summaryrefslogtreecommitdiffstats
path: root/arch/i386
diff options
context:
space:
mode:
Diffstat (limited to 'arch/i386')
-rw-r--r--arch/i386/Kconfig13
-rw-r--r--arch/i386/Makefile4
-rw-r--r--arch/i386/boot/edd.c54
-rw-r--r--arch/i386/boot/video.c2
-rw-r--r--arch/i386/kernel/alternative.c39
-rw-r--r--arch/i386/kernel/apic.c12
-rw-r--r--arch/i386/kernel/cpu/amd.c7
-rw-r--r--arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c41
-rw-r--r--arch/i386/kernel/doublefault.c13
-rw-r--r--arch/i386/kernel/head.S4
-rw-r--r--arch/i386/kernel/io_apic.c7
-rw-r--r--arch/i386/kernel/nmi.c4
-rw-r--r--arch/i386/kernel/paravirt.c52
-rw-r--r--arch/i386/kernel/vmi.c35
-rw-r--r--arch/i386/mm/fault.c5
-rw-r--r--arch/i386/mm/pageattr.c2
-rw-r--r--arch/i386/pci/common.c23
-rw-r--r--arch/i386/pci/fixup.c6
-rw-r--r--arch/i386/pci/irq.c5
-rw-r--r--arch/i386/pci/legacy.c2
-rw-r--r--arch/i386/pci/mmconfig.c14
-rw-r--r--arch/i386/pci/numa.c15
-rw-r--r--arch/i386/pci/pci.h43
-rw-r--r--arch/i386/pci/visws.c4
-rw-r--r--arch/i386/xen/enlighten.c12
-rw-r--r--arch/i386/xen/xen-head.S6
26 files changed, 243 insertions, 181 deletions
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index f9524933258..97b64d7d6bf 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -614,10 +614,14 @@ config X86_PAE
# Common NUMA Features
config NUMA
- bool "Numa Memory Allocation and Scheduler Support"
- depends on SMP && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI)
+ bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
+ depends on SMP && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI) && EXPERIMENTAL
default n if X86_PC
default y if (X86_NUMAQ || X86_SUMMIT)
+ help
+ NUMA support for i386. This is currently high experimental
+ and should be only used for kernel development. It might also
+ cause boot failures.
comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
depends on X86_SUMMIT && (!HIGHMEM64G || !ACPI)
@@ -1228,6 +1232,11 @@ menuconfig INSTRUMENTATION
bool "Instrumentation Support"
depends on EXPERIMENTAL
default y
+ ---help---
+ Say Y here to get to see options related to performance measurement,
+ debugging, and testing. This option alone does not add any kernel code.
+
+ If you say N, all options in this submenu will be skipped and disabled.
if INSTRUMENTATION
diff --git a/arch/i386/Makefile b/arch/i386/Makefile
index 01f0ff0daaf..52b932478c6 100644
--- a/arch/i386/Makefile
+++ b/arch/i386/Makefile
@@ -51,8 +51,8 @@ cflags-y += -maccumulate-outgoing-args
CFLAGS += $(shell if [ $(call cc-version) -lt 0400 ] ; then echo $(call cc-option,-fno-unit-at-a-time); fi ;)
# do binutils support CFI?
-cflags-y += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
-AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
+cflags-y += $(call as-instr,.cfi_startproc\n.cfi_rel_offset esp${comma}0\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
+AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_rel_offset esp${comma}0\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
# is .cfi_signal_frame supported too?
cflags-y += $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1,)
diff --git a/arch/i386/boot/edd.c b/arch/i386/boot/edd.c
index 658834d9f92..82b5c846a19 100644
--- a/arch/i386/boot/edd.c
+++ b/arch/i386/boot/edd.c
@@ -19,40 +19,12 @@
#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
-struct edd_dapa {
- u8 pkt_size;
- u8 rsvd;
- u16 sector_cnt;
- u16 buf_off, buf_seg;
- u64 lba;
- u64 buf_lin_addr;
-};
-
/*
* Read the MBR (first sector) from a specific device.
*/
static int read_mbr(u8 devno, void *buf)
{
- struct edd_dapa dapa;
- u16 ax, bx, cx, dx, si;
-
- memset(&dapa, 0, sizeof dapa);
- dapa.pkt_size = sizeof(dapa);
- dapa.sector_cnt = 1;
- dapa.buf_off = (size_t)buf;
- dapa.buf_seg = ds();
- /* dapa.lba = 0; */
-
- ax = 0x4200; /* Extended Read */
- si = (size_t)&dapa;
- dx = devno;
- asm("pushfl; stc; int $0x13; setc %%al; popfl"
- : "+a" (ax), "+S" (si), "+d" (dx)
- : "m" (dapa)
- : "ebx", "ecx", "edi", "memory");
-
- if (!(u8)ax)
- return 0; /* OK */
+ u16 ax, bx, cx, dx;
ax = 0x0201; /* Legacy Read, one sector */
cx = 0x0001; /* Sector 0-0-1 */
@@ -65,11 +37,10 @@ static int read_mbr(u8 devno, void *buf)
return -(u8)ax; /* 0 or -1 */
}
-static u32 read_mbr_sig(u8 devno, struct edd_info *ei)
+static u32 read_mbr_sig(u8 devno, struct edd_info *ei, u32 *mbrsig)
{
int sector_size;
char *mbrbuf_ptr, *mbrbuf_end;
- u32 mbrsig;
u32 buf_base, mbr_base;
extern char _end[];
@@ -85,15 +56,15 @@ static u32 read_mbr_sig(u8 devno, struct edd_info *ei)
/* Make sure we actually have space on the heap... */
if (!(boot_params.hdr.loadflags & CAN_USE_HEAP))
- return 0;
+ return -1;
if (mbrbuf_end > (char *)(size_t)boot_params.hdr.heap_end_ptr)
- return 0;
+ return -1;
if (read_mbr(devno, mbrbuf_ptr))
- return 0;
+ return -1;
- mbrsig = *(u32 *)&mbrbuf_ptr[EDD_MBR_SIG_OFFSET];
- return mbrsig;
+ *mbrsig = *(u32 *)&mbrbuf_ptr[EDD_MBR_SIG_OFFSET];
+ return 0;
}
static int get_edd_info(u8 devno, struct edd_info *ei)
@@ -160,6 +131,7 @@ void query_edd(void)
int do_edd = 1;
int devno;
struct edd_info ei, *edp;
+ u32 *mbrptr;
if (cmdline_find_option("edd", eddarg, sizeof eddarg) > 0) {
if (!strcmp(eddarg, "skipmbr") || !strcmp(eddarg, "skip"))
@@ -168,7 +140,8 @@ void query_edd(void)
do_edd = 0;
}
- edp = (struct edd_info *)boot_params.eddbuf;
+ edp = boot_params.eddbuf;
+ mbrptr = boot_params.edd_mbr_sig_buffer;
if (!do_edd)
return;
@@ -186,11 +159,8 @@ void query_edd(void)
boot_params.eddbuf_entries++;
}
- if (do_mbr) {
- u32 mbr_sig;
- mbr_sig = read_mbr_sig(devno, &ei);
- boot_params.edd_mbr_sig_buffer[devno-0x80] = mbr_sig;
- }
+ if (do_mbr && !read_mbr_sig(devno, &ei, mbrptr++))
+ boot_params.edd_mbr_sig_buf_entries = devno-0x80+1;
}
}
diff --git a/arch/i386/boot/video.c b/arch/i386/boot/video.c
index 958130ef004..693f20d3102 100644
--- a/arch/i386/boot/video.c
+++ b/arch/i386/boot/video.c
@@ -61,7 +61,7 @@ static void store_video_mode(void)
/* Not all BIOSes are clean with respect to the top bit */
boot_params.screen_info.orig_video_mode = ax & 0x7f;
- boot_params.screen_info.orig_video_page = page;
+ boot_params.screen_info.orig_video_page = page >> 8;
}
/*
diff --git a/arch/i386/kernel/alternative.c b/arch/i386/kernel/alternative.c
index c85598acb8f..9f4ac8b02de 100644
--- a/arch/i386/kernel/alternative.c
+++ b/arch/i386/kernel/alternative.c
@@ -11,6 +11,8 @@
#include <asm/mce.h>
#include <asm/nmi.h>
+#define MAX_PATCH_LEN (255-1)
+
#ifdef CONFIG_HOTPLUG_CPU
static int smp_alt_once;
@@ -148,7 +150,8 @@ static unsigned char** find_nop_table(void)
#endif /* CONFIG_X86_64 */
-static void nop_out(void *insns, unsigned int len)
+/* Use this to add nops to a buffer, then text_poke the whole buffer. */
+static void add_nops(void *insns, unsigned int len)
{
unsigned char **noptable = find_nop_table();
@@ -156,7 +159,7 @@ static void nop_out(void *insns, unsigned int len)
unsigned int noplen = len;
if (noplen > ASM_NOP_MAX)
noplen = ASM_NOP_MAX;
- text_poke(insns, noptable[noplen], noplen);
+ memcpy(insns, noptable[noplen], noplen);
insns += noplen;
len -= noplen;
}
@@ -174,15 +177,15 @@ extern u8 *__smp_locks[], *__smp_locks_end[];
void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
{
struct alt_instr *a;
- u8 *instr;
- int diff;
+ char insnbuf[MAX_PATCH_LEN];
DPRINTK("%s: alt table %p -> %p\n", __FUNCTION__, start, end);
for (a = start; a < end; a++) {
+ u8 *instr = a->instr;
BUG_ON(a->replacementlen > a->instrlen);
+ BUG_ON(a->instrlen > sizeof(insnbuf));
if (!boot_cpu_has(a->cpuid))
continue;
- instr = a->instr;
#ifdef CONFIG_X86_64
/* vsyscall code is not mapped yet. resolve it manually. */
if (instr >= (u8 *)VSYSCALL_START && instr < (u8*)VSYSCALL_END) {
@@ -191,9 +194,10 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
__FUNCTION__, a->instr, instr);
}
#endif
- memcpy(instr, a->replacement, a->replacementlen);
- diff = a->instrlen - a->replacementlen;
- nop_out(instr + a->replacementlen, diff);
+ memcpy(insnbuf, a->replacement, a->replacementlen);
+ add_nops(insnbuf + a->replacementlen,
+ a->instrlen - a->replacementlen);
+ text_poke(instr, insnbuf, a->instrlen);
}
}
@@ -215,16 +219,18 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end)
{
u8 **ptr;
+ char insn[1];
if (noreplace_smp)
return;
+ add_nops(insn, 1);
for (ptr = start; ptr < end; ptr++) {
if (*ptr < text)
continue;
if (*ptr > text_end)
continue;
- nop_out(*ptr, 1);
+ text_poke(*ptr, insn, 1);
};
}
@@ -351,6 +357,7 @@ void apply_paravirt(struct paravirt_patch_site *start,
struct paravirt_patch_site *end)
{
struct paravirt_patch_site *p;
+ char insnbuf[MAX_PATCH_LEN];
if (noreplace_paravirt)
return;
@@ -358,13 +365,17 @@ void apply_paravirt(struct paravirt_patch_site *start,
for (p = start; p < end; p++) {
unsigned int used;
- used = paravirt_ops.patch(p->instrtype, p->clobbers, p->instr,
- p->len);
+ BUG_ON(p->len > MAX_PATCH_LEN);
+ /* prep the buffer with the original instructions */
+ memcpy(insnbuf, p->instr, p->len);
+ used = paravirt_ops.patch(p->instrtype, p->clobbers, insnbuf,
+ (unsigned long)p->instr, p->len);
BUG_ON(used > p->len);
/* Pad the rest with nops */
- nop_out(p->instr + used, p->len - used);
+ add_nops(insnbuf + used, p->len - used);
+ text_poke(p->instr, insnbuf, p->len);
}
}
extern struct paravirt_patch_site __start_parainstructions[],
@@ -379,7 +390,7 @@ void __init alternative_instructions(void)
that might execute the to be patched code.
Other CPUs are not running. */
stop_nmi();
-#ifdef CONFIG_MCE
+#ifdef CONFIG_X86_MCE
stop_mce();
#endif
@@ -417,7 +428,7 @@ void __init alternative_instructions(void)
local_irq_restore(flags);
restart_nmi();
-#ifdef CONFIG_MCE
+#ifdef CONFIG_X86_MCE
restart_mce();
#endif
}
diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index bfc6cb7df7e..3d67ae18d76 100644
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -61,8 +61,9 @@ static int enable_local_apic __initdata = 0;
/* Local APIC timer verification ok */
static int local_apic_timer_verify_ok;
-/* Disable local APIC timer from the kernel commandline or via dmi quirk */
-static int local_apic_timer_disabled;
+/* Disable local APIC timer from the kernel commandline or via dmi quirk
+ or using CPU MSR check */
+int local_apic_timer_disabled;
/* Local APIC timer works in C2 */
int local_apic_timer_c2_ok;
EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
@@ -370,12 +371,9 @@ void __init setup_boot_APIC_clock(void)
long delta, deltapm;
int pm_referenced = 0;
- if (boot_cpu_has(X86_FEATURE_LAPIC_TIMER_BROKEN))
- local_apic_timer_disabled = 1;
-
/*
* The local apic timer can be disabled via the kernel
- * commandline or from the test above. Register the lapic
+ * commandline or from the CPU detection code. Register the lapic
* timer as a dummy clock event source on SMP systems, so the
* broadcast mechanism is used. On UP systems simply ignore it.
*/
@@ -1087,7 +1085,7 @@ static int __init detect_init_APIC (void)
if (l & MSR_IA32_APICBASE_ENABLE)
mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
- if (nmi_watchdog != NMI_NONE)
+ if (nmi_watchdog != NMI_NONE && nmi_watchdog != NMI_DISABLED)
nmi_watchdog = NMI_LOCAL_APIC;
printk(KERN_INFO "Found and enabled local APIC!\n");
diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c
index c7ba455d5ac..dcf6bbb1c7c 100644
--- a/arch/i386/kernel/cpu/amd.c
+++ b/arch/i386/kernel/cpu/amd.c
@@ -3,6 +3,7 @@
#include <linux/mm.h>
#include <asm/io.h>
#include <asm/processor.h>
+#include <asm/apic.h>
#include "cpu.h"
@@ -22,6 +23,7 @@
extern void vide(void);
__asm__(".align 4\nvide: ret");
+#ifdef CONFIG_X86_LOCAL_APIC
#define ENABLE_C1E_MASK 0x18000000
#define CPUID_PROCESSOR_SIGNATURE 1
#define CPUID_XFAM 0x0ff00000
@@ -52,6 +54,7 @@ static __cpuinit int amd_apic_timer_broken(void)
}
return 0;
}
+#endif
int force_mwait __cpuinitdata;
@@ -282,8 +285,10 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
num_cache_leaves = 3;
}
+#ifdef CONFIG_X86_LOCAL_APIC
if (amd_apic_timer_broken())
- set_bit(X86_FEATURE_LAPIC_TIMER_BROKEN, c->x86_capability);
+ local_apic_timer_disabled = 1;
+#endif
if (c->x86 == 0x10 && !force_mwait)
clear_bit(X86_FEATURE_MWAIT, c->x86_capability);
diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
index 32d04b083e3..705e13a3078 100644
--- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -68,7 +68,8 @@ struct acpi_cpufreq_data {
};
static struct acpi_cpufreq_data *drv_data[NR_CPUS];
-static struct acpi_processor_performance *acpi_perf_data[NR_CPUS];
+/* acpi_perf_data is a pointer to percpu data. */
+static struct acpi_processor_performance *acpi_perf_data;
static struct cpufreq_driver acpi_cpufreq_driver;
@@ -508,24 +509,14 @@ acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu)
* do _PDC and _PSD and find out the processor dependency for the
* actual init that will happen later...
*/
-static int acpi_cpufreq_early_init(void)
+static int __init acpi_cpufreq_early_init(void)
{
- struct acpi_processor_performance *data;
- unsigned int i, j;
-
dprintk("acpi_cpufreq_early_init\n");
- for_each_possible_cpu(i) {
- data = kzalloc(sizeof(struct acpi_processor_performance),
- GFP_KERNEL);
- if (!data) {
- for_each_possible_cpu(j) {
- kfree(acpi_perf_data[j]);
- acpi_perf_data[j] = NULL;
- }
- return -ENOMEM;
- }
- acpi_perf_data[i] = data;
+ acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
+ if (!acpi_perf_data) {
+ dprintk("Memory allocation error for acpi_perf_data.\n");
+ return -ENOMEM;
}
/* Do initialization in ACPI core */
@@ -574,14 +565,11 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
dprintk("acpi_cpufreq_cpu_init\n");
- if (!acpi_perf_data[cpu])
- return -ENODEV;
-
data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL);
if (!data)
return -ENOMEM;
- data->acpi_data = acpi_perf_data[cpu];
+ data->acpi_data = percpu_ptr(acpi_perf_data, cpu);
drv_data[cpu] = data;
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))
@@ -778,24 +766,25 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
static int __init acpi_cpufreq_init(void)
{
+ int ret;
+
dprintk("acpi_cpufreq_init\n");
- acpi_cpufreq_early_init();
+ ret = acpi_cpufreq_early_init();
+ if (ret)
+ return ret;
return cpufreq_register_driver(&acpi_cpufreq_driver);
}
static void __exit acpi_cpufreq_exit(void)
{
- unsigned int i;
dprintk("acpi_cpufreq_exit\n");
cpufreq_unregister_driver(&acpi_cpufreq_driver);
- for_each_possible_cpu(i) {
- kfree(acpi_perf_data[i]);
- acpi_perf_data[i] = NULL;
- }
+ free_percpu(acpi_perf_data);
+
return;
}
diff --git a/arch/i386/kernel/doublefault.c b/arch/i386/kernel/doublefault.c
index 265c5597efb..40978af630e 100644
--- a/arch/i386/kernel/doublefault.c
+++ b/arch/i386/kernel/doublefault.c
@@ -13,7 +13,7 @@
static unsigned long doublefault_stack[DOUBLEFAULT_STACKSIZE];
#define STACK_START (unsigned long)(doublefault_stack+DOUBLEFAULT_STACKSIZE)
-#define ptr_ok(x) ((x) > PAGE_OFFSET && (x) < PAGE_OFFSET + 0x1000000)
+#define ptr_ok(x) ((x) > PAGE_OFFSET && (x) < PAGE_OFFSET + MAXMEM)
static void doublefault_fn(void)
{
@@ -23,23 +23,23 @@ static void doublefault_fn(void)
store_gdt(&gdt_desc);
gdt = gdt_desc.address;
- printk("double fault, gdt at %08lx [%d bytes]\n", gdt, gdt_desc.size);
+ printk(KERN_EMERG "PANIC: double fault, gdt at %08lx [%d bytes]\n", gdt, gdt_desc.size);
if (ptr_ok(gdt)) {
gdt += GDT_ENTRY_TSS << 3;
tss = *(u16 *)(gdt+2);
tss += *(u8 *)(gdt+4) << 16;
tss += *(u8 *)(gdt+7) << 24;
- printk("double fault, tss at %08lx\n", tss);
+ printk(KERN_EMERG "double fault, tss at %08lx\n", tss);
if (ptr_ok(tss)) {
struct i386_hw_tss *t = (struct i386_hw_tss *)tss;
- printk("eip = %08lx, esp = %08lx\n", t->eip, t->esp);
+ printk(KERN_EMERG "eip = %08lx, esp = %08lx\n", t->eip, t->esp);
- printk("eax = %08lx, ebx = %08lx, ecx = %08lx, edx = %08lx\n",
+ printk(KERN_EMERG "eax = %08lx, ebx = %08lx, ecx = %08lx, edx = %08lx\n",
t->eax, t->ebx, t->ecx, t->edx);
- printk("esi = %08lx, edi = %08lx\n",
+ printk(KERN_EMERG "esi = %08lx, edi = %08lx\n",
t->esi, t->edi);
}
}
@@ -63,6 +63,7 @@ struct tss_struct doublefault_tss __cacheline_aligned = {
.cs = __KERNEL_CS,
.ss = __KERNEL_DS,
.ds = __USER_DS,
+ .fs = __KERNEL_PERCPU,
.__cr3 = __pa(swapper_pg_dir)
}
diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S
index 7c52b222207..8f0382161c9 100644
--- a/arch/i386/kernel/head.S
+++ b/arch/i386/kernel/head.S
@@ -162,9 +162,7 @@ page_pde_offset = (__PAGE_OFFSET >> 20);
* which will be freed later
*/
-#ifdef CONFIG_HOTPLUG_CPU
-.section .text,"ax",@progbits
-#else
+#ifndef CONFIG_HOTPLUG_CPU
.section .init.text,"ax",@progbits
#endif
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 893df828075..4b8a8da4b2e 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -1256,12 +1256,15 @@ static struct irq_chip ioapic_chip;
static void ioapic_register_intr(int irq, int vector, unsigned long trigger)
{
if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
- trigger == IOAPIC_LEVEL)
+ trigger == IOAPIC_LEVEL) {
+ irq_desc[irq].status |= IRQ_LEVEL;
set_irq_chip_and_handler_name(irq, &ioapic_chip,
handle_fasteoi_irq, "fasteoi");
- else
+ } else {
+ irq_desc[irq].status &= ~IRQ_LEVEL;
set_irq_chip_and_handler_name(irq, &ioapic_chip,
handle_edge_irq, "edge");
+ }
set_intr_gate(vector, interrupt[irq]);
}
diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index 99beac7f96c..8c1c965eb2a 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -77,7 +77,7 @@ static int __init check_nmi_watchdog(void)
unsigned int *prev_nmi_count;
int cpu;
- if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DEFAULT))
+ if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DISABLED))
return 0;
if (!atomic_read(&nmi_active))
@@ -424,7 +424,7 @@ int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
if (!!old_state == !!nmi_watchdog_enabled)
return 0;
- if (atomic_read(&nmi_active) < 0) {
+ if (atomic_read(&nmi_active) < 0 || nmi_watchdog == NMI_DISABLED) {
printk( KERN_WARNING "NMI watchdog is permanently disabled\n");
return -EIO;
}
diff --git a/arch/i386/kernel/paravirt.c b/arch/i386/kernel/paravirt.c
index ea962c0667d..739cfb207dd 100644
--- a/arch/i386/kernel/paravirt.c
+++ b/arch/i386/kernel/paravirt.c
@@ -69,7 +69,8 @@ DEF_NATIVE(read_tsc, "rdtsc");
DEF_NATIVE(ud2a, "ud2a");
-static unsigned native_patch(u8 type, u16 clobbers, void *insns, unsigned len)
+static unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
+ unsigned long addr, unsigned len)
{
const unsigned char *start, *end;
unsigned ret;
@@ -90,7 +91,7 @@ static unsigned native_patch(u8 type, u16 clobbers, void *insns, unsigned len)
#undef SITE
patch_site:
- ret = paravirt_patch_insns(insns, len, start, end);
+ ret = paravirt_patch_insns(ibuf, len, start, end);
break;
case PARAVIRT_PATCH(make_pgd):
@@ -107,7 +108,7 @@ static unsigned native_patch(u8 type, u16 clobbers, void *insns, unsigned len)
break;
default:
- ret = paravirt_patch_default(type, clobbers, insns, len);
+ ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
break;
}
@@ -129,68 +130,67 @@ struct branch {
u32 delta;
} __attribute__((packed));
-unsigned paravirt_patch_call(void *target, u16 tgt_clobbers,
- void *site, u16 site_clobbers,
+unsigned paravirt_patch_call(void *insnbuf,
+ const void *target, u16 tgt_clobbers,
+ unsigned long addr, u16 site_clobbers,
unsigned len)
{
- unsigned char *call = site;
- unsigned long delta = (unsigned long)target - (unsigned long)(call+5);
- struct branch b;
+ struct branch *b = insnbuf;
+ unsigned long delta = (unsigned long)target - (addr+5);
if (tgt_clobbers & ~site_clobbers)
return len; /* target would clobber too much for this site */
if (len < 5)
return len; /* call too long for patch site */
- b.opcode = 0xe8; /* call */
- b.delta = delta;
- BUILD_BUG_ON(sizeof(b) != 5);
- text_poke(call, (unsigned char *)&b, 5);
+ b->opcode = 0xe8; /* call */
+ b->delta = delta;
+ BUILD_BUG_ON(sizeof(*b) != 5);
return 5;
}
-unsigned paravirt_patch_jmp(void *target, void *site, unsigned len)
+unsigned paravirt_patch_jmp(const void *target, void *insnbuf,
+ unsigned long addr, unsigned len)
{
- unsigned char *jmp = site;
- unsigned long delta = (unsigned long)target - (unsigned long)(jmp+5);
- struct branch b;
+ struct branch *b = insnbuf;
+ unsigned long delta = (unsigned long)target - (addr+5);
if (len < 5)
return len; /* call too long for patch site */
- b.opcode = 0xe9; /* jmp */
- b.delta = delta;
- text_poke(jmp, (unsigned char *)&b, 5);
+ b->opcode = 0xe9; /* jmp */
+ b->delta = delta;
return 5;
}
-unsigned paravirt_patch_default(u8 type, u16 clobbers, void *site, unsigned len)
+unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
+ unsigned long addr, unsigned len)
{
void *opfunc = *((void **)&paravirt_ops + type);
unsigned ret;
if (opfunc == NULL)
/* If there's no function, patch it with a ud2a (BUG) */
- ret = paravirt_patch_insns(site, len, start_ud2a, end_ud2a);
+ ret = paravirt_patch_insns(insnbuf, len, start_ud2a, end_ud2a);
else if (opfunc == paravirt_nop)
/* If the operation is a nop, then nop the callsite */
ret = paravirt_patch_nop();
else if (type == PARAVIRT_PATCH(iret) ||
type == PARAVIRT_PATCH(irq_enable_sysexit))
/* If operation requires a jmp, then jmp */
- ret = paravirt_patch_jmp(opfunc, site, len);
+ ret = paravirt_patch_jmp(opfunc, insnbuf, addr, len);
else
/* Otherwise call the function; assume target could
clobber any caller-save reg */
- ret = paravirt_patch_call(opfunc, CLBR_ANY,
- site, clobbers, len);
+ ret = paravirt_patch_call(insnbuf, opfunc, CLBR_ANY,
+ addr, clobbers, len);
return ret;
}
-unsigned paravirt_patch_insns(void *site, unsigned len,
+unsigned paravirt_patch_insns(void *insnbuf, unsigned len,
const char *start, const char *end)
{
unsigned insn_len = end - start;
@@ -198,7 +198,7 @@ unsigned paravirt_patch_insns(void *site, unsigned len,
if (insn_len > len || start == NULL)
insn_len = len;
else
- memcpy(site, start, insn_len);
+ memcpy(insnbuf, start, insn_len);
return insn_len;
}
diff --git a/arch/i386/kernel/vmi.c b/arch/i386/kernel/vmi.c
index 72042bb7ec9..18673e0f193 100644
--- a/arch/i386/kernel/vmi.c
+++ b/arch/i386/kernel/vmi.c
@@ -87,12 +87,14 @@ struct vmi_timer_ops vmi_timer_ops;
#define IRQ_PATCH_INT_MASK 0
#define IRQ_PATCH_DISABLE 5
-static inline void patch_offset(unsigned char *eip, unsigned char *dest)
+static inline void patch_offset(void *insnbuf,
+ unsigned long eip, unsigned long dest)
{
- *(unsigned long *)(eip+1) = dest-eip-5;
+ *(unsigned long *)(insnbuf+1) = dest-eip-5;
}
-static unsigned patch_internal(int call, unsigned len, void *insns)
+static unsigned patch_internal(int call, unsigned len, void *insnbuf,
+ unsigned long eip)
{
u64 reloc;
struct vmi_relocation_info *const rel = (struct vmi_relocation_info *)&reloc;
@@ -100,14 +102,14 @@ static unsigned patch_internal(int call, unsigned len, void *insns)
switch(rel->type) {
case VMI_RELOCATION_CALL_REL:
BUG_ON(len < 5);
- *(char *)insns = MNEM_CALL;
- patch_offset(insns, rel->eip);
+ *(char *)insnbuf = MNEM_CALL;
+ patch_offset(insnbuf, eip, (unsigned long)rel->eip);
return 5;
case VMI_RELOCATION_JUMP_REL:
BUG_ON(len < 5);
- *(char *)insns = MNEM_JMP;
- patch_offset(insns, rel->eip);
+ *(char *)insnbuf = MNEM_JMP;
+ patch_offset(insnbuf, eip, (unsigned long)rel->eip);
return 5;
case VMI_RELOCATION_NOP:
@@ -128,21 +130,26 @@ static unsigned patch_internal(int call, unsigned len, void *insns)
* Apply patch if appropriate, return length of new instruction
* sequence. The callee does nop padding for us.
*/
-static unsigned vmi_patch(u8 type, u16 clobbers, void *insns, unsigned len)
+static unsigned vmi_patch(u8 type, u16 clobbers, void *insns,
+ unsigned long eip, unsigned len)
{
switch (type) {
case PARAVIRT_PATCH(irq_disable):
- return patch_internal(VMI_CALL_DisableInterrupts, len, insns);
+ return patch_internal(VMI_CALL_DisableInterrupts, len,
+ insns, eip);
case PARAVIRT_PATCH(irq_enable):
- return patch_internal(VMI_CALL_EnableInterrupts, len, insns);
+ return patch_internal(VMI_CALL_EnableInterrupts, len,
+ insns, eip);
case PARAVIRT_PATCH(restore_fl):
- return patch_internal(VMI_CALL_SetInterruptMask, len, insns);
+ return patch_internal(VMI_CALL_SetInterruptMask, len,
+ insns, eip);
case PARAVIRT_PATCH(save_fl):
- return patch_internal(VMI_CALL_GetInterruptMask, len, insns);
+ return patch_internal(VMI_CALL_GetInterruptMask, len,
+ insns, eip);
case PARAVIRT_PATCH(iret):
- return patch_internal(VMI_CALL_IRET, len, insns);
+ return patch_internal(VMI_CALL_IRET, len, insns, eip);
case PARAVIRT_PATCH(irq_enable_sysexit):
- return patch_internal(VMI_CALL_SYSEXIT, len, insns);
+ return patch_internal(VMI_CALL_SYSEXIT, len, insns, eip);
default:
break;
}
diff --git a/arch/i386/mm/fault.c b/arch/i386/mm/fault.c
index 01ffdd4964f..fcb38e7f354 100644
--- a/arch/i386/mm/fault.c
+++ b/arch/i386/mm/fault.c
@@ -249,9 +249,10 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
pmd_k = pmd_offset(pud_k, address);
if (!pmd_present(*pmd_k))
return NULL;
- if (!pmd_present(*pmd))
+ if (!pmd_present(*pmd)) {
set_pmd(pmd, *pmd_k);
- else
+ arch_flush_lazy_mmu_mode();
+ } else
BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
return pmd_k;
}
diff --git a/arch/i386/mm/pageattr.c b/arch/i386/mm/pageattr.c
index 8927222b3ab..4241a74d16c 100644
--- a/arch/i386/mm/pageattr.c
+++ b/arch/i386/mm/pageattr.c
@@ -82,7 +82,7 @@ static void flush_kernel_map(void *arg)
struct page *p;
/* High level code is not ready for clflush yet */
- if (cpu_has_clflush) {
+ if (0 && cpu_has_clflush) {
list_for_each_entry (p, lh, lru)
cache_flush_page(p);
} else if (boot_cpu_data.x86_model >= 4)
diff --git a/arch/i386/pci/common.c b/arch/i386/pci/common.c
index 85503deeda4..ebc6f3c6634 100644
--- a/arch/i386/pci/common.c
+++ b/arch/i386/pci/common.c
@@ -455,3 +455,26 @@ void pcibios_disable_device (struct pci_dev *dev)
if (!dev->msi_enabled && pcibios_disable_irq)
pcibios_disable_irq(dev);
}
+
+struct pci_bus *pci_scan_bus_with_sysdata(int busno)
+{
+ struct pci_bus *bus = NULL;
+ struct pci_sysdata *sd;
+
+ /*
+ * Allocate per-root-bus (not per bus) arch-specific data.
+ * TODO: leak; this memory is never freed.
+ * It's arguable whether it's worth the trouble to care.
+ */
+ sd = kzalloc(sizeof(*sd), GFP_KERNEL);
+ if (!sd) {
+ printk(KERN_ERR "PCI: OOM, skipping PCI bus %02x\n", busno);
+ return NULL;
+ }
+ sd->node = -1;
+ bus = pci_scan_bus(busno, &pci_root_ops, sd);
+ if (!bus)
+ kfree(sd);
+
+ return bus;
+}
diff --git a/arch/i386/pci/fixup.c b/arch/i386/pci/fixup.c
index e7306dbf6c4..c82cbf4c722 100644
--- a/arch/i386/pci/fixup.c
+++ b/arch/i386/pci/fixup.c
@@ -25,9 +25,9 @@ static void __devinit pci_fixup_i450nx(struct pci_dev *d)
pci_read_config_byte(d, reg++, &subb);
DBG("i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, suba, subb);
if (busno)
- pci_scan_bus(busno, &pci_root_ops, NULL); /* Bus A */
+ pci_scan_bus_with_sysdata(busno); /* Bus A */
if (suba < subb)
- pci_scan_bus(suba+1, &pci_root_ops, NULL); /* Bus B */
+ pci_scan_bus_with_sysdata(suba+1); /* Bus B */
}
pcibios_last_bus = -1;
}
@@ -42,7 +42,7 @@ static void __devinit pci_fixup_i450gx(struct pci_dev *d)
u8 busno;
pci_read_config_byte(d, 0x4a, &busno);
printk(KERN_INFO "PCI: i440KX/GX host bridge %s: secondary bus %02x\n", pci_name(d), busno);
- pci_scan_bus(busno, &pci_root_ops, NULL);
+ pci_scan_bus_with_sysdata(busno);
pcibios_last_bus = -1;
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82454GX, pci_fixup_i450gx);
diff --git a/arch/i386/pci/irq.c b/arch/i386/pci/irq.c
index f2cb942f828..665db063a40 100644
--- a/arch/i386/pci/irq.c
+++ b/arch/i386/pci/irq.c
@@ -138,8 +138,9 @@ static void __init pirq_peer_trick(void)
for(i = 1; i < 256; i++) {
if (!busmap[i] || pci_find_bus(0, i))
continue;
- if (pci_scan_bus(i, &pci_root_ops, NULL))
- printk(KERN_INFO "PCI: Discovered primary peer bus %02x [IRQ]\n", i);
+ if (pci_scan_bus_with_sysdata(i))
+ printk(KERN_INFO "PCI: Discovered primary peer "
+ "bus %02x [IRQ]\n", i);
}
pcibios_last_bus = -1;
}
diff --git a/arch/i386/pci/legacy.c b/arch/i386/pci/legacy.c
index 149a9588c25..5565d7016b7 100644
--- a/arch/i386/pci/legacy.c
+++ b/arch/i386/pci/legacy.c
@@ -26,7 +26,7 @@ static void __devinit pcibios_fixup_peer_bridges(void)
l != 0x0000 && l != 0xffff) {
DBG("Found device at %02x:%02x [%04x]\n", n, devfn, l);
printk(KERN_INFO "PCI: Discovered peer bus %02x\n", n);
- pci_scan_bus(n, &pci_root_ops, NULL);
+ pci_scan_bus_with_sysdata(n);
break;
}
}
diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c
index bb1afd9e589..1bf5816d34c 100644
--- a/arch/i386/pci/mmconfig.c
+++ b/arch/i386/pci/mmconfig.c
@@ -82,16 +82,15 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
switch (len) {
case 1:
- *value = readb(mmcfg_virt_addr + reg);
+ *value = mmio_config_readb(mmcfg_virt_addr + reg);
break;
case 2:
- *value = readw(mmcfg_virt_addr + reg);
+ *value = mmio_config_readw(mmcfg_virt_addr + reg);
break;
case 4:
- *value = readl(mmcfg_virt_addr + reg);
+ *value = mmio_config_readl(mmcfg_virt_addr + reg);
break;
}
-
spin_unlock_irqrestore(&pci_config_lock, flags);
return 0;
@@ -116,16 +115,15 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
switch (len) {
case 1:
- writeb(value, mmcfg_virt_addr + reg);
+ mmio_config_writeb(mmcfg_virt_addr + reg, value);
break;
case 2:
- writew(value, mmcfg_virt_addr + reg);
+ mmio_config_writew(mmcfg_virt_addr + reg, value);
break;
case 4:
- writel(value, mmcfg_virt_addr + reg);
+ mmio_config_writel(mmcfg_virt_addr + reg, value);
break;
}
-
spin_unlock_irqrestore(&pci_config_lock, flags);
return 0;
diff --git a/arch/i386/pci/numa.c b/arch/i386/pci/numa.c
index adbe17a38f6..f5f165f69e0 100644
--- a/arch/i386/pci/numa.c
+++ b/arch/i386/pci/numa.c
@@ -96,10 +96,14 @@ static void __devinit pci_fixup_i450nx(struct pci_dev *d)
pci_read_config_byte(d, reg++, &suba);
pci_read_config_byte(d, reg++, &subb);
DBG("i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, suba, subb);
- if (busno)
- pci_scan_bus(QUADLOCAL2BUS(quad,busno), &pci_root_ops, NULL); /* Bus A */
- if (suba < subb)
- pci_scan_bus(QUADLOCAL2BUS(quad,suba+1), &pci_root_ops, NULL); /* Bus B */
+ if (busno) {
+ /* Bus A */
+ pci_scan_bus_with_sysdata(QUADLOCAL2BUS(quad, busno));
+ }
+ if (suba < subb) {
+ /* Bus B */
+ pci_scan_bus_with_sysdata(QUADLOCAL2BUS(quad, suba+1));
+ }
}
pcibios_last_bus = -1;
}
@@ -123,8 +127,7 @@ static int __init pci_numa_init(void)
continue;
printk("Scanning PCI bus %d for quad %d\n",
QUADLOCAL2BUS(quad,0), quad);
- pci_scan_bus(QUADLOCAL2BUS(quad,0),
- &pci_root_ops, NULL);
+ pci_scan_bus_with_sysdata(QUADLOCAL2BUS(quad, 0));
}
return 0;
}
diff --git a/arch/i386/pci/pci.h b/arch/i386/pci/pci.h
index e58bae2076a..8c66f275756 100644
--- a/arch/i386/pci/pci.h
+++ b/arch/i386/pci/pci.h
@@ -104,3 +104,46 @@ extern DECLARE_BITMAP(pci_mmcfg_fallback_slots, 32*PCI_MMCFG_MAX_CHECK_BUS);
extern int __init pci_mmcfg_arch_reachable(unsigned int seg, unsigned int bus,
unsigned int devfn);
extern int __init pci_mmcfg_arch_init(void);
+
+/*
+ * AMD Fam10h CPUs are buggy, and cannot access MMIO config space
+ * on their northbrige except through the * %eax register. As such, you MUST
+ * NOT use normal IOMEM accesses, you need to only use the magic mmio-config
+ * accessor functions.
+ * In fact just use pci_config_*, nothing else please.
+ */
+static inline unsigned char mmio_config_readb(void __iomem *pos)
+{
+ u8 val;
+ asm volatile("movb (%1),%%al" : "=a" (val) : "r" (pos));
+ return val;
+}
+
+static inline unsigned short mmio_config_readw(void __iomem *pos)
+{
+ u16 val;
+ asm volatile("movw (%1),%%ax" : "=a" (val) : "r" (pos));
+ return val;
+}
+
+static inline unsigned int mmio_config_readl(void __iomem *pos)
+{
+ u32 val;
+ asm volatile("movl (%1),%%eax" : "=a" (val) : "r" (pos));
+ return val;
+}
+
+static inline void mmio_config_writeb(void __iomem *pos, u8 val)
+{
+ asm volatile("movb %%al,(%1)" :: "a" (val), "r" (pos) : "memory");
+}
+
+static inline void mmio_config_writew(void __iomem *pos, u16 val)
+{
+ asm volatile("movw %%ax,(%1)" :: "a" (val), "r" (pos) : "memory");
+}
+
+static inline void mmio_config_writel(void __iomem *pos, u32 val)
+{
+ asm volatile("movl %%eax,(%1)" :: "a" (val), "r" (pos) : "memory");
+}
diff --git a/arch/i386/pci/visws.c b/arch/i386/pci/visws.c
index f1b486d4190..8ecb1c72259 100644
--- a/arch/i386/pci/visws.c
+++ b/arch/i386/pci/visws.c
@@ -101,8 +101,8 @@ static int __init pcibios_init(void)
"bridge B (PIIX4) bus: %u\n", pci_bus1, pci_bus0);
raw_pci_ops = &pci_direct_conf1;
- pci_scan_bus(pci_bus0, &pci_root_ops, NULL);
- pci_scan_bus(pci_bus1, &pci_root_ops, NULL);
+ pci_scan_bus_with_sysdata(pci_bus0);
+ pci_scan_bus_with_sysdata(pci_bus1);
pci_fixup_irqs(visws_swizzle, visws_map_irq);
pcibios_resource_survey();
return 0;
diff --git a/arch/i386/xen/enlighten.c b/arch/i386/xen/enlighten.c
index 9a8c1181c00..f0c37511d8d 100644
--- a/arch/i386/xen/enlighten.c
+++ b/arch/i386/xen/enlighten.c
@@ -842,7 +842,8 @@ void __init xen_setup_vcpu_info_placement(void)
}
}
-static unsigned xen_patch(u8 type, u16 clobbers, void *insns, unsigned len)
+static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
+ unsigned long addr, unsigned len)
{
char *start, *end, *reloc;
unsigned ret;
@@ -869,7 +870,7 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insns, unsigned len)
if (start == NULL || (end-start) > len)
goto default_patch;
- ret = paravirt_patch_insns(insns, len, start, end);
+ ret = paravirt_patch_insns(insnbuf, len, start, end);
/* Note: because reloc is assigned from something that
appears to be an array, gcc assumes it's non-null,
@@ -877,8 +878,8 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insns, unsigned len)
end. */
if (reloc > start && reloc < end) {
int reloc_off = reloc - start;
- long *relocp = (long *)(insns + reloc_off);
- long delta = start - (char *)insns;
+ long *relocp = (long *)(insnbuf + reloc_off);
+ long delta = start - (char *)addr;
*relocp += delta;
}
@@ -886,7 +887,8 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insns, unsigned len)
default_patch:
default:
- ret = paravirt_patch_default(type, clobbers, insns, len);
+ ret = paravirt_patch_default(type, clobbers, insnbuf,
+ addr, len);
break;
}
diff --git a/arch/i386/xen/xen-head.S b/arch/i386/xen/xen-head.S
index bc71f3bc401..f8d6937db2e 100644
--- a/arch/i386/xen/xen-head.S
+++ b/arch/i386/xen/xen-head.S
@@ -7,20 +7,20 @@
#include <asm/boot.h>
#include <xen/interface/elfnote.h>
- .section .init.text
+.pushsection .init.text
ENTRY(startup_xen)
movl %esi,xen_start_info
cld
movl $(init_thread_union+THREAD_SIZE),%esp
jmp xen_start_kernel
+.popsection
-.pushsection ".bss.page_aligned"
+.pushsection .bss.page_aligned
.align PAGE_SIZE_asm
ENTRY(hypercall_page)
.skip 0x1000
.popsection
- .section .text
ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux")
ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION, .asciz "2.6")
ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION, .asciz "xen-3.0")
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-22 09:02:47 +0000