTION__); @@ -1351,10 +1355,14 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw, static atomic_t monarchs; task_t *previous_current; int cpu = smp_processor_id(); + struct ia64_mca_notify_die nd = + { .sos = sos, .monarch_cpu = &monarch_cpu }; oops_in_progress = 1; /* FIXME: make printk NMI/MCA/INIT safe */ console_loglevel = 15; /* make sure printks make it to console */ + (void) notify_die(DIE_INIT_ENTER, "INIT", regs, (long)&nd, 0, 0); + printk(KERN_INFO "Entered OS INIT handler. PSP=%lx cpu=%d monarch=%ld\n", sos->proc_state_param, cpu, sos->monarch); salinfo_log_wakeup(SAL_INFO_TYPE_INIT, NULL, 0, 0); @@ -1390,15 +1398,15 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw, ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_INIT; while (monarch_cpu == -1) cpu_relax(); /* spin until monarch enters */ - if (notify_die(DIE_INIT_SLAVE_ENTER, "INIT", regs, 0, 0, 0) + if (notify_die(DIE_INIT_SLAVE_ENTER, "INIT", regs, (long)&nd, 0, 0) == NOTIFY_STOP) ia64_mca_spin(__FUNCTION__); - if (notify_die(DIE_INIT_SLAVE_PROCESS, "INIT", regs, 0, 0, 0) + if (notify_die(DIE_INIT_SLAVE_PROCESS, "INIT", regs, (long)&nd, 0, 0) == NOTIFY_STOP) ia64_mca_spin(__FUNCTION__); while (monarch_cpu != -1) cpu_relax(); /* spin until monarch leaves */ - if (notify_die(DIE_INIT_SLAVE_LEAVE, "INIT", regs, 0, 0, 0) + if (notify_die(DIE_INIT_SLAVE_LEAVE, "INIT", regs, (long)&nd, 0, 0) == NOTIFY_STOP) ia64_mca_spin(__FUNCTION__); printk("Slave on cpu %d returning to normal service.\n", cpu); @@ -1409,7 +1417,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw, } monarch_cpu = cpu; - if (notify_die(DIE_INIT_MONARCH_ENTER, "INIT", regs, 0, 0, 0) + if (notify_die(DIE_INIT_MONARCH_ENTER, "INIT", regs, (long)&nd, 0, 0) == NOTIFY_STOP) ia64_mca_spin(__FUNCTION__); @@ -1426,10 +1434,10 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw, * to default_monarch_init_process() above and just print all the * tasks. */ - if (notify_die(DIE_INIT_MONARCH_PROCESS, "INIT", regs, 0, 0, 0) + if (notify_die(DIE_INIT_MONARCH_PROCESS, "INIT", regs, (long)&nd, 0, 0) == NOTIFY_STOP) ia64_mca_spin(__FUNCTION__); - if (notify_die(DIE_INIT_MONARCH_LEAVE, "INIT", regs, 0, 0, 0) + if (notify_die(DIE_INIT_MONARCH_LEAVE, "INIT", regs, (long)&nd, 0, 0) == NOTIFY_STOP) ia64_mca_spin(__FUNCTION__); printk("\nINIT dump complete. Monarch on cpu %d returning to normal service.\n", cpu); @@ -1631,6 +1639,7 @@ ia64_mca_init(void) printk(KERN_INFO "Increasing MCA rendezvous timeout from " "%ld to %ld milliseconds\n", timeout, isrv.v0); timeout = isrv.v0; + (void) notify_die(DIE_MCA_NEW_TIMEOUT, "MCA", NULL, timeout, 0, 0); continue; } printk(KERN_ERR "Failed to register rendezvous interrupt " diff --git a/arch/ia64/kernel/mca_asm.S b/arch/ia64/kernel/mca_asm.S index 60a464bfd9e2..6dff024cd62b 100644 --- a/arch/ia64/kernel/mca_asm.S +++ b/arch/ia64/kernel/mca_asm.S @@ -827,7 +827,7 @@ ia64_state_restore: ld8 r9=[temp2],16 // sal_gp ;; ld8 r22=[temp1],16 // pal_min_state, virtual - ld8 r21=[temp2],16 // prev_IA64_KR_CURRENT + ld8 r13=[temp2],16 // prev_IA64_KR_CURRENT ;; ld8 r16=[temp1],16 // prev_IA64_KR_CURRENT_STACK ld8 r20=[temp2],16 // prev_task @@ -848,7 +848,7 @@ ia64_state_restore: mov cr.iim=temp3 mov cr.iha=temp4 dep r22=0,r22,62,1 // pal_min_state, physical, uncached - mov IA64_KR(CURRENT)=r21 + mov IA64_KR(CURRENT)=r13 ld8 r8=[temp1] // os_status ld8 r10=[temp2] // context @@ -856,7 +856,7 @@ ia64_state_restore: * avoid any dependencies on the algorithm in ia64_switch_to(), just * purge any existing CURRENT_STACK mapping and insert the new one. * - * r16 contains prev_IA64_KR_CURRENT_STACK, r21 contains + * r16 contains prev_IA64_KR_CURRENT_STACK, r13 contains * prev_IA64_KR_CURRENT, these values may have been changed by the C * code. Do not use r8, r9, r10, r22, they contain values ready for * the return to SAL. @@ -873,7 +873,7 @@ ia64_state_restore: ;; srlz.d - extr.u r19=r21,61,3 // r21 = prev_IA64_KR_CURRENT + extr.u r19=r13,61,3 // r13 = prev_IA64_KR_CURRENT shl r20=r16,IA64_GRANULE_SHIFT // r16 = prev_IA64_KR_CURRENT_STACK movl r21=PAGE_KERNEL // page properties ;; @@ -883,7 +883,7 @@ ia64_state_restore: (p6) br.spnt 1f // the dreaded cpu 0 idle task in region 5:( ;; mov cr.itir=r18 - mov cr.ifa=r21 + mov cr.ifa=r13 mov r20=IA64_TR_CURRENT_STACK ;; itr.d dtr[r20]=r21 diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 7a2f0a798d12..3a30cfc9574f 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -947,7 +947,7 @@ void percpu_modcopy (void *pcpudst, const void *src, unsigned long size) { unsigned int i; - for_each_cpu(i) { + for_each_possible_cpu(i) { memcpy(pcpudst + __per_cpu_offset[i], src, size); } } diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index af7eb087dca7..d98ec49570b8 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -60,6 +60,9 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re struct siginfo si; unsigned long mask; + /* mmap_sem is performance critical.... */ + prefetchw(&mm->mmap_sem); + /* * If we're in an interrupt or have no user context, we must not take the fault.. */ diff --git a/arch/ia64/sn/kernel/xpc_channel.c b/arch/ia64/sn/kernel/xpc_channel.c index d0abddd9ffe6..8255a9be4632 100644 --- a/arch/ia64/sn/kernel/xpc_channel.c +++ b/arch/ia64/sn/kernel/xpc_channel.c @@ -1831,7 +1831,7 @@ xpc_initiate_allocate(partid_t partid, int ch_number, u32 flags, void **payload) { struct xpc_partition *part = &xpc_partitions[partid]; enum xpc_retval ret = xpcUnknownReason; - struct xpc_msg *msg; + struct xpc_msg *msg = NULL; DBUG_ON(partid <= 0 || partid >= XP_MAX_PARTITIONS); diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig index 05c864c6c2d9..41fd490af3b4 100644 --- a/arch/m32r/Kconfig +++ b/arch/m32r/Kconfig @@ -285,6 +285,11 @@ config NUMA depends on SMP && BROKEN default n +config NODES_SHIFT + int + default "1" + depends on NEED_MULTIPLE_NODES + # turning this on wastes a bunch of space. # Summit needs it only when NUMA is on config BOOT_IOREMAP diff --git a/arch/m32r/kernel/m32r_ksyms.c b/arch/m32r/kernel/m32r_ksyms.c index be8b711367ec..c50330fa83b9 100644 --- a/arch/m32r/kernel/m32r_ksyms.c +++ b/arch/m32r/kernel/m32r_ksyms.c @@ -23,9 +23,6 @@ EXPORT_SYMBOL(boot_cpu_data); EXPORT_SYMBOL(dump_fpu); EXPORT_SYMBOL(__ioremap); EXPORT_SYMBOL(iounmap); -EXPORT_SYMBOL(enable_irq); -EXPORT_SYMBOL(disable_irq); -EXPORT_SYMBOL(disable_irq_nosync); EXPORT_SYMBOL(kernel_thread); EXPORT_SYMBOL(__down); EXPORT_SYMBOL(__down_interruptible); @@ -38,13 +35,6 @@ EXPORT_SYMBOL(__udelay); EXPORT_SYMBOL(__delay); EXPORT_SYMBOL(__const_udelay); -EXPORT_SYMBOL(__get_user_1); -EXPORT_SYMBOL(__get_user_2); -EXPORT_SYMBOL(__get_user_4); - -EXPORT_SYMBOL(strpbrk); -EXPORT_SYMBOL(strstr); - EXPORT_SYMBOL(strncpy_from_user); EXPORT_SYMBOL(__strncpy_from_user); EXPORT_SYMBOL(clear_user); @@ -59,11 +49,8 @@ extern void *dcache_dummy; EXPORT_SYMBOL(dcache_dummy); #endif EXPORT_SYMBOL(cpu_data); -EXPORT_SYMBOL(cpu_online_map); -EXPORT_SYMBOL(cpu_callout_map); /* Global SMP stuff */ -EXPORT_SYMBOL(synchronize_irq); EXPORT_SYMBOL(smp_call_function); /* TLB flushing */ @@ -83,27 +70,11 @@ EXPORT_SYMBOL(__lshrdi3); EXPORT_SYMBOL(__muldi3); /* memory and string operations */ -EXPORT_SYMBOL(memchr); EXPORT_SYMBOL(memcpy); -/* EXPORT_SYMBOL(memcpy_fromio); // not implement yet */ -/* EXPORT_SYMBOL(memcpy_toio); // not implement yet */ EXPORT_SYMBOL(memset); -/* EXPORT_SYMBOL(memset_io); // not implement yet */ -EXPORT_SYMBOL(memmove); -EXPORT_SYMBOL(memcmp); -EXPORT_SYMBOL(memscan); EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); - -EXPORT_SYMBOL(strcat); -EXPORT_SYMBOL(strchr); -EXPORT_SYMBOL(strcmp); -EXPORT_SYMBOL(strcpy); EXPORT_SYMBOL(strlen); -EXPORT_SYMBOL(strncat); -EXPORT_SYMBOL(strncmp); -EXPORT_SYMBOL(strnlen); -EXPORT_SYMBOL(strncpy); EXPORT_SYMBOL(_inb); EXPORT_SYMBOL(_inw); diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c index 0d78942b4c76..3cd3c2988a48 100644 --- a/arch/m32r/kernel/setup.c +++ b/arch/m32r/kernel/setup.c @@ -9,6 +9,7 @@ #include <linux/config.h> #include <linux/init.h> +#include <linux/kernel.h> #include <linux/stddef.h> #include <linux/fs.h> #include <linux/sched.h> @@ -219,8 +220,6 @@ static unsigned long __init setup_memory(void) extern unsigned long setup_memory(void); #endif /* CONFIG_DISCONTIGMEM */ -#define M32R_PCC_PCATCR 0x00ef7014 /* will move to m32r.h */ - void __init setup_arch(char **cmdline_p) { ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV); @@ -269,15 +268,14 @@ void __init setup_arch(char **cmdline_p) paging_init(); } -static struct cpu cpu[NR_CPUS]; +static struct cpu cpu_devices[NR_CPUS]; static int __init topology_init(void) { - int cpu_id; + int i; - for (cpu_id = 0; cpu_id < NR_CPUS; cpu_id++) - if (cpu_possible(cpu_id)) - register_cpu(&cpu[cpu_id], cpu_id, NULL); + for_each_present_cpu(i) + register_cpu(&cpu_devices[i], i, NULL); return 0; } diff --git a/arch/m32r/kernel/smpboot.c b/arch/m32r/kernel/smpboot.c index d7ec16e7fb25..840b4348bf0c 100644 --- a/arch/m32r/kernel/smpboot.c +++ b/arch/m32r/kernel/smpboot.c @@ -39,8 +39,10 @@ * Martin J. Bligh : Added support for multi-quad systems */ +#include <linux/module.h> #include <linux/config.h> #include <linux/init.h> +#include <linux/kernel.h> #include <linux/mm.h> #include <linux/smp_lock.h> #include <linux/irq.h> @@ -72,11 +74,15 @@ physid_mask_t phys_cpu_present_map; /* Bitmask of currently online CPUs */ cpumask_t cpu_online_map; +EXPORT_SYMBOL(cpu_online_map); cpumask_t cpu_bootout_map; cpumask_t cpu_bootin_map; -cpumask_t cpu_callout_map; static cpumask_t cpu_callin_map; +cpumask_t cpu_callout_map; +EXPORT_SYMBOL(cpu_callout_map); +cpumask_t cpu_possible_map = CPU_MASK_ALL; +EXPORT_SYMBOL(cpu_possible_map); /* Per CPU bogomips and other parameters */ struct cpuinfo_m32r cpu_data[NR_CPUS] __cacheline_aligned; @@ -110,7 +116,6 @@ static unsigned int calibration_result; void smp_prepare_boot_cpu(void); void smp_prepare_cpus(unsigned int); -static void smp_tune_scheduling(void); static void init_ipi_lock(void); static void do_boot_cpu(int); int __cpu_up(unsigned int); @@ -177,6 +182,9 @@ void __init smp_prepare_cpus(unsigned int max_cpus) } for (phys_id = 0 ; phys_id < nr_cpu ; phys_id++) physid_set(phys_id, phys_cpu_present_map); +#ifndef CONFIG_HOTPLUG_CPU + cpu_present_map = cpu_possible_map; +#endif show_mp_info(nr_cpu); @@ -186,7 +194,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus) * Setup boot CPU information */ smp_store_cpu_info(0); /* Final full version of the data */ - smp_tune_scheduling(); /* * If SMP should be disabled, then really disable it! @@ -230,11 +237,6 @@ smp_done: Dprintk("Boot done.\n"); } -static void __init smp_tune_scheduling(void) -{ - /* Nothing to do. */ -} - /* * init_ipi_lock : Initialize IPI locks. */ @@ -629,4 +631,3 @@ static void __init unmap_cpu_to_physid(int cpu_id, int phys_id) physid_2_cpu[phys_id] = -1; cpu_2_physid[cpu_id] = -1; } - diff --git a/arch/m32r/lib/Makefile b/arch/m32r/lib/Makefile index e632d10c7d78..d16b4e40d1ae 100644 --- a/arch/m32r/lib/Makefile +++ b/arch/m32r/lib/Makefile @@ -2,6 +2,6 @@ # Makefile for M32R-specific library files.. # -lib-y := checksum.o ashxdi3.o memset.o memcpy.o getuser.o \ - putuser.o delay.o strlen.o usercopy.o csum_partial_copy.o +lib-y := checksum.o ashxdi3.o memset.o memcpy.o \ + delay.o strlen.o usercopy.o csum_partial_copy.o diff --git a/arch/m32r/lib/getuser.S b/arch/m32r/lib/getuser.S deleted file mode 100644 index 58a0db055c5c..000000000000 --- a/arch/m32r/lib/getuser.S +++ /dev/null @@ -1,88 +0,0 @@ -/* - * __get_user functions. - * - * (C) Copyright 2001 Hirokazu Takata - * - * These functions have a non-standard call interface - * to make them more efficient, especially as they - * return an error value in addition to the "real" - * return value. - */ - -#include <linux/config.h> - -/* - * __get_user_X - * - * Inputs: r0 contains the address - * - * Outputs: r0 is error code (0 or -EFAULT) - * r1 contains zero-extended value - * - * These functions should not modify any other registers, - * as they get called from within inline assembly. - */ - -#ifdef CONFIG_ISA_DUAL_ISSUE - - .text - .balign 4 - .globl __get_user_1 -__get_user_1: -1: ldub r1, @r0 || ldi r0, #0 - jmp r14 - - .balign 4 - .globl __get_user_2 -__get_user_2: -2: lduh r1, @r0 || ldi r0, #0 - jmp r14 - - .balign 4 - .globl __get_user_4 -__get_user_4: -3: ld r1, @r0 || ldi r0, #0 - jmp r14 - -bad_get_user: - ldi r1, #0 || ldi r0, #-14 - jmp r14 - -#else /* not CONFIG_ISA_DUAL_ISSUE */ - - .text - .balign 4 - .globl __get_user_1 -__get_user_1: -1: ldub r1, @r0 - ldi r0, #0 - jmp r14 - - .balign 4 - .globl __get_user_2 -__get_user_2: -2: lduh r1, @r0 - ldi r0, #0 - jmp r14 - - .balign 4 - .globl __get_user_4 -__get_user_4: -3: ld r1, @r0 - ldi r0, #0 - jmp r14 - -bad_get_user: - ldi r1, #0 - ldi r0, #-14 - jmp r14 - -#endif /* not CONFIG_ISA_DUAL_ISSUE */ - -.section __ex_table,"a" - .long 1b,bad_get_user - .long 2b,bad_get_user - .long 3b,bad_get_user -.previous - - .end diff --git a/arch/m32r/lib/putuser.S b/arch/m32r/lib/putuser.S deleted file mode 100644 index 218154cc3890..000000000000 --- a/arch/m32r/lib/putuser.S +++ /dev/null @@ -1,84 +0,0 @@ -/* - * __put_user functions. - * - * (C) Copyright 1998 Linus Torvalds - * (C) Copyright 2001 Hirokazu Takata - * - * These functions have a non-standard call interface - * to make them more efficient. - */ - -#include <linux/config.h> - -/* - * __put_user_X - * - * Inputs: r0 contains the address - * r1 contains the value - * - * Outputs: r0 is error code (0 or -EFAULT) - * r1 is corrupted (will contain "current_task"). - * - * These functions should not modify any other registers, - * as they get called from within inline assembly. - */ - -#ifdef CONFIG_ISA_DUAL_ISSUE - - .text - .balign 4 - .globl __put_user_1 -__put_user_1: -1: stb r1, @r0 || ldi r0, #0 - jmp r14 - - .balign 4 - .globl __put_user_2 -__put_user_2: -2: sth r1, @r0 || ldi r0, #0 - jmp r14 - - .balign 4 - .globl __put_user_4 -__put_user_4: -3: st r1, @r0 || ldi r0, #0 - jmp r14 - -bad_put_user: - ldi r0, #-14 || jmp r14 - -#else /* not CONFIG_ISA_DUAL_ISSUE */ - - .text - .balign 4 - .globl __put_user_1 -__put_user_1: -1: stb r1, @r0 - ldi r0, #0 - jmp r14 - - .balign 4 - .globl __put_user_2 -__put_user_2: -2: sth r1, @r0 - ldi r0, #0 - jmp r14 - - .balign 4 - .globl __put_user_4 -__put_user_4: -3: st r1, @r0 - ldi r0, #0 - jmp r14 - -bad_put_user: - ldi r0, #-14 - jmp r14 - -#endif /* not CONFIG_ISA_DUAL_ISSUE */ - -.section __ex_table,"a" - .long 1b,bad_put_user - .long 2b,bad_put_user - .long 3b,bad_put_user -.previous diff --git a/arch/m68k/kernel/m68k_ksyms.c b/arch/m68k/kernel/m68k_ksyms.c index c3319514a85e..5b7952ea2bae 100644 --- a/arch/m68k/kernel/m68k_ksyms.c +++ b/arch/m68k/kernel/m68k_ksyms.c @@ -57,7 +57,6 @@ EXPORT_SYMBOL(dump_thread); EXPORT_SYMBOL(strnlen); EXPORT_SYMBOL(strrchr); EXPORT_SYMBOL(strstr); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(enable_irq); EXPORT_SYMBOL(disable_irq); EXPORT_SYMBOL(kernel_thread); diff --git a/arch/m68knommu/kernel/m68k_ksyms.c b/arch/m68knommu/kernel/m68k_ksyms.c index f9b4ea16c099..4320d5dcc9cb 100644 --- a/arch/m68knommu/kernel/m68k_ksyms.c +++ b/arch/m68knommu/kernel/m68k_ksyms.c @@ -26,7 +26,6 @@ EXPORT_SYMBOL(__ioremap); EXPORT_SYMBOL(iounmap); EXPORT_SYMBOL(dump_fpu); EXPORT_SYMBOL(strnlen); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strrchr); EXPORT_SYMBOL(strstr); EXPORT_SYMBOL(strchr); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index e15709ce8866..7aec60d40420 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1590,6 +1590,11 @@ config ARCH_FLATMEM_ENABLE def_bool y depends on !NUMA +config NODES_SHIFT + int + default "6" + depends on NEED_MULTIPLE_NODES + source "mm/Kconfig" config SMP diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c index 86e42c633f73..e042f9d2ba31 100644 --- a/arch/mips/kernel/mips_ksyms.c +++ b/arch/mips/kernel/mips_ksyms.c @@ -39,7 +39,6 @@ EXPORT_SYMBOL(strchr); EXPORT_SYMBOL(strncmp); #endif EXPORT_SYMBOL(strlen); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strncat); EXPORT_SYMBOL(strnlen); EXPORT_SYMBOL(strrchr); diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 2fdf21989dc2..19f911c5dd58 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -177,6 +177,11 @@ config ARCH_DISCONTIGMEM_DEFAULT def_bool y depends on ARCH_DISCONTIGMEM_ENABLE +config NODES_SHIFT + int + default "3" + depends on NEED_MULTIPLE_NODES + source "kernel/Kconfig.preempt" source "kernel/Kconfig.hz" source "mm/Kconfig" diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 47ca5c0a323b..fc107add627c 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -31,7 +31,6 @@ #include <linux/string.h> EXPORT_SYMBOL(memset); -EXPORT_SYMBOL(strpbrk); #include <asm/atomic.h> EXPORT_SYMBOL(__xchg8); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2cdc35ce8045..167e70e95556 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -649,6 +649,11 @@ config NUMA depends on PPC64 default y if SMP && PPC_PSERIES +config NODES_SHIFT + int + default "4" + depends on NEED_MULTIPLE_NODES + config ARCH_SELECT_MEMORY_MODEL def_bool y depends on PPC64 diff --git a/arch/ppc/boot/lib/Makefile b/arch/ppc/boot/lib/Makefile index d4077e69086f..80c84d562fa4 100644 --- a/arch/ppc/boot/lib/Makefile +++ b/arch/ppc/boot/lib/Makefile @@ -3,7 +3,7 @@ # CFLAGS_kbd.o := -Idrivers/char -CFLAGS_vreset.o := -I$(srctree)/arch/ppc/boot/include +CFLAGS_vreset.o := -Iarch/ppc/boot/include zlib := infblock.c infcodes.c inffast.c inflate.c inftrees.c infutil.c diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 6c6b197898d0..7bb16fb97d4f 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -67,7 +67,6 @@ cflags-$(CONFIG_WARN_STACK) += -mwarn-framesize=$(CONFIG_WARN_STACK_SIZE) endif CFLAGS += -mbackchain -msoft-float $(cflags-y) -CFLAGS += $(call cc-option,-finline-limit=10000) CFLAGS += -pipe -fno-strength-reduce -Wno-sign-compare AFLAGS += $(aflags-y) diff --git a/arch/s390/defconfig b/arch/s390/defconfig index f8d0cd540a06..f4dfc10026d2 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -1,10 +1,11 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.16-rc2 -# Wed Feb 8 10:44:39 2006 +# Linux kernel version: 2.6.17-rc1 +# Mon Apr 3 14:34:15 2006 # CONFIG_MMU=y CONFIG_RWSEM_XCHGADD_ALGORITHM=y +CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_S390=y @@ -30,8 +31,8 @@ CONFIG_AUDIT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y # CONFIG_CPUSETS is not set +# CONFIG_RELAY is not set CONFIG_INITRAMFS_SOURCE="" -CONFIG_UID16=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set # CONFIG_EMBEDDED is not set CONFIG_KALLSYMS=y @@ -45,10 +46,6 @@ CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_EPOLL=y CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 CONFIG_SLAB=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 @@ -60,7 +57,6 @@ CONFIG_BASE_SMALL=0 CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_MODULE_FORCE_UNLOAD is not set -CONFIG_OBSOLETE_MODPARM=y CONFIG_MODVERSIONS=y # CONFIG_MODULE_SRCVERSION_ALL is not set CONFIG_KMOD=y @@ -69,7 +65,7 @@ CONFIG_STOP_MACHINE=y # # Block layer # -# CONFIG_LBD is not set +# CONFIG_BLK_DEV_IO_TRACE is not set # # IO Schedulers @@ -91,17 +87,20 @@ CONFIG_DEFAULT_IOSCHED="deadline" # # Processor type and features # -# CONFIG_64BIT is not set +CONFIG_64BIT=y CONFIG_SMP=y CONFIG_NR_CPUS=32 CONFIG_HOTPLUG_CPU=y -CONFIG_MATHEMU=y +CONFIG_DEFAULT_MIGRATION_COST=1000000 +CONFIG_COMPAT=y +CONFIG_SYSVIPC_COMPAT=y +CONFIG_BINFMT_ELF32=y # # Code generation options # -CONFIG_MARCH_G5=y -# CONFIG_MARCH_Z900 is not set +# CONFIG_MARCH_G5 is not set +CONFIG_MARCH_Z900=y # CONFIG_MARCH_Z990 is not set CONFIG_PACK_STACK=y # CONFIG_SMALL_STACK is not set @@ -143,7 +142,7 @@ CONFIG_VIRT_CPU_ACCOUNTING=y # CONFIG_APPLDATA_BASE is not set CONFIG_NO_IDLE_HZ=y CONFIG_NO_IDLE_HZ_INIT=y -# CONFIG_KEXEC is not set +CONFIG_KEXEC=y # # Networking @@ -173,6 +172,7 @@ CONFIG_IP_FIB_HASH=y # CONFIG_INET_AH is not set # CONFIG_INET_ESP is not set # CONFIG_INET_IPCOMP is not set +# CONFIG_INET_XFRM_TUNNEL is not set # CONFIG_INET_TUNNEL is not set CONFIG_INET_DIAG=y CONFIG_INET_TCP_DIAG=y @@ -180,9 +180,11 @@ CONFIG_INET_TCP_DIAG=y CONFIG_TCP_CONG_BIC=y CONFIG_IPV6=y # CONFIG_IPV6_PRIVACY is not set +# CONFIG_IPV6_ROUTER_PREF is not set # CONFIG_INET6_AH is not set # CONFIG_INET6_ESP is not set # CONFIG_INET6_IPCOMP is not set +# CONFIG_INET6_XFRM_TUNNEL is not set # CONFIG_INET6_TUNNEL is not set # CONFIG_IPV6_TUNNEL is not set # CONFIG_NETFILTER is not set @@ -276,6 +278,11 @@ CONFIG_PREVENT_FIRMWARE_BUILD=y # CONFIG_DEBUG_DRIVER is not set # +# Connector - unified userspace <-> kernelspace linker +# +# CONFIG_CONNECTOR is not set + +# # SCSI device support # # CONFIG_RAID_ATTRS is not set @@ -340,8 +347,7 @@ CONFIG_DASD_PROFILE=y CONFIG_DASD_ECKD=y CONFIG_DASD_FBA=y CONFIG_DASD_DIAG=y -CONFIG_DASD_EER=m -# CONFIG_DASD_CMB is not set +CONFIG_DASD_EER=y # CONFIG_ATA_OVER_ETH is not set # @@ -354,6 +360,7 @@ CONFIG_MD_RAID0=m CONFIG_MD_RAID1=m # CONFIG_MD_RAID10 is not set CONFIG_MD_RAID5=m +# CONFIG_MD_RAID5_RESHAPE is not set # CONFIG_MD_RAID6 is not set CONFIG_MD_MULTIPATH=m # CONFIG_MD_FAULTY is not set @@ -404,6 +411,7 @@ CONFIG_S390_TAPE_BLOCK=y # S/390 tape hardware support # CONFIG_S390_TAPE_34XX=m +# CONFIG_S390_TAPE_3590 is not set # CONFIG_VMLOGRDR is not set # CONFIG_VMCP is not set # CONFIG_MONREADER is not set @@ -529,7 +537,6 @@ CONFIG_SYSFS=y CONFIG_TMPFS=y # CONFIG_HUGETLB_PAGE is not set CONFIG_RAMFS=y -# CONFIG_RELAYFS_FS is not set # CONFIG_CONFIGFS_FS is not set # @@ -619,14 +626,15 @@ CONFIG_LOG_BUF_SHIFT=17 # CONFIG_DETECT_SOFTLOCKUP is not set # CONFIG_SCHEDSTATS is not set # CONFIG_DEBUG_SLAB is not set -# CONFIG_DEBUG_PREEMPT is not set +CONFIG_DEBUG_PREEMPT=y CONFIG_DEBUG_MUTEXES=y -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_SPINLOCK_SLEEP is not set +CONFIG_DEBUG_SPINLOCK=y +CONFIG_DEBUG_SPINLOCK_SLEEP=y # CONFIG_DEBUG_KOBJECT is not set # CONFIG_DEBUG_INFO is not set CONFIG_DEBUG_FS=y # CONFIG_DEBUG_VM is not set +# CONFIG_UNWIND_INFO is not set CONFIG_FORCED_INLINING=y # CONFIG_RCU_TORTURE_TEST is not set diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 58583f459471..2bcecf422573 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -527,6 +527,11 @@ config CPU_HAS_SR_RB See <file:Documentation/sh/register-banks.txt> for further information on SR.RB and register banking in the kernel in general. +config NODES_SHIFT + int + default "1" + depends on NEED_MULTIPLE_NODES + endmenu menu "Boot options" diff --git a/arch/sh/kernel/sh_ksyms.c b/arch/sh/kernel/sh_ksyms.c index 1cf94a618be3..d5d032533a8b 100644 --- a/arch/sh/kernel/sh_ksyms.c +++ b/arch/sh/kernel/sh_ksyms.c @@ -37,7 +37,6 @@ EXPORT_SYMBOL(disable_irq_nosync); EXPORT_SYMBOL(irq_desc); EXPORT_SYMBOL(no_irq_type); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strstr); EXPORT_SYMBOL(strlen); EXPORT_SYMBOL(strnlen); diff --git a/arch/sh64/kernel/sh_ksyms.c b/arch/sh64/kernel/sh_ksyms.c index de29c45f23a7..6f3a1c946339 100644 --- a/arch/sh64/kernel/sh_ksyms.c +++ b/arch/sh64/kernel/sh_ksyms.c @@ -41,7 +41,6 @@ EXPORT_SYMBOL(kernel_thread); /* Networking helper routines. */ EXPORT_SYMBOL(csum_partial_copy); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strstr); #ifdef CONFIG_VT diff --git a/arch/sparc/kernel/smp.c b/arch/sparc/kernel/smp.c index 2be812115197..a93f5da6855d 100644 --- a/arch/sparc/kernel/smp.c +++ b/arch/sparc/kernel/smp.c @@ -244,7 +244,7 @@ int setup_profiling_timer(unsigned int multiplier) return -EINVAL; spin_lock_irqsave(&prof_setup_lock, flags); - for_each_cpu(i) { + for_each_possible_cpu(i) { load_profile_irq(i, lvl14_resolution / multiplier); prof_multiplier(i) = multiplier; } diff --git a/arch/sparc/kernel/sparc_ksyms.c b/arch/sparc/kernel/sparc_ksyms.c index 2c21d7907635..ec1c9687d679 100644 --- a/arch/sparc/kernel/sparc_ksyms.c +++ b/arch/sparc/kernel/sparc_ksyms.c @@ -263,7 +263,6 @@ EXPORT_SYMBOL(strcmp); EXPORT_SYMBOL(strncmp); EXPORT_SYMBOL(strchr); EXPORT_SYMBOL(strrchr); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strstr); EXPORT_SYMBOL(page_kernel); diff --git a/arch/sparc/math-emu/Makefile b/arch/sparc/math-emu/Makefile index f84a9a6162be..8136987977f4 100644 --- a/arch/sparc/math-emu/Makefile +++ b/arch/sparc/math-emu/Makefile @@ -5,4 +5,4 @@ obj-y := math.o EXTRA_AFLAGS := -ansi -EXTRA_CFLAGS = -I. -I$(TOPDIR)/include/math-emu -w +EXTRA_CFLAGS = -I. -Iinclude/math-emu -w diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig index d1e2fc566486..648047a0bce3 100644 --- a/arch/sparc64/Kconfig +++ b/arch/sparc64/Kconfig @@ -194,6 +194,9 @@ endchoice endmenu +config ARCH_SELECT_MEMORY_MODEL + def_bool y + config ARCH_SPARSEMEM_ENABLE def_bool y diff --git a/arch/sparc64/defconfig b/arch/sparc64/defconfig index 30389085a359..1317380fa937 100644 --- a/arch/sparc64/defconfig +++ b/arch/sparc64/defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit # Linux kernel version: 2.6.16 -# Fri Mar 31 01:40:57 2006 +# Sun Apr 2 19:31:04 2006 # CONFIG_SPARC=y CONFIG_SPARC64=y @@ -838,7 +838,6 @@ CONFIG_FB_TILEBLITTING=y # CONFIG_FB_NVIDIA is not set # CONFIG_FB_RIVA is not set # CONFIG_FB_MATROX is not set -# CONFIG_FB_RADEON_OLD is not set CONFIG_FB_RADEON=y CONFIG_FB_RADEON_I2C=y # CONFIG_FB_RADEON_DEBUG is not set @@ -924,6 +923,7 @@ CONFIG_SND_MTPAV=m # PCI devices # # CONFIG_SND_AD1889 is not set +# CONFIG_SND_ALS300 is not set CONFIG_SND_ALI5451=m # CONFIG_SND_ATIIXP is not set # CONFIG_SND_ATIIXP_MODEM is not set @@ -955,6 +955,7 @@ CONFIG_SND_ALI5451=m # CONFIG_SND_MIXART is not set # CONFIG_SND_NM256 is not set # CONFIG_SND_PCXHR is not set +# CONFIG_SND_RIPTIDE is not set # CONFIG_SND_RME32 is not set # CONFIG_SND_RME96 is not set # CONFIG_SND_RME9652 is not set @@ -1109,6 +1110,11 @@ CONFIG_USB_HIDDEV=y # CONFIG_MMC is not set # +# LED devices +# +# CONFIG_NEW_LEDS is not set + +# # InfiniBand support # # CONFIG_INFINIBAND is not set diff --git a/arch/sparc64/kernel/pci_sun4v.c b/arch/sparc64/kernel/pci_sun4v.c index 9372d4f376d5..9e94db2573a2 100644 --- a/arch/sparc64/kernel/pci_sun4v.c +++ b/arch/sparc64/kernel/pci_sun4v.c @@ -1092,7 +1092,7 @@ void sun4v_pci_init(int node, char *model_name) } } - for_each_cpu(i) { + for_each_possible_cpu(i) { unsigned long page = get_zeroed_page(GFP_ATOMIC); if (!page) diff --git a/arch/sparc64/kernel/ptrace.c b/arch/sparc64/kernel/ptrace.c index eb93e9c52846..49e6dedd027d 100644 --- a/arch/sparc64/kernel/ptrace.c +++ b/arch/sparc64/kernel/ptrace.c @@ -244,6 +244,13 @@ asmlinkage void do_ptrace(struct pt_regs *regs) } switch(request) { + case PTRACE_PEEKUSR: + if (addr != 0) + pt_error_return(regs, EIO); + else + pt_succ_return(regs, 0); + goto out_tsk; + case PTRACE_PEEKTEXT: /* read word at location addr. */ case PTRACE_PEEKDATA: { unsigned long tmp64; @@ -602,6 +609,22 @@ asmlinkage void do_ptrace(struct pt_regs *regs) /* PTRACE_DUMPCORE unsupported... */ + case PTRACE_GETEVENTMSG: { + int err; + + if (test_thread_flag(TIF_32BIT)) + err = put_user(child->ptrace_message, + (unsigned int __user *) data); + else + err = put_user(child->ptrace_message, + (unsigned long __user *) data); + if (err) + pt_error_return(regs, -err); + else + pt_succ_return(regs, 0); + break; + } + default: { int err = ptrace_request(child, request, addr, data); if (err) diff --git a/arch/sparc64/kernel/setup.c b/arch/sparc64/kernel/setup.c index 7d0e67c1ce50..005167f82419 100644 --- a/arch/sparc64/kernel/setup.c +++ b/arch/sparc64/kernel/setup.c @@ -535,7 +535,7 @@ static int __init topology_init(void) while (!cpu_find_by_instance(ncpus_probed, NULL, NULL)) ncpus_probed++; - for_each_cpu(i) { + for_each_possible_cpu(i) { struct cpu *p = kzalloc(sizeof(*p), GFP_KERNEL); if (p) { register_cpu(p, i, NULL); diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c index 8175a6968c6b..90eaca3ec9a6 100644 --- a/arch/sparc64/kernel/smp.c +++ b/arch/sparc64/kernel/smp.c @@ -745,12 +745,21 @@ struct call_data_struct { int wait; }; -static DEFINE_SPINLOCK(call_lock); +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(call_lock); static struct call_data_struct *call_data; extern unsigned long xcall_call_function; -/* +/** + * smp_call_function(): Run a function on all other CPUs. + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @nonatomic: currently unused. + * @wait: If true, wait (atomically) until function has completed on other CPUs. + * + * Returns 0 on success, else a negative status code. Does not return until + * remote CPUs are nearly ready to execute <<func>> or are or have executed. + * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ @@ -759,7 +768,6 @@ static int smp_call_function_mask(void (*func)(void *info), void *info, { struct call_data_struct data; int cpus; - long timeout; /* Can deadlock when called with interrupts disabled */ WARN_ON(irqs_disabled()); @@ -777,31 +785,18 @@ static int smp_call_function_mask(void (*func)(void *info), void *info, goto out_unlock; call_data = &data; + mb(); smp_cross_call_masked(&xcall_call_function, 0, 0, 0, mask); - /* - * Wait for other cpus to complete function or at - * least snap the call data. - */ - timeout = 1000000; - while (atomic_read(&data.finished) != cpus) { - if (--timeout <= 0) - goto out_timeout; - barrier(); - udelay(1); - } + /* Wait for response */ + while (atomic_read(&data.finished) != cpus) + cpu_relax(); out_unlock: spin_unlock(&call_lock); return 0; - -out_timeout: - spin_unlock(&call_lock); - printk("XCALL: Remote cpus not responding, ncpus=%d finished=%d\n", - cpus, atomic_read(&data.finished)); - return 0; } int smp_call_function(void (*func)(void *info), void *info, @@ -1285,7 +1280,7 @@ int setup_profiling_timer(unsigned int multiplier) return -EINVAL; spin_lock_irqsave(&prof_setup_lock, flags); - for_each_cpu(i) + for_each_possible_cpu(i) prof_multiplier(i) = multiplier; current_tick_offset = (timer_tick_offset / multiplier); spin_unlock_irqrestore(&prof_setup_lock, flags); @@ -1313,12 +1308,12 @@ void __init smp_prepare_cpus(unsigned int max_cpus) } } - for_each_cpu(i) { + for_each_possible_cpu(i) { if (tlb_type == hypervisor) { int j; /* XXX get this mapping from machine description */ - for_each_cpu(j) { + for_each_possible_cpu(j) { if ((j >> 2) == (i >> 2)) cpu_set(j, cpu_sibling_map[i]); } diff --git a/arch/sparc64/kernel/sparc64_ksyms.c b/arch/sparc64/kernel/sparc64_ksyms.c index f5e8db1de76b..62d8a99271ea 100644 --- a/arch/sparc64/kernel/sparc64_ksyms.c +++ b/arch/sparc64/kernel/sparc64_ksyms.c @@ -276,7 +276,6 @@ EXPORT_SYMBOL(__prom_getsibling); EXPORT_SYMBOL(strlen); EXPORT_SYMBOL(__strlen_user); EXPORT_SYMBOL(__strnlen_user); -EXPORT_SYMBOL(strpbrk); #ifdef CONFIG_SOLARIS_EMUL_MODULE EXPORT_SYMBOL(linux_sparc_syscall); diff --git a/arch/sparc64/kernel/traps.c b/arch/sparc64/kernel/traps.c index ff090bb9734b..2793a5d82380 100644 --- a/arch/sparc64/kernel/traps.c +++ b/arch/sparc64/kernel/traps.c @@ -1130,9 +1130,9 @@ static void cheetah_log_errors(struct pt_regs *regs, struct cheetah_err_info *in (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(), afsr, afar, (afsr & CHAFSR_TL1) ? 1 : 0); - printk("%s" "ERROR(%d): TPC[%016lx] TNPC[%016lx] TSTATE[%016lx]\n", + printk("%s" "ERROR(%d): TPC[%lx] TNPC[%lx] O7[%lx] TSTATE[%lx]\n", (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(), - regs->tpc, regs->tnpc, regs->tstate); + regs->tpc, regs->tnpc, regs->u_regs[UREG_I7], regs->tstate); printk("%s" "ERROR(%d): M_SYND(%lx), E_SYND(%lx)%s%s\n", (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(), (afsr & CHAFSR_M_SYNDROME) >> CHAFSR_M_SYNDROME_SHIFT, diff --git a/arch/um/Makefile b/arch/um/Makefile index 24790bed2054..a508e7a02891 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -159,6 +159,7 @@ archclean: $(SYMLINK_HEADERS): @echo ' SYMLINK $@' ifneq ($(KBUILD_SRC),) + $(Q)mkdir -p $(objtree)/include/asm-um $(Q)ln -fsn $(srctree)/include/asm-um/$(basename $(notdir $@))-$(SUBARCH)$(suffix $@) $@ else $(Q)cd $(TOPDIR)/$(dir $@) ; \ @@ -168,7 +169,7 @@ endif include/asm-um/arch: @echo ' SYMLINK $@' ifneq ($(KBUILD_SRC),) - $(Q)mkdir -p include/asm-um + $(Q)mkdir -p $(objtree)/include/asm-um $(Q)ln -fsn $(srctree)/include/asm-$(SUBARCH) include/asm-um/arch else $(Q)cd $(TOPDIR)/include/asm-um && ln -sf ../asm-$(SUBARCH) arch diff --git a/arch/um/drivers/cow.h b/arch/um/drivers/cow.h index 04e3958266e0..dc36b222100b 100644 --- a/arch/um/drivers/cow.h +++ b/arch/um/drivers/cow.h @@ -46,7 +46,7 @@ extern int file_reader(__u64 offset, char *buf, int len, void *arg); extern int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg, __u32 *version_out, char **backing_file_out, time_t *mtime_out, - __u64 *size_out, int *sectorsize_out, + unsigned long long *size_out, int *sectorsize_out, __u32 *align_out, int *bitmap_offset_out); extern int write_cow_header(char *cow_file, int fd, char *backing_file, diff --git a/arch/um/drivers/cow_sys.h b/arch/um/drivers/cow_sys.h index 94de4ead4f7a..7a5b4afde692 100644 --- a/arch/um/drivers/cow_sys.h +++ b/arch/um/drivers/cow_sys.h @@ -28,7 +28,7 @@ static inline int cow_seek_file(int fd, __u64 offset) return(os_seek_file(fd, offset)); } -static inline int cow_file_size(char *file, __u64 *size_out) +static inline int cow_file_size(char *file, unsigned long long *size_out) { return(os_file_size(file, size_out)); } diff --git a/arch/um/drivers/cow_user.c b/arch/um/drivers/cow_user.c index 61951b721268..0ec4052db9c5 100644 --- a/arch/um/drivers/cow_user.c +++ b/arch/um/drivers/cow_user.c @@ -17,30 +17,34 @@ #define PATH_LEN_V1 256 +typedef __u32 time32_t; + struct cow_header_v1 { - int magic; - int version; + __s32 magic; + __s32 version; char backing_file[PATH_LEN_V1]; - time_t mtime; + time32_t mtime; __u64 size; - int sectorsize; -}; + __s32 sectorsize; +} __attribute__((packed)); -#define PATH_LEN_V2 MAXPATHLEN +/* Define PATH_LEN_V3 as the usual value of MAXPATHLEN, just hard-code it in + * case other systems have different values for MAXPATHLEN. + * + * The same must hold for V2 - we want file format compatibility, not anything + * else. + */ +#define PATH_LEN_V3 4096 +#define PATH_LEN_V2 PATH_LEN_V3 struct cow_header_v2 { __u32 magic; __u32 version; char backing_file[PATH_LEN_V2]; - time_t mtime; + time32_t mtime; __u64 size; - int sectorsize; -}; - -/* Define PATH_LEN_V3 as the usual value of MAXPATHLEN, just hard-code it in - * case other systems have different values for MAXPATHLEN - */ -#define PATH_LEN_V3 4096 + __s32 sectorsize; +} __attribute__((packed)); /* Changes from V2 - * PATH_LEN_V3 as described above @@ -66,6 +70,15 @@ struct cow_header_v2 { * Fixed (finally!) the rounding bug */ +/* Until Dec2005, __attribute__((packed)) was left out from the below + * definition, leading on 64-bit systems to 4 bytes of padding after mtime, to + * align size to 8-byte alignment. This shifted all fields above (no padding + * was present on 32-bit, no other padding was added). + * + * However, this _can be detected_: it means that cow_format (always 0 until + * now) is shifted onto the first 4 bytes of backing_file, where it is otherwise + * impossible to find 4 zeros. -bb */ + struct cow_header_v3 { __u32 magic; __u32 version; @@ -75,6 +88,18 @@ struct cow_header_v3 { __u32 alignment; __u32 cow_format; char backing_file[PATH_LEN_V3]; +} __attribute__((packed)); + +/* This is the broken layout used by some 64-bit binaries. */ +struct cow_header_v3_broken { + __u32 magic; + __u32 version; + __s64 mtime; + __u64 size; + __u32 sectorsize; + __u32 alignment; + __u32 cow_format; + char backing_file[PATH_LEN_V3]; }; /* COW format definitions - for now, we have only the usual COW bitmap */ @@ -84,6 +109,7 @@ union cow_header { struct cow_header_v1 v1; struct cow_header_v2 v2; struct cow_header_v3 v3; + struct cow_header_v3_broken v3_b; }; #define COW_MAGIC 0x4f4f4f4d /* MOOO */ @@ -184,8 +210,9 @@ int write_cow_header(char *cow_file, int fd, char *backing_file, err = -EINVAL; if(strlen(backing_file) > sizeof(header->backing_file) - 1){ + /* Below, %zd is for a size_t value */ cow_printf("Backing file name \"%s\" is too long - names are " - "limited to %d characters\n", backing_file, + "limited to %zd characters\n", backing_file, sizeof(header->backing_file) - 1); goto out_free; } @@ -300,7 +327,8 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg, *align_out = *sectorsize_out; file = header->v2.backing_file; } - else if(version == 3){ + /* This is very subtle - see above at union cow_header definition */ + else if(version == 3 && (*((int*)header->v3.backing_file) != 0)){ if(n < sizeof(header->v3)){ cow_printf("read_cow_header - failed to read V3 " "header\n"); @@ -310,9 +338,43 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg, *size_out = ntohll(header->v3.size); *sectorsize_out = ntohl(header->v3.sectorsize); *align_out = ntohl(header->v3.alignment); + if (*align_out == 0) { + cow_printf("read_cow_header - invalid COW header, " + "align == 0\n"); + } *bitmap_offset_out = ROUND_UP(sizeof(header->v3), *align_out); file = header->v3.backing_file; } + else if(version == 3){ + cow_printf("read_cow_header - broken V3 file with" + " 64-bit layout - recovering content.\n"); + + if(n < sizeof(header->v3_b)){ + cow_printf("read_cow_header - failed to read V3 " + "header\n"); + goto out; + } + + /* this was used until Dec2005 - 64bits are needed to represent + * 2038+. I.e. we can safely do this truncating cast. + * + * Additionally, we must use ntohl() instead of ntohll(), since + * the program used to use the former (tested - I got mtime + * mismatch "0 vs whatever"). + * + * Ever heard about bug-to-bug-compatibility ? ;-) */ + *mtime_out = (time32_t) ntohl(header->v3_b.mtime); + + *size_out = ntohll(header->v3_b.size); + *sectorsize_out = ntohl(header->v3_b.sectorsize); + *align_out = ntohl(header->v3_b.alignment); + if (*align_out == 0) { + cow_printf("read_cow_header - invalid COW header, " + "align == 0\n"); + } + *bitmap_offset_out = ROUND_UP(sizeof(header->v3_b), *align_out); + file = header->v3_b.backing_file; + } else { cow_printf("read_cow_header - invalid COW version\n"); goto out; diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 28e3760e8b98..6d7173fc55a3 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -62,7 +62,7 @@ static void mc_work_proc(void *unused) unsigned long flags; while(!list_empty(&mc_requests)){ - local_save_flags(flags); + local_irq_save(flags); req = list_entry(mc_requests.next, struct mconsole_entry, list); list_del(&req->list); @@ -87,7 +87,7 @@ static irqreturn_t mconsole_interrupt(int irq, void *dev_id, if(req.cmd->context == MCONSOLE_INTR) (*req.cmd->handler)(&req); else { - new = kmalloc(sizeof(*new), GFP_ATOMIC); + new = kmalloc(sizeof(*new), GFP_NOWAIT); if(new == NULL) mconsole_reply(&req, "Out of memory", 1, 0); else { @@ -415,7 +415,6 @@ static int mem_config(char *str) unplugged = page_address(page); if(unplug_index == UNPLUGGED_PER_PAGE){ - INIT_LIST_HEAD(&unplugged->list); list_add(&unplugged->list, &unplugged_pages); unplug_index = 0; } @@ -616,7 +615,7 @@ static void console_write(struct console *console, const char *string, return; while(1){ - n = min((size_t)len, ARRAY_SIZE(console_buf) - console_index); + n = min((size_t) len, ARRAY_SIZE(console_buf) - console_index); strncpy(&console_buf[console_index], string, n); console_index += n; string += n; @@ -655,7 +654,6 @@ static void with_console(struct mc_request *req, void (*proc)(void *), struct mconsole_entry entry; unsigned long flags; - INIT_LIST_HEAD(&entry.list); entry.request = *req; list_add(&entry.list, &clients); spin_lock_irqsave(&console_lock, flags); diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c index 0e2f06187ea7..0a7786e00cfb 100644 --- a/arch/um/drivers/net_user.c +++ b/arch/um/drivers/net_user.c @@ -182,7 +182,9 @@ static int change_tramp(char **argv, char *output, int output_len) pe_data.stdout = fds[1]; pid = run_helper(change_pre_exec, &pe_data, argv, NULL); - read_output(fds[0], output, output_len); + if (pid > 0) /* Avoid hang as we won't get data in failure case. */ + read_output(fds[0], output, output_len); + os_close_file(fds[0]); os_close_file(fds[1]); diff --git a/arch/um/drivers/slirp_user.c b/arch/um/drivers/slirp_user.c index b94c66114bc8..33c5f6e625e8 100644 --- a/arch/um/drivers/slirp_user.c +++ b/arch/um/drivers/slirp_user.c @@ -104,7 +104,7 @@ static void slirp_close(int fd, void *data) } if(err == 0) { - printk("slirp_close: process %d has not exited\n"); + printk("slirp_close: process %d has not exited\n", pri->pid); return; } diff --git a/arch/um/include/kern_util.h b/arch/um/include/kern_util.h index 42557130a408..efa3d33c0be6 100644 --- a/arch/um/include/kern_util.h +++ b/arch/um/include/kern_util.h @@ -117,10 +117,6 @@ extern struct task_struct *get_task(int pid, int require); extern void machine_halt(void); extern int is_syscall(unsigned long addr); -extern void arch_switch_to_tt(struct task_struct *from, struct task_struct *to); - -extern void arch_switch_to_skas(struct task_struct *from, struct task_struct *to); - extern void free_irq(unsigned int, void *); extern int cpu(void); diff --git a/arch/um/include/tt/tt.h b/arch/um/include/tt/tt.h index 808521980186..acb8356e1f98 100644 --- a/arch/um/include/tt/tt.h +++ b/arch/um/include/tt/tt.h @@ -19,7 +19,8 @@ extern int fork_tramp(void *sig_stack); extern int do_proc_op(void *t, int proc_id); extern int tracer(int (*init_proc)(void *), void *sp); extern void attach_process(int pid); -extern void tracer_panic(char *format, ...); +extern void tracer_panic(char *format, ...) + __attribute__ ((format (printf, 1, 2))); extern void set_init_pid(int pid); extern int set_user_mode(void *task); extern void set_tracing(void *t, int tracing); diff --git a/arch/um/include/user.h b/arch/um/include/user.h index 91b0ac4ad88c..39f8c8801076 100644 --- a/arch/um/include/user.h +++ b/arch/um/include/user.h @@ -6,8 +6,10 @@ #ifndef __USER_H__ #define __USER_H__ -extern void panic(const char *fmt, ...); -extern int printk(const char *fmt, ...); +extern void panic(const char *fmt, ...) + __attribute__ ((format (printf, 1, 2))); +extern int printk(const char *fmt, ...) + __attribute__ ((format (printf, 1, 2))); extern void schedule(void); extern void *um_kmalloc(int size); extern void *um_kmalloc_atomic(int size); diff --git a/arch/um/include/user_util.h b/arch/um/include/user_util.h index fe0c29b5144d..802d7842514d 100644 --- a/arch/um/include/user_util.h +++ b/arch/um/include/user_util.h @@ -55,7 +55,8 @@ extern int get_pty(void); extern void *um_kmalloc(int size); extern int switcheroo(int fd, int prot, void *from, void *to, int size); extern void do_exec(int old_pid, int new_pid); -extern void tracer_panic(char *msg, ...); +extern void tracer_panic(char *msg, ...) + __attribute__ ((format (printf, 1, 2))); extern int detach(int pid, int sig); extern int attach(int pid); extern void kill_child_dead(int pid); diff --git a/arch/um/kernel/ksyms.c b/arch/um/kernel/ksyms.c index 7713e7a6f476..432cf0b97a13 100644 --- a/arch/um/kernel/ksyms.c +++ b/arch/um/kernel/ksyms.c @@ -39,7 +39,6 @@ EXPORT_SYMBOL(um_virt_to_phys); EXPORT_SYMBOL(mode_tt); EXPORT_SYMBOL(handle_page_fault); EXPORT_SYMBOL(find_iomem); -EXPORT_SYMBOL(end_iomem); #ifdef CONFIG_MODE_TT EXPORT_SYMBOL(strncpy_from_user_tt); @@ -89,12 +88,10 @@ EXPORT_SYMBOL(dump_thread); EXPORT_SYMBOL(do_gettimeofday); EXPORT_SYMBOL(do_settimeofday); -/* This is here because UML expands open to sys_open, not to a system +/* This is here because UML expands lseek to sys_lseek, not to a system * call instruction. */ -EXPORT_SYMBOL(sys_open); EXPORT_SYMBOL(sys_lseek); -EXPORT_SYMBOL(sys_read); EXPORT_SYMBOL(sys_wait4); #ifdef CONFIG_SMP diff --git a/arch/um/os-Linux/drivers/ethertap_user.c b/arch/um/os-Linux/drivers/ethertap_user.c index 901b85e8a1c6..8f49507e64ef 100644 --- a/arch/um/os-Linux/drivers/ethertap_user.c +++ b/arch/um/os-Linux/drivers/ethertap_user.c @@ -40,7 +40,7 @@ static void etap_change(int op, unsigned char *addr, unsigned char *netmask, int fd) { struct addr_change change; - void *output; + char *output; int n; change.what = op; diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index 6490a4ff40ac..6987d1d247a2 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -43,7 +43,7 @@ static int helper_child(void *arg) (*data->pre_exec)(data->pre_data); execvp(argv[0], argv); errval = errno; - printk("execvp of '%s' failed - errno = %d\n", argv[0], errno); + printk("helper_child - execve of '%s' failed - errno = %d\n", argv[0], errno); os_write_file(data->fd, &errval, sizeof(errval)); kill(os_getpid(), SIGKILL); return(0); @@ -92,15 +92,15 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv, close(fds[1]); fds[1] = -1; - /*Read the errno value from the child.*/ + /* Read the errno value from the child, if the exec failed, or get 0 if + * the exec succeeded because the pipe fd was set as close-on-exec. */ n = os_read_file(fds[0], &ret, sizeof(ret)); - if(n < 0){ + if (n < 0) { printk("run_helper : read on pipe failed, ret = %d\n", -n); ret = n; kill(pid, SIGKILL); CATCH_EINTR(waitpid(pid, NULL, 0)); - } - else if(n != 0){ + } else if(n != 0){ CATCH_EINTR(n = waitpid(pid, NULL, 0)); ret = -errno; } else { diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c index 6ab372da9657..71bb90a7606d 100644 --- a/arch/um/os-Linux/mem.c +++ b/arch/um/os-Linux/mem.c @@ -53,33 +53,36 @@ static void __init find_tempdir(void) */ int make_tempfile(const char *template, char **out_tempname, int do_unlink) { - char tempname[MAXPATHLEN]; + char *tempname; int fd; + tempname = malloc(MAXPATHLEN); + find_tempdir(); - if (*template != '/') + if (template[0] != '/') strcpy(tempname, tempdir); else - *tempname = 0; + tempname[0] = '\0'; strcat(tempname, template); fd = mkstemp(tempname); if(fd < 0){ fprintf(stderr, "open - cannot create %s: %s\n", tempname, strerror(errno)); - return -1; + goto out; } if(do_unlink && (unlink(tempname) < 0)){ perror("unlink"); - return -1; + goto out; } if(out_tempname){ - *out_tempname = strdup(tempname); - if(*out_tempname == NULL){ - perror("strdup"); - return -1; - } + *out_tempname = tempname; + } else { + free(tempname); } return(fd); +out: + free(tempname); + return -1; } #define TEMPNAME_TEMPLATE "vm_file-XXXXXX" diff --git a/arch/um/os-Linux/sigio.c b/arch/um/os-Linux/sigio.c index 9ba942947146..00e9388e947a 100644 --- a/arch/um/os-Linux/sigio.c +++ b/arch/um/os-Linux/sigio.c @@ -304,8 +304,8 @@ out_clear_poll: .size = 0, .used = 0 }); out_free: - kfree(p); sigio_unlock(); + kfree(p); out_close2: close(l_sigio_private[0]); close(l_sigio_private[1]); diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c index fbb080c2fc26..b3c11cfa995a 100644 --- a/arch/um/os-Linux/skas/mem.c +++ b/arch/um/os-Linux/skas/mem.c @@ -82,8 +82,8 @@ static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr) if (offset) { data = (unsigned long *)(mm_idp->stack + offset - UML_CONFIG_STUB_DATA); - printk("do_syscall_stub : ret = %d, offset = %d, " - "data = 0x%x\n", ret, offset, data); + printk("do_syscall_stub : ret = %ld, offset = %ld, " + "data = %p\n", ret, offset, data); syscall = (unsigned long *)((unsigned long)data + data[0]); printk("do_syscall_stub: syscall %ld failed, return value = " "0x%lx, expected return value = 0x%lx\n", diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index bbf34cb91ce1..045ae0037456 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -265,7 +265,7 @@ void userspace(union uml_pt_regs *regs) if(err) panic("userspace - could not resume userspace process, " "pid=%d, ptrace operation = %d, errno = %d\n", - op, errno); + pid, op, errno); CATCH_EINTR(err = waitpid(pid, &status, WUNTRACED)); if(err < 0) @@ -369,7 +369,7 @@ int copy_context_skas0(unsigned long new_stack, int pid) */ wait_stub_done(pid, -1, "copy_context_skas0"); if (child_data->err != UML_CONFIG_STUB_DATA) - panic("copy_context_skas0 - stub-child reports error %d\n", + panic("copy_context_skas0 - stub-child reports error %ld\n", child_data->err); if (ptrace(PTRACE_OLDSETOPTIONS, pid, NULL, diff --git a/arch/um/os-Linux/sys-i386/tls.c b/arch/um/os-Linux/sys-i386/tls.c index ba21f0e04a2f..120abbe4e3ce 100644 --- a/arch/um/os-Linux/sys-i386/tls.c +++ b/arch/um/os-Linux/sys-i386/tls.c @@ -1,3 +1,4 @@ +#include <errno.h> #include <linux/unistd.h> #include "sysdep/tls.h" #include "user_util.h" diff --git a/arch/um/os-Linux/umid.c b/arch/um/os-Linux/umid.c index 198e59163288..34bfc1bb9e38 100644 --- a/arch/um/os-Linux/umid.c +++ b/arch/um/os-Linux/umid.c @@ -120,7 +120,8 @@ static int not_dead_yet(char *dir) dead = 0; fd = open(file, O_RDONLY); - if(fd < 0){ + if(fd < 0) { + fd = -errno; if(fd != -ENOENT){ printk("not_dead_yet : couldn't open pid file '%s', " "err = %d\n", file, -fd); @@ -130,9 +131,13 @@ static int not_dead_yet(char *dir) err = 0; n = read(fd, pid, sizeof(pid)); - if(n <= 0){ + if(n < 0){ + printk("not_dead_yet : couldn't read pid file '%s', " + "err = %d\n", file, errno); + goto out_close; + } else if(n == 0){ printk("not_dead_yet : couldn't read pid file '%s', " - "err = %d\n", file, -n); + "0-byte read\n", file); goto out_close; } @@ -155,9 +160,9 @@ static int not_dead_yet(char *dir) return err; - out_close: +out_close: close(fd); - out: +out: return 0; } diff --git a/arch/um/os-Linux/user_syms.c b/arch/um/os-Linux/user_syms.c index 8da6ab31152a..2598158e1f53 100644 --- a/arch/um/os-Linux/user_syms.c +++ b/arch/um/os-Linux/user_syms.c @@ -18,14 +18,19 @@ extern void *memmove(void *, const void *, size_t); extern void *memset(void *, int, size_t); extern int printf(const char *, ...); +/* If they're not defined, the export is included in lib/string.c.*/ +#ifdef __HAVE_ARCH_STRLEN EXPORT_SYMBOL(strlen); +#endif +#ifdef __HAVE_ARCH_STRSTR +EXPORT_SYMBOL(strstr); +#endif + EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(printf); -EXPORT_SYMBOL(strstr); - /* Here, instead, I can provide a fake prototype. Yes, someone cares: genksyms. * However, the modules will use the CRC defined *here*, no matter if it is * good; so the versions of these symbols will always match diff --git a/arch/um/scripts/Makefile.rules b/arch/um/scripts/Makefile.rules index b696b451774c..5e7a9c310aa5 100644 --- a/arch/um/scripts/Makefile.rules +++ b/arch/um/scripts/Makefile.rules @@ -9,10 +9,8 @@ USER_OBJS := $(foreach file,$(USER_OBJS),$(obj)/$(file)) $(USER_OBJS) $(USER_OBJS:.o=.i) $(USER_OBJS:.o=.s) $(USER_OBJS:.o=.lst): \ c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) $(CFLAGS_$(notdir $@)) -$(USER_OBJS): cmd_checksrc = -$(USER_OBJS): quiet_cmd_checksrc = -$(USER_OBJS): cmd_force_checksrc = -$(USER_OBJS): quiet_cmd_force_checksrc = +$(USER_OBJS) : CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ \ + -Dunix -D__unix__ -D__$(SUBARCH)__ # The stubs and unmap.o can't try to call mcount or update basic block data diff --git a/arch/um/sys-i386/ksyms.c b/arch/um/sys-i386/ksyms.c index db524ab3f743..2a1eac1859ce 100644 --- a/arch/um/sys-i386/ksyms.c +++ b/arch/um/sys-i386/ksyms.c @@ -15,7 +15,3 @@ EXPORT_SYMBOL(__up_wakeup); /* Networking helper routines. */ EXPORT_SYMBOL(csum_partial); - -/* delay core functions */ -EXPORT_SYMBOL(__const_udelay); -EXPORT_SYMBOL(__udelay); diff --git a/arch/um/sys-i386/ptrace_user.c b/arch/um/sys-i386/ptrace_user.c index 9f3bd8ed78f5..40aa88531446 100644 --- a/arch/um/sys-i386/ptrace_user.c +++ b/arch/um/sys-i386/ptrace_user.c @@ -57,7 +57,7 @@ static void write_debugregs(int pid, unsigned long *regs) if(ptrace(PTRACE_POKEUSR, pid, &dummy->u_debugreg[i], regs[i]) < 0) printk("write_debugregs - ptrace failed on " - "register %d, value = 0x%x, errno = %d\n", i, + "register %d, value = 0x%lx, errno = %d\n", i, regs[i], errno); } } diff --git a/arch/um/sys-i386/signal.c b/arch/um/sys-i386/signal.c index f5d0e1c37ea2..618fd8594643 100644 --- a/arch/um/sys-i386/signal.c +++ b/arch/um/sys-i386/signal.c @@ -147,7 +147,7 @@ int copy_sc_to_user_tt(struct sigcontext *to, struct _fpstate __user *fp, * delivery. The sp passed in is the original, and this needs * to be restored, so we stick it in separately. */ - err |= copy_to_user(&SC_SP(to), sp, sizeof(sp)); + err |= copy_to_user(&SC_SP(to), &sp, sizeof(sp)); if(from_fp != NULL){ err |= copy_to_user(&to->fpstate, &to_fp, sizeof(to->fpstate)); diff --git a/arch/um/sys-i386/tls.c b/arch/um/sys-i386/tls.c index a3188e861cc7..71b9796258ef 100644 --- a/arch/um/sys-i386/tls.c +++ b/arch/um/sys-i386/tls.c @@ -378,7 +378,7 @@ static int __init __setup_host_supports_tls(void) { } else printk(KERN_ERR " Host TLS support NOT detected! " "TLS support inside UML will not work\n"); - return 1; + return 0; } __initcall(__setup_host_supports_tls); diff --git a/arch/um/sys-x86_64/signal.c b/arch/um/sys-x86_64/signal.c index e75c4e1838b0..a4c46a8af008 100644 --- a/arch/um/sys-x86_64/signal.c +++ b/arch/um/sys-x86_64/signal.c @@ -137,7 +137,7 @@ int copy_sc_to_user_tt(struct sigcontext *to, struct _fpstate *fp, * delivery. The sp passed in is the original, and this needs * to be restored, so we stick it in separately. */ - err |= copy_to_user(&SC_SP(to), sp, sizeof(sp)); + err |= copy_to_user(&SC_SP(to), &sp, sizeof(sp)); if(from_fp != NULL){ err |= copy_to_user(&to->fpstate, &to_fp, sizeof(to->fpstate)); diff --git a/arch/v850/kernel/v850_ksyms.c b/arch/v850/kernel/v850_ksyms.c index 8ffc29c1c89d..6bcfcfe88384 100644 --- a/arch/v850/kernel/v850_ksyms.c +++ b/arch/v850/kernel/v850_ksyms.c @@ -43,7 +43,6 @@ EXPORT_SYMBOL (strncmp); EXPORT_SYMBOL (strchr); EXPORT_SYMBOL (strlen); EXPORT_SYMBOL (strnlen); -EXPORT_SYMBOL (strpbrk); EXPORT_SYMBOL (strrchr); EXPORT_SYMBOL (strstr); EXPORT_SYMBOL (memset); diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig index 4310b4a311a5..408d44a59756 100644 --- a/arch/x86_64/Kconfig +++ b/arch/x86_64/Kconfig @@ -136,6 +136,11 @@ config X86_L1_CACHE_SHIFT default "7" if GENERIC_CPU || MPSC default "6" if MK8 +config X86_INTERNODE_CACHE_BYTES + int + default "4096" if X86_VSMP + default X86_L1_CACHE_BYTES if !X86_VSMP + config X86_TSC bool default y @@ -283,6 +288,11 @@ config K8_NUMA Northbridge of Opteron. It is recommended to use X86_64_ACPI_NUMA instead, which also takes priority if both are compiled in. +config NODES_SHIFT + int + default "6" + depends on NEED_MULTIPLE_NODES + # Dummy CONFIG option to select ACPI_NUMA from drivers/acpi/Kconfig. config X86_64_ACPI_NUMA diff --git a/arch/x86_64/Makefile b/arch/x86_64/Makefile index 585fd4a559c8..e573e2ab5510 100644 --- a/arch/x86_64/Makefile +++ b/arch/x86_64/Makefile @@ -24,37 +24,37 @@ LDFLAGS := -m elf_x86_64 OBJCOPYFLAGS := -O binary -R .note -R .comment -S LDFLAGS_vmlinux := - CHECKFLAGS += -D__x86_64__ -m64 +cflags-y := cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic) -CFLAGS += $(cflags-y) -CFLAGS += -m64 -CFLAGS += -mno-red-zone -CFLAGS += -mcmodel=kernel -CFLAGS += -pipe +cflags-y += -m64 +cflags-y += -mno-red-zone +cflags-y += -mcmodel=kernel +cflags-y += -pipe cflags-$(CONFIG_REORDER) += -ffunction-sections # this makes reading assembly source easier, but produces worse code # actually it makes the kernel smaller too. -CFLAGS += -fno-reorder-blocks -CFLAGS += -Wno-sign-compare +cflags-y += -fno-reorder-blocks +cflags-y += -Wno-sign-compare ifneq ($(CONFIG_UNWIND_INFO),y) -CFLAGS += -fno-asynchronous-unwind-tables +cflags-y += -fno-asynchronous-unwind-tables endif ifneq ($(CONFIG_DEBUG_INFO),y) # -fweb shrinks the kernel a bit, but the difference is very small # it also messes up debugging, so don't use it for now. -#CFLAGS += $(call cc-option,-fweb) +#cflags-y += $(call cc-option,-fweb) endif # -funit-at-a-time shrinks the kernel .text considerably # unfortunately it makes reading oopses harder. -CFLAGS += $(call cc-option,-funit-at-a-time) +cflags-y += $(call cc-option,-funit-at-a-time) # prevent gcc from generating any FP code by mistake -CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,) +cflags-y += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,) +CFLAGS += $(cflags-y) AFLAGS += -m64 head-y := arch/x86_64/kernel/head.o arch/x86_64/kernel/head64.o arch/x86_64/kernel/init_task.o diff --git a/arch/x86_64/boot/video.S b/arch/x86_64/boot/video.S index 0587477c99f2..32327bb37aff 100644 --- a/arch/x86_64/boot/video.S +++ b/arch/x86_64/boot/video.S @@ -97,6 +97,7 @@ #define PARAM_VESAPM_OFF 0x30 #define PARAM_LFB_PAGES 0x32 #define PARAM_VESA_ATTRIB 0x34 +#define PARAM_CAPABILITIES 0x36 /* Define DO_STORE according to CONFIG_VIDEO_RETAIN */ #ifdef CONFIG_VIDEO_RETAIN @@ -233,6 +234,10 @@ mopar_gr: movw 18(%di), %ax movl %eax, %fs:(PARAM_LFB_SIZE) +# store mode capabilities + movl 10(%di), %eax + movl %eax, %fs:(PARAM_CAPABILITIES) + # switching the DAC to 8-bit is for <= 8 bpp only movw %fs:(PARAM_LFB_DEPTH), %ax cmpw $8, %ax diff --git a/arch/x86_64/defconfig b/arch/x86_64/defconfig index 566ecc97ee5a..3c45ec22b3fe 100644 --- a/arch/x86_64/defconfig +++ b/arch/x86_64/defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.16-git9 -# Sat Mar 25 15:18:40 2006 +# Linux kernel version: 2.6.17-rc1 +# Mon Apr 3 16:11:14 2006 # CONFIG_X86_64=y CONFIG_64BIT=y @@ -9,6 +9,7 @@ CONFIG_X86=y CONFIG_SEMAPHORE_SLEEPERS=y CONFIG_MMU=y CONFIG_RWSEM_GENERIC_SPINLOCK=y +CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_X86_CMPXCHG=y CONFIG_EARLY_PRINTK=y @@ -55,10 +56,6 @@ CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_EPOLL=y CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 CONFIG_SLAB=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 @@ -70,7 +67,6 @@ CONFIG_BASE_SMALL=0 CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_OBSOLETE_MODPARM=y # CONFIG_MODVERSIONS is not set # CONFIG_MODULE_SRCVERSION_ALL is not set # CONFIG_KMOD is not set @@ -81,6 +77,7 @@ CONFIG_STOP_MACHINE=y # CONFIG_LBD=y # CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_LSF is not set # # IO Schedulers @@ -105,6 +102,7 @@ CONFIG_X86_PC=y CONFIG_GENERIC_CPU=y CONFIG_X86_L1_CACHE_BYTES=128 CONFIG_X86_L1_CACHE_SHIFT=7 +CONFIG_X86_INTERNODE_CACHE_BYTES=128 CONFIG_X86_TSC=y CONFIG_X86_GOOD_APIC=y # CONFIG_MICROCODE is not set @@ -116,6 +114,7 @@ CONFIG_X86_LOCAL_APIC=y CONFIG_MTRR=y CONFIG_SMP=y CONFIG_SCHED_SMT=y +CONFIG_SCHED_MC=y # CONFIG_PREEMPT_NONE is not set CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_PREEMPT is not set @@ -138,6 +137,7 @@ CONFIG_NEED_MULTIPLE_NODES=y CONFIG_SPLIT_PTLOCK_CPUS=4 CONFIG_MIGRATION=y CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y +CONFIG_OUT_OF_LINE_PFN_TO_PAGE=y CONFIG_NR_CPUS=32 CONFIG_HOTPLUG_CPU=y CONFIG_HPET_TIMER=y @@ -289,6 +289,7 @@ CONFIG_IP_PNP_DHCP=y # CONFIG_INET_AH is not set # CONFIG_INET_ESP is not set # CONFIG_INET_IPCOMP is not set +# CONFIG_INET_XFRM_TUNNEL is not set # CONFIG_INET_TUNNEL is not set CONFIG_INET_DIAG=y CONFIG_INET_TCP_DIAG=y @@ -300,6 +301,7 @@ CONFIG_IPV6=y # CONFIG_INET6_AH is not set # CONFIG_INET6_ESP is not set # CONFIG_INET6_IPCOMP is not set +# CONFIG_INET6_XFRM_TUNNEL is not set # CONFIG_INET6_TUNNEL is not set # CONFIG_IPV6_TUNNEL is not set # CONFIG_NETFILTER is not set @@ -704,7 +706,6 @@ CONFIG_S2IO=m # Wireless LAN (non-hamradio) # # CONFIG_NET_RADIO is not set -# CONFIG_NET_WIRELESS_RTNETLINK is not set # # Wan interfaces @@ -791,7 +792,7 @@ CONFIG_HW_CONSOLE=y # CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y -# CONFIG_SERIAL_8250_ACPI is not set +CONFIG_SERIAL_8250_PCI=y CONFIG_SERIAL_8250_NR_UARTS=4 CONFIG_SERIAL_8250_RUNTIME_UARTS=4 # CONFIG_SERIAL_8250_EXTENDED is not set @@ -921,6 +922,7 @@ CONFIG_HWMON=y # Digital Video Broadcasting Devices # # CONFIG_DVB is not set +# CONFIG_USB_DABUSB is not set # # Graphics support @@ -932,6 +934,8 @@ CONFIG_VIDEO_SELECT=y # Console display driver support # CONFIG_VGA_CONSOLE=y +CONFIG_VGACON_SOFT_SCROLLBACK=y +CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=256 CONFIG_DUMMY_CONSOLE=y # @@ -1058,15 +1062,6 @@ CONFIG_USB_HIDINPUT=y # CONFIG_USB_MICROTEK is not set # -# USB Multimedia devices -# -# CONFIG_USB_DABUSB is not set - -# -# Video4Linux support is needed for USB Multimedia device support -# - -# # USB Network Adapters # # CONFIG_USB_CATC is not set @@ -1118,9 +1113,15 @@ CONFIG_USB_MON=y # CONFIG_MMC is not set # +# LED devices +# +# CONFIG_NEW_LEDS is not set + +# # InfiniBand support # # CONFIG_INFINIBAND is not set +# CONFIG_IPATH_CORE is not set # # EDAC - error detection and reporting (RAS) (EXPERIMENTAL) @@ -1128,6 +1129,11 @@ CONFIG_USB_MON=y # CONFIG_EDAC is not set # +# Real Time Clock +# +# CONFIG_RTC_CLASS is not set + +# # Firmware Drivers # # CONFIG_EDD is not set diff --git a/arch/x86_64/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S index 35b2faccdc6c..5a9802676689 100644 --- a/arch/x86_64/ia32/ia32entry.S +++ b/arch/x86_64/ia32/ia32entry.S @@ -15,6 +15,8 @@ #include <asm/vsyscall32.h> #include <linux/linkage.h> +#define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8) + .macro IA32_ARG_FIXUP noebp=0 movl %edi,%r8d .if \noebp @@ -109,8 +111,8 @@ ENTRY(ia32_sysenter_target) CFI_REMEMBER_STATE jnz sysenter_tracesys sysenter_do_call: - cmpl $(IA32_NR_syscalls),%eax - jae ia32_badsys + cmpl $(IA32_NR_syscalls-1),%eax + ja ia32_badsys IA32_ARG_FIXUP 1 call *ia32_sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) @@ -210,8 +212,8 @@ ENTRY(ia32_cstar_target) CFI_REMEMBER_STATE jnz cstar_tracesys cstar_do_call: - cmpl $IA32_NR_syscalls,%eax - jae ia32_badsys + cmpl $IA32_NR_syscalls-1,%eax + ja ia32_badsys IA32_ARG_FIXUP 1 call *ia32_sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) @@ -296,8 +298,8 @@ ENTRY(ia32_syscall) testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) jnz ia32_tracesys ia32_do_syscall: - cmpl $(IA32_NR_syscalls),%eax - jae ia32_badsys + cmpl $(IA32_NR_syscalls-1),%eax + ja ia32_badsys IA32_ARG_FIXUP call *ia32_sys_call_table(,%rax,8) # xxx: rip relative ia32_sysret: @@ -685,12 +687,11 @@ ia32_sys_call_table: .quad sys_readlinkat /* 305 */ .quad sys_fchmodat .quad sys_faccessat - .quad sys_ni_syscall /* pselect6 for now */ - .quad sys_ni_syscall /* ppoll for now */ + .quad quiet_ni_syscall /* pselect6 for now */ + .quad quiet_ni_syscall /* ppoll for now */ .quad sys_unshare /* 310 */ .quad compat_sys_set_robust_list .quad compat_sys_get_robust_list + .quad sys_splice + .quad sys_sync_file_range ia32_syscall_end: - .rept IA32_NR_syscalls-(ia32_syscall_end-ia32_sys_call_table)/8 - .quad ni_syscall - .endr diff --git a/arch/x86_64/kernel/aperture.c b/arch/x86_64/kernel/aperture.c index fffd6b0a2fab..70b9d21ed675 100644 --- a/arch/x86_64/kernel/aperture.c +++ b/arch/x86_64/kernel/aperture.c @@ -80,7 +80,7 @@ static int __init aperture_valid(char *name, u64 aper_base, u32 aper_size) printk("Aperture from %s beyond 4GB. Ignoring.\n",name); return 0; } - if (e820_mapped(aper_base, aper_base + aper_size, E820_RAM)) { + if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) { printk("Aperture from %s pointing to e820 RAM. Ignoring.\n",name); return 0; } diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c index 293cd71a266a..62776c07cff1 100644 --- a/arch/x86_64/kernel/e820.c +++ b/arch/x86_64/kernel/e820.c @@ -80,7 +80,12 @@ static inline int bad_addr(unsigned long *addrp, unsigned long size) return 0; } -int __init e820_mapped(unsigned long start, unsigned long end, unsigned type) +/* + * This function checks if any part of the range <start,end> is mapped + * with type. + */ +int __meminit +e820_any_mapped(unsigned long start, unsigned long end, unsigned type) { int i; for (i = 0; i < e820.nr_map; i++) { @@ -94,6 +99,35 @@ int __init e820_mapped(unsigned long start, unsigned long end, unsigned type) return 0; } +/* + * This function checks if the entire range <start,end> is mapped with type. + * + * Note: this function only works correct if the e820 table is sorted and + * not-overlapping, which is the case + */ +int __init e820_all_mapped(unsigned long start, unsigned long end, unsigned type) +{ + int i; + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + if (type && ei->type != type) + continue; + /* is the region (part) in overlap with the current region ?*/ + if (ei->addr >= end || ei->addr + ei->size <= start) + continue; + + /* if the region is at the beginning of <start,end> we move + * start to the end of the region since it's ok until there + */ + if (ei->addr <= start) + start = ei->addr + ei->size; + /* if start is now at or beyond end, we're done, full coverage */ + if (start >= end) + return 1; /* we're done */ + } + return 0; +} + /* * Find a free area in a specific range. */ diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S index 8538bfea30e6..c946e4fe67a7 100644 --- a/arch/x86_64/kernel/entry.S +++ b/arch/x86_64/kernel/entry.S @@ -180,6 +180,10 @@ rff_trace: * * XXX if we had a free scratch register we could save the RSP into the stack frame * and report it properly in ps. Unfortunately we haven't. + * + * When user can change the frames always force IRET. That is because + * it deals with uncanonical addresses better. SYSRET has trouble + * with them due to bugs in both AMD and Intel CPUs. */ ENTRY(system_call) @@ -254,7 +258,10 @@ sysret_signal: xorl %esi,%esi # oldset -> arg2 call ptregscall_common 1: movl $_TIF_NEED_RESCHED,%edi - jmp sysret_check + /* Use IRET because user could have changed frame. This + works because ptregscall_common has called FIXUP_TOP_OF_STACK. */ + cli + jmp int_with_check badsys: movq $-ENOSYS,RAX-ARGOFFSET(%rsp) @@ -280,7 +287,8 @@ tracesys: call syscall_trace_leave RESTORE_TOP_OF_STACK %rbx RESTORE_REST - jmp ret_from_sys_call + /* Use IRET because user could have changed frame */ + jmp int_ret_from_sys_call CFI_ENDPROC /* @@ -408,25 +416,9 @@ ENTRY(stub_execve) CFI_ADJUST_CFA_OFFSET -8 CFI_REGISTER rip, r11 SAVE_REST - movq %r11, %r15 - CFI_REGISTER rip, r15 FIXUP_TOP_OF_STACK %r11 call sys_execve - GET_THREAD_INFO(%rcx) - bt $TIF_IA32,threadinfo_flags(%rcx) - CFI_REMEMBER_STATE - jc exec_32bit RESTORE_TOP_OF_STACK %r11 - movq %r15, %r11 - CFI_REGISTER rip, r11 - RESTORE_REST - pushq %r11 - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rip, 0 - ret - -exec_32bit: - CFI_RESTORE_STATE movq %rax,RAX(%rsp) RESTORE_REST jmp int_ret_from_sys_call diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c index 10b3e348fc99..6f0790e8b6d3 100644 --- a/arch/x86_64/kernel/mce.c +++ b/arch/x86_64/kernel/mce.c @@ -29,6 +29,8 @@ #define MISC_MCELOG_MINOR 227 #define NR_BANKS 6 +atomic_t mce_entry; + static int mce_dont_init; /* 0: always panic, 1: panic if deadlock possible, 2: try to avoid panic, @@ -172,10 +174,12 @@ void do_machine_check(struct pt_regs * regs, long error_code) int i; int panicm_found = 0; + atomic_inc(&mce_entry); + if (regs) notify_die(DIE_NMI, "machine check", regs, error_code, 18, SIGKILL); if (!banks) - return; + goto out2; memset(&m, 0, sizeof(struct mce)); m.cpu = safe_smp_processor_id(); @@ -266,6 +270,8 @@ void do_machine_check(struct pt_regs * regs, long error_code) out: /* Last thing done in the machine check exception to clear state. */ wrmsrl(MSR_IA32_MCG_STATUS, 0); + out2: + atomic_dec(&mce_entry); } /* diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c index d9e4067faf05..4e6357fe0ec3 100644 --- a/arch/x86_64/kernel/nmi.c +++ b/arch/x86_64/kernel/nmi.c @@ -34,6 +34,7 @@ #include <asm/proto.h> #include <asm/kdebug.h> #include <asm/local.h> +#include <asm/mce.h> /* * lapic_nmi_owner tracks the ownership of the lapic NMI hardware: @@ -480,6 +481,12 @@ void __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) __get_cpu_var(nmi_touch) = 0; touched = 1; } +#ifdef CONFIG_X86_MCE + /* Could check oops_in_progress here too, but it's safer + not too */ + if (atomic_read(&mce_entry) > 0) + touched = 1; +#endif if (!touched && __get_cpu_var(last_irq_sum) == sum) { /* * Ayiee, looks like this CPU is stuck ... diff --git a/arch/x86_64/kernel/pci-dma.c b/arch/x86_64/kernel/pci-dma.c index 03c9eeedb0f3..af035ede70cd 100644 --- a/arch/x86_64/kernel/pci-dma.c +++ b/arch/x86_64/kernel/pci-dma.c @@ -48,9 +48,11 @@ dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order) { struct page *page; int node; +#ifdef CONFIG_PCI if (dev->bus == &pci_bus_type) node = pcibus_to_node(to_pci_dev(dev)->bus); else +#endif node = numa_node_id(); page = alloc_pages_node(node, gfp, order); return page ? page_address(page) : NULL; diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c index 70dd8e5c6889..1c44b53cb15b 100644 --- a/arch/x86_64/kernel/process.c +++ b/arch/x86_64/kernel/process.c @@ -781,10 +781,16 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) } case ARCH_GET_GS: { unsigned long base; + unsigned gsindex; if (task->thread.gsindex == GS_TLS_SEL) base = read_32bit_tls(task, GS_TLS); - else if (doit) - rdmsrl(MSR_KERNEL_GS_BASE, base); + else if (doit) { + asm("movl %%gs,%0" : "=r" (gsindex)); + if (gsindex) + rdmsrl(MSR_KERNEL_GS_BASE, base); + else + base = task->thread.gs; + } else base = task->thread.gs; ret = put_user(base, (unsigned long __user *)addr); diff --git a/arch/x86_64/kernel/ptrace.c b/arch/x86_64/kernel/ptrace.c index d44b2c1e63a6..da8e7903d817 100644 --- a/arch/x86_64/kernel/ptrace.c +++ b/arch/x86_64/kernel/ptrace.c @@ -274,11 +274,6 @@ static int putreg(struct task_struct *child, return -EIO; value &= 0xffff; break; - case offsetof(struct user_regs_struct, rip): - /* Check if the new RIP address is canonical */ - if (value >= TASK_SIZE_OF(child)) - return -EIO; - break; } put_stack_long(child, regno - sizeof(struct pt_regs), value); return 0; diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c index 0856ad444f90..c50b06765a80 100644 --- a/arch/x86_64/kernel/setup.c +++ b/arch/x86_64/kernel/setup.c @@ -353,8 +353,10 @@ static __init void parse_cmdline_early (char ** cmdline_p) if (fullarg(from, "enable_timer_pin_1")) disable_timer_pin_1 = -1; - if (fullarg(from, "nolapic") || fullarg(from, "disableapic")) + if (fullarg(from, "nolapic") || fullarg(from, "disableapic")) { + clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability); disable_apic = 1; + } if (fullarg(from, "noapic")) skip_ioapic_setup = 1; diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c index ef8bc46dc140..7392570f975d 100644 --- a/arch/x86_64/kernel/time.c +++ b/arch/x86_64/kernel/time.c @@ -726,7 +726,7 @@ static __init int late_hpet_init(void) unsigned int ntimer; if (!vxtime.hpet_address) - return -1; + return 0; memset(&hd, 0, sizeof (hd)); @@ -917,6 +917,8 @@ void __init time_init(void) vxtime.hpet_address = 0; if (hpet_use_timer) { + /* set tick_nsec to use the proper rate for HPET */ + tick_nsec = TICK_NSEC_HPET; cpu_khz = hpet_calibrate_tsc(); timename = "HPET"; #ifdef CONFIG_X86_PM_TIMER diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S index 39ff0708f803..b81f473c4a19 100644 --- a/arch/x86_64/kernel/vmlinux.lds.S +++ b/arch/x86_64/kernel/vmlinux.lds.S @@ -65,7 +65,7 @@ SECTIONS .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) { *(.data.cacheline_aligned) } - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES); .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) { *(.data.read_mostly) } diff --git a/arch/x86_64/kernel/x8664_ksyms.c b/arch/x86_64/kernel/x8664_ksyms.c index d78f46056bda..1def21c9f7cd 100644 --- a/arch/x86_64/kernel/x8664_ksyms.c +++ b/arch/x86_64/kernel/x8664_ksyms.c @@ -112,7 +112,6 @@ EXPORT_SYMBOL_GPL(unset_nmi_callback); #undef memcpy #undef memset #undef memmove -#undef strlen extern void * memset(void *,int,__kernel_size_t); extern size_t strlen(const char *); @@ -121,8 +120,6 @@ extern void * memcpy(void *,const void *,__kernel_size_t); extern void * __memcpy(void *,const void *,__kernel_size_t); EXPORT_SYMBOL(memset); -EXPORT_SYMBOL(strlen); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(__memcpy); diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c index e5f7f1c34462..4ba34e95d835 100644 --- a/arch/x86_64/mm/init.c +++ b/arch/x86_64/mm/init.c @@ -305,7 +305,7 @@ static void __meminit phys_pud_init(pud_t *pud, unsigned long address, unsigned if (paddr >= end) break; - if (!after_bootmem && !e820_mapped(paddr, paddr+PUD_SIZE, 0)) { + if (!after_bootmem && !e820_any_mapped(paddr, paddr+PUD_SIZE, 0)) { set_pud(pud, __pud(0)); continue; } @@ -507,9 +507,8 @@ void __init clear_kernel_mapping(unsigned long address, unsigned long size) /* * Memory hotplug specific functions - * These are only for non-NUMA machines right now. */ -#ifdef CONFIG_MEMORY_HOTPLUG +#if defined(CONFIG_ACPI_HOTPLUG_MEMORY) || defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE) void online_page(struct page *page) { @@ -520,6 +519,38 @@ void online_page(struct page *page) num_physpages++; } +#ifndef CONFIG_MEMORY_HOTPLUG +/* + * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance, + * just online the pages. + */ +int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages) +{ + int err = -EIO; + unsigned long pfn; + unsigned long total = 0, mem = 0; + for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) { + if (pfn_valid(pfn)) { + online_page(pfn_to_page(pfn)); + err = 0; + mem++; + } + total++; + } + if (!err) { + z->spanned_pages += total; + z->present_pages += mem; + z->zone_pgdat->node_spanned_pages += total; + z->zone_pgdat->node_present_pages += mem; + } + return err; +} +#endif + +/* + * Memory is added always to NORMAL zone. This means you will never get + * additional DMA/DMA32 memory. + */ int add_memory(u64 start, u64 size) { struct pglist_data *pgdat = NODE_DATA(0); diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c index 4be82d6e2b48..cc02573a3271 100644 --- a/arch/x86_64/mm/numa.c +++ b/arch/x86_64/mm/numa.c @@ -100,11 +100,30 @@ int early_pfn_to_nid(unsigned long pfn) } #endif +static void * __init +early_node_mem(int nodeid, unsigned long start, unsigned long end, + unsigned long size) +{ + unsigned long mem = find_e820_area(start, end, size); + void *ptr; + if (mem != -1L) + return __va(mem); + ptr = __alloc_bootmem_nopanic(size, + SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)); + if (ptr == 0) { + printk(KERN_ERR "Cannot find %lu bytes in node %d\n", + size, nodeid); + return NULL; + } + return ptr; +} + /* Initialize bootmem allocator for a node */ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) { unsigned long start_pfn, end_pfn, bootmap_pages, bootmap_size, bootmap_start; unsigned long nodedata_phys; + void *bootmap; const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE); start = round_up(start, ZONE_ALIGN); @@ -114,13 +133,11 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en start_pfn = start >> PAGE_SHIFT; end_pfn = end >> PAGE_SHIFT; - nodedata_phys = find_e820_area(start, end, pgdat_size); - if (nodedata_phys == -1L) - panic("Cannot find memory pgdat in node %d\n", nodeid); - - Dprintk("nodedata_phys %lx\n", nodedata_phys); + node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size); + if (node_data[nodeid] == NULL) + return; + nodedata_phys = __pa(node_data[nodeid]); - node_data[nodeid] = phys_to_virt(nodedata_phys); memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t)); NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid]; NODE_DATA(nodeid)->node_start_pfn = start_pfn; @@ -129,9 +146,15 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en /* Find a place for the bootmem map */ bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn); bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE); - bootmap_start = find_e820_area(bootmap_start, end, bootmap_pages<<PAGE_SHIFT); - if (bootmap_start == -1L) - panic("Not enough continuous space for bootmap on node %d", nodeid); + bootmap = early_node_mem(nodeid, bootmap_start, end, + bootmap_pages<<PAGE_SHIFT); + if (bootmap == NULL) { + if (nodedata_phys < start || nodedata_phys >= end) + free_bootmem((unsigned long)node_data[nodeid],pgdat_size); + node_data[nodeid] = NULL; + return; + } + bootmap_start = __pa(bootmap); Dprintk("bootmap start %lu pages %lu\n", bootmap_start, bootmap_pages); bootmap_size = init_bootmem_node(NODE_DATA(nodeid), @@ -142,6 +165,9 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size); reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start, bootmap_pages<<PAGE_SHIFT); +#ifdef CONFIG_ACPI_NUMA + srat_reserve_add_area(nodeid); +#endif node_set_online(nodeid); } @@ -335,6 +361,8 @@ __init int numa_setup(char *opt) #ifdef CONFIG_ACPI_NUMA if (!strncmp(opt,"noacpi",6)) acpi_numa = -1; + if (!strncmp(opt,"hotadd=", 7)) + hotadd_percent = simple_strtoul(opt+7, NULL, 10); #endif return 1; } diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c index 2eb879590dc4..15ae9fcd65a7 100644 --- a/arch/x86_64/mm/srat.c +++ b/arch/x86_64/mm/srat.c @@ -15,15 +15,26 @@ #include <linux/bitmap.h> #include <linux/module.h> #include <linux/topology.h> +#include <linux/bootmem.h> +#include <linux/mm.h> #include <asm/proto.h> #include <asm/numa.h> #include <asm/e820.h> +#if (defined(CONFIG_ACPI_HOTPLUG_MEMORY) || \ + defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE)) \ + && !defined(CONFIG_MEMORY_HOTPLUG) +#define RESERVE_HOTADD 1 +#endif + static struct acpi_table_slit *acpi_slit; static nodemask_t nodes_parsed __initdata; static nodemask_t nodes_found __initdata; static struct bootnode nodes[MAX_NUMNODES] __initdata; +static struct bootnode nodes_add[MAX_NUMNODES] __initdata; +static int found_add_area __initdata; +int hotadd_percent __initdata = 10; static u8 pxm2node[256] = { [0 ... 255] = 0xff }; /* Too small nodes confuse the VM badly. Usually they result @@ -71,6 +82,10 @@ static __init int conflicting_nodes(unsigned long start, unsigned long end) static __init void cutoff_node(int i, unsigned long start, unsigned long end) { struct bootnode *nd = &nodes[i]; + + if (found_add_area) + return; + if (nd->start < start) { nd->start = start; if (nd->end < nd->start) @@ -90,6 +105,8 @@ static __init void bad_srat(void) acpi_numa = -1; for (i = 0; i < MAX_LOCAL_APIC; i++) apicid_to_node[i] = NUMA_NO_NODE; + for (i = 0; i < MAX_NUMNODES; i++) + nodes_add[i].start = nodes[i].end = 0; } static __init inline int srat_disabled(void) @@ -155,11 +172,114 @@ acpi_numa_processor_affinity_init(struct acpi_table_processor_affinity *pa) pxm, pa->apic_id, node); } +#ifdef RESERVE_HOTADD +/* + * Protect against too large hotadd areas that would fill up memory. + */ +static int hotadd_enough_memory(struct bootnode *nd) +{ + static unsigned long allocated; + static unsigned long last_area_end; + unsigned long pages = (nd->end - nd->start) >> PAGE_SHIFT; + long mem = pages * sizeof(struct page); + unsigned long addr; + unsigned long allowed; + unsigned long oldpages = pages; + + if (mem < 0) + return 0; + allowed = (end_pfn - e820_hole_size(0, end_pfn)) * PAGE_SIZE; + allowed = (allowed / 100) * hotadd_percent; + if (allocated + mem > allowed) { + /* Give them at least part of their hotadd memory upto hotadd_percent + It would be better to spread the limit out + over multiple hotplug areas, but that is too complicated + right now */ + if (allocated >= allowed) + return 0; + pages = (allowed - allocated + mem) / sizeof(struct page); + mem = pages * sizeof(struct page); + nd->end = nd->start + pages*PAGE_SIZE; + } + /* Not completely fool proof, but a good sanity check */ + addr = find_e820_area(last_area_end, end_pfn<<PAGE_SHIFT, mem); + if (addr == -1UL) + return 0; + if (pages != oldpages) + printk(KERN_NOTICE "SRAT: Hotadd area limited to %lu bytes\n", + pages << PAGE_SHIFT); + last_area_end = addr + mem; + allocated += mem; + return 1; +} + +/* + * It is fine to add this area to the nodes data it will be used later + * This code supports one contigious hot add area per node. + */ +static int reserve_hotadd(int node, unsigned long start, unsigned long end) +{ + unsigned long s_pfn = start >> PAGE_SHIFT; + unsigned long e_pfn = end >> PAGE_SHIFT; + int changed = 0; + struct bootnode *nd = &nodes_add[node]; + + /* I had some trouble with strange memory hotadd regions breaking + the boot. Be very strict here and reject anything unexpected. + If you want working memory hotadd write correct SRATs. + + The node size check is a basic sanity check to guard against + mistakes */ + if ((signed long)(end - start) < NODE_MIN_SIZE) { + printk(KERN_ERR "SRAT: Hotplug area too small\n"); + return -1; + } + + /* This check might be a bit too strict, but I'm keeping it for now. */ + if (e820_hole_size(s_pfn, e_pfn) != e_pfn - s_pfn) { + printk(KERN_ERR "SRAT: Hotplug area has existing memory\n"); + return -1; + } + + if (!hotadd_enough_memory(&nodes_add[node])) { + printk(KERN_ERR "SRAT: Hotplug area too large\n"); + return -1; + } + + /* Looks good */ + + found_add_area = 1; + if (nd->start == nd->end) { + nd->start = start; + nd->end = end; + changed = 1; + } else { + if (nd->start == end) { + nd->start = start; + changed = 1; + } + if (nd->end == start) { + nd->end = end; + changed = 1; + } + if (!changed) + printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n"); + } + + if ((nd->end >> PAGE_SHIFT) > end_pfn) + end_pfn = nd->end >> PAGE_SHIFT; + + if (changed) + printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", nd->start, nd->end); + return 0; +} +#endif + /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ void __init acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) { - struct bootnode *nd; + struct bootnode *nd, oldnode; unsigned long start, end; int node, pxm; int i; @@ -172,6 +292,8 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) } if (ma->flags.enabled == 0) return; + if (ma->flags.hot_pluggable && hotadd_percent == 0) + return; start = ma->base_addr_lo | ((u64)ma->base_addr_hi << 32); end = start + (ma->length_lo | ((u64)ma->length_hi << 32)); pxm = ma->proximity_domain; @@ -181,10 +303,6 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) bad_srat(); return; } - /* It is fine to add this area to the nodes data it will be used later*/ - if (ma->flags.hot_pluggable == 1) - printk(KERN_INFO "SRAT: hot plug zone found %lx - %lx \n", - start, end); i = conflicting_nodes(start, end); if (i == node) { printk(KERN_WARNING @@ -199,6 +317,7 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) return; } nd = &nodes[node]; + oldnode = *nd; if (!node_test_and_set(node, nodes_parsed)) { nd->start = start; nd->end = end; @@ -208,8 +327,19 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) if (nd->end < end) nd->end = end; } + printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm, nd->start, nd->end); + +#ifdef RESERVE_HOTADD + if (ma->flags.hot_pluggable && reserve_hotadd(node, start, end) < 0) { + /* Ignore hotadd region. Undo damage */ + printk(KERN_NOTICE "SRAT: Hotplug region ignored\n"); + *nd = oldnode; + if ((nd->start | nd->end) == 0) + node_clear(node, nodes_parsed); + } +#endif } /* Sanity check to catch more bad SRATs (they are amazingly common). @@ -225,6 +355,9 @@ static int nodes_cover_memory(void) unsigned long e = nodes[i].end >> PAGE_SHIFT; pxmram += e - s; pxmram -= e820_hole_size(s, e); + pxmram -= nodes_add[i].end - nodes_add[i].start; + if ((long)pxmram < 0) + pxmram = 0; } e820ram = end_pfn - e820_hole_size(0, end_pfn); @@ -258,7 +391,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) /* First clean up the node list */ for (i = 0; i < MAX_NUMNODES; i++) { - cutoff_node(i, start, end); + cutoff_node(i, start, end); if ((nodes[i].end - nodes[i].start) < NODE_MIN_SIZE) unparse_node(i); } @@ -282,6 +415,12 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) /* Finally register nodes */ for_each_node_mask(i, nodes_parsed) setup_node_bootmem(i, nodes[i].start, nodes[i].end); + /* Try again in case setup_node_bootmem missed one due + to missing bootmem */ + for_each_node_mask(i, nodes_parsed) + if (!node_online(i)) + setup_node_bootmem(i, nodes[i].start, nodes[i].end); + for (i = 0; i < NR_CPUS; i++) { if (cpu_to_node[i] == NUMA_NO_NODE) continue; @@ -303,6 +442,25 @@ static int node_to_pxm(int n) return 0; } +void __init srat_reserve_add_area(int nodeid) +{ + if (found_add_area && nodes_add[nodeid].end) { + u64 total_mb; + + printk(KERN_INFO "SRAT: Reserving hot-add memory space " + "for node %d at %Lx-%Lx\n", + nodeid, nodes_add[nodeid].start, nodes_add[nodeid].end); + total_mb = (nodes_add[nodeid].end - nodes_add[nodeid].start) + >> PAGE_SHIFT; + total_mb *= sizeof(struct page); + total_mb >>= 20; + printk(KERN_INFO "SRAT: This will cost you %Lu MB of " + "pre-allocated memory.\n", (unsigned long long)total_mb); + reserve_bootmem_node(NODE_DATA(nodeid), nodes_add[nodeid].start, + nodes_add[nodeid].end - nodes_add[nodeid].start); + } +} + int __node_distance(int a, int b) { int index; diff --git a/arch/x86_64/pci/mmconfig.c b/arch/x86_64/pci/mmconfig.c index e616500207e4..a2060e4d5de6 100644 --- a/arch/x86_64/pci/mmconfig.c +++ b/arch/x86_64/pci/mmconfig.c @@ -9,11 +9,16 @@ #include <linux/init.h> #include <linux/acpi.h> #include <linux/bitmap.h> +#include <asm/e820.h> + #include "pci.h" #define MMCONFIG_APER_SIZE (256*1024*1024) +/* Verify the first 16 busses. We assume that systems with more busses + get MCFG right. */ +#define MAX_CHECK_BUS 16 -static DECLARE_BITMAP(fallback_slots, 32); +static DECLARE_BITMAP(fallback_slots, 32*MAX_CHECK_BUS); /* Static virtual mapping of the MMCONFIG aperture */ struct mmcfg_virt { @@ -55,7 +60,8 @@ static char __iomem *get_virt(unsigned int seg, unsigned bus) static char __iomem *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn) { char __iomem *addr; - if (seg == 0 && bus == 0 && test_bit(PCI_SLOT(devfn), fallback_slots)) + if (seg == 0 && bus < MAX_CHECK_BUS && + test_bit(32*bus + PCI_SLOT(devfn), fallback_slots)) return NULL; addr = get_virt(seg, bus); if (!addr) @@ -69,8 +75,10 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus, char __iomem *addr; /* Why do we have this when nobody checks it. How about a BUG()!? -AK */ - if (unlikely(!value || (bus > 255) || (devfn > 255) || (reg > 4095))) + if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095))) { + *value = -1; return -EINVAL; + } addr = pci_dev_base(seg, bus, devfn); if (!addr) @@ -129,21 +137,26 @@ static struct pci_raw_ops pci_mmcfg = { Normally this can be expressed in the MCFG by not listing them and assigning suitable _SEGs, but this isn't implemented in some BIOS. Instead try to discover all devices on bus 0 that are unreachable using MM - and fallback for them. - We only do this for bus 0/seg 0 */ + and fallback for them. */ static __init void unreachable_devices(void) { - int i; - for (i = 0; i < 32; i++) { - u32 val1; - char __iomem *addr; - - pci_conf1_read(0, 0, PCI_DEVFN(i,0), 0, 4, &val1); - if (val1 == 0xffffffff) - continue; - addr = pci_dev_base(0, 0, PCI_DEVFN(i, 0)); - if (addr == NULL|| readl(addr) != val1) { - set_bit(i, fallback_slots); + int i, k; + /* Use the max bus number from ACPI here? */ + for (k = 0; k < MAX_CHECK_BUS; k++) { + for (i = 0; i < 32; i++) { + u32 val1; + char __iomem *addr; + + pci_conf1_read(0, k, PCI_DEVFN(i,0), 0, 4, &val1); + if (val1 == 0xffffffff) + continue; + addr = pci_dev_base(0, k, PCI_DEVFN(i, 0)); + if (addr == NULL|| readl(addr) != val1) { + set_bit(i + 32*k, fallback_slots); + printk(KERN_NOTICE + "PCI: No mmconfig possible on device %x:%x\n", + k, i); + } } } } @@ -161,6 +174,14 @@ void __init pci_mmcfg_init(void) (pci_mmcfg_config[0].base_address == 0)) return; + if (!e820_all_mapped(pci_mmcfg_config[0].base_address, + pci_mmcfg_config[0].base_address + MMCONFIG_APER_SIZE, + E820_RESERVED)) { + printk(KERN_ERR "PCI: BIOS Bug: MCFG area is not E820-reserved\n"); + printk(KERN_ERR "PCI: Not using MMCONFIG.\n"); + return; + } + /* RED-PEN i386 doesn't do _nocache right now */ pci_mmcfg_virt = kmalloc(sizeof(*pci_mmcfg_virt) * pci_mmcfg_config_num, GFP_KERNEL); if (pci_mmcfg_virt == NULL) { diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 152b9370789b..a15b6e3e72c8 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -48,7 +48,6 @@ EXPORT_SYMBOL(memchr); EXPORT_SYMBOL(strcat); EXPORT_SYMBOL(strchr); EXPORT_SYMBOL(strlen); -EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(strncat); EXPORT_SYMBOL(strnlen); EXPORT_SYMBOL(strrchr); |