summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile3
-rw-r--r--arch/x86/kernel/acpi/boot.c5
-rw-r--r--arch/x86/kernel/acpi/sleep.c2
-rw-r--r--arch/x86/kernel/amd_gart_64.c5
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c1
-rw-r--r--arch/x86/kernel/cpu/amd.c64
-rw-r--r--arch/x86/kernel/cpu/common.c17
-rw-r--r--arch/x86/kernel/cpu/intel.c3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/p5.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/winchip.c2
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c2
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_ibs.c2
-rw-r--r--arch/x86/kernel/dumpstack.c2
-rw-r--r--arch/x86/kernel/e820.c16
-rw-r--r--arch/x86/kernel/entry_32.S45
-rw-r--r--arch/x86/kernel/entry_64.S34
-rw-r--r--arch/x86/kernel/ftrace.c4
-rw-r--r--arch/x86/kernel/head32.c20
-rw-r--r--arch/x86/kernel/head64.c144
-rw-r--r--arch/x86/kernel/head_32.S11
-rw-r--r--arch/x86/kernel/head_64.S212
-rw-r--r--arch/x86/kernel/i386_ksyms_32.c1
-rw-r--r--arch/x86/kernel/ioport.c3
-rw-r--r--arch/x86/kernel/kvm.c11
-rw-r--r--arch/x86/kernel/kvmclock.c15
-rw-r--r--arch/x86/kernel/machine_kexec_64.c171
-rw-r--r--arch/x86/kernel/microcode_core.c7
-rw-r--r--arch/x86/kernel/microcode_core_early.c76
-rw-r--r--arch/x86/kernel/microcode_intel.c198
-rw-r--r--arch/x86/kernel/microcode_intel_early.c796
-rw-r--r--arch/x86/kernel/microcode_intel_lib.c174
-rw-r--r--arch/x86/kernel/process_64.c2
-rw-r--r--arch/x86/kernel/setup.c273
-rw-r--r--arch/x86/kernel/signal.c184
-rw-r--r--arch/x86/kernel/traps.c9
-rw-r--r--arch/x86/kernel/vm86_32.c8
-rw-r--r--arch/x86/kernel/x8664_ksyms_64.c3
-rw-r--r--arch/x86/kernel/x86_init.c4
39 files changed, 1729 insertions, 804 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index ac3b3d002833..7bd3bd310106 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -87,6 +87,9 @@ obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o
obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o
+obj-$(CONFIG_MICROCODE_EARLY) += microcode_core_early.o
+obj-$(CONFIG_MICROCODE_INTEL_EARLY) += microcode_intel_early.o
+obj-$(CONFIG_MICROCODE_INTEL_LIB) += microcode_intel_lib.o
microcode-y := microcode_core.o
microcode-$(CONFIG_MICROCODE_INTEL) += microcode_intel.o
microcode-$(CONFIG_MICROCODE_AMD) += microcode_amd.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index bacf4b0d91f4..230c8ea878e5 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -51,7 +51,6 @@ EXPORT_SYMBOL(acpi_disabled);
#ifdef CONFIG_X86_64
# include <asm/proto.h>
-# include <asm/numa_64.h>
#endif /* X86 */
#define BAD_MADT_ENTRY(entry, end) ( \
@@ -697,6 +696,10 @@ EXPORT_SYMBOL(acpi_map_lsapic);
int acpi_unmap_lsapic(int cpu)
{
+#ifdef CONFIG_ACPI_NUMA
+ set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE);
+#endif
+
per_cpu(x86_cpu_to_apicid, cpu) = -1;
set_cpu_present(cpu, false);
num_processors--;
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index d5e0d717005a..0532f5d6e4ef 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -69,7 +69,7 @@ int acpi_suspend_lowlevel(void)
#ifndef CONFIG_64BIT
header->pmode_entry = (u32)&wakeup_pmode_return;
- header->pmode_cr3 = (u32)__pa(&initial_page_table);
+ header->pmode_cr3 = (u32)__pa_symbol(initial_page_table);
saved_magic = 0x12345678;
#else /* CONFIG_64BIT */
#ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index e66311200cbd..b574b295a2f9 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -768,10 +768,9 @@ int __init gart_iommu_init(void)
aper_base = info.aper_base;
end_pfn = (aper_base>>PAGE_SHIFT) + (aper_size>>PAGE_SHIFT);
- if (end_pfn > max_low_pfn_mapped) {
- start_pfn = (aper_base>>PAGE_SHIFT);
+ start_pfn = PFN_DOWN(aper_base);
+ if (!pfn_range_is_mapped(start_pfn, end_pfn))
init_memory_mapping(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
- }
pr_info("PCI-DMA: using GART IOMMU.\n");
iommu_size = check_iommu_size(info.aper_base, aper_size);
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 9c2aa89a11cb..9a9110918ca7 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -28,6 +28,7 @@
#include <asm/apic.h>
#include <asm/ipi.h>
#include <asm/apic_flat_64.h>
+#include <asm/pgtable.h>
static int numachip_system __read_mostly;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 782c456eaa01..fa96eb0d02fb 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -12,7 +12,6 @@
#include <asm/pci-direct.h>
#ifdef CONFIG_X86_64
-# include <asm/numa_64.h>
# include <asm/mmconfig.h>
# include <asm/cacheflush.h>
#endif
@@ -220,8 +219,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
*/
WARN_ONCE(1, "WARNING: This combination of AMD"
" processors is not suitable for SMP.\n");
- if (!test_taint(TAINT_UNSAFE_SMP))
- add_taint(TAINT_UNSAFE_SMP);
+ add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE);
valid_k7:
;
@@ -518,10 +516,9 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
static void __cpuinit init_amd(struct cpuinfo_x86 *c)
{
u32 dummy;
-
-#ifdef CONFIG_SMP
unsigned long long value;
+#ifdef CONFIG_SMP
/*
* Disable TLB flush filter by setting HWCR.FFDIS on K8
* bit 6 of msr C001_0015
@@ -559,12 +556,10 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
* (AMD Erratum #110, docId: 25759).
*/
if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
- u64 val;
-
clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
- if (!rdmsrl_amd_safe(0xc001100d, &val)) {
- val &= ~(1ULL << 32);
- wrmsrl_amd_safe(0xc001100d, val);
+ if (!rdmsrl_amd_safe(0xc001100d, &value)) {
+ value &= ~(1ULL << 32);
+ wrmsrl_amd_safe(0xc001100d, value);
}
}
@@ -617,13 +612,12 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
if ((c->x86 == 0x15) &&
(c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
!cpu_has(c, X86_FEATURE_TOPOEXT)) {
- u64 val;
- if (!rdmsrl_safe(0xc0011005, &val)) {
- val |= 1ULL << 54;
- wrmsrl_safe(0xc0011005, val);
- rdmsrl(0xc0011005, val);
- if (val & (1ULL << 54)) {
+ if (!rdmsrl_safe(0xc0011005, &value)) {
+ value |= 1ULL << 54;
+ wrmsrl_safe(0xc0011005, value);
+ rdmsrl(0xc0011005, value);
+ if (value & (1ULL << 54)) {
set_cpu_cap(c, X86_FEATURE_TOPOEXT);
printk(KERN_INFO FW_INFO "CPU: Re-enabling "
"disabled Topology Extensions Support\n");
@@ -637,11 +631,10 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
*/
if ((c->x86 == 0x15) &&
(c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
- u64 val;
- if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
- val |= 0x1E;
- wrmsrl_safe(0xc0011021, val);
+ if (!rdmsrl_safe(0xc0011021, &value) && !(value & 0x1E)) {
+ value |= 0x1E;
+ wrmsrl_safe(0xc0011021, value);
}
}
@@ -685,12 +678,10 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
* benefit in doing so.
*/
if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+ unsigned long pfn = tseg >> PAGE_SHIFT;
+
printk(KERN_DEBUG "tseg: %010llx\n", tseg);
- if ((tseg>>PMD_SHIFT) <
- (max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
- ((tseg>>PMD_SHIFT) <
- (max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) &&
- (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT))))
+ if (pfn_range_is_mapped(pfn, pfn + 1))
set_memory_4k((unsigned long)__va(tseg), 1);
}
}
@@ -703,13 +694,11 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
if (c->x86 > 0x11)
set_cpu_cap(c, X86_FEATURE_ARAT);
- /*
- * Disable GART TLB Walk Errors on Fam10h. We do this here
- * because this is always needed when GART is enabled, even in a
- * kernel which has no MCE support built in.
- */
if (c->x86 == 0x10) {
/*
+ * Disable GART TLB Walk Errors on Fam10h. We do this here
+ * because this is always needed when GART is enabled, even in a
+ * kernel which has no MCE support built in.
* BIOS should disable GartTlbWlk Errors themself. If
* it doesn't do it here as suggested by the BKDG.
*
@@ -723,6 +712,21 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
mask |= (1 << 10);
wrmsrl_safe(MSR_AMD64_MCx_MASK(4), mask);
}
+
+ /*
+ * On family 10h BIOS may not have properly enabled WC+ support,
+ * causing it to be converted to CD memtype. This may result in
+ * performance degradation for certain nested-paging guests.
+ * Prevent this conversion by clearing bit 24 in
+ * MSR_AMD64_BU_CFG2.
+ *
+ * NOTE: we want to use the _safe accessors so as not to #GP kvm
+ * guests on older kvm hosts.
+ */
+
+ rdmsrl_safe(MSR_AMD64_BU_CFG2, &value);
+ value &= ~(1ULL << 24);
+ wrmsrl_safe(MSR_AMD64_BU_CFG2, value);
}
rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9c3ab43a6954..d814772c5bed 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -37,6 +37,8 @@
#include <asm/mce.h>
#include <asm/msr.h>
#include <asm/pat.h>
+#include <asm/microcode.h>
+#include <asm/microcode_intel.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/uv/uv.h>
@@ -213,7 +215,7 @@ static inline int flag_is_changeable_p(u32 flag)
}
/* Probe for the CPUID instruction */
-static int __cpuinit have_cpuid_p(void)
+int __cpuinit have_cpuid_p(void)
{
return flag_is_changeable_p(X86_EFLAGS_ID);
}
@@ -249,11 +251,6 @@ static inline int flag_is_changeable_p(u32 flag)
{
return 1;
}
-/* Probe for the CPUID instruction */
-static inline int have_cpuid_p(void)
-{
- return 1;
-}
static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
{
}
@@ -1223,6 +1220,12 @@ void __cpuinit cpu_init(void)
int cpu;
int i;
+ /*
+ * Load microcode on this cpu if a valid microcode is available.
+ * This is early microcode loading procedure.
+ */
+ load_ucode_ap();
+
cpu = stack_smp_processor_id();
t = &per_cpu(init_tss, cpu);
oist = &per_cpu(orig_ist, cpu);
@@ -1314,6 +1317,8 @@ void __cpuinit cpu_init(void)
struct tss_struct *t = &per_cpu(init_tss, cpu);
struct thread_struct *thread = &curr->thread;
+ show_ucode_info_early();
+
if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) {
printk(KERN_WARNING "CPU#%d already initialized!\n", cpu);
for (;;)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fcaabd0432c5..1905ce98bee0 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -17,7 +17,6 @@
#ifdef CONFIG_X86_64
#include <linux/topology.h>
-#include <asm/numa_64.h>
#endif
#include "cpu.h"
@@ -168,7 +167,7 @@ int __cpuinit ppro_with_ram_bug(void)
#ifdef CONFIG_X86_F00F_BUG
static void __cpuinit trap_init_f00f_bug(void)
{
- __set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO);
+ __set_fixmap(FIX_F00F_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO);
/*
* Update the IDT descriptor and reload the IDT so that
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index fc7608a89d93..7bc126346ace 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1082,7 +1082,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
/*
* Set taint even when machine check was not enabled.
*/
- add_taint(TAINT_MACHINE_CHECK);
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
severity = mce_severity(&m, cfg->tolerant, NULL);
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c
index 2d5454cd2c4f..1c044b1ccc59 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mcheck/p5.c
@@ -33,7 +33,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
smp_processor_id());
}
- add_taint(TAINT_MACHINE_CHECK);
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
}
/* Set up machine check reporting for processors with Intel style MCE: */
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c
index 2d7998fb628c..e9a701aecaa1 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mcheck/winchip.c
@@ -15,7 +15,7 @@
static void winchip_machine_check(struct pt_regs *regs, long error_code)
{
printk(KERN_EMERG "CPU0: Machine Check Exception.\n");
- add_taint(TAINT_MACHINE_CHECK);
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
}
/* Set up machine check reporting on the Winchip C6 series */
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index e9fe907cd249..fa72a39e5d46 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -542,7 +542,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
if (tmp != mask_lo) {
printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n");
- add_taint(TAINT_FIRMWARE_WORKAROUND);
+ add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
mask_lo = tmp;
}
}
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index 6336bcbd0618..5f0581e713c2 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -528,7 +528,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
if (!test_bit(IBS_STARTED, pcpu->state)) {
/*
* Catch spurious interrupts after stopping IBS: After
- * disabling IBS there could be still incomming NMIs
+ * disabling IBS there could be still incoming NMIs
* with samples that even have the valid bit cleared.
* Mark all this NMIs as handled.
*/
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index ae42418bc50f..c8797d55b245 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -232,7 +232,7 @@ void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
bust_spinlocks(0);
die_owner = -1;
- add_taint(TAINT_DIE);
+ add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
die_nest_count--;
if (!die_nest_count)
/* Nest count reaches zero, release the lock. */
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index df06ade26bef..d32abeabbda5 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -835,7 +835,7 @@ static int __init parse_memopt(char *p)
}
early_param("mem", parse_memopt);
-static int __init parse_memmap_opt(char *p)
+static int __init parse_memmap_one(char *p)
{
char *oldp;
u64 start_at, mem_size;
@@ -877,6 +877,20 @@ static int __init parse_memmap_opt(char *p)
return *p == '\0' ? 0 : -EINVAL;
}
+static int __init parse_memmap_opt(char *str)
+{
+ while (str) {
+ char *k = strchr(str, ',');
+
+ if (k)
+ *k++ = 0;
+
+ parse_memmap_one(str);
+ str = k;
+ }
+
+ return 0;
+}
early_param("memmap", parse_memmap_opt);
void __init finish_e820_parsing(void)
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 8831176aa5ef..8f3e2dec1df3 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -699,51 +699,6 @@ END(syscall_badsys)
*/
.popsection
-/*
- * System calls that need a pt_regs pointer.
- */
-#define PTREGSCALL0(name) \
-ENTRY(ptregs_##name) ; \
- leal 4(%esp),%eax; \
- jmp sys_##name; \
-ENDPROC(ptregs_##name)
-
-#define PTREGSCALL1(name) \
-ENTRY(ptregs_##name) ; \
- leal 4(%esp),%edx; \
- movl (PT_EBX+4)(%esp),%eax; \
- jmp sys_##name; \
-ENDPROC(ptregs_##name)
-
-#define PTREGSCALL2(name) \
-ENTRY(ptregs_##name) ; \
- leal 4(%esp),%ecx; \
- movl (PT_ECX+4)(%esp),%edx; \
- movl (PT_EBX+4)(%esp),%eax; \
- jmp sys_##name; \
-ENDPROC(ptregs_##name)
-
-#define PTREGSCALL3(name) \
-ENTRY(ptregs_##name) ; \
- CFI_STARTPROC; \
- leal 4(%esp),%eax; \
- pushl_cfi %eax; \
- movl PT_EDX(%eax),%ecx; \
- movl PT_ECX(%eax),%edx; \
- movl PT_EBX(%eax),%eax; \
- call sys_##name; \
- addl $4,%esp; \
- CFI_ADJUST_CFA_OFFSET -4; \
- ret; \
- CFI_ENDPROC; \
-ENDPROC(ptregs_##name)
-
-PTREGSCALL1(iopl)
-PTREGSCALL0(sigreturn)
-PTREGSCALL0(rt_sigreturn)
-PTREGSCALL2(vm86)
-PTREGSCALL1(vm86old)
-
.macro FIXUP_ESPFIX_STACK
/*
* Switch back for ESPFIX stack to the normal zerobased stack
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 048f2240f8e6..c1d01e6ca790 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -828,23 +828,6 @@ int_restore_rest:
CFI_ENDPROC
END(system_call)
-/*
- * Certain special system calls that need to save a complete full stack frame.
- */
- .macro PTREGSCALL label,func,arg
-ENTRY(\label)
- PARTIAL_FRAME 1 8 /* offset 8: return address */
- subq $REST_SKIP, %rsp
- CFI_ADJUST_CFA_OFFSET REST_SKIP
- call save_rest
- DEFAULT_FRAME 0 8 /* offset 8: return address */
- leaq 8(%rsp), \arg /* pt_regs pointer */
- call \func
- jmp ptregscall_common
- CFI_ENDPROC
-END(\label)
- .endm
-
.macro FORK_LIKE func
ENTRY(stub_\func)
CFI_STARTPROC
@@ -861,10 +844,22 @@ ENTRY(stub_\func)
END(stub_\func)
.endm
+ .macro FIXED_FRAME label,func
+ENTRY(\label)
+ CFI_STARTPROC
+ PARTIAL_FRAME 0 8 /* offset 8: return address */
+ FIXUP_TOP_OF_STACK %r11, 8-ARGOFFSET
+ call \func
+ RESTORE_TOP_OF_STACK %r11, 8-ARGOFFSET
+ ret
+ CFI_ENDPROC
+END(\label)
+ .endm
+
FORK_LIKE clone
FORK_LIKE fork
FORK_LIKE vfork
- PTREGSCALL stub_iopl, sys_iopl, %rsi
+ FIXED_FRAME stub_iopl, sys_iopl
ENTRY(ptregscall_common)
DEFAULT_FRAME 1 8 /* offset 8: return address */
@@ -886,7 +881,6 @@ ENTRY(stub_execve)
SAVE_REST
FIXUP_TOP_OF_STACK %r11
call sys_execve
- RESTORE_TOP_OF_STACK %r11
movq %rax,RAX(%rsp)
RESTORE_REST
jmp int_ret_from_sys_call
@@ -902,7 +896,6 @@ ENTRY(stub_rt_sigreturn)
addq $8, %rsp
PARTIAL_FRAME 0
SAVE_REST
- movq %rsp,%rdi
FIXUP_TOP_OF_STACK %r11
call sys_rt_sigreturn
movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
@@ -917,7 +910,6 @@ ENTRY(stub_x32_rt_sigreturn)
addq $8, %rsp
PARTIAL_FRAME 0
SAVE_REST
- movq %rsp,%rdi
FIXUP_TOP_OF_STACK %r11
call sys32_x32_rt_sigreturn
movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 1d414029f1d8..42a392a9fd02 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -89,7 +89,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code)
* kernel identity mapping to modify code.
*/
if (within(ip, (unsigned long)_text, (unsigned long)_etext))
- ip = (unsigned long)__va(__pa(ip));
+ ip = (unsigned long)__va(__pa_symbol(ip));
return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE);
}
@@ -279,7 +279,7 @@ static int ftrace_write(unsigned long ip, const char *val, int size)
* kernel identity mapping to modify code.
*/
if (within(ip, (unsigned long)_text, (unsigned long)_etext))
- ip = (unsigned long)__va(__pa(ip));
+ ip = (unsigned long)__va(__pa_symbol(ip));
return probe_kernel_write((void *)ip, val, size);
}
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 6773c918b8cc..138463a24877 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -33,20 +33,6 @@ void __init i386_start_kernel(void)
{
sanitize_boot_params(&boot_params);
- memblock_reserve(__pa_symbol(&_text),
- __pa_symbol(&__bss_stop) - __pa_symbol(&_text));
-
-#ifdef CONFIG_BLK_DEV_INITRD
- /* Reserve INITRD */
- if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
- /* Assume only end is not page aligned */
- u64 ramdisk_image = boot_params.hdr.ramdisk_image;
- u64 ramdisk_size = boot_params.hdr.ramdisk_size;
- u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
- memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
- }
-#endif
-
/* Call the subarch specific early setup function */
switch (boot_params.hdr.hardware_subarch) {
case X86_SUBARCH_MRST:
@@ -60,11 +46,5 @@ void __init i386_start_kernel(void)
break;
}
- /*
- * At this point everything still needed from the boot loader
- * or BIOS or kernel text should be early reserved or marked not
- * RAM in e820. All other memory is free game.
- */
-
start_kernel();
}
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 849fc9e63c2f..c5e403f6d869 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -26,12 +26,83 @@
#include <asm/e820.h>
#include <asm/bios_ebda.h>
#include <asm/bootparam_utils.h>
+#include <asm/microcode.h>
-static void __init zap_identity_mappings(void)
+/*
+ * Manage page tables very early on.
+ */
+extern pgd_t early_level4_pgt[PTRS_PER_PGD];
+extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
+static unsigned int __initdata next_early_pgt = 2;
+
+/* Wipe all early page tables except for the kernel symbol map */
+static void __init reset_early_page_tables(void)
{
- pgd_t *pgd = pgd_offset_k(0UL);
- pgd_clear(pgd);
- __flush_tlb_all();
+ unsigned long i;
+
+ for (i = 0; i < PTRS_PER_PGD-1; i++)
+ early_level4_pgt[i].pgd = 0;
+
+ next_early_pgt = 0;
+
+ write_cr3(__pa(early_level4_pgt));
+}
+
+/* Create a new PMD entry */
+int __init early_make_pgtable(unsigned long address)
+{
+ unsigned long physaddr = address - __PAGE_OFFSET;
+ unsigned long i;
+ pgdval_t pgd, *pgd_p;
+ pudval_t pud, *pud_p;
+ pmdval_t pmd, *pmd_p;
+
+ /* Invalid address or early pgt is done ? */
+ if (physaddr >= MAXMEM || read_cr3() != __pa(early_level4_pgt))
+ return -1;
+
+again:
+ pgd_p = &early_level4_pgt[pgd_index(address)].pgd;
+ pgd = *pgd_p;
+
+ /*
+ * The use of __START_KERNEL_map rather than __PAGE_OFFSET here is
+ * critical -- __PAGE_OFFSET would point us back into the dynamic
+ * range and we might end up looping forever...
+ */
+ if (pgd)
+ pud_p = (pudval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
+ else {
+ if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) {
+ reset_early_page_tables();
+ goto again;
+ }
+
+ pud_p = (pudval_t *)early_dynamic_pgts[next_early_pgt++];
+ for (i = 0; i < PTRS_PER_PUD; i++)
+ pud_p[i] = 0;
+ *pgd_p = (pgdval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
+ }
+ pud_p += pud_index(address);
+ pud = *pud_p;
+
+ if (pud)
+ pmd_p = (pmdval_t *)((pud & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
+ else {
+ if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) {
+ reset_early_page_tables();
+ goto again;
+ }
+
+ pmd_p = (pmdval_t *)early_dynamic_pgts[next_early_pgt++];
+ for (i = 0; i < PTRS_PER_PMD; i++)
+ pmd_p[i] = 0;
+ *pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
+ }
+ pmd = (physaddr & PMD_MASK) + (__PAGE_KERNEL_LARGE & ~_PAGE_GLOBAL);
+ pmd_p[pmd_index(address)] = pmd;
+
+ return 0;
}
/* Don't add a printk in there. printk relies on the PDA which is not initialized
@@ -42,14 +113,25 @@ static void __init clear_bss(void)
(unsigned long) __bss_stop - (unsigned long) __bss_start);
}
+static unsigned long get_cmd_line_ptr(void)
+{
+ unsigned long cmd_line_ptr = boot_params.hdr.cmd_line_ptr;
+
+ cmd_line_ptr |= (u64)boot_params.ext_cmd_line_ptr << 32;
+
+ return cmd_line_ptr;
+}
+
static void __init copy_bootdata(char *real_mode_data)
{
char * command_line;
+ unsigned long cmd_line_ptr;
memcpy(&boot_params, real_mode_data, sizeof boot_params);
sanitize_boot_params(&boot_params);
- if (boot_params.hdr.cmd_line_ptr) {
- command_line = __va(boot_params.hdr.cmd_line_ptr);
+ cmd_line_ptr = get_cmd_line_ptr();
+ if (cmd_line_ptr) {
+ command_line = __va(cmd_line_ptr);
memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
}
}
@@ -72,54 +154,40 @@ void __init x86_64_start_kernel(char * real_mode_data)
(__START_KERNEL & PGDIR_MASK)));
BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
+ /* Kill off the identity-map trampoline */
+ reset_early_page_tables();
+
/* clear bss before set_intr_gate with early_idt_handler */
clear_bss();
- /* Make NULL pointers segfault */
- zap_identity_mappings();
-
- max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
-
- for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) {
-#ifdef CONFIG_EARLY_PRINTK
+ for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
set_intr_gate(i, &early_idt_handlers[i]);
-#else
- set_intr_gate(i, early_idt_handler);
-#endif
- }
load_idt((const struct desc_ptr *)&idt_descr);
+ copy_bootdata(__va(real_mode_data));
+
+ /*
+ * Load microcode early on BSP.
+ */
+ load_ucode_bsp();
+
if (console_loglevel == 10)
early_printk("Kernel alive\n");
+ clear_page(init_level4_pgt);
+ /* set init_level4_pgt kernel high mapping*/
+ init_level4_pgt[511] = early_level4_pgt[511];
+
x86_64_start_reservations(real_mode_data);
}
void __init x86_64_start_reservations(char *real_mode_data)
{
- copy_bootdata(__va(real_mode_data));
-
- memblock_reserve(__pa_symbol(&_text),
- __pa_symbol(&__bss_stop) - __pa_symbol(&_text));
-
-#ifdef CONFIG_BLK_DEV_INITRD
- /* Reserve INITRD */
- if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
- /* Assume only end is not page aligned */
- unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
- unsigned long ramdisk_size = boot_params.hdr.ramdisk_size;
- unsigned long ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
- memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
- }
-#endif
+ /* version is always not zero if it is copied */
+ if (!boot_params.hdr.version)
+ copy_bootdata(__va(real_mode_data));
reserve_ebda_region();
- /*
- * At this point everything still needed from the boot loader
- * or BIOS or kernel text should be early reserved or marked not
- * RAM in e820. All other memory is free game.
- */
-
start_kernel();
}
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 3c3f58a0808f..73afd11799ca 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -144,6 +144,11 @@ ENTRY(startup_32)
movl %eax, pa(olpc_ofw_pgd)
#endif
+#ifdef CONFIG_MICROCODE_EARLY
+ /* Early load ucode on BSP. */
+ call load_ucode_bsp
+#endif
+
/*
* Initialize page tables. This creates a PDE and a set of page
* tables, which are located immediately beyond __brk_base. The variable
@@ -299,6 +304,12 @@ ENTRY(startup_32_smp)
movl %eax,%ss
leal -__PAGE_OFFSET(%ecx),%esp
+#ifdef CONFIG_MICROCODE_EARLY
+ /* Early load ucode on AP. */
+ call load_ucode_ap
+#endif
+
+
default_entry:
#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \
X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 980053c4b9cc..b7de3b25adb5 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -47,14 +47,13 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map)
.code64
.globl startup_64
startup_64:
-
/*
* At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 1,
* and someone has loaded an identity mapped page table
* for us. These identity mapped page tables map all of the
* kernel pages and possibly all of memory.
*
- * %esi holds a physical pointer to real_mode_data.
+ * %rsi holds a physical pointer to real_mode_data.
*
* We come here either directly from a 64bit bootloader, or from
* arch/x86_64/boot/compressed/head.S.
@@ -66,7 +65,8 @@ startup_64:
* tables and then reload them.
*/
- /* Compute the delta between the address I am compiled to run at and the
+ /*
+ * Compute the delta between the address I am compiled to run at and the
* address I am actually running at.
*/
leaq _text(%rip), %rbp
@@ -78,45 +78,62 @@ startup_64:
testl %eax, %eax
jnz bad_address
- /* Is the address too large? */
- leaq _text(%rip), %rdx
- movq $PGDIR_SIZE, %rax
- cmpq %rax, %rdx
- jae bad_address
-
- /* Fixup the physical addresses in the page table
+ /*
+ * Is the address too large?
*/
- addq %rbp, init_level4_pgt + 0(%rip)
- addq %rbp, init_level4_pgt + (L4_PAGE_OFFSET*8)(%rip)
- addq %rbp, init_level4_pgt + (L4_START_KERNEL*8)(%rip)
+ leaq _text(%rip), %rax
+ shrq $MAX_PHYSMEM_BITS, %rax
+ jnz bad_address
- addq %rbp, level3_ident_pgt + 0(%rip)
+ /*
+ * Fixup the physical addresses in the page table
+ */
+ addq %rbp, early_level4_pgt + (L4_START_KERNEL*8)(%rip)
addq %rbp, level3_kernel_pgt + (510*8)(%rip)
addq %rbp, level3_kernel_pgt + (511*8)(%rip)
addq %rbp, level2_fixmap_pgt + (506*8)(%rip)
- /* Add an Identity mapping if I am above 1G */
+ /*
+ * Set up the identity mapping for the switchover. These
+ * entries should *NOT* have the global bit set! This also
+ * creates a bunch of nonsense entries but that is fine --
+ * it avoids problems around wraparound.
+ */
leaq _text(%rip), %rdi
- andq $PMD_PAGE_MASK, %rdi
+ leaq early_level4_pgt(%rip), %rbx
movq %rdi, %rax
- shrq $PUD_SHIFT, %rax
- andq $(PTRS_PER_PUD - 1), %rax
- jz ident_complete
+ shrq $PGDIR_SHIFT, %rax
- leaq (level2_spare_pgt - __START_KERNEL_map + _KERNPG_TABLE)(%rbp), %rdx
- leaq level3_ident_pgt(%rip), %rbx
- movq %rdx, 0(%rbx, %rax, 8)
+ leaq (4096 + _KERNPG_TABLE)(%rbx), %rdx
+ movq %rdx, 0(%rbx,%rax,8)
+ movq %rdx, 8(%rbx,%rax,8)
+ addq $4096, %rdx
movq %rdi, %rax
- shrq $PMD_SHIFT, %rax
- andq $(PTRS_PER_PMD - 1), %rax
- leaq __PAGE_KERNEL_IDENT_LARGE_EXEC(%rdi), %rdx
- leaq level2_spare_pgt(%rip), %rbx
- movq %rdx, 0(%rbx, %rax, 8)
-ident_complete:
+ shrq $PUD_SHIFT, %rax
+ andl $(PTRS_PER_PUD-1), %eax
+ movq %rdx, (4096+0)(%rbx,%rax,8)
+ movq %rdx, (4096+8)(%rbx,%rax,8)
+
+ addq $8192, %rbx
+ movq %rdi, %rax
+ shrq $PMD_SHIFT, %rdi
+ addq $(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL), %rax
+ leaq (_end - 1)(%rip), %rcx
+ shrq $PMD_SHIFT, %rcx
+ subq %rdi, %rcx
+ incl %ecx
+
+1:
+ andq $(PTRS_PER_PMD - 1), %rdi
+ movq %rax, (%rbx,%rdi,8)
+ incq %rdi
+ addq $PMD_SIZE, %rax
+ decl %ecx
+ jnz 1b
/*
* Fixup the kernel text+data virtual addresses. Note that
@@ -124,7 +141,6 @@ ident_complete:
* cleanup_highmap() fixes this up along with the mappings
* beyond _end.
*/
-
leaq level2_kernel_pgt(%rip), %rdi
leaq 4096(%rdi), %r8
/* See if it is a valid page table entry */
@@ -139,17 +155,14 @@ ident_complete:
/* Fixup phys_base */
addq %rbp, phys_base(%rip)
- /* Due to ENTRY(), sometimes the empty space gets filled with
- * zeros. Better take a jmp than relying on empty space being
- * filled with 0x90 (nop)
- */
- jmp secondary_startup_64
+ movq $(early_level4_pgt - __START_KERNEL_map), %rax
+ jmp 1f
ENTRY(secondary_startup_64)
/*
* At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 1,
* and someone has loaded a mapped page table.
*
- * %esi holds a physical pointer to real_mode_data.
+ * %rsi holds a physical pointer to real_mode_data.
*
* We come here either from startup_64 (using physical addresses)
* or from trampoline.S (using virtual addresses).
@@ -159,12 +172,14 @@ ENTRY(secondary_startup_64)
* after the boot processor executes this code.
*/
+ movq $(init_level4_pgt - __START_KERNEL_map), %rax
+1:
+
/* Enable PAE mode and PGE */
- movl $(X86_CR4_PAE | X86_CR4_PGE), %eax
- movq %rax, %cr4
+ movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx
+ movq %rcx, %cr4
/* Setup early boot stage 4 level pagetables. */
- movq $(init_level4_pgt - __START_KERNEL_map), %rax
addq phys_base(%rip), %rax
movq %rax, %cr3
@@ -196,7 +211,7 @@ ENTRY(secondary_startup_64)
movq %rax, %cr0
/* Setup a boot time stack */
- movq stack_start(%rip),%rsp
+ movq stack_start(%rip), %rsp
/* zero EFLAGS after setting rsp */
pushq $0
@@ -236,15 +251,33 @@ ENTRY(secondary_startup_64)
movl initial_gs+4(%rip),%edx
wrmsr
- /* esi is pointer to real mode structure with interesting info.
+ /* rsi is pointer to real mode structure with interesting info.
pass it to C */
- movl %esi, %edi
+ movq %rsi, %rdi
/* Finally jump to run C code and to be on real kernel address
* Since we are running on identity-mapped space we have to jump
* to the full 64bit address, this is only possible as indirect
* jump. In addition we need to ensure %cs is set so we make this
* a far return.
+ *
+ * Note: do not change to far jump indirect with 64bit offset.
+ *
+ * AMD does not support far jump indirect with 64bit offset.
+ * AMD64 Architecture Programmer's Manual, Volume 3: states only
+ * JMP FAR mem16:16 FF /5 Far jump indirect,
+ * with the target specified by a far pointer in memory.
+ * JMP FAR mem16:32 FF /5 Far jump indirect,
+ * with the target specified by a far pointer in memory.
+ *
+ * Intel64 does support 64bit offset.
+ * Software Developer Manual Vol 2: states:
+ * FF /5 JMP m16:16 Jump far, absolute indirect,
+ * address given in m16:16
+ * FF /5 JMP m16:32 Jump far, absolute indirect,
+ * address given in m16:32.
+ * REX.W + FF /5 JMP m16:64 Jump far, absolute indirect,
+ * address given in m16:64.
*/
movq initial_code(%rip),%rax
pushq $0 # fake return address to stop unwinder
@@ -270,13 +303,13 @@ ENDPROC(start_cpu0)
/* SMP bootup changes these two */
__REFDATA
- .align 8
- ENTRY(initial_code)
+ .balign 8
+ GLOBAL(initial_code)
.quad x86_64_start_kernel
- ENTRY(initial_gs)
+ GLOBAL(initial_gs)
.quad INIT_PER_CPU_VAR(irq_stack_union)
- ENTRY(stack_start)
+ GLOBAL(stack_start)
.quad init_thread_union+THREAD_SIZE-8
.word 0
__FINITDATA
@@ -284,7 +317,7 @@ ENDPROC(start_cpu0)
bad_address:
jmp bad_address
- .section ".init.text","ax"
+ __INIT
.globl early_idt_handlers
early_idt_handlers:
# 104(%rsp) %rflags
@@ -303,6 +336,7 @@ early_idt_handlers:
i = i + 1
.endr
+/* This is global to keep gas from relaxing the jumps */
ENTRY(early_idt_handler)
cld
@@ -321,14 +355,22 @@ ENTRY(early_idt_handler)
pushq %r11 # 0(%rsp)
cmpl $__KERNEL_CS,96(%rsp)
- jne 10f
+ jne 11f
+
+ cmpl $14,72(%rsp) # Page fault?
+ jnz 10f
+ GET_CR2_INTO(%rdi) # can clobber any volatile register if pv
+ call early_make_pgtable
+ andl %eax,%eax
+ jz 20f # All good
+10:
leaq 88(%rsp),%rdi # Pointer to %rip
call early_fixup_exception
andl %eax,%eax
jnz 20f # Found an exception entry
-10:
+11:
#ifdef CONFIG_EARLY_PRINTK
GET_CR2_INTO(%r9) # can clobber any volatile register if pv
movl 80(%rsp),%r8d # error code
@@ -350,7 +392,7 @@ ENTRY(early_idt_handler)
1: hlt
jmp 1b
-20: # Exception table entry found
+20: # Exception table entry found or page table generated
popq %r11
popq %r10
popq %r9
@@ -363,6 +405,9 @@ ENTRY(early_idt_handler)
addq $16,%rsp # drop vector number and error code
decl early_recursion_flag(%rip)
INTERRUPT_RETURN
+ENDPROC(early_idt_handler)
+
+ __INITDATA
.balign 4
early_recursion_flag:
@@ -374,11 +419,10 @@ early_idt_msg:
early_idt_ripmsg:
.asciz "RIP %s\n"
#endif /* CONFIG_EARLY_PRINTK */
- .previous
#define NEXT_PAGE(name) \
.balign PAGE_SIZE; \
-ENTRY(name)
+GLOBAL(name)
/* Automate the creation of 1 to 1 mapping pmd entries */
#define PMDS(START, PERM, COUNT) \
@@ -388,24 +432,37 @@ ENTRY(name)
i = i + 1 ; \
.endr
+ __INITDATA
+NEXT_PAGE(early_level4_pgt)
+ .fill 511,8,0
+ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+
+NEXT_PAGE(early_dynamic_pgts)
+ .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0
+
.data
- /*
- * This default setting generates an ident mapping at address 0x100000
- * and a mapping for the kernel that precisely maps virtual address
- * 0xffffffff80000000 to physical address 0x000000. (always using
- * 2Mbyte large pages provided by PAE mode)
- */
+
+#ifndef CONFIG_XEN
NEXT_PAGE(init_level4_pgt)
- .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
- .org init_level4_pgt + L4_PAGE_OFFSET*8, 0
- .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
- .org init_level4_pgt + L4_START_KERNEL*8, 0
+ .fill 512,8,0
+#else
+NEXT_PAGE(init_level4_pgt)
+ .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+ .org init_level4_pgt + L4_PAGE_OFFSET*8, 0
+ .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+ .org init_level4_pgt + L4_START_KERNEL*8, 0
/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
- .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
NEXT_PAGE(level3_ident_pgt)
.quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
- .fill 511,8,0
+ .fill 511, 8, 0
+NEXT_PAGE(level2_ident_pgt)
+ /* Since I easily can, map the first 1G.
+ * Don't set NX because code runs from these pages.
+ */
+ PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
+#endif
NEXT_PAGE(level3_kernel_pgt)
.fill L3_START_KERNEL,8,0
@@ -413,21 +470,6 @@ NEXT_PAGE(level3_kernel_pgt)
.quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE
.quad level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE
-NEXT_PAGE(level2_fixmap_pgt)
- .fill 506,8,0
- .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE
- /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */
- .fill 5,8,0
-
-NEXT_PAGE(level1_fixmap_pgt)
- .fill 512,8,0
-
-NEXT_PAGE(level2_ident_pgt)
- /* Since I easily can, map the first 1G.
- * Don't set NX because code runs from these pages.
- */
- PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
-
NEXT_PAGE(level2_kernel_pgt)
/*
* 512 MB kernel mapping. We spend a full page on this pagetable
@@ -442,11 +484,16 @@ NEXT_PAGE(level2_kernel_pgt)
PMDS(0, __PAGE_KERNEL_LARGE_EXEC,
KERNEL_IMAGE_SIZE/PMD_SIZE)
-NEXT_PAGE(level2_spare_pgt)
- .fill 512, 8, 0
+NEXT_PAGE(level2_fixmap_pgt)
+ .fill 506,8,0
+ .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE
+ /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */
+ .fill 5,8,0
+
+NEXT_PAGE(level1_fixmap_pgt)
+ .fill 512,8,0
#undef PMDS
-#undef NEXT_PAGE
.data
.align 16
@@ -472,6 +519,5 @@ ENTRY(nmi_idt_table)
.skip IDT_ENTRIES * 16
__PAGE_ALIGNED_BSS
- .align PAGE_SIZE
-ENTRY(empty_zero_page)
+NEXT_PAGE(empty_zero_page)
.skip PAGE_SIZE
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 9c3bd4a2050e..0fa69127209a 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -26,6 +26,7 @@ EXPORT_SYMBOL(csum_partial_copy_generic);
EXPORT_SYMBOL(__get_user_1);
EXPORT_SYMBOL(__get_user_2);
EXPORT_SYMBOL(__get_user_4);
+EXPORT_SYMBOL(__get_user_8);
EXPORT_SYMBOL(__put_user_1);
EXPORT_SYMBOL(__put_user_2);
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 8c968974253d..4ddaf66ea35f 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -93,8 +93,9 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
* on system-call entry - see also fork() and the signal handling
* code.
*/
-long sys_iopl(unsigned int level, struct pt_regs *regs)
+SYSCALL_DEFINE1(iopl, unsigned int, level)
{
+ struct pt_regs *regs = current_pt_regs();
unsigned int old = (regs->flags >> 12) & 3;
struct thread_struct *t = &current->thread;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 2b44ea5f269d..b686a904d7c3 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -297,9 +297,9 @@ static void kvm_register_steal_time(void)
memset(st, 0, sizeof(*st));
- wrmsrl(MSR_KVM_STEAL_TIME, (__pa(st) | KVM_MSR_ENABLED));
- printk(KERN_INFO "kvm-stealtime: cpu %d, msr %lx\n",
- cpu, __pa(st));
+ wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
+ pr_info("kvm-stealtime: cpu %d, msr %llx\n",
+ cpu, (unsigned long long) slow_virt_to_phys(st));
}
static DEFINE_PER_CPU(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED;
@@ -324,7 +324,7 @@ void __cpuinit kvm_guest_cpu_init(void)
return;
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
- u64 pa = __pa(&__get_cpu_var(apf_reason));
+ u64 pa = slow_virt_to_phys(&__get_cpu_var(apf_reason));
#ifdef CONFIG_PREEMPT
pa |= KVM_ASYNC_PF_SEND_ALWAYS;
@@ -340,7 +340,8 @@ void __cpuinit kvm_guest_cpu_init(void)
/* Size alignment is implied but just to make it explicit. */
BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4);
__get_cpu_var(kvm_apic_eoi) = 0;
- pa = __pa(&__get_cpu_var(kvm_apic_eoi)) | KVM_MSR_ENABLED;
+ pa = slow_virt_to_phys(&__get_cpu_var(kvm_apic_eoi))
+ | KVM_MSR_ENABLED;
wrmsrl(MSR_KVM_PV_EOI_EN, pa);
}
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 220a360010f8..0732f0089a3d 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -162,8 +162,8 @@ int kvm_register_clock(char *txt)
int low, high, ret;
struct pvclock_vcpu_time_info *src = &hv_clock[cpu].pvti;
- low = (int)__pa(src) | 1;
- high = ((u64)__pa(src) >> 32);
+ low = (int)slow_virt_to_phys(src) | 1;
+ high = ((u64)slow_virt_to_phys(src) >> 32);
ret = native_write_msr_safe(msr_kvm_system_time, low, high);
printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
cpu, high, low, txt);
@@ -218,6 +218,9 @@ static void kvm_shutdown(void)
void __init kvmclock_init(void)
{
unsigned long mem;
+ int size;
+
+ size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
if (!kvm_para_available())
return;
@@ -231,16 +234,14 @@ void __init kvmclock_init(void)
printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
msr_kvm_system_time, msr_kvm_wall_clock);
- mem = memblock_alloc(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS,
- PAGE_SIZE);
+ mem = memblock_alloc(size, PAGE_SIZE);
if (!mem)
return;
hv_clock = __va(mem);
if (kvm_register_clock("boot clock")) {
hv_clock = NULL;
- memblock_free(mem,
- sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
+ memblock_free(mem, size);
return;
}
pv_time_ops.sched_clock = kvm_clock_read;
@@ -275,7 +276,7 @@ int __init kvm_setup_vsyscall_timeinfo(void)
struct pvclock_vcpu_time_info *vcpu_time;
unsigned int size;
- size = sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS;
+ size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
preempt_disable();
cpu = smp_processor_id();
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index b3ea9db39db6..4eabc160696f 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -16,125 +16,12 @@
#include <linux/io.h>
#include <linux/suspend.h>
+#include <asm/init.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/debugreg.h>
-static int init_one_level2_page(struct kimage *image, pgd_t *pgd,
- unsigned long addr)
-{
- pud_t *pud;
- pmd_t *pmd;
- struct page *page;
- int result = -ENOMEM;
-
- addr &= PMD_MASK;
- pgd += pgd_index(addr);
- if (!pgd_present(*pgd)) {
- page = kimage_alloc_control_pages(image, 0);
- if (!page)
- goto out;
- pud = (pud_t *)page_address(page);
- clear_page(pud);
- set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
- }
- pud = pud_offset(pgd, addr);
- if (!pud_present(*pud)) {
- page = kimage_alloc_control_pages(image, 0);
- if (!page)
- goto out;
- pmd = (pmd_t *)page_address(page);
- clear_page(pmd);
- set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
- }
- pmd = pmd_offset(pud, addr);
- if (!pmd_present(*pmd))
- set_pmd(pmd, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
- result = 0;
-out:
- return result;
-}
-
-static void init_level2_page(pmd_t *level2p, unsigned long addr)
-{
- unsigned long end_addr;
-
- addr &= PAGE_MASK;
- end_addr = addr + PUD_SIZE;
- while (addr < end_addr) {
- set_pmd(level2p++, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
- addr += PMD_SIZE;
- }
-}
-
-static int init_level3_page(struct kimage *image, pud_t *level3p,
- unsigned long addr, unsigned long last_addr)
-{
- unsigned long end_addr;
- int result;
-
- result = 0;
- addr &= PAGE_MASK;
- end_addr = addr + PGDIR_SIZE;
- while ((addr < last_addr) && (addr < end_addr)) {
- struct page *page;
- pmd_t *level2p;
-
- page = kimage_alloc_control_pages(image, 0);
- if (!page) {
- result = -ENOMEM;
- goto out;
- }
- level2p = (pmd_t *)page_address(page);
- init_level2_page(level2p, addr);
- set_pud(level3p++, __pud(__pa(level2p) | _KERNPG_TABLE));
- addr += PUD_SIZE;
- }
- /* clear the unused entries */
- while (addr < end_addr) {
- pud_clear(level3p++);
- addr += PUD_SIZE;
- }
-out:
- return result;
-}
-
-
-static int init_level4_page(struct kimage *image, pgd_t *level4p,
- unsigned long addr, unsigned long last_addr)
-{
- unsigned long end_addr;
- int result;
-
- result = 0;
- addr &= PAGE_MASK;
- end_addr = addr + (PTRS_PER_PGD * PGDIR_SIZE);
- while ((addr < last_addr) && (addr < end_addr)) {
- struct page *page;
- pud_t *level3p;
-
- page = kimage_alloc_control_pages(image, 0);
- if (!page) {
- result = -ENOMEM;
- goto out;
- }
- level3p = (pud_t *)page_address(page);
- result = init_level3_page(image, level3p, addr, last_addr);
- if (result)
- goto out;
- set_pgd(level4p++, __pgd(__pa(level3p) | _KERNPG_TABLE));
- addr += PGDIR_SIZE;
- }
- /* clear the unused entries */
- while (addr < end_addr) {
- pgd_clear(level4p++);
- addr += PGDIR_SIZE;
- }
-out:
- return result;
-}
-
static void free_transition_pgtable(struct kimage *image)
{
free_page((unsigned long)image->arch.pud);
@@ -184,22 +71,62 @@ err:
return result;
}
+static void *alloc_pgt_page(void *data)
+{
+ struct kimage *image = (struct kimage *)data;
+ struct page *page;
+ void *p = NULL;
+
+ page = kimage_alloc_control_pages(image, 0);
+ if (page) {
+ p = page_address(page);
+ clear_page(p);
+ }
+
+ return p;
+}
static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
{
+ struct x86_mapping_info info = {
+ .alloc_pgt_page = alloc_pgt_page,
+ .context = image,
+ .pmd_flag = __PAGE_KERNEL_LARGE_EXEC,
+ };
+ unsigned long mstart, mend;
pgd_t *level4p;
int result;
+ int i;
+
level4p = (pgd_t *)__va(start_pgtable);
- result = init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT);
- if (result)
- return result;
+ clear_page(level4p);
+ for (i = 0; i < nr_pfn_mapped; i++) {
+ mstart = pfn_mapped[i].start << PAGE_SHIFT;
+ mend = pfn_mapped[i].end << PAGE_SHIFT;
+
+ result = kernel_ident_mapping_init(&info,
+ level4p, mstart, mend);
+ if (result)
+ return result;
+ }
+
/*
- * image->start may be outside 0 ~ max_pfn, for example when
- * jump back to original kernel from kexeced kernel
+ * segments's mem ranges could be outside 0 ~ max_pfn,
+ * for example when jump back to original kernel from kexeced kernel.
+ * or first kernel is booted with user mem map, and second kernel
+ * could be loaded out of that range.
*/
- result = init_one_level2_page(image, level4p, image->start);
- if (result)
- return result;
+ for (i = 0; i < image->nr_segments; i++) {
+ mstart = image->segment[i].mem;
+ mend = mstart + image->segment[i].memsz;
+
+ result = kernel_ident_mapping_init(&info,
+ level4p, mstart, mend);
+
+ if (result)
+ return result;
+ }
+
return init_transition_pgtable(image, level4p);
}
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 3a04b224d0c0..22db92bbdf1a 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -364,10 +364,7 @@ static struct attribute_group mc_attr_group = {
static void microcode_fini_cpu(int cpu)
{
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-
microcode_ops->microcode_fini_cpu(cpu);
- uci->valid = 0;
}
static enum ucode_state microcode_resume_cpu(int cpu)
@@ -383,6 +380,10 @@ static enum ucode_state microcode_resume_cpu(int cpu)
static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw)
{
enum ucode_state ustate;
+ struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+
+ if (uci && uci->valid)
+ return UCODE_OK;
if (collect_cpu_info(cpu))
return UCODE_ERROR;
diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c
new file mode 100644
index 000000000000..577db8417d15
--- /dev/null
+++ b/arch/x86/kernel/microcode_core_early.c
@@ -0,0 +1,76 @@
+/*
+ * X86 CPU microcode early update for Linux
+ *
+ * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
+ * H Peter Anvin" <hpa@zytor.com>
+ *
+ * This driver allows to early upgrade microcode on Intel processors
+ * belonging to IA-32 family - PentiumPro, Pentium II,
+ * Pentium III, Xeon, Pentium 4, etc.
+ *
+ * Reference: Section 9.11 of Volume 3, IA-32 Intel Architecture
+ * Software Developer's Manual.
+ *
+ * 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/module.h>
+#include <asm/microcode_intel.h>
+#include <asm/processor.h>
+
+#define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24))
+#define CPUID_INTEL1 QCHAR('G', 'e', 'n', 'u')
+#define CPUID_INTEL2 QCHAR('i', 'n', 'e', 'I')
+#define CPUID_INTEL3 QCHAR('n', 't', 'e', 'l')
+#define CPUID_AMD1 QCHAR('A', 'u', 't', 'h')
+#define CPUID_AMD2 QCHAR('e', 'n', 't', 'i')
+#define CPUID_AMD3 QCHAR('c', 'A', 'M', 'D')
+
+#define CPUID_IS(a, b, c, ebx, ecx, edx) \
+ (!((ebx ^ (a))|(edx ^ (b))|(ecx ^ (c))))
+
+/*
+ * In early loading microcode phase on BSP, boot_cpu_data is not set up yet.
+ * x86_vendor() gets vendor id for BSP.
+ *
+ * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify
+ * coding, we still use x86_vendor() to get vendor id for AP.
+ *
+ * x86_vendor() gets vendor information directly through cpuid.
+ */
+static int __cpuinit x86_vendor(void)
+{
+ u32 eax = 0x00000000;
+ u32 ebx, ecx = 0, edx;
+
+ if (!have_cpuid_p())
+ return X86_VENDOR_UNKNOWN;
+
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+
+ if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx))
+ return X86_VENDOR_INTEL;
+
+ if (CPUID_IS(CPUID_AMD1, CPUID_AMD2, CPUID_AMD3, ebx, ecx, edx))
+ return X86_VENDOR_AMD;
+
+ return X86_VENDOR_UNKNOWN;
+}
+
+void __init load_ucode_bsp(void)
+{
+ int vendor = x86_vendor();
+
+ if (vendor == X86_VENDOR_INTEL)
+ load_ucode_intel_bsp();
+}
+
+void __cpuinit load_ucode_ap(void)
+{
+ int vendor = x86_vendor();
+
+ if (vendor == X86_VENDOR_INTEL)
+ load_ucode_intel_ap();
+}
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 3544aed39338..5fb2cebf556b 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -79,7 +79,7 @@
#include <linux/module.h>
#include <linux/vmalloc.h>
-#include <asm/microcode.h>
+#include <asm/microcode_intel.h>
#include <asm/processor.h>
#include <asm/msr.h>
@@ -87,59 +87,6 @@ MODULE_DESCRIPTION("Microcode Update Driver");
MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
MODULE_LICENSE("GPL");
-struct microcode_header_intel {
- unsigned int hdrver;
- unsigned int rev;
- unsigned int date;
- unsigned int sig;
- unsigned int cksum;
- unsigned int ldrver;
- unsigned int pf;
- unsigned int datasize;
- unsigned int totalsize;
- unsigned int reserved[3];
-};
-
-struct microcode_intel {
- struct microcode_header_intel hdr;
- unsigned int bits[0];
-};
-
-/* microcode format is extended from prescott processors */
-struct extended_signature {
- unsigned int sig;
- unsigned int pf;
- unsigned int cksum;
-};
-
-struct extended_sigtable {
- unsigned int count;
- unsigned int cksum;
- unsigned int reserved[3];
- struct extended_signature sigs[0];
-};
-
-#define DEFAULT_UCODE_DATASIZE (2000)
-#define MC_HEADER_SIZE (sizeof(struct microcode_header_intel))
-#define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE)
-#define EXT_HEADER_SIZE (sizeof(struct extended_sigtable))
-#define EXT_SIGNATURE_SIZE (sizeof(struct extended_signature))
-#define DWSIZE (sizeof(u32))
-
-#define get_totalsize(mc) \
- (((struct microcode_intel *)mc)->hdr.totalsize ? \
- ((struct microcode_intel *)mc)->hdr.totalsize : \
- DEFAULT_UCODE_TOTALSIZE)
-
-#define get_datasize(mc) \
- (((struct microcode_intel *)mc)->hdr.datasize ? \
- ((struct microcode_intel *)mc)->hdr.datasize : DEFAULT_UCODE_DATASIZE)
-
-#define sigmatch(s1, s2, p1, p2) \
- (((s1) == (s2)) && (((p1) & (p2)) || (((p1) == 0) && ((p2) == 0))))
-
-#define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE)
-
static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
{
struct cpuinfo_x86 *c = &cpu_data(cpu_num);
@@ -162,128 +109,25 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
return 0;
}
-static inline int update_match_cpu(struct cpu_signature *csig, int sig, int pf)
-{
- return (!sigmatch(sig, csig->sig, pf, csig->pf)) ? 0 : 1;
-}
-
-static inline int
-update_match_revision(struct microcode_header_intel *mc_header, int rev)
-{
- return (mc_header->rev <= rev) ? 0 : 1;
-}
-
-static int microcode_sanity_check(void *mc)
-{
- unsigned long total_size, data_size, ext_table_size;
- struct microcode_header_intel *mc_header = mc;
- struct extended_sigtable *ext_header = NULL;
- int sum, orig_sum, ext_sigcount = 0, i;
- struct extended_signature *ext_sig;
-
- total_size = get_totalsize(mc_header);
- data_size = get_datasize(mc_header);
-
- if (data_size + MC_HEADER_SIZE > total_size) {
- pr_err("error! Bad data size in microcode data file\n");
- return -EINVAL;
- }
-
- if (mc_header->ldrver != 1 || mc_header->hdrver != 1) {
- pr_err("error! Unknown microcode update format\n");
- return -EINVAL;
- }
- ext_table_size = total_size - (MC_HEADER_SIZE + data_size);
- if (ext_table_size) {
- if ((ext_table_size < EXT_HEADER_SIZE)
- || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) {
- pr_err("error! Small exttable size in microcode data file\n");
- return -EINVAL;
- }
- ext_header = mc + MC_HEADER_SIZE + data_size;
- if (ext_table_size != exttable_size(ext_header)) {
- pr_err("error! Bad exttable size in microcode data file\n");
- return -EFAULT;
- }
- ext_sigcount = ext_header->count;
- }
-
- /* check extended table checksum */
- if (ext_table_size) {
- int ext_table_sum = 0;
- int *ext_tablep = (int *)ext_header;
-
- i = ext_table_size / DWSIZE;
- while (i--)
- ext_table_sum += ext_tablep[i];
- if (ext_table_sum) {
- pr_warning("aborting, bad extended signature table checksum\n");
- return -EINVAL;
- }
- }
-
- /* calculate the checksum */
- orig_sum = 0;
- i = (MC_HEADER_SIZE + data_size) / DWSIZE;
- while (i--)
- orig_sum += ((int *)mc)[i];
- if (orig_sum) {
- pr_err("aborting, bad checksum\n");
- return -EINVAL;
- }
- if (!ext_table_size)
- return 0;
- /* check extended signature checksum */
- for (i = 0; i < ext_sigcount; i++) {
- ext_sig = (void *)ext_header + EXT_HEADER_SIZE +
- EXT_SIGNATURE_SIZE * i;
- sum = orig_sum
- - (mc_header->sig + mc_header->pf + mc_header->cksum)
- + (ext_sig->sig + ext_sig->pf + ext_sig->cksum);
- if (sum) {
- pr_err("aborting, bad checksum\n");
- return -EINVAL;
- }
- }
- return 0;
-}
-
/*
* return 0 - no update found
* return 1 - found update
*/
-static int
-get_matching_microcode(struct cpu_signature *cpu_sig, void *mc, int rev)
+static int get_matching_mc(struct microcode_intel *mc_intel, int cpu)
{
- struct microcode_header_intel *mc_header = mc;
- struct extended_sigtable *ext_header;
- unsigned long total_size = get_totalsize(mc_header);
- int ext_sigcount, i;
- struct extended_signature *ext_sig;
-
- if (!update_match_revision(mc_header, rev))
- return 0;
-
- if (update_match_cpu(cpu_sig, mc_header->sig, mc_header->pf))
- return 1;
+ struct cpu_signature cpu_sig;
+ unsigned int csig, cpf, crev;
- /* Look for ext. headers: */
- if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE)
- return 0;
+ collect_cpu_info(cpu, &cpu_sig);
- ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE;
- ext_sigcount = ext_header->count;
- ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
+ csig = cpu_sig.sig;
+ cpf = cpu_sig.pf;
+ crev = cpu_sig.rev;
- for (i = 0; i < ext_sigcount; i++) {
- if (update_match_cpu(cpu_sig, ext_sig->sig, ext_sig->pf))
- return 1;
- ext_sig++;
- }
- return 0;
+ return get_matching_microcode(csig, cpf, mc_intel, crev);
}
-static int apply_microcode(int cpu)
+int apply_microcode(int cpu)
{
struct microcode_intel *mc_intel;
struct ucode_cpu_info *uci;
@@ -300,6 +144,14 @@ static int apply_microcode(int cpu)
if (mc_intel == NULL)
return 0;
+ /*
+ * Microcode on this CPU could be updated earlier. Only apply the
+ * microcode patch in mc_intel when it is newer than the one on this
+ * CPU.
+ */
+ if (get_matching_mc(mc_intel, cpu) == 0)
+ return 0;
+
/* write microcode via MSR 0x79 */
wrmsr(MSR_IA32_UCODE_WRITE,
(unsigned long) mc_intel->bits,
@@ -338,6 +190,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
unsigned int leftover = size;
enum ucode_state state = UCODE_OK;
unsigned int curr_mc_size = 0;
+ unsigned int csig, cpf;
while (leftover) {
struct microcode_header_intel mc_header;
@@ -362,11 +215,13 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
}
if (get_ucode_data(mc, ucode_ptr, mc_size) ||
- microcode_sanity_check(mc) < 0) {
+ microcode_sanity_check(mc, 1) < 0) {
break;
}
- if (get_matching_microcode(&uci->cpu_sig, mc, new_rev)) {
+ csig = uci->cpu_sig.sig;
+ cpf = uci->cpu_sig.pf;
+ if (get_matching_microcode(csig, cpf, mc, new_rev)) {
vfree(new_mc);
new_rev = mc_header.rev;
new_mc = mc;
@@ -393,6 +248,13 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
vfree(uci->mc);
uci->mc = (struct microcode_intel *)new_mc;
+ /*
+ * If early loading microcode is supported, save this mc into
+ * permanent memory. So it will be loaded early when a CPU is hot added
+ * or resumes.
+ */
+ save_mc_for_early(new_mc);
+
pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
cpu, new_rev, uci->cpu_sig.rev);
out:
diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c
new file mode 100644
index 000000000000..7890bc838952
--- /dev/null
+++ b/arch/x86/kernel/microcode_intel_early.c
@@ -0,0 +1,796 @@
+/*
+ * Intel CPU microcode early update for Linux
+ *
+ * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
+ * H Peter Anvin" <hpa@zytor.com>
+ *
+ * This allows to early upgrade microcode on Intel processors
+ * belonging to IA-32 family - PentiumPro, Pentium II,
+ * Pentium III, Xeon, Pentium 4, etc.
+ *
+ * Reference: Section 9.11 of Volume 3, IA-32 Intel Architecture
+ * Software Developer's Manual.
+ *
+ * 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/module.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/earlycpio.h>
+#include <linux/initrd.h>
+#include <linux/cpu.h>
+#include <asm/msr.h>
+#include <asm/microcode_intel.h>
+#include <asm/processor.h>
+#include <asm/tlbflush.h>
+#include <asm/setup.h>
+
+unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT];
+struct mc_saved_data {
+ unsigned int mc_saved_count;
+ struct microcode_intel **mc_saved;
+} mc_saved_data;
+
+static enum ucode_state __cpuinit
+generic_load_microcode_early(struct microcode_intel **mc_saved_p,
+ unsigned int mc_saved_count,
+ struct ucode_cpu_info *uci)
+{
+ struct microcode_intel *ucode_ptr, *new_mc = NULL;
+ int new_rev = uci->cpu_sig.rev;
+ enum ucode_state state = UCODE_OK;
+ unsigned int mc_size;
+ struct microcode_header_intel *mc_header;
+ unsigned int csig = uci->cpu_sig.sig;
+ unsigned int cpf = uci->cpu_sig.pf;
+ int i;
+
+ for (i = 0; i < mc_saved_count; i++) {
+ ucode_ptr = mc_saved_p[i];
+
+ mc_header = (struct microcode_header_intel *)ucode_ptr;
+ mc_size = get_totalsize(mc_header);
+ if (get_matching_microcode(csig, cpf, ucode_ptr, new_rev)) {
+ new_rev = mc_header->rev;
+ new_mc = ucode_ptr;
+ }
+ }
+
+ if (!new_mc) {
+ state = UCODE_NFOUND;
+ goto out;
+ }
+
+ uci->mc = (struct microcode_intel *)new_mc;
+out:
+ return state;
+}
+
+static void __cpuinit
+microcode_pointer(struct microcode_intel **mc_saved,
+ unsigned long *mc_saved_in_initrd,
+ unsigned long initrd_start, int mc_saved_count)
+{
+ int i;
+
+ for (i = 0; i < mc_saved_count; i++)
+ mc_saved[i] = (struct microcode_intel *)
+ (mc_saved_in_initrd[i] + initrd_start);
+}
+
+#ifdef CONFIG_X86_32
+static void __cpuinit
+microcode_phys(struct microcode_intel **mc_saved_tmp,
+ struct mc_saved_data *mc_saved_data)
+{
+ int i;
+ struct microcode_intel ***mc_saved;
+
+ mc_saved = (struct microcode_intel ***)
+ __pa_symbol(&mc_saved_data->mc_saved);
+ for (i = 0; i < mc_saved_data->mc_saved_count; i++) {
+ struct microcode_intel *p;
+
+ p = *(struct microcode_intel **)
+ __pa(mc_saved_data->mc_saved + i);
+ mc_saved_tmp[i] = (struct microcode_intel *)__pa(p);
+ }
+}
+#endif
+
+static enum ucode_state __cpuinit
+load_microcode(struct mc_saved_data *mc_saved_data,
+ unsigned long *mc_saved_in_initrd,
+ unsigned long initrd_start,
+ struct ucode_cpu_info *uci)
+{
+ struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
+ unsigned int count = mc_saved_data->mc_saved_count;
+
+ if (!mc_saved_data->mc_saved) {
+ microcode_pointer(mc_saved_tmp, mc_saved_in_initrd,
+ initrd_start, count);
+
+ return generic_load_microcode_early(mc_saved_tmp, count, uci);
+ } else {
+#ifdef CONFIG_X86_32
+ microcode_phys(mc_saved_tmp, mc_saved_data);
+ return generic_load_microcode_early(mc_saved_tmp, count, uci);
+#else
+ return generic_load_microcode_early(mc_saved_data->mc_saved,
+ count, uci);
+#endif
+ }
+}
+
+static u8 get_x86_family(unsigned long sig)
+{
+ u8 x86;
+
+ x86 = (sig >> 8) & 0xf;
+
+ if (x86 == 0xf)
+ x86 += (sig >> 20) & 0xff;
+
+ return x86;
+}
+
+static u8 get_x86_model(unsigned long sig)
+{
+ u8 x86, x86_model;
+
+ x86 = get_x86_family(sig);
+ x86_model = (sig >> 4) & 0xf;
+
+ if (x86 == 0x6 || x86 == 0xf)
+ x86_model += ((sig >> 16) & 0xf) << 4;
+
+ return x86_model;
+}
+
+/*
+ * Given CPU signature and a microcode patch, this function finds if the
+ * microcode patch has matching family and model with the CPU.
+ */
+static enum ucode_state
+matching_model_microcode(struct microcode_header_intel *mc_header,
+ unsigned long sig)
+{
+ u8 x86, x86_model;
+ u8 x86_ucode, x86_model_ucode;
+ struct extended_sigtable *ext_header;
+ unsigned long total_size = get_totalsize(mc_header);
+ unsigned long data_size = get_datasize(mc_header);
+ int ext_sigcount, i;
+ struct extended_signature *ext_sig;
+
+ x86 = get_x86_family(sig);
+ x86_model = get_x86_model(sig);
+
+ x86_ucode = get_x86_family(mc_header->sig);
+ x86_model_ucode = get_x86_model(mc_header->sig);
+
+ if (x86 == x86_ucode && x86_model == x86_model_ucode)
+ return UCODE_OK;
+
+ /* Look for ext. headers: */
+ if (total_size <= data_size + MC_HEADER_SIZE)
+ return UCODE_NFOUND;
+
+ ext_header = (struct extended_sigtable *)
+ mc_header + data_size + MC_HEADER_SIZE;
+ ext_sigcount = ext_header->count;
+ ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
+
+ for (i = 0; i < ext_sigcount; i++) {
+ x86_ucode = get_x86_family(ext_sig->sig);
+ x86_model_ucode = get_x86_model(ext_sig->sig);
+
+ if (x86 == x86_ucode && x86_model == x86_model_ucode)
+ return UCODE_OK;
+
+ ext_sig++;
+ }
+
+ return UCODE_NFOUND;
+}
+
+static int
+save_microcode(struct mc_saved_data *mc_saved_data,
+ struct microcode_intel **mc_saved_src,
+ unsigned int mc_saved_count)
+{
+ int i, j;
+ struct microcode_intel **mc_saved_p;
+ int ret;
+
+ if (!mc_saved_count)
+ return -EINVAL;
+
+ /*
+ * Copy new microcode data.
+ */
+ mc_saved_p = kmalloc(mc_saved_count*sizeof(struct microcode_intel *),
+ GFP_KERNEL);
+ if (!mc_saved_p)
+ return -ENOMEM;
+
+ for (i = 0; i < mc_saved_count; i++) {
+ struct microcode_intel *mc = mc_saved_src[i];
+ struct microcode_header_intel *mc_header = &mc->hdr;
+ unsigned long mc_size = get_totalsize(mc_header);
+ mc_saved_p[i] = kmalloc(mc_size, GFP_KERNEL);
+ if (!mc_saved_p[i]) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ if (!mc_saved_src[i]) {
+ ret = -EINVAL;
+ goto err;
+ }
+ memcpy(mc_saved_p[i], mc, mc_size);
+ }
+
+ /*
+ * Point to newly saved microcode.
+ */
+ mc_saved_data->mc_saved = mc_saved_p;
+ mc_saved_data->mc_saved_count = mc_saved_count;
+
+ return 0;
+
+err:
+ for (j = 0; j <= i; j++)
+ kfree(mc_saved_p[j]);
+ kfree(mc_saved_p);
+
+ return ret;
+}
+
+/*
+ * A microcode patch in ucode_ptr is saved into mc_saved
+ * - if it has matching signature and newer revision compared to an existing
+ * patch mc_saved.
+ * - or if it is a newly discovered microcode patch.
+ *
+ * The microcode patch should have matching model with CPU.
+ */
+static void _save_mc(struct microcode_intel **mc_saved, u8 *ucode_ptr,
+ unsigned int *mc_saved_count_p)
+{
+ int i;
+ int found = 0;
+ unsigned int mc_saved_count = *mc_saved_count_p;
+ struct microcode_header_intel *mc_header;
+
+ mc_header = (struct microcode_header_intel *)ucode_ptr;
+ for (i = 0; i < mc_saved_count; i++) {
+ unsigned int sig, pf;
+ unsigned int new_rev;
+ struct microcode_header_intel *mc_saved_header =
+ (struct microcode_header_intel *)mc_saved[i];
+ sig = mc_saved_header->sig;
+ pf = mc_saved_header->pf;
+ new_rev = mc_header->rev;
+
+ if (get_matching_sig(sig, pf, ucode_ptr, new_rev)) {
+ found = 1;
+ if (update_match_revision(mc_header, new_rev)) {
+ /*
+ * Found an older ucode saved before.
+ * Replace the older one with this newer
+ * one.
+ */
+ mc_saved[i] =
+ (struct microcode_intel *)ucode_ptr;
+ break;
+ }
+ }
+ }
+ if (i >= mc_saved_count && !found)
+ /*
+ * This ucode is first time discovered in ucode file.
+ * Save it to memory.
+ */
+ mc_saved[mc_saved_count++] =
+ (struct microcode_intel *)ucode_ptr;
+
+ *mc_saved_count_p = mc_saved_count;
+}
+
+/*
+ * Get microcode matching with BSP's model. Only CPUs with the same model as
+ * BSP can stay in the platform.
+ */
+static enum ucode_state __init
+get_matching_model_microcode(int cpu, unsigned long start,
+ void *data, size_t size,
+ struct mc_saved_data *mc_saved_data,
+ unsigned long *mc_saved_in_initrd,
+ struct ucode_cpu_info *uci)
+{
+ u8 *ucode_ptr = data;
+ unsigned int leftover = size;
+ enum ucode_state state = UCODE_OK;
+ unsigned int mc_size;
+ struct microcode_header_intel *mc_header;
+ struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
+ unsigned int mc_saved_count = mc_saved_data->mc_saved_count;
+ int i;
+
+ while (leftover) {
+ mc_header = (struct microcode_header_intel *)ucode_ptr;
+
+ mc_size = get_totalsize(mc_header);
+ if (!mc_size || mc_size > leftover ||
+ microcode_sanity_check(ucode_ptr, 0) < 0)
+ break;
+
+ leftover -= mc_size;
+
+ /*
+ * Since APs with same family and model as the BSP may boot in
+ * the platform, we need to find and save microcode patches
+ * with the same family and model as the BSP.
+ */
+ if (matching_model_microcode(mc_header, uci->cpu_sig.sig) !=
+ UCODE_OK) {
+ ucode_ptr += mc_size;
+ continue;
+ }
+
+ _save_mc(mc_saved_tmp, ucode_ptr, &mc_saved_count);
+
+ ucode_ptr += mc_size;
+ }
+
+ if (leftover) {
+ state = UCODE_ERROR;
+ goto out;
+ }
+
+ if (mc_saved_count == 0) {
+ state = UCODE_NFOUND;
+ goto out;
+ }
+
+ for (i = 0; i < mc_saved_count; i++)
+ mc_saved_in_initrd[i] = (unsigned long)mc_saved_tmp[i] - start;
+
+ mc_saved_data->mc_saved_count = mc_saved_count;
+out:
+ return state;
+}
+
+#define native_rdmsr(msr, val1, val2) \
+do { \
+ u64 __val = native_read_msr((msr)); \
+ (void)((val1) = (u32)__val); \
+ (void)((val2) = (u32)(__val >> 32)); \
+} while (0)
+
+#define native_wrmsr(msr, low, high) \
+ native_write_msr(msr, low, high);
+
+static int __cpuinit collect_cpu_info_early(struct ucode_cpu_info *uci)
+{
+ unsigned int val[2];
+ u8 x86, x86_model;
+ struct cpu_signature csig;
+ unsigned int eax, ebx, ecx, edx;
+
+ csig.sig = 0;
+ csig.pf = 0;
+ csig.rev = 0;
+
+ memset(uci, 0, sizeof(*uci));
+
+ eax = 0x00000001;
+ ecx = 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+ csig.sig = eax;
+
+ x86 = get_x86_family(csig.sig);
+ x86_model = get_x86_model(csig.sig);
+
+ if ((x86_model >= 5) || (x86 > 6)) {
+ /* get processor flags from MSR 0x17 */
+ native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
+ csig.pf = 1 << ((val[1] >> 18) & 7);
+ }
+ native_wrmsr(MSR_IA32_UCODE_REV, 0, 0);
+
+ /* As documented in the SDM: Do a CPUID 1 here */
+ sync_core();
+
+ /* get the current revision from MSR 0x8B */
+ native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
+
+ csig.rev = val[1];
+
+ uci->cpu_sig = csig;
+ uci->valid = 1;
+
+ return 0;
+}
+
+#ifdef DEBUG
+static void __ref show_saved_mc(void)
+{
+ int i, j;
+ unsigned int sig, pf, rev, total_size, data_size, date;
+ struct ucode_cpu_info uci;
+
+ if (mc_saved_data.mc_saved_count == 0) {
+ pr_debug("no micorcode data saved.\n");
+ return;
+ }
+ pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count);
+
+ collect_cpu_info_early(&uci);
+
+ sig = uci.cpu_sig.sig;
+ pf = uci.cpu_sig.pf;
+ rev = uci.cpu_sig.rev;
+ pr_debug("CPU%d: sig=0x%x, pf=0x%x, rev=0x%x\n",
+ smp_processor_id(), sig, pf, rev);
+
+ for (i = 0; i < mc_saved_data.mc_saved_count; i++) {
+ struct microcode_header_intel *mc_saved_header;
+ struct extended_sigtable *ext_header;
+ int ext_sigcount;
+ struct extended_signature *ext_sig;
+
+ mc_saved_header = (struct microcode_header_intel *)
+ mc_saved_data.mc_saved[i];
+ sig = mc_saved_header->sig;
+ pf = mc_saved_header->pf;
+ rev = mc_saved_header->rev;
+ total_size = get_totalsize(mc_saved_header);
+ data_size = get_datasize(mc_saved_header);
+ date = mc_saved_header->date;
+
+ pr_debug("mc_saved[%d]: sig=0x%x, pf=0x%x, rev=0x%x, toal size=0x%x, date = %04x-%02x-%02x\n",
+ i, sig, pf, rev, total_size,
+ date & 0xffff,
+ date >> 24,
+ (date >> 16) & 0xff);
+
+ /* Look for ext. headers: */
+ if (total_size <= data_size + MC_HEADER_SIZE)
+ continue;
+
+ ext_header = (struct extended_sigtable *)
+ mc_saved_header + data_size + MC_HEADER_SIZE;
+ ext_sigcount = ext_header->count;
+ ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
+
+ for (j = 0; j < ext_sigcount; j++) {
+ sig = ext_sig->sig;
+ pf = ext_sig->pf;
+
+ pr_debug("\tExtended[%d]: sig=0x%x, pf=0x%x\n",
+ j, sig, pf);
+
+ ext_sig++;
+ }
+
+ }
+}
+#else
+static inline void show_saved_mc(void)
+{
+}
+#endif
+
+#if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU)
+/*
+ * Save this mc into mc_saved_data. So it will be loaded early when a CPU is
+ * hot added or resumes.
+ *
+ * Please make sure this mc should be a valid microcode patch before calling
+ * this function.
+ */
+int save_mc_for_early(u8 *mc)
+{
+ struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
+ unsigned int mc_saved_count_init;
+ unsigned int mc_saved_count;
+ struct microcode_intel **mc_saved;
+ int ret = 0;
+ int i;
+
+ /*
+ * Hold hotplug lock so mc_saved_data is not accessed by a CPU in
+ * hotplug.
+ */
+ cpu_hotplug_driver_lock();
+
+ mc_saved_count_init = mc_saved_data.mc_saved_count;
+ mc_saved_count = mc_saved_data.mc_saved_count;
+ mc_saved = mc_saved_data.mc_saved;
+
+ if (mc_saved && mc_saved_count)
+ memcpy(mc_saved_tmp, mc_saved,
+ mc_saved_count * sizeof(struct mirocode_intel *));
+ /*
+ * Save the microcode patch mc in mc_save_tmp structure if it's a newer
+ * version.
+ */
+
+ _save_mc(mc_saved_tmp, mc, &mc_saved_count);
+
+ /*
+ * Save the mc_save_tmp in global mc_saved_data.
+ */
+ ret = save_microcode(&mc_saved_data, mc_saved_tmp, mc_saved_count);
+ if (ret) {
+ pr_err("Can not save microcode patch.\n");
+ goto out;
+ }
+
+ show_saved_mc();
+
+ /*
+ * Free old saved microcod data.
+ */
+ if (mc_saved) {
+ for (i = 0; i < mc_saved_count_init; i++)
+ kfree(mc_saved[i]);
+ kfree(mc_saved);
+ }
+
+out:
+ cpu_hotplug_driver_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(save_mc_for_early);
+#endif
+
+static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin";
+static __init enum ucode_state
+scan_microcode(unsigned long start, unsigned long end,
+ struct mc_saved_data *mc_saved_data,
+ unsigned long *mc_saved_in_initrd,
+ struct ucode_cpu_info *uci)
+{
+ unsigned int size = end - start + 1;
+ struct cpio_data cd;
+ long offset = 0;
+#ifdef CONFIG_X86_32
+ char *p = (char *)__pa_symbol(ucode_name);
+#else
+ char *p = ucode_name;
+#endif
+
+ cd.data = NULL;
+ cd.size = 0;
+
+ cd = find_cpio_data(p, (void *)start, size, &offset);
+ if (!cd.data)
+ return UCODE_ERROR;
+
+
+ return get_matching_model_microcode(0, start, cd.data, cd.size,
+ mc_saved_data, mc_saved_in_initrd,
+ uci);
+}
+
+/*
+ * Print ucode update info.
+ */
+static void __cpuinit
+print_ucode_info(struct ucode_cpu_info *uci, unsigned int date)
+{
+ int cpu = smp_processor_id();
+
+ pr_info("CPU%d microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n",
+ cpu,
+ uci->cpu_sig.rev,
+ date & 0xffff,
+ date >> 24,
+ (date >> 16) & 0xff);
+}
+
+#ifdef CONFIG_X86_32
+
+static int delay_ucode_info;
+static int current_mc_date;
+
+/*
+ * Print early updated ucode info after printk works. This is delayed info dump.
+ */
+void __cpuinit show_ucode_info_early(void)
+{
+ struct ucode_cpu_info uci;
+
+ if (delay_ucode_info) {
+ collect_cpu_info_early(&uci);
+ print_ucode_info(&uci, current_mc_date);
+ delay_ucode_info = 0;
+ }
+}
+
+/*
+ * At this point, we can not call printk() yet. Keep microcode patch number in
+ * mc_saved_data.mc_saved and delay printing microcode info in
+ * show_ucode_info_early() until printk() works.
+ */
+static void __cpuinit print_ucode(struct ucode_cpu_info *uci)
+{
+ struct microcode_intel *mc_intel;
+ int *delay_ucode_info_p;
+ int *current_mc_date_p;
+
+ mc_intel = uci->mc;
+ if (mc_intel == NULL)
+ return;
+
+ delay_ucode_info_p = (int *)__pa_symbol(&delay_ucode_info);
+ current_mc_date_p = (int *)__pa_symbol(&current_mc_date);
+
+ *delay_ucode_info_p = 1;
+ *current_mc_date_p = mc_intel->hdr.date;
+}
+#else
+
+/*
+ * Flush global tlb. We only do this in x86_64 where paging has been enabled
+ * already and PGE should be enabled as well.
+ */
+static inline void __cpuinit flush_tlb_early(void)
+{
+ __native_flush_tlb_global_irq_disabled();
+}
+
+static inline void __cpuinit print_ucode(struct ucode_cpu_info *uci)
+{
+ struct microcode_intel *mc_intel;
+
+ mc_intel = uci->mc;
+ if (mc_intel == NULL)
+ return;
+
+ print_ucode_info(uci, mc_intel->hdr.date);
+}
+#endif
+
+static int apply_microcode_early(struct mc_saved_data *mc_saved_data,
+ struct ucode_cpu_info *uci)
+{
+ struct microcode_intel *mc_intel;
+ unsigned int val[2];
+
+ mc_intel = uci->mc;
+ if (mc_intel == NULL)
+ return 0;
+
+ /* write microcode via MSR 0x79 */
+ native_wrmsr(MSR_IA32_UCODE_WRITE,
+ (unsigned long) mc_intel->bits,
+ (unsigned long) mc_intel->bits >> 16 >> 16);
+ native_wrmsr(MSR_IA32_UCODE_REV, 0, 0);
+
+ /* As documented in the SDM: Do a CPUID 1 here */
+ sync_core();
+
+ /* get the current revision from MSR 0x8B */
+ native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
+ if (val[1] != mc_intel->hdr.rev)
+ return -1;
+
+#ifdef CONFIG_X86_64
+ /* Flush global tlb. This is precaution. */
+ flush_tlb_early();
+#endif
+ uci->cpu_sig.rev = val[1];
+
+ print_ucode(uci);
+
+ return 0;
+}
+
+/*
+ * This function converts microcode patch offsets previously stored in
+ * mc_saved_in_initrd to pointers and stores the pointers in mc_saved_data.
+ */
+int __init save_microcode_in_initrd(void)
+{
+ unsigned int count = mc_saved_data.mc_saved_count;
+ struct microcode_intel *mc_saved[MAX_UCODE_COUNT];
+ int ret = 0;
+
+ if (count == 0)
+ return ret;
+
+ microcode_pointer(mc_saved, mc_saved_in_initrd, initrd_start, count);
+ ret = save_microcode(&mc_saved_data, mc_saved, count);
+ if (ret)
+ pr_err("Can not save microcod patches from initrd");
+
+ show_saved_mc();
+
+ return ret;
+}
+
+static void __init
+_load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data,
+ unsigned long *mc_saved_in_initrd,
+ unsigned long initrd_start_early,
+ unsigned long initrd_end_early,
+ struct ucode_cpu_info *uci)
+{
+ collect_cpu_info_early(uci);
+ scan_microcode(initrd_start_early, initrd_end_early, mc_saved_data,
+ mc_saved_in_initrd, uci);
+ load_microcode(mc_saved_data, mc_saved_in_initrd,
+ initrd_start_early, uci);
+ apply_microcode_early(mc_saved_data, uci);
+}
+
+void __init
+load_ucode_intel_bsp(void)
+{
+ u64 ramdisk_image, ramdisk_size;
+ unsigned long initrd_start_early, initrd_end_early;
+ struct ucode_cpu_info uci;
+#ifdef CONFIG_X86_32
+ struct boot_params *boot_params_p;
+
+ boot_params_p = (struct boot_params *)__pa_symbol(&boot_params);
+ ramdisk_image = boot_params_p->hdr.ramdisk_image;
+ ramdisk_size = boot_params_p->hdr.ramdisk_size;
+ initrd_start_early = ramdisk_image;
+ initrd_end_early = initrd_start_early + ramdisk_size;
+
+ _load_ucode_intel_bsp(
+ (struct mc_saved_data *)__pa_symbol(&mc_saved_data),
+ (unsigned long *)__pa_symbol(&mc_saved_in_initrd),
+ initrd_start_early, initrd_end_early, &uci);
+#else
+ ramdisk_image = boot_params.hdr.ramdisk_image;
+ ramdisk_size = boot_params.hdr.ramdisk_size;
+ initrd_start_early = ramdisk_image + PAGE_OFFSET;
+ initrd_end_early = initrd_start_early + ramdisk_size;
+
+ _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd,
+ initrd_start_early, initrd_end_early, &uci);
+#endif
+}
+
+void __cpuinit load_ucode_intel_ap(void)
+{
+ struct mc_saved_data *mc_saved_data_p;
+ struct ucode_cpu_info uci;
+ unsigned long *mc_saved_in_initrd_p;
+ unsigned long initrd_start_addr;
+#ifdef CONFIG_X86_32
+ unsigned long *initrd_start_p;
+
+ mc_saved_in_initrd_p =
+ (unsigned long *)__pa_symbol(mc_saved_in_initrd);
+ mc_saved_data_p = (struct mc_saved_data *)__pa_symbol(&mc_saved_data);
+ initrd_start_p = (unsigned long *)__pa_symbol(&initrd_start);
+ initrd_start_addr = (unsigned long)__pa_symbol(*initrd_start_p);
+#else
+ mc_saved_data_p = &mc_saved_data;
+ mc_saved_in_initrd_p = mc_saved_in_initrd;
+ initrd_start_addr = initrd_start;
+#endif
+
+ /*
+ * If there is no valid ucode previously saved in memory, no need to
+ * update ucode on this AP.
+ */
+ if (mc_saved_data_p->mc_saved_count == 0)
+ return;
+
+ collect_cpu_info_early(&uci);
+ load_microcode(mc_saved_data_p, mc_saved_in_initrd_p,
+ initrd_start_addr, &uci);
+ apply_microcode_early(mc_saved_data_p, &uci);
+}
diff --git a/arch/x86/kernel/microcode_intel_lib.c b/arch/x86/kernel/microcode_intel_lib.c
new file mode 100644
index 000000000000..ce69320d0179
--- /dev/null
+++ b/arch/x86/kernel/microcode_intel_lib.c
@@ -0,0 +1,174 @@
+/*
+ * Intel CPU Microcode Update Driver for Linux
+ *
+ * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
+ * H Peter Anvin" <hpa@zytor.com>
+ *
+ * This driver allows to upgrade microcode on Intel processors
+ * belonging to IA-32 family - PentiumPro, Pentium II,
+ * Pentium III, Xeon, Pentium 4, etc.
+ *
+ * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
+ * Software Developer's Manual
+ * Order Number 253668 or free download from:
+ *
+ * http://developer.intel.com/Assets/PDF/manual/253668.pdf
+ *
+ * For more information, go to http://www.urbanmyth.org/microcode
+ *
+ * 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/firmware.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/microcode_intel.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
+
+static inline int
+update_match_cpu(unsigned int csig, unsigned int cpf,
+ unsigned int sig, unsigned int pf)
+{
+ return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1;
+}
+
+int
+update_match_revision(struct microcode_header_intel *mc_header, int rev)
+{
+ return (mc_header->rev <= rev) ? 0 : 1;
+}
+
+int microcode_sanity_check(void *mc, int print_err)
+{
+ unsigned long total_size, data_size, ext_table_size;
+ struct microcode_header_intel *mc_header = mc;
+ struct extended_sigtable *ext_header = NULL;
+ int sum, orig_sum, ext_sigcount = 0, i;
+ struct extended_signature *ext_sig;
+
+ total_size = get_totalsize(mc_header);
+ data_size = get_datasize(mc_header);
+
+ if (data_size + MC_HEADER_SIZE > total_size) {
+ if (print_err)
+ pr_err("error! Bad data size in microcode data file\n");
+ return -EINVAL;
+ }
+
+ if (mc_header->ldrver != 1 || mc_header->hdrver != 1) {
+ if (print_err)
+ pr_err("error! Unknown microcode update format\n");
+ return -EINVAL;
+ }
+ ext_table_size = total_size - (MC_HEADER_SIZE + data_size);
+ if (ext_table_size) {
+ if ((ext_table_size < EXT_HEADER_SIZE)
+ || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) {
+ if (print_err)
+ pr_err("error! Small exttable size in microcode data file\n");
+ return -EINVAL;
+ }
+ ext_header = mc + MC_HEADER_SIZE + data_size;
+ if (ext_table_size != exttable_size(ext_header)) {
+ if (print_err)
+ pr_err("error! Bad exttable size in microcode data file\n");
+ return -EFAULT;
+ }
+ ext_sigcount = ext_header->count;
+ }
+
+ /* check extended table checksum */
+ if (ext_table_size) {
+ int ext_table_sum = 0;
+ int *ext_tablep = (int *)ext_header;
+
+ i = ext_table_size / DWSIZE;
+ while (i--)
+ ext_table_sum += ext_tablep[i];
+ if (ext_table_sum) {
+ if (print_err)
+ pr_warn("aborting, bad extended signature table checksum\n");
+ return -EINVAL;
+ }
+ }
+
+ /* calculate the checksum */
+ orig_sum = 0;
+ i = (MC_HEADER_SIZE + data_size) / DWSIZE;
+ while (i--)
+ orig_sum += ((int *)mc)[i];
+ if (orig_sum) {
+ if (print_err)
+ pr_err("aborting, bad checksum\n");
+ return -EINVAL;
+ }
+ if (!ext_table_size)
+ return 0;
+ /* check extended signature checksum */
+ for (i = 0; i < ext_sigcount; i++) {
+ ext_sig = (void *)ext_header + EXT_HEADER_SIZE +
+ EXT_SIGNATURE_SIZE * i;
+ sum = orig_sum
+ - (mc_header->sig + mc_header->pf + mc_header->cksum)
+ + (ext_sig->sig + ext_sig->pf + ext_sig->cksum);
+ if (sum) {
+ if (print_err)
+ pr_err("aborting, bad checksum\n");
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(microcode_sanity_check);
+
+/*
+ * return 0 - no update found
+ * return 1 - found update
+ */
+int get_matching_sig(unsigned int csig, int cpf, void *mc, int rev)
+{
+ struct microcode_header_intel *mc_header = mc;
+ struct extended_sigtable *ext_header;
+ unsigned long total_size = get_totalsize(mc_header);
+ int ext_sigcount, i;
+ struct extended_signature *ext_sig;
+
+ if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf))
+ return 1;
+
+ /* Look for ext. headers: */
+ if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE)
+ return 0;
+
+ ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE;
+ ext_sigcount = ext_header->count;
+ ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
+
+ for (i = 0; i < ext_sigcount; i++) {
+ if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf))
+ return 1;
+ ext_sig++;
+ }
+ return 0;
+}
+
+/*
+ * return 0 - no update found
+ * return 1 - found update
+ */
+int get_matching_microcode(unsigned int csig, int cpf, void *mc, int rev)
+{
+ struct microcode_header_intel *mc_header = mc;
+
+ if (!update_match_revision(mc_header, rev))
+ return 0;
+
+ return get_matching_sig(csig, cpf, mc, rev);
+}
+EXPORT_SYMBOL_GPL(get_matching_microcode);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6e68a6194965..0f49677da51e 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -117,7 +117,7 @@ void release_thread(struct task_struct *dead_task)
{
if (dead_task->mm) {
if (dead_task->mm->context.size) {
- pr_warn("WARNING: dead process %8s still has LDT? <%p/%d>\n",
+ pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
dead_task->comm,
dead_task->mm->context.ldt,
dead_task->mm->context.size);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 8b24289cc10c..9c857f05cef0 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -108,17 +108,16 @@
#include <asm/topology.h>
#include <asm/apicdef.h>
#include <asm/amd_nb.h>
-#ifdef CONFIG_X86_64
-#include <asm/numa_64.h>
-#endif
#include <asm/mce.h>
#include <asm/alternative.h>
#include <asm/prom.h>
/*
- * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
- * The direct mapping extends to max_pfn_mapped, so that we can directly access
- * apertures, ACPI and other tables without having to play with fixmaps.
+ * max_low_pfn_mapped: highest direct mapped pfn under 4GB
+ * max_pfn_mapped: highest direct mapped pfn over 4GB
+ *
+ * The direct mapping only covers E820_RAM regions, so the ranges and gaps are
+ * represented by pfn_mapped
*/
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
@@ -276,18 +275,7 @@ void * __init extend_brk(size_t size, size_t align)
return ret;
}
-#ifdef CONFIG_X86_64
-static void __init init_gbpages(void)
-{
- if (direct_gbpages && cpu_has_gbpages)
- printk(KERN_INFO "Using GB pages for direct mapping\n");
- else
- direct_gbpages = 0;
-}
-#else
-static inline void init_gbpages(void)
-{
-}
+#ifdef CONFIG_X86_32
static void __init cleanup_highmap(void)
{
}
@@ -296,8 +284,8 @@ static void __init cleanup_highmap(void)
static void __init reserve_brk(void)
{
if (_brk_end > _brk_start)
- memblock_reserve(__pa(_brk_start),
- __pa(_brk_end) - __pa(_brk_start));
+ memblock_reserve(__pa_symbol(_brk_start),
+ _brk_end - _brk_start);
/* Mark brk area as locked down and no longer taking any
new allocations */
@@ -306,27 +294,43 @@ static void __init reserve_brk(void)
#ifdef CONFIG_BLK_DEV_INITRD
+static u64 __init get_ramdisk_image(void)
+{
+ u64 ramdisk_image = boot_params.hdr.ramdisk_image;
+
+ ramdisk_image |= (u64)boot_params.ext_ramdisk_image << 32;
+
+ return ramdisk_image;
+}
+static u64 __init get_ramdisk_size(void)
+{
+ u64 ramdisk_size = boot_params.hdr.ramdisk_size;
+
+ ramdisk_size |= (u64)boot_params.ext_ramdisk_size << 32;
+
+ return ramdisk_size;
+}
+
#define MAX_MAP_CHUNK (NR_FIX_BTMAPS << PAGE_SHIFT)
static void __init relocate_initrd(void)
{
/* Assume only end is not page aligned */
- u64 ramdisk_image = boot_params.hdr.ramdisk_image;
- u64 ramdisk_size = boot_params.hdr.ramdisk_size;
+ u64 ramdisk_image = get_ramdisk_image();
+ u64 ramdisk_size = get_ramdisk_size();
u64 area_size = PAGE_ALIGN(ramdisk_size);
- u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
u64 ramdisk_here;
unsigned long slop, clen, mapaddr;
char *p, *q;
- /* We need to move the initrd down into lowmem */
- ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size,
- PAGE_SIZE);
+ /* We need to move the initrd down into directly mapped mem */
+ ramdisk_here = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
+ area_size, PAGE_SIZE);
if (!ramdisk_here)
panic("Cannot find place for new RAMDISK of size %lld\n",
ramdisk_size);
- /* Note: this includes all the lowmem currently occupied by
+ /* Note: this includes all the mem currently occupied by
the initrd, we rely on that fact to keep the data intact. */
memblock_reserve(ramdisk_here, area_size);
initrd_start = ramdisk_here + PAGE_OFFSET;
@@ -336,17 +340,7 @@ static void __init relocate_initrd(void)
q = (char *)initrd_start;
- /* Copy any lowmem portion of the initrd */
- if (ramdisk_image < end_of_lowmem) {
- clen = end_of_lowmem - ramdisk_image;
- p = (char *)__va(ramdisk_image);
- memcpy(q, p, clen);
- q += clen;
- ramdisk_image += clen;
- ramdisk_size -= clen;
- }
-
- /* Copy the highmem portion of the initrd */
+ /* Copy the initrd */
while (ramdisk_size) {
slop = ramdisk_image & ~PAGE_MASK;
clen = ramdisk_size;
@@ -360,22 +354,35 @@ static void __init relocate_initrd(void)
ramdisk_image += clen;
ramdisk_size -= clen;
}
- /* high pages is not converted by early_res_to_bootmem */
- ramdisk_image = boot_params.hdr.ramdisk_image;
- ramdisk_size = boot_params.hdr.ramdisk_size;
+
+ ramdisk_image = get_ramdisk_image();
+ ramdisk_size = get_ramdisk_size();
printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
" [mem %#010llx-%#010llx]\n",
ramdisk_image, ramdisk_image + ramdisk_size - 1,
ramdisk_here, ramdisk_here + ramdisk_size - 1);
}
+static void __init early_reserve_initrd(void)
+{
+ /* Assume only end is not page aligned */
+ u64 ramdisk_image = get_ramdisk_image();
+ u64 ramdisk_size = get_ramdisk_size();
+ u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
+
+ if (!boot_params.hdr.type_of_loader ||
+ !ramdisk_image || !ramdisk_size)
+ return; /* No initrd provided by bootloader */
+
+ memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
+}
static void __init reserve_initrd(void)
{
/* Assume only end is not page aligned */
- u64 ramdisk_image = boot_params.hdr.ramdisk_image;
- u64 ramdisk_size = boot_params.hdr.ramdisk_size;
+ u64 ramdisk_image = get_ramdisk_image();
+ u64 ramdisk_size = get_ramdisk_size();
u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
- u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
+ u64 mapped_size;
if (!boot_params.hdr.type_of_loader ||
!ramdisk_image || !ramdisk_size)
@@ -383,22 +390,18 @@ static void __init reserve_initrd(void)
initrd_start = 0;
- if (ramdisk_size >= (end_of_lowmem>>1)) {
+ mapped_size = memblock_mem_size(max_pfn_mapped);
+ if (ramdisk_size >= (mapped_size>>1))
panic("initrd too large to handle, "
"disabling initrd (%lld needed, %lld available)\n",
- ramdisk_size, end_of_lowmem>>1);
- }
+ ramdisk_size, mapped_size>>1);
printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image,
ramdisk_end - 1);
-
- if (ramdisk_end <= end_of_lowmem) {
- /* All in lowmem, easy case */
- /*
- * don't need to reserve again, already reserved early
- * in i386_start_kernel
- */
+ if (pfn_range_is_mapped(PFN_DOWN(ramdisk_image),
+ PFN_DOWN(ramdisk_end))) {
+ /* All are mapped, easy case */
initrd_start = ramdisk_image + PAGE_OFFSET;
initrd_end = initrd_start + ramdisk_size;
return;
@@ -409,6 +412,9 @@ static void __init reserve_initrd(void)
memblock_free(ramdisk_image, ramdisk_end - ramdisk_image);
}
#else
+static void __init early_reserve_initrd(void)
+{
+}
static void __init reserve_initrd(void)
{
}
@@ -419,8 +425,6 @@ static void __init parse_setup_data(void)
struct setup_data *data;
u64 pa_data;
- if (boot_params.hdr.version < 0x0209)
- return;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
u32 data_len, map_len;
@@ -456,8 +460,6 @@ static void __init e820_reserve_setup_data(void)
u64 pa_data;
int found = 0;
- if (boot_params.hdr.version < 0x0209)
- return;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
data = early_memremap(pa_data, sizeof(*data));
@@ -481,8 +483,6 @@ static void __init memblock_x86_reserve_range_setup_data(void)
struct setup_data *data;
u64 pa_data;
- if (boot_params.hdr.version < 0x0209)
- return;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
data = early_memremap(pa_data, sizeof(*data));
@@ -501,17 +501,51 @@ static void __init memblock_x86_reserve_range_setup_data(void)
/*
* Keep the crash kernel below this limit. On 32 bits earlier kernels
* would limit the kernel to the low 512 MiB due to mapping restrictions.
- * On 64 bits, kexec-tools currently limits us to 896 MiB; increase this
- * limit once kexec-tools are fixed.
*/
#ifdef CONFIG_X86_32
# define CRASH_KERNEL_ADDR_MAX (512 << 20)
#else
-# define CRASH_KERNEL_ADDR_MAX (896 << 20)
+# define CRASH_KERNEL_ADDR_MAX MAXMEM
#endif
+static void __init reserve_crashkernel_low(void)
+{
+#ifdef CONFIG_X86_64
+ const unsigned long long alignment = 16<<20; /* 16M */
+ unsigned long long low_base = 0, low_size = 0;
+ unsigned long total_low_mem;
+ unsigned long long base;
+ int ret;
+
+ total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT));
+ ret = parse_crashkernel_low(boot_command_line, total_low_mem,
+ &low_size, &base);
+ if (ret != 0 || low_size <= 0)
+ return;
+
+ low_base = memblock_find_in_range(low_size, (1ULL<<32),
+ low_size, alignment);
+
+ if (!low_base) {
+ pr_info("crashkernel low reservation failed - No suitable area found.\n");
+
+ return;
+ }
+
+ memblock_reserve(low_base, low_size);
+ pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n",
+ (unsigned long)(low_size >> 20),
+ (unsigned long)(low_base >> 20),
+ (unsigned long)(total_low_mem >> 20));
+ crashk_low_res.start = low_base;
+ crashk_low_res.end = low_base + low_size - 1;
+ insert_resource(&iomem_resource, &crashk_low_res);
+#endif
+}
+
static void __init reserve_crashkernel(void)
{
+ const unsigned long long alignment = 16<<20; /* 16M */
unsigned long long total_mem;
unsigned long long crash_size, crash_base;
int ret;
@@ -525,8 +559,6 @@ static void __init reserve_crashkernel(void)
/* 0 means: find the address automatically */
if (crash_base <= 0) {
- const unsigned long long alignment = 16<<20; /* 16M */
-
/*
* kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
*/
@@ -537,6 +569,7 @@ static void __init reserve_crashkernel(void)
pr_info("crashkernel reservation failed - No suitable area found.\n");
return;
}
+
} else {
unsigned long long start;
@@ -558,6 +591,9 @@ static void __init reserve_crashkernel(void)
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
insert_resource(&iomem_resource, &crashk_res);
+
+ if (crash_base >= (1ULL<<32))
+ reserve_crashkernel_low();
}
#else
static void __init reserve_crashkernel(void)
@@ -608,8 +644,6 @@ static __init void reserve_ibft_region(void)
memblock_reserve(addr, size);
}
-static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
-
static bool __init snb_gfx_workaround_needed(void)
{
#ifdef CONFIG_PCI
@@ -698,8 +732,7 @@ static void __init trim_bios_range(void)
* since some BIOSes are known to corrupt low memory. See the
* Kconfig help text for X86_RESERVE_LOW.
*/
- e820_update_range(0, ALIGN(reserve_low, PAGE_SIZE),
- E820_RAM, E820_RESERVED);
+ e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
/*
* special case: Some BIOSen report the PC BIOS
@@ -711,6 +744,29 @@ static void __init trim_bios_range(void)
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
}
+/* called before trim_bios_range() to spare extra sanitize */
+static void __init e820_add_kernel_range(void)
+{
+ u64 start = __pa_symbol(_text);
+ u64 size = __pa_symbol(_end) - start;
+
+ /*
+ * Complain if .text .data and .bss are not marked as E820_RAM and
+ * attempt to fix it by adding the range. We may have a confused BIOS,
+ * or the user may have used memmap=exactmap or memmap=xxM$yyM to
+ * exclude kernel range. If we really are running on top non-RAM,
+ * we will crash later anyways.
+ */
+ if (e820_all_mapped(start, start + size, E820_RAM))
+ return;
+
+ pr_warn(".text .data .bss are not marked as E820_RAM!\n");
+ e820_remove_range(start, size, E820_RAM, 0);
+ e820_add_region(start, size, E820_RAM);
+}
+
+static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
+
static int __init parse_reservelow(char *p)
{
unsigned long long size;
@@ -733,6 +789,11 @@ static int __init parse_reservelow(char *p)
early_param("reservelow", parse_reservelow);
+static void __init trim_low_memory_range(void)
+{
+ memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE));
+}
+
/*
* Determine if we were loaded by an EFI loader. If so, then we have also been
* passed the efi memmap, systab, etc., so we should use these data structures
@@ -748,6 +809,17 @@ early_param("reservelow", parse_reservelow);
void __init setup_arch(char **cmdline_p)
{
+ memblock_reserve(__pa_symbol(_text),
+ (unsigned long)__bss_stop - (unsigned long)_text);
+
+ early_reserve_initrd();
+
+ /*
+ * At this point everything still needed from the boot loader
+ * or BIOS or kernel text should be early reserved or marked not
+ * RAM in e820. All other memory is free game.
+ */
+
#ifdef CONFIG_X86_32
memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
visws_early_detect();
@@ -835,12 +907,12 @@ void __init setup_arch(char **cmdline_p)
init_mm.end_data = (unsigned long) _edata;
init_mm.brk = _brk_end;
- code_resource.start = virt_to_phys(_text);
- code_resource.end = virt_to_phys(_etext)-1;
- data_resource.start = virt_to_phys(_etext);
- data_resource.end = virt_to_phys(_edata)-1;
- bss_resource.start = virt_to_phys(&__bss_start);
- bss_resource.end = virt_to_phys(&__bss_stop)-1;
+ code_resource.start = __pa_symbol(_text);
+ code_resource.end = __pa_symbol(_etext)-1;
+ data_resource.start = __pa_symbol(_etext);
+ data_resource.end = __pa_symbol(_edata)-1;
+ bss_resource.start = __pa_symbol(__bss_start);
+ bss_resource.end = __pa_symbol(__bss_stop)-1;
#ifdef CONFIG_CMDLINE_BOOL
#ifdef CONFIG_CMDLINE_OVERRIDE
@@ -906,6 +978,7 @@ void __init setup_arch(char **cmdline_p)
insert_resource(&iomem_resource, &data_resource);
insert_resource(&iomem_resource, &bss_resource);
+ e820_add_kernel_range();
trim_bios_range();
#ifdef CONFIG_X86_32
if (ppro_with_ram_bug()) {
@@ -955,6 +1028,8 @@ void __init setup_arch(char **cmdline_p)
reserve_ibft_region();
+ early_alloc_pgt_buf();
+
/*
* Need to conclude brk, before memblock_x86_fill()
* it could use memblock_find_in_range, could overlap with
@@ -964,7 +1039,7 @@ void __init setup_arch(char **cmdline_p)
cleanup_highmap();
- memblock.current_limit = get_max_mapped();
+ memblock.current_limit = ISA_END_ADDRESS;
memblock_x86_fill();
/*
@@ -981,41 +1056,31 @@ void __init setup_arch(char **cmdline_p)
setup_bios_corruption_check();
#endif
+ /*
+ * In the memory hotplug case, the kernel needs info from SRAT to
+ * determine which memory is hotpluggable before allocating memory
+ * using memblock.
+ */
+ acpi_boot_table_init();
+ early_acpi_boot_init();
+ early_parse_srat();
+
+#ifdef CONFIG_X86_32
printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n",
(max_pfn_mapped<<PAGE_SHIFT) - 1);
+#endif
- setup_real_mode();
+ reserve_real_mode();
trim_platform_memory_ranges();
+ trim_low_memory_range();
- init_gbpages();
+ init_mem_mapping();
- /* max_pfn_mapped is updated here */
- max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
- max_pfn_mapped = max_low_pfn_mapped;
+ early_trap_pf_init();
-#ifdef CONFIG_X86_64
- if (max_pfn > max_low_pfn) {
- int i;
- unsigned long start, end;
- unsigned long start_pfn, end_pfn;
-
- for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
- NULL) {
-
- end = PFN_PHYS(end_pfn);
- if (end <= (1UL<<32))
- continue;
-
- start = PFN_PHYS(start_pfn);
- max_pfn_mapped = init_memory_mapping(
- max((1UL<<32), start), end);
- }
+ setup_real_mode();
- /* can we preseve max_low_pfn ?*/
- max_low_pfn = max_pfn;
- }
-#endif
memblock.current_limit = get_max_mapped();
dma_contiguous_reserve(0);
@@ -1045,10 +1110,6 @@ void __init setup_arch(char **cmdline_p)
/*
* Parse the ACPI tables for possible boot-time SMP configuration.
*/
- acpi_boot_table_init();
-
- early_acpi_boot_init();
-
initmem_init();
memblock_find_dma_reserve();
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index d6bf1f34a6e9..69562992e457 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -278,7 +278,7 @@ static const struct {
};
static int
-__setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
+__setup_frame(int sig, struct ksignal *ksig, sigset_t *set,
struct pt_regs *regs)
{
struct sigframe __user *frame;
@@ -286,7 +286,7 @@ __setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
int err = 0;
void __user *fpstate = NULL;
- frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+ frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate);
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return -EFAULT;
@@ -307,8 +307,8 @@ __setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
restorer = VDSO32_SYMBOL(current->mm->context.vdso, sigreturn);
else
restorer = &frame->retcode;
- if (ka->sa.sa_flags & SA_RESTORER)
- restorer = ka->sa.sa_restorer;
+ if (ksig->ka.sa.sa_flags & SA_RESTORER)
+ restorer = ksig->ka.sa.sa_restorer;
/* Set up to return from userspace. */
err |= __put_user(restorer, &frame->pretcode);
@@ -327,7 +327,7 @@ __setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
/* Set up registers for signal handler */
regs->sp = (unsigned long)frame;
- regs->ip = (unsigned long)ka->sa.sa_handler;
+ regs->ip = (unsigned long)ksig->ka.sa.sa_handler;
regs->ax = (unsigned long)sig;
regs->dx = 0;
regs->cx = 0;
@@ -340,7 +340,7 @@ __setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
return 0;
}
-static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+static int __setup_rt_frame(int sig, struct ksignal *ksig,
sigset_t *set, struct pt_regs *regs)
{
struct rt_sigframe __user *frame;
@@ -348,7 +348,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
int err = 0;
void __user *fpstate = NULL;
- frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+ frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate);
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return -EFAULT;
@@ -368,8 +368,8 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
/* Set up to return from userspace. */
restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
- if (ka->sa.sa_flags & SA_RESTORER)
- restorer = ka->sa.sa_restorer;
+ if (ksig->ka.sa.sa_flags & SA_RESTORER)
+ restorer = ksig->ka.sa.sa_restorer;
put_user_ex(restorer, &frame->pretcode);
/*
@@ -382,7 +382,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode);
} put_user_catch(err);
- err |= copy_siginfo_to_user(&frame->info, info);
+ err |= copy_siginfo_to_user(&frame->info, &ksig->info);
err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
regs, set->sig[0]);
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
@@ -392,7 +392,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
/* Set up registers for signal handler */
regs->sp = (unsigned long)frame;
- regs->ip = (unsigned long)ka->sa.sa_handler;
+ regs->ip = (unsigned long)ksig->ka.sa.sa_handler;
regs->ax = (unsigned long)sig;
regs->dx = (unsigned long)&frame->info;
regs->cx = (unsigned long)&frame->uc;
@@ -405,20 +405,20 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
return 0;
}
#else /* !CONFIG_X86_32 */
-static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+static int __setup_rt_frame(int sig, struct ksignal *ksig,
sigset_t *set, struct pt_regs *regs)
{
struct rt_sigframe __user *frame;
void __user *fp = NULL;
int err = 0;
- frame = get_sigframe(ka, regs, sizeof(struct rt_sigframe), &fp);
+ frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp);
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return -EFAULT;
- if (ka->sa.sa_flags & SA_SIGINFO) {
- if (copy_siginfo_to_user(&frame->info, info))
+ if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
+ if (copy_siginfo_to_user(&frame->info, &ksig->info))
return -EFAULT;
}
@@ -434,8 +434,8 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
/* Set up to return from userspace. If provided, use a stub
already in userspace. */
/* x86-64 should always use SA_RESTORER. */
- if (ka->sa.sa_flags & SA_RESTORER) {
- put_user_ex(ka->sa.sa_restorer, &frame->pretcode);
+ if (ksig->ka.sa.sa_flags & SA_RESTORER) {
+ put_user_ex(ksig->ka.sa.sa_restorer, &frame->pretcode);
} else {
/* could use a vstub here */
err |= -EFAULT;
@@ -457,7 +457,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
next argument after the signal number on the stack. */
regs->si = (unsigned long)&frame->info;
regs->dx = (unsigned long)&frame->uc;
- regs->ip = (unsigned long) ka->sa.sa_handler;
+ regs->ip = (unsigned long) ksig->ka.sa.sa_handler;
regs->sp = (unsigned long)frame;
@@ -469,8 +469,8 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
}
#endif /* CONFIG_X86_32 */
-static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
- siginfo_t *info, compat_sigset_t *set,
+static int x32_setup_rt_frame(struct ksignal *ksig,
+ compat_sigset_t *set,
struct pt_regs *regs)
{
#ifdef CONFIG_X86_X32_ABI
@@ -479,13 +479,13 @@ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
int err = 0;
void __user *fpstate = NULL;
- frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+ frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate);
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return -EFAULT;
- if (ka->sa.sa_flags & SA_SIGINFO) {
- if (copy_siginfo_to_user32(&frame->info, info))
+ if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
+ if (copy_siginfo_to_user32(&frame->info, &ksig->info))
return -EFAULT;
}
@@ -499,8 +499,8 @@ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
put_user_ex(0, &frame->uc.uc__pad0);
- if (ka->sa.sa_flags & SA_RESTORER) {
- restorer = ka->sa.sa_restorer;
+ if (ksig->ka.sa.sa_flags & SA_RESTORER) {
+ restorer = ksig->ka.sa.sa_restorer;
} else {
/* could use a vstub here */
restorer = NULL;
@@ -518,10 +518,10 @@ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
/* Set up registers for signal handler */
regs->sp = (unsigned long) frame;
- regs->ip = (unsigned long) ka->sa.sa_handler;
+ regs->ip = (unsigned long) ksig->ka.sa.sa_handler;
/* We use the x32 calling convention here... */
- regs->di = sig;
+ regs->di = ksig->sig;
regs->si = (unsigned long) &frame->info;
regs->dx = (unsigned long) &frame->uc;
@@ -535,70 +535,13 @@ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
return 0;
}
-#ifdef CONFIG_X86_32
-/*
- * Atomically swap in the new signal mask, and wait for a signal.
- */
-asmlinkage int
-sys_sigsuspend(int history0, int history1, old_sigset_t mask)
-{
- sigset_t blocked;
- siginitset(&blocked, mask);
- return sigsuspend(&blocked);
-}
-
-asmlinkage int
-sys_sigaction(int sig, const struct old_sigaction __user *act,
- struct old_sigaction __user *oact)
-{
- struct k_sigaction new_ka, old_ka;
- int ret = 0;
-
- if (act) {
- old_sigset_t mask;
-
- if (!access_ok(VERIFY_READ, act, sizeof(*act)))
- return -EFAULT;
-
- get_user_try {
- get_user_ex(new_ka.sa.sa_handler, &act->sa_handler);
- get_user_ex(new_ka.sa.sa_flags, &act->sa_flags);
- get_user_ex(mask, &act->sa_mask);
- get_user_ex(new_ka.sa.sa_restorer, &act->sa_restorer);
- } get_user_catch(ret);
-
- if (ret)
- return -EFAULT;
- siginitset(&new_ka.sa.sa_mask, mask);
- }
-
- ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
-
- if (!ret && oact) {
- if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)))
- return -EFAULT;
-
- put_user_try {
- put_user_ex(old_ka.sa.sa_handler, &oact->sa_handler);
- put_user_ex(old_ka.sa.sa_flags, &oact->sa_flags);
- put_user_ex(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
- put_user_ex(old_ka.sa.sa_restorer, &oact->sa_restorer);
- } put_user_catch(ret);
-
- if (ret)
- return -EFAULT;
- }
-
- return ret;
-}
-#endif /* CONFIG_X86_32 */
-
/*
* Do a signal return; undo the signal stack.
*/
#ifdef CONFIG_X86_32
-unsigned long sys_sigreturn(struct pt_regs *regs)
+unsigned long sys_sigreturn(void)
{
+ struct pt_regs *regs = current_pt_regs();
struct sigframe __user *frame;
unsigned long ax;
sigset_t set;
@@ -625,8 +568,9 @@ badframe:
}
#endif /* CONFIG_X86_32 */
-long sys_rt_sigreturn(struct pt_regs *regs)
+long sys_rt_sigreturn(void)
{
+ struct pt_regs *regs = current_pt_regs();
struct rt_sigframe __user *frame;
unsigned long ax;
sigset_t set;
@@ -667,30 +611,29 @@ static int signr_convert(int sig)
}
static int
-setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
- struct pt_regs *regs)
+setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
{
- int usig = signr_convert(sig);
+ int usig = signr_convert(ksig->sig);
sigset_t *set = sigmask_to_save();
compat_sigset_t *cset = (compat_sigset_t *) set;
/* Set up the stack frame */
if (is_ia32_frame()) {
- if (ka->sa.sa_flags & SA_SIGINFO)
- return ia32_setup_rt_frame(usig, ka, info, cset, regs);
+ if (ksig->ka.sa.sa_flags & SA_SIGINFO)
+ return ia32_setup_rt_frame(usig, ksig, cset, regs);
else
- return ia32_setup_frame(usig, ka, cset, regs);
+ return ia32_setup_frame(usig, ksig, cset, regs);
} else if (is_x32_frame()) {
- return x32_setup_rt_frame(usig, ka, info, cset, regs);
+ return x32_setup_rt_frame(ksig, cset, regs);
} else {
- return __setup_rt_frame(sig, ka, info, set, regs);
+ return __setup_rt_frame(ksig->sig, ksig, set, regs);
}
}
static void
-handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
- struct pt_regs *regs)
+handle_signal(struct ksignal *ksig, struct pt_regs *regs)
{
+ bool failed;
/* Are we from a system call? */
if (syscall_get_nr(current, regs) >= 0) {
/* If so, check system call restarting.. */
@@ -701,7 +644,7 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
break;
case -ERESTARTSYS:
- if (!(ka->sa.sa_flags & SA_RESTART)) {
+ if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
regs->ax = -EINTR;
break;
}
@@ -721,26 +664,21 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
likely(test_and_clear_thread_flag(TIF_FORCED_TF)))
regs->flags &= ~X86_EFLAGS_TF;
- if (setup_rt_frame(sig, ka, info, regs) < 0) {
- force_sigsegv(sig, current);
- return;
+ failed = (setup_rt_frame(ksig, regs) < 0);
+ if (!failed) {
+ /*
+ * Clear the direction flag as per the ABI for function entry.
+ */
+ regs->flags &= ~X86_EFLAGS_DF;
+ /*
+ * Clear TF when entering the signal handler, but
+ * notify any tracer that was single-stepping it.
+ * The tracer may want to single-step inside the
+ * handler too.
+ */
+ regs->flags &= ~X86_EFLAGS_TF;
}
-
- /*
- * Clear the direction flag as per the ABI for function entry.
- */
- regs->flags &= ~X86_EFLAGS_DF;
-
- /*
- * Clear TF when entering the signal handler, but
- * notify any tracer that was single-stepping it.
- * The tracer may want to single-step inside the
- * handler too.
- */
- regs->flags &= ~X86_EFLAGS_TF;
-
- signal_delivered(sig, info, ka, regs,
- test_thread_flag(TIF_SINGLESTEP));
+ signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP));
}
#ifdef CONFIG_X86_32
@@ -757,14 +695,11 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
*/
static void do_signal(struct pt_regs *regs)
{
- struct k_sigaction ka;
- siginfo_t info;
- int signr;
+ struct ksignal ksig;
- signr = get_signal_to_deliver(&info, &ka, regs, NULL);
- if (signr > 0) {
+ if (get_signal(&ksig)) {
/* Whee! Actually deliver the signal. */
- handle_signal(signr, &info, &ka, regs);
+ handle_signal(&ksig, regs);
return;
}
@@ -843,8 +778,9 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
}
#ifdef CONFIG_X86_X32_ABI
-asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs)
+asmlinkage long sys32_x32_rt_sigreturn(void)
{
+ struct pt_regs *regs = current_pt_regs();
struct rt_sigframe_x32 __user *frame;
sigset_t set;
unsigned long ax;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ecffca11f4e9..68bda7a84159 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -688,10 +688,19 @@ void __init early_trap_init(void)
set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
/* int3 can be called from all */
set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
+#ifdef CONFIG_X86_32
set_intr_gate(X86_TRAP_PF, &page_fault);
+#endif
load_idt(&idt_descr);
}
+void __init early_trap_pf_init(void)
+{
+#ifdef CONFIG_X86_64
+ set_intr_gate(X86_TRAP_PF, &page_fault);
+#endif
+}
+
void __init trap_init(void)
{
int i;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 1dfe69cc78a8..1cf5766dde16 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -202,7 +202,7 @@ out:
static int do_vm86_irq_handling(int subfunction, int irqnumber);
static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk);
-int sys_vm86old(struct vm86_struct __user *v86, struct pt_regs *regs)
+int sys_vm86old(struct vm86_struct __user *v86)
{
struct kernel_vm86_struct info; /* declare this _on top_,
* this avoids wasting of stack space.
@@ -222,7 +222,7 @@ int sys_vm86old(struct vm86_struct __user *v86, struct pt_regs *regs)
if (tmp)
goto out;
memset(&info.vm86plus, 0, (int)&info.regs32 - (int)&info.vm86plus);
- info.regs32 = regs;
+ info.regs32 = current_pt_regs();
tsk->thread.vm86_info = v86;
do_sys_vm86(&info, tsk);
ret = 0; /* we never return here */
@@ -231,7 +231,7 @@ out:
}
-int sys_vm86(unsigned long cmd, unsigned long arg, struct pt_regs *regs)
+int sys_vm86(unsigned long cmd, unsigned long arg)
{
struct kernel_vm86_struct info; /* declare this _on top_,
* this avoids wasting of stack space.
@@ -272,7 +272,7 @@ int sys_vm86(unsigned long cmd, unsigned long arg, struct pt_regs *regs)
ret = -EFAULT;
if (tmp)
goto out;
- info.regs32 = regs;
+ info.regs32 = current_pt_regs();
info.vm86plus.is_vm86pus = 1;
tsk->thread.vm86_info = (struct vm86_struct __user *)v86;
do_sys_vm86(&info, tsk);
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 1330dd102950..b014d9414d08 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -59,6 +59,9 @@ EXPORT_SYMBOL(memcpy);
EXPORT_SYMBOL(__memcpy);
EXPORT_SYMBOL(memmove);
+#ifndef CONFIG_DEBUG_VIRTUAL
+EXPORT_SYMBOL(phys_base);
+#endif
EXPORT_SYMBOL(empty_zero_page);
#ifndef CONFIG_PARAVIRT
EXPORT_SYMBOL(native_load_gs_index);
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index d065d67c2672..45a14dbbddaf 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -63,10 +63,6 @@ struct x86_init_ops x86_init __initdata = {
.banner = default_banner,
},
- .mapping = {
- .pagetable_reserve = native_pagetable_reserve,
- },
-
.paging = {
.pagetable_init = native_pagetable_init,
},