diff options
Diffstat (limited to 'arch/x86/kernel')
36 files changed, 348 insertions, 543 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 6f81300..21dc1a0 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -37,7 +37,8 @@ obj-$(CONFIG_X86_MSR) += msr.o obj-$(CONFIG_X86_CPUID) += cpuid.o obj-$(CONFIG_MICROCODE) += microcode.o obj-$(CONFIG_PCI) += early-quirks.o -obj-$(CONFIG_APM) += apm_32.o +apm-y := apm_32.o +obj-$(CONFIG_APM) += apm.o obj-$(CONFIG_X86_SMP) += smp_$(BITS).o smpboot_$(BITS).o tsc_sync.o obj-$(CONFIG_X86_32_SMP) += smpcommon_32.o obj-$(CONFIG_X86_64_SMP) += smp_64.o smpboot_64.o tsc_sync.o @@ -74,7 +75,8 @@ ifdef CONFIG_INPUT_PCSPKR obj-y += pcspeaker.o endif -obj-$(CONFIG_SCx200) += scx200_32.o +obj-$(CONFIG_SCx200) += scx200.o +scx200-y += scx200_32.o ### # 64 bit specific files diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index d2a5843..fc8825d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -587,25 +587,6 @@ int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base) EXPORT_SYMBOL(acpi_unregister_ioapic); -static unsigned long __init -acpi_scan_rsdp(unsigned long start, unsigned long length) -{ - unsigned long offset = 0; - unsigned long sig_len = sizeof("RSD PTR ") - 1; - - /* - * Scan all 16-byte boundaries of the physical memory region for the - * RSDP signature. - */ - for (offset = 0; offset < length; offset += 16) { - if (strncmp((char *)(phys_to_virt(start) + offset), "RSD PTR ", sig_len)) - continue; - return (start + offset); - } - - return 0; -} - static int __init acpi_parse_sbf(struct acpi_table_header *table) { struct acpi_table_boot *sb; @@ -748,27 +729,6 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table) return 0; } -unsigned long __init acpi_find_rsdp(void) -{ - unsigned long rsdp_phys = 0; - - if (efi_enabled) { - if (efi.acpi20 != EFI_INVALID_TABLE_ADDR) - return efi.acpi20; - else if (efi.acpi != EFI_INVALID_TABLE_ADDR) - return efi.acpi; - } - /* - * Scan memory looking for the RSDP signature. First search EBDA (low - * memory) paragraphs and then search upper memory (E0000-FFFFF). - */ - rsdp_phys = acpi_scan_rsdp(0, 0x400); - if (!rsdp_phys) - rsdp_phys = acpi_scan_rsdp(0xE0000, 0x20000); - - return rsdp_phys; -} - #ifdef CONFIG_X86_LOCAL_APIC /* * Parse LAPIC entries in MADT diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index cfdb2f3..a0c4d7c 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -3,6 +3,7 @@ # obj-y := intel_cacheinfo.o addon_cpuid_features.o +obj-y += feature_names.o obj-$(CONFIG_X86_32) += common.o proc.o bugs.o obj-$(CONFIG_X86_32) += amd.o diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b7b2142..f86a3c4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -623,16 +623,6 @@ cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE; * They will insert themselves into the cpu_devs structure. * Then, when cpu_init() is called, we can just iterate over that array. */ - -extern int intel_cpu_init(void); -extern int cyrix_init_cpu(void); -extern int nsc_init_cpu(void); -extern int amd_init_cpu(void); -extern int centaur_init_cpu(void); -extern int transmeta_init_cpu(void); -extern int nexgen_init_cpu(void); -extern int umc_init_cpu(void); - void __init early_cpu_init(void) { intel_cpu_init(); @@ -647,7 +637,7 @@ void __init early_cpu_init(void) } /* Make sure %fs is initialized properly in idle threads */ -struct pt_regs * __devinit idle_regs(struct pt_regs *regs) +struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs) { memset(regs, 0, sizeof(struct pt_regs)); regs->fs = __KERNEL_PERCPU; diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index ad6527a..e0b38c3 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -27,3 +27,12 @@ extern void display_cacheinfo(struct cpuinfo_x86 *c); extern void early_init_intel(struct cpuinfo_x86 *c); extern void early_init_amd(struct cpuinfo_x86 *c); +/* Specific CPU type init functions */ +int intel_cpu_init(void); +int amd_init_cpu(void); +int cyrix_init_cpu(void); +int nsc_init_cpu(void); +int centaur_init_cpu(void); +int transmeta_init_cpu(void); +int nexgen_init_cpu(void); +int umc_init_cpu(void); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index a052273..5affe91 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -827,7 +827,6 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpuf for (i = 0; i < data->acpi_data.state_count; i++) { u32 index; - u32 hi = 0, lo = 0; index = data->acpi_data.states[i].control & HW_PSTATE_MASK; if (index > data->max_hw_pstate) { diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c index 76c3ab0..98d4fdb 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c @@ -189,10 +189,7 @@ static unsigned int pentium4_get_frequency(void) printk(KERN_DEBUG "speedstep-lib: couldn't detect FSB speed. Please send an e-mail to <linux@brodo.de>\n"); /* Multiplier. */ - if (c->x86_model < 2) - mult = msr_lo >> 27; - else - mult = msr_lo >> 24; + mult = msr_lo >> 24; dprintk("P4 - FSB %u kHz; Multiplier %u; Speed %u kHz\n", fsb, mult, (fsb * mult)); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 404a6a2..7139b02 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -83,8 +83,6 @@ static char cyrix_model_mult2[] __cpuinitdata = "12233445"; * FIXME: our newer udelay uses the tsc. We don't need to frob with SLOP */ -extern void calibrate_delay(void) __init; - static void __cpuinit check_cx686_slop(struct cpuinfo_x86 *c) { unsigned long flags; diff --git a/arch/x86/kernel/cpu/feature_names.c b/arch/x86/kernel/cpu/feature_names.c new file mode 100644 index 0000000..ee975ac --- /dev/null +++ b/arch/x86/kernel/cpu/feature_names.c @@ -0,0 +1,83 @@ +/* + * Strings for the various x86 capability flags. + * + * This file must not contain any executable code. + */ + +#include "asm/cpufeature.h" + +/* + * These flag bits must match the definitions in <asm/cpufeature.h>. + * NULL means this bit is undefined or reserved; either way it doesn't + * have meaning as far as Linux is concerned. Note that it's important + * to realize there is a difference between this table and CPUID -- if + * applications want to get the raw CPUID data, they should access + * /dev/cpu/<cpu_nr>/cpuid instead. + */ +const char * const x86_cap_flags[NCAPINTS*32] = { + /* Intel-defined */ + "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce", + "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov", + "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx", + "fxsr", "sse", "sse2", "ss", "ht", "tm", "ia64", "pbe", + + /* AMD-defined */ + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL, + NULL, NULL, NULL, "mp", "nx", NULL, "mmxext", NULL, + NULL, "fxsr_opt", "pdpe1gb", "rdtscp", NULL, "lm", + "3dnowext", "3dnow", + + /* Transmeta-defined */ + "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* Other (Linux-defined) */ + "cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr", + NULL, NULL, NULL, NULL, + "constant_tsc", "up", NULL, "arch_perfmon", + "pebs", "bts", NULL, NULL, + "rep_good", NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* Intel-defined (#2) */ + "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est", + "tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL, + NULL, NULL, "dca", "sse4_1", "sse4_2", NULL, NULL, "popcnt", + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* VIA/Cyrix/Centaur-defined */ + NULL, NULL, "rng", "rng_en", NULL, NULL, "ace", "ace_en", + "ace2", "ace2_en", "phe", "phe_en", "pmm", "pmm_en", NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* AMD-defined (#2) */ + "lahf_lm", "cmp_legacy", "svm", "extapic", + "cr8_legacy", "abm", "sse4a", "misalignsse", + "3dnowprefetch", "osvw", "ibs", "sse5", + "skinit", "wdt", NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* Auxiliary (Linux-defined) */ + "ida", NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, +}; + +const char *const x86_power_flags[32] = { + "ts", /* temperature sensor */ + "fid", /* frequency id control */ + "vid", /* voltage id control */ + "ttp", /* thermal trip */ + "tm", + "stc", + "100mhzsteps", + "hwpstate", + "", /* tsc invariant mapped to constant_tsc */ + /* nothing */ +}; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index d1c372b..fae31ce 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -13,6 +13,7 @@ #include <asm/uaccess.h> #include <asm/ptrace.h> #include <asm/ds.h> +#include <asm/bugs.h> #include "cpu.h" diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index 8e139c7..ff14c32 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -7,8 +7,6 @@ #include <asm/processor-flags.h> #include "mtrr.h" -int arr3_protected; - static void cyrix_get_arr(unsigned int reg, unsigned long *base, unsigned long *size, mtrr_type * type) @@ -99,8 +97,6 @@ cyrix_get_free_region(unsigned long base, unsigned long size, int replace_reg) case 4: return replace_reg; case 3: - if (arr3_protected) - break; case 2: case 1: case 0: @@ -115,8 +111,6 @@ cyrix_get_free_region(unsigned long base, unsigned long size, int replace_reg) } else { for (i = 0; i < 7; i++) { cyrix_get_arr(i, &lbase, &lsize, <ype); - if ((i == 3) && arr3_protected) - continue; if (lsize == 0) return i; } @@ -260,107 +254,6 @@ static void cyrix_set_all(void) post_set(); } -#if 0 -/* - * On Cyrix 6x86(MX) and M II the ARR3 is special: it has connection - * with the SMM (System Management Mode) mode. So we need the following: - * Check whether SMI_LOCK (CCR3 bit 0) is set - * if it is set, write a warning message: ARR3 cannot be changed! - * (it cannot be changed until the next processor reset) - * if it is reset, then we can change it, set all the needed bits: - * - disable access to SMM memory through ARR3 range (CCR1 bit 7 reset) - * - disable access to SMM memory (CCR1 bit 2 reset) - * - disable SMM mode (CCR1 bit 1 reset) - * - disable write protection of ARR3 (CCR6 bit 1 reset) - * - (maybe) disable ARR3 - * Just to be sure, we enable ARR usage by the processor (CCR5 bit 5 set) - */ -static void __init -cyrix_arr_init(void) -{ - struct set_mtrr_context ctxt; - unsigned char ccr[7]; - int ccrc[7] = { 0, 0, 0, 0, 0, 0, 0 }; -#ifdef CONFIG_SMP - int i; -#endif - - /* flush cache and enable MAPEN */ - set_mtrr_prepare_save(&ctxt); - set_mtrr_cache_disable(&ctxt); - - /* Save all CCRs locally */ - ccr[0] = getCx86(CX86_CCR0); - ccr[1] = getCx86(CX86_CCR1); - ccr[2] = getCx86(CX86_CCR2); - ccr[3] = ctxt.ccr3; - ccr[4] = getCx86(CX86_CCR4); - ccr[5] = getCx86(CX86_CCR5); - ccr[6] = getCx86(CX86_CCR6); - - if (ccr[3] & 1) { - ccrc[3] = 1; - arr3_protected = 1; - } else { - /* Disable SMM mode (bit 1), access to SMM memory (bit 2) and - * access to SMM memory through ARR3 (bit 7). - */ - if (ccr[1] & 0x80) { - ccr[1] &= 0x7f; - ccrc[1] |= 0x80; - } - if (ccr[1] & 0x04) { - ccr[1] &= 0xfb; - ccrc[1] |= 0x04; - } - if (ccr[1] & 0x02) { - ccr[1] &= 0xfd; - ccrc[1] |= 0x02; - } - arr3_protected = 0; - if (ccr[6] & 0x02) { - ccr[6] &= 0xfd; - ccrc[6] = 1; /* Disable write protection of ARR3 */ - setCx86(CX86_CCR6, ccr[6]); - } - /* Disable ARR3. This is safe now that we disabled SMM. */ - /* cyrix_set_arr_up (3, 0, 0, 0, FALSE); */ - } - /* If we changed CCR1 in memory, change it in the processor, too. */ - if (ccrc[1]) - setCx86(CX86_CCR1, ccr[1]); - - /* Enable ARR usage by the processor */ - if (!(ccr[5] & 0x20)) { - ccr[5] |= 0x20; - ccrc[5] = 1; - setCx86(CX86_CCR5, ccr[5]); - } -#ifdef CONFIG_SMP - for (i = 0; i < 7; i++) - ccr_state[i] = ccr[i]; - for (i = 0; i < 8; i++) - cyrix_get_arr(i, - &arr_state[i].base, &arr_state[i].size, - &arr_state[i].type); -#endif - - set_mtrr_done(&ctxt); /* flush cache and disable MAPEN */ - - if (ccrc[5]) - printk(KERN_INFO "mtrr: ARR usage was not enabled, enabled manually\n"); - if (ccrc[3]) - printk(KERN_INFO "mtrr: ARR3 cannot be changed\n"); -/* - if ( ccrc[1] & 0x80) printk ("mtrr: SMM memory access through ARR3 disabled\n"); - if ( ccrc[1] & 0x04) printk ("mtrr: SMM memory access disabled\n"); - if ( ccrc[1] & 0x02) printk ("mtrr: SMM mode disabled\n"); -*/ - if (ccrc[6]) - printk(KERN_INFO "mtrr: ARR3 was write protected, unprotected\n"); -} -#endif - static struct mtrr_ops cyrix_mtrr_ops = { .vendor = X86_VENDOR_CYRIX, // .init = cyrix_arr_init, diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 7159195..b6e136f 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -59,12 +59,6 @@ struct mtrr_ops * mtrr_if = NULL; static void set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type); -#ifndef CONFIG_X86_64 -extern int arr3_protected; -#else -#define arr3_protected 0 -#endif - void set_mtrr_ops(struct mtrr_ops * ops) { if (ops->vendor && ops->vendor < X86_VENDOR_NUM) @@ -513,12 +507,6 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) printk(KERN_WARNING "mtrr: register: %d too big\n", reg); goto out; } - if (is_cpu(CYRIX) && !use_intel()) { - if ((reg == 3) && arr3_protected) { - printk(KERN_WARNING "mtrr: ARR3 cannot be changed\n"); - goto out; - } - } mtrr_if->get(reg, &lbase, &lsize, <ype); if (lsize < 1) { printk(KERN_WARNING "mtrr: MTRR %d not used\n", reg); @@ -566,10 +554,6 @@ EXPORT_SYMBOL(mtrr_del); * These should be called implicitly, but we can't yet until all the initcall * stuff is done... */ -extern void amd_init_mtrr(void); -extern void cyrix_init_mtrr(void); -extern void centaur_init_mtrr(void); - static void __init init_ifs(void) { #ifndef CONFIG_X86_64 @@ -675,7 +659,7 @@ static __init int amd_special_default_mtrr(void) */ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) { - unsigned long i, base, size, highest_addr = 0, def, dummy; + unsigned long i, base, size, highest_pfn = 0, def, dummy; mtrr_type type; u64 trim_start, trim_size; @@ -698,28 +682,27 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) mtrr_if->get(i, &base, &size, &type); if (type != MTRR_TYPE_WRBACK) continue; - base <<= PAGE_SHIFT; - size <<= PAGE_SHIFT; - if (highest_addr < base + size) - highest_addr = base + size; + if (highest_pfn < base + size) + highest_pfn = base + size; } /* kvm/qemu doesn't have mtrr set right, don't trim them all */ - if (!highest_addr) { + if (!highest_pfn) { printk(KERN_WARNING "WARNING: strange, CPU MTRRs all blank?\n"); WARN_ON(1); return 0; } - if ((highest_addr >> PAGE_SHIFT) < end_pfn) { + if (highest_pfn < end_pfn) { printk(KERN_WARNING "WARNING: BIOS bug: CPU MTRRs don't cover" - " all of memory, losing %LdMB of RAM.\n", - (((u64)end_pfn << PAGE_SHIFT) - highest_addr) >> 20); + " all of memory, losing %luMB of RAM.\n", + (end_pfn - highest_pfn) >> (20 - PAGE_SHIFT)); WARN_ON(1); printk(KERN_INFO "update e820 for mtrr\n"); - trim_start = highest_addr; + trim_start = highest_pfn; + trim_start <<= PAGE_SHIFT; trim_size = end_pfn; trim_size <<= PAGE_SHIFT; trim_size -= trim_start; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index fb74a2c..2cc77eb 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -97,3 +97,7 @@ void mtrr_state_warn(void); const char *mtrr_attrib_to_str(int x); void mtrr_wrmsr(unsigned, unsigned, unsigned); +/* CPU specific mtrr init functions */ +int amd_init_mtrr(void); +int cyrix_init_mtrr(void); +int centaur_init_mtrr(void); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 02821326..af11d31 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -10,80 +10,6 @@ */ static int show_cpuinfo(struct seq_file *m, void *v) { - /* - * These flag bits must match the definitions in <asm/cpufeature.h>. - * NULL means this bit is undefined or reserved; either way it doesn't - * have meaning as far as Linux is concerned. Note that it's important - * to realize there is a difference between this table and CPUID -- if - * applications want to get the raw CPUID data, they should access - * /dev/cpu/<cpu_nr>/cpuid instead. - */ - static const char * const x86_cap_flags[] = { - /* Intel-defined */ - "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce", - "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov", - "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx", - "fxsr", "sse", "sse2", "ss", "ht", "tm", "ia64", "pbe", - - /* AMD-defined */ - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL, - NULL, NULL, NULL, "mp", "nx", NULL, "mmxext", NULL, - NULL, "fxsr_opt", "pdpe1gb", "rdtscp", NULL, "lm", - "3dnowext", "3dnow", - - /* Transmeta-defined */ - "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* Other (Linux-defined) */ - "cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr", - NULL, NULL, NULL, NULL, - "constant_tsc", "up", NULL, "arch_perfmon", - "pebs", "bts", NULL, "sync_rdtsc", - "rep_good", NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* Intel-defined (#2) */ - "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est", - "tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL, - NULL, NULL, "dca", "sse4_1", "sse4_2", NULL, NULL, "popcnt", - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* VIA/Cyrix/Centaur-defined */ - NULL, NULL, "rng", "rng_en", NULL, NULL, "ace", "ace_en", - "ace2", "ace2_en", "phe", "phe_en", "pmm", "pmm_en", NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* AMD-defined (#2) */ - "lahf_lm", "cmp_legacy", "svm", "extapic", - "cr8_legacy", "abm", "sse4a", "misalignsse", - "3dnowprefetch", "osvw", "ibs", "sse5", - "skinit", "wdt", NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* Auxiliary (Linux-defined) */ - "ida", NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - }; - static const char * const x86_power_flags[] = { - "ts", /* temperature sensor */ - "fid", /* frequency id control */ - "vid", /* voltage id control */ - "ttp", /* thermal trip */ - "tm", - "stc", - "100mhzsteps", - "hwpstate", - "", /* constant_tsc - moved to flags */ - /* nothing */ - }; struct cpuinfo_x86 *c = v; int i, n = 0; int fpu_exception; diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index a63432d..288e7a6 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -1,6 +1,6 @@ /* ----------------------------------------------------------------------- * - * - * Copyright 2000 H. Peter Anvin - All Rights Reserved + * + * Copyright 2000-2008 H. Peter Anvin - All Rights Reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -17,6 +17,10 @@ * and then read in chunks of 16 bytes. A larger size means multiple * reads of consecutive levels. * + * The lower 32 bits of the file position is used as the incoming %eax, + * and the upper 32 bits of the file position as the incoming %ecx, + * the latter intended for "counting" eax levels like eax=4. + * * This driver uses /dev/cpu/%d/cpuid where %d is the minor number, and on * an SMP box will direct the access to CPU %d. */ @@ -43,35 +47,24 @@ static struct class *cpuid_class; -struct cpuid_command { - u32 reg; - u32 *data; +struct cpuid_regs { + u32 eax, ebx, ecx, edx; }; static void cpuid_smp_cpuid(void *cmd_block) { - struct cpuid_command *cmd = cmd_block; - - cpuid(cmd->reg, &cmd->data[0], &cmd->data[1], &cmd->data[2], - &cmd->data[3]); -} - -static inline void do_cpuid(int cpu, u32 reg, u32 * data) -{ - struct cpuid_command cmd; - - cmd.reg = reg; - cmd.data = data; + struct cpuid_regs *cmd = (struct cpuid_regs *)cmd_block; - smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1); + cpuid_count(cmd->eax, cmd->ecx, + &cmd->eax, &cmd->ebx, &cmd->ecx, &cmd->edx); } static loff_t cpuid_seek(struct file *file, loff_t offset, int orig) { loff_t ret; + struct inode *inode = file->f_mapping->host; - lock_kernel(); - + mutex_lock(&inode->i_mutex); switch (orig) { case 0: file->f_pos = offset; @@ -84,8 +77,7 @@ static loff_t cpuid_seek(struct file *file, loff_t offset, int orig) default: ret = -EINVAL; } - - unlock_kernel(); + mutex_unlock(&inode->i_mutex); return ret; } @@ -93,19 +85,21 @@ static ssize_t cpuid_read(struct file *file, char __user *buf, size_t count, loff_t * ppos) { char __user *tmp = buf; - u32 data[4]; - u32 reg = *ppos; + struct cpuid_regs cmd; int cpu = iminor(file->f_path.dentry->d_inode); + u64 pos = *ppos; if (count % 16) return -EINVAL; /* Invalid chunk size */ for (; count; count -= 16) { - do_cpuid(cpu, reg, data); - if (copy_to_user(tmp, &data, 16)) + cmd.eax = pos; + cmd.ecx = pos >> 32; + smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1); + if (copy_to_user(tmp, &cmd, 16)) return -EFAULT; tmp += 16; - *ppos = reg++; + *ppos = ++pos; } return tmp - buf; @@ -193,7 +187,7 @@ static int __init cpuid_init(void) } for_each_online_cpu(i) { err = cpuid_device_create(i); - if (err != 0) + if (err != 0) goto out_class; } register_hotcpu_notifier(&cpuid_class_cpu_notifier); @@ -208,7 +202,7 @@ out_class: } class_destroy(cpuid_class); out_chrdev: - unregister_chrdev(CPUID_MAJOR, "cpu/cpuid"); + unregister_chrdev(CPUID_MAJOR, "cpu/cpuid"); out: return err; } diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c index 1411324..32dd62b 100644 --- a/arch/x86/kernel/efi.c +++ b/arch/x86/kernel/efi.c @@ -379,11 +379,9 @@ void __init efi_init(void) #endif } -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) static void __init runtime_code_page_mkexec(void) { efi_memory_desc_t *md; - unsigned long end; void *p; if (!(__supported_pte_mask & _PAGE_NX)) @@ -392,18 +390,13 @@ static void __init runtime_code_page_mkexec(void) /* Make EFI runtime service code area executable */ for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; - end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT); - if (md->type == EFI_RUNTIME_SERVICES_CODE && - (end >> PAGE_SHIFT) <= max_pfn_mapped) { - set_memory_x(md->virt_addr, md->num_pages); - set_memory_uc(md->virt_addr, md->num_pages); - } + + if (md->type != EFI_RUNTIME_SERVICES_CODE) + continue; + + set_memory_x(md->virt_addr, md->num_pages << EFI_PAGE_SHIFT); } - __flush_tlb_all(); } -#else -static inline void __init runtime_code_page_mkexec(void) { } -#endif /* * This function will switch the EFI runtime services to virtual mode. @@ -417,30 +410,40 @@ void __init efi_enter_virtual_mode(void) { efi_memory_desc_t *md; efi_status_t status; - unsigned long end; - void *p; + unsigned long size; + u64 end, systab; + void *p, *va; efi.systab = NULL; for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; if (!(md->attribute & EFI_MEMORY_RUNTIME)) continue; - end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT); - if ((md->attribute & EFI_MEMORY_WB) && - ((end >> PAGE_SHIFT) <= max_pfn_mapped)) - md->virt_addr = (unsigned long)__va(md->phys_addr); + + size = md->num_pages << EFI_PAGE_SHIFT; + end = md->phys_addr + size; + + if ((end >> PAGE_SHIFT) <= max_pfn_mapped) + va = __va(md->phys_addr); else - md->virt_addr = (unsigned long) - efi_ioremap(md->phys_addr, - md->num_pages << EFI_PAGE_SHIFT); - if (!md->virt_addr) + va = efi_ioremap(md->phys_addr, size); + + if (md->attribute & EFI_MEMORY_WB) + set_memory_uc(md->virt_addr, size); + + md->virt_addr = (u64) (unsigned long) va; + + if (!va) { printk(KERN_ERR PFX "ioremap of 0x%llX failed!\n", (unsigned long long)md->phys_addr); - if ((md->phys_addr <= (unsigned long)efi_phys.systab) && - ((unsigned long)efi_phys.systab < end)) - efi.systab = (efi_system_table_t *)(unsigned long) - (md->virt_addr - md->phys_addr + - (unsigned long)efi_phys.systab); + continue; + } + + systab = (u64) (unsigned long) efi_phys.systab; + if (md->phys_addr <= systab && systab < end) { + systab += md->virt_addr - md->phys_addr; + efi.systab = (efi_system_table_t *) (unsigned long) systab; + } } BUG_ON(!efi.systab); diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c index 674f237..09d5c23 100644 --- a/arch/x86/kernel/efi_64.c +++ b/arch/x86/kernel/efi_64.c @@ -54,10 +54,10 @@ static void __init early_mapping_set_exec(unsigned long start, else set_pte(kpte, __pte((pte_val(*kpte) | _PAGE_NX) & \ __supported_pte_mask)); - if (level == 4) - start = (start + PMD_SIZE) & PMD_MASK; - else + if (level == PG_LEVEL_4K) start = (start + PAGE_SIZE) & PAGE_MASK; + else + start = (start + PMD_SIZE) & PMD_MASK; } } @@ -109,23 +109,23 @@ void __init efi_reserve_bootmem(void) memmap.nr_map * memmap.desc_size); } -void __iomem * __init efi_ioremap(unsigned long offset, - unsigned long size) +void __iomem * __init efi_ioremap(unsigned long phys_addr, unsigned long size) { static unsigned pages_mapped; - unsigned long last_addr; unsigned i, pages; - last_addr = offset + size - 1; - offset &= PAGE_MASK; - pages = (PAGE_ALIGN(last_addr) - offset) >> PAGE_SHIFT; + /* phys_addr and size must be page aligned */ + if ((phys_addr & ~PAGE_MASK) || (size & ~PAGE_MASK)) + return NULL; + + pages = size >> PAGE_SHIFT; if (pages_mapped + pages > MAX_EFI_IO_PAGES) return NULL; for (i = 0; i < pages; i++) { __set_fixmap(FIX_EFI_IO_MAP_FIRST_PAGE - pages_mapped, - offset, PAGE_KERNEL_EXEC_NOCACHE); - offset += PAGE_SIZE; + phys_addr, PAGE_KERNEL); + phys_addr += PAGE_SIZE; pages_mapped++; } diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index bea8474..c7341e8 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -582,7 +582,6 @@ retint_restore_args: /* return to kernel space */ TRACE_IRQS_IRETQ restore_args: RESTORE_ARGS 0,8,0 -iret_label: #ifdef CONFIG_PARAVIRT INTERRUPT_RETURN #endif @@ -593,13 +592,22 @@ ENTRY(native_iret) .quad native_iret, bad_iret .previous .section .fixup,"ax" - /* force a signal here? this matches i386 behaviour */ - /* running with kernel gs */ bad_iret: - movq $11,%rdi /* SIGSEGV */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY | ~(CLBR_RDI)) - jmp do_exit + /* + * The iret traps when the %cs or %ss being restored is bogus. + * We've lost the original trap vector and error code. + * #GPF is the most likely one to get for an invalid selector. + * So pretend we completed the iret and took the #GPF in user mode. + * + * We are now running with the kernel GS after exception recovery. + * But error_entry expects us to have user GS to match the user %cs, + * so swap back. + */ + pushq $0 + + SWAPGS + jmp general_protection + .previous /* edi: workmask, edx: work */ @@ -911,7 +919,7 @@ error_kernelspace: iret run with kernel gs again, so don't set the user space flag. B stepping K8s sometimes report an truncated RIP for IRET exceptions returning to compat mode. Check for these here too. */ - leaq iret_label(%rip),%rbp + leaq native_iret(%rip),%rbp cmpq %rbp,RIP(%rsp) je error_swapgs movl %ebp,%ebp /* zero extend */ diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 1d5a7a3..09b38d5 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -63,7 +63,7 @@ startup_64: /* Is the address not 2M aligned? */ movq %rbp, %rax - andl $~LARGE_PAGE_MASK, %eax + andl $~PMD_PAGE_MASK, %eax testl %eax, %eax jnz bad_address @@ -88,7 +88,7 @@ startup_64: /* Add an Identity mapping if I am above 1G */ leaq _text(%rip), %rdi - andq $LARGE_PAGE_MASK, %rdi + andq $PMD_PAGE_MASK, %rdi movq %rdi, %rax shrq $PUD_SHIFT, %rax @@ -250,18 +250,13 @@ ENTRY(secondary_startup_64) lretq /* SMP bootup changes these two */ -#ifndef CONFIG_HOTPLUG_CPU - .pushsection .init.data -#endif + __CPUINITDATA .align 8 - .globl initial_code -initial_code: + ENTRY(initial_code) .quad x86_64_start_kernel -#ifndef CONFIG_HOTPLUG_CPU - .popsection -#endif - .globl init_rsp -init_rsp: + __FINITDATA + + ENTRY(init_rsp) .quad init_thread_union+THREAD_SIZE-8 bad_address: diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 8a7660c..0224c36 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -35,7 +35,8 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload) if (mincount <= pc->size) return 0; oldsize = pc->size; - mincount = (mincount + 511) & (~511); + mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) & + (~(PAGE_SIZE / LDT_ENTRY_SIZE - 1)); if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE) newldt = vmalloc(mincount * LDT_ENTRY_SIZE); else diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index bd82850..af51ea8 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -1,6 +1,6 @@ /* ----------------------------------------------------------------------- * - * - * Copyright 2000 H. Peter Anvin - All Rights Reserved + * + * Copyright 2000-2008 H. Peter Anvin - All Rights Reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -45,9 +45,10 @@ static struct class *msr_class; static loff_t msr_seek(struct file *file, loff_t offset, int orig) { - loff_t ret = -EINVAL; + loff_t ret; + struct inode *inode = file->f_mapping->host; - lock_kernel(); + mutex_lock(&inode->i_mutex); switch (orig) { case 0: file->f_pos = offset; @@ -56,8 +57,11 @@ static loff_t msr_seek(struct file *file, loff_t offset, int orig) case 1: file->f_pos += offset; ret = file->f_pos; + break; + default: + ret = -EINVAL; } - unlock_kernel(); + mutex_unlock(&inode->i_mutex); return ret; } diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 1fe7f04..1b5464c 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -35,6 +35,7 @@ #include <linux/pci.h> #include <linux/delay.h> #include <linux/scatterlist.h> +#include <linux/iommu-helper.h> #include <asm/gart.h> #include <asm/calgary.h> #include <asm/tce.h> @@ -260,22 +261,28 @@ static void iommu_range_reserve(struct iommu_table *tbl, spin_unlock_irqrestore(&tbl->it_lock, flags); } -static unsigned long iommu_range_alloc(struct iommu_table *tbl, - unsigned int npages) +static unsigned long iommu_range_alloc(struct device *dev, + struct iommu_table *tbl, + unsigned int npages) { unsigned long flags; unsigned long offset; + unsigned long boundary_size; + + boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, + PAGE_SIZE) >> PAGE_SHIFT; BUG_ON(npages == 0); spin_lock_irqsave(&tbl->it_lock, flags); - offset = find_next_zero_string(tbl->it_map, tbl->it_hint, - tbl->it_size, npages); + offset = iommu_area_alloc(tbl->it_map, tbl->it_size, tbl->it_hint, + npages, 0, boundary_size, 0); if (offset == ~0UL) { tbl->chip_ops->tce_cache_blast(tbl); - offset = find_next_zero_string(tbl->it_map, 0, - tbl->it_size, npages); + + offset = iommu_area_alloc(tbl->it_map, tbl->it_size, 0, + npages, 0, boundary_size, 0); if (offset == ~0UL) { printk(KERN_WARNING "Calgary: IOMMU full.\n"); spin_unlock_irqrestore(&tbl->it_lock, flags); @@ -286,7 +293,6 @@ static unsigned long iommu_range_alloc(struct iommu_table *tbl, } } - set_bit_string(tbl->it_map, offset, npages); tbl->it_hint = offset + npages; BUG_ON(tbl->it_hint > tbl->it_size); @@ -295,13 +301,13 @@ static unsigned long iommu_range_alloc(struct iommu_table *tbl, return offset; } -static dma_addr_t iommu_alloc(struct iommu_table *tbl, void *vaddr, - unsigned int npages, int direction) +static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, + void *vaddr, unsigned int npages, int direction) { unsigned long entry; dma_addr_t ret = bad_dma_address; - entry = iommu_range_alloc(tbl, npages); + entry = iommu_range_alloc(dev, tbl, npages); if (unlikely(entry == bad_dma_address)) goto error; @@ -354,7 +360,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, badbit, tbl, dma_addr, entry, npages); } - __clear_bit_string(tbl->it_map, entry, npages); + iommu_area_free(tbl->it_map, entry, npages); spin_unlock_irqrestore(&tbl->it_lock, flags); } @@ -438,7 +444,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, vaddr = (unsigned long) sg_virt(s); npages = num_dma_pages(vaddr, s->length); - entry = iommu_range_alloc(tbl, npages); + entry = iommu_range_alloc(dev, tbl, npages); if (entry == bad_dma_address) { /* makes sure unmap knows to stop */ s->dma_length = 0; @@ -476,7 +482,7 @@ static dma_addr_t calgary_map_single(struct device *dev, void *vaddr, npages = num_dma_pages(uaddr, size); if (translation_enabled(tbl)) - dma_handle = iommu_alloc(tbl, vaddr, npages, direction); + dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction); else dma_handle = virt_to_bus(vaddr); @@ -516,7 +522,7 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size, if (translation_enabled(tbl)) { /* set up tces to cover the allocated range */ - mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL); + mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL); if (mapping == bad_dma_address) goto free; diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 4d5cc71..65f6acb 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -25,6 +25,7 @@ #include <linux/bitops.h> #include <linux/kdebug.h> #include <linux/scatterlist.h> +#include <linux/iommu-helper.h> #include <asm/atomic.h> #include <asm/io.h> #include <asm/mtrr.h> @@ -82,17 +83,24 @@ AGPEXTERN __u32 *agp_gatt_table; static unsigned long next_bit; /* protected by iommu_bitmap_lock */ static int need_flush; /* global flush state. set for each gart wrap */ -static unsigned long alloc_iommu(int size) +static unsigned long alloc_iommu(struct device *dev, int size) { unsigned long offset, flags; + unsigned long boundary_size; + unsigned long base_index; + + base_index = ALIGN(iommu_bus_base & dma_get_seg_boundary(dev), + PAGE_SIZE) >> PAGE_SHIFT; + boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, + PAGE_SIZE) >> PAGE_SHIFT; spin_lock_irqsave(&iommu_bitmap_lock, flags); - offset = find_next_zero_string(iommu_gart_bitmap, next_bit, - iommu_pages, size); + offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, next_bit, + size, base_index, boundary_size, 0); if (offset == -1) { need_flush = 1; - offset = find_next_zero_string(iommu_gart_bitmap, 0, - iommu_pages, size); + offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, 0, + size, base_index, boundary_size, 0); } if (offset != -1) { set_bit_string(iommu_gart_bitmap, offset, size); @@ -114,7 +122,7 @@ static void free_iommu(unsigned long offset, int size) unsigned long flags; spin_lock_irqsave(&iommu_bitmap_lock, flags); - __clear_bit_string(iommu_gart_bitmap, offset, size); + iommu_area_free(iommu_gart_bitmap, offset, size); spin_unlock_irqrestore(&iommu_bitmap_lock, flags); } @@ -235,7 +243,7 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem, size_t size, int dir) { unsigned long npages = to_pages(phys_mem, size); - unsigned long iommu_page = alloc_iommu(npages); + unsigned long iommu_page = alloc_iommu(dev, npages); int i; if (iommu_page == -1) { @@ -355,10 +363,11 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg, } /* Map multiple scatterlist entries continuous into the first. */ -static int __dma_map_cont(struct scatterlist *start, int nelems, - struct scatterlist *sout, unsigned long pages) +static int __dma_map_cont(struct device *dev, struct scatterlist *start, + int nelems, struct scatterlist *sout, + unsigned long pages) { - unsigned long iommu_start = alloc_iommu(pages); + unsigned long iommu_start = alloc_iommu(dev, pages); unsigned long iommu_page = iommu_start; struct scatterlist *s; int i; @@ -394,8 +403,8 @@ static int __dma_map_cont(struct scatterlist *start, int nelems, } static inline int -dma_map_cont(struct scatterlist *start, int nelems, struct scatterlist *sout, - unsigned long pages, int need) +dma_map_cont(struct device *dev, struct scatterlist *start, int nelems, + struct scatterlist *sout, unsigned long pages, int need) { if (!need) { BUG_ON(nelems != 1); @@ -403,7 +412,7 @@ dma_map_cont(struct scatterlist *start, int nelems, struct scatterlist *sout, sout->dma_length = start->length; return 0; } - return __dma_map_cont(start, nelems, sout, pages); + return __dma_map_cont(dev, start, nelems, sout, pages); } /* @@ -416,6 +425,8 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) struct scatterlist *s, *ps, *start_sg, *sgmap; int need = 0, nextneed, i, out, start; unsigned long pages = 0; + unsigned int seg_size; + unsigned int max_seg_size; if (nents == 0) return 0; @@ -426,6 +437,8 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) out = 0; start = 0; start_sg = sgmap = sg; + seg_size = 0; + max_seg_size = dma_get_max_seg_size(dev); ps = NULL; /* shut up gcc */ for_each_sg(sg, s, nents, i) { dma_addr_t addr = sg_phys(s); @@ -443,11 +456,13 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) * offset. */ if (!iommu_merge || !nextneed || !need || s->offset || + (s->length + seg_size > max_seg_size) || (ps->offset + ps->length) % PAGE_SIZE) { - if (dma_map_cont(start_sg, i - start, sgmap, - pages, need) < 0) + if (dma_map_cont(dev, start_sg, i - start, + sgmap, pages, need) < 0) goto error; out++; + seg_size = 0; sgmap = sg_next(sgmap); pages = 0; start = i; @@ -455,11 +470,12 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) } } + seg_size += s->length; need = nextneed; pages += to_pages(s->offset, s->length); ps = s; } - if (dma_map_cont(start_sg, i - start, sgmap, pages, need) < 0) + if (dma_map_cont(dev, start_sg, i - start, sgmap, pages, need) < 0) goto error; out++; flush_gart(); @@ -501,7 +517,7 @@ static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size) } a = aper + iommu_size; - iommu_size -= round_up(a, LARGE_PAGE_SIZE) - a; + iommu_size -= round_up(a, PMD_PAGE_SIZE) - a; if (iommu_size < 64*1024*1024) { printk(KERN_WARNING @@ -731,7 +747,8 @@ void __init gart_iommu_init(void) * the backing memory. The GART address is only used by PCI * devices. */ - clear_kernel_mapping((unsigned long)__va(iommu_bus_base), iommu_size); + set_memory_np((unsigned long)__va(iommu_bus_base), + iommu_size >> PAGE_SHIFT); /* * Try to workaround a bug (thanks to BenH) diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 968371a..dabdbef 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -251,7 +251,7 @@ void cpu_idle_wait(void) * because it has nothing to do. * Give all the remaining CPUS a kick. */ - smp_call_function_mask(map, do_nothing, 0, 0); + smp_call_function_mask(map, do_nothing, NULL, 0); } while (!cpus_empty(map)); set_cpus_allowed(current, tmp); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 96286df..702c33ef 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -103,9 +103,26 @@ static int set_segment_reg(struct task_struct *task, if (invalid_selector(value)) return -EIO; - if (offset != offsetof(struct user_regs_struct, gs)) + /* + * For %cs and %ss we cannot permit a null selector. + * We can permit a bogus selector as long as it has USER_RPL. + * Null selectors are fine for other segment registers, but + * we will never get back to user mode with invalid %cs or %ss + * and will take the trap in iret instead. Much code relies + * on user_mode() to distinguish a user trap frame (which can + * safely use invalid selectors) from a kernel trap frame. + */ + switch (offset) { + case offsetof(struct user_regs_struct, cs): + case offsetof(struct user_regs_struct, ss): + if (unlikely(value == 0)) + return -EIO; + + default: *pt_regs_access(task_pt_regs(task), offset) = value; - else { + break; + + case offsetof(struct user_regs_struct, gs): task->thread.gs = value; if (task == current) /* @@ -227,12 +244,16 @@ static int set_segment_reg(struct task_struct *task, * Can't actually change these in 64-bit mode. */ case offsetof(struct user_regs_struct,cs): + if (unlikely(value == 0)) + return -EIO; #ifdef CONFIG_IA32_EMULATION if (test_tsk_thread_flag(task, TIF_IA32)) task_pt_regs(task)->cs = value; #endif break; case offsetof(struct user_regs_struct,ss): + if (unlikely(value == 0)) + return -EIO; #ifdef CONFIG_IA32_EMULATION if (test_tsk_thread_flag(task, TIF_IA32)) task_pt_regs(task)->ss = value; diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 150ba29..6ba33ca 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -30,8 +30,8 @@ static void __devinit quirk_intel_irqbalance(struct pci_dev *dev) raw_pci_ops->read(0, 0, 0x40, 0x4c, 2, &word); if (!(word & (1 << 13))) { - printk(KERN_INFO "Intel E7520/7320/7525 detected. " - "Disabling irq balancing and affinity\n"); + dev_info(&dev->dev, "Intel E7520/7320/7525 detected; " + "disabling irq balancing and affinity\n"); #ifdef CONFIG_IRQBALANCE irqbalance_disable(""); #endif @@ -104,14 +104,16 @@ static void ich_force_enable_hpet(struct pci_dev *dev) pci_read_config_dword(dev, 0xF0, &rcba); rcba &= 0xFFFFC000; if (rcba == 0) { - printk(KERN_DEBUG "RCBA disabled. Cannot force enable HPET\n"); + dev_printk(KERN_DEBUG, &dev->dev, "RCBA disabled; " + "cannot force enable HPET\n"); return; } /* use bits 31:14, 16 kB aligned */ rcba_base = ioremap_nocache(rcba, 0x4000); if (rcba_base == NULL) { - printk(KERN_DEBUG "ioremap failed. Cannot force enable HPET\n"); + dev_printk(KERN_DEBUG, &dev->dev, "ioremap failed; " + "cannot force enable HPET\n"); return; } @@ -122,8 +124,8 @@ static void ich_force_enable_hpet(struct pci_dev *dev) /* HPET is enabled in HPTC. Just not reported by BIOS */ val = val & 0x3; force_hpet_address = 0xFED00000 | (val << 12); - printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n", - force_hpet_address); + dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at " + "0x%lx\n", force_hpet_address); iounmap(rcba_base); return; } @@ -142,11 +144,12 @@ static void ich_force_enable_hpet(struct pci_dev *dev) if (err) { force_hpet_address = 0; iounmap(rcba_base); - printk(KERN_DEBUG "Failed to force enable HPET\n"); + dev_printk(KERN_DEBUG, &dev->dev, + "Failed to force enable HPET\n"); } else { force_hpet_resume_type = ICH_FORCE_HPET_RESUME; - printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n", - force_hpet_address); + dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at " + "0x%lx\n", force_hpet_address); } } @@ -208,8 +211,8 @@ static void old_ich_force_enable_hpet(struct pci_dev *dev) if (val & 0x4) { val &= 0x3; force_hpet_address = 0xFED00000 | (val << 12); - printk(KERN_DEBUG "HPET at base address 0x%lx\n", - force_hpet_address); + dev_printk(KERN_DEBUG, &dev->dev, "HPET at 0x%lx\n", + force_hpet_address); return; } @@ -229,14 +232,14 @@ static void old_ich_force_enable_hpet(struct pci_dev *dev) /* HPET is enabled in HPTC. Just not reported by BIOS */ val &= 0x3; force_hpet_address = 0xFED00000 | (val << 12); - printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n", - force_hpet_address); + dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at " + "0x%lx\n", force_hpet_address); cached_dev = dev; force_hpet_resume_type = OLD_ICH_FORCE_HPET_RESUME; return; } - printk(KERN_DEBUG "Failed to force enable HPET\n"); + dev_printk(KERN_DEBUG, &dev->dev, "Failed to force enable HPET\n"); } /* @@ -294,8 +297,8 @@ static void vt8237_force_enable_hpet(struct pci_dev *dev) */ if (val & 0x80) { force_hpet_address = (val & ~0x3ff); - printk(KERN_DEBUG "HPET at base address 0x%lx\n", - force_hpet_address); + dev_printk(KERN_DEBUG, &dev->dev, "HPET at 0x%lx\n", + force_hpet_address); return; } @@ -309,14 +312,14 @@ static void vt8237_force_enable_hpet(struct pci_dev *dev) pci_read_config_dword(dev, 0x68, &val); if (val & 0x80) { force_hpet_address = (val & ~0x3ff); - printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n", - force_hpet_address); + dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at " + "0x%lx\n", force_hpet_address); cached_dev = dev; force_hpet_resume_type = VT8237_FORCE_HPET_RESUME; return; } - printk(KERN_DEBUG "Failed to force enable HPET\n"); + dev_printk(KERN_DEBUG, &dev->dev, "Failed to force enable HPET\n"); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, @@ -344,7 +347,7 @@ static void nvidia_force_enable_hpet(struct pci_dev *dev) pci_read_config_dword(dev, 0x44, &val); force_hpet_address = val & 0xfffffffe; force_hpet_resume_type = NVIDIA_FORCE_HPET_RESUME; - printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n", + dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at 0x%lx\n", force_hpet_address); cached_dev = dev; return; @@ -377,19 +380,19 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0367, void force_hpet_resume(void) { switch (force_hpet_resume_type) { - case ICH_FORCE_HPET_RESUME: - return ich_force_hpet_resume(); - - case OLD_ICH_FORCE_HPET_RESUME: - return old_ich_force_hpet_resume(); - - case VT8237_FORCE_HPET_RESUME: - return vt8237_force_hpet_resume(); - - case NVIDIA_FORCE_HPET_RESUME: - return nvidia_force_hpet_resume(); - - default: + case ICH_FORCE_HPET_RESUME: + ich_force_hpet_resume(); + return; + case OLD_ICH_FORCE_HPET_RESUME: + old_ich_force_hpet_resume(); + return; + case VT8237_FORCE_HPET_RESUME: + vt8237_force_hpet_resume(); + return; + case NVIDIA_FORCE_HPET_RESUME: + nvidia_force_hpet_resume(); + return; + default: break; } } diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c index 18df70c..c8939df 100644 --- a/arch/x86/kernel/setup_64.c +++ b/arch/x86/kernel/setup_64.c @@ -1068,82 +1068,6 @@ static int show_cpuinfo(struct seq_file *m, void *v) struct cpuinfo_x86 *c = v; int cpu = 0, i; - /* - * These flag bits must match the definitions in <asm/cpufeature.h>. - * NULL means this bit is undefined or reserved; either way it doesn't - * have meaning as far as Linux is concerned. Note that it's important - * to realize there is a difference between this table and CPUID -- if - * applications want to get the raw CPUID data, they should access - * /dev/cpu/<cpu_nr>/cpuid instead. - */ - static const char *const x86_cap_flags[] = { - /* Intel-defined */ - "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce", - "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov", - "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx", - "fxsr", "sse", "sse2", "ss", "ht", "tm", "ia64", "pbe", - - /* AMD-defined */ - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, "nx", NULL, "mmxext", NULL, - NULL, "fxsr_opt", "pdpe1gb", "rdtscp", NULL, "lm", - "3dnowext", "3dnow", - - /* Transmeta-defined */ - "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* Other (Linux-defined) */ - "cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr", - NULL, NULL, NULL, NULL, - "constant_tsc", "up", NULL, "arch_perfmon", - "pebs", "bts", NULL, "sync_rdtsc", - "rep_good", NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* Intel-defined (#2) */ - "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est", - "tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL, - NULL, NULL, "dca", "sse4_1", "sse4_2", NULL, NULL, "popcnt", - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* VIA/Cyrix/Centaur-defined */ - NULL, NULL, "rng", "rng_en", NULL, NULL, "ace", "ace_en", - "ace2", "ace2_en", "phe", "phe_en", "pmm", "pmm_en", NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* AMD-defined (#2) */ - "lahf_lm", "cmp_legacy", "svm", "extapic", - "cr8_legacy", "abm", "sse4a", "misalignsse", - "3dnowprefetch", "osvw", "ibs", "sse5", - "skinit", "wdt", NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* Auxiliary (Linux-defined) */ - "ida", NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - }; - static const char *const x86_power_flags[] = { - "ts", /* temperature sensor */ - "fid", /* frequency id control */ - "vid", /* voltage id control */ - "ttp", /* thermal trip */ - "tm", - "stc", - "100mhzsteps", - "hwpstate", - "", /* tsc invariant mapped to constant_tsc */ - /* nothing */ - }; - - #ifdef CONFIG_SMP cpu = c->cpu_index; #endif diff --git a/arch/x86/kernel/smpboot_32.c b/arch/x86/kernel/smpboot_32.c index 5787a0c..579b9b7 100644 --- a/arch/x86/kernel/smpboot_32.c +++ b/arch/x86/kernel/smpboot_32.c @@ -202,8 +202,6 @@ valid_k7: ; } -extern void calibrate_delay(void); - static atomic_t init_deasserted; static void __cpuinit smp_callin(void) diff --git a/arch/x86/kernel/srat_32.c b/arch/x86/kernel/srat_32.c index 2bf6903..b72e613 100644 --- a/arch/x86/kernel/srat_32.c +++ b/arch/x86/kernel/srat_32.c @@ -274,7 +274,7 @@ int __init get_memcfg_from_srat(void) int tables = 0; int i = 0; - rsdp_address = acpi_find_rsdp(); + rsdp_address = acpi_os_get_root_pointer(); if (!rsdp_address) { printk("%s: System description tables not found\n", __FUNCTION__); diff --git a/arch/x86/kernel/suspend_64.c b/arch/x86/kernel/suspend_64.c index 0919951..7ac7130 100644 --- a/arch/x86/kernel/suspend_64.c +++ b/arch/x86/kernel/suspend_64.c @@ -140,7 +140,12 @@ static void fix_processor_context(void) int cpu = smp_processor_id(); struct tss_struct *t = &per_cpu(init_tss, cpu); - set_tss_desc(cpu,t); /* This just modifies memory; should not be necessary. But... This is necessary, because 386 hardware has concept of busy TSS or some similar stupidity. */ + /* + * This just modifies memory; should not be necessary. But... This + * is necessary, because 386 hardware has concept of busy TSS or some + * similar stupidity. + */ + set_tss_desc(cpu, t); get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS].type = 9; @@ -160,7 +165,6 @@ static void fix_processor_context(void) loaddebug(¤t->thread, 6); loaddebug(¤t->thread, 7); } - } #ifdef CONFIG_HIBERNATION diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 8344c70..adff556 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -321,6 +321,8 @@ ENTRY(sys_call_table) .long sys_epoll_pwait .long sys_utimensat /* 320 */ .long sys_signalfd - .long sys_timerfd + .long sys_timerfd_create .long sys_eventfd .long sys_fallocate + .long sys_timerfd_settime /* 325 */ + .long sys_timerfd_gettime diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c index ae0ef2e..10b8a6f 100644 --- a/arch/x86/kernel/test_nx.c +++ b/arch/x86/kernel/test_nx.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/sort.h> #include <asm/uaccess.h> +#include <asm/asm.h> extern int rodata_test_data; @@ -89,16 +90,7 @@ static noinline int test_address(void *address) "2: mov %[zero], %[rslt]\n" " ret\n" ".previous\n" - ".section __ex_table,\"a\"\n" - " .align 8\n" -#ifdef CONFIG_X86_32 - " .long 0b\n" - " .long 2b\n" -#else - " .quad 0b\n" - " .quad 2b\n" -#endif - ".previous\n" + _ASM_EXTABLE(0b,2b) : [rslt] "=r" (result) : [fake_code] "r" (address), [zero] "r" (0UL), "0" (result) ); @@ -147,7 +139,6 @@ static int test_NX(void) * Until then, don't run them to avoid too many people getting scared * by the error message */ -#if 0 #ifdef CONFIG_DEBUG_RODATA /* Test 3: Check if the .rodata section is executable */ @@ -160,6 +151,7 @@ static int test_NX(void) } #endif +#if 0 /* Test 4: Check if the .data section of a module is executable */ if (test_address(&test_data)) { printk(KERN_ERR "test_nx: .data section is executable\n"); diff --git a/arch/x86/kernel/trampoline_32.S b/arch/x86/kernel/trampoline_32.S index 9bcc1c6..6458067 100644 --- a/arch/x86/kernel/trampoline_32.S +++ b/arch/x86/kernel/trampoline_32.S @@ -11,12 +11,7 @@ * trampoline page to make our stack and everything else * is a mystery. * - * In fact we don't actually need a stack so we don't - * set one up. - * - * We jump into the boot/compressed/head.S code. So you'd - * better be running a compressed kernel image or you - * won't get very far. + * We jump into arch/x86/kernel/head_32.S. * * On entry to trampoline_data, the processor is in real mode * with 16-bit addressing and 16-bit data. CS has some value diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S index e30b67c..4aedd0b 100644 --- a/arch/x86/kernel/trampoline_64.S +++ b/arch/x86/kernel/trampoline_64.S @@ -10,9 +10,6 @@ * trampoline page to make our stack and everything else * is a mystery. * - * In fact we don't actually need a stack so we don't - * set one up. - * * On entry to trampoline_data, the processor is in real mode * with 16-bit addressing and 16-bit data. CS has some value * and IP is zero. Thus, data addresses need to be absolute diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps_32.c index 3cf72977..b22c01e 100644 --- a/arch/x86/kernel/traps_32.c +++ b/arch/x86/kernel/traps_32.c @@ -1176,17 +1176,12 @@ void __init trap_init(void) #endif set_trap_gate(19,&simd_coprocessor_error); + /* + * Verify that the FXSAVE/FXRSTOR data will be 16-byte aligned. + * Generate a build-time error if the alignment is wrong. + */ + BUILD_BUG_ON(offsetof(struct task_struct, thread.i387.fxsave) & 15); if (cpu_has_fxsr) { - /* - * Verify that the FXSAVE/FXRSTOR data will be 16-byte aligned. - * Generates a compile-time "error: zero width for bit-field" if - * the alignment is wrong. - */ - struct fxsrAlignAssert { - int _:!(offsetof(struct task_struct, - thread.i387.fxsave) & 15); - }; - printk(KERN_INFO "Enabling fast FPU save and restore... "); set_in_cr4(X86_CR4_OSFXSR); printk("done.\n"); diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index 4525bc2..12affe1 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -220,21 +220,21 @@ static void vmi_set_tr(void) static void vmi_write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) { u32 *idt_entry = (u32 *)g; - vmi_ops.write_idt_entry(dt, entry, idt_entry[0], idt_entry[2]); + vmi_ops.write_idt_entry(dt, entry, idt_entry[0], idt_entry[1]); } static void vmi_write_gdt_entry(struct desc_struct *dt, int entry, const void *desc, int type) { u32 *gdt_entry = (u32 *)desc; - vmi_ops.write_gdt_entry(dt, entry, gdt_entry[0], gdt_entry[2]); + vmi_ops.write_gdt_entry(dt, entry, gdt_entry[0], gdt_entry[1]); } static void vmi_write_ldt_entry(struct desc_struct *dt, int entry, const void *desc) { u32 *ldt_entry = (u32 *)desc; - vmi_ops.write_idt_entry(dt, entry, ldt_entry[0], ldt_entry[2]); + vmi_ops.write_idt_entry(dt, entry, ldt_entry[0], ldt_entry[1]); } static void vmi_load_sp0(struct tss_struct *tss, |
