diff options
Diffstat (limited to 'arch/x86')
51 files changed, 704 insertions, 459 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f41c9538ca30..6c70fed0f9a0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -66,9 +66,6 @@ config MMU config ZONE_DMA def_bool y -config QUICKLIST - def_bool X86_32 - config SBUS bool @@ -1262,7 +1259,7 @@ menuconfig APM machines with more than one CPU. In order to use APM, you will need supporting software. For location - and more information, read <file:Documentation/pm.txt> and the + and more information, read <file:Documentation/power/pm.txt> and the Battery Powered Linux mini-HOWTO, available from <http://www.tldp.org/docs.html#howto>. diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 45d79ea890ae..5fed98ca0e1f 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -65,7 +65,8 @@ __setup("noreplace-paravirt", setup_noreplace_paravirt); get them easily into strings. */ asm("\t.section .rodata, \"a\"\nintelnops: " GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6 - GENERIC_NOP7 GENERIC_NOP8); + GENERIC_NOP7 GENERIC_NOP8 + "\t.previous"); extern const unsigned char intelnops[]; static const unsigned char *const intel_nops[ASM_NOP_MAX+1] = { NULL, @@ -83,7 +84,8 @@ static const unsigned char *const intel_nops[ASM_NOP_MAX+1] = { #ifdef K8_NOP1 asm("\t.section .rodata, \"a\"\nk8nops: " K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6 - K8_NOP7 K8_NOP8); + K8_NOP7 K8_NOP8 + "\t.previous"); extern const unsigned char k8nops[]; static const unsigned char *const k8_nops[ASM_NOP_MAX+1] = { NULL, @@ -101,7 +103,8 @@ static const unsigned char *const k8_nops[ASM_NOP_MAX+1] = { #ifdef K7_NOP1 asm("\t.section .rodata, \"a\"\nk7nops: " K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6 - K7_NOP7 K7_NOP8); + K7_NOP7 K7_NOP8 + "\t.previous"); extern const unsigned char k7nops[]; static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = { NULL, @@ -119,7 +122,8 @@ static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = { #ifdef P6_NOP1 asm("\t.section .rodata, \"a\"\np6nops: " P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6 - P6_NOP7 P6_NOP8); + P6_NOP7 P6_NOP8 + "\t.previous"); extern const unsigned char p6nops[]; static const unsigned char *const p6_nops[ASM_NOP_MAX+1] = { NULL, diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 608152a2a05e..00df126169b4 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -18,6 +18,7 @@ #include <linux/pci.h> #include <linux/bitops.h> #include <linux/ioport.h> +#include <linux/suspend.h> #include <asm/e820.h> #include <asm/io.h> #include <asm/gart.h> @@ -76,6 +77,8 @@ static u32 __init allocate_aperture(void) printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n", aper_size >> 10, __pa(p)); insert_aperture_resource((u32)__pa(p), aper_size); + register_nosave_region((u32)__pa(p) >> PAGE_SHIFT, + (u32)__pa(p+aper_size) >> PAGE_SHIFT); return (u32)__pa(p); } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 027e5c003b16..170d2f5523b2 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -143,14 +143,6 @@ static void __init check_config(void) #endif /* - * If we configured ourselves for a TSC, we'd better have one! - */ -#ifdef CONFIG_X86_TSC - if (!cpu_has_tsc) - panic("Kernel compiled for Pentium+, requires TSC feature!"); -#endif - -/* * If we were told we had a good local APIC, check for buggy Pentia, * i.e. all B steppings and the C2 stepping of P54C when using their * integrated APIC (see 11AP erratum in "Pentium Processor diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c index f2b5a621d27b..8a85c93bd62a 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c @@ -63,7 +63,7 @@ static struct cpufreq_frequency_table speedstep_freqs[] = { */ static int speedstep_smi_ownership (void) { - u32 command, result, magic; + u32 command, result, magic, dummy; u32 function = GET_SPEEDSTEP_OWNER; unsigned char magic_data[] = "Copyright (c) 1999 Intel Corporation"; @@ -73,8 +73,11 @@ static int speedstep_smi_ownership (void) dprintk("trying to obtain ownership with command %x at port %x\n", command, smi_port); __asm__ __volatile__( + "push %%ebp\n" "out %%al, (%%dx)\n" - : "=D" (result) + "pop %%ebp\n" + : "=D" (result), "=a" (dummy), "=b" (dummy), "=c" (dummy), "=d" (dummy), + "=S" (dummy) : "a" (command), "b" (function), "c" (0), "d" (smi_port), "D" (0), "S" (magic) : "memory" @@ -96,7 +99,7 @@ static int speedstep_smi_ownership (void) */ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) { - u32 command, result = 0, edi, high_mhz, low_mhz; + u32 command, result = 0, edi, high_mhz, low_mhz, dummy; u32 state=0; u32 function = GET_SPEEDSTEP_FREQS; @@ -109,10 +112,12 @@ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) dprintk("trying to determine frequencies with command %x at port %x\n", command, smi_port); - __asm__ __volatile__("movl $0, %%edi\n" + __asm__ __volatile__( + "push %%ebp\n" "out %%al, (%%dx)\n" - : "=a" (result), "=b" (high_mhz), "=c" (low_mhz), "=d" (state), "=D" (edi) - : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0) + "pop %%ebp" + : "=a" (result), "=b" (high_mhz), "=c" (low_mhz), "=d" (state), "=D" (edi), "=S" (dummy) + : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0), "D" (0) ); dprintk("result %x, low_freq %u, high_freq %u\n", result, low_mhz, high_mhz); @@ -135,16 +140,18 @@ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) static int speedstep_get_state (void) { u32 function=GET_SPEEDSTEP_STATE; - u32 result, state, edi, command; + u32 result, state, edi, command, dummy; command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); dprintk("trying to determine current setting with command %x at port %x\n", command, smi_port); - __asm__ __volatile__("movl $0, %%edi\n" + __asm__ __volatile__( + "push %%ebp\n" "out %%al, (%%dx)\n" - : "=a" (result), "=b" (state), "=D" (edi) - : "a" (command), "b" (function), "c" (0), "d" (smi_port), "S" (0) + "pop %%ebp\n" + : "=a" (result), "=b" (state), "=D" (edi), "=c" (dummy), "=d" (dummy), "=S" (dummy) + : "a" (command), "b" (function), "c" (0), "d" (smi_port), "S" (0), "D" (0) ); dprintk("state is %x, result is %x\n", state, result); @@ -160,7 +167,7 @@ static int speedstep_get_state (void) */ static void speedstep_set_state (unsigned int state) { - unsigned int result = 0, command, new_state; + unsigned int result = 0, command, new_state, dummy; unsigned long flags; unsigned int function=SET_SPEEDSTEP_STATE; unsigned int retry = 0; @@ -182,10 +189,12 @@ static void speedstep_set_state (unsigned int state) } retry++; __asm__ __volatile__( - "movl $0, %%edi\n" + "push %%ebp\n" "out %%al, (%%dx)\n" - : "=b" (new_state), "=D" (result) - : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0) + "pop %%ebp" + : "=b" (new_state), "=D" (result), "=c" (dummy), "=a" (dummy), + "=d" (dummy), "=S" (dummy) + : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0), "D" (0) ); } while ((new_state != state) && (retry <= SMI_TRIES)); @@ -195,7 +204,7 @@ static void speedstep_set_state (unsigned int state) if (new_state == state) { dprintk("change to %u MHz succeeded after %u tries with result %u\n", (speedstep_freqs[new_state].frequency / 1000), retry, result); } else { - printk(KERN_ERR "cpufreq: change failed with new_state %u and result %u\n", new_state, result); + printk(KERN_ERR "cpufreq: change to state %u failed with new_state %u and result %u\n", state, new_state, result); } return; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 103d61a59b19..3e18db4cefee 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -176,12 +176,13 @@ static inline void k8_enable_fixed_iorrs(void) } /** - * Checks and updates an fixed-range MTRR if it differs from the value it - * should have. If K8 extentions are wanted, update the K8 SYSCFG MSR also. - * see AMD publication no. 24593, chapter 7.8.1, page 233 for more information - * \param msr MSR address of the MTTR which should be checked and updated - * \param changed pointer which indicates whether the MTRR needed to be changed - * \param msrwords pointer to the MSR values which the MSR should have + * set_fixed_range - checks & updates a fixed-range MTRR if it differs from the value it should have + * @msr: MSR address of the MTTR which should be checked and updated + * @changed: pointer which indicates whether the MTRR needed to be changed + * @msrwords: pointer to the MSR values which the MSR should have + * + * If K8 extentions are wanted, update the K8 SYSCFG MSR also. + * See AMD publication no. 24593, chapter 7.8.1, page 233 for more information. */ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords) { @@ -199,12 +200,15 @@ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords) } } +/** + * generic_get_free_region - Get a free MTRR. + * @base: The starting (base) address of the region. + * @size: The size (in bytes) of the region. + * @replace_reg: mtrr index to be replaced; set to invalid value if none. + * + * Returns: The index of the region on success, else negative on error. + */ int generic_get_free_region(unsigned long base, unsigned long size, int replace_reg) -/* [SUMMARY] Get a free MTRR. - <base> The starting (base) address of the region. - <size> The size (in bytes) of the region. - [RETURNS] The index of the region on success, else -1 on error. -*/ { int i, max; mtrr_type ltype; @@ -249,8 +253,8 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, } /** - * Checks and updates the fixed-range MTRRs if they differ from the saved set - * \param frs pointer to fixed-range MTRR values, saved by get_fixed_ranges() + * set_fixed_ranges - checks & updates the fixed-range MTRRs if they differ from the saved set + * @frs: pointer to fixed-range MTRR values, saved by get_fixed_ranges() */ static int set_fixed_ranges(mtrr_type * frs) { @@ -294,13 +298,13 @@ static bool set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr) static u32 deftype_lo, deftype_hi; +/** + * set_mtrr_state - Set the MTRR state for this CPU. + * + * NOTE: The CPU must already be in a safe state for MTRR changes. + * RETURNS: 0 if no changes made, else a mask indicating what was changed. + */ static unsigned long set_mtrr_state(void) -/* [SUMMARY] Set the MTRR state for this CPU. - <state> The MTRR state information to read. - <ctxt> Some relevant CPU context. - [NOTE] The CPU must already be in a safe state for MTRR changes. - [RETURNS] 0 if no changes made, else a mask indication what was changed. -*/ { unsigned int i; unsigned long change_mask = 0; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index be83336fddba..a6450b3ae759 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -711,7 +711,8 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) trim_size = end_pfn; trim_size <<= PAGE_SHIFT; trim_size -= trim_start; - add_memory_region(trim_start, trim_size, E820_RESERVED); + update_memory_range(trim_start, trim_size, E820_RAM, + E820_RESERVED); update_e820(); return 1; } diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 9b838324b818..b943e10ad814 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -652,9 +652,6 @@ static void probe_nmi_watchdog(void) wd_ops = &p6_wd_ops; break; case 15: - if (boot_cpu_data.x86_model > 0x4) - return; - wd_ops = &p4_wd_ops; break; default: @@ -670,8 +667,10 @@ int lapic_watchdog_init(unsigned nmi_hz) { if (!wd_ops) { probe_nmi_watchdog(); - if (!wd_ops) + if (!wd_ops) { + printk(KERN_INFO "NMI watchdog: CPU not supported\n"); return -1; + } if (!wd_ops->reserve()) { printk(KERN_ERR diff --git a/arch/x86/kernel/e820_32.c b/arch/x86/kernel/e820_32.c index 4e16ef4a2659..80444c5c9b14 100644 --- a/arch/x86/kernel/e820_32.c +++ b/arch/x86/kernel/e820_32.c @@ -749,6 +749,32 @@ static int __init parse_memmap(char *arg) return 0; } early_param("memmap", parse_memmap); +void __init update_memory_range(u64 start, u64 size, unsigned old_type, + unsigned new_type) +{ + int i; + + BUG_ON(old_type == new_type); + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + u64 final_start, final_end; + if (ei->type != old_type) + continue; + /* totally covered? */ + if (ei->addr >= start && ei->size <= size) { + ei->type = new_type; + continue; + } + /* partially covered */ + final_start = max(start, ei->addr); + final_end = min(start + size, ei->addr + ei->size); + if (final_start >= final_end) + continue; + add_memory_region(final_start, final_end - final_start, + new_type); + } +} void __init update_e820(void) { u8 nr_map; diff --git a/arch/x86/kernel/e820_64.c b/arch/x86/kernel/e820_64.c index 9f65b4cc323c..9be697126013 100644 --- a/arch/x86/kernel/e820_64.c +++ b/arch/x86/kernel/e820_64.c @@ -744,6 +744,33 @@ void __init finish_e820_parsing(void) } } +void __init update_memory_range(u64 start, u64 size, unsigned old_type, + unsigned new_type) +{ + int i; + + BUG_ON(old_type == new_type); + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + u64 final_start, final_end; + if (ei->type != old_type) + continue; + /* totally covered? */ + if (ei->addr >= start && ei->size <= size) { + ei->type = new_type; + continue; + } + /* partially covered */ + final_start = max(start, ei->addr); + final_end = min(start + size, ei->addr + ei->size); + if (final_start >= final_end) + continue; + add_memory_region(final_start, final_end - final_start, + new_type); + } +} + void __init update_e820(void) { u8 nr_map; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index fd8ca53943a8..74d87ea85b5c 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -657,7 +657,7 @@ int_msg: .asciz "Unknown interrupt or fault at EIP %p %p %p\n" fault_msg: - .ascii \ + .asciz \ /* fault info: */ "BUG: Int %d: CR2 %p\n" \ /* pusha regs: */ " EDI %p ESI %p EBP %p ESP %p\n" \ " EBX %p EDX %p ECX %p EAX %p\n" \ diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 235fd6c77504..36652ea1a265 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -133,13 +133,16 @@ static void hpet_reserve_platform_timers(unsigned long id) #ifdef CONFIG_HPET_EMULATE_RTC hpet_reserve_timer(&hd, 1); #endif + hd.hd_irq[0] = HPET_LEGACY_8254; hd.hd_irq[1] = HPET_LEGACY_RTC; - for (i = 2; i < nrtimers; timer++, i++) - hd.hd_irq[i] = (timer->hpet_config & Tn_INT_ROUTE_CNF_MASK) >> - Tn_INT_ROUTE_CNF_SHIFT; + for (i = 2; i < nrtimers; timer++, i++) + hd.hd_irq[i] = (timer->hpet_config & Tn_INT_ROUTE_CNF_MASK) >> + Tn_INT_ROUTE_CNF_SHIFT; + hpet_alloc(&hd); + } #else static void hpet_reserve_platform_timers(unsigned long id) { } diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c index c706a3061553..5921e5f0a640 100644 --- a/arch/x86/kernel/io_delay.c +++ b/arch/x86/kernel/io_delay.c @@ -78,6 +78,14 @@ static struct dmi_system_id __initdata io_delay_0xed_port_dmi_table[] = { }, { .callback = dmi_io_delay_0xed_port, + .ident = "HP Pavilion dv6000", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), + DMI_MATCH(DMI_BOARD_NAME, "30B8") + } + }, + { + .callback = dmi_io_delay_0xed_port, .ident = "HP Pavilion tx1000", .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 236d2f8f7ddc..576a03db4511 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -233,6 +233,7 @@ NORET_TYPE void machine_kexec(struct kimage *image) void arch_crash_save_vmcoreinfo(void) { + VMCOREINFO_SYMBOL(phys_base); VMCOREINFO_SYMBOL(init_level4_pgt); #ifdef CONFIG_NUMA diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c index 027fc067b399..b402c0f3f192 100644 --- a/arch/x86/kernel/mfgpt_32.c +++ b/arch/x86/kernel/mfgpt_32.c @@ -30,6 +30,7 @@ #include <linux/kernel.h> #include <linux/interrupt.h> +#include <linux/module.h> #include <asm/geode.h> static struct mfgpt_timer_t { diff --git a/arch/x86/kernel/pci-dma_64.c b/arch/x86/kernel/pci-dma_64.c index a82473d192a3..375cb2bc45be 100644 --- a/arch/x86/kernel/pci-dma_64.c +++ b/arch/x86/kernel/pci-dma_64.c @@ -53,11 +53,6 @@ dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order) int node; node = dev_to_node(dev); - if (node == -1) - node = numa_node_id(); - - if (node < first_node(node_online_map)) - node = first_node(node_online_map); page = alloc_pages_node(node, gfp, order); return page ? page_address(page) : NULL; diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index faf3229f8fb3..700e4647dd30 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -615,8 +615,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info) nommu: /* Should not happen anymore */ - printk(KERN_ERR "PCI-DMA: More than 4GB of RAM and no IOMMU\n" - KERN_ERR "PCI-DMA: 32bit PCI IO may malfunction.\n"); + printk(KERN_WARNING "PCI-DMA: More than 4GB of RAM and no IOMMU\n" + KERN_WARNING "falling back to iommu=soft.\n"); return -1; } @@ -692,9 +692,9 @@ void __init gart_iommu_init(void) !gart_iommu_aperture || (no_agp && init_k8_gatt(&info) < 0)) { if (end_pfn > MAX_DMA32_PFN) { - printk(KERN_ERR "WARNING more than 4GB of memory " - "but GART IOMMU not available.\n" - KERN_ERR "WARNING 32bit PCI may malfunction.\n"); + printk(KERN_WARNING "More than 4GB of memory " + "but GART IOMMU not available.\n" + KERN_WARNING "falling back to iommu=soft.\n"); } return; } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index be3c7a299f02..43930e73f657 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -82,7 +82,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk) */ void (*pm_idle)(void); EXPORT_SYMBOL(pm_idle); -static DEFINE_PER_CPU(unsigned int, cpu_idle_state); void disable_hlt(void) { @@ -190,9 +189,6 @@ void cpu_idle(void) while (!need_resched()) { void (*idle)(void); - if (__get_cpu_var(cpu_idle_state)) - __get_cpu_var(cpu_idle_state) = 0; - check_pgt_cache(); rmb(); idle = pm_idle; @@ -220,40 +216,19 @@ static void do_nothing(void *unused) { } +/* + * cpu_idle_wait - Used to ensure that all the CPUs discard old value of + * pm_idle and update to new pm_idle value. Required while changing pm_idle + * handler on SMP systems. + * + * Caller must have changed pm_idle to the new value before the call. Old + * pm_idle value will not be used by any CPU after the return of this function. + */ void cpu_idle_wait(void) { - unsigned int cpu, this_cpu = get_cpu(); - cpumask_t map, tmp = current->cpus_allowed; - - set_cpus_allowed(current, cpumask_of_cpu(this_cpu)); - put_cpu(); - - cpus_clear(map); - for_each_online_cpu(cpu) { - per_cpu(cpu_idle_state, cpu) = 1; - cpu_set(cpu, map); - } - - __get_cpu_var(cpu_idle_state) = 0; - - wmb(); - do { - ssleep(1); - for_each_online_cpu(cpu) { - if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu)) - cpu_clear(cpu, map); - } - cpus_and(map, map, cpu_online_map); - /* - * We waited 1 sec, if a CPU still did not call idle - * it may be because it is in idle and not waking up - * because it has nothing to do. - * Give all the remaining CPUS a kick. - */ - smp_call_function_mask(map, do_nothing, NULL, 0); - } while (!cpus_empty(map)); - - set_cpus_allowed(current, tmp); + smp_mb(); + /* kick all the CPUs so that they exit out of pm_idle */ + smp_call_function(do_nothing, NULL, 0, 1); } EXPORT_SYMBOL_GPL(cpu_idle_wait); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3baf9b9f4c87..46c4c546b499 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -63,7 +63,6 @@ EXPORT_SYMBOL(boot_option_idle_override); */ void (*pm_idle)(void); EXPORT_SYMBOL(pm_idle); -static DEFINE_PER_CPU(unsigned int, cpu_idle_state); static ATOMIC_NOTIFIER_HEAD(idle_notifier); @@ -173,9 +172,6 @@ void cpu_idle(void) while (!need_resched()) { void (*idle)(void); - if (__get_cpu_var(cpu_idle_state)) - __get_cpu_var(cpu_idle_state) = 0; - rmb(); idle = pm_idle; if (!idle) @@ -207,40 +203,19 @@ static void do_nothing(void *unused) { } +/* + * cpu_idle_wait - Used to ensure that all the CPUs discard old value of + * pm_idle and update to new pm_idle value. Required while changing pm_idle + * handler on SMP systems. + * + * Caller must have changed pm_idle to the new value before the call. Old + * pm_idle value will not be used by any CPU after the return of this function. + */ void cpu_idle_wait(void) { - unsigned int cpu, this_cpu = get_cpu(); - cpumask_t map, tmp = current->cpus_allowed; - - set_cpus_allowed(current, cpumask_of_cpu(this_cpu)); - put_cpu(); - - cpus_clear(map); - for_each_online_cpu(cpu) { - per_cpu(cpu_idle_state, cpu) = 1; - cpu_set(cpu, map); - } - - __get_cpu_var(cpu_idle_state) = 0; - - wmb(); - do { - ssleep(1); - for_each_online_cpu(cpu) { - if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu)) - cpu_clear(cpu, map); - } - cpus_and(map, map, cpu_online_map); - /* - * We waited 1 sec, if a CPU still did not call idle - * it may be because it is in idle and not waking up - * because it has nothing to do. - * Give all the remaining CPUS a kick. - */ - smp_call_function_mask(map, do_nothing, 0, 0); - } while (!cpus_empty(map)); - - set_cpus_allowed(current, tmp); + smp_mb(); + /* kick all the CPUs so that they exit out of pm_idle */ + smp_call_function(do_nothing, NULL, 0, 1); } EXPORT_SYMBOL_GPL(cpu_idle_wait); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 8f64abe699fd..eb92ccbb3502 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -600,21 +600,6 @@ static int ptrace_bts_read_record(struct task_struct *child, return sizeof(ret); } -static int ptrace_bts_write_record(struct task_struct *child, - const struct bts_struct *in) -{ - int retval; - - if (!child->thread.ds_area_msr) - return -ENXIO; - - retval = ds_write_bts((void *)child->thread.ds_area_msr, in); - if (retval) - return retval; - - return sizeof(*in); -} - static int ptrace_bts_clear(struct task_struct *child) { if (!child->thread.ds_area_msr) @@ -657,75 +642,6 @@ static int ptrace_bts_drain(struct task_struct *child, return end; } -static int ptrace_bts_realloc(struct task_struct *child, - int size, int reduce_size) -{ - unsigned long rlim, vm; - int ret, old_size; - - if (size < 0) - return -EINVAL; - - old_size = ds_get_bts_size((void *)child->thread.ds_area_msr); - if (old_size < 0) - return old_size; - - ret = ds_free((void **)&child->thread.ds_area_msr); - if (ret < 0) - goto out; - - size >>= PAGE_SHIFT; - old_size >>= PAGE_SHIFT; - - current->mm->total_vm -= old_size; - current->mm->locked_vm -= old_size; - - if (size == 0) - goto out; - - rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT; - vm = current->mm->total_vm + size; - if (rlim < vm) { - ret = -ENOMEM; - - if (!reduce_size) - goto out; - - size = rlim - current->mm->total_vm; - if (size <= 0) - goto out; - } - - rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT; - vm = current->mm->locked_vm + size; - if (rlim < vm) { - ret = -ENOMEM; - - if (!reduce_size) - goto out; - - size = rlim - current->mm->locked_vm; - if (size <= 0) - goto out; - } - - ret = ds_allocate((void **)&child->thread.ds_area_msr, - size << PAGE_SHIFT); - if (ret < 0) - goto out; - - current->mm->total_vm += size; - current->mm->locked_vm += size; - -out: - if (child->thread.ds_area_msr) - set_tsk_thread_flag(child, TIF_DS_AREA_MSR); - else - clear_tsk_thread_flag(child, TIF_DS_AREA_MSR); - - return ret; -} - static int ptrace_bts_config(struct task_struct *child, long cfg_size, const struct ptrace_bts_config __user *ucfg) @@ -828,6 +744,91 @@ static int ptrace_bts_status(struct task_struct *child, return sizeof(cfg); } + +static int ptrace_bts_write_record(struct task_struct *child, + const struct bts_struct *in) +{ + int retval; + + if (!child->thread.ds_area_msr) + return -ENXIO; + + retval = ds_write_bts((void *)child->thread.ds_area_msr, in); + if (retval) + return retval; + + return sizeof(*in); +} + +static int ptrace_bts_realloc(struct task_struct *child, + int size, int reduce_size) +{ + unsigned long rlim, vm; + int ret, old_size; + + if (size < 0) + return -EINVAL; + + old_size = ds_get_bts_size((void *)child->thread.ds_area_msr); + if (old_size < 0) + return old_size; + + ret = ds_free((void **)&child->thread.ds_area_msr); + if (ret < 0) + goto out; + + size >>= PAGE_SHIFT; + old_size >>= PAGE_SHIFT; + + current->mm->total_vm -= old_size; + current->mm->locked_vm -= old_size; + + if (size == 0) + goto out; + + rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT; + vm = current->mm->total_vm + size; + if (rlim < vm) { + ret = -ENOMEM; + + if (!reduce_size) + goto out; + + size = rlim - current->mm->total_vm; + if (size <= 0) + goto out; + } + + rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT; + vm = current->mm->locked_vm + size; + if (rlim < vm) { + ret = -ENOMEM; + + if (!reduce_size) + goto out; + + size = rlim - current->mm->locked_vm; + if (size <= 0) + goto out; + } + + ret = ds_allocate((void **)&child->thread.ds_area_msr, + size << PAGE_SHIFT); + if (ret < 0) + goto out; + + current->mm->total_vm += size; + current->mm->locked_vm += size; + +out: + if (child->thread.ds_area_msr) + set_tsk_thread_flag(child, TIF_DS_AREA_MSR); + else + clear_tsk_thread_flag(child, TIF_DS_AREA_MSR); + + return ret; +} + void ptrace_bts_take_timestamp(struct task_struct *tsk, enum bts_qualifier qualifier) { @@ -1055,10 +1056,17 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value) R32(esi, si); R32(ebp, bp); R32(eax, ax); - R32(orig_eax, orig_ax); R32(eip, ip); R32(esp, sp); + case offsetof(struct user32, regs.orig_eax): + /* + * Sign-extend the value so that orig_eax = -1 + * causes (long)orig_ax < 0 tests to fire correctly. + */ + regs->orig_ax = (long) (s32) value; + break; + case offsetof(struct user32, regs.eflags): return set_flags(child, value); diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index c47208fc5932..d89a648fe710 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -363,6 +363,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0051, nvidia_force_enable_hpet); /* LPC bridges */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0260, + nvidia_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0360, nvidia_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0361, diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 55ceb8cdef75..484c4a80d38a 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -152,6 +152,24 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "0WF810"), }, }, + { /* Handle problems with rebooting on Dell Optiplex 745's DFF*/ + .callback = set_bios_reboot, + .ident = "Dell OptiPlex 745", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"), + DMI_MATCH(DMI_BOARD_NAME, "0MM599"), + }, + }, + { /* Handle problems with rebooting on Dell Optiplex 745 with 0KW626 */ + .callback = set_bios_reboot, + .ident = "Dell OptiPlex 745", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"), + DMI_MATCH(DMI_BOARD_NAME, "0KW626"), + }, + }, { /* Handle problems with rebooting on Dell 2400's */ .callback = set_bios_reboot, .ident = "Dell PowerEdge 2400", diff --git a/arch/x86/kernel/setup64.c b/arch/x86/kernel/setup64.c index 309366f8f603..e24c45677094 100644 --- a/arch/x86/kernel/setup64.c +++ b/arch/x86/kernel/setup64.c @@ -142,14 +142,16 @@ void __init setup_per_cpu_areas(void) printk(KERN_INFO "PERCPU: Allocating %lu bytes of per cpu data\n", size); for_each_cpu_mask (i, cpu_possible_map) { char *ptr; +#ifndef CONFIG_NEED_MULTIPLE_NODES + ptr = alloc_bootmem_pages(size); +#else + int node = early_cpu_to_node(i); - if (!NODE_DATA(early_cpu_to_node(i))) { - printk("cpu with no node %d, num_online_nodes %d\n", - i, num_online_nodes()); + if (!node_online(node) || !NODE_DATA(node)) ptr = alloc_bootmem_pages(size); - } else { - ptr = alloc_bootmem_pages_node(NODE_DATA(early_cpu_to_node(i)), size); - } + else + ptr = alloc_bootmem_pages_node(NODE_DATA(node), size); +#endif if (!ptr) panic("Cannot allocate cpu data for CPU %d\n", i); cpu_pda(i)->data_offset = ptr - __per_cpu_start; diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c index a1d7071a51c9..2b3e5d45176b 100644 --- a/arch/x86/kernel/setup_32.c +++ b/arch/x86/kernel/setup_32.c @@ -406,8 +406,6 @@ static unsigned long __init setup_memory(void) */ min_low_pfn = PFN_UP(init_pg_tables_end); - find_max_pfn(); - max_low_pfn = find_max_low_pfn(); #ifdef CONFIG_HIGHMEM @@ -764,12 +762,13 @@ void __init setup_arch(char **cmdline_p) if (efi_enabled) efi_init(); - max_low_pfn = setup_memory(); - /* update e820 for memory not covered by WB MTRRs */ + find_max_pfn(); mtrr_bp_init(); if (mtrr_trim_uncached_memory(max_pfn)) - max_low_pfn = setup_memory(); + find_max_pfn(); + + max_low_pfn = setup_memory(); #ifdef CONFIG_VMI /* diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c index 7637dc91c79b..f4f7ecfb898c 100644 --- a/arch/x86/kernel/setup_64.c +++ b/arch/x86/kernel/setup_64.c @@ -801,7 +801,7 @@ static void __cpuinit srat_detect_node(void) /* Don't do the funky fallback heuristics the AMD version employs for now. */ node = apicid_to_node[apicid]; - if (node == NUMA_NO_NODE) + if (node == NUMA_NO_NODE || !node_online(node)) node = first_node(node_online_map); numa_set_node(cpu, node); diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index 56b72fb67f9b..1c83e5124c65 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -311,6 +311,35 @@ give_sigsegv: } /* + * Return -1L or the syscall number that @regs is executing. + */ +static long current_syscall(struct pt_regs *regs) +{ + /* + * We always sign-extend a -1 value being set here, + * so this is always either -1L or a syscall number. + */ + return regs->orig_ax; +} + +/* + * Return a value that is -EFOO if the system call in @regs->orig_ax + * returned an error. This only works for @regs from @current. + */ +static long current_syscall_ret(struct pt_regs *regs) +{ +#ifdef CONFIG_IA32_EMULATION + if (test_thread_flag(TIF_IA32)) + /* + * Sign-extend the value so (int)-EFOO becomes (long)-EFOO + * and will match correctly in comparisons. + */ + return (int) regs->ax; +#endif + return regs->ax; +} + +/* * OK, we're invoking a handler */ @@ -327,9 +356,9 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, #endif /* Are we from a system call? */ - if ((long)regs->orig_ax >= 0) { + if (current_syscall(regs) >= 0) { /* If so, check system call restarting.. */ - switch (regs->ax) { + switch (current_syscall_ret(regs)) { case -ERESTART_RESTARTBLOCK: case -ERESTARTNOHAND: regs->ax = -EINTR; @@ -426,10 +455,9 @@ static void do_signal(struct pt_regs *regs) } /* Did we come from a system call? */ - if ((long)regs->orig_ax >= 0) { + if (current_syscall(regs) >= 0) { /* Restart the system call - no handlers present */ - long res = regs->ax; - switch (res) { + switch (current_syscall_ret(regs)) { case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 9d406cdc847f..071ff4798236 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -140,6 +140,9 @@ static int enable_single_step(struct task_struct *child) */ static void write_debugctlmsr(struct task_struct *child, unsigned long val) { + if (child->thread.debugctlmsr == val) + return; + child->thread.debugctlmsr = val; if (child != current) @@ -165,11 +168,11 @@ static void enable_step(struct task_struct *child, bool block) write_debugctlmsr(child, child->thread.debugctlmsr | DEBUGCTLMSR_BTF); } else { - write_debugctlmsr(child, - child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF); + write_debugctlmsr(child, + child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF); - if (!child->thread.debugctlmsr) - clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); + if (!child->thread.debugctlmsr) + clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); } } diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 022bcaa3b42e..ab6bf375a307 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -92,7 +92,7 @@ int do_set_thread_area(struct task_struct *p, int idx, asmlinkage int sys_set_thread_area(struct user_desc __user *u_info) { int ret = do_set_thread_area(current, -1, u_info, 1); - prevent_tail_call(ret); + asmlinkage_protect(1, ret, u_info); return ret; } @@ -142,7 +142,7 @@ int do_get_thread_area(struct task_struct *p, int idx, asmlinkage int sys_get_thread_area(struct user_desc __user *u_info) { int ret = do_get_thread_area(current, -1, u_info); - prevent_tail_call(ret); + asmlinkage_protect(1, ret, u_info); return ret; } diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c index f14cfd9d1f94..c2241e04ea5f 100644 --- a/arch/x86/kernel/tsc_32.c +++ b/arch/x86/kernel/tsc_32.c @@ -256,9 +256,7 @@ time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) ref_freq, freq->new); if (!(freq->flags & CPUFREQ_CONST_LOOPS)) { tsc_khz = cpu_khz; - preempt_disable(); - set_cyc2ns_scale(cpu_khz, smp_processor_id()); - preempt_enable(); + set_cyc2ns_scale(cpu_khz, freq->cpu); /* * TSC based sched_clock turns * to junk w/ cpufreq diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c index 947554ddabb6..d3bebaaad842 100644 --- a/arch/x86/kernel/tsc_64.c +++ b/arch/x86/kernel/tsc_64.c @@ -148,9 +148,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, mark_tsc_unstable("cpufreq changes"); } - preempt_disable(); - set_cyc2ns_scale(tsc_khz_ref, smp_processor_id()); - preempt_enable(); + set_cyc2ns_scale(tsc_khz_ref, freq->cpu); return 0; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d8172aabc660..e55af12e11b7 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -222,8 +222,7 @@ static int is_io_pte(unsigned long pte) static int is_rmap_pte(u64 pte) { - return pte != shadow_trap_nonpresent_pte - && pte != shadow_notrap_nonpresent_pte; + return is_shadow_present_pte(pte); } static gfn_t pse36_gfn_delta(u32 gpte) @@ -893,14 +892,25 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, int *ptwrite, gfn_t gfn, struct page *page) { u64 spte; - int was_rmapped = is_rmap_pte(*shadow_pte); + int was_rmapped = 0; int was_writeble = is_writeble_pte(*shadow_pte); + hfn_t host_pfn = (*shadow_pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; pgprintk("%s: spte %llx access %x write_fault %d" " user_fault %d gfn %lx\n", __FUNCTION__, *shadow_pte, pt_access, write_fault, user_fault, gfn); + if (is_rmap_pte(*shadow_pte)) { + if (host_pfn != page_to_pfn(page)) { + pgprintk("hfn old %lx new %lx\n", + host_pfn, page_to_pfn(page)); + rmap_remove(vcpu->kvm, shadow_pte); + } + else + was_rmapped = 1; + } + /* * We don't set the accessed bit, since we sometimes want to see * whether the guest actually used the pte (in order to detect @@ -1402,7 +1412,7 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, up_read(¤t->mm->mmap_sem); vcpu->arch.update_pte.gfn = gfn; - vcpu->arch.update_pte.page = gfn_to_page(vcpu->kvm, gfn); + vcpu->arch.update_pte.page = page; } void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 94ea724638fd..8e1462880d1f 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -349,8 +349,6 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) static void reload_tss(void) { -#ifndef CONFIG_X86_64 - /* * VT restores TR but not its size. Useless. */ @@ -361,7 +359,6 @@ static void reload_tss(void) descs = (void *)gdt.base; descs[GDT_ENTRY_TSS].type = 9; /* available TSS */ load_TR_desc(); -#endif } static void load_transition_efer(struct vcpu_vmx *vmx) @@ -1436,7 +1433,7 @@ static int init_rmode_tss(struct kvm *kvm) int ret = 0; int r; - down_read(¤t->mm->mmap_sem); + down_read(&kvm->slots_lock); r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); if (r < 0) goto out; @@ -1459,7 +1456,7 @@ static int init_rmode_tss(struct kvm *kvm) ret = 1; out: - up_read(¤t->mm->mmap_sem); + up_read(&kvm->slots_lock); return ret; } diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index cccb38a59653..3335b4595efd 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -10,21 +10,19 @@ * (such as the example in Documentation/lguest/lguest.c) is called the * Launcher. * - * Secondly, we only run specially modified Guests, not normal kernels. When - * you set CONFIG_LGUEST to 'y' or 'm', this automatically sets - * CONFIG_LGUEST_GUEST=y, which compiles this file into the kernel so it knows - * how to be a Guest. This means that you can use the same kernel you boot - * normally (ie. as a Host) as a Guest. + * Secondly, we only run specially modified Guests, not normal kernels: setting + * CONFIG_LGUEST_GUEST to "y" compiles this file into the kernel so it knows + * how to be a Guest at boot time. This means that you can use the same kernel + * you boot normally (ie. as a Host) as a Guest. * * These Guests know that they cannot do privileged operations, such as disable * interrupts, and that they have to ask the Host to do such things explicitly. * This file consists of all the replacements for such low-level native * hardware operations: these special Guest versions call the Host. * - * So how does the kernel know it's a Guest? The Guest starts at a special - * entry point marked with a magic string, which sets up a few things then - * calls here. We replace the native functions various "paravirt" structures - * with our Guest versions, then boot like normal. :*/ + * So how does the kernel know it's a Guest? We'll see that later, but let's + * just say that we end up here where we replace the native functions various + * "paravirt" structures with our Guest versions, then boot like normal. :*/ /* * Copyright (C) 2006, Rusty Russell <rusty@rustcorp.com.au> IBM Corporation. @@ -84,7 +82,6 @@ struct lguest_data lguest_data = { .blocked_interrupts = { 1 }, /* Block timer interrupts */ .syscall_vec = SYSCALL_VECTOR, }; -static cycle_t clock_base; /*G:037 async_hcall() is pretty simple: I'm quite proud of it really. We have a * ring buffer of stored hypercalls which the Host will run though next time we @@ -135,7 +132,7 @@ static void async_hcall(unsigned long call, unsigned long arg1, * lguest_leave_lazy_mode(). * * So, when we're in lazy mode, we call async_hcall() to store the call for - * future processing. */ + * future processing: */ static void lazy_hcall(unsigned long call, unsigned long arg1, unsigned long arg2, @@ -148,7 +145,7 @@ static void lazy_hcall(unsigned long call, } /* When lazy mode is turned off reset the per-cpu lazy mode variable and then - * issue a hypercall to flush any stored calls. */ + * issue the do-nothing hypercall to flush any stored calls. */ static void lguest_leave_lazy_mode(void) { paravirt_leave_lazy(paravirt_get_lazy_mode()); @@ -165,7 +162,7 @@ static void lguest_leave_lazy_mode(void) * * So instead we keep an "irq_enabled" field inside our "struct lguest_data", * which the Guest can update with a single instruction. The Host knows to - * check there when it wants to deliver an interrupt. + * check there before it tries to deliver an interrupt. */ /* save_flags() is expected to return the processor state (ie. "flags"). The @@ -197,10 +194,15 @@ static void irq_enable(void) /*M:003 Note that we don't check for outstanding interrupts when we re-enable * them (or when we unmask an interrupt). This seems to work for the moment, * since interrupts are rare and we'll just get the interrupt on the next timer - * tick, but when we turn on CONFIG_NO_HZ, we should revisit this. One way + * tick, but now we can run with CONFIG_NO_HZ, we should revisit this. One way * would be to put the "irq_enabled" field in a page by itself, and have the * Host write-protect it when an interrupt comes in when irqs are disabled. - * There will then be a page fault as soon as interrupts are re-enabled. :*/ + * There will then be a page fault as soon as interrupts are re-enabled. + * + * A better method is to implement soft interrupt disable generally for x86: + * instead of disabling interrupts, we set a flag. If an interrupt does come + * in, we then disable them for real. This is uncommon, so we could simply use + * a hypercall for interrupt control and not worry about efficiency. :*/ /*G:034 * The Interrupt Descriptor Table (IDT). @@ -213,6 +215,10 @@ static void irq_enable(void) static void lguest_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g) { + /* The gate_desc structure is 8 bytes long: we hand it to the Host in + * two 32-bit chunks. The whole 32-bit kernel used to hand descriptors + * around like this; typesafety wasn't a big concern in Linux's early + * years. */ u32 *desc = (u32 *)g; /* Keep the local copy up to date. */ native_write_idt_entry(dt, entrynum, g); @@ -244,7 +250,8 @@ static void lguest_load_idt(const struct desc_ptr *desc) * * This is the opposite of the IDT code where we have a LOAD_IDT_ENTRY * hypercall and use that repeatedly to load a new IDT. I don't think it - * really matters, but wouldn't it be nice if they were the same? + * really matters, but wouldn't it be nice if they were the same? Wouldn't + * it be even better if you were the one to send the patch to fix it? */ static void lguest_load_gdt(const struct desc_ptr *desc) { @@ -299,9 +306,9 @@ static void lguest_load_tr_desc(void) /* The "cpuid" instruction is a way of querying both the CPU identity * (manufacturer, model, etc) and its features. It was introduced before the - * Pentium in 1993 and keeps getting extended by both Intel and AMD. As you - * might imagine, after a decade and a half this treatment, it is now a giant - * ball of hair. Its entry in the current Intel manual runs to 28 pages. + * Pentium in 1993 and keeps getting extended by both Intel, AMD and others. + * As you might imagine, after a decade and a half this treatment, it is now a + * giant ball of hair. Its entry in the current Intel manual runs to 28 pages. * * This instruction even it has its own Wikipedia entry. The Wikipedia entry * has been translated into 4 languages. I am not making this up! @@ -327,8 +334,8 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, case 1: /* Basic feature request. */ /* We only allow kernel to see SSE3, CMPXCHG16B and SSSE3 */ *cx &= 0x00002201; - /* SSE, SSE2, FXSR, MMX, CMOV, CMPXCHG8B, FPU. */ - *dx &= 0x07808101; + /* SSE, SSE2, FXSR, MMX, CMOV, CMPXCHG8B, TSC, FPU. */ + *dx &= 0x07808111; /* The Host can do a nice optimization if it knows that the * kernel mappings (addresses above 0xC0000000 or whatever * PAGE_OFFSET is set to) haven't changed. But Linux calls @@ -481,7 +488,7 @@ static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval) { *pmdp = pmdval; lazy_hcall(LHCALL_SET_PMD, __pa(pmdp)&PAGE_MASK, - (__pa(pmdp)&(PAGE_SIZE-1)), 0); + (__pa(pmdp)&(PAGE_SIZE-1))/4, 0); } /* There are a couple of legacy places where the kernel sets a PTE, but we @@ -595,19 +602,25 @@ static unsigned long lguest_get_wallclock(void) return lguest_data.time.tv_sec; } +/* The TSC is an Intel thing called the Time Stamp Counter. The Host tells us + * what speed it runs at, or 0 if it's unusable as a reliable clock source. + * This matches what we want here: if we return 0 from this function, the x86 + * TSC clock will give up and not register itself. */ +static unsigned long lguest_cpu_khz(void) +{ + return lguest_data.tsc_khz; +} + +/* If we can't use the TSC, the kernel falls back to our lower-priority + * "lguest_clock", where we read the time value given to us by the Host. */ static cycle_t lguest_clock_read(void) { unsigned long sec, nsec; - /* If the Host tells the TSC speed, we can trust that. */ - if (lguest_data.tsc_khz) - return native_read_tsc(); - - /* If we can't use the TSC, we read the time value written by the Host. - * Since it's in two parts (seconds and nanoseconds), we risk reading - * it just as it's changing from 99 & 0.999999999 to 100 and 0, and - * getting 99 and 0. As Linux tends to come apart under the stress of - * time travel, we must be careful: */ + /* Since the time is in two parts (seconds and nanoseconds), we risk + * reading it just as it's changing from 99 & 0.999999999 to 100 and 0, + * and getting 99 and 0. As Linux tends to come apart under the stress + * of time travel, we must be careful: */ do { /* First we read the seconds part. */ sec = lguest_data.time.tv_sec; @@ -622,14 +635,14 @@ static cycle_t lguest_clock_read(void) /* Now if the seconds part has changed, try again. */ } while (unlikely(lguest_data.time.tv_sec != sec)); - /* Our non-TSC clock is in real nanoseconds. */ + /* Our lguest clock is in real nanoseconds. */ return sec*1000000000ULL + nsec; } -/* This is what we tell the kernel is our clocksource. */ +/* This is the fallback clocksource: lower priority than the TSC clocksource. */ static struct clocksource lguest_clock = { .name = "lguest", - .rating = 400, + .rating = 200, .read = lguest_clock_read, .mask = CLOCKSOURCE_MASK(64), .mult = 1 << 22, @@ -637,24 +650,22 @@ static struct clocksource lguest_clock = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -/* The "scheduler clock" is just our real clock, adjusted to start at zero */ -static unsigned long long lguest_sched_clock(void) -{ - return cyc2ns(&lguest_clock, lguest_clock_read() - clock_base); -} - /* We also need a "struct clock_event_device": Linux asks us to set it to go * off some time in the future. Actually, James Morris figured all this out, I * just applied the patch. */ static int lguest_clockevent_set_next_event(unsigned long delta, struct clock_event_device *evt) { + /* FIXME: I don't think this can ever happen, but James tells me he had + * to put this code in. Maybe we should remove it now. Anyone? */ if (delta < LG_CLOCK_MIN_DELTA) { if (printk_ratelimit()) printk(KERN_DEBUG "%s: small delta %lu ns\n", __FUNCTION__, delta); return -ETIME; } + + /* Please wake us this far in the future. */ hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0); return 0; } @@ -712,19 +723,8 @@ static void lguest_time_init(void) /* Set up the timer interrupt (0) to go to our simple timer routine */ set_irq_handler(0, lguest_time_irq); - /* Our clock structure looks like arch/x86/kernel/tsc_32.c if we can - * use the TSC, otherwise it's a dumb nanosecond-resolution clock. - * Either way, the "rating" is set so high that it's always chosen over - * any other clocksource. */ - if (lguest_data.tsc_khz) - lguest_clock.mult = clocksource_khz2mult(lguest_data.tsc_khz, - lguest_clock.shift); - clock_base = lguest_clock_read(); clocksource_register(&lguest_clock); - /* Now we've set up our clock, we can use it as the scheduler clock */ - pv_time_ops.sched_clock = lguest_sched_clock; - /* We can't set cpumask in the initializer: damn C limitations! Set it * here and register our timer device. */ lguest_clockevent.cpumask = cpumask_of_cpu(0); @@ -750,7 +750,7 @@ static void lguest_time_init(void) * will not tolerate us trying to use that), the stack pointer, and the number * of pages in the stack. */ static void lguest_load_sp0(struct tss_struct *tss, - struct thread_struct *thread) + struct thread_struct *thread) { lazy_hcall(LHCALL_SET_STACK, __KERNEL_DS|0x1, thread->sp0, THREAD_SIZE/PAGE_SIZE); @@ -798,9 +798,8 @@ static void lguest_safe_halt(void) hcall(LHCALL_HALT, 0, 0, 0); } -/* Perhaps CRASH isn't the best name for this hypercall, but we use it to get a - * message out when we're crashing as well as elegant termination like powering - * off. +/* The SHUTDOWN hypercall takes a string to describe what's happening, and + * an argument which says whether this to restart (reboot) the Guest or not. * * Note that the Host always prefers that the Guest speak in physical addresses * rather than virtual addresses, so we use __pa() here. */ @@ -828,8 +827,9 @@ static struct notifier_block paniced = { /* Setting up memory is fairly easy. */ static __init char *lguest_memory_setup(void) { - /* We do this here and not earlier because lockcheck barfs if we do it - * before start_kernel() */ + /* We do this here and not earlier because lockcheck used to barf if we + * did it before start_kernel(). I think we fixed that, so it'd be + * nice to move it back to lguest_init. Patch welcome... */ atomic_notifier_chain_register(&panic_notifier_list, &paniced); /* The Linux bootloader header contains an "e820" memory map: the @@ -862,12 +862,19 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) return len; } +/* Rebooting also tells the Host we're finished, but the RESTART flag tells the + * Launcher to reboot us. */ +static void lguest_restart(char *reason) +{ + hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0); +} + /*G:050 * Patching (Powerfully Placating Performance Pedants) * - * We have already seen that pv_ops structures let us replace simple - * native instructions with calls to the appropriate back end all throughout - * the kernel. This allows the same kernel to run as a Guest and as a native + * We have already seen that pv_ops structures let us replace simple native + * instructions with calls to the appropriate back end all throughout the + * kernel. This allows the same kernel to run as a Guest and as a native * kernel, but it's slow because of all the indirect branches. * * Remember that David Wheeler quote about "Any problem in computer science can @@ -920,14 +927,9 @@ static unsigned lguest_patch(u8 type, u16 clobber, void *ibuf, return insn_len; } -static void lguest_restart(char *reason) -{ - hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0); -} - -/*G:030 Once we get to lguest_init(), we know we're a Guest. The pv_ops - * structures in the kernel provide points for (almost) every routine we have - * to override to avoid privileged instructions. */ +/*G:030 Once we get to lguest_init(), we know we're a Guest. The various + * pv_ops structures in the kernel provide points for (almost) every routine we + * have to override to avoid privileged instructions. */ __init void lguest_init(void) { /* We're under lguest, paravirt is enabled, and we're running at @@ -995,6 +997,7 @@ __init void lguest_init(void) /* time operations */ pv_time_ops.get_wallclock = lguest_get_wallclock; pv_time_ops.time_init = lguest_time_init; + pv_time_ops.get_cpu_khz = lguest_cpu_khz; /* Now is a good time to look at the implementations of these functions * before returning to the rest of lguest_init(). */ @@ -1014,9 +1017,9 @@ __init void lguest_init(void) * the normal data segment to get through booting. */ asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_DS) : "memory"); - /* The Host uses the top of the Guest's virtual address space for the - * Host<->Guest Switcher, and it tells us how big that is in - * lguest_data.reserve_mem, set up on the LGUEST_INIT hypercall. */ + /* The Host<->Guest Switcher lives at the top of our address space, and + * the Host told us how big it is when we made LGUEST_INIT hypercall: + * it put the answer in lguest_data.reserve_mem */ reserve_top_address(lguest_data.reserve_mem); /* If we don't initialize the lock dependency checker now, it crashes @@ -1038,6 +1041,7 @@ __init void lguest_init(void) /* Math is always hard! */ new_cpu_data.hard_math = 1; + /* We don't have features. We have puppies! Puppies! */ #ifdef CONFIG_X86_MCE mce_disabled = 1; #endif @@ -1055,10 +1059,11 @@ __init void lguest_init(void) virtio_cons_early_init(early_put_chars); /* Last of all, we set the power management poweroff hook to point to - * the Guest routine to power off. */ + * the Guest routine to power off, and the reboot hook to our restart + * routine. */ pm_power_off = lguest_power_off; - machine_ops.restart = lguest_restart; + /* Now we're set up, call start_kernel() in init/main.c and we proceed * to boot as normal. It never returns. */ start_kernel(); diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S index 95b6fbcded63..5c7cef34c9e7 100644 --- a/arch/x86/lguest/i386_head.S +++ b/arch/x86/lguest/i386_head.S @@ -5,13 +5,20 @@ #include <asm/thread_info.h> #include <asm/processor-flags.h> -/*G:020 This is where we begin: head.S notes that the boot header's platform - * type field is "1" (lguest), so calls us here. +/*G:020 Our story starts with the kernel booting into startup_32 in + * arch/x86/kernel/head_32.S. It expects a boot header, which is created by + * the bootloader (the Launcher in our case). + * + * The startup_32 function does very little: it clears the uninitialized global + * C variables which we expect to be zero (ie. BSS) and then copies the boot + * header and kernel command line somewhere safe. Finally it checks the + * 'hardware_subarch' field. This was introduced in 2.6.24 for lguest and Xen: + * if it's set to '1' (lguest's assigned number), then it calls us here. * * WARNING: be very careful here! We're running at addresses equal to physical * addesses (around 0), not above PAGE_OFFSET as most code expectes * (eg. 0xC0000000). Jumps are relative, so they're OK, but we can't touch any - * data. + * data without remembering to subtract __PAGE_OFFSET! * * The .section line puts this code in .init.text so it will be discarded after * boot. */ @@ -24,7 +31,7 @@ ENTRY(lguest_entry) int $LGUEST_TRAP_ENTRY /* The Host put the toplevel pagetable in lguest_data.pgdir. The movsl - * instruction uses %esi implicitly as the source for the copy we' + * instruction uses %esi implicitly as the source for the copy we're * about to do. */ movl lguest_data - __PAGE_OFFSET + LGUEST_DATA_pgdir, %esi diff --git a/arch/x86/mach-rdc321x/gpio.c b/arch/x86/mach-rdc321x/gpio.c index 031269163bd6..247f33d3a407 100644 --- a/arch/x86/mach-rdc321x/gpio.c +++ b/arch/x86/mach-rdc321x/gpio.c @@ -1,91 +1,194 @@ /* - * Copyright (C) 2007, OpenWrt.org, Florian Fainelli <florian@openwrt.org> - * RDC321x architecture specific GPIO support + * GPIO support for RDC SoC R3210/R8610 + * + * Copyright (C) 2007, Florian Fainelli <florian@openwrt.org> + * Copyright (C) 2008, Volker Weiss <dev@tintuc.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. */ -#include <linux/autoconf.h> -#include <linux/init.h> + +#include <linux/spinlock.h> #include <linux/io.h> #include <linux/types.h> #include <linux/module.h> -#include <linux/delay.h> +#include <asm/gpio.h> #include <asm/mach-rdc321x/rdc321x_defs.h> -static inline int rdc_gpio_is_valid(unsigned gpio) + +/* spin lock to protect our private copy of GPIO data register plus + the access to PCI conf registers. */ +static DEFINE_SPINLOCK(gpio_lock); + +/* copy of GPIO data registers */ +static u32 gpio_data_reg1; +static u32 gpio_data_reg2; + +static u32 gpio_request_data[2]; + + +static inline void rdc321x_conf_write(unsigned addr, u32 value) { - return (gpio <= RDC_MAX_GPIO); + outl((1 << 31) | (7 << 11) | addr, RDC3210_CFGREG_ADDR); + outl(value, RDC3210_CFGREG_DATA); } -static unsigned int rdc_gpio_read(unsigned gpio) +static inline void rdc321x_conf_or(unsigned addr, u32 value) { - unsigned int val; - - val = 0x80000000 | (7 << 11) | ((gpio&0x20?0x84:0x48)); - outl(val, RDC3210_CFGREG_ADDR); - udelay(10); - val = inl(RDC3210_CFGREG_DATA); - val |= (0x1 << (gpio & 0x1F)); - outl(val, RDC3210_CFGREG_DATA); - udelay(10); - val = 0x80000000 | (7 << 11) | ((gpio&0x20?0x88:0x4C)); - outl(val, RDC3210_CFGREG_ADDR); - udelay(10); - val = inl(RDC3210_CFGREG_DATA); - - return val; + outl((1 << 31) | (7 << 11) | addr, RDC3210_CFGREG_ADDR); + value |= inl(RDC3210_CFGREG_DATA); + outl(value, RDC3210_CFGREG_DATA); } -static void rdc_gpio_write(unsigned int val) +static inline u32 rdc321x_conf_read(unsigned addr) { - if (val) { - outl(val, RDC3210_CFGREG_DATA); - udelay(10); - } + outl((1 << 31) | (7 << 11) | addr, RDC3210_CFGREG_ADDR); + + return inl(RDC3210_CFGREG_DATA); } -int rdc_gpio_get_value(unsigned gpio) +/* configure pin as GPIO */ +static void rdc321x_configure_gpio(unsigned gpio) +{ + unsigned long flags; + + spin_lock_irqsave(&gpio_lock, flags); + rdc321x_conf_or(gpio < 32 + ? RDC321X_GPIO_CTRL_REG1 : RDC321X_GPIO_CTRL_REG2, + 1 << (gpio & 0x1f)); + spin_unlock_irqrestore(&gpio_lock, flags); +} + +/* initially setup the 2 copies of the gpio data registers. + This function must be called by the platform setup code. */ +void __init rdc321x_gpio_setup() +{ + /* this might not be, what others (BIOS, bootloader, etc.) + wrote to these registers before, but it's a good guess. Still + better than just using 0xffffffff. */ + + gpio_data_reg1 = rdc321x_conf_read(RDC321X_GPIO_DATA_REG1); + gpio_data_reg2 = rdc321x_conf_read(RDC321X_GPIO_DATA_REG2); +} + +/* determine, if gpio number is valid */ +static inline int rdc321x_is_gpio(unsigned gpio) +{ + return gpio <= RDC321X_MAX_GPIO; +} + +/* request GPIO */ +int rdc_gpio_request(unsigned gpio, const char *label) { - if (rdc_gpio_is_valid(gpio)) - return (int)rdc_gpio_read(gpio); - else + unsigned long flags; + + if (!rdc321x_is_gpio(gpio)) return -EINVAL; + + spin_lock_irqsave(&gpio_lock, flags); + if (gpio_request_data[(gpio & 0x20) ? 1 : 0] & (1 << (gpio & 0x1f))) + goto inuse; + gpio_request_data[(gpio & 0x20) ? 1 : 0] |= (1 << (gpio & 0x1f)); + spin_unlock_irqrestore(&gpio_lock, flags); + + return 0; +inuse: + spin_unlock_irqrestore(&gpio_lock, flags); + return -EINVAL; } -EXPORT_SYMBOL(rdc_gpio_get_value); +EXPORT_SYMBOL(rdc_gpio_request); -void rdc_gpio_set_value(unsigned gpio, int value) +/* release previously-claimed GPIO */ +void rdc_gpio_free(unsigned gpio) { - unsigned int val; + unsigned long flags; - if (!rdc_gpio_is_valid(gpio)) + if (!rdc321x_is_gpio(gpio)) return; - val = rdc_gpio_read(gpio); + spin_lock_irqsave(&gpio_lock, flags); + gpio_request_data[(gpio & 0x20) ? 1 : 0] &= ~(1 << (gpio & 0x1f)); + spin_unlock_irqrestore(&gpio_lock, flags); +} +EXPORT_SYMBOL(rdc_gpio_free); + +/* read GPIO pin */ +int rdc_gpio_get_value(unsigned gpio) +{ + u32 reg; + unsigned long flags; + + spin_lock_irqsave(&gpio_lock, flags); + reg = rdc321x_conf_read(gpio < 32 + ? RDC321X_GPIO_DATA_REG1 : RDC321X_GPIO_DATA_REG2); + spin_unlock_irqrestore(&gpio_lock, flags); - if (value) - val &= ~(0x1 << (gpio & 0x1F)); - else - val |= (0x1 << (gpio & 0x1F)); + return (1 << (gpio & 0x1f)) & reg ? 1 : 0; +} +EXPORT_SYMBOL(rdc_gpio_get_value); - rdc_gpio_write(val); +/* set GPIO pin to value */ +void rdc_gpio_set_value(unsigned gpio, int value) +{ + unsigned long flags; + u32 reg; + + reg = 1 << (gpio & 0x1f); + if (gpio < 32) { + spin_lock_irqsave(&gpio_lock, flags); + if (value) + gpio_data_reg1 |= reg; + else + gpio_data_reg1 &= ~reg; + rdc321x_conf_write(RDC321X_GPIO_DATA_REG1, gpio_data_reg1); + spin_unlock_irqrestore(&gpio_lock, flags); + } else { + spin_lock_irqsave(&gpio_lock, flags); + if (value) + gpio_data_reg2 |= reg; + else + gpio_data_reg2 &= ~reg; + rdc321x_conf_write(RDC321X_GPIO_DATA_REG2, gpio_data_reg2); + spin_unlock_irqrestore(&gpio_lock, flags); + } } EXPORT_SYMBOL(rdc_gpio_set_value); +/* configure GPIO pin as input */ int rdc_gpio_direction_input(unsigned gpio) { + if (!rdc321x_is_gpio(gpio)) + return -EINVAL; + + rdc321x_configure_gpio(gpio); + return 0; } EXPORT_SYMBOL(rdc_gpio_direction_input); +/* configure GPIO pin as output and set value */ int rdc_gpio_direction_output(unsigned gpio, int value) { + if (!rdc321x_is_gpio(gpio)) + return -EINVAL; + + gpio_set_value(gpio, value); + rdc321x_configure_gpio(gpio); + return 0; } EXPORT_SYMBOL(rdc_gpio_direction_output); - - diff --git a/arch/x86/mach-rdc321x/platform.c b/arch/x86/mach-rdc321x/platform.c index dda6024a5862..a037041817c7 100644 --- a/arch/x86/mach-rdc321x/platform.c +++ b/arch/x86/mach-rdc321x/platform.c @@ -62,6 +62,8 @@ static struct platform_device *rdc321x_devs[] = { static int __init rdc_board_setup(void) { + rdc321x_gpio_setup(); + return platform_add_devices(rdc321x_devs, ARRAY_SIZE(rdc321x_devs)); } diff --git a/arch/x86/mach-visws/traps.c b/arch/x86/mach-visws/traps.c index 843b67acf43b..bfac6ba10f8a 100644 --- a/arch/x86/mach-visws/traps.c +++ b/arch/x86/mach-visws/traps.c @@ -46,8 +46,9 @@ static __init void cobalt_init(void) */ set_fixmap(FIX_APIC_BASE, APIC_DEFAULT_PHYS_BASE); setup_local_APIC(); - printk(KERN_INFO "Local APIC Version %#lx, ID %#lx\n", - apic_read(APIC_LVR), apic_read(APIC_ID)); + printk(KERN_INFO "Local APIC Version %#x, ID %#x\n", + (unsigned int)apic_read(APIC_LVR), + (unsigned int)apic_read(APIC_ID)); set_fixmap(FIX_CO_CPU, CO_CPU_PHYS); set_fixmap(FIX_CO_APIC, CO_APIC_PHYS); diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c index c394ca0720b8..8e25e06ff730 100644 --- a/arch/x86/mm/discontig_32.c +++ b/arch/x86/mm/discontig_32.c @@ -324,7 +324,6 @@ unsigned long __init setup_memory(void) * this space and use it to adjust the boundary between ZONE_NORMAL * and ZONE_HIGHMEM. */ - find_max_pfn(); get_memcfg_numa(); kva_pages = calculate_numa_remap_pages(); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fdc667422df9..ec08d8389850 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -91,12 +91,10 @@ static int is_prefetch(struct pt_regs *regs, unsigned long addr, int prefetch = 0; unsigned char *max_instr; -#ifdef CONFIG_X86_32 - if (!(__supported_pte_mask & _PAGE_NX)) - return 0; -#endif - - /* If it was a exec fault on NX page, ignore */ + /* + * If it was a exec (instruction fetch) fault on NX page, then + * do not ignore the fault: + */ if (error_code & PF_INSTR) return 0; diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 3d936f232704..9cf33d3ee5bc 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -73,15 +73,15 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) { enum fixed_addresses idx; unsigned long vaddr; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ - - debug_kmap_atomic_prot(type); + /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ pagefault_disable(); if (!PageHighMem(page)) return page_address(page); + debug_kmap_atomic_prot(type); + idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); BUG_ON(!pte_none(*(kmap_pte-idx))); diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 4fbafb4bc2f0..0b3d567e686d 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -178,7 +178,7 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)]; - WARN_ON(!PageCompound(page)); + WARN_ON(!PageHead(page)); return page; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index ac3c959e271d..794895c6dcc9 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -106,7 +106,7 @@ static int ioremap_change_attr(unsigned long vaddr, unsigned long size, * have to convert them into an offset in a page-aligned mapping, but the * caller shouldn't need to know that small detail. */ -static void __iomem *__ioremap(unsigned long phys_addr, unsigned long size, +static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size, enum ioremap_mode mode) { unsigned long pfn, offset, last_addr, vaddr; @@ -134,12 +134,14 @@ static void __iomem *__ioremap(unsigned long phys_addr, unsigned long size, return NULL; } - WARN_ON_ONCE(page_is_ram(pfn)); - switch (mode) { case IOR_MODE_UNCACHED: default: - prot = PAGE_KERNEL_NOCACHE; + /* + * FIXME: we will use UC MINUS for now, as video fb drivers + * depend on it. Upcoming ioremap_wc() will fix this behavior. + */ + prot = PAGE_KERNEL_UC_MINUS; break; case IOR_MODE_CACHED: prot = PAGE_KERNEL; @@ -195,13 +197,13 @@ static void __iomem *__ioremap(unsigned long phys_addr, unsigned long size, * * Must be freed with iounmap. */ -void __iomem *ioremap_nocache(unsigned long phys_addr, unsigned long size) +void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) { return __ioremap(phys_addr, size, IOR_MODE_UNCACHED); } EXPORT_SYMBOL(ioremap_nocache); -void __iomem *ioremap_cache(unsigned long phys_addr, unsigned long size) +void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size) { return __ioremap(phys_addr, size, IOR_MODE_CACHED); } diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 8ccfee10f5b5..16b82ad34b96 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -221,8 +221,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, bootmap_pages<<PAGE_SHIFT, PAGE_SIZE); if (bootmap == NULL) { if (nodedata_phys < start || nodedata_phys >= end) - free_bootmem((unsigned long)node_data[nodeid], - pgdat_size); + free_bootmem(nodedata_phys, pgdat_size); node_data[nodeid] = NULL; return; } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 14e48b5a94ba..7b79f6be4e7d 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -771,7 +771,7 @@ static inline int change_page_attr_clear(unsigned long addr, int numpages, int set_memory_uc(unsigned long addr, int numpages) { return change_page_attr_set(addr, numpages, - __pgprot(_PAGE_PCD | _PAGE_PWT)); + __pgprot(_PAGE_PCD)); } EXPORT_SYMBOL(set_memory_uc); diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 73aba7125203..2f9e9afcb9f4 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -342,12 +342,16 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *pgd = quicklist_alloc(0, GFP_KERNEL, pgd_ctor); + pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - mm->pgd = pgd; /* so that alloc_pd can use it */ + /* so that alloc_pd can use it */ + mm->pgd = pgd; + if (pgd) + pgd_ctor(pgd); if (pgd && !pgd_prepopulate_pmd(mm, pgd)) { - quicklist_free(0, pgd_dtor, pgd); + pgd_dtor(pgd); + free_page((unsigned long)pgd); pgd = NULL; } @@ -357,12 +361,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm) void pgd_free(struct mm_struct *mm, pgd_t *pgd) { pgd_mop_up_pmds(mm, pgd); - quicklist_free(0, pgd_dtor, pgd); -} - -void check_pgt_cache(void) -{ - quicklist_trim(0, pgd_dtor, 25, 16); + pgd_dtor(pgd); + free_page((unsigned long)pgd); } void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte) diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 0234f2831bf3..378136fb5044 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -219,8 +219,21 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do if (pxm >= 0) sd->node = pxm_to_node(pxm); #endif + /* + * Maybe the desired pci bus has been already scanned. In such case + * it is unnecessary to scan the pci bus with the given domain,busnum. + */ + bus = pci_find_bus(domain, busnum); + if (bus) { + /* + * If the desired bus exits, the content of bus->sysdata will + * be replaced by sd. + */ + memcpy(bus->sysdata, sd, sizeof(*sd)); + kfree(sd); + } else + bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd); - bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd); if (!bus) kfree(sd); @@ -228,7 +241,7 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do if (bus != NULL) { if (pxm >= 0) { printk("bus %d -> pxm %d -> node %d\n", - busnum, pxm, sd->node); + busnum, pxm, pxm_to_node(pxm)); } } #endif diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 10ac8c316c46..2f7109ac4c15 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -198,6 +198,11 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, "b" (bx), "D" ((long)reg), "S" (&pci_indirect)); + /* + * Zero-extend the result beyond 8 bits, do not trust the + * BIOS having done it: + */ + *value &= 0xff; break; case 2: __asm__("lcall *(%%esi); cld\n\t" @@ -210,6 +215,11 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, "b" (bx), "D" ((long)reg), "S" (&pci_indirect)); + /* + * Zero-extend the result beyond 16 bits, do not trust the + * BIOS having done it: + */ + *value &= 0xffff; break; case 4: __asm__("lcall *(%%esi); cld\n\t" diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 8b9ee27805fd..27ee26aedf94 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -95,7 +95,7 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&dummy_shared_info; * * 0: not available, 1: available */ -static int have_vcpu_info_placement = 0; +static int have_vcpu_info_placement = 1; static void __init xen_vcpu_setup(int cpu) { @@ -103,6 +103,7 @@ static void __init xen_vcpu_setup(int cpu) int err; struct vcpu_info *vcpup; + BUG_ON(HYPERVISOR_shared_info == &dummy_shared_info); per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; if (!have_vcpu_info_placement) @@ -666,10 +667,10 @@ static void xen_release_pt_init(u32 pfn) make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } -static void pin_pagetable_pfn(unsigned level, unsigned long pfn) +static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) { struct mmuext_op op; - op.cmd = level; + op.cmd = cmd; op.arg1.mfn = pfn_to_mfn(pfn); if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) BUG(); @@ -686,7 +687,8 @@ static void xen_alloc_ptpage(struct mm_struct *mm, u32 pfn, unsigned level) if (!PageHighMem(page)) { make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); - pin_pagetable_pfn(level, pfn); + if (level == PT_PTE) + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); } else /* make sure there are no stray mappings of this page */ @@ -696,27 +698,39 @@ static void xen_alloc_ptpage(struct mm_struct *mm, u32 pfn, unsigned level) static void xen_alloc_pt(struct mm_struct *mm, u32 pfn) { - xen_alloc_ptpage(mm, pfn, MMUEXT_PIN_L1_TABLE); + xen_alloc_ptpage(mm, pfn, PT_PTE); } static void xen_alloc_pd(struct mm_struct *mm, u32 pfn) { - xen_alloc_ptpage(mm, pfn, MMUEXT_PIN_L2_TABLE); + xen_alloc_ptpage(mm, pfn, PT_PMD); } /* This should never happen until we're OK to use struct page */ -static void xen_release_pt(u32 pfn) +static void xen_release_ptpage(u32 pfn, unsigned level) { struct page *page = pfn_to_page(pfn); if (PagePinned(page)) { if (!PageHighMem(page)) { - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); + if (level == PT_PTE) + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } + ClearPagePinned(page); } } +static void xen_release_pt(u32 pfn) +{ + xen_release_ptpage(pfn, PT_PTE); +} + +static void xen_release_pd(u32 pfn) +{ + xen_release_ptpage(pfn, PT_PMD); +} + #ifdef CONFIG_HIGHPTE static void *xen_kmap_atomic_pte(struct page *page, enum km_type type) { @@ -805,33 +819,43 @@ static __init void xen_pagetable_setup_start(pgd_t *base) PFN_DOWN(__pa(xen_start_info->pt_base))); } -static __init void xen_pagetable_setup_done(pgd_t *base) +static __init void setup_shared_info(void) { - /* This will work as long as patching hasn't happened yet - (which it hasn't) */ - pv_mmu_ops.alloc_pt = xen_alloc_pt; - pv_mmu_ops.alloc_pd = xen_alloc_pd; - pv_mmu_ops.release_pt = xen_release_pt; - pv_mmu_ops.release_pd = xen_release_pt; - pv_mmu_ops.set_pte = xen_set_pte; - if (!xen_feature(XENFEAT_auto_translated_physmap)) { + unsigned long addr = fix_to_virt(FIX_PARAVIRT_BOOTMAP); + /* * Create a mapping for the shared info page. * Should be set_fixmap(), but shared_info is a machine * address with no corresponding pseudo-phys address. */ - set_pte_mfn(fix_to_virt(FIX_PARAVIRT_BOOTMAP), + set_pte_mfn(addr, PFN_DOWN(xen_start_info->shared_info), PAGE_KERNEL); - HYPERVISOR_shared_info = - (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP); - + HYPERVISOR_shared_info = (struct shared_info *)addr; } else HYPERVISOR_shared_info = (struct shared_info *)__va(xen_start_info->shared_info); +#ifndef CONFIG_SMP + /* In UP this is as good a place as any to set up shared info */ + xen_setup_vcpu_info_placement(); +#endif +} + +static __init void xen_pagetable_setup_done(pgd_t *base) +{ + /* This will work as long as patching hasn't happened yet + (which it hasn't) */ + pv_mmu_ops.alloc_pt = xen_alloc_pt; + pv_mmu_ops.alloc_pd = xen_alloc_pd; + pv_mmu_ops.release_pt = xen_release_pt; + pv_mmu_ops.release_pd = xen_release_pd; + pv_mmu_ops.set_pte = xen_set_pte; + + setup_shared_info(); + /* Actually pin the pagetable down, but we can't set PG_pinned yet because the page structures don't exist yet. */ { @@ -1182,15 +1206,9 @@ asmlinkage void __init xen_start_kernel(void) x86_write_percpu(xen_cr3, __pa(pgd)); x86_write_percpu(xen_current_cr3, __pa(pgd)); -#ifdef CONFIG_SMP /* Don't do the full vcpu_info placement stuff until we have a - possible map. */ + possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; -#else - /* May as well do it now, since there's no good time to call - it later on UP. */ - xen_setup_vcpu_info_placement(); -#endif pv_info.kernel_rpl = 1; if (xen_feature(XENFEAT_supervisor_mode_kernel)) diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 0144395448ae..2a054ef2a3da 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -310,13 +310,6 @@ pgd_t xen_make_pgd(unsigned long pgd) } #endif /* CONFIG_X86_PAE */ -enum pt_level { - PT_PGD, - PT_PUD, - PT_PMD, - PT_PTE -}; - /* (Yet another) pagetable walker. This one is intended for pinning a pagetable. This means that it walks a pagetable and calls the diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index c9ff27f3ac3a..b5e189b1519d 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -3,6 +3,13 @@ #include <linux/linkage.h> #include <asm/page.h> +enum pt_level { + PT_PGD, + PT_PUD, + PT_PMD, + PT_PTE +}; + /* * Page-directory addresses above 4GB do not fit into architectural %cr3. * When accessing %cr3, or equivalent field in vcpu_guest_context, guests diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 1a43b60c0c62..6b7190449d07 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -33,12 +33,17 @@ events, then enter the hypervisor to get them handled. */ ENTRY(xen_irq_enable_direct) - /* Clear mask and test pending */ - andw $0x00ff, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_pending + /* Unmask events */ + movb $0, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask + /* Preempt here doesn't matter because that will deal with any pending interrupts. The pending check may end up being run on the wrong CPU, but that doesn't hurt. */ + + /* Test for pending */ + testb $0xff, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_pending jz 1f + 2: call check_events 1: ENDPATCH(xen_irq_enable_direct) |